DETAILED ACTION
This office action is in response to Applicant’s submission filed on 4/23/2025. Claims 1-10 are pending in the application of which Claims 1, 9, and 10 are independent and have been examined.
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 .
Priority
Acknowledgment is made of applicant’s claim for foreign priority under 35 U.S.C. 119 (a)-(d). The certified copy has been filed in parent Application No. JP2024-084612, filed on 5/24/2024.
Information Disclosure Statement
The information disclosure statement(s)(IDS) submitted on 4/23/2025 has been considered by the examiner.
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.
Claim 10 is rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter. The claims do not fall within at least one of the four categories of patent eligible subject matter because claim 10 recites “a generation support program” (understood as stated above in the claim objection to have been a computer program product, but presently is simply “software per se”), and which comprises “computer readable storage media”, where Applicants have not provided an explicit definition in their Specification that “computer readable storage media” does not include signals per se. Applicant can overcome this rejection by amending claim 10 to recite “one or more non-transitory computer readable storage media,” and amending “A generation support program” to be “A computer program product.”
Claims 1- 10 are rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter without significantly more. The claims as whole, considering all claim elements both individually and in combination, do not amount to significantly more than an abstract idea.
The group of independent claims 1, 9, and 10 disclose the same inventive concept with slightly different claim language. In this analysis, claim 1 is analyzed as a representative of the other independent claims. The independent claim 1 recites: “ … wherein when a natural sentence that is text data of a natural language is inputted, the generation support system accesses a language model that interprets the natural sentence and that probabilistically predicts an answer sentence to the natural sentence, and wherein the processor executes: a first requesting process of outputting a generation-source ticket of the natural sentence related to an incident, a check item group to be checked for the incident, and a first prompt that is the natural sentence requesting that an answer sentence about each check item of the check item group be generated with reference to the generation-source ticket, to the language model; a first acquiring process of causing the language model to acquire a postmortem including a result of a first trial of generation of an answer sentence about the each check item in the first prompt, as a result of output of the generation-source ticket, the check item group, and the first prompt by the first requesting process; and a first output process of outputting the postmortem acquired by the first acquiring process.
The aforementioned limitations, under its broadest reasonable interpretation, cover performance of the limitation in the mind but for the recitation of generic computer components. That is, other than reciting “language model”, and “processor”, nothing in the claim element precludes the step from practically being performed in the mind. For example, but for the “language model”, and “processor” language “,
“wherein when a natural sentence that is text data of a natural language is inputted,” in the context of this claim it amounts to providing data for an activity, i.e. a teacher ask a student for a summary report to be generated and he provide the needed material.
“the generation support system accesses a language model that interprets the natural sentence and that probabilistically predicts an answer sentence to the natural sentence, and” in the context of this claim, student provides an answer based on the input he received
“wherein the processor executes: a first requesting process of outputting a generation-source ticket of the natural sentence related to an incident,” in the context of this claim, student creates a note (source ticket) as what is the issue is and what needs to be done.
“a check item group to be checked for the incident, and” checking out the items inputted toward ticket creation, and in the context of this claim, student validate/check the data he received for completion.
“a first prompt that is the natural sentence requesting that an answer sentence about each check item of the check item group be generated with reference to the generation-source ticket, to the language model;” in the context of this claim, the student would check each component/item of the report.
“a first acquiring process of causing the language model to acquire a postmortem including a result of a first trial of generation of an answer sentence about the each check item in the first prompt, as a result of output of the generation-source ticket, the check item group, and the first prompt by the first requesting process; and” In the context of this claim, student provide a summary (postmortem) of the report which includes all the answers for each item.
“a first output process of outputting the postmortem acquired by the first acquiring process. “In the context of this claim, student provides the summary (postmortem) and share it with the teacher.
All of these steps (as noted above) can be performed in the mind and/or using a pen and paper. 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. Accordingly, the claim recites an abstract idea.
This judicial exception is not integrated into a practical application. In particular, the claim only recites additional elements - using a “language model”, and “processor” to perform all of the above-mentioned steps. The use of a “language model”, and “processor” is recited at a high-level of generality (i.e., as a generic computer device performing a generic computer function) 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. The only element mentioned is the usage of a “language model”, which due to lack of specificity can be considered as a generic processor. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of a processor is merely for the purpose of data gathering and/or insignificant extra-solution activity that amount 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 is not patent eligible.
The dependent Claims do not add limitations that could help the Claim as a whole to amount to significantly more than the Abstract idea identified for the Independent Claim:
Similarly, dependent claims 2- 8 are also not patent eligible as they include additional steps that are directed towards an abstract idea as they can be practically performed in the mind without being integrated into a practical application or including any additional elements sufficient to amount to significantly more than the judicial exception.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 9 and 10 are rejected under 35 U.S.C. 103 as being unpatentable over Salinas et al. (US11218357B1)(herein " Salinas "), and in further view of Jin et al. (“Assess and Summarize: Improve Outage Understanding with Large Language Models”)(herein "Jin").
Regarding claims 1, 9 and 10, Salinas teaches [A generation support system comprising: a processor that executes a program; and a storage device that stores the program, - claim 1], [A generation support method executed by a generation support system comprising a processor that executes a program, and a storage device that stores the program, - claim 9], and [A generation support program causing a processor that, - claim 10] (Salinas, Col. 2, ll. 50-52:” incident service 120 may employ a “ticket” system, wherein users and analysts of the environment may report incidents.”, and Col. 11, ll. 23-24:” retrieves and executes operating software 607 from memory device 606.”, and Col. 11, ll. 46-54:” … includes incident module 608, correlation module 609, and summary module 610, … When executed by processing circuitry 605, operating software 607 directs processing system 603 to operate computing system 600”).
[a first requesting process of outputting a generation-source ticket of the natural sentence related to an incident, - claims 1, and 10], [wherein the method causes the processor to execute: a first requesting process of outputting a generation-source ticket of the natural sentence related to an incident, - claim 9] (Salinas, Col. 2, ll. 50-65:” … incident service 120 may employ a “ticket” system, wherein users and analysts of the environment may report incidents. For example, when an email is received from an unknown source seeking personal information, the receiving user of the email may report the email as an incident such that incident service 120 may process the incident. When reported, the end user may provide information about the incident, however, automated processes may identify additional information for the incident, such as a source domain for the email, specific content or links within the email, or some other similar information that may assist incident service 120 in responding to the incident. This additional information may be determined from local databases or may be gathered from internet resources such as web services and other similar resources.”)
a check item group to be checked for the incident, and (Salinas, Col. 3, LL. 3-9:” … incident service 120 may generate and provide summaries to a responding analyst, wherein the summaries provide information about the incident. This information may include relevant IP addresses, processes, files, threat levels, incident type information, components associated with the incident, or some other type of information related to the incident.”, and Col. 4, ll. 36-45:” … incident service 120 may generate the summary that indicates an update to the quantity of incidents identified with similar attributes, information about the component or user affected by the newly identified incident, any modified values (total packets transferred, components affected, etc.). Thus, if an incident corresponded to a power failure, the summary generated may indicate a current quantity of components affected by power failure, the location or locations of the power failures, or some other similar information about the incidents.”) Note: underlined component mapped to check items.
[[a first prompt that is the natural sentence requesting that an answer sentence ]] about each check item of the check item group be generated with reference to the generation-source ticket, [[to the language model]]; (Salinas uses the incident ticket to gather necessary incident information and subsequently provide an incident summary: Col. 5, line 51- Col.6, line 2:” … obtain information about incidents via tickets from one or more users associated with IT environment 130. In response to identifying the indication of the incident, incident service 120 determines, at step 2, correlated incidents to incident 320. In some examples, to determine the correlated incidents, incident service 120 may access incident database 150, wherein incident database 150 may maintain information about other incidents associated with IT environment 130. Incident service 120 may maintain the information for incident database 150 or may rely on other services and systems to update incident database 150. In some implementations, as incidents are identified, data for the incidents may be stored in incident database 150 such that the data can be compared to later incidents identified in IT environment 130. Accordingly, when incident 320 is identified, incident service 120 may access incident database 150 to compare at least a portion of the data associated with incident 320 with the incident data for previously identified incidents.”, and Col. 6, ll. 66-67:” … generate a summary based on the aggregated incident data.”) Note: a generated incident summary reads on answer sentence for each check item.
[[in the first prompt,]] as a result of output of the generation-source ticket, the check item group, [[and the first prompt by the first requesting process]]; and (Salinas, as disclosed earlier (Col. 2, ll. 50-65, Col. 3, LL. 3-9, and Col. 4, ll. 36-45) provides the incident/ticket source.)
a first output process of outputting the postmortem acquired by the first acquiring process. (Salinas, Col. 5, ll. 5-7:” … incident service 120 may generate a notification that includes at least a portion of the summary for display to the selected analyst.”)
Salinas, does not teach, however Jin teaches [wherein when a natural sentence that is text data of a natural language is inputted, (Jin, Page 1662, Section 4.3:” GPT-x. Generative Pre-trained Transformer x (GPT-x) [3] is a large pretrained language model that can tackle a wide range of natural language processing (NLP) tasks. One typical usage scenario of GPT-x is text completion, where the model is given a block of text as context and generates text as the completion of the context. … we process the structural incident information into a paragraph of text so that the GPT-3 model can take it as input, i.e., context.”)
the generation support system accesses a language model that interprets the natural sentence and that probabilistically predicts an answer sentence to the natural sentence, and (Jin, Page 1658, Section 1:” After we obtain relevant incidents of the outage, we adopt the most popular pre-trained large language models GPT-3.x (both GPT- 3.0 and GPT-3.5), to automatically generate outage summaries. This task presents two main challenges: 1) identifying which information on relevant incidents is helpful to outage summarization; 2) identifying how to effectively generate domain-specific outage summaries with complex cloud-related information.”, and Page 1662, Section 4.3:” GPT-x. Generative Pre-trained Transformer x (GPT-x) [3] is a large pretrained language model that can tackle a wide range of natural language processing (NLP) tasks. One typical usage scenario of GPT-x is text completion, where the model is given a block of text as context and generates text as the completion of the context. … we append an instruction to the end of the text to hint the GPT-3 model to generate a summary:”)
a first prompt that is the natural sentence requesting that an answer sentence [[about each check item of the check item group be generated with reference to the generation-source ticket,]] to the language model; (Jin teaches structural incident information that is transformed into text so GPT-3 can take it as input/context. Then: an instruction is appended to the text to cause GPT-3 to generate a summary: Page 1662, Section 4.3:” GPT-x. Generative Pre-trained Transformer x (GPT-x) [3] is a large pretrained language model that can tackle a wide range of natural language processing (NLP) tasks. One typical usage scenario of GPT-x is text completion, where the model is given a block of text as context and generates text as the completion of the context. … we append an instruction [prompt] to the end of the text to hint the GPT-3 model to generate a summary:”)
a first acquiring process of causing the language model to acquire a postmortem (Jin generates outage summaries using an LLM: Page 1662, Section 4.3:” After gathering relevant incidents of an outage, Oasis generates a summary of the outage based on the incidents’ information. … we fine-tune an LLM, i.e., GPT-x, to summarize the relevant incidents.”) Note: a postmortem is essentially a particular form of incident/outage report.
including a result of a first trial of generation of an answer sentence about the each check item (Jin, Page 1663, Section 5.3: “we get five candidate generated texts from each model, except for the joint incident summary which can only give one piece of generation. To better evaluate the quality of generation models, we calculate the Top1 metrics using the first generated text, and the Top5 metrics using the best of five generated text.”) Note: candidate summaries, which read on “an answer for each check item”, are generated and that the first generated text can be evaluated. The evaluation explicitly uses the first generated text as a Top-1 candidate.
in the first prompt, [as a result of output of the generation-source ticket, the check item group,]] and the first prompt by the first requesting process; and (Jin, as shown earlier (see Page 1662, Section 4.3) provides the LLM/context/prompt/generation mechanism.)
Jin is considered to be analogous to the claimed invention because it is in the same field of endeavor. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Salinas further in view of Jin to wherein when a natural sentence that is text data of a natural language is inputted, the generation support system accesses a language model that interprets the natural sentence and that probabilistically predicts an answer sentence to the natural sentence, and a first prompt that is the natural sentence requesting that an answer sentence [[about each check item of the check item group be generated with reference to the generation-source ticket,]] to the language model; a first acquiring process of causing the language model to acquire a postmortem including a result of a first trial of generation of an answer sentence about the each check item in the first prompt, [[as a result of output of the generation-source ticket, the check item group,]] and the first prompt by the first requesting process. Motivation to do so would automatically assess impacts and summarize incidents such as outage while assessing the effect by aggregating relevant incidents and finally generating a human-readable summary by leveraging finetuned large language models.
Claim 2 is rejected under 35 U.S.C. 103 as being unpatentable over Salinas and Jin, and in further view of Poonam Rath (US20210328888A1)(herein "Rath").
Regarding claim 2, Salinas, as modified above, teaches the system of claim 1.
Salinas, as modified above, further teaches wherein in the first output process, the processor outputs the first postmortem for which whether the insufficient item is present therein is determined by the first determining process. (Salinas, Col. 5, ll. 5-7:” … incident service 120 may generate a notification that includes at least a portion of the summary for display to the selected analyst.”)
Salinas, as modified above, does not teach, however, Rath teaches wherein the processor executes a first determining process of determining whether an insufficient item is present in a first postmortem acquired by the first acquiring process, the insufficient item being a check item among the check item group that gives the result of the first trial that is not an answer sentence allowing check of the check item, and (Rath, Par. 0093:” In addition to identifying historical sequences of topics, for historical support tickets, which are similar to the support ticket's sequence of topics, a type of information is optionally identified which is associated with a topic that is in the historical sequences of topics and that is absent from the sequence of topics, block 410. The system can identify information in similar support tickets but missing from the support ticket to forecast a support ticket's resolution. By way of example and without limitation, this can include the ticket summarizer, classifier, and forecaster machine-learning model 228 identifying that most of the similar sequences of topics include information that specifies the customer's operating system, but at 5:00 P.M. the support ticket's sequence of topics is missing any information that specifies the customer Curt's operating system.”) Note: A missing/absent/insufficient item read on “the result of the first trial that is not an answer sentence allowing check of the check item”, since any insufficient item would not provide condition under which allowing check of the check item.
Rath is considered to be analogous to the claimed invention because it is in the same field of endeavor. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Salinas, as modified above, further in view of Rath to wherein the processor executes a first determining process of determining whether an insufficient item is present in a first postmortem acquired by the first acquiring process, the insufficient item being a check item among the check item group that gives the result of the first trial that is not an answer sentence allowing check of the check item. Motivation to do so would ensure reception of uniform data, making it possible to categorize, prioritize, and route the incident accurately.
Claims 3-5 are rejected under 35 U.S.C. 103 as being unpatentable over Salinas, Jin, and Rath, and in further view of Kumar et al. (US11855860B1)(herein "Kumar").
Regarding claim 3, Salinas, as modified above, teaches the system of claim 2.
Salinas, as modified above, does not teach, however, Jin further teaches [[a second requesting process of outputting the related ticket retrieved by the search process and]] a second prompt requesting generation of the answer sentence about the insufficient item using the related ticket, to the language model; (Jin, Page 1658, Section 1:” After we obtain relevant incidents of the outage, we adopt the most popular pre-trained large language models GPT-3.x (both GPT- 3.0 and GPT-3.5), to automatically generate outage summaries. This task presents two main challenges: 1) identifying which information on relevant incidents is helpful to outage summarization; 2) identifying how to effectively generate domain-specific outage summaries with complex cloud-related information.”, and Page 1662, Section 4.3:” GPT-x. Generative Pre-trained Transformer x (GPT-x) [3] is a large pretrained language model that can tackle a wide range of natural language processing (NLP) tasks. One typical usage scenario of GPT-x is text completion, where the model is given a block of text as context and generates text as the completion of the context. … we append an instruction [prompt] to the end of the text to hint the GPT-3 model to generate a summary:”) Note: Jin teaches an instruction/prompt being appended to incident information to direct GPT-3.x to generate the desired summary. The same can be used to generate an answer concerning the missing/insufficient information item, which is a design choice.
Salinas, as modified above, does not teach, however, Rath further teaches wherein the processor executes: a search process of retrieving a related ticket related to the generation-source ticket, from a ticket group, based on a search query about the insufficient item; (Rath, Par. 0093:” In addition to identifying historical sequences of topics, for historical support tickets, which are similar to the support ticket's sequence of topics, a type of information is optionally identified which is associated with a topic that is in the historical sequences of topics and that is absent from the sequence of topics, block 410. The system can identify information in similar support tickets but missing from the support ticket to forecast a support ticket's resolution. By way of example and without limitation, this can include the ticket summarizer, classifier, and forecaster machine-learning model 228 identifying that most of the similar sequences of topics include information that specifies the customer's operating system, but at 5:00 P.M. the support ticket's sequence of topics is missing any information that specifies the customer Curt's operating system.”)
a second requesting process of outputting the related ticket retrieved by the search process and [[a second prompt requesting generation of the answer sentence about the insufficient item using the related ticket, to the language model]]; (As mapped earlier Jin discloses (See 1658, Section 1) identification of relevant incidents, processes incident text, supplies the processed text to GPT-3.x and returns the generated summary, plus an instruction/prompt to an LLM. However, Jin does not teach outputting the related ticket, but Rath teaches in Par. 0093:” In addition to identifying historical sequences of topics, for historical support tickets, which are similar to the support ticket's sequence of topics, a type of information is optionally identified which is associated with a topic that is in the historical sequences of topics and that is absent from the sequence of topics, block 410.”, and Par. 0099:” Along with outputting the at least one subsequent topic, a suggestion is optionally output for a support person who is associated with at least one of the historical sequences of topics …”)
Salinas, as modified above, does not teach, however, Kumar teaches a second acquiring process of causing the language model to acquire a result of a second trial of generation of an answer sentence about the insufficient item in the second prompt, as a result of output of the related ticket and the second prompt by the second requesting process; and (Kumar, Col. 1, ll. 15-16:”ML models are designed to generate articles, essays, or other compositions, in response to a provided prompt or topic.”, and Col. 1, ll. 54-65:”an iterative processing of the plurality of resolved incident tickets to obtain processed incident tickets, including: (a) processing each resolution statement of the resolution with at least one domain-specific statement classifier that is specific to the incident domain to either discard or retain a classified resolution statement, (b) processing each retained classified resolution statement in conjunction with the worklog to determine whether to discard or retain the resolved incident, (c) providing an updated resolution for the resolved incident when the resolved incident is retained, and (d) adding the resolved incident with the updated resolution to the processed incident tickets. When executed by the at least one computing device, the instructions may be further configured to cause the at least one computing device to train at least one machine learning model to process a new incident ticket including generating a new resolution statement using a new worklog of the new incident ticket, using the processed incident tickets.”, and Col. 2, ll. 50-52:” large language models (LLMs) used to generate outputs of desired types and quantities of content in response to received inputs. “) Note: The iterative process as note above reads on a second process to acquire a result of second trial.
a second output process of outputting the result of the second trial acquired by the second acquiring process. (Kumar, Col. 2, ll. 50-52:” large language models (LLMs) used to generate outputs of desired types and quantities of content in response to received inputs. “)
Kumar is considered to be analogous to the claimed invention because it is in the same field of endeavor. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Salinas, as modified above, further in view of Kumar to a second acquiring process of causing the language model to acquire a result of a second trial of generation of an answer sentence about the insufficient item in the second prompt, as a result of output of the related ticket and the second prompt by the second requesting process; and a second output process of outputting the result of the second trial acquired by the second acquiring process. Motivation to do so would improve the quality of data in the resolution field of an incident ticket, which facilitates and improves future automation of the incident handling system (Kumar, Col. 13, ll. 18-20).
Regarding claim 4, Salinas, as modified above, teaches the system of claim 3.
Salinas, as modified above, does not teach, however, Rath further teaches wherein each ticket of the ticket group includes a ticket summary vector that is an embedded expression made by vectorizing a ticket summary text summarizing the ticket, and (Rath, Par. 0039:” … The ticket summarizer, classifier, and forecaster machine-learning models 222 and/or 228 can create an enriched representation of a sequence of topics for a support ticket in the form of a single numeric support ticket vector that contains information determined from content data, metadata, and possibly context data for individual communication text 306.”, and Par. 0040:”… the communication embedding 338 of both FIG. 3A and FIG. 3C. As also described below, the communication embedding 338 is used by a support ticket summary builder 340 to build summaries of support ticket, which may be stored in a support ticket summary store 342.”)
wherein in the search process, the processor retrieves a ticket that corresponds to a search query about the insufficient item and that has a ticket summary vector whose distance to a ticket summary vector of the generation-source ticket is equal to or less than a given distance, from the ticket group, as the related ticket. (Rath, Par. 0047:” The ticket summarizer, classifier, and forecaster machine-learning models 222 and/or 228 can generate these embeddings by using embedding models trained on a corpus of representative data from a support organization's support ticket archive database [ticket group].”, and Par. 0052:” … the ticket summarizer, classifier, and forecaster machine-learning models 222 and/or 228 can leverage time series similarity search techniques such as Symbolic Aggregate approXimation (SAX) and Dynamic Time Warping (DTW) to compute alignments between any two support tickets and generate their corresponding similarity score.”, and Par. 0057:” The ticket summarizer, classifier, and forecaster machine-learning model 228 can identify historical support tickets that have similar sequences of topics to the current support ticket's sequence of topics, and therefore had similar amounts of resolution progress at similar communication times to the current amount of resolution progress at the most recent communication time of the current support ticket.”, and Par. 0060:” After identifying a sequence of topics as a summary of a current support ticket, the ticket summarizer, classifier, and forecaster systems 218 and/or 224 then identifies older support tickets, from the support ticket summary store 342, which had starting sequences of topics that are similar to the current support ticket's entire sequence of topics, and then uses the similar starting sequences of topics to infer or forecast the future sequence of topics for the current support ticket.”, and Par. 0056:” .. compute single support ticket vectors to represent an entire support ticket, the ticket summarizer, classifier, and forecaster machine-learning models 222 and/or 228 can compute similarity across support tickets by any number of mathematical and statistical distance metrics, such as Euclidean distance, Minkowski distance, Manhattan distance, correlation distance, and cosine distance. Additionally, the ticket summarizer, classifier, and forecaster machine-learning models 222 and/or 228 can apply normalization steps to the distance vectors to enable each of the appropriate subsequent computations.”) Note: using Euclidean/cosine/etc. distance reads on distance being less than or equal a threshold distance for the similarity convention.
Regarding claim 5, Salinas, as modified above, teaches the system of claim 3.
Salinas, as modified above, further teaches wherein in the second acquiring process, the processor acquires a second postmortem including the check item group, the result of the first trial, and the result of the second trial, and wherein in the second output process, the processor outputs the second postmortem acquired by the second acquiring process. (Salinas, Col. 2, ll. 52-55:” when an email is received from an unknown source seeking personal information, the receiving user of the email may report the email as an incident such that incident service 120 may process the incident.”, and Col. 3, ll. 52-62:” in matching the data between incidents, incident service 120 may access incident database 150, wherein incident database 150 may cache incident data for previously identified incidents in IT environment 130. In correlating the current incident to one or more other incidents, incident service 120 may compare incident data for the current incidents to other incidents that occurred within a proximity time period to the current incident, to incidents that have not been responded to or have been resolved, or some other subset of the total incidents identified in IT environment 130.”, and Col. 4, ll. 14-21:” Once a correlation is identified between the incident and the one or more other incidents, incident service 120 aggregates (203) incident data associated with the incident with incident data associated with the one or more other incidents. In aggregating the incident data, data values may be summed, combined, or otherwise collected into an aggregated data set for the incident and the one or more other incidents.”, and Col. 4, ll. 27-32:” After aggregating the incident data for the incident and the one or more other incidents, incident service 120 may generate (204) an incident summary based on the aggregated data. In some implementations, the incident summary may indicate updated information regarding the correlated incidents. “, and Col. 5, ll. 5-7:” … incident service 120 may generate a notification that includes at least a portion of the summary for display to the selected analyst.”) Note: The identification of the first incident, and subsequent obtaining a related incident and aggregating the two would result in a incident report which reads on the 2nd postmortem once the incident summary of the aggregated version is created.
Claims 6-7 are rejected under 35 U.S.C. 103 as being unpatentable over Salinas, Jin, Rath and Kumar, and in further view of Gupta et al. (US20240096312A1)(herein "Gupta").
Regarding claim 6, Salinas, as modified above, teaches the system of claim 3.
Salinas, as modified above, does not teach, however, Rath further teaches [[wherein the processor executes a second determining process of determining whether the insufficient item is present,]] based on the result of the second trial acquired by the second acquiring process. (Rath, Par. 0020:” … The ticket summarizer, classifier, and forecaster machine-learning model 228 can automatically use the results of the real-time analysis of subsequent communications to update a support ticket's summary and resolution forecast periodically and then output this updated summary and forecast to end users to ensure that the support ticket's summary and resolution forecast continues to accurately reflect any changes in the support ticket's circumstances.”)
Salinas, as modified above, does not teach, however, Gupta teaches wherein the processor executes a second determining process of determining whether the insufficient item is present, [based on the result of the second trial acquired by the second acquiring process]]. (Gupta, Par. 0088:” … the method includes monitoring in real-time, at the conversation server using the at least one custom ML model and the LLM with the content boundary, a second response provided by the user to the first follow-up question asked by the artificially intelligent bot at the user device, to (a) determine whether the second response is inside or outside of the content boundary associated with the first subsequent state …”).
Gupta is considered to be analogous to the claimed invention because it is in the same field of endeavor. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Salinas, as modified above, further in view of Gupta to based on the result of the second trial acquired by the second acquiring process. Motivation to do so would prevent a ticket from progressing to the next stage unless specific verification fields are filled out.
Regarding claim 7, Salinas, as modified above, teaches the system of claim 6.
Salinas, as modified above, does not teach, however, Gupta further teaches wherein the processor repeatedly executes the search process, the second requesting process, the second acquiring process, and the second output process until determining by the second determining process that the insufficient item is no longer present. (Gupta, Par. 0005:” … ML model with the content boundary, a first response provided by the user to the first question asked by the artificially intelligent bot at the user device, to determine whether the first response is inside or outside of the content boundary associated with the first conversation state, …”, and Par. 0088:” … At step 708, the method includes generating in real-time, at the conversation server using the at least one custom ML model and the LLM, a first follow-up question by performing one of: (a) determining a missing content in the first response using the at least one domain-specific ML model associated … At step 710, the method includes monitoring in real-time, at the conversation server using the at least one custom ML model and the LLM with the content boundary, a second response provided by the user to the first follow-up question asked by the artificially intelligent bot at the user device, to (a) determine whether the second response is inside or outside of the content boundary associated with the first subsequent state and (b) extract a skill level of the user. At step 712, the method includes automatically computing possible paths of the conversation using the at least one custom ML model and the LLM with the second response to obtain an updated N subsequent conversation states of the conversation, wherein the updated N subsequent conversation states optimize contextual information retrieval from the user in the automated conversation based on the skill level of the user. At step 714, the method includes generating in real-time, at the conversation server using the custom ML model and the LLM, a second follow-up question by analyzing at least one of (i) the resume of the user, (ii) the job description, and (iii) the updated N subsequent conversation states with the at least one custom ML model and the LLM, to direct the user to the updated N subsequent conversation states of the conversation. At step 716, the method includes repeating generating follow-up questions for the artificially intelligent bot in real-time at the conversation server using the custom ML model and the LLM for adaptively traversing the N updated conversation states between the user and the artificially intelligent bot to extract contextual information.”) Note: This is essentially a closed-loop verification/iteration limitation and stops when it meets the requirement.
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Salinas and Jin, and in further view of Kumar.
Regarding claim 8, Salinas, as modified above, teaches the system of claim 1.
Salinas, as modified above, does not teach, however, Kumar teaches wherein the generation-source ticket includes a task memo summary text summarizing a task memo describing task content on the incident. (Kumar, Col. 1, ll. 47-51:” each resolved incident ticket having a worklog providing a history of actions taken during attempts to resolve a corresponding resolved incident and a resolution having at least one resolution statement for the corresponding resolved incident.”, and Col. 12, ll. 17-22:” example of a perspective summary generated by the incident handling system of FIG. 1. In FIG. 6, a worklog for ticket 602, similar to the worklog for ticket-2 (412) of FIG. 4, may be processed by a general purpose LLM to generate a summarization 604 of the worklog content.”, and Col. 12, ll. 40-43:” An actionable resolution perspective summary 610 provides a focused statement describing an action(s) taken that successfully resolved the incident, which in this case was the summary phrase …”, and Col. 13, ll. 6-8:” In contrast, described techniques summarize a “perspective” such as actions needed for resolution, and not a pure summary of what happened during an incident lifecycle.”)
Kumar is considered to be analogous to the claimed invention because it is in the same field of endeavor. Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Salinas, as modified above, further in view of Kumar to wherein the generation-source ticket includes a task memo summary text summarizing a task memo describing task content on the incident. Motivation to do so would improve the quality of data in the resolution field of an incident ticket, which facilitates and improves future automation of the incident handling system (Kumar, Col. 13, ll. 18-20).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure. Arthi Venkataraman (US 20170032029 A1) teaches in Par. 0014:” … incident ticket classification system 102 to update an incident ticket classification. The exemplary environment 100 may include an incident ticket classification system 102, an incident ticketing portal 104 and a display 106. The incident ticket classification system 102 may further include a processor 108, a memory 110, an input module 112, and an output module 114 and an incident ticket repository 116. While not shown, the exemplary environment 100 may include additional components, such as database etc. which are well known to those of ordinary skill in the art and thus will not be described here. The incident ticketing portal 104 may be an electronic gateway to a collection of one or more incident tickets raised by a user. One or more incident tickets may be at least one issue or concern or feedback, or the like raised by the user in natural language.”
Examiner's Note: Examiner has cited particular columns and line numbers and/or paragraph numbers in the references applied to the claims above for the convenience of the applicant. Although the specified citations are representative of the teachings of the art and are applied to specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested from the applicant in preparing responses, to fully consider the references in entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the Examiner.
In the case of amending the Claimed invention, Applicant is respectfully requested to indicate the portion(s) of the specification which dictate(s) the structure relied on for proper interpretation and also to verify and ascertain the metes and bounds of the claimed invention.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DARIOUSH AGAHI whose telephone number is (408)918-7689. The examiner can normally be reached Monday - Thursday and alternate Fridays, 7:30-4:30 PT.
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, Bhavesh Mehta can be reached on 571-272-7453. 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.
DARIOUSH AGAHI, P.E.
Primary Examiner
/DARIOUSH AGAHI/Primary Examiner, Art Unit 2656