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 .
DETAILED ACTION
Introduction
This office action is in response to Applicant’s response to submission filed on 12/30/2024. Claims 1-20 are pending of which claims 1, and 11 are independent. As such, claims 1-20 have been examined.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1-2, 7, 10-12, 17 and 20 are rejected under 35 U.S.C. 102 (a)(2) as being anticipated by D’Agostino (US 20250307290).
Regarding Claim 1, D’Agostino discloses: 1. A computer-implemented method that when executed on data processing hardware (see fig. 1 system configuration, including smart phone and service provider device) causes the data processing hardware to perform operations comprising: receiving a query from a user specifying a task for an assistant large language model (LLM) to perform (see fig. 1, conversation between user and its associated smart phone), the query captured by an assistant-enabled device associated with the user; ([0091] According to various embodiments, in addition to providing post-processing on call logs to generate vectors, as described in the example of FIG. 4A, the LLM framework 440 may also receive real-time interaction content from an active communication session between the source device 410 and the service provider device 420 and generate content which can be output during the communication session. For example, the LLM framework 440 may generate an instruction, a question, a query, a product offer, or the like, which can be displayed on the user interface 422 of the service provider device 420. As another example, the LLM framework 440 may generate a product offer, verification question, or the like, which can be displayed on the user interface 412 of the source device 410.,) Also see para 0038, and figs. 1 and 4a.
processing the query to identify, from a datastore of a plurality of embedding chunks each previously stored in the datastore by the assistant LLM, a particular embedding chunk that is relevant to the query; ([0144] In one embodiment, an apparatus comprising a memory and a processor coupled to the memory is configured to generate a prompt that includes the subset of vectors and input the prompt to an LLM during its execution. Upon receiving interaction content from a communication session between a source device and a service provider device, the processor identifies specific search criteria from the content. The search criteria are the basis for selecting relevant vectors from a vector database and retrieving a subset of vectors comprising previous interaction content between the user and the service provider.)
generating an on-the-fly prompt by stitching the particular embedding chunk and the query together; ([0144] The processor generates a prompt, including the subset of vectors, and inputs it to the LLM during its execution. Additionally, the processor may generate additional text based on the search criteria and add it as part of the prompt before inputting it to the LLM. The additional text further enhances the context provided to the LLM, improving the relevance and accuracy of the generated response. During the execution of the LLM, communication between the processor, memory, and the LLM occurs seamlessly, ensuring that the LLM has access to the necessary information to generate an appropriate response. The generated response is outputted to at least one of the source and service provider devices.)
and processing, by the assistant LLM, the on-the-fly prompt to generate a personalized response to the query. ([0144] During the execution of the LLM, communication between the processor, memory, and the LLM occurs seamlessly, ensuring that the LLM has access to the necessary information to generate an appropriate response. The generated response is outputted to at least one of the source and service provider devices.)
Regarding Claim 2, D’Agostino discloses all the elements of claim 1,
D’Agostino further discloses: wherein the task specified by the query comprises a retrieval request for the assistant LLM to retrieve one or more documents stored in a personal repository associated with the user. ([0144] In one embodiment, an apparatus comprising a memory and a processor coupled to the memory is configured to generate a prompt that includes the subset of vectors and input the prompt to an LLM during its execution. Upon receiving interaction content from a communication session between a source device and a service provider device, the processor identifies specific search criteria from the content. The search criteria are the basis for selecting relevant vectors from a vector database and retrieving a subset of vectors comprising previous interaction content between the user and the service provider.)
Regarding Claim 7, D’Agostino discloses all the elements of claim 1,
D’Agostino further discloses: wherein receiving the query from the user comprises one or more of: receiving audio data corresponding to the query, the audio data spoken by the user and captured by the assistant-enabled device; ([0087] Interaction content from the call may be captured by the software application in the form of audio which is then converted to text by a word to text model, or the like.)
receiving, in a graphical user interface (GUI) displayed on a screen in communication with the assistant-enabled device, a user input indication indicating a spatial input applied at a first location in the GUI;
or receiving a textual representation of the prompt. ([0104] In one embodiment, the system uses a chatbot to interact with customers seeking financial information and assistance. Message interaction occurs between users seeking financial information and assistance and the chatbot deployed on a digital platform. Users initiate conversations by sending queries or messages through the chat interface provided by the platform. Users may inquire about financial topics such as banking services, investment options, loan products, insurance policies, or general financial advice. The message content could include questions, requests for information, or specific queries regarding financial products or services. The chatbot utilizes LLM technology to extract contextual attributes from the message content.)
Regarding Claim 10, D’Agostino discloses all the elements of claim 1,
D’Agostino further discloses: wherein the operations further comprise: receiving local context associated with the query; ([0144] the processor identifies specific search criteria from the content. The search criteria are the basis for selecting relevant vectors from a vector database and retrieving a subset of vectors comprising previous interaction content between the user and the service provider. The processor generates a prompt, including the subset of vectors, and inputs it to the LLM during its execution. Additionally, the processor may generate additional text based on the search criteria and add it as part of the prompt before inputting it to the LLM.)
and concatenating the on-the-fly prompt with the local context, ([0144] The processor generates a prompt, including the subset of vectors, and inputs it to the LLM during its execution. Additionally, the processor may generate additional text based on the search criteria and add it as part of the prompt before inputting it to the LLM.)
wherein processing the on-the-fly prompt to generate the personalized response to the query comprises processing, by the assistant LLM, the on-the-fly prompt concatenated with the local context to generate the personalized response to the query. ([0144] The processor generates a prompt, including the subset of vectors, and inputs it to the LLM during its execution. Additionally, the processor may generate additional text based on the search criteria and add it as part of the prompt before inputting it to the LLM. The additional text further enhances the context provided to the LLM, improving the relevance and accuracy of the generated response. During the execution of the LLM, communication between the processor, memory, and the LLM occurs seamlessly, ensuring that the LLM has access to the necessary information to generate an appropriate response. The generated response is outputted to at least one of the source and service provider devices.)
Regarding Claim 11, D’Agostino discloses: 11. A system comprising: data processing hardware; ([0210] The above embodiments may be implemented in hardware, in a computer program executed by a processor,) and memory hardware in communication with the data processing hardware, ([0210] A computer program may be embodied on a computer readable medium, such as a storage medium. For example, a computer program may reside in random access memory (“RAM”), flash memory, read-only memory (“ROM”), erasable programmable read-only memory (“EPROM”), electrically erasable programmable read-only memory (“EEPROM”), registers, hard disk, a removable disk, a compact disk read-only memory (“CD-ROM”), or any other form of storage medium known in the art.) the memory hardware storing instructions that when executed on the data processing hardware cause the data processing hardware to perform operations comprising:
As for the rest of the claim, they recite similar elements to the method of claim 1, therefore the rationale applied in rejection of claim 1 is also applicable.
Claim 12 is a system claim with limitations similar to the limitations of Claim 2 and is rejected under similar rationale.
Claim 17 a system claim with limitations similar to the limitations of Claim 7 and is rejected under similar rationale.
Claim 20 is a system claim with limitations similar to the limitations of Claim 10 and is rejected under similar rationale.
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.
Claims 3 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over D’Agostino, in view of Pena (US 20260030275).
Regarding Claim 3, D’Agostino discloses all the elements of claim 1,
D’Agostino further discloses: and storing the embedding chunks in the datastore. ([0005] store the vectorized data within a vector database along with a timestamp.)
D’Agostino does not appear to disclose the details of the retrieval process recited below.
Pena in the related art discloses: wherein the plurality of embedding chunks are stored in the datastore during an indexing process by: obtaining a plurality of documents stored in a personal repository associated with the user; ([0019] Queries and resource documents can be encoded with rich metadata, capturing each element's relationship and position within an overall documentation scheme. Structural analysis can be performed to extract fields, segment text, and associate contextual tags with passages based on attributes such as heading, sections, and formatting cues. By representing queries and passages using embeddings of enriched content and relationships, highly similar concepts can be disambiguated based on their contextual meaning. Matching embeddings according to similarity scores retrieves semantically pertinent passages. Re-ranking a set of semantically pertinent passages with a machine learning model enables further refinement of the rankings to identify passages that are more relevant and targeted to a query. Exploiting contextual information throughout processing enables more precise linking of queries to relevant explanatory materials within extensive documentation and efficient and accurate information retrieval.)
assigning each document of the plurality of documents into one or more document chunks; ([0019] Structural analysis can be performed to extract fields, segment text, and associate contextual tags with passages based on attributes such as heading, sections, and formatting cues.) [segmenting text into passages reads on creating document chunks]
for each corresponding document chunk of the one or more document chunks,
processing the corresponding document chunk to: extract, from the corresponding document chunk, metadata associated with each of the documents assigned to the corresponding document chunk; ([0019] Structural analysis can be performed to extract fields, segment text, and associate contextual tags with passages based on attributes such as heading, sections, and formatting cues.)
and encode the respective metadata extracted from the corresponding document chunk and the documents assigned to the corresponding document chunk to generate a corresponding embedding chunk; ([0019] Queries and resource documents can be encoded with rich metadata, capturing each element's relationship and position within an overall documentation scheme. Structural analysis can be performed to extract fields, segment text, and associate contextual tags with passages based on attributes such as heading, sections, and formatting cues. By representing queries and passages using embeddings of enriched content and relationships, highly similar concepts can be disambiguated based on their contextual meaning. Matching embeddings according to similarity scores retrieves semantically pertinent passages. Re-ranking a set of semantically pertinent passages with a machine learning model enables further refinement of the rankings to identify passages that are more relevant and targeted to a query. Exploiting contextual information throughout processing enables more precise linking of queries to relevant explanatory materials within extensive documentation and efficient and accurate information retrieval.)
D’Agostino and Pena are considered analogous art. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of D’Agostino to combine the teaching of Pena, because exploiting contextual information throughout processing enables more precise linking of queries to relevant explanatory materials within extensive documentation and efficient and accurate information retrieval (Pena, [0019]).
Claim 13 is a system claim with limitations similar to the limitations of Claim 3 and is rejected under similar rationale.
Claims 4-5 and 14-15 are rejected under 35 U.S.C. 103 as being unpatentable over D’Agostino, in view of Pena (US 20260030275), and further in view of Berglund (US 20240403341).
Regarding Claim 4, D’Agostino and Pena discloses all the elements of claim 3,
D’Agostino further discloses: wherein processing the on-the-fly prompt to generate the personalized response to the query comprises: querying, using the on-the-fly prompt, the particular embedding chunk stored in the datastore to identify, from the documents assigned to the document chunk associated with the particular embedding chunk, one or more documents relevant to the query; ([0144] generate a prompt that includes the subset of vectors and input the prompt to an LLM during its execution. Upon receiving interaction content from a communication session between a source device and a service provider device, the processor identifies specific search criteria from the content. The search criteria are the basis for selecting relevant vectors from a vector database and retrieving a subset of vectors comprising previous interaction content between the user and the service provider. The processor generates a prompt, including the subset of vectors, and inputs it to the LLM during its execution. Additionally, the processor may generate additional text based on the search criteria and add it as part of the prompt before inputting it to the LLM. The additional text further enhances the context provided to the LLM, improving the relevance and accuracy of the generated response. During the execution of the LLM, communication between the processor, memory, and the LLM occurs seamlessly, ensuring that the LLM has access to the necessary information to generate an appropriate response. The generated response is outputted to at least one of the source and service provider devices.)
D’Agostino and Pena do not appear to disclose summarizing the relevant documents.
Berglund in the related art discloses: and summarizing the one or more documents identified as being relevant to the query to generate a summary of relevant documents. ([0013] To solve these problems and to generate a search system that improves both conventional search techniques and LLM-based chatbot techniques, disclosed herein is a search platform associated with a content management system that combines semantic search and large language models (LLMs) to help users interact with content. When a user submits a search query, the search platform identifies relevant content and leverages the relevant content as a knowledge base or context for an LLM to generate an answer to the search query. For example, users can submit queries such as “What are the top product differentiators for FY 2023?” “Summarize issues faced by the finserv industry and how Company A helps address these issues,” or “key takeaways from product overview deck.” A semantic search can be performed to identify content that are relevant to the submitted queries. The queries and the relevant content items are sent to the LLM to formulate an answer to the queries based on the content items. The output returned in response to the query can therefore include a portion of text generated by the LLM (such as a bulleted list of key takeaways from a product overview deck), in addition to, or instead of, a list of semantically matched content items.) [Berglund also discloses- querying, using the on-the-fly prompt, the particular embedding chunk stored in the datastore to identify, from the documents assigned to the document chunk associated with the particular embedding chunk, one or more documents relevant to the query;]
D’Agostino, Pena and Berglund are considered analogous art. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of D’Agostino and Pena to combine the teaching of Berglund, because the approach described generate a search system that improves both conventional search techniques and LLM-based chatbot techniques, that combines semantic search and large language models (LLMs) to help users interact with content (Berglund, [0013]).
Regarding Claim 5, D’Agostino/Pena/Berglund discloses all the elements of claim 4,
D’Agostino further discloses: wherein the operations further comprise displaying, in a graphical user interface (GUI) displayed on a screen in communication with the assistant-enabled device associated with the user, the personalized response to the query. ([0049] For example, a response may be generated by the one or more LLMs 122 based on one or more vectors in the vector DB 140. The response may include a product offering, a verification question, an informational notice, a chatbot response, a custom instruction, and the like. The response, which may be in the form of audio, text, images and/or video, may be output to at least one of a user interface 112 of the source device 110 and a user interface 132 of the service provider device 130. In some embodiments, the one or more LLMs 122 may generate a first response that is output on the user interface 112 of the source device 110 and a second response that is output on the user interface 132 of the service provider device 130, simultaneously with the output of the first response on the user interface 112 of the source device 110.) Also see para 0068 which mentions an GUI.
Claim 14 is a system claim with limitations similar to the limitations of Claim 4 and is rejected under similar rationale.
Claim 15 is a system claim with limitations similar to the limitations of Claim 5 and is rejected under similar rationale.
Claims 6 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over D’Agostino, in view of Pena (US 20260030275), further in view of Berglund (US 20240403341), and furthermore in view of Sonwane (US 20170046055).
Regarding Claim 6, D’Agostino/Pena/Berglund disclose all the elements of claim 5,
D’Agostino/Pena/Berglund do not appear to disclose GUI containing a ranked list of relevant documents.
Sonwane in the related art discloses: wherein displaying the personalized response to the query comprises at least one of: displaying, in the GUI, a graphical element representing a ranked list of the one or more documents identified as being relevant to the query; ([0033] At 240, the infographics are rendered in an order based on the determined ranks in a tile of the tile-based graphical user interface (GUI). In one embodiment, the tile based GUI includes a number of tiles and a tile is associated with a document. For example, when a list of ten relevant documents is extracted by a document listing module based on the request, ten tiles in the GUI are presented and each tile represents a document. Further, the tile displays the infographics associated with the document in the order based on the determined ranks. In one exemplary embodiment, the GUI for each document may be presented in a “tile view” or in a “full-screen view.” The user may switch between the GUI in the tile view and the GUI in full-screen view.)
D’Agostino, Pena, Berglund and Sonwane are considered analogous art. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of D’Agostino/Pena/Berglund to combine the teaching of Sonwane, because the technologies described herein can be used for accessing data or information in a database platform or a data repository. Adoption of the technologies can provide efficient access to the data in both transactional (e.g., previously created data) and analytical scenarios (e.g., created new data or update existing data) while allowing both data analysts as well as end users (e.g., customers) the flexibility to efficiently access and manage the data (Sonwane, [0013]).
Claim 16 is a system claim with limitations similar to the limitations of Claim 6 and is rejected under similar rationale.
Claims 8-9 and 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over D’Agostino, in view of Shin (US 20230325148).
Regarding Claim 8, D’Agostino discloses all the required elements of claim 7,
D’Agostino does not appear to disclose activating GUI for spatial input and a speech recognition model.
Shin in the related art discloses: wherein the operations further comprise: detecting a trigger event; ([0005] Implementations of the disclosure may include one or more of the following optional features. In some implementations, the operations also include detecting a trigger event, and in response to detecting the trigger event,)
and in response to detecting the trigger event, activating: the GUI displayed on the screen to enable detection of spatial inputs; ([0005] the operations also include detecting a trigger event, and in response to detecting the trigger event, activating: the GUI displayed on the screen to enable detection of spatial inputs;)
and a speech recognition model to enable the performance of speech recognition on incoming audio data captured by the assistant-enabled device. ([0005] the operations also include detecting a trigger event, and in response to detecting the trigger event, activating: the GUI displayed on the screen to enable detection of spatial inputs; and the speech recognition model to enable the performance of speech recognition on incoming audio data captured by the assistant-enabled device.)
D’Agostino, and Shin are considered analogous art. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of D’Agostino to combine the teaching of Shin, because the technologies described herein provides flexibility and efficiency by enabling multiple options to activate the assistant (Shin, [0005]).
Regarding Claim 9, D’Agostino and Shin discloses all the required elements of claim 8,
Shin further discloses: wherein detecting the trigger event comprises one of: receiving, in the GUI displayed on the screen, a user input indication indicating selection of a graphical element; ([0005] Alternatively, detecting the trigger event may include one of: receiving, in the GUI displayed on the screen, a user input indication indicating selection of a graphical element; receiving a user input indication indicating selection of a physical button disposed on the assistant-enabled device; detecting a predefined gesture performed by the user; or detecting a predefined movement/pose of the assistant-enabled device.)
receiving a user input indication indicating selection of a physical button disposed on the assistant-enabled device; ([0005] receiving a user input indication indicating selection of a physical button disposed on the assistant-enabled device;)
detecting a predefined gesture performed by the user; ([0005] detecting a predefined gesture performed by the user;)
or detecting a predefined movement/pose of the assistant-enabled device. ([0005] or detecting a predefined movement/pose of the assistant-enabled device.)
Where the rationale for the combination would be similar to the one already provided.
Claim 18 is a system claim with limitations similar to the limitations of Claim 8 and is rejected under similar rationale.
Claim 19 is a system claim with limitations similar to the limitations of Claim 9 and is rejected under similar rationale.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure: Arefaine US 20250284742 – discloses in para 0005, “a system described herein can include a chatbot system communicatively coupled to a user interface to receive a query therefrom and a web server communicatively coupled to both the user interface and the chatbot system. The web server can be configured to process a query submitted via the user interface to generate one or more vectors representing the query and to compare the one or more vectors from the query with one or more vectors generated from a document to select a chunk of the document based on the comparison. The system can further include a large language model configured to receive a prompt including the query and the chunk of the document and to provide a response to the query to the web server. The web server can be configured to provide the response from the large language model and the chunk of the document to the chatbot system for presentation on the user interface in response to the query.” Also See Abstract, para 0003-0004, 0006, and fig. 1 for additional details.
Suk US 20250348503 – discloses method/system for advanced retrieval-augmented generation through metadata and search engine mixing. It discloses prompt including the query and the data retrieved using each retriever of the plurality of retrievers. See Abstract, and figs. 3-5 for additional details.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Philip H Lam whose telephone number is (571)272-1721. The examiner can normally be reached 9 AM-3 PM Pacific time.
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, Bhavesh Mehta can be reached on 571-272-7453. 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.
/PHILIP H LAM/ Examiner, Art Unit 2656
Prosecution Insights