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
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 5/11/2026 has been entered.
Arguments and amendments filed 5/11/2026 have been examined.
Claims 1, 9 and 17 have been amended.
In this Office Action, Claims 1-23 are currently pending.
Examiner’s Note
The Examiner appreciates Applicant’s continued attention to important issues.
Please note the additional non-abstract idea concerns regarding 35 USC 101:
“It is suggested that claim 9 be amended to recite a “non-transitory” computer readable medium to overcome this rejection.” (for claims 9-16)
and
“claim(s) 1 does not recite statutory computer hardware/processors (only generic methods without even generically described computer processing elements, which can be resolved by amending the claims to recite a “computer-implemented method”)” (for claim 1-8).
Appropriate correction is requested.
Response to Arguments
Applicant’s arguments with respect to claim(s) and the prior art rejection under 35 USC 103 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.
Applicant's arguments filed concerning rejections under 35 USC 101 have been fully considered but they are not persuasive.
As to the argument: “a. The claims are patent eligible under the MPEP.”
“…However, applicants cannot ascertain the basis of the rejection as the Office Action fails to do more then to assert that the recited claims are generic and that the human activity is "commercial or legal interactions. Id In contrast, the claim 1 includes limitations pertaining to a particular arrangement of elements to implement the recited approach to extracting metadata from content on a content management system using an LLM and metadata templates - where the LLM prompt is generated based at least in part upon parameters (in a metadata template) and is sent to an LLM with a selection based on at least the metadata template of one or more portions of the content from which the metadata is to be extracted.
Therefore, since the claims do not per se or on their own recite any of the enumerated
methods for organizing human activity, Applicant respectfully submits that the claims do not corresponds to an abstract idea as a method of organizing human activity.”
The Examiner respectfully disagrees.
Please note the relevant and recent decision, Recentive Analytics, Inc. v. Fox Corp.
Where the Federal Circuit issued a precedential decision in Recentive Analytics
(decision available via https://www.cafc.uscourts.gov/opinions-orders/23-2437.OPINION.4-18-
2025_2500790.pdf ) invalidating generic machine learning claims under Section 101 via the
two-step Alice test patents using machine learning models. The Federal Circuit acknowledged
that “[m]achine learning is a burgeoning and increasingly important field and may lead to patent eligible improvements in technology.” Nevertheless, the Federal Circuit held that “patents that
do no more than claim the application of generic machine learning to new data environments,
without disclosing improvements to the machine learning models to be applied, are patent
ineligible under § 101.”
In this case, the application of machine learning (as asserted above, using the “the recited approach to extracting metadata from content on a content management system using an LLM and metadata templates”) is completely generic and unspecific, i.e. the machine learning limitations only generate/provide for generic metadata, i.e. “extract the metadata from the selected one or more portions of the content” (see claim 1) as a result of generic “generating an LLM prompt”/” sending the LLM prompt”, where Applicant fails to explain or even hint as to what process or technique provides for “generating” the generic “LLM prompt” and thus as recited in Recentive Analytics, the claimed machine learning limitations of the current claims “do no more than claim the application of generic machine learning to new data environments”; thus the above argument is moot and the rejection under 35 USC 101 remains.
As to the argument:
“Here, the Office Action at least at page 8 asserts that the claim recites abstract ideas
under the mental processes category. Applicant respectfully disagrees. The current claims do not fall within this category since the claims recite numerous limitations that are expressly link to the underlying computing elements (e.g., the content management system, the LLM, and the metadata store) and operates on the contents using the metadata templates to generate an LLM prompt that is sent to and executed by an LLM before placing metadata extracted from that content as a result of executing the LLM prompt in a metadata store. In fact, the recited approach discloses concepts that must be performed by at least a computing system such as a content management system with the LLM, and the metadata store, and cannot be performed by the human mind. See CyberSource, 654 F.3d at 1376, 99 USPQ2d at 1699 (distinguishing Research Corp. Techs. v. Microsoft Corp., 627 F.3d 859, 97 USPQ2d 1274 (Fed Cir. 2010), and SiRF Tech., Inc. v. Int'l Trade Comm 'n, 601 F.3d 1319, 94 USPQ2d 1607 (Fed Cir. 2010), as directed to inventions that '' could not, as a practical matter, be performed entirely in a human' s mind''); and Synopsys., 839 F.3d at 1148, 120 USPQ2d at 1481 (a claim to a specific data encryption method for computer communication involving a several-step manipulation of data could not practically be performed in the human mind - which is analogous to the several steps required here including at least the execution of the LLM prompt). As indicated above, a process that cannot practically be performed in the human mind is not a mental process. Id”
The Examiner respectfully disagrees.
To the contrary, the claim language does not provide any functionalities in the claims that could
not be done mentally and also does not provide any functionalities of determination and
identification that cannot be done mentally. The claim language also does not provide any
improvements to the technologies in the claim language.
MPEP 2106.04(a) states the following:
The courts consider a mental process (thinking) that "can be performed in the human
mind, or by a human using a pen and paper" to be an abstract idea. CyberSource Corp.
v. Retail Decisions, Inc., 654 F.3d 1366, 1372, 99 USPQ2d 1690, 1695 (Fed. Cir. 2011 ).
As the Federal Circuit explained, "methods which can be performed mentally, or which
are the equivalent of human mental work, are unpatentable abstract ideas the 'basic
tools of scientific and technological work' that are open to all."' 654 F.3d at 1371, 99
USPQ2d at 1694 (citing Gottschalk v. Benson, 409 U.S. 63, 175 USPQ 673 (1972)).
See also Mayo Collaborative Servs. v. Prometheus Labs. Inc., 566 U.S. 66, 71, 101
USPQ2d 1961, 1965 (2012) ('"[M]ental processes[] and abstract intellectual concepts
are not patentable, as they are the basic tools of scientific and technological work"'
(quoting Benson, 409 U.S. at 67, 175 USPQ at 675)); Parker v. Flook, 437 U.S. 584,
589, 198 USPQ 193, 197 (1978) (same).
Accordingly, the "mental processes" abstract idea grouping is defined as
concepts performed in the human mind, and examples of mental processes include
observations, evaluations, judgments, and opinions.
The claimed is directed to an abstract idea because the following element merely
involve observations, evaluations, judgments, and opinions with respect to electronic
data:
"executing the LLM prompt at an LLM to extract the metadata from the selected one or
more portions of the content; " (see claim 1)
recites a mental process as an evaluation or judgement, one can mentally determine “metadata” using generic “portions of content” by simply looking at a document collection/data to pick/suggests generic metadata from generic document portions, i.e. this is
simply using a text portions to extract/highlight desired information.
Additionally please note the relevant and recent decision, Recentive Analytics, Inc. v. Fox Corp.
Where the Federal Circuit issued a precedential decision in Recentive Analytics
(decision available via https://www.cafc.uscourts.gov/opinions-orders/23-2437.OPINION.4-18-
2025_2500790.pdf ) invalidating generic machine learning claims under Section 101 via the
two-step Alice test patents using machine learning models. The Federal Circuit acknowledged
that “[m]achine learning is a burgeoning and increasingly important field and may lead to patent eligible improvements in technology.” Nevertheless, the Federal Circuit held that “patents that
do no more than claim the application of generic machine learning to new data environments,
without disclosing improvements to the machine learning models to be applied, are patent
ineligible under § 101.”
In this case, the application of machine learning (here, a generic “LLM” for generically “executing the LLM prompt”, for extracting metadata) is completely generic and unspecific, and thus as recited in Recentive Analytics, the claimed machine learning limitations i.e. the “large language model” of the current claims “do no more than claim the application of generic machine learning to new data environments”; thus the above argument is moot and the rejection under 35 USC 101 remains.
As to the argument:
“For example, independent claims 1, 9, and 17 recite at least the following:
maintaining content within a content management system;
identifying a metadata template that stores parameters about
metadata to be extracted from the content;
generating an LLM prompt based at least in part upon the
parameters about the metadata to be extracted from the content;
sending the LLM prompt and a selection based on at least the
metadata template of one or more portions of the content from which the
metadata is to be extracted;
executing the LLM prompt at an LLM to extract the metadata from
the selected one or more portions of the content; and
placing the metadata extracted from the content into a metadata
store.
(emphases added)
Based upon the above, Applicant respectfully submits that the claims do not recite matter within the enumerated groupings of abstract ideas, and therefore should not be treated as reciting an abstract idea.
Furthermore, the claims integrate any allege abstract idea into a practical application that is patent eligible. See MPEP § 2106. For instance, Limitations the courts have found indicative that an additional element ( or combination of elements) may have integrated the exception into a practical application include: An improvement in the functioning of a computer, or an improvement to other technology or technical field, as discussed in MPEP §§ 2106.04(d)(l) and 2106.05(a)..”;
The Examiner respectfully disagrees.
Applicant asserts above that: “Applicant respectfully submits that the claims do not recite matter within the enumerated groupings of abstract ideas, and therefore should not be treated as reciting an abstract idea. Furthermore, the claims integrate any allege abstract idea into a practical application that is patent eligible”; however, nowhere does Applicant provide and specific details or explanation as to why claim limitations such as: “executing the LLM prompt at an LLM to extract the metadata from the selected one or more portions of the content” (see above) would ever be considered to constitute a “practical application”. Rather, Applicant simply copies claim language from the application and simply asserts that any claim language is a “practical application”, without any specific explanation(s). Thus as Applicant has failed to explain their position with regards to the assertion above, the Examiner remains unconvinced and the rejection under 35 USC 101 remains.
As to the argument that:
“Furthermore, the claims integrate any allege abstract idea into a practical application that is patent eligible. See MPEP § 2106. For instance, Limitations the courts have found indicative that an additional element ( or combination of elements) may have integrated the exception into a practical application include: An improvement in the functioning of a computer, or an improvement to other technology or technical field, as discussed in MPEP §§ 2106.04(d)(l) and 2106.05(a).
Therefore, even if it is argued that the claims are directed to a judicial exception (which
they are not as discussed above), Applicant respectfully notes that the claims very clearly integrate the claim recitations into a practical application. Without repeating all of the arguments provided above, it is noted that the claims recite the practical application of an approach to process content in a content management system using metadata templates to generate an LLM prompt, sending that LLM prompt and a selection based on at least the metadata template of one or more portions of the content from which the metadata is to be extracted to the LLM, and executing that prompt with the LLM is a practical application at least because it improves the functioning of a computer, or an improvement to other technology or technical field, at least because it addresses issue related to context limits for LLMs as discussed in the present Application at least at ,i,i [0093 ], [0 102], and [0 103].
Since the claims as a whole integrate into a practical application of any possible
exception, Applicant respectfully submits that the claims recite eligible subject matter.”;
The Examiner respectfully disagrees.
Applicant asserts above that the recites claim limitations above “…is a practical application at least because it improves the functioning of a computer, or an improvement to other technology or technical field, at least because it addresses issue related to context limits for LLMs”.
Firstly, nowhere do the claims even mention “context limits”. Thus, In response to applicant's argument that the references fail to show certain features of the invention, it is noted that the features upon which applicant relies (i.e., “context limits”) are not recited in the rejected claim(s). Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993). Thus this argument is moot and the rejection remains.
Additionally, nowhere does applicant explain or even hint as to why “executing that prompt with the LLM” (see above) would provide for the perceived benefit of “addresses issue related to context limits for LLMs”. Nor does Applicant bother to specifically describe what a “issue related to context limits for LLMs” would specifically be, i.e. what are these generic “issues”, specifically, that are being addressed? Thus this argument is moot, the Examiner remains unconvinced, and the rejection remains.
As to the argument: “b. The claims are not abstract per DDR Holdings”
Applicant asserts:
“the patents were related to approaches for keeping a user that had clicked an ad on a website on the website instead of taking the user to a different website…. Here, as was the case in DDR Holdings, the present application addresses a challenge particular to technological (e.g., context limits of LLMs).”
The Examiner respectfully disagrees.
Nowhere does Applicant explain why the current claim limitations of “executing the LLM prompt at an LLM to extract the metadata from the selected one or more portions of the content;” (see claim 1, for example) would be relevant to the subject matter at hand in the DDR Holdings opinion, namely “approaches for keeping a user that had clicked an ad on a website on the website instead of taking the user to a different website” (see above). Thus this argument is moot, the Examiner remains unconvinced and the rejection remains.
As to the argument: “c. Ex parte Desjardins (Appeal No. 2024-000567)”
Applicant asserts:
“Applicant would like to bring the follow to the examiner's attention: Ex Parte
Desjardins, Appeal No. 2024-000567 (PTAB September 26, 2025, Appeals Review Panel
Decision) (precedential as of November 4th 2025). This decision is of particular relevance here
as the claims at issue here and in the decision address machine learning improvements which the panel (which includes the director of the USPTO John Squires) found to be subject matter
eligible under 35 U.S.C. § 101.
In particular, Ex Parte Desjardins recites that the specification is directed towards
"improvements in training the machine learning model" which are subject matter eligible if the claim reflects at least one of these "improvements". Id at page 8 last paragraph ("[T]he
Specification, ... identifies improvements in training the machine learning model itself ... is
insufficient ... absent a subsequent determination that the claim itself reflects the disclosed
improvement. ... we are persuaded that the claims reflect such an improvement.'' There, the
review panel found multiple improvements incorporated into the claims including: learn new
tasks while protecting knowledge about previous tasks, use of less system resources, and a
reduction in system complexity. Id at pages 8-9 ("For example, one improvement identified in
the Specification is to "effectively learn new tasks in succession whilst protecting knowledge
about previous tasks." Spec. ,i 21. The Specification also recites that the claimed improvement
allows artificial intelligence (AI) systems to "us[ e] less of their storage capacity" and enables
"reduced system complexity." Id ''). The indicated paragraph is reproduced below in full.
Paragraph 21 of the Specification, which the Appellant cites,
identifies improvements in training the machine learning model itself Of
course, such an assertion in the Specification alone is insufficient to
support a patent eligibility determination, absent a subsequent
determination that the claim itself reflects the disclosed improvement. See
MPEP § 2106.0S(a) (citing Intellectual Ventures I LLC v. Symantec Corp.,
838 F.3d 1307, 1316 (Fed. Cir. 2016)). Here, however, we are persuaded
that the claims reflect such an improvement. For example, one
improvement identified in the Specification is to "effectively learn new
tasks in succession whilst protecting knowledge about previous tasks."
Spec. ,i 21. The Specification also recites that the claimed improvement
allows artificial intelligence (AI) systems to "us[e] less of their storage
capacity" and enables "reduced system complexity." Id When evaluating
the claim as a whole, we discern at least the following limitation of
independent claim 1 that reflects the improvement: "adjust the first values
of the plurality of parameters to optimize performance of the machine
learning model on the second machine learning task while protecting
performance of the machine learning model on the first machine learning
task." We are persuaded that constitutes an improvement to how the
machine learning model itself operates, and not, for example, the
identified mathematical calculation.
Ex Parte Desjardins page 8-9 (emphasis added)
Applicant respectfully assert that the present claims also incorporate improvements to
machine learning into the claims at least with regard to the specific way to generate an LLM
prompt based on parameters from a metadata template as discussed in the prior section where
the claims are directed to a technological problem of at least addressing context limits for LLMs
as discussed in the present Application at least at ,-i,i [0093 ], [0102], and [0103]. In particular,
the claims recite an approach that allows artificial intelligence (AI) systems such as LLMs to
"us[e] less of their storage capacity" and enables "reduced system complexity."
Therefore, even if it is argued that the claims are directed to a judicial exception,
Applicant respectfully notes that the claims very clearly integrate the claim recitations into a
practical application.”
The Examiner respectfully disagrees.
Nowhere does Applicant explain why the current claim limitations of “executing the LLM prompt at an LLM to extract the metadata from the selected one or more portions of the content;” (see claim 1, for example) would be relevant to the subject matter at hand in the Ex parte Desjardins opinion, namely “adjust the first values of the plurality of parameters to optimize performance of the machine learning model on the second machine learning task while protecting performance of the machine learning model on the first machine learning task” and “... identifies improvements in training the machine learning model itself” (see above). Thus this argument is moot, the Examiner remains unconvinced and the rejection remains.
For example, nowhere in the claim language or in applicant’s arguments above does applicant specifically explain why limitations such as “executing the LLM prompt at an LLM to extract the metadata from the selected one or more portions of the content;” (see claim 1, for example) would provide for the asserted “identifies improvements in training the machine learning model itself” present in Ex parte Desjardins. Applicant generic execution of a generic “LLM prompt” simply does not provide for any “improvements in training the machine learning model itself”, as required in the Ex parte Desjardins decision, thus again this argument is moot, the Examiner remains unconvinced and the rejection remains.
As to the argument: “d. The claims are not abstract because they provide a specific implementation of a solution to a problem in the software arts as interpreted under Enfish LLC.”
The Examiner respectfully disagrees.
Nowhere does Applicant explain why the current claim limitations of “executing the LLM prompt at an LLM to extract the metadata from the selected one or more portions of the content;” (see claim 1, for example) would be relevant to the subject matter at hand in the Enfish LLC v. Microsoft Corp. opinion, namely “claims directed to an improvement to the way a computer stores and retrieves data through use of a specific implementation of a new data structure” (see Enfish LLC v. Microsoft Corp.). Thus this argument is moot, the Examiner remains unconvinced and the rejection remains.
As to the argument: “e. The claims contain an "inventive concept" and thus is not rendered ineligible under Digitech”
The Examiner respectfully disagrees.
Nowhere does Applicant explain why the current claim limitations of “executing the LLM prompt at an LLM to extract the metadata from the selected one or more portions of the content;” (see claim 1, for example) would be relevant to the subject matter at hand in the Digitech. opinion, namely, limiations “directed to the generation and use of an “improved device profile” that describes spatial and color properties of a device within a digitalimage processing system. In general, digital image pro-cessing involves electronically capturing an image of a scene with a “source device,” such as a digital camera, altering the image in a desired fashion, and transferring the altered image to an “output device,” such as a color printer.” (see page 5 of Digitech Image Technologies, LLC v. Electronics for Imaging, Inc. 2014 U.S. App. LEXIS 13149 at 12 (Fed. Cir. 2014.). Thus this argument is moot, the Examiner remains unconvinced and the rejection remains.
As to the argument: “f. The claims contain an "inventive concept" and thus is not rendered ineligible under Bascom”
The Examiner respectfully disagrees.
Nowhere does Applicant explain why the current claim limitations of “executing the LLM prompt at an LLM to extract the metadata from the selected one or more portions of the content;” (see claim 1, for example) would be relevant to the subject matter at hand in the Bascom Glob. Internet Servs., Inc. v. AT&T Mobility LLC. opinion, namely “a filtering scheme using a local filtering element and a remote filtering element.”; and “The claimed invention is able to provide individually customizable filtering at the remote ISP server by taking advantage of the technical capability of certain communication networks.” (see See Bascom Glob. Internet Servs., Inc. v. AT&T Mobility LLC, No. 2015-1763, at 15 (Fed. Cir. June 27, 2016), at page 5.). Thus this argument is moot, the Examiner remains unconvinced and the rejection remains.
In summary, simply nowhere does Applicant address the previously noted recent and relevant decision Recentive Analytics, Inc. v. Fox Corp. (CAFC Case: 23-2437) explaining that “we hold only that patents that do no more than claim the application of generic machine learning to new data environments, without disclosing improvements to the machine learning models to be applied, are patent ineligible under § 101”); where here Applicant is claiming a completely generic and unspecific “LLM” in the limitation “executing the LLM prompt at an LLM to extract the metadata” see claim 1 for example.
Again, the test is not whether the claim is confined to a particular field of use or technological environment, see Intellectual Ventures ILLC v. Capital One Bank (USA), 792 F.3d 1363, 1366 (Fed. Cir. 2015) (“[a]n abstract idea does not become nonabstract by limiting the invention to a particular field of use or technological environment”). The relevant question, even at the first step of the Mayo/Alice analysis, is “whether the claims are directed to an improvement in computer functionality versus being directed to an abstract idea.” Enfish, LLC v. Microsoft Corp., 822 F.3d 1327, 1335 (Fed. Cir. 2016).
Here, the invention uses computer technology, but the Specification describes the claimed
solution as a scheme in collecting, storing and managing electronic records over time (see for
example specification para. [0149] “Various implementations of database 832 comprise storage media organized to hold a series of records or files such that individual records or files are accessed using a name or key (e.g., a primary key or a combination of keys and/or query clauses).”). And collecting, storing, and organizing information describes the abstract idea to
which Appellants’ claims are directed, not an improvement in computer technology. Erie
Indemnity Co., 850 F.3d at 1328 (“the heart of the claimed invention lies in creating and using
an index to search for and retrieve data ... an abstract concept”).
Thus, as the test for patent eligibility is not whether the claim is confined to a particular field of
use or technological environment, (see, again Intellectual Ventures ILLC v. Capital One Bank
(USA)), the Examiner is unconvinced the claims are directed to eligible subject matter and thus
this argument is moot.
Furthermore, Applicant again fails to address statutory subject matter rejections under 35 USC 101 regarding claims 1-8 (regarding the lack of statutory computer hardware/processors) and claims 9-16 (regarding explicitly claiming non-transitory media), thus these claims remain rejected under 35 USC 101. The Examiner will continue to direct Applicants attention to the “Examiners Note” on the first page of the Office Action to hopefully make progress on this specific issue.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-23 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
The term “sending” in claims 1, 9 and 17 is/are a relative term which renders the claim indefinite. The term “sending” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention.
For example, claims 1, 9 and 17 recite:
“sending the LLM prompt and a selection based on at least the metadata template of one or more portions of the content from which the metadata is to be extracted;”
However, nowhere do the claims explain where or what the “LLM prompt and a selection” are being sent to; for example, is the “LLM prompt and a selection” being sent to the aforementioned “content management system”?
As the scope of this claim limitation is impossible to determine, these claims are rejected under 35 USC 112. As the dependent claims do not resolve the defects inherited from the parent claims, these claims are also rejected under 35 USC 112.
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.
Please note, Claims 1-8 are rejected under 35 U.S.C. 101 because the claimed invention is
Directed to non-statutory subject matter. The claim(s) does/do not fall within at least one of the
four categories of patent eligible subject matter because independent claim(s) 1 does not recite
statutory computer hardware/processors (only generic methods without even generically described computer processing elements, such as a “computer-implemented method”) without limitation and thus the claim(s) is/are directed to a signal per se and/or mere information in the form of data, and dependent claims 2-8 do not correct this deficiency.
See generally guidance on the New Form Paragraphs for Subject Matter Eligibility Rejections
under the 2019 Revised Patent Subject Matter Eligibility Guidance (¶ 7.05.01 Rejection, 35
U.S.C. 101, Nonstatutory (Not One of the Four Statutory Categories);
Available via:
https://www.uspto.gov/sites/default/files/documents/form_para_for_2019peg_20190108.pdf
Additionally, Claim 9 (as well as claim 10-16) is/are rejected under 35 U.S.C. 101 because the claimed invention is directed to nonstatutory subject matter. The claim does not fall within at least one of the four categories of patent eligible subject matter because the broadest reasonable interpretation of the “computer readable medium” encompasses signals per se. The specification discloses that the “computer readable medium” in para [0143] recites: “The term "computer readable medium" or "computer usable medium" as used herein refers to any medium that participates in providing instructions to data processor 807 for execution. Such a medium may take many forms including, but not limited to, non-volatile media and volatile media. Non-volatile media includes, for example, optical or magnetic disks such as disk drives or tape drives. Volatile media includes dynamic memory such as RAM.” (see Paragraph [0143]). A claim whose BRI covers both statutory and non-statutory embodiments embraces subject matter that is not eligible for patent protection and therefore is directed to non-statutory subject matter. See MPEP 2106.03(II). It is suggested that claim 9 be amended to recite a “non-transitory” computer readable medium to overcome this rejection.
Accordingly, Claim 9 fails to recite statutory subject matter under 35 U.S.C. 101; and claims 10-16 are also rejected as these claims do not correct the above noted deficiency.
Claims 1-23 are rejected under 35 U.S.C. 101 because the claimed invention is
directed to an abstract idea without significantly more.
Claim 1 recites: (Step 2a, Prong One)
placing the metadata extracted from the content into a metadata store.
The limitation of placing the metadata extracted from the content into a metadata store, 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. That is, other than reciting a generic content management system/metadata store, and a generic “LLM prompt/LLM” nothing in the claim element precludes the step from practically being performed in the mind. For example, but for the content management system language, “placing” in the context of this claim encompasses the user manually moving generic “metadata” using generic “extracted” steps of generic “content” steps using a generic “store”. Additionally, note the recent and relevant decision Recentive Analytics, Inc. v. Fox Corp. (CAFC Case: 23-2437) explaining that “we hold only that patents that do no more than claim the application of generic machine learning to new data environments, without disclosing improvements to the machine learning models to be applied, are patent ineligible under § 101”). Similarly, the limitation(s) of maintaining; identifying; generating, sending and executing 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. For example, but for the content management system/metadata store, and a generic “LLM prompt/LLM” language, maintaining; identifying; generating, and executing in the context of this claim encompasses the user manually receiving generic “content” and performing generic “identifying”; ”generating” and “extracting” steps. If a claim limitation, 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 (concepts
performed in the human mind (including an observation, evaluation, judgment, opinion)).
Further, these concepts also recite “Certain Methods of Organizing Human Activity”; (such as
commercial or legal interactions (including agreements in the form of contracts; legal
obligations; advertising, marketing or sales activities or behaviors; business relations) where
performing generic placing of extracted metadata of generic content using generic “identifying”; ”generating” and “extracting” steps is a method of human activity in commercial or legal interactions.
Accordingly, the claim recites an abstract idea.
(Step 2a, Prong Two)
This judicial exception is not integrated into a practical application. In particular, the claim only
recites one additional element – using a content management system/metadata store and a method to perform both the maintaining; identifying; generating, sending and executing; and placing steps. The content management system/metadata store and a method in both steps is recited at a high level of generality (i.e., as a generic content management system without a processor performing a generic computer function of “placing”) such that it amounts no more than mere instructions to apply the exception using a generic computer component.
Accordingly, this additional element does not integrate the abstract idea into a practical
application because it does not impose any meaningful limits on practicing the abstract idea.
The claim is directed to an abstract idea. The claim does not include additional elements that
are sufficient to amount to significantly more than the judicial exception.
(Step 2b)
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract
idea into a practical application, the additional element of a content management system/metadata store and a method to perform both the maintaining; identifying; generating, sending and executing; and placing steps 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. The claim(s) is/are not patent eligible.
Referring to claim 2, (Step 2a, Prong One) this further merely performs an additional abstract
mental step of “wherein the LLM prompt is generated and placed into the metadata template”.
(Step 2a, Prong Two)
This judicial exception is not integrated into a practical application. In particular, the claim only
recites the additional elements of “wherein the LLM prompt is generated and placed into the metadata template” steps to perform both the aforementioned maintaining; identifying; generating, sending and executing; and placing steps. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
(Step 2b)
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract
idea into a practical application, the additional element of using “wherein the LLM prompt is generated and placed into the metadata template” steps to perform both the aforementioned maintaining; identifying; generating, sending and executing; and placing steps 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.
The claim(s) is/are not patent eligible.
Referring to claim 3, (Step 2a, Prong One) this further merely performs an additional abstract
mental step of “wherein the LLM prompt is generated on a per-field basis in the metadata template”.
(Step 2a, Prong Two)
This judicial exception is not integrated into a practical application. In particular, the claim only
recites the additional elements of “wherein the LLM prompt is generated on a per-field basis in the metadata template” steps to perform both the aforementioned maintaining; identifying; generating, sending and executing; and placing steps. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
(Step 2b)
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract
idea into a practical application, the additional element of using “wherein the LLM prompt is generated on a per-field basis in the metadata template” steps to perform both the aforementioned maintaining; identifying; generating, sending and executing; and placing steps 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.
The claim(s) is/are not patent eligible.
Referring to claim 4, (Step 2a, Prong One) this further merely performs an additional abstract
mental step of “wherein a feedback process is performed to update the LLM prompt based at least in part upon actual values extracted for the metadata”.
(Step 2a, Prong Two)
This judicial exception is not integrated into a practical application. In particular, the claim only
recites the additional elements of “wherein a feedback process is performed to update the LLM prompt based at least in part upon actual values extracted for the metadata” steps to perform both the aforementioned maintaining; identifying; generating, sending and executing; and placing steps. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
(Step 2b)
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract
idea into a practical application, the additional element of using “wherein a feedback process is performed to update the LLM prompt based at least in part upon actual values extracted for the metadata” steps to perform both the aforementioned maintaining; identifying; generating, sending and executing; and placing steps 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.
The claim(s) is/are not patent eligible.
Referring to claim 5, (Step 2a, Prong One) this further merely performs an additional abstract
mental step of “wherein the feedback process is performed based at least in part upon a human update or an update from an LLM”.
(Step 2a, Prong Two)
This judicial exception is not integrated into a practical application. In particular, the claim only
recites the additional elements of “wherein the feedback process is performed based at least in part upon a human update or an update from an LLM” steps to perform both the aforementioned maintaining; identifying; generating, sending and executing; and placing steps. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
(Step 2b)
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract
idea into a practical application, the additional element of using “wherein the feedback process is performed based at least in part upon a human update or an update from an LLM” steps to perform both the aforementioned maintaining; identifying; generating, sending and executing; and placing steps 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.
The claim(s) is/are not patent eligible.
Referring to claim 6, (Step 2a, Prong One) this further merely performs an additional abstract
mental step of “wherein fields within the metadata template are grouped together for submission of related LLM prompts to an LLM”.
(Step 2a, Prong Two)
This judicial exception is not integrated into a practical application. In particular, the claim only
recites the additional elements of “wherein fields within the metadata template are grouped together for submission of related LLM prompts to an LLM” steps to perform both the aforementioned maintaining; identifying; generating, sending and executing; and placing steps. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
(Step 2b)
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract
idea into a practical application, the additional element of using “wherein fields within the metadata template are grouped together for submission of related LLM prompts to an LLM” steps to perform both the aforementioned maintaining; identifying; generating, sending and executing; and placing steps 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.
The claim(s) is/are not patent eligible.
Referring to claim 7, (Step 2a, Prong One) this further merely performs an additional abstract
mental step of “wherein dependencies are identified within the fields to group the fields together”.
(Step 2a, Prong Two)
This judicial exception is not integrated into a practical application. In particular, the claim only
recites the additional elements of “wherein dependencies are identified within the fields to group the fields together” steps to perform both the aforementioned maintaining; identifying; generating, sending and executing; and placing steps. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
(Step 2b)
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract
idea into a practical application, the additional element of using “wherein dependencies are identified within the fields to group the fields together” steps to perform both the aforementioned maintaining; identifying; generating, sending and executing; and placing steps 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.
The claim(s) is/are not patent eligible.
Referring to claim 8, (Step 2a, Prong One) this further merely performs an additional abstract
mental step of “wherein an AI agent is employed to generate and execute the LLM prompt to extract the metadata”.
(Step 2a, Prong Two)
This judicial exception is not integrated into a practical application. In particular, the claim only
recites the additional elements of “wherein an AI agent is employed to generate and execute the LLM prompt to extract the metadata” steps to perform both the aforementioned maintaining; identifying; generating, sending and executing; and placing steps. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
(Step 2b)
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract
idea into a practical application, the additional element of using “wherein an AI agent is employed to generate and execute the LLM prompt to extract the metadata” steps to perform both the aforementioned maintaining; identifying; generating, sending and executing; and placing steps 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.
The claim(s) is/are not patent eligible.
Claim 9 recites: (Step 2a, Prong One)
placing the metadata extracted from the content into a metadata store.
The limitation of placing the metadata extracted from the content into a metadata store, 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. That is, other than reciting a generic processor/medium, and a generic “LLM prompt/LLM” nothing in the claim element precludes the step from practically being performed in the mind. For example, but for the processor/medium language, “placing” in the context of this claim encompasses the user manually moving generic “metadata” using generic “extracted” steps of generic “content” steps using a generic “store”. Additionally, note the recent and relevant decision Recentive Analytics, Inc. v. Fox Corp. (CAFC Case: 23-2437) explaining that “we hold only that patents that do no more than claim the application of generic machine learning to new data environments, without disclosing improvements to the machine learning models to be applied, are patent ineligible under § 101”). Similarly, the limitation(s) of maintaining; identifying; generating; sending and executing 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. For example, but for the processor/medium, and a generic “LLM prompt/LLM” language, maintaining; identifying; generating, and executing in the context of this claim encompasses the user manually receiving generic “content” and performing generic “identifying”; ”generating” and “extracting” steps. If a claim limitation, 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 (concepts performed in the human mind (including an observation, evaluation, judgment, opinion)).
Further, these concepts also recite “Certain Methods of Organizing Human Activity”; (such as
commercial or legal interactions (including agreements in the form of contracts; legal
obligations; advertising, marketing or sales activities or behaviors; business relations) where
performing generic placing of extracted metadata of generic content using generic “identifying”; ”generating” and “extracting” steps is a method of human activity in commercial or legal interactions.
Accordingly, the claim recites an abstract idea.
(Step 2a, Prong Two)
This judicial exception is not integrated into a practical application. In particular, the claim only
recites one additional element – using processor/medium and a method to perform both the maintaining; identifying; generating; sending and executing; and placing steps. The processor/medium and a method in both steps is recited at a high level of generality (i.e., as a generic processor performing a generic computer function of “placing”) such that it amounts no more than mere instructions to apply the exception using a generic computer component.
Accordingly, this additional element does not integrate the abstract idea into a practical
application because it does not impose any meaningful limits on practicing the abstract idea.
The claim is directed to an abstract idea. The claim does not include additional elements that
are sufficient to amount to significantly more than the judicial exception.
(Step 2b)
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract
idea into a practical application, the additional element of a processor/medium and a method to perform both the maintaining; identifying; generating; sending and executing; and placing steps 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. The claim(s) is/are not patent eligible.
Referring to claim 10, (Step 2a, Prong One) this further merely performs an additional abstract
mental step of “wherein the LLM prompt is generated and placed into the metadata template”.
(Step 2a, Prong Two)
This judicial exception is not integrated into a practical application. In particular, the claim only
recites the additional elements of “wherein the LLM prompt is generated and placed
into the metadata template” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
(Step 2b)
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract
idea into a practical application, the additional element of using “wherein the LLM prompt is generated and placed into the metadata template” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps 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.
The claim(s) is/are not patent eligible.
Referring to claim 11, (Step 2a, Prong One) this further merely performs an additional abstract
mental step of “wherein the LLM prompt is generated on a per-field basis in the metadata template”.
(Step 2a, Prong Two)
This judicial exception is not integrated into a practical application. In particular, the claim only
recites the additional elements of “wherein the LLM prompt is generated on a per-field basis in the metadata template” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
(Step 2b)
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract
idea into a practical application, the additional element of using “wherein the LLM prompt is generated on a per-field basis in the metadata template” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps 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.
The claim(s) is/are not patent eligible.
Referring to claim 12, (Step 2a, Prong One) this further merely performs an additional abstract
mental step of “wherein a feedback process is performed to update the LLM prompt based at least in part upon actual values extracted for the metadata”.
(Step 2a, Prong Two)
This judicial exception is not integrated into a practical application. In particular, the claim only
recites the additional elements of “wherein a feedback process is performed to update the LLM prompt based at least in part upon actual values extracted for the metadata” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
(Step 2b)
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract
idea into a practical application, the additional element of using “wherein a feedback process is performed to update the LLM prompt based at least in part upon actual values extracted for the metadata” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps 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.
The claim(s) is/are not patent eligible.
Referring to claim 13, (Step 2a, Prong One) this further merely performs an additional abstract
mental step of “wherein the feedback process is performed based at least in part upon a human update or an update from an LLM”.
(Step 2a, Prong Two)
This judicial exception is not integrated into a practical application. In particular, the claim only
recites the additional elements of “wherein the feedback process is performed based at least in part upon a human update or an update from an LLM” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
(Step 2b)
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract
idea into a practical application, the additional element of using “wherein the feedback process is performed based at least in part upon a human update or an update from an LLM” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps 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.
The claim(s) is/are not patent eligible.
Referring to claim 14, (Step 2a, Prong One) this further merely performs an additional abstract
mental step of “wherein fields within the metadata template are grouped together for submission of related LLM prompts to an LLM”.
(Step 2a, Prong Two)
This judicial exception is not integrated into a practical application. In particular, the claim only
recites the additional elements of “wherein fields within the metadata template are grouped together for submission of related LLM prompts to an LLM” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
(Step 2b)
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract
idea into a practical application, the additional element of using “wherein fields within the metadata template are grouped together for submission of related LLM prompts to an LLM” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps 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.
The claim(s) is/are not patent eligible.
Referring to claim 15, (Step 2a, Prong One) this further merely performs an additional abstract
mental step of “wherein dependencies are identified within the fields to group the fields together”.
(Step 2a, Prong Two)
This judicial exception is not integrated into a practical application. In particular, the claim only
recites the additional elements of “wherein dependencies are identified within the fields to group the fields together” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
(Step 2b)
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract
idea into a practical application, the additional element of using “wherein dependencies are identified within the fields to group the fields together” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps 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.
The claim(s) is/are not patent eligible.
Referring to claim 16, (Step 2a, Prong One) this further merely performs an additional abstract
mental step of “wherein an AI agent is employed to generate and execute the LLM prompt to extract the metadata”.
(Step 2a, Prong Two)
This judicial exception is not integrated into a practical application. In particular, the claim only
recites the additional elements of “wherein an AI agent is employed to generate and
execute the LLM prompt to extract the metadata” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
(Step 2b)
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract
idea into a practical application, the additional element of using “wherein an AI agent is employed to generate and execute the LLM prompt to extract the metadata” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps 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.
The claim(s) is/are not patent eligible.
Claim 17 recites: (Step 2a, Prong One)
placing the metadata extracted from the content into a metadata store.
The limitation of placing the metadata extracted from the content into a metadata store, 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. That is, other than reciting a generic processor/memory, and a generic “LLM prompt/LLM” nothing in the claim element precludes the step from practically being performed in the mind. For example, but for the processor/memory language, “placing” in the context of this claim encompasses the user manually moving generic “metadata” using generic “extracted” steps of generic “content” steps using a generic “store”. Additionally, note the recent and relevant decision Recentive Analytics, Inc. v. Fox Corp. (CAFC Case: 23-2437) explaining that “we hold only that patents that do no more than claim the application of generic machine learning to new data environments, without disclosing improvements to the machine learning models to be applied, are patent ineligible under § 101”). Similarly, the limitation(s) of maintaining; identifying; generating, and executing 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. For example, but for the processor/memory, and a generic “LLM prompt/LLM” language, maintaining; identifying; generating; sending and executing in the context of this claim encompasses the user manually receiving generic “content” and performing generic “identifying”; ”generating” and “extracting” steps. If a claim limitation, 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 (concepts performed in the human mind (including an observation, evaluation, judgment, opinion)).
Further, these concepts also recite “Certain Methods of Organizing Human Activity”; (such as
commercial or legal interactions (including agreements in the form of contracts; legal
obligations; advertising, marketing or sales activities or behaviors; business relations) where
performing generic placing of extracted metadata of generic content using generic “identifying”; ”generating” and “extracting” steps is a method of human activity in commercial or legal interactions.
Accordingly, the claim recites an abstract idea.
(Step 2a, Prong Two)
This judicial exception is not integrated into a practical application. In particular, the claim only
recites one additional element – using processor/memory and a system to perform both the maintaining; identifying; generating; sending and executing; and placing steps. The processor/memory and a method in both steps is recited at a high level of generality (i.e., as a generic processor performing a generic computer function of “placing”) such that it amounts no more than mere instructions to apply the exception using a generic computer component.
Accordingly, this additional element does not integrate the abstract idea into a practical
application because it does not impose any meaningful limits on practicing the abstract idea.
The claim is directed to an abstract idea. The claim does not include additional elements that
are sufficient to amount to significantly more than the judicial exception.
(Step 2b)
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract
idea into a practical application, the additional element of a processor/memory and a system to perform both the maintaining; identifying; generating; sending and executing; and placing steps 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. The claim(s) is/are not patent eligible.
Referring to claim 18, (Step 2a, Prong One) this further merely performs an additional abstract
mental step of “wherein the LLM prompt is generated and placed into the metadata template”.
(Step 2a, Prong Two)
This judicial exception is not integrated into a practical application. In particular, the claim only
recites the additional elements of “wherein the LLM prompt is generated and placed into the metadata template” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
(Step 2b)
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract
idea into a practical application, the additional element of using “wherein the LLM prompt is generated and placed into the metadata template” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps 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.
The claim(s) is/are not patent eligible.
Referring to claim 19, (Step 2a, Prong One) this further merely performs an additional abstract
mental step of “wherein the LLM prompt is generated on a per-field basis in the metadata template”.
(Step 2a, Prong Two)
This judicial exception is not integrated into a practical application. In particular, the claim only
recites the additional elements of “wherein the LLM prompt is generated on a per-field basis in the metadata template” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
(Step 2b)
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract
idea into a practical application, the additional element of using “wherein the LLM prompt is generated on a per-field basis in the metadata template” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps 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.
The claim(s) is/are not patent eligible.
Referring to claim 20, (Step 2a, Prong One) this further merely performs an additional abstract
mental step of “wherein a feedback process is performed to update the LLM prompt based at least in part upon actual values extracted for the metadata”.
(Step 2a, Prong Two)
This judicial exception is not integrated into a practical application. In particular, the claim only
recites the additional elements of “wherein a feedback process is performed to update the LLM prompt based at least in part upon actual values extracted for the metadata” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
(Step 2b)
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract
idea into a practical application, the additional element of using “wherein a feedback process is performed to update the LLM prompt based at least in part upon actual values extracted for the metadata” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps 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.
The claim(s) is/are not patent eligible.
Referring to claim 21, (Step 2a, Prong One) this further merely performs an additional abstract
mental step of “wherein the feedback process is performed based at least in part upon a human update or an update from an LLM”.
(Step 2a, Prong Two)
This judicial exception is not integrated into a practical application. In particular, the claim only
recites the additional elements of “wherein the feedback process is performed based at least in part upon a human update or an update from an LLM” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
(Step 2b)
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract
idea into a practical application, the additional element of using “wherein the feedback process is performed based at least in part upon a human update or an update from an LLM” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps 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.
The claim(s) is/are not patent eligible.
Referring to claim 22, (Step 2a, Prong One) this further merely performs an additional abstract
mental step of “wherein fields within the metadata template are grouped together for submission of related LLM prompts to an LLM”.
(Step 2a, Prong Two)
This judicial exception is not integrated into a practical application. In particular, the claim only
recites the additional elements of “wherein fields within the metadata template are grouped together for submission of related LLM prompts to an LLM” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
(Step 2b)
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract
idea into a practical application, the additional element of using “wherein fields within the metadata template are grouped together for submission of related LLM prompts to an LLM” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps 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.
The claim(s) is/are not patent eligible.
Referring to claim 23, (Step 2a, Prong One) this further merely performs an additional abstract
mental step of “wherein dependencies are identified within the fields to group the fields together”.
(Step 2a, Prong Two)
This judicial exception is not integrated into a practical application. In particular, the claim only
recites the additional elements of “wherein dependencies are identified within the fields to group the fields together” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
(Step 2b)
The claim does not include additional elements that are sufficient to amount to significantly
more than the judicial exception. As discussed above with respect to integration of the abstract
idea into a practical application, the additional element of using “wherein dependencies are identified within the fields to group the fields together” steps to perform both the aforementioned maintaining; identifying; generating; sending and executing; and placing steps 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.
The claim(s) is/are not patent eligible.
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.
Claim(s) 1, 9, 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Berglund et al., US Pub. No. 2024/0403569 A1, in view of Aldersberg et al., US Pub. No.: 2025/0006201 A1, in view of Ryan et al. US Pub. No. 2024/0330583 A1.
As to claim 1 (and substantially similar claim 9 and claim 17)
Berglund discloses
a method,
(Berglund [0081-0088])
comprising:
maintaining content within a content management system;
(Berglund [0014] The content management platform 110 enables access to content items in the content repository 150. The content management platform 110 can provide user interfaces via a web portal or application, which are accessed by the user devices 120 to enable users to create content items, view content items, share content items, or search content items. In some implementations, the content management platform 110 includes enterprise software that manages access to a company's private data repositories and controls access rights with respect to content items in the repositories.)
identifying a metadata template that stores parameters about metadata to be extracted
from the content;
(Berglund teaches selecting templates for message types and message generation including style templates/metadata to be retrieved with content items that are identified to be associated with the message, i.e. “identifying a metadata template that stores parameters about metadata to be extracted from the content”
See [0030] The user can also select a pitch template from a menu 232 or create a new pitch template, or select a pitch style from the menu 234 or create a new pitch style. A pitch template
can specify certain formatting or content parameters for the message. When a pitch template is selected, the content management platform 110 can modify message content received from the LLM to conform to the template, or can include the template in a prompt to the LLM to cause the
LLM to output conforming content. The pitch style can specify, for example, whether the message should be "formal" or "casual." When a pitch style is selected, the content
management platform 110 can include the selected style in the prompt to the LLM that instructs the LLM to generate the message content.;
see also [0038] For example, the platform can retrieve preconfigured prompt templates that correspond to each of the message types.;
see also [0049] The signals retrieved by the computer system can include metadata associated with any content items that are identified to be associated with the message. The metadata
can include, for example, a title of the content item, an author of the content item, a type of the content item (e.g., a document, a slide deck, or a video), or a description of the content item. With respect to content item description metadata, some content descriptions are generated by a user, and include information such as a summary of the content item, the author of the content item, date content as created, date content was last modified, modification history, access
rights, and so on.;
see also [0054] These prompt generation models can select message features that include, for example, length of the message, formatting of the message, style or tone of the message, or number of content items that can be associated with the message. These features can then be directly specified in a prompt.)
generating an LLM prompt based at least in part upon the parameters about the metadata
to be extracted from the content;
(Berglund teaches generating different types of prompts to the LLM, based on the type of message to be generated, i.e. “generating an LLM prompt based at least in part upon the parameters about the metadata to be extracted”;
See [0030] When a pitch style is selected, the content management platform 110 can include the selected style in the prompt to the LLM that instructs the LLM to generate the message content.;
See also [0038] The options 242 for message types can be preconfigured types of messages. Selection of these preconfigured options can cause the platform to generate different types of
prompts to the LLM, based on the type of message to be generated. For example, the platform can retrieve preconfigured prompt templates that correspond to each of the message types.; see also [0054] These prompt generation models can select message features that include, for example, length of the message, formatting of the message, style or tone of the message, or number of content items that can be associated with the message. These features can then be directly specified in a prompt)
Berglund does not disclose:
sending the LLM prompt and a selection based on at least the metadata template of one or
more portions of the content from which the metadata is to be extracted;
executing the LLM prompt at an LLM to extract the metadata from the selected one or
more portions of the content;
However, Aldersberg discloses:
sending the LLM prompt and a selection based on at least the metadata template of one or more portions of the content from which the metadata is to be extracted;
(Aldersberg teaches generating/feeding LLM prompts based on AI/DL/ML/RL/NN analysis that takes into account business-related parameters, i.e. “sending the LLM prompt and a selection based on at least the metadata template”
See [0028] An LLM Prompt Constructor and Feeder Unit 114 operates to construct one or more prompts, and to feed them to the LLM engine 120. In some embodiments, the prompt may be selected from a pre-defined list of prompts. See also [0031] In some embodiments, optionally, the LLM Prompt Constructor and Feeder Unit 114 may be-by itself-an AI engine that constructs prompts (to the LLM engine 120) based on AI/DL/ML/RL/NN analysis that takes into account
business-related parameters that are tailored to the specific organization.;
see also [0027] An Organizational Transcripts Feeder Unit 113 operates to feed or to send or to enter as input, in to the LLM engine 120, the organizational textual transcripts that were
collected automatically by the Organizational Meetings and Transcripts Collector Unit 110 for a time-period T (e.g., one day, one week, two weeks, one month). For example, in some embodiments, the Transcripts Feeder Unit 113 may operate nightly, such as at 1 AM every night; may obtain all the transcripts of all the organizational meetings that took place in the preceding day; and may feed all these transcripts into the LLM engine;
see also [0030] (D) do you want to add a particular filtering condition? Select from, No filtering
condition, or "only insights from what Customers said in meetings and not team-members", or "only insights from what External Consultants said in meetings", or "only insights from what Vendors/Suppliers said in meetings"; and then, (E) do you want to add a particular keyword or name or topic-of-interest such that only for that keyword/s or topic-of-interest the insights would be generated? Select from No keywords/No topic-of-interest, or "Topic=Budget",
or "Topic=Legal", or "Topic-Marketing", or Keyword that is free-style text that the end-user can type and provide (e.g., keyword "Microsoft", or keyword "Promotion", or keyword "Public Relations", or keyword "Recurring Problem"). The LLM Prompt Constructor and Feeder Unit 114 then constructs the LLM prompt accordingly, based on selection of strings (that correspond to the user's selections) and concatenation of such strings (prompt-segments) into a final LLM prompt.;
see also [0049] the LLM engine is configured to generated LLM-generated that only pertain to the one or more user-provided keywords that indicate the topics-of-interest defined by the user. A user-provided keyword that indicates a topic-of-interest, as provided by the user and as then
constructed to be part of the prompt to the LLM engine, can be one or more of, for example: a name of a person ( e.g., "Jeff Bezos"); a name of an entity or organization or company or corporation ( e.g., "Microsoft"); a name of a geographical place or venue or region (e.g., "Japan", or "Europe", or "Boston"); a name of a time-period or timestamp or dime-indication (e.g., "Winter", or "February", or "Labor Day"))
executing the LLM prompt at an LLM to extract the metadata from the selected one or
more portions of the content;
(Aldersberg teaches feeding/generating outputs from the LLM for business/sales/revenue parameters/ business-related parameters that are tailored to the specific organization, i.e. “executing the LLM prompt at an LLM to extract the metadata from the selected one or more portions of the content”
See [0032] In some embodiments, optionally, two or more different prompts, or even all
the prompts from the prompts list, may be fed sequentially to the LLM engine, to generate a plurality of outputs;
see also [0015] In some embodiments, each insight that is derived or generated by the LLM engine, from the plurality of meeting transcripts that it reviews as input, may optionally
be accompanied by proof/evidence/quoted text/excerpts, and/or may be accompanied by "text snippets" and/or "audio snippets" and/or "video snippets" that correspond/support/
demonstrate each such insight generated by the LLM engine. For example, the LLM engine may generate an output indicating to the manager, "Based on LLM analysis
of 6,000 meeting transcripts from the past 14 days, the topic of Sales in France is of great importance/relevance to the organization"; and the LLM engine or the associated system
may provide textual snippets from selected meeting transcript that demonstrate/prove/support that insight; and/or may provide links or shortcuts or other GUI elements that enable the manager to directly access the relevant audio segments/video clips that demonstrate/prove/support that insight.;
see also Aldersberg teaches prompt generation using business-related parameters, i.e. “generating an LLM prompt based at least in part upon the parameters about the metadata” see [0031] In some embodiments, optionally, the LLM Prompt Constructor and Feeder Unit 114 may be-by itself-an AI engine that constructs prompts (to the LLM engine 120) based on AI/DL/ML/RL/NN analysis that takes into account business-related parameters that are tailored to the specific organization.;
see also [0014] the manager may define that such alerts or notifications would be sent only in accordance with additional filtering criteria that the manager can define; for example, "only
those related to Europe, or derived from European meetings", or "only those that are related to Budget/Profit/ Revenue/Expenses, and not to Marketing/Sales/Legal"; or other filtering criteria.)
It would have been obvious to one having ordinary skill in the art at the time the time of the effective filing date to apply LLM prompt generation as taught by Aldersberg to the system of Berglund, since it was known in the art that Large Language Model (LLM) systems provide for
An LLM engine can be prompted or inquired to configured to autonomously analyze such large
plurality of organizational meeting transcripts, and to autonomously generate from them insights where a user of such system (e.g., a manager or CEO of a large organization), does not need to explicitly prompt the system, manually or otherwise, with a prompt such as "Please review the
transcripts of 5,000 meetings that were held in the organization this week, and show me all the transcript-portions that relate to Client Adam"; but rather, the system is already configured to search by itself and to autonomously generates insights that a human cannot necessarily predict or estimate in advance that they exist or that they are meaningful or important or relevant where the system may be automatically prompted to "generate a description of a
surprising Trend related to Marketing that you, the LLM engine, can extract from the 5,000 meeting transcripts of last week"; or the system may be automatically prompted to "generate a description of the Topic/the Client/the Customer/ the Supplier/the Product/the Service/the Problem, that was most frequently discussed in all 4,000 meeting transcript of the organization last week"; or the system may be automatically prompted to "generate a description of the
topic or problem or trend, that you-the LLM engine determine to be of the highest level of business importance, from the 6,000 organizational meetings that were held yesterday"; or the system may be automatically prompted to "generate a description of the topic or problem or trend, that you-the LLM engine-determine to be of the highest affect on the organization's Profit/Revenue/Expenses/Legal Situation, from the 7,000 organizational meetings that were held yesterday". (Aldersberg [0009-0010]).
Berglund/Aldersberg do not disclose:
and placing the metadata extracted from the content into a metadata store;
however, Ryan discloses:
and placing the metadata extracted from the content into a metadata store;
(Ryan teaches a content management system which stores unique identifier(s) and report tags for the report in a database, i.e. “placing the metadata extracted from the content into a metadata store” [0126] In some embodiments, processor 104 may publish structured data report 648 and/or final report 150 using a content management system (CMS). In some embodiments, after the structured data report 648 and/or final report 150 is published, processor 104 may receive a unique identifier tied to the report. In some embodiments, processor 104 may store that unique identifier and report tags for the report in a database. In some embodiments, processor 104 may store that unique identifier and report tags for the report in a lookup table.)
It would have been obvious to one having ordinary skill in the art at the time the time of the effective filing date to apply LLM producing reports using classification tags/tokens as taught by Ryan to the system of Berglund/Aldersberg, since it was known in the art that Large Language Model (LLM) systems provide for determining an activity classification as a function of the structured data, wherein the activity classification includes an activity identifier, generating a structured data report as a function of the activity identifier, and generating, a final report using a large language model (LLM), wherein structured data report and/or previous report may be stored in database described above where storing structured data report and/or previous report may include storing them based on their report tag where this may allow for related reports to be
quickly located, so that they may be linked to in a structured data report as this improves the technology of automated report or article generation by allowing for links to other media to be intelligently and quickly incorporated into the article where the system may publish structured data report and/or final report using a content management system (CMS). (Ryan [0005, 0125]).
Claim(s) 6-7, 14-15, 22-23 is/are rejected under 35 U.S.C. 103 as being unpatentable over Berglund et al., US Pub. No. 2024/0403569 A1, in view of Aldersberg et al., US Pub. No.: 2025/0006201 A1, in view of Ryan et al. US Pub. No. 2024/0330583 A1, in view of Fernandez et al., US Pub. No. 2025/0045516 A1.
As to claim 6, Berglund/Aldersberg/Ryan do not disclose:
wherein fields within the template are grouped together for submission of related LLM prompts to an LLM;
however, Fernandez discloses the method of claim 1, wherein fields within the template are grouped together for submission of related LLM prompts to an LLM;
(Fernandez teaches appending the previous template recommendations to the natural language request to provide the language model context/selecting subsection of templates that are selected from among a set of available templates, i.e. wherein fields within the template are grouped together for submission of related LLM prompts to an LLM see [0048] The user can provide a natural language request in the prompt field 240 to refine the recommendation that is
provide by the language model 138. The prompt construction unit 124 appends the previous template recommendation to the natural language request to provide the language model 138 with context regarding the previous recommendation provided to the user. The language model 138 can use this information to predict a template subsection to recommend to the user that satisfies the user request. A technical benefit of this approach is that the language model 138 is
provided context by including the previous template recommendation in addition to at least a portion of the textual content from the electronic content item in the prompt. Consequently, the language model 138 is more likely to predict a relevant template subsection to recommend to the user.;
see also [0077] FIG. 6C is a flow chart of an example process 670 for providing template component recommendations in an application according to the techniques disclosed herein.
The process 670 can be implemented by the application services platform 110 shown in the preceding examples. The process 670 trains the language model and the utilizes the recommendations of a language model, such as the language model 138, to dynamically construct a template from a plurality of template subsections from one or more existing
templates to provide a customized template for the user. Rather than selecting a static, page-level template before any content is added to the electronic content item, the process 670 enables the user to begin authoring the electronic content item and the application services platform 110 uses the language model to predict which template subsections would be useful to the user based on the current textual content of the electronic content item. This approach is an
iterative process that creates a custom template that fits the user's needs for a particular electronic content item from the subsection of templates that are selected from among a set of available templates. In some implementations, the user can also choose to save the custom template layout so that the user can select that template again in the future.).
It would have been obvious to one having ordinary skill in the art at the time the time of the effective filing date to apply appending the previous template recommendations as taught by Fernandez to the system of Berglund/Aldersberg/Ryan, since it was known in the art that Large Language Model (LLM) systems provide for utilizing the recommendations of a language model, such as the language model to dynamically construct a template from a plurality of template subsections from one or more existing templates to provide a customized template for the user to provide for rather than selecting a static, page-level template before any content is added to the electronic content item, the process enables the user to begin authoring the electronic content item and the application services platform uses the language model to predict which template subsections would be useful to the user based on the current textual content of the electronic content item where this approach is an iterative process that creates a custom template that fits the user's needs for a particular electronic content item from the subsection of templates that are selected from among a set of available templates where the user can also choose to save the custom template layout so that the user can select that template again in the future. (Fernandez [0077]).
As to claim 7, Ryan as modified discloses the method of claim 6, wherein dependencies are identified within the fields to group the fields together
(Ryan teaches classifying a plurality of headers of desired data of the content data/ correlating a plurality of content category for templates, i.e. “dependencies are identified within the fields to group the fields together” See [0046] An "article template," as used herein, is a data structure outlining data to be populated to create an article. For example, an article template for an obituary may include an intro (e.g. name of deceased, names of family members), discussion ( e.g., cause of death, life biography), and a conclusion (e.g., name of cemetery, date of funeral) space. For example, template classifier may be trained by training data correlating a plurality of content category and data file types to corresponding article templates
see [0039] Still referring to FIG. 1, in some embodiments, importing content data 124 from data file 120 may include classifying a plurality of headers 128 to desired data 136 of the content data 124, wherein desired data 136 is related to the content category 116. "Desired data," as used herein, is content data 124 relevant to a content category 116. Classifying the plurality of headers 128 may include determining a plurality of desired data headers 140. A "desired data
header," as a used herein, is a header relevant to a content category 116).
Referring to claim 14, this dependent claim recites similar limitations as claim 6;
therefore, the arguments above regarding claim 6 are also applicable to claim 14.
Referring to claim 15, this dependent claim recites similar limitations as claim 7;
therefore, the arguments above regarding claim 7 are also applicable to claim 15.
Referring to claim 22, this dependent claim recites similar limitations as claim 6;
therefore, the arguments above regarding claim 6 are also applicable to claim 22.
Referring to claim 23, this dependent claim recites similar limitations as claim 7;
therefore, the arguments above regarding claim 7 are also applicable to claim 23.
Claim(s) 2, 4-5, 8, 10, 12-13, 16, 18, 20-21 is/are rejected under 35 U.S.C. 103 as being unpatentable over Berglund et al., US Pub. No. 2024/0403569 A1, in view of Aldersberg et al., US Pub. No.: 2025/0006201 A1, in view of Ryan et al. US Pub. No. 2024/0330583 A1, in view of Fabian et al. US Pub. No. 2024/0303421.
As to claim 2, Berglund/Aldersberg/Ryan do not disclose:
wherein the LLM prompt is generated and placed into the metadata template;
However, Fabian discloses:
the method of claim 1, wherein the LLM prompt is generated and placed into the metadata template
(Fabian teaches configuring prompts using prompt templates / prompt configurations with context data, i.e. “wherein the LLM prompt is generated and placed into the metadata template” see [0066-0067] [0066] To configure the prompt, prompt engine 305 identifies a prompt template according to the type of request in the input in an implementation. Prompt templates can include prompt configurations for suggesting a calculated column to be added to workbook data 320, for a general inquiry about workbook data 320, for analyzing data in workbook data 320 to project a result, such as for a hypothetical scenario, and so on. Using a selected prompt template, prompt engine 305 configures a prompt to include the input or the substance of the input and contextual information from application 301, e.g., from various ones of application component 303. Contextual information may include a chat history of user inputs and replies from LLM 330 and spreadsheet data, such as table information and at least a portion of the spreadsheet data. The portion of spreadsheet data included in the prompt may be column headers, row headers, a table name, and the first few rows of data or another portion or subset of the data that is relevant to the request. For example, if the user input asks in user interface 307 how a column of last names can be added to a data table in workbook data 320 based on a name column in the data table, prompt engine 305 may provide several entries in the name column in the prompt. [0067] Prompt engine 305 configures the prompt including parameters to direct LLM 330 to provide a focused response to the input.;
see also [0082] Prompt engine 305 selects a prompt template based on a type or classification of the inquiry and configures a prompt according to the template. In the prompt,
prompt engine 305 includes tasks, instructions, or rules applicable to generating a reply to the input,)
It would have been obvious to one having ordinary skill in the art at the time the time of the effective filing date to apply selecting a prompt template based on a type or classification of the inquiry and configures a prompt according to the template as taught by Fabian to the system of Berglund/Aldersberg/Ryan, since it was known in the art that Large Language Model (LLM) systems provide a prompt engine which selects a prompt template based on a type or classification of the inquiry and configures a prompt according to the template where in the prompt, prompt engine includes tasks, instructions, or rules applicable to generating a reply to the input, such as tasking LLM to perform a self-evaluation of its reply and a rule to return the reply in a particular output format which is suitable for parsing where for inputs involving generating an explanation, the prompt may specify the explanation is to be enclosed in tags where the tasks, instructions, and rules included in the prompt may be predetermined according to the prompt template or according to the type or classification of the inquiry where the prompt engine also includes contextual information in the prompt. (Fabian [0082-0083]).
As to claim 4, Fabian as modified discloses the method of claim 1, wherein a feedback process is performed to update the LLM prompt based at least in part upon actual values extracted for the metadata
(Fabian teaches updates based on user data and turn based conversation, i.e. update the LLM prompt based at least in part upon actual values extracted for the metadata see [0077-0079] [0077] In yet another implementation of operational scenario 400, user interface 307 receives a natural language input from the user or a selection of a suggested action displayed in user interface 307. Prompt engine 305 configures a prompt based on the input, including context data from application 301, and sends the prompt to LLM 330. Prompt engine 305 configures a response to the input based on the reply. The response is presented to the user in user interface 307, where the user selects a suggestion in response. [0078] In user interface 307, prompt engine 305 receives the selection of a suggestion in the response. Based on the selection, prompt engine 305 sends instructions to various ones of application component 303 to implement the suggestion. Application 301 implements the suggestion in workbook data 320 and sends an update to the display to user interface 307. [0079] Subsequent to displaying an update to the display in user interface 307, the user provides additional natural language inputs to prompt engine 305 via user interface 307. The inputs may relate to the suggestion that was implemented, to another suggestion, to an error generated in relation to the implemented suggestion, or to another aspect of workbook data 320. The inputs trigger replies from LLM 330 and responses to the inputs based on the replies. With each new input, prompt engine 305 gathers context data from application 301 which includes the chat history, i.e., previous inputs, replies, suggestions, and so on. The series of inputs and responses result in a turn-based conversation. In some turns, the user may not select a suggestion but instead submit another natural language input.).
As to claim 5, Fabian as modified discloses the method of claim 4, wherein the feedback process is performed based at least in part upon a human update or an update from an LLM
(Fabian teaches a turn/conversation based prompts feedback, i.e. human updates of LLM updates to the prompt see [0077-0079] [0077] In yet another implementation of operational scenario 400, user interface 307 receives a natural language input from the user or a selection of a suggested action displayed in user interface 307. Prompt engine 305 configures a prompt based on the input, including context data from application 301, and sends the prompt to LLM 330. Prompt engine 305 configures a response to the input based on the reply. The response is presented to the user in user interface 307, where the user selects a suggestion in response. [0078] In user interface 307, prompt engine 305 receives the selection of a suggestion in the response. Based on the selection, prompt engine 305 sends instructions to various ones of application component 303 to implement the suggestion. Application 301 implements the suggestion in workbook data 320 and sends an update to the display to user interface 307. [0079] Subsequent to displaying an update to the display in user interface 307, the user provides additional natural language inputs to prompt engine 305 via user interface 307. The inputs may relate to the suggestion that was implemented, to another suggestion, to an error generated in relation to the implemented suggestion, or to another aspect of workbook data 320. The inputs trigger replies from LLM 330 and responses to the inputs based on the replies. With each new input, prompt engine 305 gathers context data from application 301 which includes the chat history, i.e., previous inputs, replies, suggestions, and so on. The series of inputs and responses result in a turn-based conversation. In some turns, the user may not select a suggestion but instead submit another natural language input.).
As to claim 8, Fabian as modified discloses the method of claim 1, wherein an AI agent is employed to generate and execute the LLM prompt to extract the metadata
(Fabian teaches a copilot/assistant with a chat interface by which the application receives natural language input from the user, i.e. “wherein an AI agent is employed to generate and execute the prompt to extract the metadata” see Fig. 9B,9C,9D,9E,10A,10C showing a copilot;
See also [0116] Upon receiving a user selection to open the task pane in the user interface, the application displays task pane 1010 including a chat interface by which the application receives natural language input from the user. The application sends a prompt including spreadsheet contextual data to the LLM to generate a description of the spreadsheet and/or the data table. The application receives a reply from the LLM which the application processes for display, resulting in output 1011 in task pane 1010. The application also receives three suggested actions from the LLM which relate to modifying spreadsheet 1001 which the application processes and displays in output 1012. The user is also presented with textbox 1013 by which the user can submit natural language inputs, such as requests or queries, to the LLM via the application.;
See also [0065] FIG. 4 illustrates operational scenario 400 of an LLM integration with a spreadsheet environment and referring to elements of FIG. 3 in an implementation. In operational scenario 400, prompt engine 305 receives a natural language input from a user via user interface 307, such as in a task pane or chat interface in user interface 307. The input
may be a text entry keyed into a textbox of user interface 307 by the user or a spoken communication from the user captured by a microphone on the user computing device and which is translated to text by a speech-to-text engine. The input includes a request or query regarding workbook data 320. Prompt engine 305 configures).
Referring to claim 10, this dependent claim recites similar limitations as claim 2;
therefore, the arguments above regarding claim 2 are also applicable to claim 10.
Referring to claim 12, this dependent claim recites similar limitations as claim 4;
therefore, the arguments above regarding claim 4 are also applicable to claim 12.
Referring to claim 13, this dependent claim recites similar limitations as claim 5;
therefore, the arguments above regarding claim 5 are also applicable to claim 13.
Referring to claim 16, this dependent claim recites similar limitations as claim 8;
therefore, the arguments above regarding claim 8 are also applicable to claim 16.
Referring to claim 18, this dependent claim recites similar limitations as claim 2;
therefore, the arguments above regarding claim 2 are also applicable to claim 18.
Referring to claim 20, this dependent claim recites similar limitations as claim 4;
therefore, the arguments above regarding claim 4 are also applicable to claim 20.
Referring to claim 21, this dependent claim recites similar limitations as claim 5;
therefore, the arguments above regarding claim 5 are also applicable to claim 21.
Claim(s) 3, 11 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Berglund et al., US Pub. No. 2024/0403569 A1, in view of Aldersberg et al., US Pub. No.: 2025/0006201 A1, in view of Ryan et al. US Pub. No. 2024/0330583 A1, in view of Fabian et al. US Pub. No. 2024/0303421, in view of Fernandez et al. US Pub. No. 2025/0045516 A1.
As to claim 3, Berglund/Aldersberg/Ryan/Fabian do not disclose:
wherein the LLM prompt is generated on a per-field basis in the metadata template
However, Fernandez discloses
the method of claim 2, wherein the LLM prompt is generated on a per-field basis in the metadata template
(Fernandez teaches prompt construction unit including at least a subsections/fields of the textual content, i.e. “the LLM prompt is generated on as per-field basis in the metadata template”
See [0030-0031] [0030] In some implementations, the prompt construction unit 124 constructs a natural language query that is provided to as a prompt to the language model 138. In such implementations, the prompt construction unit 124 includes at least an application identifier and at least a subsection of the textual content of the electronic content item. The textual
content may include but is not limited to a file title, section header or subtitles, and/or other textual content that has been added to the electronic content item. This textual content provides context to the language model 138 to determine which categories of template and which types of template subsections may be relevant to the user. The generation of the template suggestions is an iterative process that continues as the user creates or modifies the electronic content items. This approach enables the system to dynamically construct a custom template from among the available templates and template subsections. [0031] In a nonlimiting example, the prompt construction unit 124 constructs a natural language query having the following format: "what template could I use in application X for Y" where X represents a name or other application identifier associated with the application for which the template is to be created and Y represents at least a portion of the textual content from the electronic content item being
created.;
See also Fernandez teaches appending previous template recommendations to the natural language request [0048] The user can provide a natural language request in the prompt field 240 to refine the recommendation that is provide by the language model 138. The prompt construction unit 124 appends the previous template recommendation to the natural language request to provide the language model 138 with context regarding the previous recommendation
provided to the user.).
It would have been obvious to one having ordinary skill in the art at the time the time of the effective filing date to apply construct a template from a plurality of template subsections as taught by Fernandez to the system of Berglund/Aldersberg/Ryan/Fabian, since it was known in the art that Large Language Model (LLM) systems provide for utilizing the recommendations of a language model, such as the language model to dynamically construct a template from a plurality of template subsections from one or more existing templates to provide a customized template for the user to provide for rather than selecting a static, page-level template before any content is added to the electronic content item, the process enables the user to begin authoring the electronic content item and the application services platform uses the language model to predict which template subsections would be useful to the user based on the current textual content of the electronic content item where this approach is an iterative process that creates a custom template that fits the user's needs for a particular electronic content item from the subsection of templates that are selected from among a set of available templates where the user can also choose to save the custom template layout so that the user can select that template again in the future. (Fernandez [0077]).
Referring to claim 11, this dependent claim recites similar limitations as claim 3;
therefore, the arguments above regarding claim 3 are also applicable to claim 11.
Referring to claim 19, this dependent claim recites similar limitations as claim 3;
therefore, the arguments above regarding claim 3 are also applicable to claim 19.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Mukherjee et al., US Pub. No. 2024/0354436 A1, teaches methods are disclosed, including systems and methods utilizing language models for searching a large corpus of data. A computer-implemented method may include: receiving a first user input comprising a natural language query; vectorizing the first user input into a query vector; executing, using the query vector, a similarity search in a document search model to identify one or more similar document portions, where the document search model includes a plurality of vectors corresponding to a plurality of portions of a set of documents; generating a first prompt for a large language model (“LLM”), the first prompt including at least the first user input, and the one or more similar document portions; transmitting the first prompt to the LLM; receiving a first output from the LLM in response to the first prompt; and providing, via a user interface, the first output from the LLM;
Roper et al., US Pub., No. 2025/0278526, teaches a digital documentation system for preparation of engineering documents utilizing one or more artificial intelligence (AI) algorithms is provided. The system includes a user interface for selecting and populating templates with data, and one or more AI algorithms for creating and recommending templates, and preparing documents based on the recommended templates. The system uses natural language processing and semantic analysis algorithms to understand the content of the templates, documents, and associated engineering data, and to generate and recommend relevant templates to the user based on user prompts. The system also uses machine learning and predictive modeling and decision-tree algorithms to assist with the preparation of documents, by generating suggestions for data fields and values based on the user's previous inputs and the overall context of the document and available engineering data, including model data and metadata from digital models accessed in a zero-trust framework.
CONTACT INFORMATION
Any inquiry concerning this communication or earlier communications from the examiner should be directed to EVAN S ASPINWALL whose telephone number is (571)270-7723. The examiner can normally be reached Monday-Friday 8am-5pm.
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 Ajay Bhatia can be reached at 571-272-3906. 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.
/Evan Aspinwall/Primary Examiner, Art Unit 2156
Prosecution Insights