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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on May 13, 2026 has been entered.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on June 3, 2026 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Objections
Claims 2, 3, 9, and 12-18 are objected to because of the following informalities:
Claim 2, line 2, before “at least”, insert --the--.
Claim 3, line 2, before “at least”, insert --the--.
Claim 9, line 2, before “at least”, insert --the-- and replace “a” before “generative” with --the--.
Claim 12, line 14, “the selected message” lacks proper antecedent basis.
Claim 13, line 1, before “prompt”, replace “a” with --the--.
Claim 14, line 2, before “prompt” and “generative”, replace “a” with --the--, respectively.
Claim 15, line 2, before “prompt” and “generative”, replace “a” with --the--, respectively.
Claim 16, lines 3-4, “the generative plan execution model” lacks proper antecedent basis. Further, “the execution results” in line 4 lacks proper antecedent basis.
Claim 17, line 3, before “communications”, insert --the-- and replace “a” before “plurality” with --the--.
Claim 18, lines 1-2, before “prompt” and “generative”, replace “a” with --the--, respectively.
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.
Claim 16 is 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.
Line 4, “the functions” is unclear whether it refers to “functions” in line 13 of claim 12 or “a set of functions” in line 5 of claim 15. For the examination purposes, “the functions” in line 4 of clam 16 will be treated as –the identified functions--.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1: Is the claim to a process, machine, manufacture, or composition of matter?
Yes.
Claims 1-11 are directed to a process and claims 12-20 are directed to a system.
Claim 1 recites:
automatically selecting a communication, from a plurality of different communications for a user;
identifying user context information for the user, wherein the user context information comprises subject matter of a project or a document on which the user has worked;
automatically generating at least one prompt to a generative model based on the selected communication, the at least one prompt including user context information and requesting identification of a task in the selected communication, the at least one prompt further including a request to generate and execute a task execution plan to execute the identified task, wherein the task execution plan is based at least on the user context information and comprises chain-of-thought reasoning output, from the generative model, identifying intermediate reasoning steps for decomposing the task into executable functions;
automatically sending the task execution plan to a plan execution system;
receiving an execution result from the plan execution system, the execution result being indicative of a result of executing the task execution plan; and
outputting the execution result for user interaction.
Step 2A, Prong I: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, abstract ideas.
The “automatically selecting ...” limitation in #1 above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “automatically selecting ...” in the context of this claim encompasses the person making a judgement.
The “identifying ...” limitation in #2 above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “identifying ...” in the context of this claim encompasses the person making a judgement.
The “automatically ...” limitation in #3 above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “automatically ...” in the context of this claim encompasses the person creating a prompt.
Step 2A, Prong II: Does the claim recite additional elements that integrate the judicial exception into a practical application?
No.
The “automatically ... ” limitation in #4 above, as claimed and under BRI, is an additional element that is insignificant extra-solution activity. For example, “automatically ...” in the context of this claim encompasses mere data transmitting. See MPEP 2106.05(g).
The “receiving ...” limitation in #5 above, as claimed and under BRI, is an additional element that is insignificant extra-solution activity. For example, “receiving ...” in the context of this claim encompasses mere data gathering. See MPEP 2106.05(g).
The “outputting ...” limitation in #6 above, as claimed and under BRI, is an additional element that is insignificant extra-solution activity. For example, “outputting” in the context of this claim encompasses mere data transmitting. See MPEP 2106.05(g).
Additionally, the claim recites the following additional elements:
a generative model
executable functions
These additional elements are recited at a high level of generality (i.e., as generic computer components) such that they amount to no more than linking the judicial exception to a technological environment. Accordingly, these additional elements do not integrate the abstract idea(s) into a practical application because they do not impose any meaningful limits on practicing the abstract idea(s).
Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception?
No.
With regard to #4, #5, and #6 above, per MPEP 2106.05(d)(II), the courts have recognized the following computer function as well-understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity:
i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014) ("Unlike the claims in Ultramercial, the claims at issue here specify how interactions with the Internet are manipulated to yield a desired result‐‐a result that overrides the routine and conventional sequence of events ordinarily triggered by the click of a hyperlink." (emphasis added)).
As discussed above with respect to integration of the abstract idea(s) into a practical application, the aforementioned additional elements amount to no more than employing generic computer functions to execute an abstract idea, even when limiting the use of the idea to one particular environment. Mere linking the judicial exception to a technological environment using generic computer components cannot provide an inventive concept.
Claim 2 recites:
wherein automatically generating at least one prompt comprises:
automatically generating a task identification prompt to prompt a task identification model to identify the task in the selected communication; and
receiving a response to the task identification prompt, the response identifying the task.
Step 2A, Prong I: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, the abstract ideas of claim 1.
The “automatically ...” limitation above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “automatically ...” in the context of this claim encompasses the person creating a prompt.
Step 2A, Prong II: Does the claim recite additional elements that integrate the judicial exception into a practical application?
No.
The “receiving ...” limitation above, as claimed and under BRI, is an additional element that is insignificant extra-solution activity. For example, “receiving” in the context of this claim encompasses mere data gathering. See MPEP 2106.05(g).
Step 2B: Does the claim recite additional elements that amount to significantly more than the
judicial exception?
No.
With regard to the “receiving ...” limitation above, per MPEP 2106.05(d)(II), the courts have recognized the following computer function as well-understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity:
i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014) ("Unlike the claims in Ultramercial, the claims at issue here specify how interactions with the Internet are manipulated to yield a desired result‐‐a result that overrides the routine and conventional sequence of events ordinarily triggered by the click of a hyperlink." (emphasis added)).
Claim 3 recites:
wherein automatically generating at least one prompt further comprises:
automatically generating, based on receiving the response to the task identification prompt, a plan generation prompt to a plan generation model, the plan generation prompt including the identified task and requesting the task execution plan; and
receiving a response to the plan generation prompt, the response to the plan generation prompt including the task execution plan, the task execution plan identifying executable functions to be executed to perform the identified task.
Step 2A, Prong I: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, the abstract ideas of claim 2.
The “automatically ...” limitation above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “automatically” in the context of this claim encompasses the person creating a prompt.
Step 2A, Prong II: Does the claim recite additional elements that integrate the judicial exception
into a practical application?
No.
The “receiving ...” limitation above, as claimed and under BRI, is an additional element that is insignificant extra-solution activity. For example, “receiving” in the context of this claim encompasses mere data gathering. See MPEP 2106.05(g).
Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception?
No.
With regard to the “receiving ...” limitation above, per MPEP 2106.05(d)(II), the courts have recognized the following computer function as well-understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity:
i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014) ("Unlike the claims in Ultramercial, the claims at issue here specify how interactions with the Internet are manipulated to yield a desired result‐‐a result that overrides the routine and conventional sequence of events ordinarily triggered by the click of a hyperlink." (emphasis added)).
Claim 4 recites:
wherein automatically generating the task identification prompt includes generating a summarization request to summarize the identified task and wherein receiving the response to the task identification prompt comprises receiving a summary of the identified task.
Step 2A, Prong I: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, the abstract ideas of claim 3.
The “generating ...” limitation above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “generating” in the context of this claim encompasses the person creating a request.
Step 2A, Prong II: Does the claim recite additional elements that integrate the judicial exception into a practical application?
No.
The “receiving ...” limitation above, as claimed and under BRI, is an additional element that is insignificant extra-solution activity. For example, “receiving” in the context of this claim encompasses mere data gathering. See MPEP 2106.05(g).
Step 2B: Does the claim recite additional elements that amount to significantly more than the
judicial exception?
No.
With regard to the “receiving ...” limitation above, per MPEP 2106.05(d)(II), the courts have recognized the following computer function as well-understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity:
i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014) ("Unlike the claims in Ultramercial, the claims at issue here specify how interactions with the Internet are manipulated to yield a desired result‐‐a result that overrides the routine and conventional sequence of events ordinarily triggered by the click of a hyperlink." (emphasis added)).
Claim 5 recites:
wherein automatically generating the plan generation prompt comprises:
generating the plan generation prompt to include the summary of the identified task.
Step 2A, Prong I: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, the abstract ideas of claim 4.
The “generating” limitation above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “generating” in the context of this claim encompasses the person creating a prompt.
Step 2A, Prong II: Does the claim recite additional elements that integrate the judicial exception
into a practical application?
No.
Claim 6 recites:
wherein receiving the response to the plan generation prompt includes:
receiving a function trigger corresponding to each of the executable functions identified in the task execution plan, each function trigger triggering, in the plan execution system, execution of a corresponding function.
Step 2A, Prong I: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, the abstract ideas of claim 3.
Step 2A, Prong II: Does the claim recite additional elements that integrate the judicial exception
into a practical application?
No.
The “receiving” limitation above, as claimed and under BRI, is an additional element that is insignificant extra-solution activity. For example, “receiving” in the context of this claim encompasses mere data gathering. See MPEP 2106.05(g).
Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception?
No.
With regard to the “receiving” limitation above, per MPEP 2106.05(d)(II), the courts have recognized the following computer function as well-understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity:
i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014) ("Unlike the claims in Ultramercial, the claims at issue here specify how interactions with the Internet are manipulated to yield a desired result‐‐a result that overrides the routine and conventional sequence of events ordinarily triggered by the click of a hyperlink." (emphasis added)).
Claim 7 recites:
wherein receiving the execution result comprises:
sending the task execution plan to the plan execution system for execution of the functions triggered by the function triggers to generate the task execution result; and
receiving the execution result generated by executing the functions.
Step 2A, Prong I: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, the abstract ideas of claim 6.
Step 2A, Prong II: Does the claim recite additional elements that integrate the judicial exception into a practical application?
No.
The “sending” limitation above, as claimed and under BRI, is an additional element that is insignificant extra-solution activity. For example, “sending” in the context of this claim encompasses mere data transmitting. See MPEP 2106.05(g).
The “receiving” limitation above, as claimed and under BRI, is an additional element that is insignificant extra-solution activity. For example, “receiving” in the context of this claim encompasses mere data gathering. See MPEP 2106.05(g).
Step 2B: Does the claim recite additional elements that amount to significantly more than the
judicial exception?
No.
With regard to the “sending” and “receiving” limitations above, per MPEP 2106.05(d)(II), the courts have recognized the following computer function as well-understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity:
i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014) ("Unlike the claims in Ultramercial, the claims at issue here specify how interactions with the Internet are manipulated to yield a desired result‐‐a result that overrides the routine and conventional sequence of events ordinarily triggered by the click of a hyperlink." (emphasis added)).
Claim 8 recites:
wherein the plan execution system comprises a generative task execution model and wherein sending the task execution plan to the plan execution system further comprises:
automatically generating a task execution prompt to the generative task execution model, the task execution prompt including the function triggers.
Step 2A, Prong I: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, the abstract ideas of claim 7.
The “automatically” limitation above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “automatically” in the context of this claim encompasses the person creating a prompt.
Step 2A, Prong II: Does the claim recite additional elements that integrate the judicial exception into a practical application?
No.
Claim 9 recites:
wherein automatically generating at least one prompt to a generative model comprises:
automatically generating a single prompt that prompts a set of generative models to identify the task in the selected communication and to generate the task execution plan based on the identified task, the task execution plan identifying a set of functions to be executed to perform the identified task.
Step 2A, Prong I: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, the abstract ideas of claim 1.
The “automatically” limitation above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “automatically” in the context of this claim encompasses the person creating a prompt.
Step 2A, Prong II: Does the claim recite additional elements that integrate the judicial exception into a practical application?
No.
Claim 10 recites:
wherein automatically generating the single prompt further comprises:
automatically generating the single prompt to prompt the plan execution system to execute the functions in the task execution plan and return the execution results.
Step 2A, Prong I: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, the abstract ideas of claim 1.
The “automatically” limitation above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “automatically” in the context of this claim encompasses the person creating a prompt.
Step 2A, Prong II: Does the claim recite additional elements that integrate the judicial exception into a practical application?
No.
Claim 11 recites:
receiving communications from a plurality of different communication channels; and
filtering the communications based on filter criteria to obtain a filtered set of communications for further processing and wherein selecting the communication comprises selecting the communication from the filtered set of communications.
Step 2A, Prong I: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, the abstract ideas of claim 1.
The “filtering” limitation above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “filtering” in the context of this claim encompasses the person making a judgement.
The “selecting” limitation above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “selecting” in the context of this claim encompasses the person making a judgement.
Step 2A, Prong II: Does the claim recite additional elements that integrate the judicial exception into a practical application?
No.
The “receiving” limitation above, as claimed and under BRI, is an additional element that is insignificant extra-solution activity. For example, “receiving” in the context of this claim encompasses mere data gathering. See MPEP 2106.05(g).
Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception?
No.
With regard to the “receiving” limitation above, per MPEP 2106.05(d)(II), the courts have recognized the following computer function as well-understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity:
i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014) ("Unlike the claims in Ultramercial, the claims at issue here specify how interactions with the Internet are manipulated to yield a desired result‐‐a result that overrides the routine and conventional sequence of events ordinarily triggered by the click of a hyperlink." (emphasis added)).
Claim 12 recites:
automatically selecting a communication, from a plurality of different communications for a user;
automatically generating a prompt to a generative model based on the selected communication, the prompt including user context information;
identifying user context information for the user, wherein the user context information comprises subject matter of a project or a document on which the user has worked;
receiving a response to the prompt from the generative model, the response being indicative of a task execution plan with a set of function triggers that trigger functions to execute to perform a task identified in the selected message, wherein the task execution plan is based at least on the user context information and indicates chain-of-thought reasoning identifying intermediate reasoning steps for decomposing the task into executable functions;
automatically generating a task execution prompt for a generative task execution model, the task execution prompt including the set of function triggers;
receiving an execution result from the generative task execution model, the execution result being indicative of a result of executing the task; and
outputting the execution result for user interaction.
Step 2A, Prong I: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, abstract ideas.
The “automatically” limitation in #1 above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “automatically” in the context of this claim encompasses the person making a judgement.
The “automatically” limitation in #2 above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “automatically” in the context of this claim encompasses the person creating a prompt.
The “identifying” limitation in #3 above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “identifying” in the context of this claim encompasses the person making a judgement.
The “automatically” limitation in #5 above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “automatically” in the context of this claim encompasses the person creating a prompt.
Step 2A, Prong II: Does the claim recite additional elements that integrate the judicial exception into a practical application?
No.
The “receiving” limitation in #4 above, as claimed and under BRI, is an additional element that is insignificant extra-solution activity. For example, “receiving” in the context of this claim encompasses mere data gathering. See MPEP 2106.05(g).
The “receiving” limitation in #6 above, as claimed and under BRI, is an additional element that is insignificant extra-solution activity. For example, “receiving” in the context of this claim encompasses mere data gathering. See MPEP 2106.05(g).
The “outputting” limitation in #7 above, as claimed and under BRI, is an additional element that is insignificant extra-solution activity. For example, “outputting” in the context of this claim encompasses mere data transmitting. See MPEP 2106.05(g).
Additionally, the claim recites the following additional elements:
at least one processor
memory
computer executable instructions
executable functions
These additional elements are recited at a high level of generality (i.e., as generic computer components) such that they amount to no more than linking the judicial exception to a technological environment. Accordingly, these additional elements do not integrate the abstract idea(s) into a practical application because they do not impose any meaningful limits on practicing the abstract idea(s).
Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception?
No.
With regard to #4, #6, and #7 above, per MPEP 2106.05(d)(II), the courts have recognized the following computer function as well-understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity:
i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014) ("Unlike the claims in Ultramercial, the claims at issue here specify how interactions with the Internet are manipulated to yield a desired result‐‐a result that overrides the routine and conventional sequence of events ordinarily triggered by the click of a hyperlink." (emphasis added)).
As discussed above with respect to integration of the abstract idea(s) into a practical application, the aforementioned additional elements amount to no more than employing generic computer functions to execute an abstract idea, even when limiting the use of the idea to one particular environment. Mere linking the judicial exception to a technological environment using generic computer components cannot provide an inventive concept.
Claim 13 recites:
wherein automatically generating a prompt comprises:
automatically generating a task identification prompt to prompt a generative task identification model to identify the task in the selected communication; and
receiving a response to the task identification prompt, the response identifying the task and including a summary of the identified task.
Step 2A, Prong I: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, the abstract ideas of claim 12.
The “automatically” limitation above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “automatically” in the context of this claim encompasses the person creating a prompt.
Step 2A, Prong II: Does the claim recite additional elements that integrate the judicial exception into a practical application?
No.
The “receiving” limitation above, as claimed and under BRI, is an additional element that is insignificant extra-solution activity. For example, “receiving” in the context of this claim encompasses mere data gathering. See MPEP 2106.05(g).
Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception?
No.
With regard to the “receiving” limitation above, per MPEP 2106.05(d)(II), the courts have recognized the following computer function as well-understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity:
i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014) ("Unlike the claims in Ultramercial, the claims at issue here specify how interactions with the Internet are manipulated to yield a desired result‐‐a result that overrides the routine and conventional sequence of events ordinarily triggered by the click of a hyperlink." (emphasis added)).
Claim 14 recites:
wherein automatically generating a prompt to a generative model further comprises:
automatically generating, based on receiving the response to the task identification prompt, a plan generation prompt to a generative plan generation model, the plan generation prompt including the identified task and the summary of the identified task and a request portion requesting the task execution plan; and
receiving a response to the plan generation prompt, the response to the plan generation prompt including the task execution plan, the task execution plan identifying executable functions that can be executed to perform the identified task.
Step 2A, Prong I: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, the abstract ideas of claim 13.
The “automatically” limitation above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “automatically” in the context of this claim encompasses the person creating a prompt.
Step 2A, Prong II: Does the claim recite additional elements that integrate the judicial exception into a practical application?
No.
The “receiving” limitation above, as claimed and under BRI, is an additional element that is insignificant extra-solution activity. For example, “receiving” in the context of this claim encompasses mere data gathering. See MPEP 2106.05(g).
Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception?
No.
With regard to the “receiving” limitation above, per MPEP 2106.05(d)(II), the courts have recognized the following computer function as well-understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity:
i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014) ("Unlike the claims in Ultramercial, the claims at issue here specify how interactions with the Internet are manipulated to yield a desired result‐‐a result that overrides the routine and conventional sequence of events ordinarily triggered by the click of a hyperlink." (emphasis added)).
Claim 15 recites:
wherein automatically generating a prompt to a generative model comprises:
automatically generating a single prompt that prompts a set of generative models to identify the task in the selected communication and to generate the task execution plan based on the identified task, the task execution plan identifying a set of functions that can be executed to perform the identified task.
Step 2A, Prong I: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, the abstract ideas of claim 13.
The “automatically” limitation above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “automatically” in the context of this claim encompasses the person creating a prompt.
Step 2A, Prong II: Does the claim recite additional elements that integrate the judicial exception into a practical application?
No.
Claim 16 recites:
wherein generating the single prompt further comprises:
automatically generating the single prompt to prompt the generative plan execution model to execute the functions in the task execution plan and return the execution results.
Step 2A, Prong I: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, the abstract ideas of claim 15.
The “automatically” limitation above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “automatically” in the context of this claim encompasses the person creating a prompt.
Step 2A, Prong II: Does the claim recite additional elements that integrate the judicial exception into a practical application?
No.
Claim 17 recites:
receiving communications from a plurality of different communication channels; and
a filter configured to receive communications from a plurality of different communication channels and configured to filter the communications based on filter criteria to obtain a filtered set of communications for further processing and wherein selecting a communication comprises selecting the communication from the filtered set of communications.
Step 2A, Prong I: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, the abstract ideas of claim 12.
The “filter” limitation above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “filter” in the context of this claim encompasses the person making a judgement.
The “selecting” limitation above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “selecting” in the context of this claim encompasses the person making a judgement.
Step 2A, Prong II: Does the claim recite additional elements that integrate the judicial exception into a practical application?
No.
The “receiving” limitation above, as claimed and under BRI, is an additional element that is insignificant extra-solution activity. For example, “receiving” in the context of this claim encompasses mere data gathering. See MPEP 2106.05(g).
Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception?
No.
With regard to the “receiving” limitation above, per MPEP 2106.05(d)(II), the courts have recognized the following computer function as well-understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity:
i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014) ("Unlike the claims in Ultramercial, the claims at issue here specify how interactions with the Internet are manipulated to yield a desired result‐‐a result that overrides the routine and conventional sequence of events ordinarily triggered by the click of a hyperlink." (emphasis added)).
Claim 18 recites:
wherein automatically generating a prompt to a generative model comprises:
accessing the user context information from a plurality of dynamically changing user information sources to obtain the user context information.
Step 2A, Prong I: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, the abstract ideas of claim 12.
The “accessing” limitation above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “accessing” in the context of this claim encompasses the person viewing information.
Claim 19 recites:
a prompting system configured to automatically select a communication, from a plurality of different communications for a user and to automatically generate an artificial intelligence (AI) prompt to a generative AI model based on the selected communication, the AI prompt including; user context information imported from a user information source that stores dynamically changing user context information and; a request to generate a task execution plan to execute a task, the task execution plan comprising chain-of-thought reasoning identifying intermediate reasoning steps for decomposing the task into executable functions, wherein the user context information comprises action patterns identifying historical behavior of the user related to the selected communication; and
a response receiving system configured to receive a response to the AI prompt from the generative AI model, the response being indicative of a mapping between a task identified in the selected communication and a set of function triggers that trigger functions to execute to perform the task identified in the selected communication, the prompting system being configured to automatically generate a task execution prompt for a generative AI task execution model, the task execution prompt including the set of function triggers; and
a result processor configured to receive an execution result from the generative AI task execution model, the execution result being indicative of a result of executing the task, and to output the execution result for user interaction.
Step 2A, Prong I: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, abstract ideas.
The “automatically select” limitation above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “automatically select” in the context of this claim encompasses the person making a judgement.
The “automatically generate an artificial intelligence (AI) prompt” limitation above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “automatically generate an artificial intelligence (AI) prompt” in the context of this claim encompasses the person creating a prompt.
The “automatically generate a task execution prompt” limitation above, as claimed and under broadest reasonable interpretation (BRI), is a mental process that covers performance of the limitation in the mind. For example, “automatically generate a task execution prompt” in the context of this claim encompasses the person creating a prompt.
Step 2A, Prong II: Does the claim recite additional elements that integrate the judicial exception into a practical application?
No.
The “receive a response” limitation above, as claimed and under BRI, is an additional element that is insignificant extra-solution activity. For example, “receive a response” in the context of this claim encompasses mere data gathering. See MPEP 2106.05(g).
The “receive an execution result” limitation above, as claimed and under BRI, is an additional element that is insignificant extra-solution activity. For example, “receive an execution result” in the context of this claim encompasses mere data gathering. See MPEP 2106.05(g).
The “output” limitation above, as claimed and under BRI, is an additional element that is insignificant extra-solution activity. For example, “output” in the context of this claim encompasses mere data transmitting. See MPEP 2106.05(g).
Additionally, the claim recites the following additional elements:
at least one processor
a prompting system
a generative AI model
a response receiving system
a generative AI task execution model
a result processor
executable functions
These additional elements are recited at a high level of generality (i.e., as generic computer components) such that they amount to no more than linking the judicial exception to a technological environment. Accordingly, these additional elements do not integrate the abstract idea(s) into a practical application because they do not impose any meaningful limits on practicing the abstract idea(s).
Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception?
No.
With regard to the “receive a response”, “receive an execution result”, and “output” limitations above, per MPEP 2106.05(d)(II), the courts have recognized the following computer function as well-understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity:
i. Receiving or transmitting data over a network, e.g., using the Internet to gather data, Symantec, 838 F.3d at 1321, 120 USPQ2d at 1362 (utilizing an intermediary computer to forward information); TLI Communications LLC v. AV Auto. LLC, 823 F.3d 607, 610, 118 USPQ2d 1744, 1745 (Fed. Cir. 2016) (using a telephone for image transmission); OIP Techs., Inc., v. Amazon.com, Inc., 788 F.3d 1359, 1363, 115 USPQ2d 1090, 1093 (Fed. Cir. 2015) (sending messages over a network); buySAFE, Inc. v. Google, Inc., 765 F.3d 1350, 1355, 112 USPQ2d 1093, 1096 (Fed. Cir. 2014) (computer receives and sends information over a network); but see DDR Holdings, LLC v. Hotels.com, L.P., 773 F.3d 1245, 1258, 113 USPQ2d 1097, 1106 (Fed. Cir. 2014) ("Unlike the claims in Ultramercial, the claims at issue here specify how interactions with the Internet are manipulated to yield a desired result‐‐a result that overrides the routine and conventional sequence of events ordinarily triggered by the click of a hyperlink." (emphasis added)).
As discussed above with respect to integration of the abstract idea(s) into a practical application, the aforementioned additional elements amount to no more than components comprising mere instructions to apply the exception or links the judicial exception to a technological environment. Mere instructions to apply an exception using generic computer components or linking the judicial exception.
Claim 20 recites:
wherein the prompting system includes a prompt chaining processor configured to generate chained prompts and a chain-of-thought processor configured to generate a chain-of-thought prompt.
Step 2A, Prong I: Does the claim recite an abstract idea, law of nature, or natural phenomenon?
Yes, the abstract ideas of claim 15.
The “generate” limitations above, as claimed and under broadest reasonable interpretation (BRI), are mental processes that covers performance of the limitation in the mind. For example, “generate” in the context of this claim encompasses the person creating prompts.
Step 2A, Prong II: Does the claim recite additional elements that integrate the judicial exception into a practical application?
No.
The claim recites the following additional elements:
the prompting system
a prompt chaining processor
a chain-of-thought processor
These additional elements are recited at a high level of generality (i.e., as generic computer
components) such that they amount to no more than linking the judicial exception to a technological environment. Accordingly, these additional elements do not integrate the abstract idea(s) into a practical application because they do not impose any meaningful limits on practicing the abstract idea(s).
Step 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception?
No.
As discussed above with respect to integration of the abstract idea(s) into a practical application, the aforementioned additional elements amount to no more than components comprising mere instructions to apply the exception or links the judicial exception to a technological environment. Mere instructions to apply an exception using generic computer components or linking 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.
Claims 1-10, 12-16, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Pulsipher (U.S. Patent Application Publication No. US 20080005053 A1, from IDS filled on 5 September 2024) in view of Khyatti (WIPO Patent Application Publication No. WO 2024163363 A1) and Carolan et al. (U.S. Patent Application Publication No. US 20150143258 A1, hereinafter “Carolan”).
With regard to claim 1, Pulsipher discloses:
A computer implemented method (“systems and/or methods of the embodiments can be utilized in task recognition facilitating computer components”, para [0044]), comprising:
automatically selecting a communication, from a plurality of different communications for a user ("the task recognition system 100 is comprised of a task assistant component 102 that receives communications 104 and provides candidate tasks 106. The communications 104 can include, but are not limited to, voice communications and/or written communications and the like such as, for example, emailing, instant messaging, text messaging, telephone calls, etc. The task assistant component 102 can be adapted to perform various types of recognition based on the type of communications 104", para [0016]);
identifying user context information for the user ("The intent recognition component 208 can also employ contextual and/or environmental information to assist in assessing tasks'', para [0023]),
automatically generating at least one prompt to a generative model based on the selected communication, the at least one prompt including the user context information and requesting identification of a task in the selected communication ("The candidate task component 210 receives the task intent from the intent recognition component 208 and associates it with a task. Thus, for example, if the intent recognition component 208 determined that a user intends to schedule a meeting, the candidate task component 210 determines what task and/or tasks need to be performed to accomplish it.", para [0025], "The intent recognition component 208 can also employ contextual and/or environmental information to assist in assessing tasks'', para [0023]), the at least one prompt further including a request to generate and execute a task execution plan to execute the identified task ("if the intent recognition component 208 determined that a user intends to schedule a meeting, the candidate task component 210 determines what task and/or tasks need to be performed to accomplish it. The tasks for scheduling a meeting can include opening up a calendar and inserting meeting titles, parties to the meeting, times of the meeting, and/or adding additional information such as, for example, a link to why the meeting was input into the calendar, etc. It can also include a task to remind the user of the meeting and/or a task to follow-up with another party to obtain additional information such as their contact information to allow completion of the meeting scheduling. Another task can include notification of others that a meeting is to take place. Thus, the candidate task component 210 determines what tasks are associated with the user's intent and provides them as the candidate tasks 206.”, para [0025]),
automatically sending the task execution plan to a plan execution system ("when an action intention is recognized, an item is added to the action stack 412 by the task assistant component 404… The action manager component 414, in this example, pulls items from the action stack 412 on a first-in, first-out (FIFO) basis". par. [0035]);
receiving an execution result from the plan execution system, the execution result being indicative of a result of executing the task execution plan (“The selected task is then executed utilizing an action profile and a task associated application 606”, para [0040], “The user is then provided with a visualization of the executed task that includes information relating to an origin of the task 608, ending the flow 610.”, para [0041]); and
outputting the execution result for user interaction (“The user is then provided with a visualization of the executed task that includes information relating to an origin of the task 608, ending the flow 610.”, para [0041]).
Pulsipher does not disclose:
wherein the user context information comprises subject matter of a project or a document on which the user has worked;
wherein the task execution plan is based at least on the user context information and comprises chain-of-thought reasoning output, from the generative model, identifying intermediate reasoning steps for decomposing the task into executable functions;
Carolan discloses:
wherein the user context information comprises subject matter of (“Additionally, contextual information may be obtained from the content of an email, such as the sender's name or other information in the subject line or the body of the email. For example, a command such as "Flowers $50 `to the one I Love`" in the context of received email from a loved one may be interpreted to generate a command to order flowers for the person associated with the email.”, para [0084]);
Both the systems of Pulsipher and Carolan deal with automated task identification. It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to combine Pulsipher in view of Carolan to “better use the time of knowledge workers and to increase productivity in organizations.” (Carolan, para [0003]).
Khyatti discloses:
wherein the task execution plan (i.e. “CoT chain”) is based at least on the user context information (“In block 206, an initiating prompt is built, based on the received task description, any supplemental information, and prompt rules. The initiating prompt is built to include the required prompt rules, such as core rules, as described herein.”, para [101], "In some implementations, the task description may be accompanied by supplemental information, such as target output, context information, and guidelines, to add to directions provided by the task description for the machine learning model. Such supplemental information enables an output result that aligns closer with a target result of the user. For example, context information may be entered by the user 402 to provide considerations for the CoT meta-prompting process. Context information may include, for example, background information, particulars to be included in the task, reasons or applications for the task, a user perspective on the task, a setting and/or scope, etc." para [115], “In block 212, the initiating prompt and the series of ordered next prompt(s) are fed into the machine learning model to form the basis of each instruction and generate the series of agents of the CoT chain.”, para [104], 206, 212, fig 2) and comprises chain-of-thought reasoning output (i.e. “step-by-step instructions”), from the generative model (i.e. “GPT-3”), identifying intermediate reasoning steps for decomposing the task into executable functions (“the machine learning model to create step-by-step instructions for the given task, hence producing the requested CoT chain.”, para [116], “The machine learning model 120 is an artificial intelligence (Al) model that is configured to create the CoT for a given task. The machine learning model may be a large language model (LLM) that can perform complex reasoning, such as Generative Pre-trained Transformer (GPT-3, GPT-4, GPT-4-Turbo, etc.) large language model, or other language models that may be developed appropriate to create a CoT according to the CoT meta-prompt process described herein.”, para [0086], “In block 214, the series of sequential instructions of the resulting CoT chain is received from the machine learning model. The resulting CoT chain may be provided to a user via the frontend, to a task performance unit to execute the task according to the series of instructions, and/or to a storage unit. In some implementations, the user views the completed CoT and accepts or rejects the completed CoT. If the sequence of instructions are accepted, the user may activate performance of the task, such as by a task performance unit.”, para [110]);
Both the systems of Pulsipher and Khyatti deal with generating steps to execute a task. It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to combine Pulsipher as modified in view of Khyatti to “optimally performs a task and facilitates a better-quality result” (Khyatti, para [05]).
With regard to claim 2, Pulsipher as modified discloses the computer implemented method of claim 1.
Pulsipher further discloses:
wherein automatically generating at least one prompt comprises:
automatically generating a task identification prompt to prompt a task identification model to identify the task in the selected communication (“The recognition of the task intent can be assisted with artificial intelligence techniques such as, for example, natural language processing techniques and the like. The intent recognition component 208 determines if a task has been referred to and the intent, if any, regarding accomplishment of the task.”, para [0022], “As an example, the intent recognition component 208 can dynamically recognize a phrase such as "schedule a meeting on Wednesday" and can determine, for example, if user A is the party that will do the scheduling (e.g. user A states "yes, I'll schedule that").”, para [0023]); and
receiving a response to the task identification prompt, the response identifying the task (“Thus, user A can be presented with a candidate task for scheduling the meeting.”, para [0023]).
With regard to claim 3, Pulsipher as modified discloses the computer implemented method of claim 2.
Pulsipher further discloses:
wherein automatically generating at least one prompt further comprises:
automatically generating, based on receiving the response to the task identification prompt, a plan generation prompt to a plan generation model, the plan generation prompt including the identified task and requesting the task execution plan (“The candidate task component 210 receives the task intent from the intent recognition component 208 and associates it with a task. Thus, for example, if the intent recognition component 208 determined that a user intends to schedule a meeting, the candidate task component 210 determines what task and/or tasks need to be performed to accomplish it. The tasks for scheduling a meeting can include opening up a calendar and inserting meeting titles, parties to the meeting, times of the meeting, and/or adding additional information such as, for example, a link to why the meeting was input into the calendar, etc. It can also include a task to remind the user of the meeting and/or a task to follow-up with another party to obtain additional information such as their contact information to allow completion of the meeting scheduling. Another task can include notification of others that a meeting is to take place. Thus, the candidate task component 210 determines what tasks are associated with the user's intent and provides them as the candidate tasks 206.”, para [0025]); and
receiving a response to the plan generation prompt, the response to the plan generation prompt including the task execution plan, the task execution plan identifying the executable functions to be executed to perform the identified task (“A detected intent is then associated with a task to create a candidate task 506. A user intent can require one or more tasks to complete. For example, a user might state "yes, I'll go on the trip with you" and that might require not only an input to a calendar program as a reminder, but also a task to contact a travel agency and/or request tickets, a rental car, and/or a hotel and the like. A user is then prompted of the candidate task following a trigger event 508, ending the flow 510.”, para [0039]).
With regard to claim 4, Pulsipher as modified discloses the computer implemented method of claim 3.
Pulsipher further discloses:
wherein automatically generating the task identification prompt includes generating a summarization request to summarize the identified task and wherein receiving the response to the task identification prompt comprises receiving a summary of the identified task (“Instances disclosed herein can allow such a communication device to "listen" for the intent of users regarding a mentioned task during their conversation, and after the call completes, prompt for further action based on those task intents. Phrases like "follow-up," "schedule a meeting," "call you tomorrow," etc. can be construed as an intent by a user to actually commit to performing a certain task. For example, if a user was talking to "Bob" and said "I'll follow up on this tomorrow." After the call, the communication device can speak the prompt "Would you like to add a task to follow-up with Bob?’”, para [0033]).
With regard to claim 5, Pulsipher as modified discloses the computer implemented method of claim 4.
Pulsipher further discloses:
wherein automatically generating the plan generation prompt comprises:
generating the plan generation prompt to include the summary of the identified task (“A detected intent is then associated with a task to create a candidate task 506. A user intent can require one or more tasks to complete. For example, a user might state "yes, I'll go on the trip with you" and that might require not only an input to a calendar program as a reminder, but also a task to contact a travel agency and/or request tickets, a rental car, and/or a hotel and the like. A user is then prompted of the candidate task following a trigger event 508, ending the flow 510.”. para [0039]).
With regard to claim 6, Pulsipher as modified discloses the computer implemented method of claim 3.
Pulsipher further discloses:
wherein receiving the response to the plan generation prompt includes:
receiving a function trigger corresponding to each of the executable functions identified in the task execution plan, each function trigger triggering, in the plan execution system, execution of a corresponding function (“The action manager component 312 receives the user input 318 and acts upon any desired tasks…This interaction with the user 316, allows the user 316 to maintain control over what, how and/or when the tasks are accomplished.”, para [0028], “Looking at FIG. 6, another flow diagram of a method 600 of facilitating task recognition in communications in accordance with an aspect of an embodiment is depicted. The method 600 starts 602 by accepting a candidate task selection from a user 604. As noted supra, candidate tasks are presented to a user at an appropriate time, giving the user control over what tasks and when and/or how the tasks are completed. The selected task is then executed utilizing an action profile and a task associated application 606.”, para [0040]).
With regard to claim 7, Pulsipher as modified discloses the computer implemented method of claim 6.
Pulsipher further discloses:
wherein receiving the execution result comprises:
sending the task execution plan to the plan execution system for execution of the functions triggered by the function triggers to generate the task execution result (“Looking at FIG. 6, another flow diagram of a method 600 of facilitating task recognition in communications in accordance with an aspect of an embodiment is depicted. The method 600 starts 602 by accepting a candidate task selection from a user 604. As noted supra, candidate tasks are presented to a user at an appropriate time, giving the user control over what tasks and when and/or how the tasks are completed. The selected task is then executed utilizing an action profile and a task associated application 606. Action profiles can be supplied by third parties such as, for example, the providers of the task associated application and the like.”, para [0040]); and
receiving the execution result generated by executing the functions (“The user is then provided with a visualization of the executed task that includes information relating to an origin of the task 608, ending the flow 610. For example, a user is presented with a completed calendar entry with a hyperlink linking to when a communication occurred, who the communication was with, and/or the length of the communication. This can assist a user in remembering why the calendar entry was made.”, para [0041]).
With regard to claim 8, Pulsipher as modified discloses the computer implemented method of claim 7.
Pulsipher further discloses:
wherein the plan execution system comprises a generative task execution model (“The task assistant component 102 can employ artificial intelligence mechanisms to facilitate task recognition as well.”, para [0016], “Looking at FIG. 6, another flow diagram of a method 600 of facilitating task recognition in communications in accordance with an aspect of an embodiment is depicted.”, para [0040]) and wherein sending the task execution plan to the plan execution system further comprises:
automatically generating a task execution prompt to the generative task execution model, the task execution prompt including the function triggers (“A detected intent is then associated with a task to create a candidate task 506. A user intent can require one or more tasks to complete. For example, a user might state "yes, I'll go on the trip with you" and that might require not only an input to a calendar program as a reminder, but also a task to contact a travel agency and/or request tickets, a rental car, and/or a hotel and the like. A user is then prompted of the candidate task following a trigger event 508, ending the flow 510.”, para [0039], “ The method 600 starts 602 by accepting a candidate task selection from a user 604. As noted supra, candidate tasks are presented to a user at an appropriate time, giving the user control over what tasks and when and/or how the tasks are completed. The selected task is then executed utilizing an action profile and a task associated application 606.”. para [0040]).
With regard to claim 9, Pulsipher as modified discloses the computer implemented method of claim 1.
Pulsipher further discloses:
wherein automatically generating at least one prompt to a generative model comprises:
automatically generating a single prompt that prompts a set of generative models to identify the task in the selected communication and to generate the task execution plan based on the identified task, the task execution plan identifying a set of functions to be executed to perform the identified task (“The recognition of the task intent can be assisted with artificial intelligence techniques such as, for example, natural language processing techniques and the like. The intent recognition component 208 determines if a task has been referred to and the intent, if any, regarding accomplishment of the task.”, para [0022], “As an example, the intent recognition component 208 can dynamically recognize a phrase such as "schedule a meeting on Wednesday" and can determine, for example, if user A is the party that will do the scheduling (e.g. user A states "yes, I'll schedule that").”, para [0023], “The candidate task component 210 receives the task intent from the intent recognition component 208 and associates it with a task. Thus, for example, if the intent recognition component 208 determined that a user intends to schedule a meeting, the candidate task component 210 determines what task and/or tasks need to be performed to accomplish it…Thus, the candidate task component 210 determines what tasks are associated with the user's intent and provides them as the candidate tasks 206.”, para [0025]).
With regard to claim 10, Pulsipher as modified discloses the computer implemented method of claim 9.
Pulsipher further discloses:
wherein automatically generating the single prompt further comprises:
automatically generating the single prompt to prompt the plan execution system to execute the functions in the task execution plan and return the execution results (“The selected task is then executed utilizing an action profile and a task associated application 606. Action profiles can be supplied by third parties such as, for example, the providers of the task associated application and the like.”, para [0040], “The user is then provided with a visualization of the executed task that includes information relating to an origin of the task 608, ending the flow 610. For example, a user is presented with a completed calendar entry with a hyperlink linking to when a communication occurred, who the communication was with, and/or the length of the communication. This can assist a user in remembering why the calendar entry was made.”, para [0041]).
With regard to claim 12, Pulsipher discloses:
A computer system (“systems and/or methods of the embodiments can be utilized in task recognition facilitating computer components”, para [0044]), comprising:
at least one processor (“a processor”, para [0014]); and
memory that stores computer executable instructions which (“computer-executable instructions”, para [0038], “server data store(s) 706 that can be employed to store information local to the server(s)”, para [0043]), when executed by the at least one processor (“computer-executable instructions, such as program modules, executed by one or more components.”, para [0038], “As used in this application, the term "component" is intended to refer to a computer-related entity, either hardware, a combination of hardware and software, software, or software in execution.”, para [0014]), cause the at least one processor to perform steps, comprising:
automatically selecting a communication, from a plurality of different communications for a user ("the task recognition system 100 is comprised of a task assistant component 102 that receives communications 104 and provides candidate tasks 106. The communications 104 can include, but are not limited to, voice communications and/or written communications and the like such as, for example, emailing, instant messaging, text messaging, telephone calls, etc. The task assistant component 102 can be adapted to perform various types of recognition based on the type of communications 104", para [0016]);
identifying user context information for the user ("The intent recognition component 208 can also employ contextual and/or environmental information to assist in assessing tasks'', para [0023]),
automatically generating a prompt to a generative model based on the selected communication, the prompt including the user context information ("The candidate task component 210 receives the task intent from the intent recognition component 208 and associates it with a task. Thus, for example, if the intent recognition component 208 determined that a user intends to schedule a meeting, the candidate task component 210 determines what task and/or tasks need to be performed to accomplish it.", para [0025], "The intent recognition component 208 can also employ contextual and/or environmental information to assist in assessing tasks'', para [0023]);
receiving a response to the prompt from the generative model, the response being indicative of a task execution plan with a set of function triggers that trigger functions to execute to perform a task identified in the selected message (“The candidate task component 210 receives the task intent from the intent recognition component 208 and associates it with a task. Thus, for example, if the intent recognition component 208 determined that a user intends to schedule a meeting, the candidate task component 210 determines what task and/or tasks need to be performed to accomplish it. The tasks for scheduling a meeting can include opening up a calendar and inserting meeting titles, parties to the meeting, times of the meeting, and/or adding additional information such as, for example, a link to why the meeting was input into the calendar, etc. It can also include a task to remind the user of the meeting and/or a task to follow-up with another party to obtain additional information such as their contact information to allow completion of the meeting scheduling. Another task can include notification of others that a meeting is to take place. Thus, the candidate task component 210 determines what tasks are associated with the user's intent and provides them as the candidate tasks 206.”, para [0025]),
automatically generating a task execution prompt to the generative task execution model, the task execution prompt including the function triggers (“A detected intent is then associated with a task to create a candidate task 506. A user intent can require one or more tasks to complete. For example, a user might state "yes, I'll go on the trip with you" and that might require not only an input to a calendar program as a reminder, but also a task to contact a travel agency and/or request tickets, a rental car, and/or a hotel and the like. A user is then prompted of the candidate task following a trigger event 508, ending the flow 510.”, para [0039], “ The method 600 starts 602 by accepting a candidate task selection from a user 604. As noted supra, candidate tasks are presented to a user at an appropriate time, giving the user control over what tasks and when and/or how the tasks are completed. The selected task is then executed utilizing an action profile and a task associated application 606.”. para [0040], “instances can automatically perform candidate task actions without user intervention”, para [0003]);
receiving an execution result from the generative task execution model, the execution result being indicative of a result of executing the task (“The selected task is then executed utilizing an action profile and a task associated application 606”, para [0040], “The user is then provided with a visualization of the executed task that includes information relating to an origin of the task 608, ending the flow 610.”, para [0041]); and
outputting the execution result for user interaction (“The user is then provided with a visualization of the executed task that includes information relating to an origin of the task 608, ending the flow 610.”, para [0041]).
Pulsipher does not disclose:
wherein the user context information comprises subject matter of a project or a document on which the user has worked;
wherein the task execution plan is based at least on the user context information and comprises chain-of-thought reasoning output, from the generative model, identifying intermediate reasoning steps for decomposing the task into executable functions;
Carolan discloses:
wherein the user context information comprises subject matter of (“Additionally, contextual information may be obtained from the content of an email, such as the sender's name or other information in the subject line or the body of the email. For example, a command such as "Flowers $50 `to the one I Love`" in the context of received email from a loved one may be interpreted to generate a command to order flowers for the person associated with the email.”, para [0084]);
Both the systems of Pulsipher and Carolan deal automated task identification. It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to combine Pulsipher in view of Carolan to “better use the time of knowledge workers and to increase productivity in organizations.” (Carolan, para [0003]).
Khyatti discloses:
wherein the task execution plan (i.e. “CoT chain”) is based at least on the user context information (“In block 206, an initiating prompt is built, based on the received task description, any supplemental information, and prompt rules. The initiating prompt is built to include the required prompt rules, such as core rules, as described herein.”, para [101], "In some implementations, the task description may be accompanied by supplemental information, such as target output, context information, and guidelines, to add to directions provided by the task description for the machine learning model. Such supplemental information enables an output result that aligns closer with a target result of the user. For example, context information may be entered by the user 402 to provide considerations for the CoT meta-prompting process. Context information may include, for example, background information, particulars to be included in the task, reasons or applications for the task, a user perspective on the task, a setting and/or scope, etc." para [115], “In block 212, the initiating prompt and the series of ordered next prompt(s) are fed into the machine learning model to form the basis of each instruction and generate the series of agents of the CoT chain.”, para [104], 206, 212, fig 2) and comprises chain-of-thought reasoning output (i.e. “step-by-step instructions”), from the generative model (i.e. “GPT-3”), identifying intermediate reasoning steps for decomposing the task into executable functions (“the machine learning model to create step-by-step instructions for the given task, hence producing the requested CoT chain.”, para [116], “The machine learning model 120 is an artificial intelligence (Al) model that is configured to create the CoT for a given task. The machine learning model may be a large language model (LLM) that can perform complex reasoning, such as Generative Pre-trained Transformer (GPT-3, GPT-4, GPT-4-Turbo, etc.) large language model, or other language models that may be developed appropriate to create a CoT according to the CoT meta-prompt process described herein.”, para [0086], “In block 214, the series of sequential instructions of the resulting CoT chain is received from the machine learning model. The resulting CoT chain may be provided to a user via the frontend, to a task performance unit to execute the task according to the series of instructions, and/or to a storage unit. In some implementations, the user views the completed CoT and accepts or rejects the completed CoT. If the sequence of instructions are accepted, the user may activate performance of the task, such as by a task performance unit.”, para [110]);
Both the systems of Pulsipher and Khyatti deal with generating steps to execute a task. It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to combine Pulsipher as modified in view of Khyatti to “optimally performs a task and facilitates a better-quality result” (Khyatti, para [05]).
With regard to claim 13, Pulsipher as modified discloses the computer system of claim 12.
Pulsipher further discloses:
wherein automatically generating a prompt comprises:
automatically generating a task identification prompt to prompt a generative task identification model to identify the task in the selected communication (“The recognition of the task intent can be assisted with artificial intelligence techniques such as, for example, natural language processing techniques and the like. The intent recognition component 208 determines if a task has been referred to and the intent, if any, regarding accomplishment of the task.”, para [0022], “As an example, the intent recognition component 208 can dynamically recognize a phrase such as "schedule a meeting on Wednesday" and can determine, for example, if user A is the party that will do the scheduling (e.g. user A states "yes, I'll schedule that").”, para [0023]); and
receiving a response to the task identification prompt, the response identifying the task and including a summary of the identified task (“Thus, user A can be presented with a candidate task for scheduling the meeting.”, para [0023]).
With regard to claim 14, Pulsipher as modified discloses the computer system of claim 13.
Pulsipher further discloses:
wherein automatically generating a prompt to a generative model further comprises:
automatically generating, based on receiving the response to the task identification prompt, a plan generation prompt to a generative plan generation model, the plan generation prompt including the identified task and the summary of the identified task and a request portion requesting the task execution plan ("The candidate task component 210 receives the task intent from the intent recognition component 208 and associates it with a task. Thus, for example, if the intent recognition component 208 determined that a user intends to schedule a meeting, the candidate task component 210 determines what task and/or tasks need to be performed to accomplish it.", para [0025], "The intent recognition component 208 can also employ contextual and/or environmental information to assist in assessing tasks'', para [0023], “instances can automatically perform candidate task actions without user intervention”, para [0003]); and
receiving a response to the plan generation prompt, the response to the plan generation prompt including the task execution plan, the task execution plan identifying executable functions to be executed to perform the identified task (“The candidate task component 210 receives the task intent from the intent recognition component 208 and associates it with a task. Thus, for example, if the intent recognition component 208 determined that a user intends to schedule a meeting, the candidate task component 210 determines what task and/or tasks need to be performed to accomplish it. The tasks for scheduling a meeting can include opening up a calendar and inserting meeting titles, parties to the meeting, times of the meeting, and/or adding additional information such as, for example, a link to why the meeting was input into the calendar, etc. It can also include a task to remind the user of the meeting and/or a task to follow-up with another party to obtain additional information such as their contact information to allow completion of the meeting scheduling. Another task can include notification of others that a meeting is to take place. Thus, the candidate task component 210 determines what tasks are associated with the user's intent and provides them as the candidate tasks 206.”, para [0025]).
With regard to claim 15, Pulsipher as modified discloses the computer system of claim 12.
Pulsipher further discloses:
wherein automatically generating a prompt to a generative model comprises:
automatically generating a single prompt that prompts a set of generative models to identify the task in the selected communication and to generate the task execution plan based on the identified task, the task execution plan identifying a set of functions to be executed to perform the identified task (“The recognition of the task intent can be assisted with artificial intelligence techniques such as, for example, natural language processing techniques and the like. The intent recognition component 208 determines if a task has been referred to and the intent, if any, regarding accomplishment of the task.”, para [0022], “As an example, the intent recognition component 208 can dynamically recognize a phrase such as "schedule a meeting on Wednesday" and can determine, for example, if user A is the party that will do the scheduling (e.g. user A states "yes, I'll schedule that").”, para [0023], “The candidate task component 210 receives the task intent from the intent recognition component 208 and associates it with a task. Thus, for example, if the intent recognition component 208 determined that a user intends to schedule a meeting, the candidate task component 210 determines what task and/or tasks need to be performed to accomplish it…Thus, the candidate task component 210 determines what tasks are associated with the user's intent and provides them as the candidate tasks 206.”, para [0025]).
With regard to claim 16, Pulsipher as modified discloses the computer system claim 15.
Pulsipher further discloses:
wherein generating the single prompt further comprises:
automatically generating the single prompt to prompt the generative plan execution model to execute the functions in the task execution plan and return the execution results (“The selected task is then executed utilizing an action profile and a task associated application 606. Action profiles can be supplied by third parties such as, for example, the providers of the task associated application and the like.”, para [0040], “The user is then provided with a visualization of the executed task that includes information relating to an origin of the task 608, ending the flow 610. For example, a user is presented with a completed calendar entry with a hyperlink linking to when a communication occurred, who the communication was with, and/or the length of the communication. This can assist a user in remembering why the calendar entry was made.”, para [0041]).
With regard to claim 18, Pulsipher as modified discloses the computer system claim 12.
Pulsipher further discloses:
wherein automatically generating a prompt to a generative model comprises:
accessing the user context information from a plurality of dynamically changing user information sources to obtain the user context information (“The intent recognition component 208 can also employ contextual and/or environmental information to assist in assessing tasks and/or intent. For example, time-of-day can be utilized to determine when a user intends to do a task. Thus, if the time is 11 am and the user refers to completing the task "by 10," they are most likely referring to 10 pm and not 10 am. Similarly, environmental information such as whether the user is on the phone, on the computer, in the office or in a car, etc., can be utilized to facilitate determination of the intention of the user associated with a task.”, para [0023]).
Claims 11 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Pulsipher in view of Khyatti and Carolan as applied to claims 1 and 12 above, and further in view of Chow et al. (U.S. Patent Application Publication No. US 20220215351 A1, hereinafter “Chow”).
With regard to claim 11, Pulsipher as modified discloses the computer implemented method claim 1.
Pulsipher further discloses:
further comprising:
receiving communications from a plurality of different communication channels ("the task recognition system 100 is comprised of a task assistant component 102 that receives communications 104 and provides candidate tasks 106. The communications 104 can include, but are not limited to, voice communications and/or written communications and the like such as, for example, emailing, instant messaging, text messaging, telephone calls, etc. The task assistant component 102 can be adapted to perform various types of recognition based on the type of communications 104", para [0016]); and
Pulsipher as modified does not disclose however, Chow discloses:
filtering the communications based on filter criteria to obtain a filtered set of communications for further processing (“At stage 315, the SEG 120 or mail server 110 can filter for task-related emails. This can include parsing the email by applying an ML model 135 to determine intents and slots, or simply looking for keywords. A task can be identified based on recognition of a relationship between sender and recipient, reference to a backend system 140, reference to a project, or reference to a document, among other ways.”, para [0052]) and wherein selecting the communication comprises selecting the communication from the filtered set of communications (“If a task is identified, the task-related email can be processed for task scheduling. In one example, this can include sending a copy of that email to the management server 130 for task processing”, para [0052]).
Both the systems of Pulsipher and Chow deal with autonomous task recognition. It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to combine Pulsipher as modified in view of Chow to utilize processing capability efficiently.
With regard to claim 17, Pulsipher as modified discloses the computer system claim 12.
Pulsipher further discloses:
further comprising:
receiving communications from a plurality of different communication channels ("the task recognition system 100 is comprised of a task assistant component 102 that receives communications 104 and provides candidate tasks 106. The communications 104 can include, but are not limited to, voice communications and/or written communications and the like such as, for example, emailing, instant messaging, text messaging, telephone calls, etc. The task assistant component 102 can be adapted to perform various types of recognition based on the type of communications 104", para [0016]); and
Pulsipher as modified does not disclose however, Chow discloses:
a filter configured to receive communications from a plurality of different communication channels and configured to filter the communications based on filter criteria to obtain a filtered set of communications for further processing (“At stage 315, the SEG 120 or mail server 110 can filter for task-related emails. This can include parsing the email by applying an ML model 135 to determine intents and slots, or simply looking for keywords. A task can be identified based on recognition of a relationship between sender and recipient, reference to a backend system 140, reference to a project, or reference to a document, among other ways.”, para [0052]) and wherein selecting the communication comprises selecting the communication from the filtered set of communications (“If a task is identified, the task-related email can be processed for task scheduling. In one example, this can include sending a copy of that email to the management server 130 for task processing”, para [0052]).
Both the systems of Pulsipher and Chow deal with autonomous task recognition. It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to combine Pulsipher as modified in view of Chow to utilize processing capability efficiently.
31. Claims 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Pulsipher (U.S. Patent Application Publication No. US 20080005053 A1, from IDS filled on 5 September 2024) in view of Khyatti (WIPO Patent Application Publication No. WO 2024163363 A1) and Jina et al. (U.S. Patent Application Publication No. US 20200374243 A1, hereinafter “Jina”).
With regard to claim 19, Pulsipher discloses:
A computer system (“systems and/or methods of the embodiments can be utilized in task recognition facilitating computer components”, para [0044]), comprising:
at least one processor (“a processor”, para [0014]);
a prompting system configured to automatically select a communication, from a plurality of different communications for a user ("the task recognition system 100 is comprised of a task assistant component 102 that receives communications 104 and provides candidate tasks 106. The communications 104 can include, but are not limited to, voice communications and/or written communications and the like such as, for example, emailing, instant messaging, text messaging, telephone calls, etc. The task assistant component 102 can be adapted to perform various types of recognition based on the type of communications 104", para [0016]) and to automatically generate an artificial intelligence (AI) prompt to a generative AI model based on the selected communication, the AI prompt including;
user context information imported from a user information source that stores dynamically changing user context information ("The candidate task component 210 receives the task intent from the intent recognition component 208 and associates it with a task. Thus, for example, if the intent recognition component 208 determined that a user intends to schedule a meeting, the candidate task component 210 determines what task and/or tasks need to be performed to accomplish it.", para [0025], "The intent recognition component 208 can also employ contextual and/or environmental information to assist in assessing tasks. For example, time-of-day can be utilized to determine when a user intends to do a task. Thus, if the time is 11 am and the user refers to completing the task "by 10," they are most likely referring to 10 pm and not 10 am. '', para [0023]),
a request to generate a task execution plan to execute a task ("if the intent recognition component 208 determined that a user intends to schedule a meeting, the candidate task component 210 determines what task and/or tasks need to be performed to accomplish it. The tasks for scheduling a meeting can include opening up a calendar and inserting meeting titles, parties to the meeting, times of the meeting, and/or adding additional information such as, for example, a link to why the meeting was input into the calendar, etc. It can also include a task to remind the user of the meeting and/or a task to follow-up with another party to obtain additional information such as their contact information to allow completion of the meeting scheduling. Another task can include notification of others that a meeting is to take place. Thus, the candidate task component 210 determines what tasks are associated with the user's intent and provides them as the candidate tasks 206.”, para [0025]),
a response receiving system configured to receive a response to the AI prompt from the generative AI model, the response being indicative of a mapping between a task identified in the selected communication and a set of function triggers that trigger functions to execute to perform the task identified in the selected communication (“The candidate task component 210 receives the task intent from the intent recognition component 208 and associates it with a task. Thus, for example, if the intent recognition component 208 determined that a user intends to schedule a meeting, the candidate task component 210 determines what task and/or tasks need to be performed to accomplish it. The tasks for scheduling a meeting can include opening up a calendar and inserting meeting titles, parties to the meeting, times of the meeting, and/or adding additional information such as, for example, a link to why the meeting was input into the calendar, etc. It can also include a task to remind the user of the meeting and/or a task to follow-up with another party to obtain additional information such as their contact information to allow completion of the meeting scheduling. Another task can include notification of others that a meeting is to take place. Thus, the candidate task component 210 determines what tasks are associated with the user's intent and provides them as the candidate tasks 206.”, para [0025]), the prompting system being configured to automatically generate a task execution prompt for a generative AI task execution model, the task execution prompt including the set of function triggers (“The action manager component 312 then carries out a task utilizing an appropriate program from task related applications 322 based on an action profile if provided”, para [0028], “The action profiles 320 represent, for example, templates on how to accomplish various tasks.”, para [0028], “instances can automatically perform candidate task actions without user intervention”, para [0003]); and
a result processor configured to receive an execution result from the generative AI task execution model, the execution result being indicative of a result of executing the task, and to output the execution result for user interaction (“The selected task is then executed utilizing an action profile and a task associated application 606”, para [0040], “The user is then provided with a visualization of the executed task that includes information relating to an origin of the task 608, ending the flow 610.”, para [0041]).
Pulsipher does not disclose:
wherein the user context information comprises action patterns identifying historical behavior of the user related to the selected communication;
the task execution plan comprising chain-of-thought reasoning identifying intermediate reasoning steps for decomposing the task into executable functions
Jina discloses:
wherein the user context information comprises action patterns identifying historical behavior of the user related to the selected communication (“In some examples, the context information, such as context information corresponding to the message response history includes user location information. For example, the context information may indicate that, for the affirmative response category, a user typically responds with a specific response when in transit, such as “Talk later,” such that the suggested input “Talk later” is provided as a suggested input in response to a message received while the user is in transit. In some examples, the context information corresponding to the message response history includes a received message type. For example, the context information may indicate that, in response to receiving a media item from another user such as a picture or video, the user typically responds with a “thumbs up” emoji, such that the “thumbs up” emoji is provided as a suggested input in response to a picture or video. In some examples, the context information corresponding to the message response history includes a device type. For example, the context information may indicate that, when using a gratuitous response on a phone, the user typically enters a custom response, whereas when using a gratuitous response on a smart watch, the user typically responds with “Thanks!”, such that “Thanks!” is provided as a suggested input when using a gratuitous response on a smart watch.”, para [0251]);
Both the systems of Pulsipher and Jina deal with automated task identification. It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to combine Pulsipher in view of Jina to improve relevance and accuracy of task identification.
Khyatti discloses:
the task execution plan (i.e. “CoT chain”) comprising chain-of-thought reasoning (i.e. “step-by-step instructions”) identifying intermediate reasoning steps for decomposing the task into executable functions (“the machine learning model to create step-by-step instructions for the given task, hence producing the requested CoT chain.”, para [116], “In block 214, the series of sequential instructions of the resulting CoT chain is received from the machine learning model. The resulting CoT chain may be provided to a user via the frontend, to a task performance unit to execute the task according to the series of instructions, and/or to a storage unit. In some implementations, the user views the completed CoT and accepts or rejects the completed CoT. If the sequence of instructions are accepted, the user may activate performance of the task, such as by a task performance unit.”, para [110]);
Both the systems of Pulsipher and Khyatti deal with generating steps to execute a task. It would have been obvious to one of ordinary skill in the art before the effective filling date of the claimed invention to combine Pulsipher as modified in view of Khyatti to “optimally performs a task and facilitates a better-quality result” (Khyatti, para [05]).
With regard to claim 20, Pulsipher as modified discloses the computer system claim 19.
Pulsipher further discloses:
wherein the prompting system includes a prompt chaining processor (“a processor”, para [0014]) configured to generate chained prompts (“The tasks for scheduling a meeting can include opening up a calendar and inserting meeting titles, parties to the meeting, times of the meeting, and/or adding additional information such as, for example, a link to why the meeting was input into the calendar, etc. It can also include a task to remind the user of the meeting and/or a task to follow-up with another party to obtain additional information such as their contact information to allow completion of the meeting scheduling. Another task can include notification of others that a meeting is to take place. Thus, the candidate task component 210 determines what tasks are associated with the user's intent and provides them as the candidate tasks 206.”, para [0025], Examiner’s note: Chained prompts interpreted “a plan to perform that task (e.g., through prompt chaining, chain-of-thought prompting, etc.)”, para [00016], i.e. a set of steps to perform a task,) and a chain-of-thought processor (“a processor”, para [0014]) configured to generate a chain-of-thought prompt (“a task to remind the user of the meeting”, para [0025]).
Response to Arguments
Regarding the applicant’s requests of withdrawal of the rejection of claims 1-20 under 35 U.S.C. § 101, the amended claims recite limitations that amount to a judicial exception and do not amount to significantly more than the exception itself, and cannot integrate a judicial exception into a practical application. Applicant’s argument is addressed in the above rejections.
Applicant’s arguments with respect to claims 1-20 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Swinke (U.S. Patent Application No. US 20180144126 A1) discloses “Based on the recognized patterns, the bot may create rules or suggestions to assist the user's performance of his or her tasks. A rule may, for example, describe how to respond to a system event or message based on a recognized pattern in the user's past responses to the same or similar system events or messages. The rules or suggestions may be a function of different variables, for example, user identity, user role, location, and time, etc. The bot may include or be coupled to a notification/chatting tool, which can be used to notify the user of a proposed rule and get the user's approval (or disapproval) of the proposed rule for future implementation.” (Swinke, para [0019]).
White (U.S. Patent Application Publication No. US 10818287 B2) discloses “As another example, context data can indicate that the user is not busy; however, based on historic interaction data, it may be inferred that the user prefers to not be disturbed at a particular time (e.g., in the morning before 9:00 AM, in the afternoon between 12-2 PM, in the evening after 6 PM), at a particular location (e.g., at work, at home), or while engaged in a particular activity (e.g., driving, walking, when listening to music, while watching television),” (White, col 15, lines 6-14).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SELENA SABAH NAHRA whose telephone number is (571)272-6115. The examiner can normally be reached Monday-Thursday 7:00 AM -5:30 PM.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Hyung Sough can be reached at (571) 272-6799. 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.
/S.S.N./Examiner, Art Unit 2192 /S. Sough/SPE, Art Unit 2192
Prosecution Insights