DETAILED ACTION
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 .
Receipt of Applicant’s Amendment filed January 26, 2026, is acknowledged.
Response to Amendment
Claims 1-5, 8, and 9 have been amended. Claims 6, 7, and 10-20 have been canceled. Claims 21-33 are new. Claims 1-5, 8, 9, and 21-33 are pending and are provided to be examined upon their merits.
Response to Arguments
Applicant’s arguments with respect to claims 1-5, 8, 9, and 21-33 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. A response is provided below in bold where appropriate.
Applicant argues 35 USC §101 Rejection, starting pg. 9 of Remarks:
I. Rejection of Claims 1-20 under 35 U.S.C. § 101
Claims 1-20 stand rejected under 35 U.S.C. § 101 because the claimed invention is allegedly directed to an abstract idea without significantly more. Assignee's representative respectfully traverses as follows.
Claim 1 recites:
A system, comprising:
at least one processor; and
at least one memory coupled to the at least one processor and having instructions stored thereon, wherein, in response to the at least one processor executing the instructions, the instructions facilitate performance of operations, comprising:
receiving, from one or more healthcare information sources, a plurality of patient reports associated with a patient;
generating, for each patient report of the plurality of patient reports, a report summary of the patient report using a large language model, resulting in a plurality of report summaries, wherein each report summary comprises a textual summary of content of a corresponding patient report;
storing, the patient reports and the report summaries in the at least one memory or another memory accessible to the at least one processor;
receiving input identifying a summary type for a consolidated report for the patient, the summary type being selected from the group consisting of: a first summary of all the patient reports, a second summary of patient information occurring within a defined time interval, and a third summary comprising a comparison between two patient reports;
based on the receiving, generating the consolidated report from two or more of the report summaries using the large language model in association with applying a prompt to the large language model indicating the summary type; and
presenting the consolidated report for review.
Claim 1 is not directed to an abstract idea but instead recites a specific computer- implemented architecture that improves the way computerized systems generate, structure, and present patient-report information in an electronic environment. In particular, claim 1 requires receiving a plurality of patient reports, generating and storing a plurality of report summaries for the respective patient reports using a large language model, receiving an input that selects a particular summary type, and then generating a consolidated report from two or more of the stored report summaries using the large language model in association with applying a prompt that indicates the selected summary type, followed by presenting the consolidated report for review. This is not merely "summarizing information" in the abstract; it is a defined, multi-stage processing pipeline that creates and persists intermediate machine-generated artifacts (the report summaries) and then uses a controlled prompt corresponding to a selected summary type to drive a second-stage generation of a consolidated report from those intermediate artifacts. This claimed configuration addresses a problem that is rooted in computerized information environments, namely, that patient data exists as large volumes of heterogeneous electronic reports that are costly to repeatedly parse and difficult to navigate efficiently, and provides a concrete technical solution by restructuring the processing flow and reuse of derived representations within the computer system.
Respectfully, summarizing patient reports and provide a consolidated report is managing interactions between people by providing a person with information about a patient. Providing information is teaching. Specific steps to do this would be following rules or instructions. Also, a person with pen and paper can summarize and consolidate reports.
The USPTO's December 5, 2025 memorandum titled "Advance notice of change to the MPEP in light of Ex Parte Desjardins" emphasizes that eligibility analysis should consider whether the claims are directed to an improvement in the functioning of a computer or an improvement to another technology or technical field, consistent with longstanding precedent such as Enfish and McRO, and that this is particularly important for machine learning and artificial intelligence related claims. The memorandum further explains that examiners should evaluate the specification to determine whether an improvement would be apparent to one of ordinary skill in the art, and then evaluate the claim "as a whole" to ensure the claim reflects the disclosed improvement, while avoiding oversimplifying the claim at a high level of generality that dismisses meaningful technical limitations. Applying that guidance here, the claimed ordered combination reflects a technological improvement in computer-based processing of electronic patient reports by requiring a staged architecture that generates intermediate report summaries, stores those summaries for reuse, and then generates consolidated reports of different types by applying prompts that control the model's operation as a function of the selected summary type, rather than repeatedly reprocessing the original reports or producing a single undifferentiated summary output.
Respectfully, there is no improvement in computer technology itself. Using computers to perform a judicial exception is not improving computers.
Claim 1 is also consistent with the type of computer-centric solution found eligible in DDR Holdings, which recognized eligibility where claims recited a particular way of achieving a desired outcome by changing how a computer-based system operates to address a problem rooted in computer technology, rather than merely implementing an abstract idea on a computer. In the same way, claim 1 recites a particular, non-conventional solution in the AI/LLM setting: a defined, two-stage generation flow from raw reports to stored report summaries to a prompt- controlled consolidated report, with user-selected summary types constraining the system's generation behavior. Under Step 2A, Prong Two, the claim therefore integrates any alleged judicial exception into a practical application by reciting a specific technical architecture that improves computer-based processing and presentation of voluminous, heterogeneous electronic reports.
DDR solved a problem rooted in use of computer technology. A person with pen and paper can create report summaries and consolidate the reports.
Even if the Examiner were to maintain that claim 1 recites a judicial exception at Step 2A, Prong One, claim 1 nonetheless recites significantly more under Step 2B because its ordered combination is not a mere instruction to "apply" an abstract idea using generic computer components. The December 5, 2025 Desjardins memorandum reiterates that examiners should not dismiss additional elements as generic when, evaluated as an ordered combination, those elements confer a technological improvement to a technical problem, and it specifically links this analysis to DDR and the "improvement" consideration in MPEP § 2106.05(a). Here, the claim's multi-stage, prompt-controlled LLM workflow and its storage and reuse of intermediate report summaries impose meaningful technical limits on how the system operates, thereby providing significantly more than any alleged abstract idea. Accordingly, withdrawal of the § 101 rejection of claim 1 and those claims which depend therefrom is respectfully requested.
Respectfully, even the claims recite “using” large language model (LLM). This is just not a technical improvement. The rejection is respectfully modified for the claim amendments but maintained.
Applicant argues 35 USC §102 Rejection, pg. 12 of Remarks:
II. Rejection of Claims 11 and 12 under 35 U.S.C. § 102(a)(1)
Claims 11 and 12 stand rejected under 35 U.S.C. § 102(a)(1) as allegedly being anticipated by Amarasingham et al. (U.S. Patent Publication No. 2023/0104655, hereinafter "Amarasingham"). Claims 11 and 12 have been canceled, rendering the rejection thereof moot.
Noted and withdrawn as canceled.
Applicant argues 35 USC §103 Rejection, pg. 12 of Remarks:
III. Rejection of Claim 13, 17, 18, and 20 under 35 U.S.C. § 103
Claim 13, 17, 18, and 20 stands rejected under 35 U.S.C. § 103 as allegedly being unpatentable over Amarasingham. Claims 13, 17, 18, and 20 have been canceled, rendering the rejection thereof moot.
Noted and withdrawn as canceled.
Applicant argues 35 USC §103 Rejection, pg. 12 of Remarks:
IV. Rejection of Claims 1-6, 8, 9, 14-16 and 19 under 35 U.S.C. § 103
Applicant has amended their claims requiring new prior art, therefore, the arguments are moot.
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 1-5, 8, 9, and 21-33 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claims 1-5, 8, 9, and 21-33 are directed to a system, method, or product which are statutory categories of invention. (Step 1: YES).
The Examiner has identified method Claim 26 as the claim that represents the claimed invention for analysis and is similar to system Claim 1 and product Claim 32.
Claim 26 recites the limitations of:
A computer-implemented method, comprising:
receiving, from one or more healthcare information sources by a system comprising at least one processor, a plurality of patient reports associated with a patient;
for each patient report of the plurality of patient reports, generating, by the system, a report summary of the patient report using a large language model, resulting in a plurality of report summaries, wherein each report summary comprises a textual summary of content of a corresponding patient report;
storing, by the system, the patient reports and the report summaries in at least one memory accessible to the at least one processor;
receiving, by the system, input identifying a summary type for a consolidated report for the patient, the summary type being selected from the group consisting of: a first summary of all the patient reports, a second summary of patient information occurring within a defined time interval, and a third summary comprising a comparison between two patient reports;
based on the receiving, generating, by the system, the consolidated report from two or more of the report summaries using the large language model in association with applying a prompt to the large language model indicating the summary type; and
presenting, by the system, the consolidated report for review.
These above limitations, under their broadest reasonable interpretation, cover performance of the limitation as certain methods of organizing human activity. The claim recites elements, highlighted in bold above, which covers performance of the limitation as managing personal behavior and interactions or relations between people. Receiving patient reports, generating a report summary of the patient report, receiving input identifying a summary type for a consolidated report for the patient, generating a consolidated report from two or more report summaries and presenting the consolidated report is following rules and instructions and teaching. See also MPEP 2106.04(a)(2) II where it is not the number of people involved in an activity, rather the activity itself. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation as a managing personal behavior or interactions between peoples, then it falls within the “Certain Methods of Organizing Human Activity” grouping of abstract ideas. Accordingly, the claim recites an abstract idea. Claims 1 and 32 are also abstract for similar reasons. (Step 2A-Prong 1: YES. The claims are abstract)
In as much as the claim is creating first and second summary reports, generating a consolidated report, and presenting the consolidated summary, the claims are also abstract as a mental process as a person with pen and paper can create a report summary and consolidate the reports and present the consolidated summary. Further, using a computer to perform a mental process has been shown to be abstract (see MPEP 2106.04(a)(2) III C).
This judicial exception is not integrated into a practical application. In particular, the claims only recite: processor, memory (Claim 1); computer, processor (Claim 26); non-transitory computer readable medium, machine (Claim 32). The computer hardware is recited at a high-level of generality (i.e., as a generic processor performing a generic computer function) such that it amounts no more than mere instructions to apply the exception using a generic computer component. The machine is a generic machine and could be just about anything. The large language model is a generic model, being used and applied at a high level of generality. Accordingly, these additional elements, when considered separately and as an ordered combination, do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Therefore claims 1, 26, and 32 are directed to an abstract idea without a practical application. (Step 2A-Prong 2: NO. The additional claimed elements are not integrated into a practical application)
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because, when considered separately and as an ordered combination, they do not add significantly more (also known as an “inventive concept”) to the exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a computer hardware amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. Accordingly, these additional elements, when considered separately and as an ordered combination, do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Steps such as presenting are steps that are considered insignificant extra solution activity and mere instructions to apply the exception using general computer components (see MPEP 2106.05(d), II). Thus claims 1, 26, and 32 are not patent eligible. (Step 2B: NO. The claims do not provide significantly more)
Dependent claims 2-5, 8, 9, 21-25, 27-31, and 33 further define the abstract idea that is present in their respective independent claims 1, 26, and 32 and thus correspond to Certain Methods of Organizing Human Activity and Mental Processes and hence are abstract for the reasons presented above. The dependent claims do not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception when considered both individually and as an ordered combination. Claim 3 recites machine, which is a generic machine applied at a high level of generality. Claims 9 and 20 recite language model at a high level of generality. Claims 12-14, and 16 recite device, which is a generic device (processor) applied at a high level of generality. Claims 8, 21-23, 27-29, and 33 recite hyperlink which is computer software recited at a high level of generality. Claims 9, 24, 30 recite vector similarity or representation as a high level of generality. Claims 9, 24, 25, 30, 31 recite large language model at a high level of generality. Therefore, the claims 2-5, 8, 9, 21-25, 27-31, and 33 are directed to an abstract idea. Thus, the claims 1-5, 8, 9, and 21-33 are not patent-eligible.
Examiner Request
The Applicant is requested to indicate where in the specification there is support for amendments to claims should Applicant amend. The purpose of this is to reduce potential 35 U.S.C. §112(a) or §112 1st paragraph issues that can arise when claims are amended without support in the specification. The Examiner thanks the Applicant in advance.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-5, 8, 25, 26, 31, and 32 are rejected under 35 U.S.C. 103 as being unpatentable over Pub. No. US 2024/0281487 to Bathwal et al. in view of Pub. No. US 2025/0061290 to Gardner et al. and in view of Pub. No. US 2025/0094473 to Wilezynski.
Regarding claims 1, 26, and 32
A system, comprising:
at least one processor; and
Bathwal et al. teaches:
Processors…
“As utilized herein, circuits, controllers, computing devices, components, modules, or other similar aspects set forth herein should be understood broadly. Such terminology is utilized to highlight that the related hardware devices may be configured in a number of arrangements, and include any hardware configured to perform the operations herein. Any such devices may be a single device, a distributed device, and/or implemented as any hardware configuration to perform the described operations. In certain embodiments, hardware devices may include computing devices of any type, logic circuits, input/output devices, processors, sensors, actuators, web-based servers, LAN servers, WLAN servers, cloud computing devices, memory storage of any type, and/or aspects embodied as instructions stored on a computer readable medium and configured to cause a processor to perform recited operations. Communication between devices, whether inter-communication (e.g., a user device 104 communicating with controller 102) or intra-device communication (e.g., one circuit or component of the controller 102 communicating with another circuit or component of the controller 102) may be performed in any manner, for example using internet-based communication, LAN/WLAN communication, direct networking communication, Wi-Fi communication, or the like.” [0034]
at least one memory coupled to the at least one processor and having instructions stored thereon, wherein, in response to the at least one processor executing the instructions, the instructions facilitate performance of operations, comprising:
Computer (processor coupled to memory) and memory for instructions to cause processor to perform operations….
“As utilized herein, circuits, controllers, computing devices, components, modules, or other similar aspects set forth herein should be understood broadly. Such terminology is utilized to highlight that the related hardware devices may be configured in a number of arrangements, and include any hardware configured to perform the operations herein. Any such devices may be a single device, a distributed device, and/or implemented as any hardware configuration to perform the described operations. In certain embodiments, hardware devices may include computing devices of any type, logic circuits, input/output devices, processors, sensors, actuators, web-based servers, LAN servers, WLAN servers, cloud computing devices, memory storage of any type, and/or aspects embodied as instructions stored on a computer readable medium and configured to cause a processor to perform recited operations. Communication between devices, whether inter-communication (e.g., a user device 104 communicating with controller 102) or intra-device communication (e.g., one circuit or component of the controller 102 communicating with another circuit or component of the controller 102) may be performed in any manner, for example using internet-based communication, LAN/WLAN communication, direct networking communication, Wi-Fi communication, or the like.” [0034]
receiving, from one or more healthcare information sources, a plurality of patient reports associated with a patient;
Retrieving multiple documents (reports)…
“Examples of the multi-document summarization system can include receiving a user query as input at a web browser and retrieving multiple search results (e.g., documents) in response to the query. The system summarizes each result (e.g., document) using one or more per-document summarization models and then further synthesizes the per-document summaries into a single coherent answer (e.g., output) to the user's query. The finalized coherent answer includes cited sources for each summarized document. Examples of the enhanced summarization system include a multi-step process of per-document summarization, cross-document summarization, and answer synthesis employing specific model architectures used for abstractive summarization to format final query answers with citations.” [0031]
Source (receiving) that includes reports…
“According to examples, determination of potential machine generated content, and how it may be utilized or not, may be combined with other determinations, for example, the machine generated content may be utilized where it is expected that the content may be machine generated initially (e.g., reports, listings, data sets, etc.) and/or where the source is otherwise of a high quality (e.g., provided by a university or expert in the field of the query) and would be expected to be correct. In examples, responses of users over time to certain machine generated content elements may be utilized to determine whether the machine generated content should be used or not, for example based on responses of users to searches including the content. The detection, flagging, and/or management of machine generated content can avoid recursive information loops, where the machine generated content is not a primary source of information but effectively gets used as such, while still allowing the use of the content where it would be helpful to specific users for specific purposes.” [0070]
Summarization for medical field…
“Other example summarization techniques include query-based summarization 418, which tailors the summary to answer a specific query or set of queries. It focuses on extracting or generating information from the document that is most relevant to the user's search intent. Thematic summarization 420 technique identifies the central themes or topics within a document and creates a summary that covers these key themes, providing a broad overview of the content's subject matter. Opinion summarization 422 technique is often used for reviews and feedback, opinion summarization aggregates and presents the sentiments or viewpoints expressed in the text, giving readers a summary of the overall opinions. Domain-specific summarization 424 technique can be tailored to specific fields such as legal, medical, or scientific texts. Domain-specific summarization incorporates specialized knowledge to create summaries that are meaningful within the context of the field. Narrative summarization 426 technique focuses on summarizing stories or events by identifying and presenting the narrative elements, such as the plot, characters, and setting, in a condensed form. Multimedia summarization 428 technique is applicable to content like videos, images, and audio. Multimedia summarization involves creating a condensed version of the media, such as a highlight reel or a visual abstract, which captures the main points or moments.” [0077]
See Patient below.
generating, for each patient report of the plurality of patient reports, a report summary of the patient report using a large language model, resulting in a plurality of report summaries, wherein each report summary comprises a textual summary of content of a corresponding patient report;
Summarizes each document (report)…
“Examples of the multi-document summarization system can include receiving a user query as input at a web browser and retrieving multiple search results (e.g., documents) in response to the query. The system summarizes each result (e.g., document) using one or more per-document summarization models and then further synthesizes the per-document summaries into a single coherent answer (e.g., output) to the user's query. The finalized coherent answer includes cited sources for each summarized document. Examples of the enhanced summarization system include a multi-step process of per-document summarization, cross-document summarization, and answer synthesis employing specific model architectures used for abstractive summarization to format final query answers with citations.” [0031]
Document (report) summarization using LLM models…
“The multi-turn disambiguation personalization layer 222 retrieves documents from LLM ranking and retrieval models 212 that are associated with the input 236 query based on ranking and filtering of relevant documents. Each of the selected relevant individual documents is provided to a per-document summaries layer 224 to be processed according to a first phase of summarization.” [0055]
See Patient below.
storing the patient reports and the report summaries in the at least one memory or another memory accessible to the at least one processor;
Data stores…
“FIG. 1 is an example high-level system architecture illustrating an example of a multi-document summarization system 100 including a controller 102 embodying circuits, controllers, computing devices, data stores, communication infrastructure (e.g., network connections, protocols, etc.), or the like that implement operations described herein, in accordance with some embodiments of the present disclosure.” [0033]
See Patient below.
receiving input identifying a summary type for a consolidated report for the patient, the summary type being selected from the group consisting of: a first summary of all the patient reports, a second summary of patient information occurring within a defined time interval, and a third summary comprising a comparison between two patient reports;
Summarization process of per-document summaries (summary of all reports)…
“Once the per-document summaries layer 224 has completed analysis and summarization of each individual document, the per-document summaries are provided to a cited multi-documents layer 226. A pivotal feature of this summarization approach is its attribution mechanism, wherein the cited multi-documents layer 226 enables each segment of the compiled summary to be meticulously traced back to its original source, providing clear citations or hyperlinks for reference. The summarization process is meticulously designed to prioritize relevance, selectively incorporating information that is most germane to the topic at hand, while simultaneously employing algorithms to eliminate redundancy. This ensures that the final summary presents a comprehensive and non-repetitive overview of the subject matter, derived from an extensive corpus of documents that is timely and relevant to the user's query. Once the dual-process (e.g., two phases) summarization techniques are complete, the output 238 is returned to the user via a frontend web interface.” [0056]
See Patient below.
based on the receiving, generating the consolidated report from two or more of the report summaries using the large language model in association with applying a prompt to the large language model indicating the summary type.
Further synthesizes the per-document (report) summaries into a single answer (consolidated report)…
“Examples of the multi-document summarization system can include receiving a user query as input at a web browser and retrieving multiple search results (e.g., documents) in response to the query. The system summarizes each result (e.g., document) using one or more per-document summarization models and then further synthesizes the per-document summaries into a single coherent answer (e.g., output) to the user's query. The finalized coherent answer includes cited sources for each summarized document. Examples of the enhanced summarization system include a multi-step process of per-document summarization, cross-document summarization, and answer synthesis employing specific model architectures used for abstractive summarization to format final query answers with citations.” [0031]
Generative artificial intelligence (GAI) prompt to generate new content (consolidated report) abased on input …
“The GAI model 912 can be used to generate new content based on the GAI prompt 910 used as input, and the GAI model 912 creates a newly generated item 916 as output.” [0169]
See Prompt with Type below.
presenting the consolidated report for review.
Creates output…
“The GAI model 912 can be used to generate new content based on the GAI prompt 910 used as input, and the GAI model 912 creates a newly generated item 916 as output.” [0169]
Fig. 3, ref. 308 also teaches output…
PNG
media_image1.png
270
658
media_image1.png
Greyscale
Patient
Bathwal et al. teaches summarization for medical purposes. They do not specifically teach patient report and medical records.
Gardner et al. teaches also in the business of summarization for medical purposes teaches:
Medical records with patient reports…
“A medical records system invoking the summarization to pull out critical information from patient reports into standardized, condensed formats for physician review;…” [ 0249]
Distilling (generating) medical records into condensed summaries…
“Distilling medical records into condensed summaries for physician review;” [363]
Summary of content using LLM and prompts to summarize its own prior outputs (summary of summary)…
“The present disclosure provides specific technological solutions to these problems through one or more described features or combinations of features. The disclosed system enables users to precisely define a target level of abstraction (e.g., by specifying a percentage of length reduction) for a representation of a summary of a content item. For example, the system gives granular control over depth and brevity. The system may also be configured to engineer iterative prompts to have the LLM summarize its own prior outputs at increasing levels of abstraction. This allows for gradual refinement while preserving substantive information.” [0015]
Retain (store) summary information…
“Providing explicit instructions in the prompts generated for the LLM to retain specific highlighted information in the summary, overriding the abstraction process;” [0228]
Summarize by patient…
“A doctor can summarize lengthy patient medical histories into condensed overviews for reference on their phone when visiting patients. Negative zoom can expand details by inferring missing diagnosis dates based on medication timelines and incorporating relevant external data like clinical trial results. This provides richer context.
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of Bathwal et al. the ability to summarize medical records of patients as taught by Gardner et al. 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, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Bathwal et al. who teaches there system can be used for medical purposes, it would be obvious this could be used for medical records of patients.
Prompt with Type
The combined references teach large language model and prompt. They do not teach type.
Wilezynski also in the business of large language model and prompt teaches:
Higher level text summaries with shorter, specific subjects (type)…
“According to certain embodiments, the one or more generated text summaries are utilized as subsequent input to the computing model (e.g., the language model) to generate additional higher level text summaries (e.g., shorter in size, specific in subjects, etc.). In some embodiments, the one or more generated text summaries are utilized recursively as subsequent input to the computing model to generate additional higher level text summaries. In some examples, the recursive process includes inputting the previously generated text summary in combination with one or more event logs containing unstructured data and/or structured data. In certain examples, generating recursive text summaries (e.g., daily, weekly, monthly, etc.) provides the benefit of creating text summaries including different windows aggregated for different information consumers. In some examples, this allows information consumers to consume more aggregated text summaries while still retaining the ability to highlight and analyze particular topics of interest at a granular level by retaining the underlying event logs with the text summaries.” [0028]
Example of user input for type based on period of time, etc. with prompt of “summarize important topics…”…
“In some examples, a user provides as input to the computing model (e.g., the language model) work chat messages windowed to a period of time (e.g., one month) including a number of messages (e.g., over 200 messages about 4000 words). In some examples, each chat message corresponds to an event log of unstructured data with an event time of when the message was transmitted. In certain examples, the user includes a natural language prompt such as “summarize important topics, discussions, and decisions from the team over the past month” in addition to the event logs. In some examples, the computing model (e.g., the language model) generates a text summary of the chat messages in a number of words (e.g., around 100 words), for example, discussions of replacing and improving certain aspects of a project, a decision for a new branding option, and open questions still remaining to be answered, and/or other similar items. In some examples, the resulting text summary has a semantic compression ratio (e.g., 30 times) from the words in the event logs. In certain examples, the resulting text summary has a significant temporal compression ratio from the time duration of the event logs, for example, almost 40,000 times temporal compression ratio such that one month of team communications can be consumed by an information consumer in about a single minute. In some examples, this is a significant improvement over the established summarization method in terms of substantive content quality as well as a reduction in labor costs to produce an equivalent text summary.” [0030]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to use prompt with type as taught as taught by Wilezynski 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, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by the combined references who teach systems can be used for medical purposes, it would be obvious this could be used for medical records of patients.
Regarding claim 2
The system of claim 1, wherein the operations further comprise:
detecting a selection from the consolidated report;
Bathwal et al. teaches:
Example of Fig. 3 (consolidated report) and select…
“An example embodiment provides the single answer as a generative answer, or an abstractive answer. Additional example embodiments provide more than one single answer, by providing a component for generated follow-up queries 328. For example, according to multiple intents that may be determined from the search query, user information, user context, or other user summarization settings 330, such as setting from the user information processing component 132 components. An example embodiment adjusts the single answer in real time or near real time, for example based on a user adjusting a preference, responding to a clarifying question from the interface, or the like. In certain embodiments, the user can select source types, source trust values (e.g., including quantitative values, such as a trust index value on a slider bar, and/or qualitative values such as categories of sources to include or exclude), or the like, where the single answer may be updated, for example, by refreshing the answer and/or modifying the answer in real time. An example embodiment allows the user to select various user information and/or preferences, such as, for example and not limitation, an answer format, source types to include or exclude, trust levels of sources to be utilized, treatment of machine generated content versus user generated content, document types (e.g., white papers, journal articles, news articles, opinion articles, peer reviewed sources, etc.), formality of the answer (e.g., reading level of the answer, utilization of formatting techniques, utilization of complete sentences, etc.), and/or certainty ratings for the answer (e.g., level of speculative content allowed, correlation or agreement with other sources on factual information).” [0066] Inherent with select is detecting the selection.
determining patient medical data included in at least one of the patient reports corresponding to the selection; and
Determine document types…
“An example embodiment provides the single answer as a generative answer, or an abstractive answer. Additional example embodiments provide more than one single answer, by providing a component for generated follow-up queries 328. For example, according to multiple intents that may be determined from the search query, user information, user context, or other user summarization settings 330, such as setting from the user information processing component 132 components. An example embodiment adjusts the single answer in real time or near real time, for example based on a user adjusting a preference, responding to a clarifying question from the interface, or the like. In certain embodiments, the user can select source types, source trust values (e.g., including quantitative values, such as a trust index value on a slider bar, and/or qualitative values such as categories of sources to include or exclude), or the like, where the single answer may be updated, for example, by refreshing the answer and/or modifying the answer in real time. An example embodiment allows the user to select various user information and/or preferences, such as, for example and not limitation, an answer format, source types to include or exclude, trust levels of sources to be utilized, treatment of machine generated content versus user generated content, document types (e.g., white papers, journal articles, news articles, opinion articles, peer reviewed sources, etc.), formality of the answer (e.g., reading level of the answer, utilization of formatting techniques, utilization of complete sentences, etc.), and/or certainty ratings for the answer (e.g., level of speculative content allowed, correlation or agreement with other sources on factual information).” [0066]
presenting the patient medical data pertaining to the selection.
Provide user information….
“In example embodiments, various user information and/or preferences may be adjusted in real time or near real time, provided in advance, and/or may be provided according to context (e.g., time-of-day, search terms used, etc.). Various user information and/or preferences may be utilized to update search results and/or the single answer in real time. User information and/or preference adjustments may be made, for example and not limitation, by entering keywords, selecting radio buttons, using a slider bar, or the like.” [0067]
Patient
The combined references teach summarization for medical purposes. They do not specifically teach patient report and medical records and data.
Gardner et al. teaches also in the business of summarization for medical purposes teaches:
Medical records with patient reports…
“A medical records system invoking the summarization to pull out critical information from patient reports into standardized, condensed formats for physician review;…” [ 0249]
Distilling (generating) medical records into condensed summaries…
“Distilling medical records into condensed summaries for physician review;” [363]
Summary of content using LLM and prompts to summarize its own prior outputs (summary of summary)…
“The present disclosure provides specific technological solutions to these problems through one or more described features or combinations of features. The disclosed system enables users to precisely define a target level of abstraction (e.g., by specifying a percentage of length reduction) for a representation of a summary of a content item. For example, the system gives granular control over depth and brevity. The system may also be configured to engineer iterative prompts to have the LLM summarize its own prior outputs at increasing levels of abstraction. This allows for gradual refinement while preserving substantive information.” [0015]
Retain (store) summary information…
“Providing explicit instructions in the prompts generated for the LLM to retain specific highlighted information in the summary, overriding the abstraction process;” [0228]
Summarize by patient…
“A doctor can summarize lengthy patient medical histories into condensed overviews for reference on their phone when visiting patients. Negative zoom can expand details by inferring missing diagnosis dates based on medication timelines and incorporating relevant external data like clinical trial results. This provides richer context.” [1010]
Links for drilling down (selecting) to data source…
“Links are provided enabling drilling down to the specific sections of the source data that contributed to a given summary excerpt. This allows tracing back to the underlying evidence.” [0472]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to summarize medical records of patients as taught by Gardner et al. 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, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by the combined references who teaches their system can be used for medical purposes, it would be obvious this could be used for medical records of patients.
Regarding claim 3
The system of claim 2, wherein the consolidated report is presented on a human-machine interface (HMI), and the patient medical data is co-presented with the consolidated report on the HMI
[No Patentable Weight is given to non-functional descriptive claim language of “the patient medical data is co-presented with the consolidated report on the HMI.]
Bathwal et al. teaches:
Fig. 3 teaches HMI interface with cited example of picture (co presented)…
PNG
media_image2.png
260
650
media_image2.png
Greyscale
Patient
The combined references teach summarization for medical purposes. They do not specifically teach patient report and medical records and data.
Gardner et al. teaches also in the business of summarization for medical purposes teaches:
Medical records with patient reports…
“A medical records system invoking the summarization to pull out critical information from patient reports into standardized, condensed formats for physician review;…” [ 0249]
Distilling (generating) medical records into condensed summaries…
“Distilling medical records into condensed summaries for physician review;” [363]
Summary of content using LLM and prompts to summarize its own prior outputs (summary of summary)…
“The present disclosure provides specific technological solutions to these problems through one or more described features or combinations of features. The disclosed system enables users to precisely define a target level of abstraction (e.g., by specifying a percentage of length reduction) for a representation of a summary of a content item. For example, the system gives granular control over depth and brevity. The system may also be configured to engineer iterative prompts to have the LLM summarize its own prior outputs at increasing levels of abstraction. This allows for gradual refinement while preserving substantive information.” [0015]
Retain (store) summary information…
“Providing explicit instructions in the prompts generated for the LLM to retain specific highlighted information in the summary, overriding the abstraction process;” [0228]
Summarize by patient…
“A doctor can summarize lengthy patient medical histories into condensed overviews for reference on their phone when visiting patients. Negative zoom can expand details by inferring missing diagnosis dates based on medication timelines and incorporating relevant external data like clinical trial results. This provides richer context.” [1010]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to summarize medical records of patients as taught by Gardner et al. 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, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by the combined references who teaches their system can be used for medical purposes, it would be obvious this could be used for medical records of patients.
Regarding claim 4
The system of claim 1, wherein the plurality of patient reports comprises at least one of an image, medical information pertaining to the patient, patient personal information, or medical research information pertinent to the patient.
Bathwal et al. teaches:
Fig. 3 teaches HMI interface with cited example of image …
PNG
media_image2.png
260
650
media_image2.png
Greyscale
Patient
The combined references teach summarization for medical purposes. They do not specifically teach patient report and medical records and data.
Gardner et al. teaches also in the business of summarization for medical purposes teaches:
Medical records with patient reports…
“A medical records system invoking the summarization to pull out critical information from patient reports into standardized, condensed formats for physician review;…” [ 0249]
Distilling (generating) medical records into condensed summaries…
“Distilling medical records into condensed summaries for physician review;” [363]
Summary of content using LLM and prompts to summarize its own prior outputs (summary of summary)…
“The present disclosure provides specific technological solutions to these problems through one or more described features or combinations of features. The disclosed system enables users to precisely define a target level of abstraction (e.g., by specifying a percentage of length reduction) for a representation of a summary of a content item. For example, the system gives granular control over depth and brevity. The system may also be configured to engineer iterative prompts to have the LLM summarize its own prior outputs at increasing levels of abstraction. This allows for gradual refinement while preserving substantive information.” [0015]
Retain (store) summary information…
“Providing explicit instructions in the prompts generated for the LLM to retain specific highlighted information in the summary, overriding the abstraction process;” [0228]
Summarize by patient…
“A doctor can summarize lengthy patient medical histories into condensed overviews for reference on their phone when visiting patients. Negative zoom can expand details by inferring missing diagnosis dates based on medication timelines and incorporating relevant external data like clinical trial results. This provides richer context.” [1010]
Links for drilling down (selecting) to data source…
“Links are provided enabling drilling down to the specific sections of the source data that contributed to a given summary excerpt. This allows tracing back to the underlying evidence.” [0472]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to summarize medical records of patients as taught by Gardner et al. 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, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by the combined references who teaches their system can be used for medical purposes, it would be obvious this could be used for medical records of patients.
Regarding claim 5
The system of claim 1, wherein at least one of the patient reports is selected from the group consisting of: a radiology report, a oncology report, a cardiology report, a neurology report, a patient intervention report, an intensive care report, a general practitioner report, a report pertaining to the patient, a note pertaining to the patient, a report in an electronic medical record (EMR) system pertaining to the patient, a report in a non-EMR system pertaining to the patient, and a medical specialty report.
Bathwal et al. teaches:
Tailored to medical field (medical specialty report)…
“… Domain-specific summarization 424 technique can be tailored to specific fields such as legal, medical, or scientific texts. Domain-specific summarization incorporates specialized knowledge to create summaries that are meaningful within the context of the field. Narrative summarization 426 technique focuses on summarizing stories or events by identifying and presenting the narrative elements, such as the plot, characters, and setting, in a condensed form. Multimedia summarization 428 technique is applicable to content like videos, images, and audio. Multimedia summarization involves creating a condensed version of the media, such as a highlight reel or a visual abstract, which captures the main points or moments.” [0077]
Patient
The combined references teach summarization for medical purposes. They do not specifically teach patient report and medical records and data.
Gardner et al. teaches also in the business of summarization for medical purposes teaches:
Medical records with patient reports…
“A medical records system invoking the summarization to pull out critical information from patient reports into standardized, condensed formats for physician review;…” [ 0249]
Distilling (generating) medical records into condensed summaries…
“Distilling medical records into condensed summaries for physician review;” [363]
Summary of content using LLM and prompts to summarize its own prior outputs (summary of summary)…
“The present disclosure provides specific technological solutions to these problems through one or more described features or combinations of features. The disclosed system enables users to precisely define a target level of abstraction (e.g., by specifying a percentage of length reduction) for a representation of a summary of a content item. For example, the system gives granular control over depth and brevity. The system may also be configured to engineer iterative prompts to have the LLM summarize its own prior outputs at increasing levels of abstraction. This allows for gradual refinement while preserving substantive information.” [0015]
Retain (store) summary information…
“Providing explicit instructions in the prompts generated for the LLM to retain specific highlighted information in the summary, overriding the abstraction process;” [0228]
Summarize by patient…
“A doctor can summarize lengthy patient medical histories into condensed overviews for reference on their phone when visiting patients. Negative zoom can expand details by inferring missing diagnosis dates based on medication timelines and incorporating relevant external data like clinical trial results. This provides richer context.” [1010]
Links for drilling down (selecting) to data source…
“Links are provided enabling drilling down to the specific sections of the source data that contributed to a given summary excerpt. This allows tracing back to the underlying evidence.” [0472]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to summarize medical records of patients as taught by Gardner et al. 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, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by the combined references who teaches their system can be used for medical purposes, it would be obvious this could be used for medical records of patients.
Regarding claim 8
The system of claim 1, wherein the consolidated report further includes hyperlinks to data content included in one or more of the patient reports and the operations further comprising:
detecting selection of a hyperlink; and
Bathwal et al. teaches:
Hyperlinks to trace back to original source…
“Once the per-document summaries layer 224 has completed analysis and summarization of each individual document, the per-document summaries are provided to a cited multi-documents layer 226. A pivotal feature of this summarization approach is its attribution mechanism, wherein the cited multi-documents layer 226 enables each segment of the compiled summary to be meticulously traced back to its original source, providing clear citations or hyperlinks for reference. The summarization process is meticulously designed to prioritize relevance, selectively incorporating information that is most germane to the topic at hand, while simultaneously employing algorithms to eliminate redundancy. This ensures that the final summary presents a comprehensive and non-repetitive overview of the subject matter, derived from an extensive corpus of documents that is timely and relevant to the user's query. Once the dual-process (e.g., two phases) summarization techniques are complete, the output 238 is returned to the user via a frontend web interface.” [0056]
presenting corresponding data content associated with the hyperlink as extracted from a corresponding patient report.
Trace back (present) to original source…
“Once the per-document summaries layer 224 has completed analysis and summarization of each individual document, the per-document summaries are provided to a cited multi-documents layer 226. A pivotal feature of this summarization approach is its attribution mechanism, wherein the cited multi-documents layer 226 enables each segment of the compiled summary to be meticulously traced back to its original source, providing clear citations or hyperlinks for reference. The summarization process is meticulously designed to prioritize relevance, selectively incorporating information that is most germane to the topic at hand, while simultaneously employing algorithms to eliminate redundancy. This ensures that the final summary presents a comprehensive and non-repetitive overview of the subject matter, derived from an extensive corpus of documents that is timely and relevant to the user's query. Once the dual-process (e.g., two phases) summarization techniques are complete, the output 238 is returned to the user via a frontend web interface.” [0056]
Patient
The combined references teach summarization for medical purposes. They do not specifically teach patient report and medical records and data.
Gardner et al. teaches also in the business of summarization for medical purposes teaches:
Medical records with patient reports…
“A medical records system invoking the summarization to pull out critical information from patient reports into standardized, condensed formats for physician review;…” [ 0249]
Distilling (generating) medical records into condensed summaries…
“Distilling medical records into condensed summaries for physician review;” [363]
Summary of content using LLM and prompts to summarize its own prior outputs (summary of summary)…
“The present disclosure provides specific technological solutions to these problems through one or more described features or combinations of features. The disclosed system enables users to precisely define a target level of abstraction (e.g., by specifying a percentage of length reduction) for a representation of a summary of a content item. For example, the system gives granular control over depth and brevity. The system may also be configured to engineer iterative prompts to have the LLM summarize its own prior outputs at increasing levels of abstraction. This allows for gradual refinement while preserving substantive information.” [0015]
Retain (store) summary information…
“Providing explicit instructions in the prompts generated for the LLM to retain specific highlighted information in the summary, overriding the abstraction process;” [0228]
Summarize by patient…
“A doctor can summarize lengthy patient medical histories into condensed overviews for reference on their phone when visiting patients. Negative zoom can expand details by inferring missing diagnosis dates based on medication timelines and incorporating relevant external data like clinical trial results. This provides richer context.” [1010]
Links for drilling down (selecting) to data source…
“Links are provided enabling drilling down to the specific sections of the source data that contributed to a given summary excerpt. This allows tracing back to the underlying evidence.” [0472]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to summarize medical records of patients as taught by Gardner et al. 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, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by the combined references who teaches their system can be used for medical purposes, it would be obvious this could be used for medical records of patients.
Regarding claims 25 and 31
(claim 25) The system of claim 1, wherein the operations further comprise:
receiving a query regarding information pertaining to the patient; and
Bathwal et al. teaches:
Interface for search to a query…
“Additional examples of the user interface 300 provide the retrieval-augmented generated summary 306 (e.g., search response to a query), that includes a generated single answer from multiple sources. In certain embodiments, the single answer includes citations built into the answer. In example embodiments, the multi-document summarized single answer includes paraphrased, summarized, and/or aggregated information from one or more of the sources. In certain embodiments, the single answer, or portions thereof, does not match up with an exact quantum of information available from any one or more, or all, of the multiple sources. The single answer, or portions thereof, includes information that is inferred and/or derived from any one or more, or all of the multiple sources.” [0064]
generating an answer to the query, wherein generating the answer comprises constructing a composed prompt for the large language model that includes the query and contextual content derived from one or more of the report summaries or the consolidated report, and applying the composed prompt to the large language model to generate the answer.
Answer…
“Additional examples of the user interface 300 provide the retrieval-augmented generated summary 306 (e.g., search response to a query), that includes a generated single answer from multiple sources. In certain embodiments, the single answer includes citations built into the answer. In example embodiments, the multi-document summarized single answer includes paraphrased, summarized, and/or aggregated information from one or more of the sources. In certain embodiments, the single answer, or portions thereof, does not match up with an exact quantum of information available from any one or more, or all, of the multiple sources. The single answer, or portions thereof, includes information that is inferred and/or derived from any one or more, or all of the multiple sources.” [0064]
Synthesizes (generating) the result (answer) based on prompting large language model, based on search related documents summary for each document….
“In block 602, the method 600 receives, from a user device, a search query. In block 604, the method 600 retrieves a plurality of search result documents based on the search query. In block 606, the method 600 generates a summary of each of the plurality of search result documents using distinct per-document summarization machine learning models. According to some examples, the distinct per-document summarization machine learning models have been fine-tuned using a training dataset automatically created by prompting a large language model. In block 608, the method 600 synthesizes the summary of each of the plurality of search result documents into a single-consolidated answer responsive to the received search query from the user device. In block 610, the method 600 formats the consolidated answer to include citations to the plurality of search results documents.” [0093]
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over the combined references in section (6) above in further view of Pub. No. US 2026/0029900 to He et al.
Regarding claim 9
The system of claim 1, wherein the operations further comprise:
identifying first content in one or more of the patient reports pertaining to second content in a query received at the system, wherein identification of the first content is based on vector similarity between the first content and the second content of the query;
Bathwal et al. teaches:
Retrieve relevant (identify) content…
“Example embodiments of the enhanced summarization system can stand alone or be incorporated in a technical architecture that is multi-layered framework that integrates several components, such as a search engine to retrieve relevant documents from a vast index of web pages, a summarization engine configured to summarize the content of retrieved and/or selected documents, a query processor to analyze and interpret the user's search intent, a response generator that compiles the summaries into a human-coherent answer to the user's query, and the like. The system also features a unique architecture that supports query-independent and query-dependent summarization of documents, enabling it to handle a wide range of search queries effectively. For query-independent summarization, the system generates a general summary of a document without specific user input. For query-dependent summarization, the system tailors the summary to the user's particular search intent.” [0025]
Vector description of elements…
“Returning to the controller 102, the controller includes the result construction component 130, which includes a result parsing 136 component, which performs operations to parse potentially responsive documents for relevant data, text, tables, figures, or the like. Operations to parse potentially responsive documents may include providing a vector description of elements of the potentially responsive documents, allowing for identification of relevant portions, as well as determining which elements to utilize in constructing an answer. The example result construction component 130 includes a result builder 140 component, which determines which elements to include in the answer, ordering of the elements, combination of elements into single sentences, paragraphs, and/or visual elements, or the like. In example embodiments, the result builder 140 component accesses the natural language processor 134, which may be utilized to finalize the answer into a natural reading information packet: for example, as sentences, paragraphs, illustrations, and/or as a web page or other document.”[0042]
See Vector below.
generating a query answer using the large language model based on the first content and the second content; and
Compiles (generating) answers to query…
“Example embodiments of the enhanced summarization system can stand alone or be incorporated in a technical architecture that is multi-layered framework that integrates several components, such as a search engine to retrieve relevant documents from a vast index of web pages, a summarization engine configured to summarize the content of retrieved and/or selected documents, a query processor to analyze and interpret the user's search intent, a response generator that compiles the summaries into a human-coherent answer to the user's query, and the like. The system also features a unique architecture that supports query-independent and query-dependent summarization of documents, enabling it to handle a wide range of search queries effectively. For query-independent summarization, the system generates a general summary of a document without specific user input. For query-dependent summarization, the system tailors the summary to the user's particular search intent.” [0025]
presenting the query answer for review.
Delivers (presenting) the answers…
“Examples of the multi-document summarization system is configured to handle ambiguous queries by identifying and managing multiple potential user intents, ensuring that the synthesized answer remains relevant and accurate. The system further innovates model training, where it fine-tunes smaller, domain-specific models using, for example, labels generated from larger, more comprehensive models. This allows for efficient scaling and deployment of the system to handle real-time user queries with lower latency. Additionally, the system incorporates a reward modeling component that uses heuristics and user feedback to continuously improve the quality of the generated answers, ensuring that the system adapts and evolves with use. The multi-document summarization system provides an advancement in search technology by providing a system that not only simplifies the user's search experience but also delivers high-quality, synthesized answers that are both informative and easily digestible.” [0028]
Patient
The combined references teach summarization for medical purposes. They do not specifically teach patient report and medical records and data.
Gardner et al. teaches also in the business of summarization for medical purposes teaches:
Medical records with patient reports…
“A medical records system invoking the summarization to pull out critical information from patient reports into standardized, condensed formats for physician review;…” [ 0249]
Distilling (generating) medical records into condensed summaries…
“Distilling medical records into condensed summaries for physician review;” [363]
Summary of content using LLM and prompts to summarize its own prior outputs (summary of summary)…
“The present disclosure provides specific technological solutions to these problems through one or more described features or combinations of features. The disclosed system enables users to precisely define a target level of abstraction (e.g., by specifying a percentage of length reduction) for a representation of a summary of a content item. For example, the system gives granular control over depth and brevity. The system may also be configured to engineer iterative prompts to have the LLM summarize its own prior outputs at increasing levels of abstraction. This allows for gradual refinement while preserving substantive information.” [0015]
Retain (store) summary information…
“Providing explicit instructions in the prompts generated for the LLM to retain specific highlighted information in the summary, overriding the abstraction process;” [0228]
Summarize by patient…
“A doctor can summarize lengthy patient medical histories into condensed overviews for reference on their phone when visiting patients. Negative zoom can expand details by inferring missing diagnosis dates based on medication timelines and incorporating relevant external data like clinical trial results. This provides richer context.” [1010]
Links for drilling down (selecting) to data source…
“Links are provided enabling drilling down to the specific sections of the source data that contributed to a given summary excerpt. This allows tracing back to the underlying evidence.” [0472]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to summarize medical records of patients as taught by Gardner et al. 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, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by the combined references who teaches their system can be used for medical purposes, it would be obvious this could be used for medical records of patients.
Vector
The combined references teach large language model and vector. They do not teach vector with similarity.
He et al. also in the business of large language model and vector teaches:
Answers based on question-answer …
“In some embodiments, when the document digest, answers of the multiple rounds of question-answer, or the like are generated based on AIGC, a large language model (LLM) may be used. The LLM is a type of artificial intelligence model designed to understand and generate a human language. The LLM is trained on a large amount of text data and may perform a wide range of tasks, including text summarization, translation, sentiment analysis, and the like. The LLM is characterized by a large scale, including billions of parameters, which helps the LLM learn complex patterns in language data. These models are usually based on a deep learning architecture, such as a transformer, which helps the LLM achieve impressive performance in various NLP tasks.” [0068]
“The following describes the related process of question-answer by using an example in which the preset slice granularity is a sentence: First, a round or multiple rounds of rewriting are performed with reference to the question and the previous answer in the context, and an original meaning of question-answer content is maintained. Finally, a rewritten question is obtained. For example, the object first asks “How to make scrambled eggs with tomatoes?” and then (in this question-answer) asks “How should soy sauce be added in this dish?”, in this question-answer process, the second question needs to be rewritten with reference to the previous (that is, the first) asked question, an answer message, and the like. For example, the rewritten question is “How should soy sauce be added when making scrambled eggs with tomatoes?”” [0373] – [0374]
Document content based on related to question (query) and similarity with vectors…
“Then, the document content is retrieved with reference to the first feature information and the second feature information, to find document content related to the question. In this operation, in some embodiments, a similarity between the first feature information and each second feature information may be separately calculated. For example, a similarity is represented by a distance between vectors, and a sentence corresponding to second feature information with a similarity higher than a specific threshold is used as the document content related to the question.” [0377]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to use vector similarity as taught by He et al. 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, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by He et al. who teaches the benefits of using vector for similarity analysis to provide the correct content.
Claims 21 and 27 are rejected under 35 U.S.C. 103 as being unpatentable over the combined references in section (6) above in further view of Pub. No. US 2001/0037332 to Miller et al.
Regarding claims 21 and 27
(claim 21) The system of claim 1, wherein the consolidated report includes first hyperlinks that map portions of the consolidated report to corresponding report summaries, and wherein each report summary includes second hyperlinks to corresponding patient reports from which the report summary was generated.
Bathwal et al. teaches:
Each summary to be traced back to its original source (report)…
“Once the per-document summaries layer 224 has completed analysis and summarization of each individual document, the per-document summaries are provided to a cited multi-documents layer 226. A pivotal feature of this summarization approach is its attribution mechanism, wherein the cited multi-documents layer 226 enables each segment of the compiled summary to be meticulously traced back to its original source, providing clear citations or hyperlinks for reference. The summarization process is meticulously designed to prioritize relevance, selectively incorporating information that is most germane to the topic at hand, while simultaneously employing algorithms to eliminate redundancy. This ensures that the final summary presents a comprehensive and non-repetitive overview of the subject matter, derived from an extensive corpus of documents that is timely and relevant to the user's query. Once the dual-process (e.g., two phases) summarization techniques are complete, the output 238 is returned to the user via a frontend web interface.” [0056]
The combined references teach hyperlinks. They do not teach with consolidate report.
Miller et al. also in the business of hyperlinks teaches:
Consolidated report with hyperlinks…
“Referring to FIG. 3, the user interface 12 further displays the results of the search to the user. For example, the search results are shown to the user in a summary format using hyperlinks. Hyperlinks may be implemented using HTML but other presentation or markup languages such as DHTML, XML, etc. can be used. The results displayed to the user are consolidated results retrieved from the various specified databases. As will be explained further below, the control engine 14 receives the respective results from the translators 16a-h and consolidates such results for presentation to the user via the user interface 12.” [0029]
Summary record with hyperlink…
“At 650, the translator 16 further creates a number of hyperlinks which are linked to the summary records respectively. In the event that a summary record also has a corresponding full record, a hyperlink is also created to link the summary record and the corresponding full record together.” [0052]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to use hyperlinks with consolidated report as taught by Miller et al. 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, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Miller et al. who teaches the benefits of using hyperlinks for accessing information.
Claims 22 and 33 are rejected under 35 U.S.C. 103 as being unpatentable over the combined references in section (6) above in further view of Pub. No. US 2008/0282141 to Eisen
Regarding claims 22, 28, and 33
(claim 22) The system of claim 1, wherein generating the consolidated report comprises identifying respective portions of text in the consolidated report that are derived from corresponding ones of the report summaries, and integrating, into the consolidated report, hyperlinks associated with the respective portions of text, wherein selection of a hyperlink causes presentation of the corresponding report summary from which the respective portion of text was derived.
Bathwal et al. teaches:
Linking to relevant portion of the answer….
“For example, the user 108 can enter a search query into the user input box 304, such as: “what are unreal facts about rabbits? The retrieval-augmented generated summary 306 will be generated according to the methods described throughout to answer the input query directly in the user's browser. The system outputs summarized text with internal citations 308 based on the query. Without leaving the browser or having to select and search through hyperlinks to gather aggregated answers with sourced citations, the user will receive a multi-document summarization with sources 312, including citations, such as footnotes or endnotes, linking to each relevant portion of the answer.” [0061]
The combined references teach hyperlinks. They do not teach links to summary.
Eisen et al. also in the business of hyperlinks teaches:
List 400 (consolidated report) with hyperlinks to report summaries…
“FIG. 4 illustrates a list 400, according to one embodiment, that is created by the computer when the user selects entries 302 and 304 of summary view 300 and indicates to the computer that the user desires to have the computer create a list based on the selected entries. List 400 includes two entries: entry 402 and 404. Entry 402 corresponds to entry 302 and entry 404 corresponds to entry 304. As shown in FIG. 4, entry 402 includes document summary data 412 that was copied from entry 302 and a hyperlink 413 that references the document associated with entry 302. Similarly, entry 404 includes document summary data 414 that was copied from entry 304 and a hyperlink 415 that references the document associated with entry 304.” [0029]
Hyperlinks combined (consolidated) and links to document summary….
“In other embodiments, as described above, hyperlinks 413 and 415 can be combined with document summary data 412 and 414, respectively, so that the document summary data 412 and 414 are themselves hyperlinks to the document to which the summary data pertains. That is, for example, the user can view the document associated with document summary data 412 by clicking-on or otherwise selecting document summary data 412.” [0034]
Fig. 4, ref. 413 (hyperlink associated with portion of text)…
PNG
media_image3.png
190
550
media_image3.png
Greyscale
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to use hyperlinks with document summary as taught by Eisen et al. 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, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Eisen et al. who teaches the benefits of using hyperlinks for accessing information.
Claims 23 and 29 are rejected under 35 U.S.C. 103 as being unpatentable over the combined references in section (9) above in further view of Pub. No. US 2004/0064432 to Oetringer et al.
Regarding claims 23 and 29
(claim 23) The system of claim 22, wherein the respective portions of text in the consolidated report are presented as selectable text, and wherein selection of the selectable text invokes the corresponding hyperlink to cause presentation of the corresponding report summary.
The combined teach links. They do not teach selectable text.
Oetringer et al. also in the business of links teaches:
Hypertext links (selectable links)….
“FIG. 1A is an illustration of one embodiment of a graphical user interface (GUI) 180 associated with repository 102. GUI 180 illustrates a summary report associated with repository 102. The summary report may be used, for example, by a higher level manager to determine the status of repository 102 and initiate actions to increase reliability of repository 102. The summary report may be generated based on, for example, status 120 and the number of red, amber and green status indications in status 120. The summary report may also configurably show historical information, such as the number of red, amber and/or green documents on a given date in the past. The manager may identify red reliability documents in the manager's area of responsibility and instruct owner 140 to update document 110 to remove the red status indication. For example, the manager may select "directions for high availability" in order to view that document and determine owner 140. In general, the summary report may be configured to display appropriate information for the manager or other user of the summary report, and may include hypertext links to more detailed information related to information displayed in the summary report.” [0054]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to use hypertext as taught by Oetringer et al. 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, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Oetringer et al. who teaches the benefits of using hypertext for accessing information.
Claims 24 and 30 are rejected under 35 U.S.C. 103 as being unpatentable over the combined references in section (6) above in further view of Pub. No. US 2026/0029900 to He et al. in view of Pub. No. US 2008/0301113 to Chi et al.
Regarding claims 24 and 30
(claim 24) The system of claim 1, wherein the operations further comprise:
receiving a query regarding information pertaining to the patient; and
Bathwal et al. teaches:
Interface for seach to a query…
“Additional examples of the user interface 300 provide the retrieval-augmented generated summary 306 (e.g., search response to a query), that includes a generated single answer from multiple sources. In certain embodiments, the single answer includes citations built into the answer. In example embodiments, the multi-document summarized single answer includes paraphrased, summarized, and/or aggregated information from one or more of the sources. In certain embodiments, the single answer, or portions thereof, does not match up with an exact quantum of information available from any one or more, or all, of the multiple sources. The single answer, or portions thereof, includes information that is inferred and/or derived from any one or more, or all of the multiple sources.” [0064]
generating an answer to the query, wherein generating the answer comprises embedding the query into an embedding space, retrieving a predefined number of vector representations based on similarity between the embedded query and vector representations associated with at least one of the report summaries or the consolidated report, and providing content corresponding to the retrieved vector representations for processing by the large language model.
Answer…
“Additional examples of the user interface 300 provide the retrieval-augmented generated summary 306 (e.g., search response to a query), that includes a generated single answer from multiple sources. In certain embodiments, the single answer includes citations built into the answer. In example embodiments, the multi-document summarized single answer includes paraphrased, summarized, and/or aggregated information from one or more of the sources. In certain embodiments, the single answer, or portions thereof, does not match up with an exact quantum of information available from any one or more, or all, of the multiple sources. The single answer, or portions thereof, includes information that is inferred and/or derived from any one or more, or all of the multiple sources.” [0064]
The combined references teach vector. They do not teach embedding vector.
He et al. also in the business of vector teaches:
Embedding vector…
“FIG. 33 is a schematic diagram of a feature matching process according to some embodiments. A parsed document may be divided into multiple content slices at a granularity of a sentence, such as sentence 1, sentence 2, . . . , sentence n in FIG. 33. Second feature information corresponding to each sentence may be extracted through encoding (Encoder), that is, a sentence-level embedding vector for each sentence in the document, such as embedding 1, embedding 2, . . . , embedding n in FIG. 33, is extracted. These embeddings may be stored on a server side, and directly queried during subsequent question-answer and the like.” [0378]
Question (query) embedded….
“In addition, after the question is rewritten in the context, first feature information corresponding to the rewritten question may be extracted through encoding (Encoder), that is, a sentence-level embedding for a question asked in a session, such as embedding a in FIG. 33, is extracted.” [0379]
Sentence with higher threshold is used as the document content…
“Then, question retrieval is performed. According to the embedding obtained through feature extraction, the document embedding is retrieved to learn if there is similar content. In some embodiments, embedding a is matched with embedding 1, embedding 2, . . . , and embedding n separately. A distance between vectors is calculated. A closer distance between two vectors corresponds to a higher similarity. Further, a sentence corresponding to second feature information with a similarity higher than a specific threshold is used as the document content related to the question.” [0380]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to use vector similarity as taught by He et al. 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, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by He et al. who teaches the benefits of using vector for similarity analysis to provide the correct content.
Predefined
The combined references teach vector. They do not teach predetermined number.
Chi et al. also in the business of vector teaches:
Example of set limit (predefined) number of vector terms…
“Search provider 102 may be operative to generate term vectors in conjunction with the generation of a result set in response to a user query. A vector term generator 116 may be operative to analyze the one or more content items in the result set and generate term vectors for a given one of the one or more content items. The generation of term vectors is described more fully in U.S. Pat. No. 6,947,930, entitled "SYSTEM AND METHOD FOR INTERACTIVE SEARCH QUERY REFINEMENT," which was filed on Apr. 25, 2003, the disclosure of which is hereby incorporated by reference in its entirety. The vector term generator 118 may further be operative to extract the most relevant vector terms from a given vector. In one embodiment, a set limit on the number of returned vector terms may be defined by the search provider 102. In an alternative embodiment, the number of vector terms selected by the vector term generator may be a percentage of the total number of vector terms generated. Other thresholds should be apparent to those of skill in the art.” [0027]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to set a limit as taught by Chi et al. 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, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Chi et al. and the benefit of setting a limit and this would limit processing requirements.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
The following prior art teaches at least long language model:
US-20250045525-A1; US-20250111166-A1; US-20250111932-A1; US-20250148020-A1; US-20250166762-A1; US-20260024037-A1; CN-116975252-A; CN-116991518-A
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KENNETH BARTLEY whose telephone number is (571)272-5230. The examiner can normally be reached Mon-Fri: 7:30 - 4:00 EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, SHAHID MERCHANT can be reached at (571) 270-1360. 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.
/KENNETH BARTLEY/Primary Examiner, Art Unit 3684
Prosecution Insights