DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
The amendments were received on 2/10/2026. Claims 1, 3-11, 13-16, and 18-20 are pending where claims 1, 3-11, 13-16, and 18-20 were previously presented.
Specification
The title of the invention is not descriptive. A new title is required that is clearly indicative of the invention to which the claims are directed.
35 USC § 112
The applicant amended the claims to address the 35 USC 112 rejections in view of the amendments, the respective 35 USC 112 rejections have been withdrawn.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1, 3, 4, 6-11, 13, 14, 16, 18, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Abrams et al [US 2024/0256622 A1] in view of Arrouye et al [US 2008/0033921 A1] and Shah et al [US 2006/0218488 A1].
With regard to claim 1, Abrams teaches a method of improving an accuracy of results generated by a generative model, comprising: receiving input information via a homepage of an application (see paragraphs [0019] and [0033]; the system can receive, as input, information/query from a user where the application is used to receive the initial query/input);
recognizing an intention category by performing intention recognition on the input information (see paragraphs [0030] and [0034]; the system can perform an intention recognition on the input to determine the user’s intent);
determining a generates a final result (see paragraph [0027]-[0029], [0022], and [0032] and [0038]; the system can determine the type of output format that result are intended to be in and be able to utilize particular tools such as APIs/libraries with respect to particular types of data as well as determining the type of intent including whether to generate a direct answer or summarized answer; the system can utilize the API to gather initial results before the generative model produces its respective result);
performing, by the generative model
generating the final result of processing the input information by the generative model
Abrams teaches the usage of a generative model and API (see paragraph [0027]) but does not explicitly indicate the usage of a plugin; in particular Abrams does not appear to explicitly teach:
determining a plugin from a plurality of plugins based on the recognized intention category; selecting a first cooperative mode from a plurality of cooperative modes based on a requirement of implementing the plugin, wherein the first cooperative mode indicates that the plugin is to generate an initial result before the generative model generates a final result,
and wherein at least a second cooperative mode of the plurality of cooperative modes indicates that the generative model is to generate the initial result before the plugin generates the final result;
performing, by the generative model based on determining that the plugin requires a statement derived from the input information, induction processing on the input information to generate the statement;
calling, by the generative model, the plugin and acquiring, by the generative model, the initial result generated by the plugin based on the statement;
generating the final result of processing the input information by the generative model based on the initial result generated by the plugin.
Arrouye teaches a plugin; …determining that the plugin requires a statement… (see paragraphs [0030] and [0035]-[0037]; plugins can be used to provide specific functionality that a search engine or other programs can utilize to perform various tasks where the plugin has certain parameters/statements that can be passed to it in order to perform the associated task).
It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to modify the search system of Abrams by incorporating plugins that programs can utilize as taught by Arrouye in order to expand upon the functionality and capabilities of various programs including search/retrieval programs by utilizing various plugins that can allow for those programs to be able to automatically perform additional tasks including displaying particular graphical formats as results or access various databases thereby allowing a user to utilize one tool to receive their desired results without having to perform multiple different searches on different tools or through different search engines/interfaces thus also saving the user time in reaching desirable results.
Abrams in view of Arrouye teach determining a plugin from a plurality of plugins based on the recognized intention category; selecting a first cooperative mode from a plurality of cooperative modes based on a requirement of implementing the plugin, wherein the first cooperative mode indicates that the plugin is to generate an initial result before the generative model generates a final result (see Arrouye, paragraphs [0030] and [0035]-[0037]; see Abrams, paragraph [0027]-[0029], [0022], and [0032] and [0038]; the system can determine the type of output format that result are intended to be in and be able to utilize particular tools such as APIs/libraries with respect to particular types of data as well as determining the type of intent including whether to generate a direct answer or summarized answer; the system can utilize the API/plugin to gather initial results before the generative model produces its respective result),
performing, by the generative model based on determining that the plugin requires a statement derived from the input information, induction processing on the input information to generate the statement; calling, by the generative model, the plugin and acquiring, by the generative model, the initial result generated by the plugin based on the statement; generating the final result of processing the input information by the generative model based on the initial result generated by the plugin (see Arrouye, paragraphs [0030] and [0035]-[0037]; see Abrams, Figure 2; see paragraphs [0027]-[0028] and [0030]; the system can utilize plugins to access and perform processing associated with data from various data repositories as well as be able to generate an answer result for the received query/information).
Abrams in view of Arrouye do not appear to explicitly teach:
wherein at least a second cooperative mode of the plurality of cooperative modes indicates that the generative model is to generate the initial result before the plugin generates the final result.
Shah teaches wherein at least a second cooperative mode of the plurality of cooperative modes indicates
It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to modify the content generation system of Abrams in view of Arrouye by including means for plug-ins to be utilized after the initial results are generated as taught by Shah in order to provide greater flexibility to the system to expand upon various functionality and output data formats without having to always modify/update the respective application thus allowing the application’s size to not grow and take up memory in the device by having to support all possible functionality/formats but still provide ability for clients to be able to customize and have particular functionality/formats that they desire.
Abrams in view of Arrouye and Shah teach wherein at least a second cooperative mode of the plurality of cooperative modes indicates that the generative model is to generate the initial result before the plugin generates the final result (see Shah, paragraphs [0037] and [0068]-[0069]; see Abrams, [0022]; the system can utilize a plug-in after content has been generated to perform various actions to generate/create the final result).
With regard to claim 3, Abrams in view of Arrouye and Shah teach wherein the result of processing the input information is determined by: when the information is input for a target functional module that is selected, determining the target plugin associated with the target functional module, wherein different target functional modules are used to answer questions in different vertical scenes; and according to the cooperative mode of the generative model and the target plugin, generating the final result of processing the input information based on the generative model and the target plugin (see Arrouye, paragraph [0035]; see Abrams, paragraphs [0024] and [0027]; different tasks/functionalities can be determined and appropriate API and associated plugin utilized to request and retrieve results/answers from respective verticals/data sources such as weather or stock data).
With regard to claim 4, Abrams in view of Arrouye and Shah teach wherein, the according to the cooperative mode of the generative model and the target plugin, generating the final result of processing the input information based on the generative model and the target plugin, comprises: calling the target plugin by the generative model to acquire an initial result of the target plugin, and acquiring the final result of processing the input information based on the generative model and the initial result; or calling the target plugin by the generative model to acquire the initial result generated by the target plugin (see Arrouye, paragraph [0035]; see Abrams, paragraphs [0022]-[0028]; the system can utilize the API and plugin to retrieve initial results or via the generative model when performing the additional search queries).
With regard to claim 6, Abrams in view of Arrouye and Shah teach wherein the calling the target plugin by the generative model to acquire an initial answer of the target plugin, comprises: when the target plugin is a search plugin, using the information and an induction prompt statement as input based on the generative model, performing induction processing on the information according to the induction prompt statement to generate a search statement that has a same semantic as the information , wherein the induction prompt statement is used to indicate an induction requirement for performing the induction processing; and calling the search plugin by the generative model, and acquiring an initial search result matched with the search statement based on the search plugin (see Arrouye, paragraph [0035]; see Abrams, paragraphs [0024] and [0021]; the system can generate search statements that are semantically the same or related in order to search for and receive results so that the system can provide the user with an answer to their inquiry).
With regard to claim 7, Abrams in view of Arrouye and Shah teach wherein the performing induction processing on the information according to the induction prompt statement to generate a search statement that has a same semantic as the information , comprises: performing semantic analysis on the information according to the induction prompt statement, determining a first semantic topic of the information , and according to the first semantic topic, extracting a search statement accorded with the first semantic topic from the information ; or, performing the semantic analysis on the information and multi-round dialogue information related to the information , determining a second semantic topic corresponding to the information and the multi-round dialogue information, and according to the second semantic topic, extracting a search statement accorded with the second semantic topic from the information and the multi-round dialogue information (see Arrouye, paragraph [0035]; see Abrams, paragraphs [0024] and [0021]; the system can generate search statements that are semantically the same or related in order to search for and receive results so that the system can provide the user with an answer to their inquiry).
With regard to claim 8, Abrams in view of Arrouye and Shah teach wherein the calling the target plugin by the generative model to acquire the initial result generated by the target plugin, comprises: when the target plugin is a drawing plugin, using the information as input based on the generative model, and performing semantic analysis on the information to extract image key description information corresponding to the information ; and calling the drawing plugin, inputting the image key description information into the drawing plugin, and generating an image generation result corresponding to the image key description information based on the drawing plugin (see Abrams, paragraphs [0038], [0032], [0022], and [0019]; the system can utilize different content types as well as plugins for functionality for those content types including graphics/drawing plugin where textual input can be received but an image result be generated as an answer).
With regard to claim 9, Abrams in view of Arrouye and Shah teach in response to the information not matching with the target plugin and the generative model answering the information, performing semantic analysis on the information based on the generative model to generate the final result of processing the input information (see Abrams, paragraphs [0023], [0026], and [0028]; the system can allow the generative model to determine if additional queries are needed that can make use of specific functionality/plugins; while also determining when that is not necessary and thus not use the plugin and still be able to respond/answer the user’s request/query).
With regard to claim 10, Abrams in view of Arrouye and Shah teach wherein, the according to the cooperative mode of the generative model and the target plugin, generating the final result of processing the input information based on the generative model and the target plugin, comprises: calling the target plugin by the generative model to acquire the initial answer result of the target plugin, and acquiring the final result of processing the input information based on the generative model and the initial result; or, calling the target plugin by the generative model to acquire the initial result generated by the target plugin (see Arrouye, paragraph [0035]; see Abrams, paragraphs [0022]-[0028]; the system can utilize the API and plugin to retrieve initial results or via the generative model when performing the additional search queries).
With regard to claims 11, 13, and 14 and 16, 18, and 19, these claims are substantially similar to claims 1, 3, and 4 and are rejected for similar reasons as discussed above.
Claims 5, 15, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Abrams et al [US 2024/0256622 A1] in view of Arrouye et al [US 2008/0033921 A1] and Shah et al [US 2006/0218488 A1] in further view of He et al [US 2008/0183685 A1].
With regard to claim 5, Abrams in view of Arrouye and Shah teach all the claim limitations of claims 1 and 2 as discussed above.
Abrams in view of Arrouye and Shah teach using the information and an intention judgment prompt statement as input based on the generative model, performing semantic analysis on words comprised in the information according to the intention judgment prompt statement (see Abrams, paragraphs [0021], [0036], and [0023]; the generative model can analyze the query/information and be able to determine a query intent).
Abrams in view of Arrouye and Shah teach intent determination means but do not appear to explicitly teach wherein the recognizing an intention category by performing intention recognition on the input information, comprises: determining the target intention category matched with the information, wherein the intention judgment prompt statement is used to indicate an ability requirement judgment requirement of the intention categories and represent a word example corresponding to the intention category.
He teaches wherein the recognizing an intention category by performing intention recognition on the input information, comprises: determining the target intention category matched with the information (see paragraphs [0018], [0020]-[0021] and [0064]; the system can receive a query and be able to determine the intent classification based on a taxonomy and its respective terms associated with a taxonomy category level).
It would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to modify the search system of Abrams in view of Arrouye and Shah by utilizing a taxonomy in conjunction with a machine learning classifier trained on previous queries that were classified as taught by He in order to leverage an intent classification scheme (i.e. taxonomy) as well as the knowledge of past classifications to be able to help ensure a correct or related intent is determined for current user queries.
Abrams in view of Arrouye and Shah in further view of He teach wherein the intention judgment prompt statement is used to indicate an ability requirement judgment requirement of the intention categories and represent a word example corresponding to the intention category (see He, paragraphs [0018], [0020]-[0021] and [0064]; see Abrams, paragraphs [0021], [0036], and [0023]; the generative model can analyze the query/information and be able to determine a query intent based on comparison of the query to the various intention categories).
With regard to claims 15 and 20, these claims are substantially similar to claim 5 and are rejected for similar reasons as discussed above.
Response to Arguments
Applicant's arguments (see the second and third paragraph on page 10) have been fully considered and are persuasive. The 35 USC 112 rejections to the claims have been withdrawn in view of the amendments. The applicant amended the claims to address the 35 USC 112 rejections in view of the amendments, the respective 35 USC 112 rejections have been withdrawn.
Applicant's arguments (see the fourth paragraph on page 10 through the first paragraph on page 12) have been fully considered but they are not persuasive. The applicant argues that the cited prior art references do not teach all the claim limitations including “determining a plugin based on the recognized intention category”. The Examiner respectfully disagrees. As discussed in Abrams at paragraphs [0019] and [0027], the system can determine that different data sources can have particular information and has means of utilizing tools (i.e. APIs or libraries) to access data from those different data sources where such queries can be based on the intent of the query, such as queries for stock information can be gathered from a data source that has an API or library where the user has given the respective ML model permission to utilize those other specific data repositories. Therefore, applicant’s arguments are not persuasive and the respective rejection still stands.
Applicant's arguments (see the second paragraph on page 12) have been fully considered but they are not persuasive. The applicant argues that the Abrams method doesn’t teach plugins and also respective cooperative mode with plugins. The Examiner respectfully disagrees. As noted in the 35 USC 103 rejections, Abrams teaches that various third-party platforms and other data sources can be used as well as have a variety of output formats. With regard to plugins, Abrams recites various features that can be associated with using plugins; however, due to not explicitly utilizing the term, an additional reference was provided to illustrate and teach plugins. In response to applicant's arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986). With regard to the cooperative mode, as illustrated in the 35 USC 103 rejections, the combination of references taught the claim limitation and not merely Abrams alone; however, Abrams did illustrate that multiple components can cooperate or work together in order to arrive at the final result including leveraging searching first (including the different data sources) for initial results before the generative model processes those results to generate a final result or that the output of a first machine/generative model can be provided to another generative model (see Abrams para 22).
Applicant’s arguments (see the last paragraph on page 12) with respect to the rejection(s) of claim(s) under 35 USC 103 have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Shah. The applicant amended the claims to incorporate new limitations that required further search and consideration. As shown in the 35 USC 103 rejections, the additional reference, when combined, illustrates various additional cooperative models of a plugin being used after results/content is generated.
Applicant's arguments (see the first whole paragraph on page 13 through the last paragraph on page 14) have been fully considered but they are not persuasive. The applicant argues that the Abrams reference does not teach the performing induction processing limitation. The Examiner respectfully disagrees. Applicant's arguments fail to comply with 37 CFR 1.111(b) because they amount to a general allegation that the claims define a patentable invention without specifically pointing out how the language of the claims patentably distinguishes them from the references. As illustrated in the 35 USC 103 rejections, Abrams teaches the system can send information to the machine learning model that includes the query where that generative/machine learning model can generate queries to various data sources where the respective APIs/plugins can be used to access those data sources to perform the search with the statement referring to the query/command utilized to access the respective data source(s). Therefore, as can be seen, the combination of references teach the claim limitations as recited.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Muhammad et al [US 2024/0354823 A1] (teaches at paragraphs 25-26 and 23 that the system can utilize a diffusion model that makes use of a plugin for another model that helps the first model) and Vlahos et al [US 2002/0133504 A1] (teaches at paragraph 82 that information about the queries/request can be used to create new queries for particular data sources with wrappers/APIs for that source performing further transformation on the request in order to access the data source).
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MARC S SOMERS whose telephone number is (571)270-3567. The examiner can normally be reached M-F 11-8 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, Ann Lo can be reached on 5712729767. 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.
/MARC S SOMERS/Primary Examiner, Art Unit 2159 3/13/2026