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 .
Continued Examination Under 37 CFR 1.114
2. A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 3/30/2026 has been entered.
Accordingly, claims 1-20 are pending in this application. Claims 1, 6, and 16-17 are currently amended.
Response to Arguments
Applicant’s arguments with respect to amended pending claims filed on 3/30/2026 have been fully considered. In view of the claim amendment filed, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made.
Further, regarding the new limitations recited in claims 1, 6, and 16-17, it is submitted that they are properly addressed by the new ground of rejection.
Furthermore, it is also submitted that all limitations in pending claims, including those not specifically argued, are properly addressed. The reason is set forth in the rejections. See claim analysis below for detail.
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 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.
Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over Jaganathan (Jaganathan, Sowmiya,"Personalized text generation-Part 1," www.medium.com, A Medium Corporation, September 9, 2023) in view of Manavoglu (US 20240256757 A1) and Rollwage et al. (US 20240404514 A1).
Regarding Claim 1, Jaganathan discloses a computing system, comprising: one or more processors; and a memory storing program instructions that, when executed by the one or more processors, cause the one or more processors to at least ([Pages2-3]: Using the Retriever, Ranker, Summarization, and Synthesis inputs to fine-tune a model to generate the personalized text… We will collect these documents using a Retriever and Ranking system):
obtain a plurality of user information associated with a user that includes information associated with a first plurality of content items with which the user has interacted ([Page 3]: To generate personalized text, we will use the user’s past documents to understand their unique writing style, phrases, and key elements. We will collect these documents using a Retriever and Ranking system);
extract textual information associated with the plurality of content items ([Page 3]: Once we have the ranked entries, we extract the important information with two techniques i.e., Summarization and Synthesis);
aggregate the textual information to generate a text-based user summary associated with the user ([Page 5]: Finally, once we have all the entries, the ranked entries are concatenated as strings and truncated to 2,500 characters).
However, Jaganathan does not explicitly teach “generate a prompt for a generative model, the prompt including the text-based user summary and the prompt instructing the generative model to generate an output, based at least in part on the text-based user summary, wherein the prompt instructs the generative model to generate a summary of an aspect of the user and a plurality of queries related to the aspect of the user as the output; generate the output by the generative model using the prompt, the output of the generative model including the summary of the aspect of the user and the plurality of queries; determine a second plurality of content items that are responsive to the plurality of queries generated by the generative model; and provide the summary and at least a portion of the second plurality of content items to a client device associated with the user for presentation”.
On the other hand, in the same field of endeavor, Manavoglu teaches
generate a prompt for a generative model (Fig. 1; [0063]-[0064]: For instance, the user of the client computing device 104 can provide consent for their history to be analyzed, such that the user history 122 includes information about the user),
the prompt including the text-based user summary and the prompt instructing the generative model to generate an output, based at least in part on the text-based user summary (Fig. 1; [0063]-[0064]: The generative model 114 receives such user history and generates a semantic representation of interests of the user based upon the user history),
wherein the prompt instructs the generative model to generate a summary of an aspect of the user and a plurality of queries related to the aspect of the user as the output ([0064]-[0067]: the prompt provided to the generative model 114 can be designed to cause the generative model 114 to perform these tasks);
generate the output by the generative model using the prompt, the output of the generative model including the summary of the aspect of the user and the plurality of queries (Fig. 1; [0048]: At 806, the generative model generates output based upon the user input; [0064]-[0065]: the GLM 114 generates a semantic representation of interests of a user based upon history of the user interacting with webpages, supplemental content items, search results, etc… Accordingly, given the user history, the generative model 114 can summarize the history into a few phrases/sentences that summarize the interests of the user);
determine a second plurality of content items that are responsive to the plurality of queries generated by the generative model ([0064]-[0070]: The supplemental content provision system 112 can be provided with this summary and can employ such information when selecting supplemental content items to provide to the user of the client computing device 104… The generative model 114 can be provided with supplemental content items in the supplemental content 120 and assign labels to the supplemental content items that are indicative of relevance to particular queries, keywords, sets of users, and so forth… context from a dialogue between the user and the generative model 114 can be incorporated into a user representation as a near real time signal in connection with identifying a supplemental content item for presentment to the user).
Additionally, Rollwage teaches, provide the summary and at least a portion of the second plurality of content items to a client device associated with the user for presentation (Fig. 6; [0300]: Because these systems are so large, this text completion ability allows them to also engage in other text-related tasks, like summarisation or conversations; Fig. 3; [0383]: In S305, the system response is output to the user; [0400]: In some examples, an assessment or treatment plan may be generated after an interaction with the dialogue system 102 comprising a plurality of dialogue turns. This may then be presented to a therapist, or a patient management system; [0560]: in other examples the input to the language model comprises a processed or filtered summary of previous user inputs).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teaching of Jaganathan to incorporate the teachings of Manavoglu and Rollwage to process the input by the generative model to generate the output, and cause the summary and at least a portion of the second plurality of content items to be presented on a client device associated with the user.
The motivation for doing so would be to allow for more targeted retrieval of content for the user, as recognized by Manavoglu ([0067] of Manavoglu: For instance, the generative model 114, based upon rich contextual information from a dialogue between the user and the generative model 114, can construct an embedding for the user to allow for more targeted and personalized retrieval of supplemental content for the user) and to present items to a user in a personalized manner, as recognized by Rollwage ([0413]-[0415] of Rollwage: Recommender systems are a class of machine learning techniques that broadly aim to present items to a user in a personalised manner).
Regarding Claim 2, the combined teachings of Jaganathan, Manavoglu, and Rollwage disclose the computing system of claim 1.
Rollwage further teaches wherein the summary relates to at least one of an aesthetic, a taste, a preference, a location, an animal, or a color associated with the user ([0556]-[0557]: A further function of the understanding module 31 is to contain general information about the patient like demographics, questionnaire scores, or diagnosis… this specific information is then summarised).
Regarding Claim 3, the combined teachings of Jaganathan, Manavoglu, and Rollwage disclose the computing system of claim 1.
Rollwage further teaches wherein: the first plurality of content items include a plurality of associated weights ([0347]: The training dataset may comprise historical patient utterances (sequences of text) and may be used to learn the weights of the deep learning algorithm); and
the textual information is aggregated in accordance with the plurality of associated weights in generating the text-based user summary ([0376]-[0379]: Each attention module comprises three stored matrices of weights… The outputs from the attention heads are then merged).
Regarding Claim 4, the combined teachings of Jaganathan, Manavoglu, and Rollwage disclose the computing system of claim 3.
Rollwage further teaches wherein the plurality of weights are determined based at least in part on at least one of a recency of one or more of the first plurality of content items, a type of interaction with one or more of the first plurality of content items, or a frequency of interaction with one or more of the first plurality of content items ([0411]: This information may be provided through the history module 37, which may act as a kind of filter, which has access to the entire conversation history of a patient, but only selects the most relevant exchanges. For example, this could apply a “recency” filter, which always outputs the last N user utterances).
Regarding Claim 5, the combined teachings of Jaganathan, Manavoglu, and Rollwage disclose the computing system of claim 1.
Rollwage further teaches, wherein: the summary and the at least the portion of the second plurality of content items are presented according to a predetermined layout ([0398]: The interface 70 may interact with the user at predetermined times, or at predetermined time intervals, or in response to certain activities performed on the user device 200);
the predetermined layout includes a plurality of content items layout locations for presenting a respective content item of the second plurality of content items ([0398]: As shown in FIG. 6, a chatbot interface 70 is shown. The chatbot presents text to the user of a user device 200 and allows responses to be input by the user);
the plurality of queries includes a plurality of subset of queries; and one or more of the plurality of subset of queries corresponds to a respective content item layout location of the plurality of content items layout locations (Fig. 6; [0398]-[0401]: The interface 70 may interact with the user… upon detecting certain keywords being entered via the user interface 70… Alternatively, the reports may comprise a subset of the data collected and/or a subset of the evaluations).
Regarding Claim 6, Jaganathan discloses a computer-implemented method , comprising:
obtaining a first plurality of textual information associated with a first content item with which a user has interacted ([Page 3]: To generate personalized text, we will use the user’s past documents to understand their unique writing style, phrases, and key elements. We will collect these documents using a Retriever and Ranking system);
However, Jaganathan does not explicitly teach “generating a prompt for a generative model, the prompt including the first plurality of textual information and the prompt instructing the generative model to generate, based at least in part on the first plurality of textual information, a customized content and a first plurality of queries related to the customized content as an output of the generative model; generate the output using the generative model, wherein the generative model is configured to process the prompt to generate the output including the customized content and the first plurality of queries; processing at least some of the first plurality of queries to determine a second plurality of content items that are responsive to the plurality of queries; and providing the customized content and at least a portion of the second plurality of content items to a user device for presentation”.
On the other hand, in the same field of endeavor, Manavoglu teaches
generating a prompt for a generative model (Fig. 1; [0063]-[0064]: For instance, the user of the client computing device 104 can provide consent for their history to be analyzed, such that the user history 122 includes information about the user),
the prompt including the first plurality of textual information and the prompt instructing the generative model to generate, based at least in part on the first plurality of textual information, a customized content and a first plurality of queries related to the customized content as an output of the generative model (Fig. 1; [0063]-[0064]: For instance, the user of the client computing device 104 can provide consent for their history to be analyzed, such that the user history 122 includes information about the user; [0064]-[0067]: the prompt provided to the generative model 114 can be designed to cause the generative model 114 to perform these tasks);
generate the output using the generative model, wherein the generative model is configured process the prompt to generate the output including the customized content and the first plurality of queries (Fig. 1; [0048]: At 806, the generative model generates output based upon the user input; [0064]-[0065]: the GLM 114 generates a semantic representation of interests of a user based upon history of the user interacting with webpages, supplemental content items, search results, etc… Accordingly, given the user history, the generative model 114 can summarize the history into a few phrases/sentences that summarize the interests of the user);
processing at least some of the first plurality of queries to determine a second plurality of content items that are responsive to the plurality of queries ([0064]-[0070]: The supplemental content provision system 112 can be provided with this summary and can employ such information when selecting supplemental content items to provide to the user of the client computing device 104… The generative model 114 can be provided with supplemental content items in the supplemental content 120 and assign labels to the supplemental content items that are indicative of relevance to particular queries, keywords, sets of users, and so forth… context from a dialogue between the user and the generative model 114 can be incorporated into a user representation as a near real time signal in connection with identifying a supplemental content item for presentment to the user); and
Additionally, Rollwage teaches providing the customized content and at least a portion of the second plurality of content items to a user device for presentation ([0609]-[0610]: In response to detecting that the user is in crisis, the crisis dialogue module 63 may perform a specific rules based dialogue flow asking if the user needs urgent support, based on stored text templates… If the user answers with a “Yes” as seen in FIG. 14b and FIG. 14c, then the crisis dialogue module 63 may output a stored template including a follow-up question).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teaching of Jaganathan to incorporate the teachings of Manavoglu and Rollwage to process the input by the generative model to generate the output, and cause the summary and at least a portion of the second plurality of content items to be presented on a client device associated with the user.
The motivation for doing so would be to allow for more targeted retrieval of content for the user, as recognized by Manavoglu ([0067] of Manavoglu: For instance, the generative model 114, based upon rich contextual information from a dialogue between the user and the generative model 114, can construct an embedding for the user to allow for more targeted and personalized retrieval of supplemental content for the user) and to present items to a user in a personalized manner, as recognized by Rollwage ([0413]-[0415] of Rollwage: Recommender systems are a class of machine learning techniques that broadly aim to present items to a user in a personalised manner).
Regarding Claim 7, the combined teachings of Jaganathan, Manavoglu, and Rollwage disclose the computer-implemented method of claim 6.
Jaganathan further comprising: aggregating a second plurality of textual information associated with a first plurality of content items to generate a text-based user summary ([Page 5]: Finally, once we have all the entries, the ranked entries are concatenated as strings and truncated to 2,500 characters),
wherein: the first plurality of content items is determined, based on content items with which a user has interacted, from a user history associated with the user; the first content item is one of the first plurality of content items ([Page 3]: To generate personalized text, we will use the user’s past documents to understand their unique writing style, phrases, and key elements); and
Additionally, Rollwage teaches the prompt includes the text-based user summary ([0021]: The system prompt may be generated using the input data and the subject profile information).
Regarding Claim 8, the combined teachings of Jaganathan, Manavoglu, and Rollwage disclose the computer-implemented method of claim 7.
Rollwage further teaches wherein: the first plurality of content items are assigned a plurality of weights ([0347]: The training dataset may comprise historical patient utterances (sequences of text) and may be used to learn the weights of the deep learning algorithm); and
aggregating the second plurality of textual information associated with the first plurality of content items is performed in accordance with the plurality of weights ([0376]-[0379]: Each attention module comprises three stored matrices of weights… The outputs from the attention heads are then merged).
Regarding Claim 9, the combined teachings of Jaganathan, Manavoglu, and Rollwage disclose the computer-implemented method of claim 7.
Rollwage further teaches wherein the customized content includes at least one of an aesthetic of the user, a taste or the user, or an object linked to the user ([0556]-[0557]: A further function of the understanding module 31 is to contain general information about the patient like demographics, questionnaire scores, or diagnosis… this specific information is then summarised).
Regarding Claim 10, the combined teachings of Jaganathan, Manavoglu, and Rollwage disclose the computer-implemented method of claim 8.
Rollwage further teaches wherein the plurality of weights are determined based at least in part on at least one of a recency of one or more of the first plurality of content items, a type of interaction with one or more of the first plurality of content items, or a frequency of interaction with one or more of the first plurality of content items ([0556]-[0557]: A further function of the understanding module 31 is to contain general information about the patient like demographics, questionnaire scores, or diagnosis… this specific information is then summarised).
Regarding Claim 11, the combined teachings of Jaganathan, Manavoglu, and Rollwage disclose the computer-implemented method of claim 10.
Rollwage further teaches wherein: the at least the portion of the second plurality of content items are presented according to a predetermined layout ([0398]-[0403]: The interface 70 may interact with the user at predetermined times, or at predetermined time intervals, or in response to certain activities performed on the user device 200… [0403] For example, a user may be allocated to a predetermined treatment pathway… The action logic may be configured to prioritize some users for treatment based on the output);
the predetermined layout includes a plurality of content items layout locations for presenting a respective content item of the second plurality of content items; each of the plurality of plurality of content items layout locations corresponds to a respective aspect of the taste of the user ([0398]: As shown in FIG. 6, a chatbot interface 70 is shown. The chatbot presents text to the user of a user device 200 and allows responses to be input by the user… The action logic may be configured to prioritize some users for treatment based on the output);
the plurality of queries includes a plurality of subset of queries (Fig. 6; [0401]: In one example, the first module 30 reports results… Alternatively, the reports may comprise a subset of the data collected and/or a subset of the evaluations); and
one or more of the plurality of subset of queries corresponds to a respective content item layout location of the plurality of content items layout locations Fig. 6; [0398]: The interface 70 may interact with the user… upon detecting certain keywords being entered via the user interface 70).
Regarding Claim 12, the combined teachings of Jaganathan, Manavoglu, and Rollwage disclose the computer-implemented method of claim 11.
Rollwage further teaches wherein: the customized content includes a questionnaire (Fig. 9; [0426]: The example of this recommender model 32 is described as applied to CBT. The recommender model 32 uses… more clearly grounded information, such as therapist diagnosis or questionnaire data); and one or more of the first plurality of queries corresponds to a possible response to a question of the questionnaire ([0609]- [0610]: FIGS. 14a-14c are example dialogue flows… If the user answers with a “Yes” as seen in FIG. 14b and FIG. 14c, then the crisis dialogue module 63 may output a stored template including a follow-up question).
Regarding Claim 13, the combined teachings of Jaganathan, Manavoglu, and Rollwage disclose the computer-implemented method of claim 12.
Rollwage further teaches wherein the prompt further instructs the generative model to, based at least in part on the text-based user summary, generate a plurality of conclusions associated with the questionnaire ([0431]: Once this information is fed to the recommender system 32, the recommender system 32 might engage in one or more of the following actions: [0432] Suggest a single intervention/exercise for the next time step. [0433] Plan a sequence of several next exercises).
Regarding Claim 14, the combined teachings of Jaganathan, Manavoglu, and Rollwage disclose the computer-implemented method of claim 13.
Rollwage further teaches further comprising: in response to causing the customized content to be presented to the user:
receiving interactions specifying responses to questions of the questionnaire ([0609]- [0610]: FIGS. 14a-14c are example dialogue flows… If the user answers with a “Yes” as seen in FIG. 14b and FIG. 14c, then the crisis dialogue module 63 may output a stored template including a follow-up question);
selecting, based at least in part on the responses, one or more queries of the first plurality of queries that are associated with the conclusion ([0610]-[0611]: The crisis dialogue module 63 may also output a stored template providing options for support to the user (e.g., phone numbers to seek support)); and
determining, based at least in part on the responses, the at least some of the first plurality of queries from the first plurality of queries ([0611]: If the user answers the follow-up question with a “No,” as seen in FIG. 14c, then the crisis dialogue module 63 may output a different stored template).
Regarding Claim 15, the combined teachings of Jaganathan, Manavoglu, and Rollwage disclose the computer-implemented method of claim 13.
Rollwage further teaches wherein one or more of the plurality of conclusions corresponds to a respective combination of responses to questions included in the questionnaire ([0607]-[0614]: The crisis dialogue module 63 may comprise one or more stored templates of system responses and/or system utterances that are to be outputted to the user… FIGS. 14a-14c are example dialogue flows that the crisis dialogue module 63 triggers to provide support to the user.... The input safety module 60 uses a combination of “trigger words” (checked using regular expressions in the matching engine 61) and a zero-shot large language model 62)).
Regarding Claim 16, the combined teachings of Jaganathan, Manavoglu, and Rollwage disclose the computer-implemented method of claim 6.
Rollwage further teaches wherein: the prompt includes the first content item ([0188]-[0191]: In one example, generating the first system response comprises generating a first system prompt comprising the input data and providing the system prompt to the first trained model… In one example, the second system prompt includes instructions to modify a portion of the first system response);
the generative model includes a multimodal generative model ([0317]: The model-based system in the first module guides and constrains the conversation between the application and the patient. This can for example be done through producing a prompt (or any other input modality) for the language model that contains relevant background information; [0367]-[0369]: The language model is a large language model. The language model 21 is a generative model… Various large language models are known and can be used);
the customized content includes a decision tree having a root node and a plurality of child nodes; the root node is associated with the first content item; and each child node of the plurality of child nodes is associated with a feature of a respective parent node to which it is directed connected ([0350]: In another example, the cognitive understanding model comprises a tree-based model; [0410]: The recommender module 32 may comprise a trained neural network, for example a transformer-based or a multi-layer feed-forward network, or, a tree-based classifier model for example; [0681]: models comprise any suitable machine learning methodologies such as for example, neural networks, decision trees).
Regarding Claim 17, Jaganathan discloses a method, comprising:
obtaining a plurality of user information associated with a user that includes information associated with a first plurality of content items with which the user has interacted ([Page 3]: To generate personalized text, we will use the user’s past documents to understand their unique writing style, phrases, and key elements. We will collect these documents using a Retriever and Ranking system);
extracting textual information associated with the plurality of content items ([Page 3]: Once we have the ranked entries, we extract the important information with two techniques i.e., Summarization and Synthesis);
aggregating the textual information to generate a text-based user summary associated with the user ([Page 5]: Finally, once we have all the entries, the ranked entries are concatenated as strings and truncated to 2,500 characters).
However, Jaganathan does not explicitly teach “generating a prompt for a generative model, the prompt including the text-based user summary and the prompt instructing to the generative model to generate an output, based at least in part on the text-based user summary,
wherein the prompt instructs the generative model to generate a questionnaire, a plurality of conclusions, and a plurality of queries as the output; generate the output by the generative model using the prompt, the output of the generative mode includes the questionnaire, the plurality of conclusions, and the first plurality of queries; providing the questionnaire to a client device associated with the user for presentation; receiving, from the client device and via interactions with the client device, responses to questions included in the questionnaire; determining, based at least in part on the responses, a conclusion from the plurality of conclusions; determining, based at least in part on the responses, a second plurality of queries from the first plurality of queries; processing the second plurality of queries to determine a second plurality of content items that are responsive to the second plurality of queries; and providing the conclusion and at least a portion of the second plurality of content items to the client device for presentation.”
On the other hand, in the same field of endeavor, Manavoglu teaches
generating a prompt for a generative model (Fig. 1; [0063]-[0064]: For instance, the user of the client computing device 104 can provide consent for their history to be analyzed, such that the user history 122 includes information about the user),
the prompt including the text-based user summary and the prompt instructing to the generative model to generate an output, based at least in part on the text-based user summary (Fig. 1; [0063]-[0064]: The generative model 114 receives such user history and generates a semantic representation of interests of the user based upon the user history),
wherein the prompt instructs the generative model to generate a questionnaire, a plurality of conclusions, and a plurality of queries as the output ([0096]: In yet another aspect, a method disclosed herein includes providing a prompt to a generative model, where the prompt includes an instruction to the generative model. The instruction instructs the generative model to: 1) review output that is to be generated by the generative model based upon the prompt for text that is to be associated with a supplemental content item);
generate the output by the generative model using the prompt, the output of the generative mode includes the questionnaire, the plurality of conclusions, and the first plurality of queries (Fig. 1; [0048]: At 806, the generative model generates output based upon the user input; [0096]-[0100]: The method additionally includes causing the output to be displayed in a graphical user interface (GUI)… The method also includes causing the second supplemental content item to be displayed in the GUI as part of a conversation between a user and a chatbot);
Additionally, Rollwage teaches providing the questionnaire to a client device associated with the user for presentation ([0608]: FIG. 13(b) is a schematic illustration of a rules based dialogue flow, in which a series of safety questions, provided in stored templates, are output to the user);
receiving, from the client device and via interactions with the client device, responses to questions included in the questionnaire; determining, based at least in part on the responses, a conclusion from the plurality of conclusions ([0600]: If a concern is detected in response to one of the safety questions, sign-posting of options for support is provided.);
determining, based at least in part on the responses, a second plurality of queries from the first plurality of queries ([0609] FIGS. 14a-14c are example dialogue flows that the crisis dialogue module 63 triggers to provide support to the user… In response to detecting that the user is in crisis, the crisis dialogue module 63 may perform a specific rules based dialogue flow);
processing the second plurality of queries to determine a second plurality of content items that are responsive to the second plurality of queries ([0610] If the user answers with a “Yes” as seen in FIG. 14b and FIG. 14c, then the crisis dialogue module 63 may output a stored template including a follow-up question); and
providing the conclusion and at least a portion of the second plurality of content items to the client device for presentation ([0610]: then the crisis dialogue module 63 may output stored templates similar to the outputs seen in FIG. 14a. For example, the crisis dialogue module 63 may output a stored template suggesting that the user talk to a human).
language model comprises a processed or filtered summary of previous user inputs).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teaching of Jaganathan to incorporate the teachings of Manavoglu and Rollwage to process the input by the generative model to generate the output, and cause the summary and at least a portion of the second plurality of content items to be presented on a client device associated with the user.
The motivation for doing so would be to allow for more targeted retrieval of content for the user, as recognized by Manavoglu ([0067] of Manavoglu: For instance, the generative model 114, based upon rich contextual information from a dialogue between the user and the generative model 114, can construct an embedding for the user to allow for more targeted and personalized retrieval of supplemental content for the user) and to present items to a user in a personalized manner, as recognized by Rollwage ([0413]-[0415] of Rollwage: Recommender systems are a class of machine learning techniques that broadly aim to present items to a user in a personalised manner).
Regarding Claim 18, the combined teachings of Jaganathan, Manavoglu, and Rollwage disclose the method of claim 17.
Rollwage further teaches wherein: the first plurality of content items are assigned a plurality of weights ([0347]: The training dataset may comprise historical patient utterances (sequences of text) and may be used to learn the weights of the deep learning algorithm); and
aggregating the textual information to generate the text-based user summary is performed in accordance with the plurality of weights ([0376]-[0379]: Each attention module comprises three stored matrices of weights… The outputs from the attention heads are then merged)..
Regarding Claim 19, the combined teachings of Jaganathan, Manavoglu, and Rollwage disclose the method of claim 18.
Rollwage further teaches wherein the plurality of weights are determined based at least in part on at least one of a recency of each of the first plurality of content items, a type of interaction with one or more of the first plurality of content items, or a frequency of interaction with each of the first plurality of content items ([0411]: This information may be provided through the history module 37, which may act as a kind of filter, which has access to the entire conversation history of a patient, but only selects the most relevant exchanges. For example, this could apply a “recency” filter, which always outputs the last N user utterances).
Regarding Claim 20, the combined teachings of Jaganathan, Manavoglu, and Rollwage disclose the method of claim 17.
Rollwage further teaches wherein one or more of the first plurality of queries is associated with at least one of: a conclusion from the plurality of conclusions; or a response to a question of the questionnaire ([0610]: If the user answers the follow-up question with a “Yes,” as seen in FIG. 14b, then the crisis dialogue module 63 may output stored templates similar to the outputs seen in FIG. 14a. For example, the crisis dialogue module 63 may output a stored template suggesting that the user talk to a human if they cannot keep themselves or others around safe. The crisis dialogue module 63 may also output a stored template providing options for support to the user (e.g., phone numbers to seek support)).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHIRLEY D. HICKS whose telephone number is (571)272-3304. The examiner can normally be reached Mon - Fri 7:30 - 4:00.
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, Charles Rones can be reached on (571) 272-4085. 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.
/S.D.H./Examiner, Art Unit 2168
/CHARLES RONES/Supervisory Patent Examiner, Art Unit 2168
Prosecution Insights