Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
1. The pending claims 1-20 are presented for examination.
Claim Rejections - 35 USC § 101
2. 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.
3. Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The analysis below of the claims’ subject matter eligibility follows the guidance set forth in MPEP 2106 which has incorporated the 2019 PEG.
Regarding to claim 1,
Step 1 Analysis: Claim 1 is directed to a method, which is directed to a process, one of the statutory categories.
Step 2A Prong One Analysis:
Claim 1 recites: A method comprising:
“receiving, from an LLM-powered search engine, a response comprising a natural language summary, a data payload, and an action recommendation, wherein the natural language summary includes a reference to a data element of the data payload”. This element reads on a person receives a query response comprising a natural language summary, a data payload, and an action recommendation, wherein the natural language summary includes a reference to a data element of the data payload which could be considered a mental process of an observation or evaluation.
“displaying the natural language summary in a first section of a user interface of a user application, wherein the reference is embedded in a corresponding widget”. This element reads on a person displays the natural language summary in a first section of a user interface of a user application, wherein the reference is embedded in a corresponding widget which could be considered a mental process of an observation or evaluation.
“monitoring the user interface to detect a selection of the corresponding widget of the reference”. This element reads on a person monitors the user interface to detect a selection of the corresponding widget of the reference which could be considered a mental process of an observation or evaluation.
“identifying, upon detecting the selection of the corresponding widget, a viewer type corresponding to the data element”. This element reads on a person identifies, upon detecting the selection of the corresponding widget, a viewer type corresponding to the data element which could be considered a mental process of an observation or evaluation.
“invoking a viewing tool corresponding to the viewer type to generate a visualization of the data element”. This element reads on a person invokes a viewing tool corresponding to the viewer type to generate a visualization of the data element which could be considered a mental process of an observation or evaluation.
“rendering, by the viewing tool, the visualization in a first viewer section of the user interface”. This element reads on a person renders, by the viewing tool, the visualization in a first viewer section of the user interface which could be considered a mental process of an observation or evaluation.
“monitoring the first viewer section for user interactions to detect selection of a second widget, wherein the second widget embeds a second reference to a second data element”. This element reads on a person monitors the first viewer section for user interactions to detect selection of a second widget, wherein the second widget embeds a second reference to a second data element which could be considered a mental process of an observation or evaluation.
Overall, the limitations directed to identify a widget for a data element of a data payload and the various mental process limitations in the context of this claim encompasses limitations that are not only considered to be directed to limitations that could be practically performed in the human mind (including observations and preform an evaluation, judgment, and opinion) aided by the use of pen and paper. If the claim limitations, under their broadest reasonable interpretations, cover performance of the limitation in the mind but for the recitation of generic computer components, then they fall within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
Step 2A Prong Two Analysis: In Step 2A Prong 2, we are directed to Identify whether there are any additional elements recited in the claim beyond the judicial exception(s), and evaluate those additional elements to determine whether they integrate the exception into a practical application of the exception.
There is no additional element integrate the judicial exception into a practical application.
Step 2B Analysis: In Step 2B, we are directed to Identify whether there are any additional elements recited in the claim beyond the judicial exception(s), and evaluate those additional elements to determine whether the additional elements, taken individually and in combination, result in the claim as a whole amounting to significantly more than the judicial exception.
As discussed above with respect to integration of the abstract idea into a practical application, The additional elements “a computer-based” is simply applying the abstract idea, and there is nothing done with results.
There is no additional element(s), taken individually and in combination, result in the claim as a whole amounting to significantly more than the judicial exception. The claim is not patent eligible.
Regarding claim 2,
Step 1 Analysis: Claim 2 is directed to a method, which is directed to a process, one of the statutory categories.
Step 2A Prong One Analysis:
Claim 2 is dependent on claim 1, which as indicated in the analysis above, is directed to an abstract idea without significantly more.
Claim 2 recites “
identifying a nested data element, wherein the nested data element is included in the data element;
adding a nested reference to the nested data element; and
generating the visualization of the data element, wherein the visualization further comprises a nested widget, wherein the nested widget embeds the nested reference to the nested data element." That is, the claim recites
identifying a nested data element, wherein the nested data element is included in the data element;
adding a nested reference to the nested data element; and
generating the visualization of the data element, wherein the visualization further comprises a nested widget, wherein the nested widget embeds the nested reference to the nested data element
. The above-noted limitation of claim 2, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
Step 2A Prong Two Analysis: This judicial exception is not integrated into a practical application.
Step 2B Analysis: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Regarding claim 3,
Step 1 Analysis: Claim 3 is directed to a method, which is directed to a process, one of the statutory categories.
Step 2A Prong One Analysis:
Claim 3 is dependent on claim 1, which as indicated in the analysis above, is directed to an abstract idea without significantly more.
Claim 3 recites “
identifying a second viewer type corresponding to the second data element;
invoking a second viewing tool corresponding to the second viewer type to generate a second visualization of the second data element; and
rendering, by the second viewing tool, the second visualization in a second viewer section of the user interface.”
That is, the claim recites
identifying a second viewer type corresponding to the second data element;
invoking a second viewing tool corresponding to the second viewer type to generate a second visualization of the second data element; and
rendering, by the second viewing tool, the second visualization in a second viewer section of the user interface.
The above-noted limitation of claim 3, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
Step 2A Prong Two Analysis: This judicial exception is not integrated into a practical application.
Step 2B Analysis: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Regarding claim 4,
Step 1 Analysis: Claim 4 is directed to a method, which is directed to a process, one of the statutory categories.
Step 2A Prong One Analysis:
Claim 4 is dependent on claim 1, which as indicated in the analysis above, is directed to an abstract idea without significantly more.
Claim 4 recites “
identifying a schema type associated with the data element;
selecting the viewing tool based on a mapping between the schema type and the viewer type; and
executing the viewing tool to generate the visualization of the data element”
That is, the claim recites
identifying a schema type associated with the data element;
selecting the viewing tool based on a mapping between the schema type and the viewer type; and
executing the viewing tool to generate the visualization of the data element. The above-noted limitation of claim 4, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
Step 2A Prong Two Analysis: This judicial exception is not integrated into a practical application.
Step 2B Analysis: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Regarding claim 5,
Step 1 Analysis: Claim 5 is directed to a method, which is directed to a process, one of the statutory categories.
Step 2A Prong One Analysis:
Claim 5 is dependent on claim 1, which as indicated in the analysis above, is directed to an abstract idea without significantly more.
Claim 5 recites “
the corresponding widget of the reference to the data element of the data payload comprises a preview of the visualization of the data element" That is, the claim recites
the corresponding widget of the reference to the data element of the data payload comprises a preview of the visualization of the data element. The above-noted limitation of claim 5, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
Step 2A Prong Two Analysis: This judicial exception is not integrated into a practical application.
Step 2B Analysis: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Regarding claim 6,
Step 1 Analysis: Claim 6 is directed to a method, which is directed to a process, one of the statutory categories.
Step 2A Prong One Analysis:
Claim 6 is dependent on claim 1, which as indicated in the analysis above, is directed to an abstract idea without significantly more.
Claim 6 recites “
the data element comprises image data, plot data, a database query, database records, and document identifiers." That is, the claim recites
the data element comprises image data, plot data, a database query, database records, and document identifiers. The above-noted limitation of claim 6, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
Step 2A Prong Two Analysis: This judicial exception is not integrated into a practical application.
Step 2B Analysis: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Regarding claim 7,
Step 1 Analysis: Claim 7 is directed to a method, which is directed to a process, one of the statutory categories.
Step 2A Prong One Analysis:
Claim 7 is dependent on claim 1, which as indicated in the analysis above, is directed to an abstract idea without significantly more.
Claim 7 recites “
receiving, by the LLM-powered search engine, a natural language query from a conversational interface, wherein the conversational interface is the first section of the user interface; and
generating, by the LLM-powered search engine, the response comprising the natural language summary, the data payload, and the action recommendation" That is, the claim recites
receiving, by the LLM-powered search engine, a natural language query from a conversational interface, wherein the conversational interface is the first section of the user interface; and
generating, by the LLM-powered search engine, the response comprising the natural language summary, the data payload, and the action recommendation. The above-noted limitation of claim 7, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
Step 2A Prong Two Analysis: This judicial exception is not integrated into a practical application.
Step 2B Analysis: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Accordingly, this additional element, taken individually and in combination, does not result in the claim as a whole amounting to significantly more than the judicial exception. The claim is not patent eligible.
Regarding claim 8,
Step 1 Analysis: Claim 8 is directed to a method, which is directed to a process, one of the statutory categories.
Step 2A Prong One Analysis:
Claim 8 is dependent on claim 1, which as indicated in the analysis above, is directed to an abstract idea without significantly more.
Claim 8 recites “
displaying the natural language summary in a conversational interface, wherein the conversational interface is the first section of the user interface, and wherein the natural language summary includes a reference to the action recommendation of the response, and wherein the action recommendation comprises a workflow action,
and monitoring the conversational interface to detect a selection of the reference." That is, the claim recites
displaying the natural language summary in a conversational interface, wherein the conversational interface is the first section of the user interface, and wherein the natural language summary includes a reference to the action recommendation of the response, and wherein the action recommendation comprises a workflow action,
and monitoring the conversational interface to detect a selection of the reference”. The above-noted limitation of claim 8, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
Step 2A Prong Two Analysis: This judicial exception is not integrated into a practical application.
Step 2B Analysis: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Regarding claim 9,
Step 1 Analysis: Claim 9 is directed to a method, which is directed to a process, one of the statutory categories.
Step 2A Prong One Analysis:
Claim 9 is dependent on claims 1&8, which as indicated in the analysis above, is directed to an abstract idea without significantly more.
Claim 9 recites “
receiving, from the conversational interface, the selection of the reference;
identifying a workflow type of the action recommendation;
invoking a workflow tool to perform a workflow corresponding to the workflow type, using the data payload, to obtain an output of the workflow tool;
displaying a second reference to the output of the workflow tool in the conversational interface, wherein the second reference includes a viewer type corresponding to the output of the workflow tool; and
monitoring the user interface to detect a selection of the second reference." That is, the claim recites
receiving, from the conversational interface, the selection of the reference;
identifying a workflow type of the action recommendation;
invoking a workflow tool to perform a workflow corresponding to the workflow type, using the data payload, to obtain an output of the workflow tool;
displaying a second reference to the output of the workflow tool in the conversational interface, wherein the second reference includes a viewer type corresponding to the output of the workflow tool; and
monitoring the user interface to detect a selection of the second reference.. The above-noted limitation of claim 9, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
Step 2A Prong Two Analysis: This judicial exception is not integrated into a practical application.
Step 2B Analysis: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Regarding claim 10,
Step 1 Analysis: Claim 10 is directed to a method, which is directed to a process, one of the statutory categories.
Step 2A Prong One Analysis:
Claim 10 is dependent on claim 1, which as indicated in the analysis above, is directed to an abstract idea without significantly more.
Claim 10 recites “
prior to rendering the natural language summary, iteratively performing:
validating the data payload with respect to the action recommendation to obtain a validation result; and
responsive to the validation result being an error result, performing operations comprising:
generating, by a correction LLM, a correction prompt based on the error result and the response,
processing, by the LLM-powered search engine, the correction prompt to generate a second response;
for a pre-defined number of iterations
." That is, the claim recites
prior to rendering the natural language summary, iteratively performing:
validating the data payload with respect to the action recommendation to obtain a validation result; and
responsive to the validation result being an error result, performing operations comprising:
generating, by a correction LLM, a correction prompt based on the error result and the response,
processing, by the LLM-powered search engine, the correction prompt to generate a second response;
for a pre-defined number of iterations
”. The above-noted limitation of claim 10, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
Step 2A Prong Two Analysis: This judicial exception is not integrated into a practical application.
Step 2B Analysis: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Regarding claim 11,
Step 1 Analysis: Claim 11 is directed to a method, which is directed to a process, one of the statutory categories.
Step 2A Prong One Analysis:
Claim 11 is dependent on claims 1&10, which as indicated in the analysis above, is directed to an abstract idea without significantly more.
Claim 11 recites “
responsive to the pre-defined number of iterations being performed, and the validation result being the error result, generating an error response; and
displaying the error response in a conversational interface of the user interface.
." That is, the claim recites
responsive to the pre-defined number of iterations being performed, and the validation result being the error result, generating an error response; and
displaying the error response in a conversational interface of the user interface.
”. The above-noted limitation of claim 11, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
Step 2A Prong Two Analysis: This judicial exception is not integrated into a practical application.
Step 2B Analysis: The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception.
Claims 12-19 are rejected under 35 U.S.C. 101 with the same rational of claims 1-9.
Claim 20 is rejected under 35 U.S.C. 101 with the same rational of claim 1.
Claim Rejections - 35 USC § 103
4. 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 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.
5. 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.
6. 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.
7. The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied 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.
8. Claims 1,3, 7, 12, 14, 18 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Sheikh et al (US 20250097292 A1, hereinafter “Sheikh”) in view of Faonte et al (U.S. 20250139145 A1 hereinafter, “Faonte”).
9. With respect to claim 1,
Sheikh discloses
a method comprising:
receiving, from an LLM-powered search engine (Sheikh [0040], [0048], [0136] e.g. LLM – [0136] The data flow 1200 illustrated by the data flow diagram of FIG. 12 is shown to involve a digital assistant 1202 and a task manager and notification service layer 1204 of a cloud service provider platform 1206. The digital assistant 1202 may include, or be associated with, one or more machine learning models, such as large language models (LLMs) for interpreting natural language end user inputs, scheduling events and tasks, and generating notifications. An end user may converse with the digital assistant using a client application of a client computing device 1208, as described above. In this example, the client computing device 1208 is a mobile computing device and the client application is a mobile client application, but conversations with the digital assistant 1202 may also occur via a desktop computing device and an associated desktop client application in other examples), a response comprising a natural language summary (Sheikh Abstract, [0037], [0042], [0050], [0057], [0216] e.g. [0037] For example, embodiments of the application may enable an end user to easily record conversations with patients, dictate in natural language, generate patient notes, populate patient records, request and receive patient information, fill prescriptions, create or have automatically created task and event reminders, and receive associated notifications. [0042] In some implementations, the responses can be natural language responses and/or graphical responses … and subsequently provide a response to the user which may be or may include a textual or audible natural language response. In one example, a user may utilize the clinical automation service (110c) to perform various clinical tasks via natural language-based conversations therewith), a data payload (Sheikh [0107] e.g. [0107] For example, the payload may include a natural language response to a query (e.g., a request for information), which may initiate further conversation between the healthcare provider and the digital assistant 1006), and an action recommendation (Sheikh [0040], [0046], [0046], [0078], [0080], [0093], [0098], [0127] – [0128], [0150] e.g. actions suggested, action suggestions/buttons – [0093] The dictation service 212 may be activated by, for example, engaging (e.g., selecting/clicking) an action button of the client application home screen or another widget that may be provided and displayed for the same purpose. As represented in FIG. 6, such an action button may be configured as a dictation mode initiation button. …." [0127] Another sequence flow can result from an end user activating and entering the dictation mode of operation from the mobile computing device 1104. For example, the end user may click on a dictation widget (e.g., action button) on the user interface 1134 of the mobile computing device 1104. [0128] For example, with respect to audio capture and wake word detection, the mobile client application 1102 can include additional widgets (e.g., action buttons) for controlling actions such as, without limitation, starting and stopping dictation, navigating form fields, pasting dictation box contents while in dictation mode, starting the clinical automation (assistant) mode by clicking a button rather than uttering a wake word; and muting the microphone. [0150] For example, this could be either a user interface where a healthcare provider can view the details of the notification or it may be some actions suggested by the digital assistant 1202 based on the notification), wherein the natural language summary includes a reference to a data element of the data payload (Sheikh [0004] – [0005], [0009] – [0011], [0045] – [0046], [0069], [0082] – [0090], [0107], [0123], [0144], [0151], [0161] – [0162] e.g. [0004] The response message has a payload content including a set of configuration parameters that define a layout of the payload content. The response message is then provided to one or both of the first client device and the second client device. Providing the response message to one or both of the first client device and the second client device causes the payload content of the response message to be displayed on one or both of a first client device display and a second client device display according to the configuration parameters and the capabilities of the first client device and the second client device. [0069] The framework embodiment of FIG. 4 is configured to allow a cloud service provider platform and services thereof to handle end user actions and to remotely (centrally) manage the application state by leveraging the Redux paradigm. With the Redux approach, views 406 are not burdened with complex business/communication logic. Instead, views 406 can gather data in the form of end user gestures (e.g., speaking, typing, tapping on buttons) and dispatch the same as actions 408 with payloads (i.e., the data associated with the gestures) to a Redux store 410. The view layer 406, the actions 408, and the Redux store 410 may all be associated with an application framework middleware layer. The middleware layer can process the actions and payloads to determine a single application state, thereby reducing two types of information into one (hence the use of the "Redux" descriptor). When response messages are eventually returned by the services of the cloud service provider platform to WebSocket connections managed by the middleware layer, the content of the response message payloads can also be dispatched as update actions to the client application state. The middleware layer may also include other logic, such as logic capable of transmitting a natural language utterance to a cloud service provider platform (e.g., to a digital assistant) through a WebSocket connection, retrieving transcribed utterances from a speech-to-text server, or generating an audible (verbal utterance) response by sending a textual input to a text-to-speech server. As described in more detail below, the centrally managed client application state allows an end user to move seamlessly between client devices when performing a clinical task);
displaying the natural language summary in a first section of a user interface of a user application, wherein the reference is in a corresponding widget (Sheikh [0004] – [0005], [0009] – [0011], [0040], [0045] – [0046], [0069], [0077] - [0082] – [0090], [0093], [0098], [0107], [0116], [0123], [0127] – [0128], [0144], [0150] -[0151], [0161] – [0162] e.g. widget – [0093] FIG. 9 illustrates one embodiment of a dictation service data flow 900, in reference to the system architecture depicted in FIG. 2. In some embodiments, the dictation service 212 may be activated from the client application 230 via messages sent across the unified event channel 248 of the frontend 244 of the cloud service provider platform 202. The dictation service 212 may be activated by, for example, engaging (e.g., selecting/clicking) an action button of the client application home screen or another widget that may be provided and displayed for the same purpose. [0127] Another sequence flow can result from an end user activating and entering the dictation mode of operation from the mobile computing device 1104. For example, the end user may click on a dictation widget (e.g., action button) on the user interface 1134 of the mobile computing device 1104.);
monitoring the user interface to detect a selection of the corresponding widget of the reference (Sheikh [0040], [0046], [0046], [0066], [0078], [0080], [0093], [0098], [0104], [0127] – [0128], [0138], [0150] e.g. selecting/clicking … selecting a clinical automation (assistant) mode widget);
identifying, upon detecting the selection of the corresponding widget, a viewer type (Sheikh [0077] e.g. types of widgets) corresponding to the data element;
invoking a viewing tool (Sheikh [0131], [0148], [0158] e.g. viewer; viewing) corresponding to the viewer type to generate a visualization of the data element (Sheikh [0086], [0162] e.g. a visual representation for display);
rendering, by the viewing tool, the visualization in a first viewer section of the user interface (Sheikh [0076], [0079] – [0080], [0089] – [0090], [0151], [0162] e.g. rendered/rendering); and
monitoring the first viewer section for user interactions to detect selection of a second widget, wherein the second widget embeds a second reference to a second data element (Sheikh [0004] – [0005], [0009] – [0011], [0040], [0045] – [0046], [0069], [0077] - [0082] – [0090], [0093], [0098], [0104], [0107], [0116], [0123], [0127] – [0128], [0144], [0150] -[0151], [0161] – [0162] e.g. 0104] selecting clicking … another widget/different widgets).
Although Sheikh substantially teaches the claimed invention, Sheikh does not explicitly indicate the reference is embedded in a corresponding widget.
Faonte teaches the limitations by stating
receiving, from an LLM-powered search engine (Faonte [0042], [0064], [0067] – [0068], [0071] e.g. LLM), a data payload (Faonte [0016], [0037], [0045] – [0051], [0056] – [0057], [0071] – [0072], [0079] – [0088] e.g. payload), wherein the natural language summary includes a reference (Faonte [0071] - [0076] e.g. [0071] The trained embeddings map high-dimensional vectors representing semantic and syntactic properties of a payload request (e.g., generates a vector representing the natural language request) to the information describing the widgets (e.g., to vectors representing the widget 142 including, e.g., its title, metadata, additional information, etc.). As described above, the additional information may be a vector generated by an LLM representing the semantic, syntactic, and intentional content of a widget. In other words, the small language model identifies widgets having metadata semantically or syntactically similar to language in the payload request …. [0072] These embeddings are generated through the training process where the small language model learns to associate linguistic patterns and relationships in a payload request to widgets in a catalog within a training dataset. When given an input prompt, the model looks up the embeddings for each token or word in the payload request. The model computes a contextualized representation considering the surrounding context and maps that contextualized representation to various widgets based on the trained embedding. By leveraging the learned relationships between words within the embedding space, the model can then assess the likelihood that words in a payload request relate to the functionality of various widgets. Subsequently, the model generates widgets for the payload request by selecting the most suitable widgets candidates based on the embedding-derived probabilities. … [0074] …. In the illustrated example, a natural language query 610 (e.g., a widget search query) is passed to a model 620 (e.g., a small language model such as an embedder). The model 620 generates an embedding 630 representing the content, syntax, and content of the natural language query 610 in higher dimensional space. The embedding 630 is compared to enhanced vectors representing the widgets. The enhanced vectors may be the information about widgets stored in the enhanced vector store 640 (e.g., vectors representing the additional information 440 about widgets generated from the output of a model). The analytics module 124 calculates a score representing a similarity between the embedding and the enhanced vector and uses the comparison (e.g., score) to select widgets (e.g., K selected widgets 650) with the highest degree of similarity. The selected widgets are then returned as a result to the natural language query. [0075] …. In this example, a user submits a natural language search query 610 "Recent Event C" to the analytics module 124. The analytics module 124 performs the vector search 760 (e.g., applying a model to generate embeddings representing the query, and comparing the embeddings to the enhanced vectors). The vector search 760 returns five selected widgets 760 (e.g., 750A, 7508, 750C, 750D, and 750D), including (1) How did Relevant Entity respond to Event for Event C?; (2) What did Associated Person say about Event C?; (3) What are historical metrics for Topic C related to Event C?; (4) What are current metrics for Topic D?; and (5) What other events are related to Event C? As with the generation of additional information, it should be appreciated that some or all of these results are unlikely to be generated using a conventional embedding-centric approach. For example, metrics for Topic D, which may only be loosely associated with Event C, is unlikely to be identified by an embedder as relevant to Event C. …) to a data element of the data payload;
displaying the natural language summary in a first section of a user interface of a user application, wherein the reference is embedded (Faonte [0071] - [0076] e.g. embedding) in a corresponding widget;
monitoring the user interface to detect a selection of the corresponding widget of the reference;
invoking a viewing tool corresponding to the viewer type to generate a visualization (Faonte [0006] – [0007], [0011] – [0012], [0016] – [0017], [0021] – [0022], [0025], [0037], [0048] – [0049], [0063] – [0064], [0073], [0079] – [0083], [0088] e.g. visualization – [0063] The widget creation module 330 provides a user interface via which users may submit or create widgets. In one embodiment, all users of the system may create widgets. Alternatively, widget creation may be limited to a set of authorized users. A widget has a title which may be selected by the creator, assigned by another user (e.g., an administrator), or assigned automatically and includes a layout of one or more elements. Widgets may also have additional associated metadata as described above. At least some of the elements of a widget provide a visualization or other analysis of data from the data corpus 160 (e.g., a "data visualization"). In some example embodiments, widgets may be used to visualize data generated from APls. When the widget is viewed, it may access real-time data (e.g., prices of one or more specified assets) and provide a visualization of the retrieved data according to one or more rules. Widgets can include a wide range of charts and tables. The widget may also include hard coded information, such as information to aid in the interpretation of the visualized data. When a user creates a new widget, it may be added to the widget datastore 350. [0073] Thus, the widget discover module 340 can compare the vector representing the natural language request to the enhanced vectors representing the data visualizations. The widget discover module 340 generates a similarity score (e.g., cosine similarity) quantifying the similarity between the natural language request and the widget title based on their corresponding vectors. The widget discover module 340 may then use the similarity scores for each data visualization to select widgets for providing to the client device. Different criteria are possible. For example, the widget discover module 340 may select the ten highest-ranked widgets, or all widgets for which the similarity score exceeds a threshold, etc. In some instances, the widget discover module 340 may rank the widgets based on their score.) of the data element (Faonte [0063], [0076] e.g. [0076] The analytics module 124 may provide the search results (e.g., the selected widgets) to a requesting client device 110 in a number of ways. For instance, the analytics module 124 may provide the appropriate executables to execute each of the widgets locally on the client device 110, provide an option for the user of the client device 110 to select a widget to execute on the network system 120, or provide the location of the widget in the environment 100 such that the client device 110 can access and execute the widget. Once a user receives search results, the user may select one or more of the widgets to view them within this context. In some embodiments, the user may add selected widgets to a dashboard or favorites list to enable quick recall of these widgets at a later time);
rendering, by the viewing tool, the visualization in a first viewer section of the user interface (Faonte [0056] e.g. [0056] The application 210 is software that executes on the client device 110 to enable interaction with the analytics module 124. The application 210 may include a communications module 212 and a rendering engine 214. The communications module 212 sends requests for widgets 142 and/or Apls 132 (e.g., a payload request) to the network system 120 over the network 170 and receives/processes search results and data for providing selected widgets 142 and/or APls 132 (e.g., a payload response). The rendering engine 214 causes the client device 110 to display various visualizations provided by the widgets 142 and or APls 132. The rendering engine 214 may interact with or be executed by one or more graphics processing units (GPUs) to generate the visualizations. The local datastore 220 includes one or more computer-readable media that store the data used by the client device 110. For example, the local datastore 220 may include cached copies of data used by the widgets 142 and or APls 132.); and
monitoring the first viewer section for user interactions to detect selection of a second widget, wherein the second widget embeds a second reference to a second data element.
Therefore, it would have been obvious to one of ordinary skill in the art at the time of the effective filing date of the invention, in view of the teachings of Sheikh and Faonte, to provide a system that combines the efficiency of small language models with the accuracy of large language models in a single architecture specifically designed for API orchestration systems (Faonte [0005]).
10. With respect to claim 3,
Sheikh further discloses
identifying a second viewer type (Sheikh [0077] e.g. types of widgets) corresponding to the second data element (Sheikh [0131], [0148], [0158] e.g. viewer; viewing);
invoking a second viewing tool corresponding to the second viewer type to generate a second visualization of the second data element (Sheikh [0131], [0148], [0158] e.g. viewer; viewing); and
rendering (Sheikh [0076], [0079] – [0080], [0089] – [0090], [0151], [0162] e.g. rendered/rendering), by the second viewing tool, the second visualization (Sheikh [0086], [0162] e.g. a visual representation for display) in a second viewer section of the user interface.
11. With respect to claim 7,
Sheikh further discloses
receiving, by the LLM-powered search engine, a natural language query from a conversational interface (Sheikh [0048] e.g. conversational-type interface), wherein the conversational interface is the first section of the user interface (Sheikh Abstract, [0037], [0042], [0050], [0057], [0216] e.g. [0037] For example, embodiments of the application may enable an end user to easily record conversations with patients, dictate in natural language, generate patient notes, populate patient records, request and receive patient information, fill prescriptions, create or have automatically created task and event reminders, and receive associated notifications. [0042] In some implementations, the responses can be natural language responses and/or graphical responses … and subsequently provide a response to the user which may be or may include a textual or audible natural language response. In one example, a user may utilize the clinical automation service (110c) to perform various clinical tasks via natural language-based conversations therewith); and
generating, by the LLM-powered search engine, the response comprising the natural language summary, the data payload (Sheikh [0107] e.g. [0107] For example, the payload may include a natural language response to a query (e.g., a request for information), which may initiate further conversation between the healthcare provider and the digital assistant 1006), and the action recommendation (Sheikh [0040], [0046], [0046], [0078], [0080], [0093], [0098], [0127] – [0128], [0150] e.g. actions suggested, action suggestions/buttons – [0093] The dictation service 212 may be activated by, for example, engaging (e.g., selecting/clicking) an action button of the client application home screen or another widget that may be provided and displayed for the same purpose. As represented in FIG. 6, such an action button may be configured as a dictation mode initiation button. …." [0127] Another sequence flow can result from an end user activating and entering the dictation mode of operation from the mobile computing device 1104. For example, the end user may click on a dictation widget (e.g., action button) on the user interface 1134 of the mobile computing device 1104. [0128] For example, with respect to audio capture and wake word detection, the mobile client application 1102 can include additional widgets (e.g., action buttons) for controlling actions such as, without limitation, starting and stopping dictation, navigating form fields, pasting dictation box contents while in dictation mode, starting the clinical automation (assistant) mode by clicking a button rather than uttering a wake word; and muting the microphone. [0150] For example, this could be either a user interface where a healthcare provider can view the details of the notification or it may be some actions suggested by the digital assistant 1202 based on the notification).
12. Claims 12, 14 and 18 are same as claims 1, 3 and 7 and are rejected for the same reasons as applied hereinabove.
13. Claim 20 is same as claim 1 and is rejected for the same reasons as applied hereinabove.
14. Claims 2 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Sheikh in view of Faonte, and further in view of Jirak et al (U.S. 11537366 B1 hereinafter, “Jirak”).
15. With respect to claim 2,
Although Sheikh and Faonte combination substantially teaches the claimed invention, they do not explicitly indicate
identifying a nested data element, wherein the nested data element is included in the data element;
adding a nested reference to the nested data element; and
generating the visualization of the data element, wherein the visualization further comprises a nested widget, wherein the nested widget embeds the nested reference to the nested data element.
Jirak teaches the limitations by stating
identifying a nested data element, wherein the nested data element is included in the data element;
adding a nested reference to the nested data element; and
generating the visualization of the data element, wherein the visualization further comprises a nested widget, wherein the nested widget embeds the nested reference to the nested data element (Jirak col. 8 lines 39 – 63 e.g. (33) The elements tag defines an ordered array of widget elements included in a panel widget or a container widget. A panel widget type extends a container widget type to include a title and to be toggleable. Using the elements tag any number of additional panel widgets, container widgets, or UI widget renderers can be nested based on the UI functionality defined for UI application 122. The elements array of any contained UI Widget Renderer defines an ordered array of any non-container (or panel, since it extends container) defined in the widget library. For example, a panel widget may include a container widget that further includes a UI Widget renderer which contains additional widgets having specified widget types. (34) For example, the illustrative ErrorFormPanel class included in Appendix A Includes an array of elements that includes a widget renderer that has its own array of elements that includes a numeric input widget and a radio button group widget. An elements array is associated with each panel/container to create one or more panel/containers and/or widget renderers associated with each panel/container where each panel/container may further include another nested panel/container with an additional one or more widget renderers and/or one or more panels/containers. Each widget renderer will contain one or more non-panel/container widgets. elements:).
Therefore, it would have been obvious to one of ordinary skill in the art at the time of the effective filing date of the invention, in view of the teachings of Sheikh, Faonte and Jirak, to provide a system that combines the efficiency of small language models with the accuracy of large language models in a single architecture specifically designed for API orchestration systems (Faonte [0005]).
16. Claim 13 is same as claim 2 and is rejected for the same reasons as applied hereinabove.
17. Claims 4-5, 8-9, 15-16 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Sheikh in view of Faonte, and further in view of MIller et al (U.S. 12235865 B1 hereinafter, “MIller”).
18. With respect to claim 4,
Although Sheikh and Faonte combination substantially teaches the claimed invention, they do not explicitly indicate
identifying a schema type associated with the data element;
selecting the viewing tool based on a mapping between the schema type and the viewer type; and
executing the viewing tool to generate the visualization of the data element.
MIller teaches the limitations by stating
identifying a schema type associated with the data element;
selecting the viewing tool based on a mapping between the schema type and the viewer type; and
executing the viewing tool to generate the visualization of the data element (Miller col. 15 line 48 – col. 16 line 9 e.g. (57) FIG. 6 illustrates that, in some implementations, in the configuration/apply stage, a mapper 602 maps schemas 604 owned or served by a data visualization application 230 to a schema 606 (e.g., a Salesforce® flow or an external service) to create a workflow action. In some implementations, the schemas 604 include domains of each data element that the data visualization application 230 (or the data visualization server 300) can expose as triggers for the workflow action. In some implementations, as illustrated in FIG. 6, the schemas 604 include datapoints, dashboards, filters, marks, data, extensions (e.g., APls and events), site, user, workbook, views, Tableau server events, random Tableau constants, and Tableau content management service (CMS) as structured metadata. In some implementations, the schemas 606 fetch or register (620) actions from an external system holding one or more business process automation applications 622. (58) In some implementations, the mapper 602 maps attributes (e.g., data elements, data fields, data values, and data marks) of the schemas 604 to respective parameters of one or more mapping templates 608 (e.g., predefined action templates). The mapping template 608 specifies the inputs (from the data visualization application and/or the data dashboard) that are needed for the action. In some implementations, the computing device uses the mapping templates to form a builder for unmapped data (610) in the execution stage.).
Therefore, it would have been obvious to one of ordinary skill in the art at the time of the effective filing date of the invention, in view of the teachings of Sheikh, Faonte and MIller, to provide a system that combines the efficiency of small language models with the accuracy of large language models in a single architecture specifically designed for API orchestration systems (Faonte [0005]).
19. With respect to claim 5,
MIller further discloses wherein the corresponding widget of the reference to the data element of the data payload comprises a preview (Miller figures 8A-C, F-I, K-N e.g. preview) of the visualization of the data element.
20. With respect to claim 8,
Sheikh further discloses
displaying the natural language summary in a conversational interface, wherein the conversational interface is the first section of the user interface, and wherein the natural language summary includes a reference to the action recommendation of the response, and wherein the action recommendation comprises a workflow (Sheikh [0096], [0170] e.g. workflow),
and monitoring the conversational interface to detect a selection of the reference.
MIller further discloses
displaying the natural language summary in a conversational interface, wherein the conversational interface is the first section of the user interface, and wherein the natural language summary includes a reference to the action recommendation of the response, and wherein the action recommendation comprises a workflow action (Miller col. 1 line 58 – col. 4 line 27 e.g. workflow action),
and monitoring the conversational interface to detect a selection of the reference.
21. With respect to claim 9,
MIller further discloses
receiving, from the conversational interface, the selection of the reference;
identifying a workflow type (Miller col. 13 lines 53-59 e.g. Flow Types) of the action recommendation;
invoking a workflow tool to perform a workflow corresponding to the workflow type, using the data payload, to obtain an output of the workflow tool;
displaying a second reference to the output of the workflow tool in the conversational interface, wherein the second reference includes a viewer type corresponding to the output of the workflow tool; and
monitoring the user interface to detect a selection of the second reference.
22. Claims 15-16 and 19 are same as claims 4-5 and 8-9 and are rejected for the same reasons as applied hereinabove.
23. Claims 6 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Sheikh in view of Faonte, and further in view of Angelides (U.S. 20180233235 A1 hereinafter, “Angelides”).
24. With respect to claim 6,
MIller further discloses wherein the data element comprises image data (Sheikh [0035], [0102], [0117], [0131], [0134], [0157] e.g. images), a database query (Sheikh [0107], [0124], [0141], [0150] e.g. query), database records (Sheikh [0035] - [0043], [0057] e.g. records), and document identifiers (Sheikh [0043] e.g. identifier).
Although Sheikh and Faonte combination substantially teaches the claimed invention, they do not explicitly indicate plot data.
Angelides teaches the limitations by stating wherein the data element comprises plot data (Angelides [0035] e.g. [0035] The structured data 210 is gathered and generally subjected to data extraction analytic programs residing within the IMS 200 and/or the processing unit 120. Typically, the data extraction programs employed for the structured data identifies and maps key data elements, links related data, plots data over time and stores the data in a structural database).
Therefore, it would have been obvious to one of ordinary skill in the art at the time of the effective filing date of the invention, in view of the teachings of Sheikh, Faonte and Angelides, to provide a system that combines the efficiency of small language models with the accuracy of large language models in a single architecture specifically designed for API orchestration systems (Faonte [0005]).
25. Claim 17 is same as claim 6 and is rejected for the same reasons as applied hereinabove.
26. Claims 10-11 are rejected under 35 U.S.C. 103 as being unpatentable over Sheikh in view of Faonte, and further in view of Saikia et al (U.S. 20250094735 A1 hereinafter, “Saikia”).
27. With respect to claim 10,
Although Sheikh and Faonte combination substantially teaches the claimed invention, they do not explicitly indicate
prior to rendering the natural language summary, iteratively performing:
validating the data payload with respect to the action recommendation to obtain a validation result; and
responsive to the validation result being an error result, performing operations comprising:
generating, by a correction LLM, a correction prompt based on the error result and the response,
processing, by the LLM-powered search engine, the correction prompt to generate a second response;
for a pre-defined number of iterations.
Saikia teaches the limitations by stating
prior to rendering the natural language summary, iteratively performing:
validating the data payload with respect to the action recommendation to obtain a validation result; and
responsive to the validation result being an error result, performing operations comprising:
generating, by a correction LLM, a correction prompt based on the error result and the response,
processing, by the LLM-powered search engine, the correction prompt to generate a second response;
for a pre-defined number of iterations (Saikia [0004], [0006], [0010], [0019] – [0020], [0132], [0139], [0162], [0169], [0176], [0184], [0196] – [0203] e.g. iteratively … LLM … validating whether the response payload follows the reasoning or explanation … correct the error or invalid data … iteration-termination criterion/In some instances, this process is repeated multiple times, where-for each iteration-a different GenAI Model 505 is selected to evaluate the new request payload and may be omitted from the set of GenAI Model 505 used to generate the potential response payload options).
Therefore, it would have been obvious to one of ordinary skill in the art at the time of the effective filing date of the invention, in view of the teachings of Sheikh, Faonte and Saikia, to provide a system that combines the efficiency of small language models with the accuracy of large language models in a single architecture specifically designed for API orchestration systems (Faonte [0005]).
28. With respect to claim 11,
Saikia further discloses
responsive to the pre-defined number of iterations being performed, and the validation result being the error result, generating an error response; and
displaying the error response in a conversational interface of the user interface (Saikia [0004], [0006], [0010], [0019] – [0020], [0132], [0139], [0162], [0169], [0176], [0184], [0196] – [0203] e.g. iteratively … LLM … validating whether the response payload follows the reasoning or explanation … correct the error or invalid data … iteration-termination criterion/In some instances, this process is repeated multiple times, where-for each iteration-a different GenAI Model 505 is selected to evaluate the new request payload and may be omitted from the set of GenAI Model 505 used to generate the potential response payload options).
Conclusion
The prior art made of record, listed on form PTO-892, and not relied upon, if any, is considered pertinent to applicant's disclosure.
29. The examiner requests, in response to this office action, support be shown for language added to any original claims on amendment and any new claims. That is, indicate support for newly added claim language by specifically pointing to page(s) and line no(s) in the specification and/or drawing figure(s). This will assist the examiner in prosecuting the application.
30. When responding to this office action, Applicant is advised to clearly point out the patentable novelty which he or she thinks the claims present, in view of the state of the art disclosed by the reference cited or the objections made. He or she must also show how the amendments avoid such references or objections See 37 CFR 1.111(c).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SyLing Yen whose telephone number is 571-270-1306. The examiner can normally be reached on Mon-Fri 8:30am - 5:00pm.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Sanjiv Shah can be reached at 571-272-4098. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/SYLING YEN/Primary Examiner, Art Unit 2166
July 27, 2026
Prosecution Insights