DETAILED ACTION
Summary and Status of Claims
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This Office Action is in response to Application No. 19/238,139 filed 6/13/2025.
Claims 1-20 are pending.
Claims 2 and 12 are rejected under 35 U.S.C. 112(b).
Claims 1-20 are rejected under 35 U.S.C. 101.
Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Gajek et al. (US Patent 11,861,320) (Gajek) in view of Edwards et al. (US Patent Pub 2024/0394481).
Priority
The claim of priority to US Provisional Patent Application 63/659,600 filed 6/13/2024 is acknowledged.
Drawings
The drawings are objected to as failing to comply with 37 CFR 1.84(p)(5) because they include the following reference character(s) not mentioned in the description: Fig. 2-260. Corrected drawing sheets in compliance with 37 CFR 1.121(d), or amendment to the specification to add the reference character(s) in the description in compliance with 37 CFR 1.121(b) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Specification
The disclosure is objected to because of the following informalities:
The heading above the listing of figures should be corrected.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
Claims 2 and 12 are rejected under 35 U.S.C. 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention.
Claims 2 and 12 each recite “substantially equal”. The term “substantially” is a relative term which renders the claim indefinite. The term “substantially” 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.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more. Determining whether claims are statutory under 35 U.S.C. 101 involves a two-step analysis. Step 1 requires a determination of whether the claims are directed to the statutory categories of invention. Step 2 requires a determination of whether the claims are directed to a judicial exception without significantly more. Step 2 is divided into two prongs, with the first prong having a part 1 and part 2. See MPEP 2106.
Claim 1
Pursuant to Step 2A, part 1, claims are analyzed to determine whether they are directed to an abstract idea. Pursuant to MPEP 2106, claims are deemed to be directed to an abstract idea if, under their broadest reasonable interpretation, they fall within one of the enumerated categories of (a) mathematical concepts, (b) certain methods of organizing human activity, and (c) mental processes. Under the broadest reasonable interpretation, the terms of the claim are presumed to have their plain meaning consistent with the specification as it would be interpreted by one of ordinary skill in the art. See MPEP 2111.
Claim 1 recites the limitations of: (1) receiving, at an online system, an analysis request from a user, wherein the analysis request comprises free text requesting analytics of a set of data stored by the online system in a database, (2) generating an initialization prompt based on the analysis request, wherein the initialization prompt comprises text instructing a large language model to generate a merge prompt template based on the analysis request, (3) transmitting the initialization prompt to the large language model, (4) receiving a response to the initialization prompt, wherein the response comprises the merge prompt template, (5) generating a response to the analysis request by applying a recursive process to the set of data, wherein the recursive process comprises, (6) determining whether a terminating condition for the recursive process is met, (7) and responsive to determining that the terminating condition is not met: applying the recursive process to a first portion of the set of data to generate a first output, wherein applying the recursive process to the first portion comprises applying the analysis request to the first portion of the set of data using the large language mode, (8) applying the recursive process to a second portion of the set of data to generate a second output, wherein applying the recursive process to the second portion comprises applying the analysis request to the second portion of the set of data using the large language model, (9) generating a merge prompt based on the merge prompt template, the first output, and the second output, (10) transmitting the merge prompt to the large language model, (11) receiving a response to the merge prompt from the large language model, and (12) transmitting a response to the analysis request based on the received response to the merge prompt.
Courts consider a mental process if it “can be performed in the human mind, or by a human using a pen and paper.” The mental process grouping covers concepts performed in the human mind, including observation, evaluation, judgment, and opinion. MPEP 2016(a)(2)(III). Limitations can also be deemed insignificant extra-solution activity (IESA). The term "extra-solution activity" can be understood as activities incidental to the primary process or product that are merely a nominal or tangential addition to the claim. Extra-solution activity includes both pre-solution and post-solution activity. An example of pre-solution activity is a step of gathering data for use in a claimed process, e.g., a step of obtaining information about credit card transactions, which is recited as part of a claimed process of analyzing and manipulating the gathered information by a series of steps in order to detect whether the transactions were fraudulent. An example of post-solution activity is an element that is not integrated into the claim as a whole, e.g., a printer that is used to output a report of fraudulent transactions, which is recited in a claim to a computer programmed to analyze and manipulate information about credit card transactions in order to detect whether the transactions were fraudulent. MPEP 2106.05(g).
Limitation (1) is directed to IESA in the form of mere data gathering because it merely receives an analysis request from the user. Limitation (2) is directed to a mental step of generating an initialization prompt, which can be performed by a person. Limitation (3) is directed to IESA in the form of transmission of data over a network. Limitation (4) is also directed to IESA in the form of receiving information over a network or mere data gathering. Limitation (5) is directed to mental step of generating a response to the analysis request by applying a recursive process, which can be performed by a person. Limitation (6) is directed to a mental step of determining, which involves evaluation and judgement, that can be performed by a person. Limitation (7) is directed to a mental step of applying the analysis request to a first portion of data using the LLM, which can be performed by a person with the aid of a computer as a tool. Limitation (8) similarly is directed to a mental step of applying the analysis request to a second portion of data using the LLM, which can be performed by a person with the aid of a computer as a tool. Limitation (9) is directed to generating a merge prompt, which is a mental step that can be performed by a person to create a merge prompt using a merge prompt template, the first output, and the second output. Limitation (10) is directed to IESA in the form of transmitting data over a network. Limitation (11) is directed to IESA of receiving data over a network. Limitation (12) is directed to IESA of transmitting data over a network or outputting results.
The recited online system and database is/are recited at a high level of generality, i.e., as a generic components performing generic computer functions.
For at least these reasons, claim 1 is directed to an abstract idea categorized under mental processes.
Pursuant to Step 2A, part 2, claims are analyzed to determine whether the claim as a whole integrates the recited judicial exception into a practical application of the exception. This evaluation is performed by (1) identifying whether there are any additional elements recited in the claim beyond the judicial exception, and (2) evaluating those additional elements individually and in combination to determine whether the claim as a whole integrates the exception into a practical application. See MPEP 2106.04(d). One way to determine integration into a practical application is when the claimed invention improves the functioning of a computer or improves another technology or technical field. To evaluate an improvement to a computer or technical field, the specification must set forth an improvement in technology and the claim itself must reflect the disclosed improvement. See MPEP 2106.04(d)(1).
In this case, as explained above, claim 1 merely recites an abstract idea categorized under mental processes.
Limitations (1), (3), (4), and (10) through (12) are directed to IESA, which cannot integrate an abstract idea into a practical application. Limitation (2) is directed to a mental step of generating an initialization prompt, which can be performed by a person. The limitation does not require specifics of how the prompt is generated that would make it impractical or impossible for a person to perform. It also does not include specific steps that demonstrate an asserted improvement. Limitation (5) is directed to a mental step of generating a response to the analysis request, which can be performed by a person. The limitation requires applying a recursive process, which essentially comprises utilization of an LLM (discussed further below). The limitation does not recite specifics as to how the response is generated in a manner that adequately demonstrates an asserted improvement. Limitation (6) is a mental step of determining, which involves evaluation and judgment actions that can be performed by a person. The limitation does not recite what type of condition is being evaluated and the broadest reasonable interpretation encompasses any type of condition that can be reasonably evaluated by a person. Accordingly, it does not recite specifics that adequately demonstrate an improvement to the technology. Limitations (7) and (8) are directed to steps of applying analysis to respective portions of data using the LLM. However, both limitations recite the application at a high level and simply require usage of an LLM, which does not adequately demonstrate any asserted improvement. Limitation (9) is directed to a mental step of generating a merge prompt, which can be performed by a person. The limitation does not include specifics that adequately demonstrate an improvement to the technology. Moreover, limitations above using the LLM provide nothing more than mere instructions to implement an abstract idea on a generic computer. See MPEP 2106.05(f). MPEP 2106.05(f) provides the following considerations for determining whether a claim simply recites a judicial exception with the words “apply it” (or an equivalent), such as mere instructions to implement an abstract idea on a computer: (1) whether the claim recites only the idea of a solution or outcome i.e., the claim fails to recite details of how a solution to a problem is accomplished; (2) whether the claim invokes computers or other machinery merely as a tool to perform an existing process; and (3) the particularity or generality of the application of the judicial exception. Here, the claim recites no details about a particular LLM. The LLMis used to generally apply the abstract idea (i.e., perform the performing analysis on portions of data) without placing any limitation on how the LLM operates. In addition, the limitation would cover every mode of implementing the recited abstract idea using a LLM. The claim omits any details as to how the LLM solves a technical problem and instead recites only the idea of a solution or outcome. See MPEP 2106.05(f).
While claim 1 recite additional components in the form of an online system and a database, these components are recited at a high level of generality, which do not add meaningful limits on the recited abstract idea to integrate it into a practical application by providing an improvement to the functioning of a computer or technology, implementing the abstract idea with a particular machine or manufacture that is integral to the claim, effecting a transformation or reduction of a particular article to a different state or thing, nor applying the abstract idea in some meaningful way beyond linking its use to computer technology. See MPEP 2106.04(d).
For at least these reasons, claim 1 does not integrate the judicial exception into a practical application.
Pursuant to Step 2B, claims are analyzed to determine whether the claim as a whole amounts to significantly more than the recited exception i.e., whether any additional element, or combination of additional elements, adds an inventive concept to the claim. See MPEP 2106.05. In this case, claim 1 does not recite limitations that amount to significantly more than the abstract idea. For much of the reasons discussed above, the limitations cannot provide an inventive concept as they are essentially reciting steps at a high level and do not recite specific limitations that demonstrate an improvement or amount to significantly more than the abstract idea. See MPEP 2106.05(f). At Step 2B, the evaluation of the insignificant extra-solution activity consideration takes into account whether or not the extra-solution activity is well understood, routine, and conventional in the field. See MPEP 2106.05(g). The limitations indicated above as directed to IESA as generally directed to the form of receiving or transmitting data over a network, e.g., using the Internet to gather data, which is well understood, routine, and conventional. See MPEP 2106.05(d), subsection II. Even when considered in combination, these additional elements represent mere instructions to implement an abstract idea or other exception on a computer and insignificant extra-solution activity, which do not provide an inventive concept. For at least these reasons, claim 1 is nonstatutory because they are directed to a judicial exception without significantly more.
Claim 2
Pursuant to step 2A, part 1, claim 2 depends on claim 1 and therefore recites the same abstract idea. Pursuant to step 2A, part 2, claim 2 recites the additional limitations of wherein the first portion and the second portion each comprise substantially equal subsets of the set of data. The limitation is essentially IESA because it merely specifies or selects the type of data that is to be manipulated. MPEP 2106.05(g). Therefore, these additional limitations do not integrate the abstract idea into a practical application. Pursuant to step 2B, for at least the same reasons explained, these additional limitations do not provide an inventive concept. For at least these reasons, claim 2 is directed to a judicial exception without significantly more.
Claim 3
Pursuant to step 2A, part 1, claim 3 depends on claim 1 and therefore recites the same abstract idea. Pursuant to step 2A, part 2, claim 3 recites the additional limitations of wherein the first portion and the second portion each comprise a semantically segmented subset of the set of data. The limitation is essentially IESA because it merely specifies or selects the type of data that is to be manipulated. MPEP 2106.05(g). Therefore, these additional limitations do not integrate the abstract idea into a practical application. Pursuant to step 2B, for at least the same reasons explained, these additional limitations do not provide an inventive concept. For at least these reasons, claim 3 is directed to a judicial exception without significantly more.
Claim 4
Pursuant to step 2A, part 1, claim 4 depends on claim 1 and therefore recites the same abstract idea. Pursuant to step 2A, part 2, claim 4 recites the additional limitations of wherein receiving the analysis request from the user comprises: receiving the analysis request through a chat user interface presented on a display of a client device of the user. The limitation recites the additional component of a display, which is recited at a high level of generality and does not provide meaningful limits on the abstract idea. The remaining portion of the limitation is directed to IESA in the form of receiving data. Although a chat interface is recited, it is not recited in a manner that provides any meaningful limits on the abstract idea. Therefore, these additional limitations do not integrate the abstract idea into a practical application. Pursuant to step 2B, for at least the same reasons explained, these additional limitations do not provide an inventive concept. For at least these reasons, claim 4 is directed to a judicial exception without significantly more.
Claim 5
Pursuant to step 2A, part 1, claim 5 depends on claim 1 and therefore recites the same abstract idea. Pursuant to step 2A, part 2, claim 5 recites the additional limitations of (1) receiving, through a user interface presented to the user on a display of a client device, input parameters for the recursive prompting and (2) generating the initialization prompt based on the input parameters. Limitation (1) is directed to IESA in the form of receiving data. It recites the additional component of a display, but it is recited at a high level of generality and does not provide meaningful limits on the abstract idea. Limitation (2) is directed to a mental step of generating the initialization prompt, which can be performed by a person. The limitation does recite specifics that adequately demonstrate an asserted improvement and merely requires use of input parameters to generate the prompt. Therefore, these additional limitations do not integrate the abstract idea into a practical application. Pursuant to step 2B, for at least the same reasons explained, these additional limitations do not provide an inventive concept. For at least these reasons, claim 5 is directed to a judicial exception without significantly more.
Claim 6
Pursuant to step 2A, part 1, claim 6 depends on claim 1 and therefore recites the same abstract idea. Pursuant to step 2A, part 2, claim 6 recites the additional limitations of wherein the merge prompt template includes fields for outputs generated by applying the recursive process to the first portion and the second portion. The limitation identifies fields in a merge prompt template, but amounts to merely tying the limitation to a field of technology. It otherwise does not recite specifics that would adequately demonstrate an improvement to the technology. Therefore, these additional limitations do not integrate the abstract idea into a practical application. Pursuant to step 2B, for at least the same reasons explained, these additional limitations do not provide an inventive concept. For at least these reasons, claim 6 is directed to a judicial exception without significantly more.
Claim 7
Pursuant to step 2A, part 1, claim 7 depends on claim 6 and therefore recites the same abstract idea. Pursuant to step 2A, part 2, claim 7 recites the additional limitations of wherein the merge prompt template includes fields for text descriptions of the first portion and the second portion in association with the corresponding fields for the outputs. The limitation is similar to those discussed in the rejection of claim 6 above. Accordingly, the same rationale applies. Therefore, these additional limitations do not integrate the abstract idea into a practical application. Pursuant to step 2B, for at least the same reasons explained, these additional limitations do not provide an inventive concept. For at least these reasons, claim 7 is directed to a judicial exception without significantly more.
Claim 8
Pursuant to step 2A, part 1, claim 8 depends on claim 1 and therefore recites the same abstract idea. Pursuant to step 2A, part 2, claim 8 recites the additional limitations of wherein the merge prompt template includes a field for some or all of the set of data. The limitation is similar to those discussed in the rejection of claim 6 above. Accordingly, the same rationale applies as the limitation merely requires that the template has fields for data without recite specifics that demonstrate an improvement to the technology. Therefore, these additional limitations do not integrate the abstract idea into a practical application. Pursuant to step 2B, for at least the same reasons explained, these additional limitations do not provide an inventive concept. For at least these reasons, claim 8 is directed to a judicial exception without significantly more.
Claim 9
Pursuant to step 2A, part 1, claim 9 depends on claim 1 and therefore recites the same abstract idea. Pursuant to step 2A, part 2, claim 9 recites the additional limitations of wherein applying the recursive process to the first portion comprises: determining whether the first portion meets the terminating condition. The limitation is directed to a mental step of determination that would involve evaluation and judgment by a person. The limitation does not recite additional specifics as to how the determination is performed that would make it impossible or impractical for a person to perform. Accordingly, it does not recite specifics that would adequately demonstrate an improvement to the technology. Therefore, these additional limitations do not integrate the abstract idea into a practical application. Pursuant to step 2B, for at least the same reasons explained, these additional limitations do not provide an inventive concept. For at least these reasons, claim 9 is directed to a judicial exception without significantly more.
Claim 10
Pursuant to step 2A, part 1, claim 10 depends on claim 9 and therefore recites the same abstract idea. Pursuant to step 2A, part 2, claim 10 recites the additional limitations of responsive to determining that the first portion does not meet the terminating condition, applying the recursive process to subsets of the first portion. The limitation is directed to a step of applying in response to the determination recited in claim 9. The limitation does not recite specifics as to how the application is performed. It is recited at a high level and does not contain specifics that would adequately demonstrate an asserted improvement to the technology. Therefore, these additional limitations do not integrate the abstract idea into a practical application. Pursuant to step 2B, for at least the same reasons explained, these additional limitations do not provide an inventive concept. For at least these reasons, claim 10 is directed to a judicial exception without significantly more.
Claims 11-20 recite essentially the same subject matter as claims 1-10, respectively, in the form of non-transitory computer-readable medium. Therefore, they are rejected for the same reasons. The additional component of a non-transitory computer readable medium is recited at a high level of generality and does not provide meaningful limits on the abstract idea. Therefore, it cannot integrate the abstract idea and cannot provide an inventive step that amounts to significantly more.
Claims 1-20 are therefore not drawn to eligible subject matter as they are directed to an abstract idea without significantly more.
To expedite a complete examination of the instant application, the claims rejected under 35 U.S.C. 101 (nonstatutory) above are further rejected as set forth below in anticipation of applicant amending these claims to overcome the rejection.
Note on Prior Art Rejections
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Gajek et al. (US Patent 11,861,320) (Gajek) in view of Edwards et al. (US Patent Pub 2024/0394481) (Edwards).
In regards to claim 1, Gajek discloses a method comprising:
receiving, at an online system, an analysis request from a user, wherein the analysis request comprises free text requesting analytics of a set of data stored by the online system in a database (Gajek at col. 5, lines 56-67; col. 6, lines 1-3)1;
determining a prompt template, such as a consolidation template, for the particular flow (Gajek at col. 11, lines 22-42);
generating a response to the analysis request by applying a recursive process to the set of data (Gajek at Fig. 9; col. 20, lines 32-67; col. 21, lines 1-28; col. 23, lines 29-32)2, wherein the recursive process comprises:
determining whether a terminating condition for the recursive process is met (Gajek at col. 13, lines 55-58)3; and
responsive to determining that the terminating condition is not met (Gajek at col. 13, lines 66-67):
applying the recursive process to a first portion of the set of data to generate a first output, wherein applying the recursive process to the first portion comprises applying the analysis request to the first portion of the set of data using the large language model (Gajek at col. 14, lines 13-38, 59-67)4;
applying the recursive process to a second portion of the set of data to generate a second output, wherein applying the recursive process to the second portion comprises applying the analysis request to the second portion of the set of data using the large language model (Gajek at col. 14, lines 13-38, 59-67)5;
generating a merge prompt based on the merge prompt template, the first output, and the second output (Gajek at col. 23, lines 4-21; col. 38, lines 1-43)6;
transmitting the merge prompt to the large language model (Gajek at col. 23, lines 14-17)7; and
receiving a response to the merge prompt from the large language model (Gajek at col. 23, lines 28-32)8; and
transmitting a response to the analysis request based on the received response to the merge prompt. Gajek at col. 23, lines 28-32.9
Gajek does not expressly disclose generating an initialization prompt, wherein the initialization prompt comprises text instructions a LLM to generate a merge prompt template based on the analysis request, transmitting the initialization prompt to the large language model, and receiving a response to the initialization prompt, wherein the response comprises the merge prompt template. As noted above, Gajek does disclose generating an initialization prompt to determine and select a prompt template, such as a consolidation prompt template. What is not expressly disclosed is the generation of a prompt template based on a received request.
Edwards discloses a system and method for prompt generation. The method includes an initial prompt template generation prompt that includes constraints to be applied when a prompt is generated by an LLM using the template, which are based on the desired task (i.e., based on the analysis request). Edwards at paras. 0045, 0048. The method includes communicating the instruction prompt to a prompt template generation module at a first LLM (i.e., transmitting the initialization prompt to the LLM). Edwards at para. 0055. The generated candidate templates are returned from the LLM and stored, tested, and further stored for future use to generate prompts (i.e., receiving a response …). Edwards at para. 0055-56, 0068.
Gajek and Edwards are analogous art because they are directed to the same field of endeavor of LLM prompt based information analysis.
At the time before the effective filing date of the instant application, it would have been obvious to one of ordinary skill in the art to modify Gajek by adding the features of generating an initialization prompt, wherein the initialization prompt comprises text instructions a LLM to generate a merge prompt template based on the analysis request, transmitting the initialization prompt to the large language model, and receiving a response to the initialization prompt, wherein the response comprises the merge prompt template, as disclosed by Edwards.
The motivation for doing so would have been to provide useful workflow automation for desired tasks. Edwards at paras. 0030, 0034.
In regards to claim 2, Gajek in view of Edwards discloses the method of claim 1, wherein the first portion and the second portion each comprise substantially equal subsets of the set of data. Gajek at col. 16, lines 18-20.10
In regards to claim 3, Gajek in view of Edwards discloses the method of claim 1, wherein the first portion and the second portion each comprise a semantically segmented subset of the set of data. Gajek at col. 5, lines 1-9, 32-35; col. 14, lines 27-41.11
In regards to claim 4, Gajek in view of Edwards discloses the method of claim 1, wherein receiving the analysis request from the user comprises: receiving the analysis request through a chat user interface presented on a display of a client device of the user. Gajek at col. 5, lines 57-60.
In regards to claim 5, Gajek in view of Edwards discloses the method of claim 1, further comprising:
receiving, through a user interface presented to the user on a display of a client device, input parameters for the recursive prompting (Gajek at Fig. 8; col. 5, lines 57-60; col. 10, lines 32-48; col. 16, lines 53-64)12; and
generating the initialization prompt based on the input parameters. Gajek at col. 11, lines 21-23.13
In regards to claim 6, Gajek in view of Edwards discloses the method of claim 1, wherein the merge prompt template includes fields for outputs generated by applying the recursive process to the first portion and the second portion. Gajek at col. 23, lines 6-33; col. 38, lines 1-44.14
In regards to claim 7, Gajek in view of Edwards discloses the method of claim 6, wherein the merge prompt template includes fields for text descriptions of the first portion and the second portion in association with the corresponding fields for the outputs. Gajek at col. 23, lines 6-33; col. 38, lines 1-44.15
In regards to claim 8, Gajek in view of Edwards discloses the method of claim 1, wherein the merge prompt template includes a field for some or all of the set of data. Gajek at col. 23, lines 6-33; col. 38, lines 1-44.16
In regards to claim 9, Gajek in view of Edwards discloses the method of claim 1, wherein applying the recursive process to the first portion comprises: determining whether the first portion meets the terminating condition. Gajek at col. 13, lines 55-67; col. 14, lines 1-2, 27-41; col. 20, lines 60-67; col. 21, lines 1-4.17
In regards to claim 10, Gajek in view of Edwards discloses the method of claim 9, further comprising: responsive to determining that the first portion does not meet the terminating condition, applying the recursive process to subsets of the first portion. Gajek at Fig. 9; col. 21, lines 6-27; col. 22, lines 62-67; col. 23, lines 1-33.18
Claims 11-20 are essentially the same as claims 1-10, respectively, in the form of a non-transitory computer readable medium. Gajek at col. 38, lines 56-63. Therefore, they are rejected for the same reasons.
Additional Prior Art
Additional relevant prior art are listed on the attached PTO-892 form. Some examples are:
Almaer et al. (US Patent 12,411,841) discloses a system and method for generating source code using AI models and templates.
Gardner (US Patent Pub 2024/0296279) discloses a system and method for using LLMs for document based tasks and splitting documents based on context window size.
Siracusano et al. (US Patent Pub 2024/0411994) discloses a system and method for extraction information from reports using LLMs.
Krishnan et al. (US Patent Pub 2025/0005050) discloses a system and method for generative summarization in an information retrieval system that uses prompt templates.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Examiner Michael Le whose telephone number is 571-272-7970 and fax number is 571-273-7970. The examiner can normally be reached Mon-Fri 9:30 AM – 6 PM.
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, Tony Mahmoudi can be reached on 571-272-4078. 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.
/MICHAEL LE/Examiner, Art Unit 2163
/TONY MAHMOUDI/Supervisory Patent Examiner, Art Unit 2163
1 A user can submit a query request (i.e., analysis request) in a chat session (i.e., free text) pertaining to identified documents/text that can be in a repository or returned from a database (i.e., stored … in a database).
2 In response to the received input, the documents (i.e., set of data) are analyzed to produce summaries in a process that chunks the documents to process the chunks within the allowed context size limitations (i.e., apply recursive process).
3 Determining whether a text portion fits within a chunk based on a max chunk size.
4 Text portion (i.e., first portion) is analyzed using the text generation system (i.e., LLM).
5 Another text portion is selected if they are available, or until a condition is met (i.e., second portion).
6 Consolidation prompts are generated to consolidate the summaries. The prompts use the consolidation prompt template, which includes partial results (i.e., first and second output).
7 The consolidation prompt is sent to the text generation modeling system (i.e., LLM).
8 A result of the consolidation prompt is received.
9 The consolidated output is presented to the client.
10 Text portions are divided into text chunks equally (i.e., substantially equal subsets…).
11 Text portions are chunked to ensure semantically similar elements are chunked together (i.e., semantically segmented …).
12 User inputs their query (i.e., analysis request) through a chat interface using their client device. The input includes instructions, input data (i.e., input parameters).
13 The prompt template is determined based on input. This is interpreted as generating the initialization prompt because the initialization prompt instructs the LLM to generate an appropriate prompt template. In combination with Edwards, an appropriate prompt template can be created and selected.
14 The consolidation prompt includes a prompt template to consolidate the answers into one answer. The template contains fields for partial answers (i.e., fields for outputs …).
15 The consolidation prompt template contains fields for partial answers and summaries (i.e., text descriptions …).
16 The consolidation prompt template includes fields identifying subsets of the set of data input.
17 A determination is made if selected portion exceeds the max chunk size (i.e., does not meet termination condition).
18 If the selected portion exceeds the max chunk size, it is further chunked and parsed for summarization (i.e., applying recursive process to subsets of first portion).