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 .
2. In view of the Pre-Appeal Brief filed on 02/17/2026, PROSECUTION IS HEREBY REOPENED. A new ground of rejection is set forth below.
To avoid abandonment of the application, appellant must exercise one of the following two options:
(1) file a reply under 37 CFR 1.111 (if this Office action is non-final) or a reply under 37 CFR 1.113 (if this Office action is final); or,
(2) initiate a new appeal by filing a notice of appeal under 37 CFR 41.31 followed by an appeal brief under 37 CFR 41.37. The previously paid notice of appeal fee and appeal brief fee can be applied to the new appeal. If, however, the appeal fees set forth in 37 CFR 41.20 have been increased since they were previously paid, then appellant must pay the difference between the increased fees and the amount previously paid.
A Supervisory Patent Examiner (SPE) has approved of reopening prosecution by signing below:
Response to Amendments
The action is responsive to the Applicant’s Arguments filed on 8/08/2025. Claims 1-20 are pending in the application.
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 Papayiannis (US 20250104693 A1) in view of Ni et al. (US 20250068633 A1).
Regarding Claim 1, Papayiannis discloses a system for implementing deep search using a large language model ("LLM") ([0031]: FIG. 1 illustrates example processing and components of the system 100; [Abstract]: Techniques for using a language model (e.g., a large language model (LLM)) to generate a natural language response to a user input… are described), the system comprising:
a processing system ([0205]: Each of these devices (410/420/425) may include one or more controllers/processors (1004/1104)); and
memory coupled to the processing system, the memory comprising computer executable instructions that ([0205]: a memory (1006/1106) for storing data and instructions of the respective device), when executed by the processing system, causes the system to perform operations comprising:
receiving an initial user query ([0032]: As shown in FIG. 1, the prompt generation component 110 receives user input data 102; [0035]: user input data 102 (e.g., search-query results);
providing, as input to a first LLM, a first prompt requesting generation of a plurality of intents for the initial user query ([0032]: In some embodiments, the prompt generation component 110 may generate prompt data representing a prompt for input to the natural language and prosody LLM 117; [0036]: In some embodiments, the prompt data 115 may be an instruction for the natural language and prosody LLM 117 to generate a natural language response to the user input given the information… included in the prompt data 115… [0040]: The prompt data 115 is received at the natural language layers 120 and the prosody layers 130 of the natural language and prosody LLM 117; [0087]: TABLE-US-00004 { Create a new task if necessary to help complete a request to [user input data 102 (or a representation of a determined intent of the user input data 102]);
However, Papayiannis does not explicitly teach “receiving, from the first LLM, the plurality of intents and a representative query for each intent; identifying a primary intent among the plurality of intents; providing, as input to a second LLM, a second prompt requesting generation of a plurality of primary alternative queries for the primary intent based at least in part on at least one of the primary intent or its corresponding representative query; receiving, from the second LLM, the plurality of primary alternative queries; querying a search engine or an index of the search engine, using the plurality of primary alternative queries, to retrieve a first plurality of web search results; receiving, from the search engine, the first plurality of web search results; and causing display of at least top results of the first plurality of web search results.”
On the other hand, in the same field of endeavor, Ni teaches
receiving, from the first LLM, the plurality of intents and a representative query for each intent (Fig. 3; [0084]- [0091]: an intermediate output may match query intents with proper provider information (e.g., matching condition “stomach pain” with specialty “gastroenterology”)… In some embodiment, the search domain is associated with a plurality of potential query results. The potential query results may be represented within the domain knowledge datastore 302 as query result data objects 360);
identifying a primary intent among the plurality of intents (Fig. 3; [0085]-[0091]: For instance, a multi-modal, multi-stage topic search may match query intents with proper query resolutions, such as provider information, and return relevant results in each topic… The query result data objects 360 may include a plurality of source features that describe one or more characteristics of the query result data objects 360);
providing, as input to a second LLM, a second prompt requesting generation of a plurality of primary alternative queries for the primary intent based at least in part on at least one of the primary intent or its corresponding representative query (Fig. 3; [0052]-[0054]: The source features, for example, may be aggregated for each of the query result data objects 360 from a plurality of different data sources, such as the first data source 304, the second data source 306; [0080]: In some examples, if selected by a user, a second stage of a multi-stage search process may be performed to generate a query resolution based on the source features identified by the intermediate query resolution.);
receiving, from the second LLM, the plurality of primary alternative queries (Fig. 3; [0081]: In some examples, a query resolution may include an output of a second stage of a multi-stage search process. A query resolution, for example, may identify one or more query result data objects for a search query based on a plurality of source features identified by an intermediate query resolution; [0094]-[0100]: The medical claim data, for example, may be extracted and/or received from one or more second data sources 306… A language model may include one or more machine learning models configured, trained (e.g., jointly, separately, etc.), and/or the like to generate contextual information for a search query… By increasing the contextual information for the taxonomy categories of various taxonomy datasets, the enhanced taxonomy may be leveraged to make more relevant and targeted connections between a search query and a plurality of potential search results);
querying a search engine or an index of the search engine, using the plurality of primary alternative queries, to retrieve a first plurality of web search results (Fig. 3; [0103]-[0105]: The domain knowledge datastore 302 may be communicatively connected to the search engine 314, which may be configured to receive a search query and leverage the domain knowledge datastore 302 to generate a query resolution for the search query);
receiving, from the search engine, the first plurality of web search results (Fig. 3; [0105]: the key word search routine may return one or more matched query result data objects to the textual search interface 322 for providing a query resolution to the user 350); and
causing display of at least top results of the first plurality of web search results (Fig. 3; [0104]-[0106]: In some embodiments, the search engine 314 includes a plurality of search interfaces configured to interact with a plurality of users 350… In some examples, the code search routine may return one or more matched query result data objects to the textual search interface 322 for providing a query resolution to the user 350).
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 Papayiannis to incorporate the teachings of Ni to include receiving, from the first LLM, the plurality of intents and a representative query for each intent, identifying a primary intent, providing to a second LLM a second prompt, receiving, from the second LLM, the plurality of primary alternative queries, querying a search engine, using the plurality of primary alternative queries, to retrieve a first plurality of web search results; receiving, from the search engine, the first plurality of web search results, and display results of the first plurality of web search results.
The motivation for doing so would be to capture the underlying intent behind search queries in complex search domains, as recognized by Ni ([0010] of Ni: FIG. 3 is a system diagram showing an example query resolution system in accordance with some embodiments discussed herein… search results May be generated that capture the underlying intent behind search queries in complex search domains. Meanwhile, by providing multi-channel information in response to a search, the techniques of the present disclosure may improve both the accuracy and interpretability of query resolutions).
Regarding Claim 2, the combined teachings of Papayiannis and Ni disclose the system of claim 1, wherein the operations further comprise:
querying a cache to determine whether the cache contains sorted results for an LLM-assisted deep search that is applicable to the user query ([0121]: In some embodiments, the LLM orchestrator component 430 may further include a memory storage (not illustrated) which may store various information associated with the processing performed (e.g., user input data 102, the prompt data 515… the action response data 458a-n, the potential response data 443a-n, etc);
wherein providing the first prompt, receiving the plurality of intents, identifying the primary intent, providing the second prompt, receiving the plurality of primary alternative queries, querying the search engine or the index of the search engine, receiving the first plurality of web search results, and causing display of the at least top results of the first plurality of web search results are based on a determination that the cache does not contain sorted results for an LLM-assisted deep search that is applicable to the user query (Fig. 4; [0119]-[0121]: In some embodiments, the action response data 458a-n may indicate whether or not the corresponding component is able to respond (e.g., the action response data 458a may include a Boolean value such as “yes” or “no” or other similar indications). In some embodiments, the shortlister language model 640 may filter and/or rank the action response data 458a-n based on information included in the prompt data 615)… the LLM orchestrator component 430 may further include a memory storage (not illustrated) which may store various information associated with the processing performed).
Regarding Claim 3, the combined teachings of Papayiannis and Ni disclose the system of claim 1, wherein the operations further comprise:
querying an index of a search engine to retrieve a plurality of grounding results based on the user query (Fig. 6; [0115]: For further example, the API provider component 650 may include a search component, which may be configured to query a storage (e.g., a database, repository, knowledge base, etc.) for information usable for generating a response to a user input);
wherein the first prompt, which is provided as input to the first LLM, includes the grounding results and requests generation of the plurality of intents and a representative query for each intent for the initial user query ([0115]: For example, if the action data 647a-n represents a request for information of “Who won the game between [Team 1 Name] and [Team 2 Name],” then the search component may query the storage (or other sources, such as the Internet), to retrieve the information “[Team 1 Name] won the game between [Team 1 Name] and [Team 2 Name].”).
Regarding Claim 4, the combined teachings of Papayiannis and Ni disclose the system of claim 1, wherein the operations further comprise:
providing, as input to a third LLM, a third prompt requesting generation of a relevance score for each first web search result among the first plurality of web search results based on the primary intent ([0032]: In some embodiments, the prompt generation component 110 may generate prompt data representing a prompt for input to the natural language and prosody LLM 117… with respect to FIG. 8, the ASR component 850 may determine ASR data that includes an ASR N-best list including multiple ASR hypotheses and corresponding confidence scores representing what the user may have said);
receiving, from the third LLM, the relevance score for each first web search result ([0164]: the orchestrator component 830 and/or the LLM orchestrator component 430 may include further logic for determining further confidence scores during processing representing whether the orchestrator component 830 and/or the LLM orchestrator component 430 should continue processing); and
sorting the first plurality of web search results based on their relevance scores ([0078]: The LLM shortlister component 440 receives and processes the action response data 458a-n and generates… ranked potential responses; [0119]: In some embodiments, the shortlister language model 640 may filter and/or rank the action response data 458a-n based on information included in the prompt data 615);
wherein causing display of the at least top results of the first plurality of web search results comprises causing display of at least top results of the first plurality of web search results that have been sorted based on their relevance scores ([0165]: An N-best list may additionally include a respective score associated with each ASR hypothesis represented therein; [0208]: The user device 410 may additionally include a display 1016 for displaying content).
Regarding Claim 5, the combined teachings of Papayiannis and Ni disclose the 3system of claim 4, wherein at least one of providing the first prompt to the first LLM, providing the second prompt to the second LLM, or providing the third prompt to the third LLM is performed using an application programming interface ("API") call to each corresponding LLM (Fig. 5; [0099]-[0104]: For further example, based on processing the second example prompt data provided above, the task selection language model 540 may output model output data: {“1. Find an API that sells [Company name] pizza,” } or the like).
Regarding Claim 6, the combined teachings of Papayiannis and Ni disclose the system of claim 1, wherein identifying the primary intent includes one of:
selecting a top result of the plurality of intents as received from the first LLM (TABLE-US-00007 { Select the top prioritized task given the ultimate goal of [user input data 102 (or a representation of a determined intent included in the user input data 102]); or
receiving a user selection from among a list of disambiguation choices of the plurality of intents ([0032]: in some embodiments, the user input may correspond to an actuation of a physical button, data representing selection of a button displayed on a graphical user interface (GUI), image data of a gesture user input, combination of different types of user inputs (e.g., gesture and button actuation)).
Regarding Claim 7, the combined teachings of Papayiannis and Ni disclose the system of claim 1, wherein each intent among the plurality of intents has a weighted value, wherein the primary intent is identified based on the weighted value ([0056]: The natural language output head 270 processes the intermediate natural language processing data 122n to generate a posteriorgram 275 representing a result of applying one or more weights (determined as a result of training the natural language output head 270 for the natural language generation task) to the intermediate natural language processing data 122n; [0070]: A neural network model includes trainable parameters (e.g., “weights”) that indicate how much weight (e.g., in the form of an arithmetic multiplier) a cell should give to a particular input when generating an output).
Regarding Claim 8, Papayiannis discloses a computer-implemented method for implementing deep search using a large language model ("LLM") ( [Abstract]: Techniques for using a language model (e.g., a large language model (LLM)) to generate a natural language response to a user input… are described), the method comprising:
receiving a user query for initiating a web search ([0032]: As shown in FIG. 1, the prompt generation component 110 receives user input data 102; [0078]: to provide a potential responses(s) to the user input or current task (e.g., a response to a user-provided question, a paragraph from a website, etc.));
querying a search engine or an index of the search engine to retrieve a plurality of grounding results based on the user query (Figs. 8-9; [0166]-[0168]: The arbitrator component 882 may be in communication with a global index storage 920 and a personalized index storage 930… The global retriever component 950 queries a global index storage 920 for global index data 925);
providing, as input to a first LLM, a request for generation of a plurality of intents and a representative query for each intent based on the plurality of grounding results ([0032]: In some embodiments, the prompt generation component 110 may generate prompt data representing a prompt for input to the natural language and prosody LLM 117; [0036]: In some embodiments, the prompt data 115 may be an instruction for the natural language and prosody LLM 117 to generate a natural language response to the user input given the information… included in the prompt data 115… [0040]: The prompt data 115 is received at the natural language layers 120 and the prosody layers 130 of the natural language and prosody LLM 117; [0087]: TABLE-US-00004 { Create a new task if necessary to help complete a request to [user input data 102 (or a representation of a determined intent of the user input data 102]);
sorting the first plurality of web search results based on their relevance scores ([0032]: with respect to FIG. 8, the ASR component 850 may determine ASR data that includes an ASR N-best list including multiple ASR hypotheses and corresponding confidence scores representing what the user may have said); and
causing display of at least top results of the first plurality of web search results that have been sorted based on their relevance scores (Fig. 4; [0078]: The LLM shortlister component 440… generates potential response data 443a-n representing… ranked potential responses; [0080]: In some embodiments, the response arbitration component 460 may generate a natural language summary of one or more of the selected responses and output the natural language summary; [0208]: The user device 410 may additionally include a display 1016 for displaying content).
However, Papayiannis does not explicitly teach “receiving, from the first LLM, the plurality of intents and the representative query for each intent; receiving selection of a primary intent among the plurality of intents; providing, as input to a second LLM, a request for generation of a plurality of primary alternative queries for the primary intent based at least in part on at least one of the primary intent or its corresponding representative query; receiving, from the second LLM, the plurality of primary alternative queries; querying the search engine, using the plurality of primary alternative queries, to retrieve a first plurality of web search results; receiving, from the search engine, the first plurality of web search results; providing, as input to a third LLM, a request for generation of a relevance score for each first web search result among the first plurality of web search results based on the primary intent; receiving, from the third LLM, the relevance score for each first web search result.”
On the other hand, in the same field of endeavor, Ni teaches
receiving, from the first LLM, the plurality of intents and the representative query for each intent (Fig. 3; [0084]- [0091]: an intermediate output may match query intents with proper provider information (e.g., matching condition “stomach pain” with specialty “gastroenterology”)… In some embodiment, the search domain is associated with a plurality of potential query results. The potential query results may be represented within the domain knowledge datastore 302 as query result data objects 360);
receiving selection of a primary intent among the plurality of intents (Fig. 3; [0085]-[0091]: For instance, a multi-modal, multi-stage topic search may match query intents with proper query resolutions, such as provider information, and return relevant results in each topic… The query result data objects 360 may include a plurality of source features that describe one or more characteristics of the query result data objects 360);
providing, as input to a second LLM, a request for generation of a plurality of primary alternative queries for the primary intent based at least in part on at least one of the primary intent or its corresponding representative query (Fig. 3; [0052]-[0054]: The source features, for example, may be aggregated for each of the query result data objects 360 from a plurality of different data sources, such as the first data source 304, the second data source 306; [0080]: In some examples, if selected by a user, a second stage of a multi-stage search process may be performed to generate a query resolution based on the source features identified by the intermediate query resolution.);
receiving, from the second LLM, the plurality of primary alternative queries (Fig. 3; [0081]: In some examples, a query resolution may include an output of a second stage of a multi-stage search process. A query resolution, for example, may identify one or more query result data objects for a search query based on a plurality of source features identified by an intermediate query resolution; [0094]-[0100]: The medical claim data, for example, may be extracted and/or received from one or more second data sources 306… A language model may include one or more machine learning models configured, trained (e.g., jointly, separately, etc.), and/or the like to generate contextual information for a search query… By increasing the contextual information for the taxonomy categories of various taxonomy datasets, the enhanced taxonomy may be leveraged to make more relevant and targeted connections between a search query and a plurality of potential search results);
querying the search engine, using the plurality of primary alternative queries, to retrieve a first plurality of web search results (Fig. 3; [0103]-[0105]: The domain knowledge datastore 302 may be communicatively connected to the search engine 314, which may be configured to receive a search query and leverage the domain knowledge datastore 302 to generate a query resolution for the search query);
receiving, from the search engine, the first plurality of web search results (Fig. 3; [0105]: the key word search routine may return one or more matched query result data objects to the textual search interface 322 for providing a query resolution to the user 350);
providing, as input to a third LLM, a request for generation of a relevance score for each first web search result among the first plurality of web search results based on the primary intent ([0127]-[0129]: In some embodiments, the similarity scores are generated for each of a plurality of source features from a multi-channel dataset… In addition, or alternatively, the other domain channels 430 may include… a third domain channel with a plurality of third channel features corresponding to a third topic type);
receiving, from the third LLM, the relevance score for each first web search result (Fig. 4; [0128]-[0129]: A plurality of additional similarity scores may be generated in the same and/or similar manner with respect to each of the other domain channels 430 within the multi-channel dataset to generate a plurality of multi-modal similarity scores across a plurality of different information channels).
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 Papayiannis to incorporate the teachings of Ni to include receiving, from the first LLM, the plurality of intents and a representative query for each intent, identifying a primary intent, providing to a second LLM a second prompt, receiving, from the second LLM, the plurality of primary alternative queries, querying a search engine, using the plurality of primary alternative queries, to retrieve a first plurality of web search results; receiving, from the search engine, the first plurality of web search results, and display results of the first plurality of web search results.
The motivation for doing so would be to capture the underlying intent behind search queries in complex search domains, as recognized by Ni ([0010] of Ni: FIG. 3 is a system diagram showing an example query resolution system in accordance with some embodiments discussed herein… search results May be generated that capture the underlying intent behind search queries in complex search domains. Meanwhile, by providing multi-channel information in response to a search, the techniques of the present disclosure may improve both the accuracy and interpretability of query resolutions).
Regarding Claim 9, the combined teachings of Papayiannis and Ni disclose the computer-implemented method of claim 8, wherein two or more of the first through third LLMs are the same LLM ([0049]: the natural language and prosody LLM 117 may include a single set of layers configured to generate both of the model output natural language data 125 and the model output prosody data 135.).
Regarding Claim 10, the combined teachings of Papayiannis and Ni disclose the computer-implemented method of claim 8, wherein:
providing the request for generation of the plurality of intents and the representative query for each intent includes providing, as input to the first LLM, a first prompt requesting generation of the plurality of intents and the representative query for each intent based on the plurality of grounding results ([0032]: In some embodiments, the prompt generation component 110 may generate prompt data representing a prompt for input to the natural language and prosody LLM 117; [0036]: In some embodiments, the prompt data 115 may be an instruction for the natural language and prosody LLM 117 to generate a natural language response to the user input given the information… included in the prompt data 115… [0040]: The prompt data 115 is received at the natural language layers 120 and the prosody layers 130 of the natural language and prosody LLM 117; [0087]: TABLE-US-00004 { Create a new task if necessary to help complete a request to [user input data 102 (or a representation of a determined intent of the user input data 102]);
providing the request for generation of the plurality of primary alternative queries for the primary intent includes providing, as input to the second LLM, a second prompt requesting generation of the plurality of primary alternative queries for the primary intent based at least in part on at least one of the primary intent or its corresponding representative query ([0033]: As further shown in FIG. 1, in some embodiments, the prompt generation component 110 may further receive context data 105.); and
providing the request for generation of the relevance score for each first web search result includes providing, as input to the third LLM, a third prompt requesting generation of the relevance score for each first web search result among the first plurality of web search results based on the primary intent ([0032]: In some embodiments, the prompt generation component 110 may generate prompt data representing a prompt for input to the natural language and prosody LLM 117… with respect to FIG. 8, the ASR component 850 may determine ASR data that includes an ASR N-best list including multiple ASR hypotheses and corresponding confidence scores representing what the user may have said… In some instances, the user input data 102 may include a top scoring ASR hypothesis of the ASR data).
Regarding Claim 11, the combined teachings of Papayiannis and Ni disclose the computer-implemented method of claim 10, wherein at least one of providing the first prompt to the first LLM, providing the second prompt to the second LLM, or providing the third prompt to the third LLM is performed using an application programming interface ("API") call to each corresponding LLM (Fig. 5; [0099]-[0104]: For further example, based on processing the second example prompt data provided above, the task selection language model 540 may output model output data: {“1. Find an API that sells [Company name] pizza,” } or the like)..
Regarding Claim 12, the combined teachings of Papayiannis and Ni disclose the computer-implemented method of claim 10, wherein the first prompt includes query information associated with the user query, the query information including location, time, and language of the user query ([0185]: The system component(s) 420/user device 410 may include a presence detection component that determines the presence and/or location of one or more users using a variety of data).
Regarding Claim 13, the combined teachings of Papayiannis and Ni disclose the computer-implemented method of claim 8, further comprising: collecting information about the user based at least in part on an Internet browsing history of the user, wherein the primary intent is further selected based on the collected information about the user ([0019]: The LLM(s) receive a prompt including a user input, contextual information (e.g., weather information, time of day, device information associated with the device that captured the user input (e.g., device ID, device states, historical device interaction data, etc.), information associated with a user that provided the user input (e.g., information associated with a user profile of the user).
Regarding Claim 14, the combined teachings of Papayiannis and Ni disclose the computer-implemented method of claim 8, wherein each intent among the plurality of intents has a weighted value that is based on multiple factors, wherein the plurality of intents is sorted for selection based on the weighted value ([0056]: The natural language output head 270 processes the intermediate natural language processing data 122n to generate a posteriorgram 275 representing a result of applying one or more weights (determined as a result of training the natural language output head 270 for the natural language generation task) to the intermediate natural language processing data 122n; [0070]: A neural network model includes trainable parameters (e.g., “weights”) that indicate how much weight (e.g., in the form of an arithmetic multiplier) a cell should give to a particular input when generating an output).
Regarding Claim 15, the combined teachings of Papayiannis and Ni disclose the computer-implemented method of claim 8, wherein the plurality of primary alternative queries is each a deeper focused query compared with the user query ([0045]: In other words, the attention information may indicate one or more portions of the intermediate natural language processing data 122a-n (e.g., representing the one or more words) that should be focused on during processing; [0051] As shown in FIG. 2, the prompt data 715… may be used by the decoder 280 to determine which portion(s) of the representation (e.g., which words of the prompt data 115) to focus on to generate the model output natural language data 125)).
Regarding Claim 16, Papayiannis discloses the system, comprising:
a processing system ([0205]: Each of these devices (410/420/425) may include one or more controllers/processors (1004/1104)); and
memory coupled to the processing system, the memory comprising computer executable instructions that ([0205]: a memory (1006/1106) for storing data and instructions of the respective device), when executed by the processing system, causes the system to perform operations comprising:
querying a search utility or an index of the search utility to retrieve a plurality of grounding results based on an initial user query ([0032]: As shown in FIG. 1, the prompt generation component 110 receives user input data 102; [0035]: user input data 102 (e.g., search-query results);
providing, as input to a first large language model ("LLM"), a first prompt requesting generation of a plurality of intents and a representative query for each intent based on the plurality of grounding results ([0032]: In some embodiments, the prompt generation component 110 may generate prompt data representing a prompt for input to the natural language and prosody LLM 117; [0036]: In some embodiments, the prompt data 115 may be an instruction for the natural language and prosody LLM 117 to generate a natural language response to the user input given the information… included in the prompt data 115… [0040]: The prompt data 115 is received at the natural language layers 120 and the prosody layers 130 of the natural language and prosody LLM 117; [0087]: TABLE-US-00004 { Create a new task if necessary to help complete a request to [user input data 102 (or a representation of a determined intent of the user input data 102]);
causing display of at least top results of the first plurality of search results (Fig. 4; [0078]: The LLM shortlister component 440… generates potential response data 443a-n representing… ranked potential responses; [0080]: In some embodiments, the response arbitration component 460 may generate a natural language summary of one or more of the selected responses and output the natural language summary; [0208]: The user device 410 may additionally include a display 1016 for displaying content).
However, Papayiannis does not explicitly teach “receiving, from the first LLM, the plurality of intents and the representative query for each intent; receiving selection of a primary intent among the plurality of intents; providing, as input to a second LLM, a second prompt requesting generation of a plurality of primary alternative queries for the primary intent based at least in part on at least one of the primary intent or its corresponding representative query; receiving, from the second LLM, the plurality of primary alternative queries; querying a search utility, using the plurality of primary alternative queries, to retrieve a first plurality of search results; receiving, from the search utility, the first plurality of search results.”.
On the other hand, in the same field of endeavor, Ni teaches
receiving, from the first LLM, the plurality of intents and the representative query for each intent (Fig. 3; [0084]- [0091]: an intermediate output may match query intents with proper provider information (e.g., matching condition “stomach pain” with specialty “gastroenterology”)… In some embodiment, the search domain is associated with a plurality of potential query results. The potential query results may be represented within the domain knowledge datastore 302 as query result data objects 360);
receiving selection of a primary intent among the plurality of intents (Fig. 3; [0085]-[0091]: For instance, a multi-modal, multi-stage topic search may match query intents with proper query resolutions, such as provider information, and return relevant results in each topic… The query result data objects 360 may include a plurality of source features that describe one or more characteristics of the query result data objects 360);
providing, as input to a second LLM, a second prompt requesting generation of a plurality of primary alternative queries for the primary intent based at least in part on at least one of the primary intent or its corresponding representative query (Fig. 3; [0052]-[0054]: The source features, for example, may be aggregated for each of the query result data objects 360 from a plurality of different data sources, such as the first data source 304, the second data source 306; [0080]: In some examples, if selected by a user, a second stage of a multi-stage search process may be performed to generate a query resolution based on the source features identified by the intermediate query resolution);
receiving, from the second LLM, the plurality of primary alternative queries (Fig. 3; [0081]: In some examples, a query resolution may include an output of a second stage of a multi-stage search process. A query resolution, for example, may identify one or more query result data objects for a search query based on a plurality of source features identified by an intermediate query resolution; [0094]-[0100]: The medical claim data, for example, may be extracted and/or received from one or more second data sources 306… A language model may include one or more machine learning models configured, trained (e.g., jointly, separately, etc.), and/or the like to generate contextual information for a search query… By increasing the contextual information for the taxonomy categories of various taxonomy datasets, the enhanced taxonomy may be leveraged to make more relevant and targeted connections between a search query and a plurality of potential search results);
querying a search utility, using the plurality of primary alternative queries, to retrieve a first plurality of search results (Fig. 3; [0103]-[0105]: The domain knowledge datastore 302 may be communicatively connected to the search engine 314, which may be configured to receive a search query and leverage the domain knowledge datastore 302 to generate a query resolution for the search query);
receiving, from the search utility, the first plurality of search results (Fig. 3; [0105]: the key word search routine may return one or more matched query result data objects to the textual search interface 322 for providing a query resolution to the user 350).
Regarding Claim 17, the combined teachings of Papayiannis and Ni disclose the system of claim 16, wherein the search utility is one of: an Internet search engine; a file storage search utility; an email search utility; or a document storage search utility (Fig. 4; [0075]: The network(s) 499 may include the Internet and/or any other wide- or local-area network; [0115]: the search component may query the storage (or other sources, such as the Internet), to retrieve the information).
Regarding Claim 18, the combined teachings of Papayiannis and Ni disclose the system of claim 16, wherein the operations further comprise:
receiving a user query for initiating a search ([0032]: As shown in FIG. 1, the prompt generation component 110 receives user input data 102); and
querying a cache to determine whether the cache contains sorted results for an LLM-assisted deep search that is applicable to the user query ([0121]: In some embodiments, the LLM orchestrator component 430 may further include a memory storage (not illustrated) which may store various information associated with the processing performed (e.g., user input data 102, the prompt data 515… the action response data 458a-n, the potential response data 443a-n, etc);
wherein querying the search utility or the index of the search utility to retrieve the plurality of grounding results, providing the first prompt, receiving the plurality of intents and the representative query for each intent, selecting the primary intent, providing the second prompt, receiving the plurality of primary alternative queries, querying the search engine to retrieve the first plurality of search results, receiving the first plurality of search results, and causing display of the at least top results of the first plurality of search results are based on a determination that the cache does not contain sorted results for an LLM-assisted deep search that is applicable to the user query (Fig. 4; [0119]-[0121]: In some embodiments, the action response data 458a-n may indicate whether or not the corresponding component is able to respond (e.g., the action response data 458a may include a Boolean value such as “yes” or “no” or other similar indications). In some embodiments, the shortlister language model 640 may filter and/or rank the action response data 458a-n based on information included in the prompt data 615)… the LLM orchestrator component 430 may further include a memory storage (not illustrated) which may store various information associated with the processing performed).
Regarding Claim 19, the combined teachings of Papayiannis and Ni disclose the system of claim 16, wherein the operations further comprise:
providing, as input to a third LLM, a third prompt requesting generation of a relevance score for each first search result among the first plurality of search results based on the primary intent ([0032]: In some embodiments, the prompt generation component 110 may generate prompt data representing a prompt for input to the natural language and prosody LLM 117… with respect to FIG. 8, the ASR component 850 may determine ASR data that includes an ASR N-best list including multiple ASR hypotheses and corresponding confidence scores representing what the user may have said);
receiving, from the third LLM, the relevance score for each first search result ([0032]: The ASR hypotheses may include text data, token data, ASR confidence score, etc. as representing the input utterance); and
sorting the first plurality of search results based on their relevance scores; wherein causing display of the at least top results of the first plurality of search results comprises causing display of at least top results of the first plurality of search results that have been sorted based on their relevance scores ([0032]: with respect to FIG. 8, the ASR component 850 may determine ASR data that includes an ASR N-best list including multiple ASR hypotheses and corresponding confidence scores representing what the user may have said).
Regarding Claim 20, the combined teachings of Papayiannis and Ni disclose the system of claim 16, wherein the user query is received from an electronic device associated with a user ([0034]: As used herein, a “dialog” may refer to multiple related user inputs and system 100 outputs (e.g., through user device(s) 410), wherein identifying the primary intent includes one of:
selecting the primary intent based on a top result as received from the first LLM ([0094]: TABLE-US-00007 { Select the top prioritized task given the ultimate goal of [user input data 102 (or a representation of a determined intent included in the user input data 102] Here are the completed tasks, their potential responses, and user inputs so far);
selecting the primary intent based on weighted values of the plurality of intents ([0056]: The natural language output head 270 processes the intermediate natural language processing data 122n to generate a posteriorgram 275 representing a result of applying one or more weights (determined as a result of training the natural language output head 270 for the natural language generation task) to the intermediate natural language processing data 122n; [0070]: A neural network model includes trainable parameters (e.g., “weights”) that indicate how much weight (e.g., in the form of an arithmetic multiplier) a cell should give to a particular input when generating an output);
selecting the primary intent based on information about the user, the information about the user including information collected based on a search history of the user; or selecting the primary intent based on user selection from among a list of disambiguation choices that are caused to be displayed to the user ([0094]: TABLE-US-00007 { Select the top prioritized task given the ultimate goal of [user input data 102 (or a representation of a determined intent included in the user input data 102] Here are the completed tasks, their potential responses, and user inputs so far: [completed tasks, potential responses associated with the tasks, dialog history; [0126]: [0126] The personalized context data 467 may represent… historical user interaction data… dialog history data)).
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