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 .
Priority
Applicant claims benefit of U.S. Provisional Patent Application No. 63/587,975, filed October 4, 2023. Claims 1-20 have been afforded the benefit of the October 4, 2023, effective filing date.
Response to Arguments Regarding Claim Rejections - 35 USC § 101
In light of Applicant’s arguments, the rejection under 35 USC § 101 is withdrawn.
Response to Arguments Regarding Claim Rejections - 35 USC § 103
Regarding Claims 1-20. Applicant’s remarks filed on July 28, 2026 have been fully considered. The examiner has reviewed each of the Applicant’s arguments and respectfully responds as follows.
Applicant’s Arguments- Independent Claim 1
Amended claim 1 recites "wherein the computer system is configured to terminate iteratively generating the one or more prompts responsive to a determination that
a similarity between the first topic and one or more of the first set of additional topics identified exceeds a predetermined threshold" (Emphasis supplied).
The Office cites to Maschmeyer as disclosing iteratively generating the one or more prompts (pp. 11-12). However, Maschmeyer does not disclose that the iterative generation terminates responsive to a determination of a similarity, as recited. At most, Maschmeyer discloses that "[t]his process of iteratively modifying input prompts to the generative model and producing new content outputs may be continued until the user either flags one of the outputs as the final content output or manually terminates the process," but not terminating based on a determination of a similarity.
Examiner’s response
Applicant’s argument concerning Maschmeyer’s user controlled termination is acknowledged. The rejection has been revised to additionally rely on Thatcher in view of XU, BO which teaches iterating the search process with a stopping condition, as modified to terminate further matching when a semantic similarity score exceeds a predetermined threshold. Accordingly, the revised rejection relies on the proposed combination, rather than Maschmeyer alone, for the similarity-based termination limitation.
Applicant’s Arguments- Independent Claim 12
Amended independent claim 12 recites limitations similar to the limitations of claim 1. As should be clear from the foregoing discussion, Maschmeyer fails to disclose at least the above- emphasized language. Accordingly, independent claim 12 patentably distinguishes over cited references and it is respectfully requested that the 35 U.S.C. § 103 rejection of claim 12, and claims depending therefrom, be withdrawn for at least the same reasons.
Examiner’s Response
Applicant’s argument regarding independent claim 12 is acknowledged. As with claim 1, rejection has been revised to additionally rely on Thatcher in view of XU BO which teaches iterating the search process with a stopping condition, as modified to terminate further matching when a semantic similarity score exceeds a predetermined threshold. Accordingly, the revised rejection relies on the combined teachings of Maschmeyer, Zhang, and Thatcher in view of XU BO, rather than Maschmeyer alone, to address the identified limitation.
Applicant’s Arguments- Independent Claim 17
Amended independent claim 17 recites limitations similar to the limitations of claim 1. As should be clear from the foregoing discussion, Maschmeyer fails to disclose at least the above- emphasized language. Accordingly, independent claim 17 patentably distinguishes over the cited references and it is respectfully requested that the 35 U.S.C. § 103 rejection of claim 17, and claims depending therefrom, be withdrawn for at least the same reasons.
Examiner’s Response
Applicant’s argument regarding independent claim 17 is acknowledged. As with claim 1 and claim 12, rejection has been revised to additionally rely on Thatcher in view of XU BO which teaches iterating the search process with a stopping condition, as modified to terminate further matching when a semantic similarity score exceeds a predetermined threshold. The revised rejection therefore relies on the combined teachings of Maschmeyer, Zhang, and Thatcher in view of XU, BO to address the identified limitation.
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.
Claim [1, 5, 6, 8, 11, 12, 14, 15,17, 19] are rejected under 35 U.S.C. 103 as
being unpatentable over Maschmeyer (US 2024/0320444 Al) in view of Zhang (US 12,019,663 Bl) and in view of Thatcher (US 11720554 B2 ) and in further view of XU, BO (CN107247709A).
Regarding claim 1, Maschmeyer teaches a method comprising: [0014 " The method may
include: obtaining at least one output of a generative model based on input of a first text prompt; presenting the at least one output via a user interface; receiving, via the user interface, user selection of a desired portion of the at least one output; modifying the first text prompt based on the user selection to obtain a second text prompt; and providing the second text prompt as input to the generative model for obtaining a second output"].
receiving at a computer system, via a user interface, an instruction to generate a content item,
wherein the instruction includes a first topic for the content item; iteratively generating, by the computer system, one or more prompts for input into a generative model based on the instruction by: [0078 "An input prompt supplied by a user is received from the user device 120 via a network 150. In the context
of content generation, the input prompt may be or include a command/request to generate content of a specific type"]; [0094 "The graphical user interface may be provided by the computing system to a user device for displaying thereon. For example, a user interface module (such as the module 116 shown in FIG. 1) of the computing system may be adapted to generate and present the graphical user interface on a user device”]; [0012 " This process of iteratively modifying input prompts to the generative model and producing new content outputs may be continued until the user either flags one of the outputs as the final content output or manually terminates the process"]
outputting the first set of additional topics for display by the user interface; [0026
"obtain at least one output of a generative model based on input of a first text prompt; present the at least one output via a user interface; receive, via the user interface, user selection of a desired portion of the at least one output"]; [0036 "A generative model is initially requested to produce multiple outputs, each from the same text prompt. Upon generation, the multiple outputs are presented to the user via a graphical user interface. The outputs may be displayed concurrently ( e.g., side-by-side) on the GUI or they may be viewed separately (e.g., sequentially) by navigating using the GUI"]; [0031 "The generative AI trained on such a data set is then able to take an input prompt in text form, which may include suggested topics, features, styles or other suggestions, and provide an output image that reflects, at least to some degree, the input prompt" where the multiple outputs are additional topics displayed]
receiving a user selection, via the user interface, of at least one second topic selected from the
first set of additional topics; [0026" obtain at least one output of a generative model based on input of a first text prompt; present the at least one output via a user interface; receive, via the user interface, user selection of a desired portion of the at least one output; modify the first text prompt based on
the user selection to obtain a second text prompt; and provide the second text prompt as input to the generative model for obtaining a second output"]
and generating the one or more prompts based on at least the first topic and the at least one
second topic; [0026"modify the first text prompt based on the user selection to obtain a second text prompt; and provide the second text prompt as input to the generative model for obtaining a second output" where modifying means using the first text prompt and modifying it based on the user selection to a generate a second prompt]; [0079 "In some implementations, a user-supplied prompt may be processed by the system 100 to generate a suitable prompt for inputting to the generative AI model 112. In particular, a user-supplied prompt may be modified to produce the input prompt. For example, an input prompt may be generated by adjusting a user command or request to generate new content, in accordance with one or more defined constraints associated with the generative AI model 112. The constraints may, for example, relate to restrictions ( e.g., character limits, content filters, etc.) on acceptable prompts for the generative AI model" where a second text prompt can be used to generate a second suitable prompt for the AI model]
wherein the one or more prompts instruct the generative model to generate the
content item based on the first topic and the at least one second topic and return the generated content item;
[0099 " The computing system automatically modifies the first text prompt based on the user selection to obtain a second text prompt, in operation 208. The second text prompt may be an input prompt to the generative model for a subsequent iteration of content generation. That is, the generative model may produce new content based on the second text prompt. The first text prompt, e.g., the initial prompt supplied by the user, may be modified so that the second text prompt reflects the user's preferences as indicated by the user-selected portions from the at least one output. In particular, the second text prompt may retain the original intent and context associated with the first text prompt while also representing preference data supplied by the user through their selection(s).
and outputting the generated content item to the user interface [0102 "In operation 210, the
computing system provides the second text prompt as input to the generative model for obtaining one or more second outputs. The second output comprises new content that is produced by the generative model in a subsequent iteration of content generation based on the second text prompt. In particular, the second output may be an output of the generative model that includes representations of user-selected portions from the outputs of preceding iteration(s) of content generation. The second output data may be presented to the user via the user Interface"]
However, Maschmeyer does not teach performing a first search of an information source using at least a portion of the first topic, wherein the first search identifies a first set of additional topics related to the first topic using the information source;
But Zhang teaches performing a first search of an information source using at least a
portion of the first topic, wherein the first search identifies a first set of additional topics related to the first topic using the information source; first topic and one or more of the first set of additional topics [Column 2, lines 4-14 " A technique to enable a user to verify the accuracy of a query response provided by an LLM is disclosed. The technique includes receiving a query comprised of one or more words from a client device. In some embodiments, the query includes a plurality of words and the words included in the query are rephrased to present the query in an improved format for an LLM prompt. A prompt is generated for an LLM. The prompt includes a request for the LLM to generate a plurality of subtopics related to the query and a corresponding plurality of keywords for each of the plurality 15 of subtopics"] ;[ Column 2, lines 27-30 " One or more search engines are utilized to perform a plurality of searches, in parallel, utilizing the plurality of subtopics and the corresponding plurality of keywords received from the LLM" where the first topic is in the form of the query and then the prompt request for the LLM (search request via search engine) to generate a plurality of subtopics].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings Maschmeyer with the teaching of Zhang
because using prompts generated as search queries to retrieve information from external data sources and incorporating the retrieved information into the generated outputs would improve the completeness and relevance of the outputs. This combination represents the predictable use of known search and content generation techniques to enhance the quality, accuracy and completeness of generated content.
Maschmeyer in view of Zhang do not teach and wherein the computer system is configured to terminate iteratively generating the one or more prompts responsive to a determination that a similarity between the first topic and one or more of the first set of additional topics identified exceeds a predetermined threshold;
But Thatcher teaches terminate iteratively generating the one or more prompts responsive to a determination that a similarity between the first topic and one or more of the first set of additional topics identified
[Column 7, lines 3-5 “The iterative search query expansion method is explained in further detail below with respect to FIGS. 2 and 3.”];
[Column 8, lines 42- “According to at least one other embodiment, the stopping criterion may be met when the identified updated enrichment terms from the most recent previous search query match the
enrichment terms of the new search query. For example, if five enrichment terms T 1 -T 5 were identified in the initial set of documents, the first iteration may include the search terms
of the initial search query Q0 and the enrichment terms T 1 -Ts- Continuing the example, if the first iteration retrieves a set of documents where two additional enrichment terms are identified, e.g., T6- T7, then the second iteration may include the search terms of the initial search query Q0 and
the enrichment terms T6-T7 . This process may continue until no additional enrichment terms are identified. For example, if the search query submitted to the IR system containing the
initial search query Q0 and enrichment terms T6-T7 generates the same enrichment terms, i.e., enrichment terms T6-T7, then the stopping criterion may be met.”];
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings Maschmeyer in view of Zhang with Thatcher, so that further topic expansion stops when successive searches identify no additional enrichment terms. This would avoid repeated searches yielding the same topics and reduce unnecessary processing.
Maschmeyer in view of Zhang in view of Thatcher do not teach
exceeds a predetermined threshold
But XU, BO teaches exceeds a predetermined threshold
[Page 4, Detailed Description “(3)By setting a similarity threshold, when the cosine similarity is greater than the set similarity threshold, then the matching ends. For example, we can calculate the semantic similarity between the following word pairs:
Cosine (WE "Money", WE "buy") = 0.79
Cosine (WE Money, WE Cash) = 0.93
Cosine (WE "Money", WE "Make Money") = 0.81
Cosine (WE Money, WE Banknote) = 0.95
If you set a threshold of 0.9, just get a similarity, 'money' and 'cash' do not follow similar tags. Because has met the requirements, improve efficiency.“]
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings Maschmeyer in view of Zhang in view of Thatcher with XU, BO’s semantic similarity comparison to the original topic and search identified additional topics, and terminating further prompt generation when that similarity exceeds a preset threshold. This would avoid generating further prompts once a sufficiently related topic has been identified, thereby reducing unnecessary comparisons and processing.
Regarding claim 5, Maschmeyer teaches the method of claim 1, wherein generating the one or more prompts comprises: generating a first prompt that includes the first topic and the at least one second topic; [0092 "Once the generative model is trained and deployed, the computing system obtains at least one output of the generative model based on input of a first text prompt, in operation 202. The first text prompt is an initial prompt that is supplied by the user to the generative model. In particular,
the first text prompt may be or include a command/request to generate new content”]; [0026 "modify the first text prompt based on the user selection to obtain a second text prompt; and provide the second text prompt as input to the generative model for obtaining a second output" where generating a prompt means using the first text prompt which includes the first topic and based on the user selection of the second topic to a generate another prompt]; [0079 "In some implementations, a user-supplied prompt may be processed by the system 100 to generate a suitable prompt for inputting to the generative AI model 112. In particular, a user-supplied prompt may be modified to produce
the input prompt. For example, an input prompt may be generated by adjusting a user command or request to generate new content, in accordance with one or more defined constraints associated with the generative AI model 112. The constraints may, for example, relate to restrictions ( e.g., character limits, content filters, etc.) on acceptable prompts for the generative AI model" where a second text prompt can be used to generate a second output which includes the initial prompt (first topic) and user selection data (second topic) for the AI model]
and sending the first prompt to the generative model to cause the generative model to generate the content item based on the first prompt [0092 "Once the generative model is trained and deployed, the computing system obtains at least one output of the generative model based on input of a first text prompt, in operation 202. The first text prompt is an initial prompt that is supplied by the user to the generative model. In particular, the first text prompt may be or include a command/request to generate new content”].
Regarding claim 6, Maschmeyer teaches the method of claim 1, wherein the instruction to generate the content item is received at a chat window of the user interface, and wherein outputting the first set of additional topics for display by the user interface comprises: [0082 "The generative AI model 112 may be accessed via a user interface, such as a chatbot (e.g., ChatGPT), that facilitates text-based conversation. The generative AI model 112 may provide chat-like outputs responsive to user-supplied prompts"]; [0083 "In at least some implementations, the content outputs produced by the generative AI model 112 may be accessed via a user interface for a content management system. In particular, a user interface module 116 may provide a graphical user interface for displaying the content outputs on user devices 120"]
displaying, for each of additional topics in the first set of additional topics, a selectable option in the chat window; [0082 "The generative AI model 112 may be accessed via a user interface, such as a chatbot (e.g., ChatGPT), that facilitates text-based conversation. The generative AI model 112 may provide chat-like outputs responsive to user-supplied prompts"]; [0083 "The content outputs may be displayed in an output display area within the graphical user interface. A user may view the content outputs, either one-by-one or by suitable groupings. For example, the outputs from an iteration of content generation may be displayed one at a time, requiring the user to navigate through the outputs, or they may be displayed concurrently (e.g., displayed side-by-side) in the output display area”]; [0084 "The graphical user interface may additionally enable users to interact with the content outputs. In particular, users may input selections of portions from different content outputs using the graphical user interface"]
wherein receiving the user selection of the at least one second topic comprises receiving a user input at the selectable option in the chat window that corresponds to the at least one second topic [0084 "By way of example, for each content output associated with a given prompt, a user may indicate selections of one or more preferred portions from the content output using the graphical user interface. The selected portions may represent information that is desired by the user to be incorporated into a final content output. User input for indicating the selections may be received via an input device such as a mouse, pen, stylus, keyboard, microphone, and the like."]; [0085 "The sandbox area may be a region within the graphical user interface that is different from the output display area. As will be described in greater detail below, the sandbox area may comprise a canvas or textbox that is updated to represent a user's selections across multiple content outputs. In particular, the sandbox area may be gradually populated as the user makes selections of portions from different content outputs that are displayed in the output display area. In this way, when the user is finished making their selections, the totality of the selected portions may be displayed in the sandbox area" where the selection options are in the chat window that corresponds to the second topic selected by user].
Regarding claim 8, Maschmeyer teaches the method of claim 1, further comprising: receiving, at the user interface, another instruction including a third topic for the content item; [0086 "The generative AI model 112 may iteratively produce new outputs based on modified prompts provided by the content generation engine 114, and user may select an output from one of the iterations as
the final content output. The content data of the final content output may then be transmitted to the user device 120 for display thereon" where the iterative process can produce new content based on third topic for the content item]
and receiving a user selection, via the user interface, of at least one fourth topic selected from the second set of additional topics; [0102"The second output comprises new content that is produced by the generative model in a subsequent iteration of content generation based on the second text prompt. In particular, the second output may be an output of the generative model that includes representations of user-selected portions from the outputs of preceding iteration( s) of content generation. The second output data may be presented to the user via the user Interface. In some implementations, the computing system may prompt the user to confirm the second output data as the
final content output or to make further selections of portions from the second output(s) " where the iterative process can include a fourth topic selected from the additional topics via the user interface]
wherein generating the one or more prompts comprises generating the one or more prompts further based on the third topic and the at least one fourth topic [0102 "This process of iteratively modifying input prompts to the generative model and producing new content outputs may be continued until the user either flags one of the outputs as the final content output or manually terminates the process." where the iterative creation input prompts can be based on third topic and at least one fourth topic which is the new content output].
However, Maschmeyer does not teach performing a second search of the information source using at least a portion of the third topic, wherein the second search identifies a second set of additional topics related to the third topic;
But Zhang teaches performing a second search of the information source using at least a portion of the third topic, wherein the second search identifies a second set of additional topics related to the third topic; [column 2, lines 27-30 "One or more search engines are utilized to perform a plurality of searches, in parallel, utilizing the plurality of subtopics and the corresponding plurality of keywords received from the LLM]; [column 2, lines 42-45 " The plurality of search engine responses is
filtered to generate a corresponding subset of search engine responses for each of the subtopics based on the number of times keywords are included in a search engine response" where the corresponding subset of search engine responses can be a second set of additional topics related to a third topic].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings Maschmeyer with the teaching of Zhang because using the prompts generated as search queries to retrieve information from external data sources and incorporate the retrieved information into the generated outputs would improve the completeness and relevancy of generated outputs. This combination represents the predictable use of known search and content generation techniques to enhance the quality, accuracy and completeness of generated content.
Regarding claim 11, Maschmeyer does not teach the method of claim 1, wherein performing the first search of the information source comprises performing a semantic search based on the first topic.
However, Zhang teaches performing the first search of the information source comprises performing a semantic search based on the first topic [Column 2, lines 4-21" A technique to enable a user to verify the accuracy of a query response provided by an LLM is disclosed. The technique includes receiving a query comprised of one or more words from a client device. In some embodiments, the query includes a plurality of words and the words included in the query are rephrased to present the query in an improved format for an LLM prompt. A prompt is generated for an LLM. The prompt includes a request for the LLM to generate a plurality of subtopics related to the query and a corresponding plurality of keywords for each of the plurality of subtopics. For example, the prompt may include a request for the LLM to generate 3 different subtopics related to the query and 15 keywords for each of the 3 different subtopics. The prompt may be modified by the user via the client device before being sent to the LLM. For example, the user may modify the prompt to generate 4 different subtopics related to the query instead of 3 different subtopics" where rephrasing a query and expanding them to related subtopics and keywords demonstrates a semantic search. By generating context aware terms rather than relying solely on literal text is a form of semantic searching].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings Maschmeyer with the teaching of Zhang because the semantic search techniques would improve the relevance of generated outputs. Using refined prompts as input to the semantic search process would thereby retrieve more contextually relevant information based on the underlying meaning of the prompt rather than simple matching of words. This combination predictably improves accuracy and contextual relevance of generated content.
Regarding claim 12, Maschmeyer teaches a non-transitory computer-readable storage medium
storing executable instructions, the executable instructions when executed by one or more processors of a system causing the system to perform steps comprising: [0026 “In another aspect, the present application discloses a non-transitory, processor-readable medium storing processor-executable instructions that, when executed by a processor, may cause the processor to: obtain at least one output of a generative model based on input of a first text prompt; present the at least one output via a user interface;]
iteratively generating one or more prompts for input into a generative model that instruct the generative model to generate at least a portion of a content item,
[0034 “Each revised prompt produces a new set of outputs, and a user may repeatedly revise input prompts until arriving at a preferred content output. This approach of iteratively generating new outputs may limit the user's ability to track historical outputs and preferred content data effectively.”];
[0102 “This process of iteratively modifying input prompts to the generative model and producing new content outputs may be continued until the user either flags one of the outputs as the final content output or manually terminates the process.”];
[0078 "An input prompt supplied by a user is received from the user device 120 via a network 150. In the context of content generation, the input prompt may be or include a command/request to generate content of a specific type"]; [0079 "In some implementations, a user-supplied prompt may be processed by the system 100 to generate a suitable prompt for inputting to the generative AI model 112. In particular, a user-supplied prompt may be modified to produce the input prompt. For example, an input prompt may be generated by adjusting a user command or request to generate new content, in accordance with one or more defined constraints associated with the generative AI model 112. The constraints may, for example, relate to restrictions ( e.g., character limits, content filters, etc.) on acceptable prompts for the generative AI model”]
outputting the first set of additional topics for display by a user interface; [0026
"obtain at least one output of a generative model based on input of a first text prompt; present the at least one output via a user interface; receive, via the user interface, user selection of a desired portion of the at least one output"]; [0036 "A generative model is initially requested to produce multiple outputs, each from the same text prompt. Upon generation, the multiple outputs are presented to the user via a graphical user interface. The outputs may be displayed concurrently ( e.g., side-by-side) on the GUI or they may be viewed separately (e.g., sequentially) by navigating using the GUI"]; [0031 "The generative AI trained on such a data set is then able to take an input prompt in text form, which may include suggested topics, features, styles or other suggestions, and provide an output image that reflects, at least to some degree, the input prompt" where the multiple outputs are additional topics displayed]
receiving a user selection, via the user interface, that identifies at least one second topic selected from the first set of additional topics; [0026" obtain at least one output of a generative model based on input of a first text prompt; present the at least one output via a user interface; receive, via the user interface, user selection of a desired portion of the at least one output; modify the first text prompt based on the user selection to obtain a second text prompt; and provide the second text prompt as input to the generative model for obtaining a second output" where at least output is the first set of additional topics]
and generating the one or more prompts based on at least the first topic and the at least one
second topic wherein the one or more prompts instruct the generative model to generate the content item based on the first topic and the at least one second topic and return a generated content item, and
[0026"modify the first text prompt based on the user selection to obtain a second text prompt; and provide the second text prompt as input to the generative model for obtaining a second output" where modifying means using the first text prompt and modifying it based on the user selection to a generate a second prompt]; [0079 "In some implementations, a user-supplied prompt may be processed by the system 100 to generate a suitable prompt for inputting to the generative AI model 112. In particular, a user-supplied prompt may be modified to produce the input prompt. For example, an input prompt may be generated by adjusting a user command or request to generate new content, in accordance with one or more defined constraints associated with the generative AI model 112. The constraints may, for example, relate to restrictions ( e.g., character limits, content filters, etc.) on acceptable prompts for the generative AI model" where a second text prompt can be used to generate a second suitable prompt for the AI model]; [0102 "In operation 210, the computing system provides the second text prompt as input to the generative model for obtaining one or more second outputs. The second output comprises new content that is produced by the generative model in a subsequent iteration of content generation based on the second text prompt. In particular, the second output may be an output of the generative model that includes representations of user-selected portions from the outputs of preceding iteration( s) of content generation. The second output data may be presented to the user via the user Interface"]
outputting the generated content item to the user interface. [0026 “The second output data may be presented to the user via the user Interface"]
However, Maschmeyer does not teach generating the one or more prompts comprises: performing a first search of an information source using at least a portion of a first topic, wherein the first search identifies a first set of additional topics related to the first topic;
But Zhang teaches performing a first search of an information source using at least a portion of a first topic, wherein the first search identifies a first set of additional topics related to the first topic;
first topic and one or more of the first set of additional topics
[Column 2, lines 4-14 " A technique to enable a user to verify the accuracy of a query response provided by an LLM is disclosed. The technique includes receiving a query comprised of one or more words from a client device. In some embodiments, the query includes a plurality of words and the words included in the query are rephrased to present the query in an improved format for an LLM prompt. A prompt is generated for an LLM. The prompt includes a request for the LLM to generate a plurality of subtopics related to the query and a corresponding plurality of keywords for each of the plurality 15 of subtopics"]; [ Column 2, lines 27-30 " One or more search engines are utilized to perform a plurality of searches, in parallel, utilizing the plurality of subtopics and the corresponding plurality of keywords received from the LLM" where the first topic is in the form of the query and then the prompt request for the LLM (search request via search engine) to generate a plurality of subtopics which are the additional topics related to the first topic].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings Maschmeyer with the teaching of Zhang
because using prompts generated as search queries to retrieve information from external data sources and incorporating the retrieved information into the generated outputs would improve the completeness and relevance of the outputs. This combination represents the predictable use of known search and content generation techniques to enhance the quality, accuracy and completeness of generated content.
Maschmeyer in view of Zhang do not teach wherein iterative generation of the one or more prompts is configured to be terminated responsive to a determination that a similarity between the first topic and one or more of the first set of additional topics identified exceeds a predetermined threshold; and
But Thatcher teaches wherein iterative generation of the one or more prompts is configured to be terminated responsive to a determination that a similarity between the first topic and one or more of the first set of additional topics identified
[Column 7, lines 3-5 “The iterative search query expansion method is explained in further detail below with respect to FIGS. 2 and 3.”];
[Column 8, lines 42- “According to at least one other embodiment, the stopping criterion may be met when the identified updated enrichment terms from the most recent previous search query match the
enrichment terms of the new search query. For example, if five enrichment terms T 1 -T 5 were identified in the initial set of documents, the first iteration may include the search terms
of the initial search query Q0 and the enrichment terms T 1 -Ts- Continuing the example, if the first iteration retrieves a set of documents where two additional enrichment terms are identified, e.g., T6- T7, then the second iteration may include the search terms of the initial search query Q0 and
the enrichment terms T6-T7 . This process may continue until no additional enrichment terms are identified. For example, if the search query submitted to the IR system containing the
initial search query Q0 and enrichment terms T6-T7 generates the same enrichment terms, i.e., enrichment terms T6-T7, then the stopping criterion may be met.”];
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings Maschmeyer in view of Zhang with Thatcher, so that further topic expansion stops when successive searches identify no additional enrichment terms. This would avoid repeated searches yielding the same topics and reduce unnecessary processing.
Maschmeyer in view of Zhang in view of Thatcher do not teach
exceeds a predetermined threshold
But XU, BO teaches exceeds a predetermined threshold
[Brief description of the drawings “(3)By setting a similarity threshold, when the cosine similarity is greater than the set similarity threshold, then the matching ends. For example, we can calculate the semantic similarity between the following word pairs:
Cosine (WE "Money", WE "buy") = 0.79
Cosine (WE Money, WE Cash) = 0.93
Cosine (WE "Money", WE "Make Money") = 0.81
Cosine (WE Money, WE Banknote) = 0.95
If you set a threshold of 0.9, just get a similarity, 'money' and 'cash' do not follow similar tags. Because has met the requirements, improve efficiency.“]
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings Maschmeyer in view of Zhang in view of Thatcher with XU, BO’s semantic similarity comparison to the original topic and search identified additional topics, and terminating further prompt generation when that similarity exceeds a preset threshold. This would avoid generating further prompts once a sufficiently related topic has been identified, thereby reducing unnecessary comparisons and processing.
Regarding claim 14, Maschmeyer teaches the non-transitory computer-readable storage medium of claim 12, wherein generating the one or more prompts comprises: generating a first prompt that includes the first topic and the at least one second topic; and sending the first prompt to the generative model to cause the generative model to generate the content item based on the first prompt.
Claim 14 is rejected for the same reasons as claim 5.
Regarding claim 15, the non-transitory computer-readable storage medium of claim 12, wherein the instructions when executed further cause the system to: : receive, at a chat window of the user interface, a user instruction to generate the content item; wherein outputting the first set of additional topics for display by the user interface comprises: displaying, for each of additional topics in the first set of additional topics, a selectable option in the chat window; wherein receiving the user selection of the at least one second topic comprises receiving a user input at the selectable option in the chat window that corresponds to the at least one second topic.
Claim 15 is rejected for the same reasons as claim 6.
Regarding claim 17, Maschmeyer teaches a system comprising: one or more processors; and one or more non-transitory computer-readable storage media storing executable instructions, the executable instructions when executed by the one or more processors causing the system to perform steps comprising: [0026 “In another aspect, the present application discloses a non-transitory, processor-readable medium storing processor-executable instructions that, when executed by a processor, may cause the processor to: obtain at least one output of a generative model based on input of a first text prompt; present the at least one output via a user interface;”]
iteratively generating one or more prompts for input into a generative model, wherein the one or more prompts instruct the generative model to generate a content item return a generated content item, and wherein generating the one or more prompts comprises: receiving a user input identifying a first topic;
[0034 “Each revised prompt produces a new set of outputs, and a user may repeatedly revise input prompts until arriving at a preferred content output. This approach of iteratively generating new outputs may limit the user's ability to track historical outputs and preferred content data effectively.”];
[0102 “This process of iteratively modifying input prompts to the generative model and producing new content outputs may be continued until the user either flags one of the outputs as the final content output or manually terminates the process.”];
[0078 "An input prompt supplied by a user is received from the user device 120 via a network 150. In the context of content generation, the input prompt may be or include a command/request to generate content of a specific type"]; [0079 "In some implementations, a user-supplied prompt may be processed by the system 100 to generate a suitable prompt for inputting to the generative AI model 112. In particular, a user-supplied prompt may be modified to produce the input prompt. For example, an input prompt may be generated by adjusting a user command or request to generate new content, in accordance with one or more defined constraints associated with the generative AI model 112. The constraints may, for example, relate to restrictions ( e.g., character limits, content filters, etc.) on acceptable prompts for the generative AI model”]
outputting the first set of additional topics for display by the a user interface; [0026
"obtain at least one output of a generative model based on input of a first text prompt; present the at least one output via a user interface; receive, via the user interface, user selection of a desired portion of the at least one output"]; [0036 "A generative model is initially requested to produce multiple outputs, each from the same text prompt. Upon generation, the multiple outputs are presented to the user via a graphical user interface. The outputs may be displayed concurrently ( e.g., side-by-side) on the GUI or they may be viewed separately (e.g., sequentially) by navigating using the GUI"]; [0031 "The generative AI trained on such a data set is then able to take an input prompt in text form, which may include suggested topics, features, styles or other suggestions, and provide an output image that reflects, at least to some degree, the input prompt" where the multiple outputs are additional topics displayed]
receiving a user selection that identifies at least one second topic selected from the first set of additional topics; and [0026" obtain at least one output of a generative model based on input of a first text prompt; present the at least one output via a user interface; receive, via the user interface, user selection of a desired portion of the at least one output; modify the first text prompt based on the user selection to obtain a second text prompt; and provide the second text prompt as input to the generative model for obtaining a second output" where at least output is the first set of additional topics]
and generating the one or more prompts based on at least the first topic and the at least one second topic;
and outputting the generated content item to the user interface [0026"modify the first text prompt based on the user selection to obtain a second text prompt; and provide the second text prompt as input to the generative model for obtaining a second output" where modifying means using the first text prompt and modifying it based on the user selection to a generate a second prompt]; [0079 "In some implementations, a user-supplied prompt may be processed by the system 100 to generate a suitable prompt for inputting to the generative AI model 112. In particular, a user-supplied prompt may be modified to produce the input prompt. For example, an input prompt may be generated by adjusting a user command or request to generate new content, in accordance with one or more defined constraints associated with the generative AI model 112. The constraints may, for example, relate to restrictions ( e.g., character limits, content filters, etc.) on acceptable prompts for the generative AI model" where a second text prompt can be used to generate a second suitable prompt for the AI model]; [0102 "In operation 210, the computing system provides the second text prompt as input to the generative model for obtaining one or more second outputs. The second output comprises new content that is produced by the generative model in a subsequent iteration of content generation based on the second text prompt. In particular, the second output may be an output of the generative model that includes representations of user-selected portions from the outputs of preceding iteration( s) of content generation. The second output data may be presented to the user via the user Interface"]
However, Maschmeyer does not teach performing a first search of an information source using at least a portion of the first topic, wherein the first search returns a first set of additional topics related to the first topic; first topic and one or more of the first set of additional topics
But Zhang teaches performing a first search of an information source using at least a portion of the first topic, wherein the first search returns a first set of additional topics related to the first topic; first topic and one or more of the first set of additional topics
[Column 2, lines 4-14 " A technique to enable a user to verify the accuracy of a query response provided by an LLM is disclosed. The technique includes receiving a query comprised of one or more words from a client device. In some embodiments, the query includes a plurality of words and the words included in the query are rephrased to present the query in an improved format for an LLM prompt. A prompt is generated for an LLM. The prompt includes a request for the LLM to generate a plurality of subtopics related to the query and a corresponding plurality of keywords for each of the plurality 15 of subtopics"]; [ Column 2, lines 27-30 " One or more search engines are utilized to perform a plurality of searches, in parallel, utilizing the plurality of subtopics and the corresponding plurality of keywords received from the LLM" where the first topic is in the form of the query and then the prompt request for the LLM (search request via search engine) to generate a plurality of subtopics which are the additional topics related to the first topic].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings Maschmeyer with the teaching of Zhang
because using prompts generated as search queries to retrieve information from external data sources and incorporating the retrieved information into the generated outputs would improve the completeness and relevance of the outputs. This combination represents the predictable use of known search and content generation techniques to enhance the quality, accuracy and completeness of generated content.
Maschmeyer in view of Zhang do not teach terminating iterative generation of the one or more prompts responsive to determining that a similarity between the first topic and one or more of the first set of additional topics identified exceeds a predetermined threshold; and
But Thatcher teaches terminating iterative generation of the one or more prompts responsive to determining that a similarity between the first topic and one or more of the first set of additional topics identified
[Column 7, lines 3-5 “The iterative search query expansion method is explained in further detail below with respect to FIGS. 2 and 3.”];
[Column 8, lines 42- “According to at least one other embodiment, the stopping criterion may be met when the identified updated enrichment terms from the most recent previous search query match the
enrichment terms of the new search query. For example, if five enrichment terms T 1 -T 5 were identified in the initial set of documents, the first iteration may include the search terms
of the initial search query Q0 and the enrichment terms T 1 -Ts- Continuing the example, if the first iteration retrieves a set of documents where two additional enrichment terms are identified, e.g., T6- T7, then the second iteration may include the search terms of the initial search query Q0 and
the enrichment terms T6-T7 . This process may continue until no additional enrichment terms are identified. For example, if the search query submitted to the IR system containing the
initial search query Q0 and enrichment terms T6-T7 generates the same enrichment terms, i.e., enrichment terms T6-T7, then the stopping criterion may be met.”];
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings Maschmeyer in view of Zhang with Thatcher, so that further topic expansion stops when successive searches identify no additional enrichment terms. This would avoid repeated searches yielding the same topics and reduce unnecessary processing.
Maschmeyer in view of Zhang in view of Thatcher do not teach
exceeds a predetermined threshold
But XU, BO teaches exceeds a predetermined threshold
[Brief description of the drawings “(3)By setting a similarity threshold, when the cosine similarity is greater than the set similarity threshold, then the matching ends. For example, we can calculate the semantic similarity between the following word pairs:
Cosine (WE "Money", WE "buy") = 0.79
Cosine (WE Money, WE Cash) = 0.93
Cosine (WE "Money", WE "Make Money") = 0.81
Cosine (WE Money, WE Banknote) = 0.95
If you set a threshold of 0.9, just get a similarity, 'money' and 'cash' do not follow similar tags. Because has met the requirements, improve efficiency.“]
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings Maschmeyer in view of Zhang in view of Thatcher with XU, BO’s semantic similarity comparison to the original topic and search identified additional topics, and terminating further prompt generation when that similarity exceeds a preset threshold. This would avoid generating further prompts once a sufficiently related topic has been identified, thereby reducing unnecessary comparisons and processing.
Regarding claim 19, Maschmeyer teaches the system of claim 17, wherein generating the one or more prompts comprises: generating a first prompt that includes the first topic and the at least one second topic; and sending the first prompt to the generative model to cause the generative model to generate the content item based on the first prompt.
Claim 19 is rejected for the same reasons as claim 5.
Claim [2, 3, 4, 9, 13, 18 ] are rejected under 35 U.S.C. 103 as being unpatentable over Maschmeyer (US 2024/0320444 Al) in view of Zhang (US 12,019,663 Bl) and in view of Thatcher (US 11720554 B2 ) and in further view of XU BO (CN107247709A) and in further view of Dolan (US-20220414320-A1).
Regarding claim 2, Maschmeyer in view of Zhang in view of Thatcher in view of XU BO teaches
the method of claim 1, wherein generating the one or more prompts comprises: generating a first prompt that includes the first topic;
Maschmeyer teaches [0092 "Once the generative model is trained and deployed, the computing system obtains at least one output of the generative model based on input of a first text prompt, in operation 202. The first text prompt is an initial prompt that is supplied by the user to the generative model. In particular, the first text prompt may be or include a command/request to generate new content. For example, the first text prompt may include a description of content that is requested to be generated. Additionally, or alternatively, the first text prompt may indicate certain features, properties, or requirements for the requested content. The first text prompt may be provided directly by a user, or it may be generated by the computing system based on user-inputted data (e.g., input text, image upload, etc.”] ;[0031 "The generative AI trained on such a data set is then able to take an input prompt in text form, which may include suggested topics, features, styles or other suggestions, and provide an output image that reflects, at least to some degree, the input prompt" where the new content comprises about the first topic based on user input]
sending the first prompt to the generative model to cause the generative model to
generate a first draft of the generated content item; [0092 "The first text prompt is an initial prompt that is supplied by the user to the generative model. In particular, the first text prompt may be or include a command/request to generate new content"]
outputting the first draft of the generated content item to the user interface; [0094 "The
computing system presents the at least one output of the generative model via a user interface, in operation 204. More particularly, the at least one output may be displayed on a graphical user interface associated with a content management ( or related) system. The graphical user interface may be provided by the computing system to a user device for displaying thereon"]
after outputting the first draft of the generated content item, receiving the user selection of the
at least one second topic; [0095 "The outputs may be displayed one-by-one or by suitable groupings on the graphical user interface. A user may navigate the graphical user interface on their device in order to access the contents of the at least one output. For example, a user may interact with one or more navigational user interface elements on a graphical user interface to browse through a plurality of outputs of the generative model" where the plurality of outputs can be a second topic”]; [0096 "The user interface may allow users to interact with the at least one output. In particular, users may select, edit, delete, replace, or otherwise manipulate one or more portions of the outputs that are presented in the user interface"]
and generating a second prompt that includes the at least one second topic
modifies the first text prompt based on the user selection to obtain a second text prompt, in operation 208. The second text prompt may be an input prompt to the generative model for a subsequent iteration of content generation. That is, the generative model may produce new content based on the second text prompt. The first text prompt, e.g., the initial prompt supplied by the user, may be modified so that the second text prompt reflects the user's preferences as indicated by the user-selected portions from the at least one output"] ;[0079 "In some implementations, a user-supplied prompt may be processed by the system 100 to generate a suitable prompt for inputting to the generative AI model 112. In particular, a user-supplied prompt may be modified to produce
the input prompt. For example, an input prompt may be generated by adjusting a user command or request to generate new content, in accordance with one or more defined constraints associated with the generative AI model 112. The constraints may, for example, relate to restrictions ( e.g., character limits, content filters, etc.) on acceptable prompts for the generative AI model" where a second text prompt can be used to generate a second suitable prompt for the AI model]
However, Maschmeyer in view of Zhang in view of Thatcher in view of XU BO does not teach that instructs the generative model to modify the first draft of the generated content item based on the at least one second topic to produce a second draft of the generated content item.
But Dolan teaches instructs the generative model to modify the first draft of the generated content item based on the at least one second topic to produce a second draft of the generated content item [0024 "In other examples, user input may be received in the form of one or more revisions to the processed content. As an example, a user may revise a sentence or add a paragraph, such that the generative model may be used to update one or more subparts of the processed content accordingly. For instance, a user may change a city or add additional detail with respect to a range of dates described by the document, such that the generative model may produce updated processed content having additional or different detail based on such additions or changes. In such instances, the generative model may use preceding content and subsequent content as context with which to produce the updated processed content"].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings Maschmeyer in view Zhang in view of Thatcher in view of XU BO with the teaching of Dolan because using the second prompt generated as input to the refinement process of Dolan, thereby modifying the first generated content based on the second prompt to produce second draft would be a predictable use of known prompt refinement and content updating techniques to iteratively improve generated outputs.
Regarding claim 3, Maschmeyer teaches the method of claim 2, further comprising: outputting the second draft of the generated content item to the user interface; [0102 "In operation 210, the computing system provides the second text prompt as input to the generative model for obtaining one or more second outputs. The second output comprises new content that is produced by the generative model in a subsequent iteration of content generation based on the second text prompt. In particular, the second output may be an output of the generative model that includes representations of user-selected portions from the outputs of preceding iteration( s) of content generation. The second output data may be presented to the user via the user Interface"]
outputting the second set of additional topics for display by the user interface; [0102 "In operation 210, the computing system provides the second text prompt as input to the generative model for obtaining one or more second outputs. The second output comprises new content that is produced by the generative model in a subsequent iteration of content generation based on the second text prompt. In particular, the second output may be an output of the generative model that includes representations of user-selected portions from the outputs of preceding iteration( s) of content generation. The second output data may be presented to the user via the user interface" where the subsequent iteration of content generation is the second set of additional topics”].
receiving a user selection, via the user interface, of at least one third topic selected from the second set of additional topics; [0102" In some implementations, the computing system may prompt the user to confirm the second output data as the final content output or to make further selections of portions from the second output(s). This process of iteratively modifying input prompts to the generative model and producing new content outputs may be continued until the user either flags one of the outputs as the final content output or manually terminates the process" where the iterative process can include a third topic selected]
generating a third prompt that includes the at least one third topic and that instructs the generative model to modify the second draft of the generated content item based on the at least one third topic [0102" This process of iteratively modifying input prompts to the generative model and producing new content outputs may be continued until the user either flags one of the outputs as the final content output or manually terminates the process" where the iterative process can include the third prompt and the content items is based on the third topic]; [0079 "In some implementations, a user-supplied prompt may be processed by the system 100 to generate a suitable prompt for inputting to the generative AI model 112. In particular, a user-supplied prompt may be modified to produce
the input prompt. For example, an input prompt may be generated by adjusting a user command or request to generate new content, in accordance with one or more defined constraints associated with the generative AI model 112. The constraints may, for example, relate to restrictions ( e.g., character limits, content filters, etc.) on acceptable prompts for the generative AI model" where a third prompt (iterative process) can be used to generate a new content(second draft of the content)].
However, Maschmeyer does not teach performing a second search of the information source using at least a portion of the at least one second topic, wherein the second search identifies a second set of additional topics related to the at least one second topic;
But Zhang teaches performing a second search of the information source using at least a portion of the at least one second topic, wherein the second search identifies a second set of additional topics related to the at least one second topic; [column 2, lines 27-30 "One or more search engines are utilized to perform a plurality of searches, in parallel, utilizing the plurality of subtopics and the corresponding plurality of keywords received from the LLM]; [column 2, lines 42-45 " The plurality of search engine responses is filtered to generate a corresponding subset of search engine responses for each of the subtopics based on the number of times keywords are included in a search engine response" where the corresponding subset of search engine responses can be a second set of additional topics].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings Maschmeyer with the teaching of Zhang because using the prompts generated as search queries to retrieve information from external data sources and incorporate the retrieved information into the generated outputs would improve the completeness and relevancy of generated outputs. This combination represents the predictable use of known search and content generation techniques to enhance the quality, accuracy and completeness of generated content.
Regarding claim 4, Maschmeyer in view of Zhang in view of Thatcher in view of XU BO teaches the method of claim 2, further comprising: outputting the second draft of the generated content item to the user interface; [0102 "In operation 210, the computing system provides the second text prompt as input to the generative model for obtaining one or more second outputs. The second output comprises new content that is produced by the generative model in a subsequent iteration of content generation based on the second text prompt. In particular, the second output may be an output of the generative model that includes representations of user-selected portions from the outputs of preceding iteration( s) of content generation. The second output data may be presented to the user via the user Interface"]
receiving a user input to deselect the at least one second topic; [0122 "In operation 416, responsive to receiving user confirmation, the computing system provides the second text prompt as input to the generative model for obtaining a second output. Once the user has finished editing, the user may provide an indication for confirming that desired changes have been made to selected portions of the at least one output. The computing system may then request for the generative model to produce a second output based on the second text prompt"]; [0128 "Further, a user can edit one or more of the selected portions in the sandbox 610. By editing a selected portion in the sandbox 610, the user can indicate their preference of what the final image output will look like" where editing a selected portion can include deselecting the portion that user does not want to include]; [0101 "Additionally, or alternatively, the supplementary text may comprise text describing information that is to be excluded in subsequent outputs. More particularly, the second text prompt may describe portions of the at least one output that are not selected by the user as content to exclude in subsequent iterations of content generation. This description of exclusionary information may be appended to the first text prompt to generate the second text prompt" where not selecting can be considered deselecting a portion that user does not want to include.]
and generating a third prompt that instructs the generative model user's selections across multiple content outputs. In particular, the sandbox area may be gradually populated as the user makes selections of portions from different content outputs that are displayed in the output display area. In this way, when the user is finished making their selections, the totality of the selected portions may be displayed in the sandbox area”]; [0086 "The content generation engine 114 may be configured to send a final content output over the network 150 to the user device 120. If a user is satisfied with one of the outputs of the generative AI model 112, the user may flag the output as the final content output. The generative AI model112 may iteratively produce new outputs based on modified prompts provided by the content generation engine 114, and the user may select an output from one of the iterations as the final content output. The content data of the final content output may then be transmitted to the user device 120 for display thereon”]; [0128 "Further, a user can edit one or more of the selected portions in the sandbox 610. By editing a selected portion in the sandbox 610, the user can indicate their preference of what the final image output will look like" where editing a selected portion can include deselecting the portion that user does not want to include in the new prompt generation. The iterative process shows additional prompts can be generated including a third prompt].
However, Maschmeyer in view of Zhang in view of Thatcher in view of XU BO do not teach modify the second draft of the generated content item.
But Dolan teaches modify the second draft of the generated content item [0024 "In other examples, user input may be received in the form of one or more revisions to the processed content. As an example, a user may revise a sentence or add a paragraph, such that the generative model may be used to update one or more subparts of the processed content accordingly. For instance, a user may change a city or add additional detail with respect to a range of dates described by the document, such that the generative model may produce updated processed content having additional or different detail based on such additions or changes. In such instances, the generative model may use preceding content and subsequent content as context with which to produce the updated processed content"]; [0028 “As a result, iterative document engine 112 may utilize content generator 114 to produce processed content and updated generative content accordingly" where the iterative process can be a modification of the second draft of the content item].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings Maschmeyer in view Zhang in view of Thatcher in view of XU BO with the teaching of Dolan because using modified prompts (including deselecting) as additional input to the refinement process of Dolan would help with modification of the previous generated second draft. This represent a predictable use of known iterative prompt refinement and content updating techniques to provide user controlled revisions of generated content.
Regarding claim 9, Maschmeyer in view of Zhang in view of Thatcher in view of XU BO teaches the method of claim 1 wherein generating the one or more prompts comprises generating at least a first prompt based on the at least one second topic, and wherein the method further comprises: after generating the first prompt, receiving a user input modifying the at least one second topic to obtain a modified second topic; [0121 “In some implementations, the computing system presents a preview of a final content output based on the user selection and editing input (operation 414). That is, a preview of a subsequent output of the generative model that may be produced based on an input prompt that reflects the user selection and the user edits may be presented to the user "where the input prompt is the first prompt generated]; [0125 "The user can indicate preference for a certain portion of a generated output by selecting the portion in the output display area 520. For example, the user can select/highlight text within the first text output 510a. The selected text 509a can be stored for inclusion in a final text output by selecting the "Keep" button 506b. The stored data for preferred text portions may include the actual selected text, relative location of the selection, edits to the selected text (ifany), and the like. By generating new product descriptions (i.e., 510a, 510b, etc.) and selecting preferred text portions(i.e., 509a, 509b, etc.) from each of those descriptions, the user can customize what the final text output will look like" where the user can modify the output (second topic)]
and generating a second prompt based on the modified second topic, wherein the second prompt instructs the generative model selected text portions from previously generated descriptions. A second input prompt may be obtained by modifying the first input prompt, and the second input prompt is provided to the generative AI model as part of a request to generated the
final text output 510c. The second input prompt may include, at least, a description of the user selections from and/or edits of the previously generated descriptions "where the edits/modifications based on user selection is used to generate a second prompt].
However, Maschmeyer in view of Zhang in view of Thatcher in view of XU BO do not teach to modify the content item based on the modified second topic.
But Dolan does teach to modify the content item based on the modified second topic [0024 "In other examples, user input may be received in the form of one or more revisions to the processed content. As an example, a user may revise a sentence or add a paragraph, such that the generative model may be used to update one or more subparts of the processed content accordingly. For instance, a user may change a city or add additional detail with respect to a range of dates described by the document, such that the generative model may produce updated processed content having additional or different detail based on such additions or changes. In such instances, the generative model may use preceding content and subsequent content as context with which to produce the updated processed content"].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings Maschmeyer in view Zhang in view of Thatcher in view of XU BO with the teaching of Dolan because modifying content based on additional input or feedback to produce an updated version would be helpful in the context of the generated output. It represents a predictable use of known prompt refinement and content updating techniques to iteratively improve generated outputs.
Regarding claim 13, Maschmeyer in view of Zhang in view of Thatcher in view of XU BO and in
view of Dolan teaches the method of claim 1, the non-transitory computer-readable storage medium of claim 12, wherein generating the one or more prompts comprises: generating a first prompt that includes the first topic; sending the first prompt to the generative model to cause the generative model to generate a first draft of the generated content item; outputting the first draft of the generated content item to the user interface; after outputting the first draft of the generated content item, receiving the user selection that identifies the at least one second topic; and generating a second prompt that includes the at least one second topic and that instructs the generative model to modify the first draft of the generated content item based on the at least one second topic to produce a second draft of the generated content item.
Claim 13 is rejected for the same reasons as claim 2.
Regarding claim 18, Maschmeyer in view of Zhang in view of Thatcher in view of XU BO and in view of Dolan teach the system of claim 17, wherein generating the one or more prompts comprises: generating a first prompt that includes the first topic; sending the first prompt to the generative model to cause the generative model to generate a first draft of the generated content item; outputting the first draft of the generated content item to the user interface; after outputting the first draft of the generated content item, receiving the user selection of the at least one second topic; and generating a second prompt that includes the at least one second topic and that instructs the generative model to modify the first draft of the generated content item based on the at least one second topic to produce a second draft of the generated content item.
Claim 18 is rejected for the same reasons as claim 2.
Claim [7, 16, 20 ] are rejected under 35 U.S.C. 103 as being unpatentable over Maschmeyer (US 2024/0320444 Al) in view of Zhang (US 12,019,663 Bl) and in view of Thatcher (US 11720554 B2 ) and in in view of XU BO (CN107247709A) and in further view of Sabharwal (US 2022/0300716 Al) and in further view of Burnett (AU-2014101081-A4).
Regarding claim 7, Maschmeyer in view of Zhang in view of Thatcher view of XU BO teaches the
method of claim 1, wherein outputting the first set of additional topics for display by the user interface comprises: Maschmeyer teaches [0083 "The content outputs may be displayed in an output display area within the graphical user interface. A user may view the content outputs, either one-by-one or by suitable groupings. For example, the outputs from an iteration of content generation may be displayed one at a time, requiring the user to navigate through the outputs, or they may be displayed concurrently (e.g., displayed side-by-side) in the output display area”]; [0084 "The graphical user interface may additionally enable users to interact with the content outputs. In particular, users may input selections of portions from different content outputs using the graphical user interface" where the different outputs is additional topics].
However, Maschmeyer in view of Zhang in view of Thatcher view of XU BO do not teach generating for display by the user interface, a tree diagram that includes a plurality of nodes, wherein a first in the plurality of nodes corresponds to the first topic and a set of second nodes correspond respectively to the additional topics in the first set of additional topics; and wherein the tree diagram visually represents a relationship between the first topic and the first set of additional topics; wherein receiving the user selection of the at least one second topic comprises receiving a user input at one of the set of second nodes in the tree diagram.
But Sabharwal et al teaches generating for display by the user interface, a tree diagram that includes a plurality of nodes, [0072 “The AI based hierarchical multi-conversation system 102 may be configured to create the hierarchical tree 300A that includes a root node, one or more child nodes (also referred as internal nodes) and one or more leaf child nodes using a first pre-trained machine learning model to identify hierarchy for each of topic or sub-topic associated with the user query as illustrated in FIG. 3A”]; [0031 “The external device 106 may include suitable logic, circuitry, interfaces, and/or code that may be configured to facilitate communication of the one or more users, such as the user 112, with the AI based hierarchical multi-conversation system 102 and/or the live agent system 108”where the Al based hierarchical system( tree diagram) can allow communication with user via an interface]
wherein a first in the plurality of nodes corresponds to the first topic and a set of second nodes correspond respectively to the additional topics in the first set of additional topics; [0055 "The machine learning module 216 may include suitable logic, circuitry, and/or interfaces that may be configured
to create a hierarchical tree that includes a root node and at least one child node using a first pre-trained machine learning model. The first pre-trained machine learning model may correspond to a classification machine learning model, such as, but not limited to, Long-Short-Term Memory (LSTM) based models and Gated Recurring Units (GRU) based models. The at least one child node may be associated with match data corresponding to a topic related to the user query. The at least one leaf child node may be associated with match data corresponding to a sub-topic related to the user query" where root node, child node and leaf node shows the plurality of nodes related to first topic(root/child nodes-match data corresponding to user query input) and second nodes related to additional topics (leaf child node -match data corresponding to sub-topic)]
and wherein the tree diagram visually represents a relationship between the first topic and the first set of additional topics; [0131 "At 1002, a relationship between a first topic associated with a first child node and a second topic associated with a second child node may be generated to identify the topic hierarchy, using a second pre-trained machine learning model. In accordance with an embodiment, the machine learning module 216 of the AI based hierarchical multi conversation
system 102 may be configured to generate the relationship between the first topic associated with the first child node and the second topic associated with the second child node to identify the topic hierarchy, using the second pre-trained machine learning model"]
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings Maschmeyer in view Zhang in view of Thatcher view of XU BO with the teachings of Sabharwal because incorporating the hierarchical tree interface into the iterative prompt-generation and refinement framework would improve user control and relevance of generated content. The combination represents the predictable use of structured navigation interface, which improves usability, precision of user intent capture, and relevance of generated outputs.
However, Maschmeyer in view of Zhang in view of Thatcher view of XU BO and in view of Sabharwal do not teach wherein receiving the user selection of the at least one second topic comprises receiving a user input at one of the set of second nodes in the tree diagram.
But Burnett teaches this wherein receiving the user selection of the at least one second topic comprises receiving a user input at one of the set of second nodes in the tree diagram [Page 4, 0013 "The tree is formed from a classification of metadata associated with items, and includes one or more value nodes, attribute nodes and group nodes. The method further includes detecting user selection of one or more nodes of the interactive tree. Subsequently, the method proceeds to convert the selected nodes into a Boolean search string based on the corresponding states of the selected nodes, provide the Boolean search string to a search engine to retrieve search results from the items, and display the search results on the GUI.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings Maschmeyer in view Zhang in view of Thatcher view of XU BO and in view Sabharwal with Burnett because using node selection techniques into the hierarchical system would improve user control and accuracy in navigating topic hierarchies. Incorporating explicit selection of nodes allows user to precisely indicate the intended topic within the hierarchal structure.
Regarding claim 16, Maschmeyer in view Zhang in view of Thatcher view of XU BO and in view Sabharwal in view of Burnett teach the non-transitory computer-readable storage medium of claim 12, wherein outputting the first set of additional topics for display by the user interface comprises: generating for display by the user interface, a tree diagram that includes a plurality of nodes, wherein a first in the plurality of nodes corresponds to the first topic and a set of second nodes correspond respectively to the additional topics in the first set of additional topics; and wherein the tree diagram visually represents a relationship between the first topic and the first set of additional topics; wherein receiving the user selection of the at least one second topic comprises receiving a user input at one of the set of second nodes in the tree diagram.
Claim 16 is rejected for the same reasons as claim 7.
Regarding claim 20, Maschmeyer in view Zhang in view of Thatcher view of XU BO and in view Sabharwal in view of Burnett teach the system of claim 17, wherein outputting the first set of additional topics for display by the user interface comprises: generating for display by the user interface, a tree diagram that includes a plurality of nodes, wherein a first in the plurality of nodes corresponds to the first topic and a set of second nodes correspond respectively to the first set of additional topics in the first set of additional topics; and wherein the tree diagram visually represents a relationship between the first topic and the first set of additional topics; wherein receiving the user selection of the at least one second topic comprises receiving a user input at one of the set of second nodes in the tree diagram.
Claim 20 is rejected for the same reason as claim 7.
Claim [10 ] are rejected under 35 U.S.C. 103 as being unpatentable over Maschmeyer (US 2024/0320444 Al) in view of Zhang (US 12,019,663 Bl) view of Thatcher (US 11720554 B2 ) and in further view of XU BO (CN107247709A) and in further view of Kogler (US 10,885,263 B2).
Regarding claim 10, Maschmeyer in view of Zhang in view of Thatcher in view of XU BO
do teach the method of claim 1, further comprising:
However, Maschmeyer in view of Zhang in view of Thatcher in view of XU BO
does not teach accessing a template for the content item based on the instruction to generate the content item; and generating the content item using the template.
But Kogler, et al teaches accessing a template for the content item based on the instruction to generate the content item; and generating the content item using the template
[Column 2, lines 30-40 "The at least one memory may be configured to store a plurality of static templates, a plurality of dynamic templates, and a plurality of instructions that, when executed by
the at least one processor, cause the at least one processor to perform processing. The processing may include receiving raw data. The processing may include determining at least one document formatting feature by analyzing the raw data. The processing may include selecting at least one static
template and at least one dynamic template corresponding to the at least one document formatting feature from the at least 40 one memory."]; [Column 19, lines 27-30 "generating, by the at least one processor, a dynamic document template including content of the selected at least one static template, content of the selected at least one dynamic template, and at least a portion of the raw
Data”… where templates are used for content generation].
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teachings Maschmeyer in view Zhang in view of Thatcher in view of XU BO with the teaching of Kogler because prompts that include instructions corresponding to using a template and directs the generative model to generate content in accordance with the template would result in more organized, consistent, user tailored outputs. This represents predictable use of structured templates to guide prompt based generative models.
Conclusion
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 SHEZA ABDUL AZIZ whose telephone number is (571)272-9610. The examiner can normally be reached Monday-Friday 7:30am-5pm Alternate Fridays off.
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, Daniel Washburn can be reached at (571) 272-5551. 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.
/SHEZA ABDUL AZIZ/Examiner, Art Unit 2657
/DANIEL C WASHBURN/Supervisory Patent Examiner, Art Unit 2657
