Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statements (IDSs) submitted on 10/10/2024 and 04/02/2025 were filed in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to and abstract idea without significantly more. Independent claims 1, 19, and 20 relate to the statutory category of method/process and machine/apparatus. The independent claims recites “…receiving, by a server and from a user device, a natural-language text prompt provided by the user to a chat application operating on the user device; receiving, by the server and from the user device, at least one user preference for a user, the at least one user preference indicative of at least one preferred characteristic of natural-language outputs generated by a machine-learning language model based on user-provided natural-language text inputs; modifying, by the server, a system prompt for the machine-learning language model with the received at least one user preference to generate a modified system prompt; providing, by the server, the modified system prompt as an initial input to the machine-learning language model; providing, by the server and after providing the modified system prompt, the natural-language text prompt as an input to the machine-learning language model to generate a natural-language text output; transmitting, by the server, the natural-language text output to the user device; and causing, by the user device, the chat application to communicate the natural-language text output to the user”.
With respect to claim 19, the claim recites “…receiving, by a remote device and from a user device, a first natural-language text prompt provided by the user to a chat application operating on the user device; receiving, by the remote device and from the user device, at least one user preference for a user, the at least one user preference indicative of at least one preferred characteristic of natural-language outputs generated by a machine-learning language model based on user-provided natural-language text inputs; modifying, by the remote device, a system prompt for the machine-learning language model with the received at least one user preference to generate a first modified system prompt; providing, by the remote device, the first modified system prompt as an initial input to the machine-learning language model; providing, by the remote device and after providing the first modified system prompt, the first natural-language text prompt as an input to the machine-learning language model to generate a first natural-language text output; transmitting, by the remote device, the first natural-language text output to the user device; causing, by the user device, the chat application to communicate the first natural-language text output to the user; updating, after causing the chat application to communicate the first natural-language output, the at least one user preference based on at least one input received by a user interface of the user device to generate at least one updated user preference; receiving, by the remote device and from the user device, a second natural-language text prompt provided by the user to a chat application operating on the user device; receiving, by the remote device and from the user device, the at least updated one user preference for a user; modifying, by the remote device, the first modified system prompt with the received at least updated one user preference to generate a second modified system prompt; providing, by the remote device, the second modified system prompt as an initial input to the machine-learning language model; providing, by the remote device and after providing the second modified system prompt, the second natural-language text prompt as an input to the machine-learning language model to generate a second natural-language text output; transmitting, by the remote device, the second natural-language text output to the user device; and causing, by the user device, the chat application to communicate the second natural-language text output to the use”.
With respect to claim 20, the claim recites “…a user device comprising: a first processor; and at least one first memory storing at least one user preference indicative of at least one preferred characteristic of natural-language outputs generated by a machine-learning language model based on user-provided natural-language text inputs, the at least one first memory encoded with first instructions that, when executed, cause the first processor to: receive at least one input indicative of a natural-language text string; and provide the natural-language text string as a natural-language text prompt to a chat application operating on the user device; and a remote device communicatively connected to the user device, the remote device comprising: a second processor; and at least one second memory encoded with second instructions that, when executed, cause the second processor to: receive the natural language text prompt from the user device; receive the at least one user preference from the user device; modify a system prompt for the machine-learning language model based on the at least one user preference; provide the system prompt as an initial input to the machine-learning language model; provide, subsequent to providing the system prompt, the natural-language text prompt as an input to the machine-learning language model to generate a natural-language text output; and transmit the natural-language text output to the user device”.
The limitations of claim 1 of “receiving…”, “receiving…”, “modifying…”, “providing…”, “providing…”, “transmitting…”, and “causing…” as drafted covers mental activity. More specifically, a human given a textual prompt during a conversation can modify the prompt based on their preference and use the modified prompt as the new prompt that requires a response. Feedback is then received in response the modified prompt in text format.
The limitations of claim 19 of “receiving…”, “receiving…”, “modifying…”, “providing…”, “providing…”, “transmitting…”, “causing…”. “updating,,,”, “receiving…”, “receiving…”, “modifying…”, “providing…”, “providing…”, “transmitting…”, and “causing…” as drafted covers mental activity. More specifically, a human given a textual prompt during a conversation can modify the prompt based on their preference and use the modified prompt as the new prompt that requires a response. Feedback is then received in response the modified prompt in text format. The preference is updated and the updated preference is then used to modify the originally modified prompt to create a second modified prompt. Feedback is then received in response to the second modified response.
The limitations of claim 20 of “…receive…”, “provide…”, “…receive”, “receive”, “modify…”, “provide…”, “provide…”, and “transmit…” as drafted covers mental activity. More specifically, a human given a textual prompt during a conversation can modify the prompt based on their preference and use the modified prompt as the new prompt that requires a response. Feedback is then received in response the modified prompt in text format.
This judicial exception is not integrated into a practical application. In particular claim 20 recites the additional elements of “user device”, “remote device”, processor”, and “memory” which are recited generally in the specification. For example, in paragraphs [0014]-[0016] of the as filed specification. there is a description of using a general purpose operating system. Claims 1, 19, and 20 recite the additional limitation of “machine-learning language model” which is recited generally in the specification. For example, in paragraph [0015\ of the as filed specification, there is a description of using a general purpose operating system which uses a machine-learning language model. However, the claims fail to disclose how the language model is specifically trained and how it is specifically used to generate the responses. Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are directed to an abstract idea.
The claims does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to the integration of the abstract idea into a practical application, the additional element of using a computer as a general computer is noted. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The claims are not patent eligible.
With respect to claim 2, the claim relates to encoding and storing the user preference. The claim relates to a mental activity of embedding the user preference in a table or list that can be accessed and retrieved. No additional limitations are present.
With respect to claim 3, the claim relates to encoding the user preference by tokenizing the preference by using an algorithm and storing the tokenized preference. The claim relates a mental activity of encoding the user preference by using a formula to creating a word or phrase to define the preference. This word or phrase is stored in a list or table that can be accessed to retrieve the user preference. No additional limitations are present.
With respect to claim 4, the claim relates to generating the token when user input is received and storing the token. The token is retrieved after a period of inactivity between user prompts. The claim relates to a mental activity of retrieving a user preference if no new prompts have recently been received. No additional limitations are present.
With respect to claim 5, the claim relates to updating the user preference based on user input. The claim relates to a mental activity of changing the user preference based on what is input by the user. No additional limitations are present.
With respect to claim 6, the claim relates to receiving a prompt based on user input and modifying the prompt based on the user preference and then transmitting the modified prompt. The claim relates to a mental activity of modifying the prompt based on user preference before it is sent. No additional limitations are present.
With respect to claim 7, the claim relates to requesting the user preference when the prompt is received. The claim relates to asking for the user preference upon receipt of the prompt. No additional limitations are present.
With respect to claims 8 and 9, the claim relates to having a conversation and detecting the user is part of the conversation and the user preference and requesting to modify the prompt based on the user preference. The claim relates to a mental activity of if the user is part of the conversation taking place, modifying the prompt based on the user preference. No additional limitations are present.
With respect to claims 10-12, the claims relate to sending a first request to modify the prompt and sending a second request to generate a textual output based on the textual prompt. The claim relates to a mental activity of modifying the prompt and providing textual feedback to the original textual prompt. No additional limitations are present.
With respect to claim 13, the claim relates to the user preference being a membership, a subscription, a preferred vendor, a preferred advertisement, and a particular data source for content. The claim relates to a mental activity of having particular sources as preferences. No additional limitations are present.
With respect to claim 14-16, the claims relate to displaying a list for managing the user preferences, getting input for generating the user preferences, and storing the selected user preferences. The claims relate to a mental activity of determining, generating, and storing the user preferences. No additional limitations are present.
With respect to claims 17 and 18, the claims relate to receiving input which describes one or more words corresponding to user preference and wherein receiving the user preferences comprises the one or more words. The claims relate to a mental activity of using words that describe the user preference and vice versa. No additional limitations are present.
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.
Claims 1-3, 5-13, 17-18, and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Amershi et al. (US 2024/0386038) in view of Bailey et al (US 2025/0068881).
Regarding Claim 1, Amershi et al teaches a method of automated pre-prompt generation based on user preferences, the method comprising:
receiving, by the server and from the user device, at least one user preference for a user, the at least one user preference indicative of at least one preferred characteristic of natural-language outputs (At operation 208, the AI guidance system 140 determines if one or more embedded attributes are associated with the one or more applications, documents, interfaces, and/or contents. If the AI guidance system 140 determines that the one or more embedded attributes exist at operation 210, the method 200 advances to operation 212 ) (page 3, paragraph [0035]) generated by a machine-learning language model based on user-provided natural-language text inputs (With reference first to FIG. 4A, conceptual diagram 400 depicts an overview of pre-trained generative model package 404 that processes an input 402 to generate model output for storing entries in and/or retrieving information from a generative model output 406 (e.g., suggestions and/or suggested modifications) according to aspects described herein) (page 4, paragraph [0044]);
modifying, by the server, a system prompt for the machine-learning language model with the received at least one user preference to generate a modified system prompt (At operation 212, the AI guidance system 140 generates a new supplemental prompt and/or modifies the input prompt based on the one or more attributes) (page 3, paragraph [0036]);
providing, by the server, the modified system prompt as an initial input to the machine-learning language model (Additionally, or alternatively, the AI guidance system may modify the input prompt based on the embedded attribute and provide the modified input prompt to the LLM AI) (page 4, paragraph [0039]);
providing, by the server and after providing the modified system prompt, the natural-language text prompt as an input to the machine-learning language model to generate a natural-language text output (Additionally, or alternatively, the AI guidance system may modify the input prompt based on the embedded attribute and provide the modified input prompt to the LLM AI) (page 4, paragraph [0039]);
transmitting, by the server, the natural-language text output to the user device (At operation 214, the AI guidance system 140 provides one or more prompts to the one or more generative AI systems. The one or more prompts may include a new supplemental prompt, a modified prompt, and/or the original input prompt) (page 3, paragraph [0037]);
Amershi et al. fails to teach receiving, by a server and from a user device, a natural-language text prompt provided by the user to a chat application operating on the user device; and causing, by the user device, the chat application to communicate the natural-language text output to the user.
Bailey et al. teaches receiving, by a server and from a user device, a natural-language text prompt provided by the user to a chat application operating on the user device (In step 201, the computer system or server receives a chatbot prompt form a user) (page 4, paragraph [0029]); and
causing, by the user device, the chat application to communicate the natural-language text output to the user (In step 209, the computer system or server generates a response to the chatbot prompt, based on the modified chatbot prompt (provided in step 207) and datasets (identified in step 208)) (page 5, paragraph [0037).
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Amershi with the teachings of Bailey to improve the communication quality by modifying the input prompts based on the user’s preferences and by providing responses geared towards the users preferences.
Regarding Claim 2, Amershi et al. teaches the method, further comprising encoding, before receiving the at least one user preference (At operation 208, the AI guidance system 140 determines if one or more embedded attributes are associated with the one or more applications, documents, interfaces, and/or contents) (page 3, paragraph [0035]), the at least one user preference to at least one memory of the user device based on at least one input received by a user interface of the user device ( the AI guidance system 140 may be executed on the AI platform server 150 and/or the computing device 120) (page 2, paragraph [0025]), wherein receiving the at least one preference comprises retrieving the at one preference from the at least one memory (The computing device 120 has a processor 122, a memory 124, and a communication interface 126) (page 2, paragraph [0024]).
Regarding Claim 3, Amershi et al. teaches the method, wherein: encoding the at least one user preference to the at least one memory comprises:
generating at least one token representative of the at least one user preference using a tokenizer algorithm configured to generate input tokens usable by the machine-learning language model (generative model package 404 includes input tokenization 408, input embedding 410, model layers 412, output layer 414, and output decoding 416. In examples, input tokenization 408 processes input 402 to generate input embedding 410, which includes a sequence of symbol representations that corresponds to input 402. Accordingly, input embedding 410 is processed by model layers 412, output layer 414, and output decoding 416 to produce model output 406) (page 5, paragraph [0048]); and
storing the at least one token to the at least one memory, and retrieving the at least one user preference comprises retrieving the at least one token (With reference first to FIG. 4A, conceptual diagram 400 depicts an overview of pre-trained generative model package 404 that processes an input 402 to generate model output for storing entries in and/or retrieving information from a generative model output 406) (page 4, paragraph [0044]).
Regarding Claim 5, Amershi et al. teaches the method, further comprising updating the at least one user preference, before receiving the at least one user preference, based on at least one additional input received by the user interface of the user device (The method may include obtaining an input prompt associated with a requested task for one or more generative AI systems, obtaining one or more attributes based on the input prompt, modifying the input prompt based on the one or more embedded attributes) (page 9, paragraph [0096]).
Regarding Claim 6, Amershi et al. fails to teach the method, further comprising: receiving, by the chat application, the natural-language text prompt based on at least one input at the user device; upon receiving the natural-language text prompt, causing, by the chat application, the user device to transmit the at least one user preference to the server and a command to the server to modify the system prompt based on the at least one user preference; and upon transmitting the at least one user preference to the server, causing, by the chat application, the user device to transmit the natural-language text prompt to the server.
Bailey et al teaches the method, further comprising:
receiving, by the chat application, the natural-language text prompt based on at least one input at the user device (n step 201, the computer system or server receives a chatbot prompt form a use) (page 4, paragraph [0029]);
upon receiving the natural-language text prompt, causing, by the chat application, the user device to transmit the at least one user preference to the server ( In step 206, the computer system or server identifies an intent of the chatbot prompt, by using natural language processing to disambiguate the chatbot prompt. In this step, the computer system or server determines what the user's specific need is in the user's chatbot prompt) (page 4, paragraph 034]) and a command to the server to modify the system prompt based on the at least one user preference (In step 207, the computer system or server improves quality of the chatbot prompt and provides a modified chatbot prompt, according to the context and the intent) (page 4, paragraph [0035]; and
upon transmitting the at least one user preference to the server, causing, by the chat application, the user device to transmit the natural-language text prompt to the server (In step 207, the computer system or server improves quality of the chatbot prompt and provides a modified chatbot prompt, according to the context and the intent. In this step, the computer system or server provides a context-aware prompt that is more specific to the context the user's intent) (page 4, paragraph [0035]).
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Amershi with the teachings of Bailey to improve the communication quality by modifying the input prompts based on the user’s preferences and by providing responses geared towards the users preferences.
Regarding Claim 7, Amershi et al. fails to teach the method, further comprising requesting, by the server, the at least one user preference from the user device upon receiving the natural-language text prompt.
Bailey et al. teaches the method, further comprising requesting, by the server, the at least one user preference from the user device upon receiving the natural-language text prompt (In step 206, the computer system or server identifies an intent of the chatbot prompt, by using natural language processing to disambiguate the chatbot prompt. In this step, the computer system or server determines what the user's specific need is in the user's chatbot prompt) (page 4, paragraph [0034]).
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Amershi with the teachings of Bailey to improve the communication quality by modifying the input prompts based on the user’s preferences and by providing responses geared towards the users preferences.
Regarding Claim 8, Amershi et al. fails to teach the method, further comprising: causing the user device to begin operating the chat application; detecting, by a preference management application operating on the user device, that the user device is operating the chat application, the preference management application configured to manage the at least one user preference; and causing, by the preference management application, the user device to transmit to the server, upon detecting that the user device is operating the chat application: the at least one user preference; and a command to modify the system prompt based on the at least one user preference.
Bailey et al. teaches the method, further comprising:
causing the user device to begin operating the chat application (In step 201, the computer system or server receives a chatbot prompt form a user) (page 4, paragraph [0029]);
detecting, by a preference management application operating on the user device, that the user device is operating the chat application, the preference management application configured to manage the at least one user preference (In step 204, the computer system or server identifies context of the chatbot prompt, by analyzing the pre-processed data. Through the analysis of the pre-processed data, the computer system or server detects context of user's communication and topics of user's request in the chatbot prompt) page 4, paragraph [0032]); and
causing, by the preference management application, the user device to transmit to the server, upon detecting that the user device is operating the chat application: the at least one user preference (In step 206, the computer system or server identifies an intent of the chatbot prompt, by using natural language processing to disambiguate the chatbot prompt. In this step, the computer system or server determines what the user's specific need is in the user's chatbot prompt) (page 4, paragraph [0034]); and
a command to modify the system prompt based on the at least one user preference (In step 207, the computer system or server improves quality of the chatbot prompt and provides a modified chatbot prompt, according to the context and the intent) (page 4, paragraph [0035]).
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Amershi with the teachings of Bailey to improve the communication quality by modifying the input prompts based on the user’s preferences and by providing responses geared towards the users preferences.
Regarding Claim 9, Amershi et al. teaches the method, wherein the command is configured to invoke one or more functions of an application programming interface operated by the server to cause the server to modify the system prompt (In other words, the behaviors of generative AI systems may be customized or directed by users (e.g., developers and/or authors) at a finer level (e.g., by enabling different prompt augmentations on any document or user interface element) using embedded attributes) (page 2, paragraph [0022]).
Regarding Claim 10, Amershi et al. teaches the method, wherein the machine-learning language model is operated by a language server connected to the server by a wide area network (The network 170 may include any kind of computing network including, without limitation, a wired or wireless local area network (LAN), a wired or wireless wide area network (WAN), and/or the Internet) (page 2, paragraph [0023]), and wherein:
modifying the system prompt comprises transmitting, by the server, a first request to the language server including a first command to modify the system prompt (For example, the AI guidance system 140 may be any tool that is capable of generating a new prompt or modifying an existing prompt and is communicatively coupled to a computing device providing an input prompt (e.g., the computing device 120) and one or more generative systems 160) (page 3, paragraph [0032]); and
providing the natural-language text prompt as an input to the machine-learning language model comprises transmitting a second request to the language server including a second command to generate the natural-language text output based on the natural-language text prompt (The input prompt is an input or a query that a user or a program provides to the one or more generative AI systems 160 in order to elicit a requested output or response from the one or more generative AI systems) (page 3, paragraph [0033]).
Regarding Claim 11, Amershi et al. teaches the method, wherein the first command invokes at least one first function of an application programming interface operated by the language server to cause the language server to modify the system prompt, and the second command invokes at least one second function of the application programming interface to cause the server to generate the natural-language text output (In other words, the behaviors of generative AI systems may be customized or directed by users (e.g., developers and/or authors) at a finer level (e.g., by enabling different prompt augmentations on any document or user interface element) using embedded attributes) (page 2, paragraph [0022]).
Regarding Claim 12, Amershi et al. teaches the method, wherein:
modifying the system prompt comprises receiving, by the server, a command from the user device to modify the system prompt (For example, the AI guidance system 140 may be any tool that is capable of generating a new prompt or modifying an existing prompt and is communicatively coupled to a computing device providing an input prompt (e.g., the computing device 120) and one or more generative systems 160) (page 3, paragraph [0032]); and
transmitting, by the server, the request to the language server comprises transmitting the request in response to the command from the user device (The input prompt is an input or a query that a user or a program provides to the one or more generative AI systems 160 in order to elicit a requested output or response from the one or more generative AI systems) (page 3, paragraph [0033]).
Regarding Claim 13, Amershi et al. fails to teach the method, wherein the at least one user preference is at least one of a membership, a subscription, a preferred vendor, an advertisement preference, and a data source for context injection.
Bailey et al. teaches the method, wherein the at least one user preference is at least one of a membership, a subscription, a preferred vendor, an advertisement preference, and a data source for context injection (In step 202, the computer system or server collects data from various sources, including video conferencing services, instant messages, and email messages. To detect context of user's communication and topics of user's request in the chatbot prompt, the computer system or server will use the collected data from the various sources) (page 4, paragraph [0029]).
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Amershi with the teachings of Bailey to improve the communication quality by collecting data from various sources that is geared towards the users preferences.
Regarding Claim 17, Amershi et al. fails to teach the method, further comprising receiving, by the user device, at least one input from an input device electronically connected to the user device, the at least one input describing one or more natural-language words corresponding to the at least one user preference, and wherein receiving the at least one user preference comprises receiving an indication of the one or more natural-language words.
Bailey et al. teaches the method, further comprising receiving, by the user device, at least one input from an input device electronically connected to the user device, the at least one input describing one or more natural-language words corresponding to the at least one user preference, and wherein receiving the at least one user preference comprises receiving an indication of the one or more natural-language words (The system proposed in the present invention expands the user's prompt to “What's the best way to optimize performance for CICS Transaction Server running on IBM z/OS v 2.5?”) (page 5, paragraph [0039]).
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Amershi with the teachings of Bailey to improve the communication quality by modifying the input prompts based on the user’s preferences and by providing responses geared towards the users preferences.
Regarding Claim 18, Amershi et al. fails to teach the method, further comprising removing at least one filler word from the one or more natural-language words prior to receiving the indication of the one or more natural-language words.
Bailey et al. teaches the method, further comprising removing at least one filler word from the one or more natural-language words prior to receiving the indication of the one or more natural-language words (The computer system or server applies the stop word removal technique to remove words that are not relevant to the context) (page 4, paragraph [0031]).
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Amershi with the teachings of Bailey to improve the communication quality by modifying the input prompts based on the user’s preferences and by providing responses geared towards the users preferences.
Regarding Claim 20, Amershi et al. teaches a system for language generation, the system comprising:
a user device (computing device 120) (page 2, paragraph [0024])comprising: a first processor (Fig. 1, processor 122) (page 2, paragraph [0024]); and
at least one first memory storing at least one user preference indicative of at least one preferred characteristic of natural-language outputs generated by a machine-learning language model based on user-provided natural-language text inputs (Fig. 1, memory 124) (page 2, paragraph 0024]), the at least one first memory encoded with first instructions that, when executed, cause the first processor to:
receive at least one input (For example, the user 110 may provide a prompt for one or more generative AI systems 160) (page 3, paragraph [0027]) indicative of a natural-language text string (The prompts may be a single word, a list of words, one or more phrase, or one or more sentences) (page 2, paragraph [0020]); and
a remote device communicatively connected to the user device (AI platform server 150) (page 2, paragraph [0024]) and (The computing device components described below may be suitable for the computing devices described above, including one or more devices associated with machine learning service (e.g., productive platform server 160)) (page 6, paragraph [0059]), the remote device comprising:
a second processor (processing unit 502) (page 6, paragraph [0059]); and
at least one second memory (system memory 504) (page 6, paragraph [0059]) encoded with second instructions that, when executed, cause the second processor to:
receive the natural language text prompt (The prompts may be a single word, a list of words, one or more phrase, or one or more sentences) (page 2, paragraph [0020]) from the user device (For example, the user 110 may provide a prompt for one or more generative AI systems 160) (page 3, paragraph [0027]);
receive the at least one user preference from the user device (At operation 208, the AI guidance system 140 determines if one or more embedded attributes are associated with the one or more applications, documents, interfaces, and/or contents. If the AI guidance system 140 determines that the one or more embedded attributes exist at operation 210, the method 200 advances to operation 212 ) (page 3, paragraph [0035]);
modify a system prompt for the machine-learning language model (With reference first to FIG. 4A, conceptual diagram 400 depicts an overview of pre-trained generative model package 404 that processes an input 402 to generate model output for storing entries in and/or retrieving information from a generative model output 406 (e.g., suggestions and/or suggested modifications) according to aspects described herein) (page 4, paragraph [0044]) based on the at least one user preference (At operation 212, the AI guidance system 140 generates a new supplemental prompt and/or modifies the input prompt based on the one or more attributes) (page 3, paragraph [0036]);
provide the system prompt as an initial input to the machine-learning language model (Additionally, or alternatively, the AI guidance system may modify the input prompt based on the embedded attribute and provide the modified input prompt to the LLM AI) (page 4, paragraph [0039]);
provide, subsequent to providing the system prompt, the natural-language text prompt as an input to the machine-learning language model to generate a natural-language text output (Additionally, or alternatively, the AI guidance system may modify the input prompt based on the embedded attribute and provide the modified input prompt to the LLM AI) (page 4, paragraph [0039]); and
transmit the natural-language text output to the user device (At operation 214, the AI guidance system 140 provides one or more prompts to the one or more generative AI systems. The one or more prompts may include a new supplemental prompt, a modified prompt, and/or the original input prompt) (page 3, paragraph [0037]).
Amershi et al. fails to teach provide the natural-language text string as a natural-language text prompt to a chat application operating on the user device.
Bailey et al. teaches provide the natural-language text string as a natural-language text prompt to a chat application operating on the user device (In step 201, the computer system or server receives a chatbot prompt form a user) (page 4, paragraph [0029]).
Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Amershi with the teachings of Bailey to improve the communication quality by modifying the input prompts based on the user’s preferences and by providing responses geared towards the users preferences.
Allowable Subject Matter
Claim 19 would be allowed if the above 35 USC 101 rejections are overcome.
The following is a statement of reasons for the indication of allowable subject matter: Claim 19 teaches similar subject matter as the prior art of Amershi et al. (US 2024/0386038), Bailey et al. (US 2025/0068881), and Molitor et al. (US 2024/0419922). However, the prior art, alone or in combination, fails to disclose “receiving, by the remote device and from the user device, a second natural-language text prompt provided by the user to a chat application operating on the user device; receiving, by the remote device and from the user device, the at least updated one user preference for a user; modifying, by the remote device, the first modified system prompt with the received at least updated one user preference to generate a second modified system prompt; providing, by the remote device, the second modified system prompt as an initial input to the machine-learning language model; providing, by the remote device and after providing the second modified system prompt, the second natural-language text prompt as an input to the machine-learning language model to generate a second natural-language text output; transmitting, by the remote device, the second natural-language text output to the user device; and causing, by the user device, the chat application to communicate the second natural-language text output to the user” as recited in claim 19
Claims 4, and 14-16 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims and if the above 35 USC 101 rejections are overcome.
Cited Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Dolan et al. (US 2023/0122202) discloses grounded multimodal agent interactions.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SATWANT K SINGH whose telephone number is (571)272-7468. The examiner can normally be reached Monday thru Friday 9:00 AM to 6:00 PM EST.
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, Paras D Shah can be reached at (571}270-1650. 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.
/SATWANT K SINGH/ Primary Examiner, Art Unit 2653
Prosecution Insights