DETAILED ACTION
This action is responsive to application filed on 06/06/2024, in which claims 1-20 are pending.
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 .
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
With respect to claim 1:
Step 1: The claim recites a series of steps and, therefore, is a process/method.
Step 2A, Prong One: The invention as claimed comprises:
A method for artifact completion using a generative artificial intelligence (AI) agent comprising: generating, by an interface and based on a guided conversation definition, a prompt, the prompt including a context, the artifact to be completed during a guided conversation, and rules to be followed in conducting the guided conversation; providing, by the interface, the prompt to the generative AI agent; receiving, by the interface and from a user interface and from a user, a response to a message from the generative AI agent; receiving, by the interface and from the generative AI agent and based on the response, a first function call to update a field of the artifact, the function call including a field and a value; determining, based on the value and a schema of the artifact, a result indicating whether the update is valid or invalid; providing, to the generative AI agent, the result; and receiving, from the generative AI agent, the artifact after the artifact is completed.
The above step, as drafted, is a process that under its broadest reasonable interpretation covers Certain Methods Of Organizing Human Activity managing personal behavior or relationships or interactions between people (including social activities, teaching, and following rules or instructions).
The claim presents activity of completing form/artifact via the conversation guidance; it further fills the form and validates the form fields (which could also be grouped under mental process of filling forms using paper and pen). The distinction being the concept is being implement using generative AI. The claims are not presenting any technical details, and merely applying generative AI, and automation to execute the abstract idea.
Step 2A Prong Two: The claim recites additional element of such as generative artificial intelligence (AI) agent, prompting, interface, function call etc.….
The additional elements are no more than mere instructions to apply the exception using a generic computer component (computer), in instant case merely generative AI is being used to complete the form via guided conversation; in other words, the abstract idea of filling a form, and guiding one to how to fill the form, is being accomplished using generative AI, and prompting. Accordingly, the additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Step 2B: As discussed with respect to Step 2A Prong Two, the additional elements in the claim amount to no more than mere instructions to apply the exception using a generic computer component.
The same conclusion is reached in 2B, i.e., mere instructions to apply an exception on a generic computer cannot integrate a judicial exception into a practical application at Step 2A or provide an inventive concept in Step 2B.
Claims 10, and 16 present interface and machine-readable medium claims corresponding to claim 1, and are rejected under same rational. In addition, claims 10, and 16 further recite additional limitations of machine-readable medium.
Step 2A Prong Two: The additional elements are no more than mere instructions to apply the exception using a generic computer component (computer). Accordingly, the additional elements alone or in combination do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Step 2B: As discussed with respect to Step 2A Prong Two, the additional elements in the claim amount to no more than mere instructions to apply the exception using a generic computer component.
The same conclusion is reached in 2B, i.e., mere instructions to apply an exception on a generic computer cannot integrate a judicial exception into a practical application at Step 2A or provide an inventive concept in Step 2B.
Claims 2-9, 11-15, and 17-20, further narrow the recited abstract idea above, and are rejected under same rational as claim 1. Note, limitations such as limit to a length (one can select the threshold), and indicating length that have been consumed (one can calculate the iterations, and indicate) is further narrowing the abstract idea. Furthermore, the state transition, rules, constrains, etc.… all falls with organizing human activity, and could also fall under mental process as all of this can be defined using paper, and pen.
Regarding claims 10-15, the claims don’t pass step 1, and are further rejected under software per se. The only potential structure in claim 1is interface, however under broadest reasonable interpretation in light of specification, the interface can be interpreted as software, especially in instant claim, the interface is between AI agent, and user interface. Claims 11-15 don’t introduce any structure either.
Regarding claims 16-20, claim 16 recites machine-readable medium, which under the broadest reasonable interpretation could be interpreted as transit medium. Instant specification, para 0072 discusses the machine-readable medium, however it doesn’t explicitly limit the medium to be non-transitory, or excluding the signal per se.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-2, 4-5, 8, 10-11, 13-14, 16, and 19 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by NAHUM et al. (US 20240403545 A1)
With respect to claim 1:
Nahum teaches:
A method for artifact completion using a generative artificial intelligence (AI) agent comprising (See, abstract, Fig. 4): generating, by an interface and based on a guided conversation definition, a prompt, the prompt including a context, the artifact to be completed during a guided conversation, and rules to be followed in conducting the guided conversation (Fig. 1A teaches obtaining prompt (para 0067 input being prompt), Fig. 1A, teaches getting user context, selecting target form (artifact); para 0040 for providing guidance by AI.); providing, by the interface, the prompt to the generative AI agent (See, para 0076-0077); receiving, by the interface and from a user interface and from a user, a response to a message from the generative AI agent (Para 0024 teaches …“prompting the user to provide the user input, the user input is a second natural language input that is provided via the user interface…” Para 040 teaches “[0040] Another technical problem may be to enhance and facilitate these digital tasks and form filing by utilizing AI algorithms to provide guidance, context-aware prompts, personalized assistance, and improve the overall user experience. It may be desired to provide users with a robust, yet simple, natural-language-based interface in which the user interacts with the interface and the interface identifies the relevant form in the digital systems utilized by the organization of the user that is relevant to the user's intent, and to enable automated filling of the relevant form.”); receiving, by the interface and from the generative AI agent and based on the response, a first function call to update a field of the artifact, the function call including a field and a value (Para 0087 teaches “….In some cases, the prompt may indicate current values of fields of the target form, indication of mandatory fields with undetermined values, indication of wrong values, or the like. In some exemplary embodiments, the user input may comprise an update instruction to a field in the target form, a change of an initial value to an updated value, or the like. Additionally, or alternatively, the user input may comprise an additional value of a field in the target form or an instruction to set a value to a field in the target-form that does not have a previous set value. Also see para 0120 etc.…); determining, based on the value and a schema of the artifact, a result indicating whether the update is valid or invalid (Para 0146 teaches “In some cases, validation checks to the form may be performed before processing the form, the system may perform validation checks to ensure that the provided information is valid and complete. The system may be configured to verify if required fields are filled, validate email addresses or phone numbers, enforce specific data formats, or the like….”.”); providing, to the generative AI agent, the result (See, para 0058, claim 18, etc.…); and receiving, from the generative AI agent, the artifact after the artifact is completed (See, para 0120, 0058, 0078, etc.…).
With respect to claim 10:
Nahum teaches:
An interface between a generative artificial intelligence (AI) agent and a user interface (UI), the interface configured to (See, abstract, Fig. 4): provide a prompt to the generative AI agent, the prompt including a context, an artifact to be completed during a guided conversation, and rules to be followed in conducting the guided conversation (Fig. 1A teaches obtaining prompt (para 0067 input being prompt), Fig. 1A, teaches getting user context, selecting target form (artifact); para 0040 for providing guidance by AI.); receive a message from the generative AI agent (See, para 0172); reformat and provide the message on the UI to a user (Para 0069 teaches “ Additionally, or alternatively, other types of input may be obtained using other types of conversational interfaces, such as visual input, vocal input, or the like. Such input may be converted to a textual format to enable processing thereof. As an example, the conversation interface may be a smart assistance, such as Siri™, Google™ assistant, or the like, in which user input is provided using voice.”); receive, from the user and by the UI, a response to the message (See, para 0172, Fig. 2; also see para 0024); reformat and provide the response to the generative AI agent (see, para 0069; note different type of inputs can be received and converted; also note, this is taking places as a guided conversation, thus multiple iterations of receiving messages between user and agent; se Fig, 2); receive, from the generative AI agent and based on the response, a first function call to update a field of the artifact, the function call including a field and a value (Para 0087 teaches “….In some cases, the prompt may indicate current values of fields of the target form, indication of mandatory fields with undetermined values, indication of wrong values, or the like. In some exemplary embodiments, the user input may comprise an update instruction to a field in the target form, a change of an initial value to an updated value, or the like. Additionally, or alternatively, the user input may comprise an additional value of a field in the target form or an instruction to set a value to a field in the target-form that does not have a previous set value. Also see para 0120 etc.…); call a function associated with the first function call based on the first function call, the value, and a schema of the artifact (See, para 0146); receive, from the function, a result indicating whether the update is valid or invalid (Para 0146 teaches “In some cases, validation checks to the form may be performed before processing the form, the system may perform validation checks to ensure that the provided information is valid and complete. The system may be configured to verify if required fields are filled, validate email addresses or phone numbers, enforce specific data formats, or the like….”.”); provide, to the generative AI agent, the result (See, para 0058, claim 18, etc.…); and receive, from the generative AI agent, the artifact after it is completed (See, para 0120, 0058, 0078, etc.…).
With respect to claim 16:
Nahum teaches:
A machine-readable medium including instructions stored thereon that, when executed by a machine, cause the machine to perform operations for supervising a guided conversation with a goal of completing an artifact, the operations comprising (See, abstract, Fig. 4): providing a prompt to a generative artificial intelligence (AI) agent, the prompt including a context, the artifact to be completed during a guided conversation, and rules to be followed in conducting the guided conversation (Fig. 1A teaches obtaining prompt (para 0067 input being prompt), Fig. 1A, teaches getting user context, selecting target form (artifact); para 0040 for providing guidance by AI.); providing, by a user, a response to a message from the generative AI agent (See, para 0076-0077); receiving, from the generative AI agent and based on the response, a first function call to update a field of the artifact, the function call including a field and a value (Para 0087 teaches “….In some cases, the prompt may indicate current values of fields of the target form, indication of mandatory fields with undetermined values, indication of wrong values, or the like. In some exemplary embodiments, the user input may comprise an update instruction to a field in the target form, a change of an initial value to an updated value, or the like. Additionally, or alternatively, the user input may comprise an additional value of a field in the target form or an instruction to set a value to a field in the target-form that does not have a previous set value. Also see para 0120 etc.…); determining, based on the value and a schema of the artifact, a result indicating whether the update is valid or invalid (Para 0146 teaches “In some cases, validation checks to the form may be performed before processing the form, the system may perform validation checks to ensure that the provided information is valid and complete. The system may be configured to verify if required fields are filled, validate email addresses or phone numbers, enforce specific data formats, or the like….”.”); providing, to the generative AI agent, the result (See, para 0058, claim 18, etc.…); and receiving, from the generative AI agent, the artifact after it is completed (See, para 0120, 0058, 0078, etc.…).
With respect to claims 2, and 11:
Nahum teaches the method of claim 1, and the interface of claim 10; and Nahum further teaches wherein the schema includes fields with respective field names, general descriptions of data to be populated in the fields, and a type of data to populate the fields (Para 0082 teaches “…The form description may comprise properties of the form, such as names of fields of the form, types of values to be filled, fill requirements, categorical fields, mandatory fields, or the like…”))
With respect to claims 4, and 13:
Nahum teaches the method of claim 1, and the interface of claim 10; and Nahum further teaches wherein the context specifies, in natural language, that the guided conversation is for the generative AI agent to fill in all fields of the artifact (Para 0040 teaches “Another technical problem may be to enhance and facilitate these digital tasks and form filing by utilizing AI algorithms to provide guidance, context-aware prompts, personalized assistance, and improve the overall user experience. It may be desired to provide users with a robust, yet simple, natural-language-based interface in which the user interacts with the interface and the interface identifies the relevant form in the digital systems utilized by the organization of the user that is relevant to the user's intent, and to enable automated filling of the relevant form.”)
With respect to claims 5, and 14:
Nahum teaches the method of claim 1, and the interface of claim 10; and Nahum further teaches wherein the rules define constraints on operations to be performed by the agent in conducting the guided conversation and how the agent is to respond in certain situations (Para 0104 teaches “….to configure the automation process, by defining rules, conditions, and triggers for when the automation should run, and set access permissions indicating which users can utilize the automation.” Para 0106 teaches “In some exemplary embodiments, the automation process may be set up to automatically fill in values in the target form as per the configured rules and conditions. When certain conditions are met, the DAP platform may be configured to execute the automation to replicate the recorded steps and populate the form. The DAP platform may further be configured to provide real-time guidance to users, making it easier for them to understand and utilize the automated process. Users may receive on-screen prompts or instructions when interacting with the form….”)
With respect to claims 8, and 19:
Nahum teaches the method of claim 1, and the machine-readable medium of claim 16.
Nahum further teaches wherein the prompt further includes a conversation flow specified in natural language that defines steps to be taken by the generative AI agent in completing the artifact (Para 0104 teaches “In some exemplary embodiments, the automation process may be configured to fill in values in the target form in the third-party digital system using a DAP platform. The DAP platform may be configured to create a step-by-step workflow of filling-in the form….”)
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 3 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over NAHUM et al. in view of Zhu et al. (US 20240403545 A1)
With respect to claims 3, and 12:
Nahum teaches the method of claim 2, and the interface of claim 11; and Nahum further teaches wherein: the schema further includes a format of data that is to populate the field (Para 0178 teaches format), and the schema result indicates that the update was invalid because the value does not fit the format (See, para 0058; it does not explicitly teach that invalid is format (it could be nay thing, including value)) and the method further comprises providing options to the generative AI agent including (i) messaging the user (Para 0058 teaches messaging user when field value is invalid) and (ii) reformatting the value and retrying the function call (Para 0028 teaches asking the user for value, and trying again; however, it does not explicitly teaches reformatting.).
Nahum doesn’t explicitly teach invalidity due to format, and reformatting the value.
Zhu teaches reformatting the value if the format is not correct (Para 0091, “analyzer 208 can determine that a format for a data point or value is incorrect or inconsistent, and then reformat the data point. The consumption analyzer 208 can determine to update, correct or otherwise modify the values in the consumption data 226 data structure, or determine to create a new entry in the data repository 224 for the modified consumption data so as to maintain the raw consumption data.”)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention (AIA ) to incorporate reformatting as disclosed by Zhu into the teachings of Nahum in order to perform data error correction. (See, para 0091)
Claims 6-7, 15, and 17-18 are rejected under 35 U.S.C. 103 as being unpatentable over NAHUM et al. in view of Wang et al. (US 20250094866 A1)
With respect to claims 6, 15, and 17:
Nahum teaches the method of claim 1, the interface of claim 10, and the machine-readable medium of claim 16; and Nahum further teaches guided conversation (para 0076).
Nahum does not explicitly teach wherein the prompt further includes a resource constraint that defines a limit to a length of the guided conversation.
Wang teaches wherein the prompt further includes a resource constraint that defines a limit to a length of the guided conversation (Para 0044 teaches “…attempt checker 150 determines whether a threshold number of attempts have been made to improve the accuracy of assertions within the output generated by LLM 110. The threshold number of attempts may be a value assigned by an entity to limit the usage of LLM 110.” Para 0045 teaches “In an embodiment, the value is based on a size of the textual content. For example, a paragraph of text (e.g., 3-6 sentences) may be assigned a relatively high threshold number. Multiple paragraphs of text (e.g., 7+ sentences) may be assigned a relatively low threshold number to prevent excessive use of computing resources….” Note: here number is being assigned based on resources, and number of prompt iteration is being equated to length of conversation/interactions to refine the output.)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention (AIA ) to incorporate threshold length/attempts as disclosed by Wang into the teachings of Nahum in order to determine if LLM is not performing well for particular artifact. (See, para 0046; basically, if the artifact can’t be completed with threshold number of guidance prompts, then model is not performing well in the specific domain.)
With respect to claims 7, and 18:
Nahum teaches the method of claim 6, and the machine-readable medium of claim 17.
Wang further teaches further comprising receiving, from the generative AI agent, a second function call to update a field of an agenda to reflect how much of the length has been consumed (Para 0050 teaches “In an embodiment, new prompt generator 160 includes, in the new prompt, a prompt identifier (which may be extracted from the output generated by LLM 110) and increments a value (in the output) that indicates a number of times that the initial prompt and/or subsequent prompts based on that initial prompt have been processed by LLM 110.” Note: Nahum reference already teaches populating form/agenda fields with value, Wang teaches determining the length of chat (count of subsequent prompts), thus form field of Nahum can be updated with determined value for subsequent prompts.)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention (AIA ) to incorporate threshold length/attempts as disclosed by Wang into the teachings of Nahum in order to determine if LLM is not performing well for particular artifact. (See, para 0046; basically, if the artifact can’t be completed with threshold number of guidance prompts, then model is not performing well in the specific domain.)
Claims 9 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over NAHUM et al. in view of McCarthy et al. (US 20250259086 A1)
With respect to claims 9, and 20:
Nahum teaches the method of claim 1, and the machine-readable medium of claim 16.
Nahum doesn’t explicitly teaches wherein the prompt further includes a conversation flow specified as a state machine that indicates a current state of the generative AI agent, states to which the generative AI agent can transition, conditions to be satisfied in deciding whether and to which state to transition, and operations to be performed in the states including the current state.
McCarthy teaches wherein the prompt further includes a conversation flow specified as a state machine that indicates a current state of the generative AI agent, states to which the generative AI agent can transition, conditions to be satisfied in deciding whether and to which state to transition, and operations to be performed in the states including the current state (Para 0061 teaches “Instructions 614 can indicate what the machine learning model (e.g., a large language model) is supposed to do with the other content provided in the prompt. For example, the machine learning model instructions may request, via instructions 614, an LLM to select the most relevant instructions from content 616 to train or guide a customer service representative having a specified role 612, determine if a predicted response was generated with each instruction followed correctly, determine what function to execute, determine whether or not to transition to a new state within a state machine, and so forth. The instructions can be retrieved or accessed from vector database 450, data store 460, a combination of these sources, as well as other sources.” Also see para 0062, 0075, etc.…)
It would have been obvious to a person of ordinary skill in the art before the effective filing date of the claimed invention (AIA ) to incorporate flow control as disclosed by Wang into the teachings of Nahum in order to provide flow control. (Para 0035)
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 20250245483 A1: “Systems and methods are described for training a large language model to operate as a completeness graph generator to automatically generate completeness graphs in response to queries based on instructions including forms, rules, and regulations. A dataset is obtained that includes instructions and associated ground truth completeness graphs, previously generated manually by domain experts. An active large language model is trained configured to produce a generated completeness graph in response to a query that is evaluated with a reward model based on validity of the generated completeness graph and semantic similarity of the generated completeness graph and the associated ground truth completeness graph. The active large language model is re-trained based at least partially on the reward.” (See, Abstract)
Any inquiry concerning this communication or earlier communications from the examiner should be directed to WASEEM ASHRAF whose telephone number is (571)270-3948. The examiner can normally be reached Monday-Friday 09:30 A.M-06:00 P.M.
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, Tariq Hafiz can be reached at 571-272-5350. 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.
/WASEEM ASHRAF/Supervisory Patent Examiner, Art Unit 3621
Prosecution Insights