CTNF 18/924,875 CTNF 100871 DETAILED ACTION This communication is in response to the Application filed on October 23, 2024. Claims 1-20 are pending and have been examined. Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. Priority Receipt is acknowledged that application claims priority to foreign application with application number 202311388566.1 dated October 24, 2023. Copies of certified papers required by 37 CFR 1.55 have been received. Priority is acknowledged under 35 USC 119(e) and 37 CFR 1.78. Claim Objections 07-29-01 AIA Claim s 1, 6, 10, 15, and 19 are objected to because of the following informalities: Claim 1, lines 4-5, should be “ in which the input request satisfies a relevant condition with the user information in a direction of the a requested result ” Claim 6, lines 4-5, should be “ generating first sub-prompt information based on the portion of the partial second data ” Claims 10 and 19 are objected to because of similar reasons to claim 1. Claim 15 is objected to because of similar reasons to claim 6 . Appropriate correction is required. Claim Rejections - 35 USC § 101 07-04-01 AIA 07-04 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. All of the claims are method claims (1-9), apparatus/machine claims (10-20) or manufacture claim under (Step 1), but under Step 2A all of these claims recite abstract ideas and specifically mental processes. These mental processes are more particularly recited in claims 1, 10, and 19 as: based on a relationship between the input request and user information of the user, determining, from a target data source, at least first data in which the input request satisfies a relevant condition with the user information in a direction of the requested result… generating first prompt information based on the first data… sending the input request and model prompt information to a target model, wherein the target model performs language processing on the input request based on the model prompt information and obtains a feedback result corresponding to the input request in the direction of the requested result… Under Step 2A Prong One, claims 1, 10, and 19 are directed to an abstract idea and specifically a mental process. As detailed above, the steps of determining, generating, sending, performing, etc. may be practically performed in the human mind with the use of a physical aid such as a pen and paper. For example, a human receptionist could receive an initial request from a client for a purchase recommendation, compare the initial request to the client’s profile to find products relevant to the client, retrieve the name of the relevant product, make an intermediate request to a human expert to explain the relevant product to the client, the intermediate request comprising the client’s initial request and the relevant product’s name, and obtain a summary of the product that the receptionist then relays to the client. Under Step 2A Prong Two, this judicial exception is not integrated into a practical application because claims 1-20 do not recite additional elements that integrate the exception into a practical application. In particular, claims 1, 10, and 19 recite the additional elements of a target model (¶ [0017]-[0018]), a processor (¶ [0131]), and a memory (¶ [0147]). These additional elements are recited at a high level of generality and merely equate to “apply it” or otherwise merely uses a generic computer as a tool to perform an abstract which are not indicative of integration into a practical application as per MPEP 2106.05(f). Further, claims 1, 10, and 19 recite the additional elements of “obtaining…” which amounts to insignificant extra-solution activities which are not indicative of integration into a practical application as per MPEP 2106.05(g). Accordingly, these 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. The claim is directed to an abstract idea. Under Step 2B, the claims do not recite 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 elements of using a computer is noted as a general computer {processor (¶ [0131]); memory (¶ [0147])}. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. Further, the additional limitations in the claims noted above are directed towards insignificant extra-solution activities. The claims are not patent eligible. With respect to claims 2, 11, and 20, the claim relates to generating second prompt information based on second data if the input request does not satisfy a relevant condition with the user information. This relates to a human receptionist making an intermediate request to the human expert that is not personalized to the client due to a lack of topic relevancy to the client’s profile. No additional limitations are present. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. With respect to claims 3 and 12, the claim relates to searching a first index data set based on overlapping words between a user’s input request and a user’s background information. This relates to a human receptionist searching through their company’s product list for product names that overlap with words from the client’s profile. For example, if the client’s profile details an interest in security, the human receptionist could search for products related to security cameras. No additional limitations are present. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. With respect to claims 4 and 13, the claim relates to searching a first index data set based on semantic features of a user’s input request when no overlap exists between the user’s input request and their background information. This relates to a human receptionist searching for generic products if there is no relevancy between the client’s request and the client’s profile. No additional limitations are present. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. With respect to claims 5 and 14, the claim relates to determining second data based on search results returned based on semantic features of the input request. This relates to a human receptionist returning relevant product names from their search of the company product list. No additional limitations are present. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. With respect to claims 6 and 15, the claim relates to determining a plurality of sub-prompt information based on whether keywords overlap between the second data and keywords of the user information. This relates to a human receptionist determining what type of intermediate request they should make to the human expert based on the retrieved product names and their relevance to the client’s profile. For example, if product names (e.g. “security cameras”) overlap with keywords from a client’s profile (e.g. “security”), the receptionist could create two sub-requests for the human expert, the first sub-request requesting information about security cameras and the second sub-request requesting information about alternative products. If product names do not overlap with keywords from a client’s profile, the receptionist could simply request a generic description of the company’s best-selling products from the human expert. No additional limitations are present. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. With respect to claims 7 and 16, the claim relates to deduplicating first prompt and first sub-prompt information. This relates to a human receptionist removing duplicate product names from their intermediate request before sending the intermediate request to the human expert. No additional limitations are present. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. With respect to claims 8 and 17, the claim relates to using a public data source and a private data source to search for data. This relates to a human receptionist searching through both their company’s public product list as well as their internal product list. No additional limitations are present. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. With respect to claims 9 and 16, the claim relates to updating the feedback result of the target model based on feedback from the user. This relates to a human receptionist repeating the process of searching, making an intermediate request, and returning the human expert’s response to the client because the client did not express satisfaction with the initial response. No additional limitations are present. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. For all of the above reasons, taken alone or in combination, claims 1-20 recite a non-statutory mental process. Claim Rejections - 35 USC § 102 07-07-aia AIA 07-07 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 – 07-08-aia AIA (a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention. 07-12-aia AIA (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. 07-15-03-aia AIA Claim s 1-2 , 9-11 , and 18-20 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by US Patent Publication 20250131020 A1 (Gupta et al.) . Claim 1 Regarding claim 1 , Gupta et al. disclose an information processing method comprising: obtaining an input request of a user (Gupta et al. ¶ [0122], "With reference to FIGS. 1A-2C, the at least one processor may receive an initial user prompt as described for the like numbered block on the method 200 as described.") ; based on a relationship between the input request and user information of the user, determining, from a target data source, at least first data (Gupta et al. ¶ [0117], "the at least one processor may select a user profile from among a plurality of user profiles based on the user context information and the user prompt." User profile data is considered analogous to first data) in which the input request satisfies a relevant condition with the user information in a direction of the requested result (Gupta et al. ¶ [0117], "For example, the at least one processor may analyze the GPS data to determine the user's current location and time of day. If the user is determined to be at an office location during regular business hours and the prompt inquiries about “upcoming meetings,” the at least one processor could select a “Professional” or “Work” profile." The input request (upcoming meetings) satisfies a relevant condition with user information (GPS location)) , wherein the target data source includes data related to the user information (Gupta et al. ¶ [0068], "the computing system may be configured to retrieve available user profiles (stored on the local user end device, in a cloud-based storage solution, etc.)") ; generating first prompt information based on the first data (Gupta et al. ¶ [0117], "the at least one processor may select a user profile from among a plurality of user profiles based on the user context information and the user prompt. For example, ... If the user is determined to be at an office location during regular business hours and the prompt inquiries about “upcoming meetings,” the at least one processor could select a “Professional” or “Work” profile." User profile data is considered analogous to first prompt information; see claim interpretation) ; and sending the input request and model prompt information to a target model (Gupta et al. ¶ [0140], "In block 250, the at least one processor may ... create the enhanced prompt based on the user profile and contextual information, and forward this enhanced prompt to the LXM to receive a more tailored and precise response.”) , wherein the target model performs language processing on the input request based on the model prompt information (Gupta et al. ¶ [0106], "The continuous speech-monitoring AI system 172 may also implement and/or use advanced natural language processing (NLP) algorithms to interpret spoken words, phrases, or sentences for context and user profile information.") and obtains a feedback result corresponding to the input request in the direction of the requested result (Gupta et al. ¶ [0058], "For example, the at least one processor may generate an enhanced prompt asking for “safety precautions for do-it-yourself (DIY) home electrical repairs,” identify a relevant LXM model trained on home improvement and safety guidelines, and forward the prompt to the selected model specialized knowledge, which may generate a detailed list of safety measures tailored to DIY electrical tasks.") , wherein the model prompt information includes the first prompt information (Gupta et al. ¶ [0140], "In block 250, the at least one processor may ... create the enhanced prompt based on the user profile and contextual information, and forward this enhanced prompt to the LXM to receive a more tailored and precise response.”) . Claim 2 Regarding claim 2 , the rejection of claim 1 is incorporated. Gupta et al. further disclose based on the relationship between the input request and the user information (Gupta et al. ¶ [0123], "In block 222, the at least one processor may identify, based on observing user responses, one or more portions of the output received from the LXM that elicited positive, negative, or neutral user responses.”) , determining, from the target data source, at least second data (Gupta et al. ¶ [0124], "In block 224, the at least one processor may submit a prompt to an LXM inquiring about prompt parameters and/or content characteristics that resulted in positive, negative, or neutral user responses of the identified one or more portions of the output.”) in which the input request does not satisfy the relevant condition with the user information in the direction of the requested result (Gupta et al. ¶ [0124], "if a certain output is flagged by users as convoluted or lacking in detail, the system may interact with the LXM to determine the specific parameters that guided that response. ... The system can use this information to update the prompt and the user's profile.”) ; and generating second prompt information based on the second data (Gupta et al. ¶ [0050], "In block 226, the at least one processor may update the selected user profile based on information on prompt parameters received from the LXM to include or increase prompt parameters that elicited positive user responses and remove or reduce prompt parameters that elicited negative user responses." Updated user profile is considered analogous to second prompt data based on second data) , wherein the model prompt information also includes the second prompt information, and a prompt method of the first prompt information is same as or different from a prompt method of the second prompt information (Gupta et al. ¶ [0061], "In some embodiments, the computing system may be configured to ... generate LXM prompts (e.g., enhanced prompts) based on the updated user profile and context data; use the generated prompts to receive LXM-generated content that is tailored to the current user profile; and present the tailored LXM-generated content to the user.") . Claim 9 Regarding claim 9 , the rejection of claim 1 is incorporated. Gupta et al. further disclose when feedback result does not achieve an expected goal, performing at least one round of: sending at least the output feedback result of the target model for the input request to the target model (Gupta et al. ¶ [0123], "In block 222, the at least one processor may identify, based on observing user responses, one or more portions of the output received from the LXM that elicited positive, negative, or neutral user responses. ... In block 224, the at least one processor may submit a prompt to an LXM inquiring about prompt parameters and/or content characteristics that resulted in positive, negative, or neutral user responses of the identified one or more portions of the output.”) , such that the target model updates the feedback result for the input request based on at least the output feedback result (Gupta et al. ¶ [0124], "if a certain output is flagged by users as convoluted or lacking in detail, the system may interact with the LXM to determine the specific parameters that guided that response. ... The system can use this information to update the prompt and the user's profile.") . Claim 10 Regarding claim 10 , Gupta et al. disclose one or more processors (Gupta et al. ¶ [0096], "Various embodiments may be implemented on a number of single-processor and multiprocessor computer systems, including a system-on-chip (SOC) or system in a package (SIP).") , and a memory containing a computer program (Gupta et al. ¶ [0199], " A number of different types of memories and memory technologies are available or contemplated in the future, any or all of which may be included and used in systems and computing devices that implement the various embodiments. ... each of the above-mentioned memory technologies include, for example, elements suitable for storing instructions, programs, control signals, and/or data for use in a computing device, system on chip (SOC) or other electronic component."). The remaining limitations of claim 10 are similar to that of claim 1 and therefore are rejected for similar reasons as described above. Claim 11 Regarding claim 11 , the rejection of claim 10 is incorporated. The limitations of claim 11 are similar to that of claim 2 and therefore are rejected for similar reasons as described above. Claim 18 Regarding claim 18 , the rejection of claim 10 is incorporated. The limitations of claim 18 are similar to that of claim 9 and therefore are rejected for similar reasons as described above. Claim 19 Regarding claim 19 , Gupta et al. disclose a non-transitory computer readable storage medium containing a computer program (Gupta et al. ¶ [0186], "the example methods discussed in the following paragraphs may be implemented as a non-transitory processor-readable storage medium having stored thereon processor-executable instructions configured to cause a processor of a computing device to perform the operations of the methods of the following implementation examples.") . The remaining limitations of claim 19 are similar to that of claim 1 and therefore are rejected for similar reasons as described above. Claim 20 Regarding claim 20 , the rejection of claim 19 is incorporated. The limitations of claim 20 are similar to that of claim 2 and therefore are rejected for similar reasons as described above . Claim Rejections - 35 USC § 103 07-20-aia AIA 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 3-5 and 12-14 are rejected under 35 U.S.C. 103 as obvious over Gupta et al. as applied to claims 1 and 10 above, and further in view of US Patent Publication 20200192978 A1 (Sivagnanam et al.) . Claim 3 Regarding claim 3, the rejection of claim 2 is incorporated. Gupta et al. disclose all the elements of the claimed invention as stated above. Gupta et al. do not explicitly disclose all of searching a first index data set based on overlapping keywords. However, Sivagnanam et al. disclose when keywords of the input request overlap with keywords of the user information (Sivagnanam et al. ¶ [0045], "In an example, a request, made by a user who is a manager located in the United States, may be tokenized into “List” and “upcoming courses.” ... the bot server 250 first searches the contextualized database for matching tokens. The contextualized database of the database 117 may include matching tokens and addresses that may have been previously associated with the specific user making the request") , searching a first index data set based on the overlapping keywords to obtain first search result data, and determining the first search result data as the first data (Sivagnanam et al. ¶ [0047], "If an exact match is found between the tokens of the user request 220 and the stored tokens at database 117 (which are mapped to an address), then the bot server 250 (or machine learning node 115 therein) may select the address and access the address to obtain the data from the destination identified by the address (yes at 235 and 245).") , wherein the first index data set is a data set created based on index data corresponding to each piece of data in the user information and the target data source (Sivagnanam et al. ¶ [0023], "The database 117 may store mappings between stored tokens and addresses (e.g., an application programming interface (API), a uniform resource locator (URL), an IP address, or other types of address), and may store a history of requests and responses. In some implementations, the database 117 may store the user's tasks or to do list, the user's profile (e.g., demographics, work profile, educational profile, skills, preferences), peer group interaction data, and peer jargon, and/or other parameters (e.g., user parameters). ... the database 117 additionally or alternatively includes a contextualized database (e.g., a filtered or narrowed database), which may store the mappings between stored tokens and addresses that are associated with a particular user and/or types of users" Database 117 is considered analogous to a target data source. The contextualized database stores tokens and addresses (index data) corresponding to a particular user's data. Thus, a contextualized database is considered analogous to a first index data set) . It would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to modify Gupta et al.’s information processing method to incorporate Sivagnanam et al.’s contextualized database. The suggestion/motivation for doing so would have been that, “The contextualized database may help to narrow the search for a matching tokens performed by the machine learning node 115, thereby allowing for faster and more efficient searching,” as noted by the Sivagnanam et al. disclosure in paragraph [0023]. Claim 4 Regarding claim 4, the rejection of claim 2 is incorporated. Gupta et al. do not explicitly disclose all of searching a first index data set based on semantic features of the input request when there exists no overlapping keywords. However, Sivagnanam et al. disclose when there are no overlapping keywords between keywords of the input request and keywords of the user information, searching a first index data set based on semantic features of the input request (Sivagnanam et al. ¶ [0048], "If an exact match is not found between the tokens of the request and the stored tokens at database 117, the bot server 250/machine learning node 115 may at 240 ... [propose] one or more alternatives from one or more near matching tokens stored at database 117.... As noted above, if the tokens of the request are a near match to one or more of the stored tokens at database 117, the bot server 250/machine learning node 115 may select the address of the near matching stored token at database 117 and access the address at 245 to obtain the data from the destination identified by the address of the near matching token.") , and determining search result data as the second data (Sivagnanam et al. ¶ [0048], "As noted above, if the tokens of the request are a near match to one or more of the stored tokens at database 117, the bot server 250/machine learning node 115 may select the address of the near matching stored token at database 117 and access the address at 245 to obtain the data from the destination identified by the address of the near matching token.") , wherein the first index data set is a data set created based on index data corresponding to each piece of data in the user information and the target data source (Sivagnanam et al. ¶ [0023], "The database 117 may store mappings between stored tokens and addresses (e.g., an application programming interface (API), a uniform resource locator (URL), an IP address, or other types of address), and may store a history of requests and responses. In some implementations, the database 117 may store the user's tasks or to do list, the user's profile (e.g., demographics, work profile, educational profile, skills, preferences), peer group interaction data, and peer jargon, and/or other parameters (e.g., user parameters). ... the database 117 additionally or alternatively includes a contextualized database (e.g., a filtered or narrowed database), which may store the mappings between stored tokens and addresses that are associated with a particular user and/or types of users" Database 117 is considered analogous to a target data source. The contextualized database stores tokens and addresses (index data) corresponding to a particular user's data. Thus, a contextualized database is considered analogous to a first index data set) . It would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to modify Gupta et al.’s information processing method to incorporate Sivagnanam et al.’s contextualized database. The suggestion/motivation for doing so is similar to the suggestion/motivation described above with respect to claim 3. Claim 5 Regarding claim 5, the rejection of claim 3 is incorporated. Sivagnanam et al. further disclose when there are overlapping keywords between the keywords of the input request and the keywords of the user information, searching the first index data set based on semantic features of the input request to obtain second search result data (Sivagnanam et al. ¶ [0045]-[0047], "In an example, a request, made by a user who is a manager located in the United States, may be tokenized into “List” and “upcoming courses.” ... the bot server 250 first searches the contextualized database for matching tokens. ... If an exact match is found between the tokens of the user request 220 and the stored tokens at database 117 (which are mapped to an address), then the bot server 250 (or machine learning node 115 therein) may select the address and access the address to obtain the data from the destination identified by the address (yes at 235 and 245).") , and determining the second search result data as the second data (Sivagnanam et al. ¶ [0047], "the bot server 250 (which may include as node machine learning node 115) may search database 117 for stored tokens matching the token request “List” and “upcoming courses.” As noted, if there is an exact match at 305/310, the bot server/machine learning node may select the API information 330, and then access the location identified by the API information 330 to obtain the list of upcoming courses, for example.") ; or searching the first index data set based on semantic features of the input request other than the overlapping keywords, and determining search result data as the second data. Claim 12 Regarding claim 12, the rejection of claim 11 is incorporated. The limitations of claim 12 are similar in scope to that of claim 3 and therefore are rejected for similar reasons as described above. Claim 13 Regarding claim 13, the rejection of claim 11 is incorporated. The limitations of claim 13 are similar in scope to that of claim 4 and therefore are rejected for similar reasons as described above. Claim 14 Regarding claim 14, the rejection of claim 12 is incorporated. The limitations of claim 14 are similar in scope to that of claim 5 and therefore are rejected for similar reasons as described above. Claims 6-7 and 15-16 are rejected under 35 U.S.C. 103 as obvious over Gupta et al. in view of Sivagnanam et al. as applied to claims 4 and 13 above, and further in view of US Patent Publication 20210019309 A1 (Yadav et al.) . Claim 6 Regarding claim 6, the rejection of claim 4 is incorporated. Gupta et al. further disclose generating first sub-prompt information based on a portion of the second data (Gupta et al. ¶ [0061], "In some embodiments, the computing system may be configured to ... generate LXM prompts (e.g., enhanced prompts) based on the updated user profile and context data" Enhanced prompts based on an updated user profile (second data) is considered analogous to first sub- prompt information) , [and generating second sub-prompt information based on data other than the portion of the second data in the second data; and when there is no portion of the second data containing the keywords of the user information in the second data, generating third sub-prompt information based on the second data] wherein: [the second prompt information includes the first sub-prompt information and the second sub-prompt information, or includes the third sub-prompt information;] a prompt method of the first sub-prompt information is the same as the prompt method of the first prompt information (Gupta et al. ¶ [0061], "In some embodiments, the computing system may be configured to ... generate LXM prompts (e.g., enhanced prompts) based on the updated user profile and context data; use the generated prompts to receive LXM-generated content that is tailored to the current user profile; and present the tailored LXM-generated content to the user." Submitting a prompt to an LXM is considered analogous to the prompt method) ; [and prompt methods of the second sub-prompt information and the third sub-prompt information are respectively different from the prompt method of the first prompt information]. Sivagnanam et al. disclose when there is no portion of the second data containing the keywords of the user information in the second data, generating third sub-prompt information based on the second data (Sivagnanam et al. ¶ [0048]-[0053], "If an exact match is not found between the tokens of the request and the stored tokens at database 117, the bot server 250/machine learning node 115 may at 240 attempt to ... [propose] one or more alternatives from one or more near matching tokens stored at database 117.... If one potential near match is obtained (e.g., one potential near match has a distance metric greater than or equal to the threshold distance metric) after applying the one or more weighted user parameters at 244, the bot server 250/machine learning node 115 may make a prediction at 248 and may present, at client interface 107, a response including the obtained data and a query asking, for example, “Is this responsive to your original question or request?”" The query presented at client interface 107 is considered analogous to third sub-prompt information based on the second data) , wherein: the second prompt information [includes the first sub-prompt information and the second sub-prompt information, or] includes the third sub-prompt information (Sivagnanam et al. ¶ [0053], "the bot server 250/machine learning node 115 may make a prediction at 248 and may present, at client interface 107, a response including the obtained data and a query asking, for example, “Is this responsive to your original question or request?”") ; [a prompt method of the first sub-prompt information is the same as the prompt method of the first prompt information;] and prompt methods of [the second sub-prompt information and] the third sub-prompt information are respectively different from the prompt method of the first prompt information (Sivagnanam et al. ¶ [0053], "the bot server 250/machine learning node 115 may make a prediction at 248 and may present, at client interface 107, a response including the obtained data and a query asking, for example, “Is this responsive to your original question or request?”" It is noted that the prompt method of the third sub-prompt information (e.g. querying the user) is different from the prompt method of the first prompt information (e.g. prompting an LXC with an enhanced prompt)) . Gupta et al. in view of Sivagnanam et al. do not explicitly disclose all of a second sub-prompt information generated from data other than the portion of second data. However, Yadav et al. disclose when there is a portion of the second data containing the keywords of the user information in the second data, generating first sub-prompt information based on the portion of the second data (Yadav et al. ¶ [0138]-[0151], "In some implementations, during a candidate generation phase, all possible sequences of matched 510 tokens for this string may be generated for consideration as potential database queries. For example, if the input is “who directed titanic”. We may have the following matches: ... Titanic[:] Titanic <Value from movie_title>[,] “Raise the titanic <Vale from movie_title> ... these candidates may be ranked 550 and then the top K of the candidates may be selected to advance for further processing." The input “who directed titanic” is considered analogous to user information. Matches to the token "Titanic" are considered analogous to a portion of the second data containing keywords of the user information) , and generating second sub-prompt information based on data other than the portion of the second data in the second data (Yadav et al. ¶ [0138]-[0151], "if the input is “who directed titanic”. We may have the following matches: ... Who: Director_name Actor_1_name Actor_2_name Actor_3_name ... these candidates may be ranked 550 and then the top K of the candidates may be selected to advance for further processing." The input “who directed titanic” is considered analogous to user information. Matches to the token "Who" are considered analogous to data other than a portion of the second data since the matches do not overlap exactly) [; and when there is no portion of the second data containing the keywords of the user information in the second data, generating third sub-prompt information based on the second data], wherein: [the second prompt information includes the first sub-prompt information and the second sub-prompt information, or includes the third sub-prompt information; a prompt method of the first sub-prompt information is the same as the prompt method of the first prompt information; and] prompt methods of the second sub-prompt information and the third sub-prompt information are respectively different from the prompt method of the first prompt information (Yadav et al. ¶ [0066]-[0067], "The technique 400 includes selecting 450, based on the first score and the second score, the first candidate database query from the set of candidate database queries.... The technique 400 includes invoking 460 a search of the database using a query based on the first candidate database query to obtain search results." It is noted that the prompt method of the second sub-prompt information (e.g. querying a database) is different from the prompt method of the first prompt information (e.g. prompting an LXC with an enhanced prompt)) . It would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to modify Gupta et al. in view of Sivagnanam et al. to incorporate Yadav et al.’s second sub-prompt information based on data other than the portion of the second data because such a modification is the result of combining prior art elements according to known methods to yield predictable results . More specifically, Gupta et al.’s second prompt information as modified by Yadav et al.’s second sub-prompt information based on data other than the portion of the second data can yield a predictable result of improving model output for the user since the target model would be able to utilize multiple components of the second data to provide a more comprehensive output for the user. Thus, a person of ordinary skill would have appreciated including in Gupta et al.’s second prompt information the ability to do Yadav et al.’s second sub-prompt information based on data other than the portion of the second data since the claimed invention is merely a combination of old elements, and in the combination each element merely would have performed the same function as it did separately , and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Claim 7 Regarding claim 7, the rejection of claim 6 is incorporated. Yadav et al. further disclose before sending the input request and the model prompt information to the target model, deduplicating the first prompt information and the first sub-prompt information (Yadav et al. ¶ [0154], "if the input string contains “pirates of the caribbean” each possible substring of that string will match all the movies in that movie franchise. For example, “pirates”, “pirates of”, “pirates of the”, will all match all 3 pirates movies. In some implementations, before throwing all possible tokenizations that may bring in multiple tokens representing different pirates movie, the system may be configured to default to the longest match for a given token.") . Claim 15 Regarding claim 15, the rejection of claim 13 is incorporated. The limitations of claim 15 are similar in scope to that of claim 6 and therefore are rejected for similar reasons as described above. Claim 16 Regarding claim 16, the rejection of claim 15 is incorporated. The limitations of claim 16 are similar in scope to that of claim 7 and therefore are rejected for similar reasons as described above. Claims 8 and 17 are rejected under 35 U.S.C. 103 as obvious over Gupta et al. as applied to claims 1 and 10 above, and further in view of US Patent Publication 20230259406 A1 (Guan et al.) . Claim 8 Regarding claim 8, the rejection of claim 1 is incorporated. Gupta et al. disclose all the elements of the claimed invention as stated above. Gupta et al. further disclose wherein: the target data source is an existing first data source (Gupta et al. ¶ [0068], "the computing system may be configured to allow the LXM to access and employ the most relevant profile at any given time to account for users operating in different capacities at different times. In some embodiments, the computing system may be configured to retrieve available user profiles (stored on the local user end device, in a cloud-based storage solution, etc.)") , or a first data source determined based on a second data source; and [the second data source is a public domain data source formed by public domain data, and] the first data source is a non-public domain data source (Gupta et al. ¶ [0068], "In some embodiments, the computing system may be configured to retrieve available user profiles (stored on the local user end device, in a cloud-based storage solution, etc.)" Local storage on a user end device is considered analogous to a non-public domain data source) formed by multiple data related to the user information (Gupta et al. ¶ [0068], "Each user may have several user profiles corresponding to different roles or situations, such as work, personal, school, or specific usages.") . Gupta et al. do not explicitly disclose all of a second data source being a public domain data source. However, Guan et al. disclose wherein: a target data source is an existing first data source ( (Guan et al. ¶ [0075], "The hybrid workflow redistributor 100 may perform a similar search of the private cloud catalog schema database 194 for a previously generated catalog in the private cloud's catalog data store 190 that satisfies the requirements of the user request." A private cloud's catalog data store 190 is considered analogous to an existing first data source; see Figure 1) , or a first data source determined based on a second data source; and the second data source is a public domain data source formed by public domain data (Guan et al. ¶ [0040], "A data catalog, or simply catalog, is one or more data structures that provide an organized inventory of data assets and provides metadata for assisting with the organization and use of the data assets. The catalog may be used to compile data assets to generate a result for servicing a user request from publicly stored catalog data.") , and the first data source is a non-public domain data source (Guan et al. ¶ [0075], "The hybrid workflow redistributor 100 may perform a similar search of the private cloud catalog schema database 194 for a previously generated catalog in the private cloud's catalog data store 190 that satisfies the requirements of the user request." A private cloud's catalog data store 190 is considered analogous to an existing first data source; see Figure 1) [formed by multiple data related to the user information]. It would have been obvious to a person having ordinary skill in the art before the time of the effective filing date of the claimed invention of the instant application to modify Gupta et al.’s target data source to incorporate Guan et al.’s separation of public and private data sources. The suggestion/motivation for doing so would have been that, “it is important to protect the business data 108 stored in the backend databases 106 of the private cloud 102 against unauthorized access or distribution of such sensitive, private information, by users who only have access via the public cloud computing environment 104. Moreover, it is important to service requests by users received via the public cloud computing environment 104 without exposing this sensitive, private information, … and instead only providing …. data derived from the business data 108 stored in the backend databases 106, which does not include any sensitive, private information” as noted by the Guan et al. disclosure in paragraph [0065]. Claim 17 Regarding claim 17, the rejection of claim 10 is incorporated. The limitations of claim 17 are similar in scope to that of claim 8 and therefore are rejected for similar reasons as described above. Reference Cited 07-96 AIA The prior art made of record and not relied upon is considered pertinent to applicant’s disclosure. US Patent Publication 20190018899 A1 to Podgorny et al. discloses performing a search for assistance documents (first data) based on user attributes (user information) and a search query (input request). US Patent Publication 20250131190 A1 to Teng et al. discloses a similar system to Gupta et al., with the addition of a sensing hub that collects user information from various sensors on a client device. US Patent Publication 20250117863 A1 to Zangrilli et al. discloses generating verbose tax category descriptions based on exact word matches between a user query (input request), user information, and a product knowledge database (first data source) . Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to JACOB B VOGT whose telephone number is (571)272-7028. The examiner can normally be reached Monday - Friday 9:30am - 7pm 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. /JACOB B VOGT/ Examiner, Art Unit 2653 /Paras D Shah/ Supervisory Patent Examiner, Art Unit 2653 05/26/2026 Application/Control Number: 18/924,875 Page 2 Art Unit: 2653 Application/Control Number: 18/924,875 Page 3 Art Unit: 2653 Application/Control Number: 18/924,875 Page 4 Art Unit: 2653 Application/Control Number: 18/924,875 Page 5 Art Unit: 2653 Application/Control Number: 18/924,875 Page 6 Art Unit: 2653 Application/Control Number: 18/924,875 Page 7 Art Unit: 2653 Application/Control Number: 18/924,875 Page 8 Art Unit: 2653 Application/Control Number: 18/924,875 Page 9 Art Unit: 2653 Application/Control Number: 18/924,875 Page 10 Art Unit: 2653 Application/Control Number: 18/924,875 Page 11 Art Unit: 2653 Application/Control Number: 18/924,875 Page 12 Art Unit: 2653 Application/Control Number: 18/924,875 Page 13 Art Unit: 2653 Application/Control Number: 18/924,875 Page 14 Art Unit: 2653 Application/Control Number: 18/924,875 Page 15 Art Unit: 2653 Application/Control Number: 18/924,875 Page 16 Art Unit: 2653 Application/Control Number: 18/924,875 Page 17 Art Unit: 2653 Application/Control Number: 18/924,875 Page 18 Art Unit: 2653 Application/Control Number: 18/924,875 Page 19 Art Unit: 2653 Application/Control Number: 18/924,875 Page 20 Art Unit: 2653 Application/Control Number: 18/924,875 Page 21 Art Unit: 2653 Application/Control Number: 18/924,875 Page 22 Art Unit: 2653 Application/Control Number: 18/924,875 Page 23 Art Unit: 2653 Application/Control Number: 18/924,875 Page 24 Art Unit: 2653 Application/Control Number: 18/924,875 Page 25 Art Unit: 2653
