DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on January 25, 2024 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Priority
Applicant’s claim for the benefit of a prior-filed application under 35 U.S.C. 119(e) or under 35 U.S.C. 120, 121, 365(c), or 386(c) is acknowledged. Applicant has not complied with one or more conditions for receiving the benefit of an earlier filing date under 35 U.S.C. 119(e) as follows:
The later-filed application must be an application for a patent for an invention which is also disclosed in the prior application (the parent or original nonprovisional application or provisional application). The disclosure of the invention in the parent application and in the later-filed application must be sufficient to comply with the requirements of 35 U.S.C. 112(a) or the first paragraph of pre-AIA 35 U.S.C. 112, except for the best mode requirement. See Transco Products, Inc. v. Performance Contracting, Inc., 38 F.3d 551, 32 USPQ2d 1077 (Fed. Cir. 1994).
The disclosures of the prior-filed applications, Application Nos. 63/543,503, 63/527,534, and 63/463,049, fail to provide adequate support or enablement in the manner provided by 35 U.S.C. 112(a) or pre-AIA 35 U.S.C. 112, first paragraph for one or more claims of this application. At least the limitations of “recording of occurrences of collaboration activities by the plurality of user devices over the individual ones of the stored content objects or the one or more chunks; and generating a prompt to a large language model system, wherein contents of the prompt are determined based on correspondence between one or more chunks and one or more of the collaboration activities” are not supported by the prior applications. Accordingly, claims 1-24 are not entitled to the benefit of the prior applications.
Specification
The disclosure is objected to because of the following informalities:
[0001]: the blank Serial No. should be replaced with 18/398,058
[0044]: “answer that that derives” should read “answer that derives”
[0055]: “(not show)” should read “(not shown)”
[0095]: “How many files in this folder contracts?” should read “How many files in this folder are contracts?”
[0105]: “portions corresponding closest matches” should read “portions corresponding to closest matches”
[0117]: “to select only a chapter (e.g., chapter D1CH3) or chapters that have a higher relevance score are selected.” should read “to select only a chapter (e.g., chapter D1CH3) or chapters that have a higher relevance score.”
[0161]: “and/or the , the” should read “and/or the”
[0165]: “populate variable of the template” should read “populate variables of the template”
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.
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 20 and 21 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.
Claims 20 and 21 recite the limitation "The non-transitory computer readable medium of claim 13.” There is insufficient antecedent basis for this limitation in the claims, as claim 13 is a method claim. For examination purposes, Examiner will assume this limitation reads “The non-transitory computer readable medium of claim 14.”
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 1-24 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The analysis of the claims will follow the 2019 Revised Patent Subject Matter Eligibility Guidance (“2019 PEG”).
Claim 1
Step 1: The claim recites a method, and therefore is directed to the statutory category of processes.
Step 2A Prong 1: The claim recites, inter alia:
“identifying one or more chunks that are present in individual ones of the stored content objects”; This limitation encompasses mentally identifying one or more chunks that are present in individual ones of the stored content objects.
“generating a prompt to a large language model system, wherein contents of the prompt are determined based on correspondence between one or more chunks and one or more of the collaboration activities”; This limitation encompasses mentally generating a prompt to a large language model system, by mentally determining contents of the prompt based on correspondence between one or more chunks and one or more of the collaboration activities.
Step 2A Prong 2: This judicial exception is not integrated into a practical application. The claim further recites “configuring the content management system to expose stored content objects to a plurality of user devices through an electronic interface” and “recording of occurrences of collaboration activities by the plurality of user devices over the individual ones of the stored content objects or the one or more chunks,” however these limitations amount to the insignificant extra-solution activity of mere data gathering and outputting (MPEP 2106.05(g)).
Step 2B: The claim does not contain significantly more than the judicial exception. The “configuring the content management system to expose stored content objects…” and “recording of occurrences of collaboration activities…” limitations, in addition to reciting insignificant extra-solution activity, are also directed to the well-understood, routine, and conventional activity of receiving or transmitting data over a network (MPEP 2106.05(d)(II)(i) OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015)). As an ordered whole, the claim is directed to a mentally performable process of identifying one or more chunks that are present in stored content objects, and generating a prompt to a large language model system based on correspondence between one or more chunks and one or more collaboration activities. Nothing in the claim provides significantly more than this. As such, the claim is not patent eligible.
Claim 2
Step 1: A process, as above.
Step 2A Prong 1: The claim recites the same judicial exception as claim 1 above.
Step 2A Prong 2: This judicial exception is not integrated into a practical application. The claim further recites “submitting the prompt to a large language model to get a large language model system answer,” however this limitation amounts to the insignificant extra-solution activity of mere data gathering and outputting (MPEP 2106.05(g)).
Step 2B: The claim does not contain significantly more than the judicial exception. The “submitting the prompt to a large language model…” limitation, in addition to reciting insignificant extra-solution activity, is also directed to the well-understood, routine, and conventional activity of receiving or transmitting data over a network (MPEP 2106.05(d)(II)(i) OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015)).
Claim 3
Step 1: A process, as above.
Step 2A Prong 1: The claim recites, inter alia:
“wherein at least a portion of the prompt comprises contents derived from a prompt template”; This limitation merely further limits the “generating a prompt…” limitation of claim 1, and generating a prompt to a large language model system is still mentally performable when at least a portion of the prompt comprises contents derived from a prompt template, as one can mentally add contents from a prompt template to the prompt.
Step 2A Prong 2: This judicial exception is not integrated into a practical application. No further additional elements are recited, see analysis of claim 1.
Step 2B: The claim does not contain significantly more than the judicial exception. No further additional elements are recited, see analysis of claim 1.
Claim 4
Step 1: A process, as above.
Step 2A Prong 1: The claim recites, inter alia:
“wherein the prompt includes at least a portion that derives from one or more of the chunks”; This limitation merely further limits the “generating a prompt…” limitation of claim 1, and generating a prompt to a large language model system is still mentally performable when the prompt includes at least a portion that derives from one or more of the chunks, as one can mentally add contents from one or more of the chunks to the prompt.
Step 2A Prong 2: This judicial exception is not integrated into a practical application. No further additional elements are recited, see analysis of claim 1.
Step 2B: The claim does not contain significantly more than the judicial exception. No further additional elements are recited, see analysis of claim 1.
Claim 5
Step 1: A process, as above.
Step 2A Prong 1: The claim recites, inter alia:
“wherein the prompt template includes one or more variable fields”; This limitation merely further limits the prompt template of claim 3 used to perform the “generating a prompt…” limitation of claim 1, and generating a prompt to a large language model system is still mentally performable when the prompt template includes one or more variable fields.
Step 2A Prong 2: This judicial exception is not integrated into a practical application. No further additional elements are recited, see analysis of claim 1.
Step 2B: The claim does not contain significantly more than the judicial exception. No further additional elements are recited, see analysis of claim 1.
Claim 6
Step 1: A process, as above.
Step 2A Prong 1: The claim recites, inter alia:
“performing natural language processing over the large language model system answer before providing at least a portion of the large language model system answer to one or more of the plurality of user devices”; This limitation encompasses mentally performing natural language processing over the large language model system answer before providing it to the user(s), such as by mentally converting the raw answer into natural language.
Step 2A Prong 2: This judicial exception is not integrated into a practical application. The claim further recites “receiving a large language model system answer” and “providing at least a portion of the large language model system answer to one or more of the plurality of user devices,” however these limitations amount to the insignificant extra-solution activity of mere data gathering and outputting (MPEP 2106.05(g)).
Step 2B: The claim does not contain significantly more than the judicial exception. The “receiving a large language model system answer” and “providing at least a portion…” limitations, in addition to reciting insignificant extra-solution activity, are also directed to the well-understood, routine, and conventional activity of receiving or transmitting data over a network (MPEP 2106.05(d)(II)(i) OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015)).
Claim 7
Step 1: A process, as above.
Step 2A Prong 1: The claim recites, inter alia:
“wherein the large language model system is implemented as a generative large language model AI entity”; This limitation merely further limits the large language model system that the prompt is generated for in claim 1, and generating a prompt to a large language model system is still mentally performable when the large language model system is implemented as a generative large language model AI entity.
Step 2A Prong 2: This judicial exception is not integrated into a practical application. No further additional elements are recited, see analysis of claim 1.
Step 2B: The claim does not contain significantly more than the judicial exception. No further additional elements are recited, see analysis of claim 1.
Claim 8
Step 1: A process, as above.
Step 2A Prong 1: The claim recites the same judicial exception as claim 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application. The claim further recites “wherein the collaboration activities by the plurality of user devices over the individual ones of the stored content objects comprise one or more interaction events that have been captured and stored in a manner to permit subsequent retrieval,” however this limitation amounts to the insignificant extra-solution activity of mere data gathering and outputting (MPEP 2106.05(g)).
Step 2B: The claim does not contain significantly more than the judicial exception. The “collaboration activities by the plurality of user devices over the individual ones of the stored content objects comprise one or more interaction events that have been captured and stored in a manner to permit subsequent retrieval” limitation, in addition to reciting insignificant extra-solution activity, is also directed to the well-understood, routine, and conventional activity of receiving or transmitting data over a network (MPEP 2106.05(d)(II)(i) OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015)).
Claim 9
Step 1: A process, as above.
Step 2A Prong 1: The claim recites the same judicial exception as claim 1.
Step 2A Prong 2: This judicial exception is not integrated into a practical application. The claim further recites “wherein the one or more interaction events comprise one or more of, a user-to-object interaction event, a user-to-user interaction event, a user-to-chunk interaction event, a content object preview event, a content object edit event, or a content object delete event,” however this limitation amounts to the insignificant extra-solution activity of mere data gathering and outputting (MPEP 2106.05(g)).
Step 2B: The claim does not contain significantly more than the judicial exception. The “one or more interaction events comprise one or more of, a user-to-object interaction event, a user-to-user interaction event, a user-to-chunk interaction event, a content object preview event, a content object edit event, or a content object delete event,” limitation, in addition to reciting insignificant extra-solution activity, is also directed to the well-understood, routine, and conventional activity of receiving or transmitting data over a network (MPEP 2106.05(d)(II)(i) OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015)).
Claim 10
Step 1: A process, as above.
Step 2A Prong 1: The claim recites, inter alia:
“wherein the identifying of the one or more chunks comprises applying a cosine similarity between an embedding of a portion of text within a document and an embedding of a user question”; This limitation encompasses a mathematical calculation of applying a cosine similarity between an embedding of a portion of text within a document and an embedding of a user question.
Step 2A Prong 2: This judicial exception is not integrated into a practical application. No further additional elements are recited, see analysis of claim 1.
Step 2B: The claim does not contain significantly more than the judicial exception. No further additional elements are recited, see analysis of claim 1.
Claim 11
Step 1: A process, as above.
Step 2A Prong 1: The claim recites, inter alia:
“wherein at least some of the one or more chunks are identified before receipt of the user question”; This limitation encompasses mentally identifying some of the one or more chunks before receipt of the user question.
Step 2A Prong 2: This judicial exception is not integrated into a practical application. No further additional elements are recited, see analysis of claim 1.
Step 2B: The claim does not contain significantly more than the judicial exception. No further additional elements are recited, see analysis of claim 1.
Claim 12
Step 1: A process, as above.
Step 2A Prong 1: The claim recites, inter alia:
“wherein at least some of the one or more chunks are scored for relevance based at least in part on the collaboration activities by a first one of the user devices”; This limitation encompasses mentally scoring at least some of the one or more chunks for relevance based at least in part on the collaboration activities by a first one of the user devices.
Step 2A Prong 2: This judicial exception is not integrated into a practical application. No further additional elements are recited, see analysis of claim 1.
Step 2B: The claim does not contain significantly more than the judicial exception. No further additional elements are recited, see analysis of claim 1.
Claim 13
Step 1: A process, as above.
Step 2A Prong 1: The claim recites, inter alia:
“wherein at least some of the one or more chunks are scored for relevance based at least in part on the collaboration activities by a second one of the user devices”; This limitation encompasses mentally scoring at least some of the one or more chunks for relevance based at least in part on the collaboration activities by a second one of the user devices.
Step 2A Prong 2: This judicial exception is not integrated into a practical application. No further additional elements are recited, see analysis of claim 1.
Step 2B: The claim does not contain significantly more than the judicial exception. No further additional elements are recited, see analysis of claim 1.
Claims 14-21
Step 1: The claims recite a non-transitory computer readable medium, and therefore are directed to the statutory category of articles of manufacture.
Step 2A Prong 1: Claims 14-21 recite the same judicial exception as claims 1-8, respectively.
Step 2A Prong 2: This judicial exception is not integrated into a practical application. The claims further recite “A non-transitory computer readable medium having stored thereon a sequence of instructions which, when stored in memory and executed by a processor cause the processor to perform acts for performing prompt engineering in a content management system, the acts comprising… [the method],” however, this limitation amounts to mere instructions to apply a judicial exception on a generic computer (MPEP 2106.05(f)). Otherwise, the analysis at this step mirrors that of claims 1-8, respectively.
Step 2B: The claims do not contain significantly more than the judicial exception. The “non-transitory computer readable medium” limitation amounts to mere instructions to apply a judicial exception on a generic computer (MPEP 2106.05(f)) as stated above. Otherwise, the analysis at this step mirrors that of claims 1-8, respectively.
Claim 22-24
Step 1: The claims recite a system, and therefore are directed to the statutory category of machines.
Step 2A Prong 1: Claims 22-24 recite the same judicial exception as claims 1-3, respectively.
Step 2A Prong 2: This judicial exception is not integrated into a practical application. The claims further recite “A system for performing prompt engineering in a content management system, the system comprising: a storage medium having stored thereon a sequence of instructions; and a processor that executes the sequence of instructions to cause the processor to perform acts comprising… [the method],” however, this limitation amounts to mere instructions to apply a judicial exception on a generic computer (MPEP 2106.05(f)). Otherwise, the analysis at this step mirrors that of claims 1-3, respectively.
Step 2B: The claims do not contain significantly more than the judicial exception. The system comprising a storage medium and a processor limitation amounts to mere instructions to apply a judicial exception on a generic computer (MPEP 2106.05(f)) as stated above. Otherwise, the analysis at this step mirrors that of claims 1-3, respectively.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-24 are rejected under 35 U.S.C. 103 as being unpatentable over Shea et al. (US20250110975) (hereinafter “Shea”) in view of Dicklin et al. (US20250103826) (hereinafter “Dicklin”).
Regarding claim 1, Shea discloses “A method for performing prompt engineering in a content management system, the method comprising:
configuring the content management system to expose stored content objects to a plurality of user devices through an electronic interface (Shea, [0226]: “FIG. 5 depicts an example graphical user interface of a frontend of a collaboration platform. The graphical user interface 500 may be provided by a client application (e.g., a fronted application) operating on a client device that is operably coupled to a backend of the collaboration platform using a computer network…In the following example, the collaboration platform is a documentation platform configured to manage content items like user-generated pages or electronic documents” and [0227]: “The user may transition the graphical user interface 500 into a content viewer mode by selecting the publish control 514 on the control bar 510. User selection of the publish control 514 may cause the content of the page or electronic document to be saved on the collaboration platform backend and the page or electronic document may be accessible to other users of the system having been authenticated and having a permissions profile that is consistent with a permissions profile of the page or electronic document”);
identifying one or more chunks that are present in individual ones of the stored content objects (Shea, [0181]: “Each of the index services 222 may be adapted to identify matching or corresponding content managed by one or more indexed content stores 224. In some implementations, the indexed content store 224 includes content identifiers or pointers to content managed by the collaboration platform” and [0182]: “Results obtained by the index service 222, including content identifiers and/or partial or full text content, may be sent back to the search gateway service 210 for further processing” and [0183]: “Once text has been obtained by the search gateway service 210, the search gateway service 210 may prepare a prompt for sending to the generative output engine 240… the search gateway service 210 may select blocks of text for inclusion in the prompt” and [0184]: “Blocks of text or snippets of the content may be selected based on a correlation with the user input. In some implementations, a correlation score may be computed for each block of text and those blocks of texts having a correlation score that satisfies a correlation criteria may be selected for inclusion in the prompt”; Examiner notes that blocks of text/snippets of the content correspond to one or more chunks that are present in individual ones of the stored content objects);
recording of occurrences of collaboration activities by the plurality of user devices over the individual ones of the stored content objects or the one or more chunks (Shea, [0100]: “The documentation system may also save user interaction events including user edit action, content viewing actions, commenting, content sharing, and other user interactions. The document content in addition to select user interaction events may be indexed and searchable by the system”; Examiner notes that user interaction events correspond to occurrences of collaboration activities by a plurality of user devices over individual ones of stored content objects); and
generating a prompt to a large language model system… (Shea, [0186]: “The search gateway service 210 may combine at least a portion of the query input 202, the selected blocks of text (or all of the identified text), context data, and predetermined prompt text (also referred to as predetermine query prompt text, template prompt text, or simply prompt text) in order to generate or complete the prompt that will be transmitted to the generative output engine 240” and [0189]: “As described throughout herein, the generative output engine 240 may include a large language model or other predictive engine that is adapted to produce or synthesize content in response to a given prompt”).
Shea does not appear to explicitly disclose the further limitations of the claim.
However, Dicklin discloses “generating a prompt to a large language model system, wherein contents of the prompt are determined based on correspondence between one or more chunks and one or more… collaboration activities” (Dicklin, [0159-0161]: “FIG. 11 is a flowchart illustrating an example method 1100 of providing real-time anticipation of user interest in information contained in documents in cloud storage, in accordance with implementations disclosed herein…At block 1110, the real-time anticipation subsystem 116 may identify an action of a user of the cloud-based content management platform 100 with respect to one or more first documents of multiple documents. The multiple documents may be stored at the platform 100. The action of the user may include an action of a user on a user interface. The user interface may include a user interface of a client 140-1, . . . , 140-m. In one implementation, the action of the user may include the user inputting text data into a text input field of the user interface. The text data may include a search term being input into a search field of the user interface or some other text input field. The action of the user may include the user selecting a document or a folder displayed by the user interface. The action of the user may include the user opening a document or folder displayed by the user interface. The action of the user may include the user hovering a mouse cursor over a document or folder. The action of the user may include some other action using the user interface in order to interact with the platform 100. The client 140-1 may send the data identifying the action of the user to the cloud content management system 110 over the computer network 150” and [0164]: “At block 1122, the real-time anticipation subsystem 116 may select the one or more second documents stored in the cloud-based content management platform 100. The selection may be based on a selection criterion. These one or more selected second documents may be referred to as the ‘working set’” and [0166]: “At block 1124, the real-time anticipation subsystem 116 may select a portion of a document in the working set. The selection may be based on the action of the user of block 910. For example, where the action of the user includes input text data, an embedding model may generate a query embedding based on the text data and may compare the query embedding to a query embedding of a portion of a document in the working set. If the query embeddings are within a threshold similarity, the portion of the document may be selected” and [0170]: “At block 1126, the real-time anticipation subsystem 116 may generate a generative MLM prompt via a generative MLM 120. The generative MLM 120 may generate the generative MLM prompt based on the selected portion of the document of block 1124. The generative MLM prompt may include a generative MLM prompt that the user may find helpful and relevant to the action of the user of block 1110”; Examiner notes that an action of a user with respect to one or more first documents corresponds to a collaboration activity, selecting a portion of a document based on similarity to the action of the user corresponds to “correspondence between one or more chunks and one or more collaboration activities,” and generating a generative MLM prompt based on the selected portion of the document corresponds to generating a prompt to a large language model system (see [0054], generative MLM may include a LLM), wherein contents of the prompt are determined based on said correspondence).
Dicklin and the instant application both relate to performing prompt engineering in a content management system and are analogous. It would have been obvious to one of ordinary skill in the art, prior to the effective filing date of the claimed invention, to have modified Shea with the teachings of Dicklin such that the contents of the prompt are determined based on correspondence between one or more chunks and one or more of the collaboration activities, and one would have been motivated to do so for the purpose of increasing efficiency of cloud-based content management platforms and expediting user collaboration (see Dicklin, [0038]).
Regarding claim 2, the rejection of claim 1 is incorporated. Shea as modified by Dicklin further discloses “submitting the prompt to a large language model system to get a large language model system answer” (Shea, [0189]: “In accordance with other examples described herein, the prompt generated by the search gateway service 210 may be communicated to the generative output engine 240” and [0190]: “In response to the prompt, the generative output engine 240 sends a generative response to the search gateway service 210”).
Regarding claim 3, the rejection of claim 1 is incorporated. Shea as modified by Dicklin further discloses “at least a portion of the prompt comprises contents derived from a prompt template” (Shea, [0186]: “The search gateway service 210 may combine at least a portion of the query input 202, the selected blocks of text (or all of the identified text), context data, and predetermined prompt text (also referred to as predetermine query prompt text, template prompt text, or simply prompt text) in order to generate or complete the prompt that will be transmitted to the generative output engine 240”).
Regarding claim 4, the rejection of claim 3 is incorporated. Shea as modified by Dicklin further discloses “wherein the prompt includes at least a portion that derives from one or more of the chunks” (Shea, [0186]: “The search gateway service 210 may combine at least a portion of the query input 202, the selected blocks of text (or all of the identified text), context data, and predetermined prompt text (also referred to as predetermine query prompt text, template prompt text, or simply prompt text) in order to generate or complete the prompt that will be transmitted to the generative output engine 240”).
Regarding claim 5, the rejection of claim 3 is incorporated. Shea as modified by Dicklin further discloses “wherein the prompt template includes one or more variable fields” (Shea, [0076]: “In some embodiments, a prompt provided as input to a generative output engine can be engineered from user input. For example, in some cases, a user input can be inserted into an engineered template prompt that itself is stored in a database. For example, an engineered prompt template can include one or more fields into which user input portions thereof can be inserted”; Examiner notes that fields into which user input portions can be inserted correspond to variable fields, because they change based on the user input).
Regarding claim 6, the rejection of claim 1 is incorporated. Shea as modified by Dicklin further discloses “receiving a large language model system answer and performing natural language processing over the large language model system answer before providing at least a portion of the large language model system answer to one or more of the plurality of user devices” (Shea, [0190]: “In response to the prompt, the generative output engine 240 sends a generative response to the search gateway service 210. The search gateway service 210 or a related service may perform post processing on the generative response including validation of the response, filtering operations to remove prohibited or non-preferred terms, eliminate potentially inaccurate phrases or terms, or perform other post-processing operations. As discussed above, the search gateway service 210 may also process any tags or similar items returned in the generative response that indicate the source of content that was used for the generative response. The search gateway service 210 or a related service may generate links, icons, or other selectable objects to be rendered/displayed in the generative answer interface. Subsequent to any post-processing operations, the generative response, or portions thereof, are communicated to the frontend application for display in the generative answer interface”).
Regarding claim 7, the rejection of claim 1 is incorporated. Shea as modified by Dicklin further discloses “wherein the large language model system is implemented as a generative large language model AI entity” (Shea, [0189]: “As described throughout herein, the generative output engine 240 may include a large language model or other predictive engine that is adapted to produce or synthesize content in response to a given prompt”).
Regarding claim 8, the rejection of claim 1 is incorporated. Shea as modified by Dicklin further discloses “wherein the collaboration activities by the plurality of user devices over the individual ones of the stored content objects comprise one or more interaction events that have been captured and stored in a manner to permit subsequent retrieval” (Shea, [0100]: “The documentation system may also save user interaction events including user edit action, content viewing actions, commenting, content sharing, and other user interactions. The document content in addition to select user interaction events may be indexed and searchable by the system”).
Regarding claim 9, the rejection of claim 8 is incorporated. Shea as modified by Dicklin further discloses “wherein the one or more interaction events comprise one or more of, a user-to-object interaction event, a user-to-user interaction event, a user-to-chunk interaction event, a content object preview event, a content object edit event, or a content object delete event” (Shea, [0100]: “The documentation system may also save user interaction events including user edit action, content viewing actions, commenting, content sharing, and other user interactions”).
Regarding claim 10, the rejection of claim 1 is incorporated. Shea as modified by Dicklin further discloses “wherein the identifying of the one or more chunks comprises applying a cosine similarity between an embedding of a portion of text within a document and an embedding of a user question” (Shea, [0184]: “Blocks of text or snippets of the content may be selected based on a correlation with the user input. In some implementations, a correlation score may be computed for each block of text and those blocks of texts having a correlation score that satisfies a correlation criteria may be selected for inclusion in the prompt” and [0185]: “The correlation score may be computed using a language processing technique that is able to quantify a correlation between a given natural language input and the text of a particular block. In one example an input vector may be determined or constructed using the natural language input. The input vector may be constructed using a word vectorization service that maps words or phrases into a vector of numbers or other characters. A similar technique may be applied to the blocks of text to obtain a set of block vectors. A correlation score may be computed using a vector comparison or evaluation technique including a cosine similarity, Euclidian distance, Jaccard similarity, or other technique”).
Regarding claim 11, the rejection of claim 10 is incorporated. Shea does not appear to explicitly disclose the further limitations of the claim.
However, Dicklin further discloses “wherein at least some of… one or more chunks are identified before receipt of… [a] user question” (Dicklin, [0059]: “At block 210, the document pre-processing subsystem 112 may select a portion of a document stored in the cloud-based content management platform 100” and [0080]: “At block 250, the document pre-processing subsystem 112 may store an association of the query embedding with the portion of the document selected in block 210. The association may be subsequently used by the generative MLM 120 to provide information related to content of the documents to users of the platform 100” and [0081]: “In some implementations, the subsequent use by the generative MLM may include the generative response subsystem 118 selecting the portion of the document based on a similarity between the query embedding generated in block 240 and a query embedding of a user input to the platform 100”).
Dicklin and the instant application both relate to large language models in content management systems and are analogous. It would have been obvious to one of ordinary skill in the art, prior to the effective filing date of the claimed invention, to have modified Shea with the teachings of Dicklin such that at least some of the one or more chunks are identified before receipt of the user question, and one would have been motivated to do so for the purpose of increasing efficiency of cloud-based content management platforms and expediting user collaboration (see Dicklin, [0038]).
Regarding claim 12, the rejection of claim 1 is incorporated. Shea does not appear to explicitly disclose the further limitations of the claim.
However, Dicklin further discloses “wherein at least some of… one or more chunks are scored for relevance based at least in part on… collaboration activities by a first one of… user devices” (Dicklin, [0160]: “At block 1110, the real-time anticipation subsystem 116 may identify an action of a user of the cloud-based content management platform 100 with respect to one or more first documents of multiple documents. The multiple documents may be stored at the platform 100. The action of the user may include an action of a user on a user interface. The user interface may include a user interface of a client 140-1, . . . , 140-m” and [0166]: “At block 1124, the real-time anticipation subsystem 116 may select a portion of a document in the working set. The selection may be based on the action of the user of block 910. For example, where the action of the user includes input text data, an embedding model may generate a query embedding based on the text data and may compare the query embedding to a query embedding of a portion of a document in the working set. If the query embeddings are within a threshold similarity, the portion of the document may be selected”; Examiner notes that a user interface of a client 140-1 corresponds to a first one of user devices, and when the action comes from a user of client 140-1, the similarity between a query embedding based on the action and a query embedding of a portion of a document corresponds to scoring one or more chunks for relevance based at least in part on collaboration activities by a first one of user devices).
Dicklin and the instant application both relate to large language models in content management systems and are analogous. It would have been obvious to one of ordinary skill in the art, prior to the effective filing date of the claimed invention, to have modified Shea with the teachings of Dicklin such that at least some of the one or more chunks are scored for relevance based at least in part on the collaboration activities by a first one of the user devices, and one would have been motivated to do so for the purpose of increasing efficiency of cloud-based content management platforms and expediting user collaboration (see Dicklin, [0038]).
Regarding claim 13, the rejection of claim 12 is incorporated. Shea does not appear to explicitly disclose the further limitations of the claim.
However, Dicklin further discloses “wherein at least some of… one or more chunks are scored for relevance based at least in part on… collaboration activities by a second one of… user devices” (Dicklin, [0160]: “At block 1110, the real-time anticipation subsystem 116 may identify an action of a user of the cloud-based content management platform 100 with respect to one or more first documents of multiple documents. The multiple documents may be stored at the platform 100. The action of the user may include an action of a user on a user interface. The user interface may include a user interface of a client 140-1, . . . , 140-m” and [0166]: “At block 1124, the real-time anticipation subsystem 116 may select a portion of a document in the working set. The selection may be based on the action of the user of block 910. For example, where the action of the user includes input text data, an embedding model may generate a query embedding based on the text data and may compare the query embedding to a query embedding of a portion of a document in the working set. If the query embeddings are within a threshold similarity, the portion of the document may be selected”; Examiner notes that a user interface of a client 140-2 corresponds to a second one of user devices, and when the action comes from client 140-2, the similarity between a query embedding based on the action and a query embedding of a portion of a document corresponds to scoring one or more chunks for relevance based at least in part on collaboration activities by a second one of user devices).
Dicklin and the instant application both relate to large language models in content management systems and are analogous. It would have been obvious to one of ordinary skill in the art, prior to the effective filing date of the claimed invention, to have modified Shea with the teachings of Dicklin such that at least some of the one or more chunks are scored for relevance based at least in part on the collaboration activities by a second one of the user devices, and one would have been motivated to do so for the purpose of increasing efficiency of cloud-based content management platforms and expediting user collaboration (see Dicklin, [0038]).
Regarding claim 14, Shea discloses “A non-transitory computer readable medium having stored thereon a sequence of instructions which, when stored in memory and executed by a processor cause the processor to perform acts for performing prompt engineering in a content management system (Shea, [0249]: “FIG. 8 shows a sample electrical block diagram of an electronic device 800 that may perform the operations described herein…The electronic device 800 can include one or more of a processing unit 802, a memory 804 or storage device, input devices 806, a display 808, output devices 810, and a power source 812” and [0251]: “The processing unit 802 can be implemented as any electronic device capable of processing, receiving, or transmitting data or instructions. For example, the processing unit 802 can be a microprocessor, a central processing unit (CPU), an application-specific integrated circuit (ASIC), a digital signal processor (DSP), or combinations of such devices” and [0254]: “The memory 804 can store electronic data that can be used by the electronic device 800…The memory 804 can be configured as any type of memory. By way of example only, the memory 804 can be implemented as random access memory, read-only memory, flash memory, removable memory, other types of storage elements, or combinations of such devices), the acts comprising:
configuring the content management system to expose stored content objects to a plurality of user devices through an electronic interface (Shea, [0226]: “FIG. 5 depicts an example graphical user interface of a frontend of a collaboration platform. The graphical user interface 500 may be provided by a client application (e.g., a fronted application) operating on a client device that is operably coupled to a backend of the collaboration platform using a computer network…In the following example, the collaboration platform is a documentation platform configured to manage content items like user-generated pages or electronic documents” and [0227]: “The user may transition the graphical user interface 500 into a content viewer mode by selecting the publish control 514 on the control bar 510. User selection of the publish control 514 may cause the content of the page or electronic document to be saved on the collaboration platform backend and the page or electronic document may be accessible to other users of the system having been authenticated and having a permissions profile that is consistent with a permissions profile of the page or electronic document”);
identifying one or more chunks that are present in individual ones of the stored content objects (Shea, [0181]: “Each of the index services 222 may be adapted to identify matching or corresponding content managed by one or more indexed content stores 224. In some implementations, the indexed content store 224 includes content identifiers or pointers to content managed by the collaboration platform” and [0182]: “Results obtained by the index service 222, including content identifiers and/or partial or full text content, may be sent back to the search gateway service 210 for further processing” and [0183]: “Once text has been obtained by the search gateway service 210, the search gateway service 210 may prepare a prompt for sending to the generative output engine 240… the search gateway service 210 may select blocks of text for inclusion in the prompt” and [0184]: “Blocks of text or snippets of the content may be selected based on a correlation with the user input. In some implementations, a correlation score may be computed for each block of text and those blocks of texts having a correlation score that satisfies a correlation criteria may be selected for inclusion in the prompt”; Examiner notes that blocks of text/snippets of the content correspond to one or more chunks that are present in individual ones of the stored content objects);
recording of occurrences of collaboration activities by the plurality of user devices over the individual ones of the stored content objects or the one or more chunks (Shea, [0100]: “The documentation system may also save user interaction events including user edit action, content viewing actions, commenting, content sharing, and other user interactions. The document content in addition to select user interaction events may be indexed and searchable by the system”; Examiner notes that user interaction events correspond to occurrences of collaboration activities by a plurality of user devices over individual ones of stored content objects); and
generating a prompt to a large language model system… (Shea, [0186]: “The search gateway service 210 may combine at least a portion of the query input 202, the selected blocks of text (or all of the identified text), context data, and predetermined prompt text (also referred to as predetermine query prompt text, template prompt text, or simply prompt text) in order to generate or complete the prompt that will be transmitted to the generative output engine 240” and [0189]: “As described throughout herein, the generative output engine 240 may include a large language model or other predictive engine that is adapted to produce or synthesize content in response to a given prompt”).
Shea does not appear to explicitly disclose the further limitations of the claim.
However, Dicklin discloses “generating a prompt to a large language model system, wherein contents of the prompt are determined based on correspondence between one or more chunks and one or more… collaboration activities” (Dicklin, [0159-0161]: “FIG. 11 is a flowchart illustrating an example method 1100 of providing real-time anticipation of user interest in information contained in documents in cloud storage, in accordance with implementations disclosed herein…At block 1110, the real-time anticipation subsystem 116 may identify an action of a user of the cloud-based content management platform 100 with respect to one or more first documents of multiple documents. The multiple documents may be stored at the platform 100. The action of the user may include an action of a user on a user interface. The user interface may include a user interface of a client 140-1, . . . , 140-m. In one implementation, the action of the user may include the user inputting text data into a text input field of the user interface. The text data may include a search term being input into a search field of the user interface or some other text input field. The action of the user may include the user selecting a document or a folder displayed by the user interface. The action of the user may include the user opening a document or folder displayed by the user interface. The action of the user may include the user hovering a mouse cursor over a document or folder. The action of the user may include some other action using the user interface in order to interact with the platform 100. The client 140-1 may send the data identifying the action of the user to the cloud content management system 110 over the computer network 150” and [0164]: “At block 1122, the real-time anticipation subsystem 116 may select the one or more second documents stored in the cloud-based content management platform 100. The selection may be based on a selection criterion. These one or more selected second documents may be referred to as the ‘working set’” and [0166]: “At block 1124, the real-time anticipation subsystem 116 may select a portion of a document in the working set. The selection may be based on the action of the user of block 910 [should read block 1110]. For example, where the action of the user includes input text data, an embedding model may generate a query embedding based on the text data and may compare the query embedding to a query embedding of a portion of a document in the working set. If the query embeddings are within a threshold similarity, the portion of the document may be selected” and [0170]: “At block 1126, the real-time anticipation subsystem 116 may generate a generative MLM prompt via a generative MLM 120. The generative MLM 120 may generate the generative MLM prompt based on the selected portion of the document of block 1124. The generative MLM prompt may include a generative MLM prompt that the user may find helpful and relevant to the action of the user of block 1110”; Examiner notes that an action of a user with respect to one or more first documents corresponds to a collaboration activity, selecting a portion of a document based on similarity to the action of the user corresponds to “correspondence between one or more chunks and one or more collaboration activities,” and generating a generative MLM prompt based on the selected portion of the document corresponds to generating a prompt to a large language model system (see [0054], generative MLM may include a LLM), wherein contents of the prompt are determined based on said correspondence).
Dicklin and the instant application both relate to performing prompt engineering in a content management system and are analogous. It would have been obvious to one of ordinary skill in the art, prior to the effective filing date of the claimed invention, to have modified Shea with the teachings of Dicklin such that the contents of the prompt are determined based on correspondence between one or more chunks and one or more of the collaboration activities, and one would have been motivated to do so for the purpose of increasing efficiency of cloud-based content management platforms and expediting user collaboration (see Dicklin, [0038]).
Regarding claim 15, the rejection of claim 14 is incorporated. Claim 15 is a computer readable medium claim corresponding to method claim 2, and the remainder of the rejection follows the same rationale as the rejection of claim 2 above.
Regarding claim 16, the rejection of claim 14 is incorporated. Claim 16 is a computer readable medium claim corresponding to method claim 3, and the remainder of the rejection follows the same rationale as the rejection of claim 3 above.
Regarding claim 17, the rejection of claim 16 is incorporated. Claim 17 is a computer readable medium claim corresponding to method claim 4, and the remainder of the rejection follows the same rationale as the rejection of claim 4 above.
Regarding claim 18, the rejection of claim 16 is incorporated. Claim 18 is a computer readable medium claim corresponding to method claim 5, and the remainder of the rejection follows the same rationale as the rejection of claim 5 above.
Regarding claim 19, the rejection of claim 14 is incorporated. Claim 19 is a computer readable medium claim corresponding to method claim 6, and the remainder of the rejection follows the same rationale as the rejection of claim 6 above.
Regarding claim 20, the rejection of claim 14 is incorporated. Claim 20 is a computer readable medium claim corresponding to method claim 7, and the remainder of the rejection follows the same rationale as the rejection of claim 7 above.
Regarding claim 21, the rejection of claim 14 is incorporated. Claim 21 is a computer readable medium claim corresponding to method claim 8, and the remainder of the rejection follows the same rationale as the rejection of claim 8 above.
Regarding claim 22, Shea discloses “A system for performing prompt engineering in a content management system, the system comprising: a storage medium having stored thereon a sequence of instructions; and a processor that executes the sequence of instructions to cause the processor to perform acts comprising (Shea, [0249]: “FIG. 8 shows a sample electrical block diagram of an electronic device 800 that may perform the operations described herein…The electronic device 800 can include one or more of a processing unit 802, a memory 804 or storage device, input devices 806, a display 808, output devices 810, and a power source 812” and [0251]: “The processing unit 802 can be implemented as any electronic device capable of processing, receiving, or transmitting data or instructions. For example, the processing unit 802 can be a microprocessor, a central processing unit (CPU), an application-specific integrated circuit (ASIC), a digital signal processor (DSP), or combinations of such devices” and [0254]: “The memory 804 can store electronic data that can be used by the electronic device 800…The memory 804 can be configured as any type of memory. By way of example only, the memory 804 can be implemented as random access memory, read-only memory, flash memory, removable memory, other types of storage elements, or combinations of such devices),
configuring the content management system to expose stored content objects to a plurality of user devices through an electronic interface (Shea, [0226]: “FIG. 5 depicts an example graphical user interface of a frontend of a collaboration platform. The graphical user interface 500 may be provided by a client application (e.g., a fronted application) operating on a client device that is operably coupled to a backend of the collaboration platform using a computer network…In the following example, the collaboration platform is a documentation platform configured to manage content items like user-generated pages or electronic documents” and [0227]: “The user may transition the graphical user interface 500 into a content viewer mode by selecting the publish control 514 on the control bar 510. User selection of the publish control 514 may cause the content of the page or electronic document to be saved on the collaboration platform backend and the page or electronic document may be accessible to other users of the system having been authenticated and having a permissions profile that is consistent with a permissions profile of the page or electronic document”);
identifying one or more chunks that are present in individual ones of the stored content objects (Shea, [0181]: “Each of the index services 222 may be adapted to identify matching or corresponding content managed by one or more indexed content stores 224. In some implementations, the indexed content store 224 includes content identifiers or pointers to content managed by the collaboration platform” and [0182]: “Results obtained by the index service 222, including content identifiers and/or partial or full text content, may be sent back to the search gateway service 210 for further processing” and [0183]: “Once text has been obtained by the search gateway service 210, the search gateway service 210 may prepare a prompt for sending to the generative output engine 240… the search gateway service 210 may select blocks of text for inclusion in the prompt” and [0184]: “Blocks of text or snippets of the content may be selected based on a correlation with the user input. In some implementations, a correlation score may be computed for each block of text and those blocks of texts having a correlation score that satisfies a correlation criteria may be selected for inclusion in the prompt”; Examiner notes that blocks of text/snippets of the content correspond to one or more chunks that are present in individual ones of the stored content objects);
recording of occurrences of collaboration activities by the plurality of user devices over the individual ones of the stored content objects or the one or more chunks (Shea, [0100]: “The documentation system may also save user interaction events including user edit action, content viewing actions, commenting, content sharing, and other user interactions. The document content in addition to select user interaction events may be indexed and searchable by the system”; Examiner notes that user interaction events correspond to occurrences of collaboration activities by a plurality of user devices over individual ones of stored content objects); and
generating a prompt to a large language model system… (Shea, [0186]: “The search gateway service 210 may combine at least a portion of the query input 202, the selected blocks of text (or all of the identified text), context data, and predetermined prompt text (also referred to as predetermine query prompt text, template prompt text, or simply prompt text) in order to generate or complete the prompt that will be transmitted to the generative output engine 240” and [0189]: “As described throughout herein, the generative output engine 240 may include a large language model or other predictive engine that is adapted to produce or synthesize content in response to a given prompt”).
Shea does not appear to explicitly disclose the further limitations of the claim.
However, Dicklin discloses “generating a prompt to a large language model system, wherein contents of the prompt are determined based on correspondence between one or more chunks and one or more… collaboration activities” (Dicklin, [0159-0161]: “FIG. 11 is a flowchart illustrating an example method 1100 of providing real-time anticipation of user interest in information contained in documents in cloud storage, in accordance with implementations disclosed herein…At block 1110, the real-time anticipation subsystem 116 may identify an action of a user of the cloud-based content management platform 100 with respect to one or more first documents of multiple documents. The multiple documents may be stored at the platform 100. The action of the user may include an action of a user on a user interface. The user interface may include a user interface of a client 140-1, . . . , 140-m. In one implementation, the action of the user may include the user inputting text data into a text input field of the user interface. The text data may include a search term being input into a search field of the user interface or some other text input field. The action of the user may include the user selecting a document or a folder displayed by the user interface. The action of the user may include the user opening a document or folder displayed by the user interface. The action of the user may include the user hovering a mouse cursor over a document or folder. The action of the user may include some other action using the user interface in order to interact with the platform 100. The client 140-1 may send the data identifying the action of the user to the cloud content management system 110 over the computer network 150” and [0164]: “At block 1122, the real-time anticipation subsystem 116 may select the one or more second documents stored in the cloud-based content management platform 100. The selection may be based on a selection criterion. These one or more selected second documents may be referred to as the ‘working set’” and [0166]: “At block 1124, the real-time anticipation subsystem 116 may select a portion of a document in the working set. The selection may be based on the action of the user of block 910 [should read block 1110]. For example, where the action of the user includes input text data, an embedding model may generate a query embedding based on the text data and may compare the query embedding to a query embedding of a portion of a document in the working set. If the query embeddings are within a threshold similarity, the portion of the document may be selected” and [0170]: “At block 1126, the real-time anticipation subsystem 116 may generate a generative MLM prompt via a generative MLM 120. The generative MLM 120 may generate the generative MLM prompt based on the selected portion of the document of block 1124. The generative MLM prompt may include a generative MLM prompt that the user may find helpful and relevant to the action of the user of block 1110”; Examiner notes that an action of a user with respect to one or more first documents corresponds to a collaboration activity, selecting a portion of a document based on similarity to the action of the user corresponds to “correspondence between one or more chunks and one or more collaboration activities,” and generating a generative MLM prompt based on the selected portion of the document corresponds to generating a prompt to a large language model system (see [0054], generative MLM may include a LLM), wherein contents of the prompt are determined based on said correspondence).
Dicklin and the instant application both relate to performing prompt engineering in a content management system and are analogous. It would have been obvious to one of ordinary skill in the art, prior to the effective filing date of the claimed invention, to have modified Shea with the teachings of Dicklin such that the contents of the prompt are determined based on correspondence between one or more chunks and one or more of the collaboration activities, and one would have been motivated to do so for the purpose of increasing efficiency of cloud-based content management platforms and expediting user collaboration (see Dicklin, [0038]).
Regarding claim 23, the rejection of claim 22 is incorporated. Claim 23 is a system claim corresponding to method claim 2, and the remainder of the rejection follows the same rationale as the rejection of claim 2 above.
Regarding claim 24, the rejection of claim 22 is incorporated. Claim 24 is a system claim corresponding to method claim 3, and the remainder of the rejection follows the same rationale as the rejection of claim 3 above.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to GWYNEVERE A DETERDING whose telephone number is (571)272-7657. The examiner can normally be reached Mon-Fri. 9am-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, Kamran Afshar can be reached at (571) 272-7796. 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.
/G.A.D./Examiner, Art Unit 2125
/KAMRAN AFSHAR/Supervisory Patent Examiner, Art Unit 2125
Prosecution Insights