DETAILED ACTION
Notice of 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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 11/22/2024 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an
abstract idea without significantly more.
The Independent claims 1, 11, 20 recite “receiving, from a user interface, a query in natural language describing challenges encountered by a user”; “obtaining, in runtime, one or more text segments that are semantically related to the query”; “composing, in runtime, a prompt using a prompt template, wherein the prompt template includes a placeholder for receiving the one or more text segments”; “prompting, in runtime, a generative artificial intelligence (AI) model using the prompt to determine a ranked list of documents containing solutions to address the challenges”; “and presenting a response generated by the generative AI model on the user interface”. The limitations above as drafted, is a process that, under its broadest reasonable interpretation, covers a mental process, as this could be performed in the human mind or with the aid of pen and paper.
The limitation of " receiving ... ",’obtaining..”, "composing ... ", "prompting ... ",’presenting…” as drafted covers mental activities. More specifically, a person can receive a query in natural language from another person which describes his struggle/challenge with something, the person can obtain semantically similar text segments of the query from some documents, he can rank the list of documents that can solve the other person’s problem and present the solution to the other person on the paper. The above steps, as drafted, is a process that under its broadest reasonable interpretation, covers performance of the limitation in the mind. There is, nothing in the claim element precludes the step from practically being performed in the human mind. Additionally, the mere nominal recitation of a generic computer appliance does not take the claim limitation out of the mental processes grouping. Thus, the claim recites a mental process.
The claims recite the additional limitation of “memory’, “processor”,” computer readable storage media”, “ non-transitory computer readable media”, “user interface”, “generative artificial intelligence ( AI) model” for performing the method, which is recited at a high level of generality and are recited as performing generic computer functions routinely used in computer applications. The current specification in paragraph [0020],[0054],[0055], specifies “ generative AI model 114 can be Generative Pre-trained Transformer (GPT) or BERT-based models, developed by OpenAI, Bidirectional Encoder Representations from Transforms (BERT) by Google, A Robustly Optimized BERT Pretraining Approach developed by Facebook AI, Megatron-LM of NVIDIA, or the like”, which is generic and not sufficient to amount to significantly more than the judicial exception. “memory’, “processor”,” computer readable storage media”, “ non-transitory computer readable media”, “user interface” , all those are recited at a high level of generality and are recited as performing generic computer functions routinely used in computer applications. This is no more than mere instructions to apply the exception using a generic computer component. Accordingly, this additional elements does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea.
Thus, taken alone, the additional elements do not amount to significantly more than the above identified judicial exception (the abstract idea). Looking at the limitations as an ordered combination adds
nothing that is not already present when looking at the elements taken individually. There is no indication
that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation. Claims 1, 11 and 20 are therefore not drawn to eligible subject matter as this is directed to an abstract idea without
significantly more than the abstract idea.
Claims 2, 12 recite “wherein the operation of obtaining one or more text segments semantically related to the query comprises converting the query into an input vector embedding”, where converting a query into an vector embedding could be performed with the aid of pen and paper. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception, as claims 2, 12 do not recite any additional limitations. The claims as drafted, are not patent eligible.
Claims 3, 13 recite “wherein the operation of obtaining one or more text segments semantically related to the query further comprises measuring similarities between the input vector embedding and a plurality of vector embeddings stored in a vector database”, where comparing the input vector embedding with other vector embedding in the database to find out similarities, is an evaluation, observation, could be performed in human mind or with the aid of pen and paper. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception, as claims 3, 13 do not recite any additional limitations. The claims as drafted, are not patent eligible.
Claims 4, 14 recite “wherein the operation of obtaining one or more text segments semantically related to the query further comprises ranking the similarities and identifying top N vector embeddings that are associated with highest similarities, wherein N is a predefined positive integer”, where ranking the similarities and identifying top input vector embedding associated with highest similarities, is an evaluation, observation, could be performed in human mind or with the aid of pen and paper. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception, as claims 4, 14 do not recite any additional limitations. The claims as drafted, are not patent eligible.
Claims 5, 15 recite “wherein the operations further comprise creating the vector database based on a set of documents collected from a plurality of data sources”, where creating the vector database based on the set of documents from different sources, could be performed with the aid of pen and paper. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception, as claims 5, 15 do not recite any additional limitations. The claims as drafted, are not patent eligible.
Claims 6, 16 recite “wherein the operation of creating the vector database comprises cleaning the set of documents, wherein the cleaning removes duplicates and special characters from the set of documents, and organizes remaining text in the set of documents in respective text fields”, where during the creation of vector database removing duplicates, special characters, organizing the remaining texts, could be performed with the aid of pen and paper. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception, as claims 6, 16 do not recite any additional limitations. The claims as drafted, are not patent eligible.
Claim 7 recites “wherein the operation of creating the vector data comprises dividing the set of documents into a plurality of text segments”, where during the creation of vector database sets of documents are divided into a plurality of text segments, could be performed with the aid of pen and paper. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception, as claim 7 does not recite any additional limitations. The claim as drafted, is not patent eligible.
Claim 8 recites “wherein the operation of creating the vector data further comprises converting the plurality of text segments into respective vector embeddings, and indexing the plurality of text segments and the respective vector embeddings in the vector database”, where the converted text embedding and the associated text segment is indexed in the database, which could be performed with the aid of pen and paper. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception, as claim 8 does not recite any additional limitations. The claim as drafted, is not patent eligible.
Claims 9, 18 recite “wherein the operations further comprise periodically updating the vector database, comprising scanning the plurality of data sources to detect whether there is an update to the set of documents”, where updating the vector database by checking the plurality of the documents, could be performed with the aid of pen and paper. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception, as claims 9, 18 do not recite any additional limitations. The claims as drafted, are not patent eligible.
Claims 10, 19 recite “wherein the operations further comprise retrieving reference sources based on the response generated by the generative AI model, and presenting the reference sources on the user interface”, where presenting the reference sources based on the response to the user, could be performed with the aid of pen and paper. The claims recite additional element “generative AI model”, which is specified in paragraph [0020],[0054],[0055], “ generative AI model 114 can be Generative Pre-trained Transformer (GPT) or BERT-based models, developed by OpenAI, Bidirectional Encoder Representations from Transforms (BERT) by Google, A Robustly Optimized BERT Pretraining Approach developed by Facebook AI, Megatron-LM of NVIDIA, or the like”, which is generic and not sufficient to amount to significantly more than the judicial exception. The claims 10, 19 as drafted, are not patent eligible.
Claim 17 recites “wherein creating the vector data comprises dividing the set of documents into a plurality of text segments, converting the plurality of text segments into respective vector embeddings, and indexing the plurality of text segments and the respective vector embeddings in the vector database”, where during the creation of vector database sets of documents are divided into a plurality of text segments, converted text embedding and the associated text segment is indexed in the database, could be performed with the aid of pen and paper. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception, as claim 17 does not recite any additional limitations. The claim as drafted, is not patent eligible.
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 of this title, 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 1-3, 5-8, 10-13, 15-17, 19 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Vouitsis et al. ( US 20260056981 A1), hereinafter referenced as Vouitsis, in view of Addanki et al. (US 20250103625 A1), hereinafter referenced as Addanki.
Regarding Claim 1, Vouitsis teaches a computing system comprising:
Memory ( Vouitsis: Para.[0148], Fig. 12, memory 1204);
one or more hardware processors coupled to the memory ( Vouitsis: Para.[0148], Fig. 12, processor 1202 operatively coupled to at least one memory 1204);
and one or more computer readable storage media storing instructions that, when loaded into the memory, cause the one or more hardware processors to perform operations comprising: receiving, from a user interface, a query in natural language describing challenges encountered by a user ( Vouitsis: Para.[0149], Fig. 12, computer readable storage media that stores instructions executed or executable by the processor 1202, and input and output data used or generated during execution of the instructions. The memory 1204 may also include non-volatile memory used to store input and/or output data-e.g., within a database-along with program code containing executable instructions ):
receiving, from a user interface, a query [in natural language describing challenges encountered by a user] ( Vouitsis: Para.[0064], Fig. 2, the user query 212 may be received from a user via, for example a user interface 230);
composing, in runtime, a prompt using a prompt template, wherein the prompt template includes a placeholder for receiving the one or more text segments ( Vouitsis: Para.[0076],[0080], illustrates the prompt template which includes a placeholder ( enclosed in curly brackets) for receiving one or more segments, such as “The following are passages related to a query { {query}} [1] { {chunk_1}} [2] { { chunk_2}}”. Para.[0055], chunk is the text segments or subdivided part of a document. Para.[0018], the method for generating a response to a query, is executed in a computing environment ( runtime));
prompting, in runtime, a generative artificial intelligence (AI) model using the prompt to determine a ranked list of documents containing solutions to address the challenges ( Vouitsis: Para.[0075],[0076], Fig. 2, the re-ranker LLM 216 is provided the original user query 212, the set of chunks 236 retrieved by the information retrieval system 220 and one or more re-ranker (RR) prompts 238 which instruct the re-ranker LLM 216 to rank the set of chunks 236 based on their relevance to the original user query 212. Prompt(s) 238 may be configured to cause the re-ranker LLM 216 to perform listwise ranking. Para.[0018], the method for generating a response to a query, is executed in a computing environment ( runtime)) ;
and presenting a response generated by the generative AI model on the user interface ( Vouitsis: Para.[0085], [0086], Fig. 2, Once the subset of chunks 240 has been selected from the ranking of the set of chunks 236, the generation LLM 218 is used to generate a response 210 to the original query 212 based on the subset of chunks 240. The response 210 is provided to a client device 190 via the user interface 230).
Vouitsis while teaching the computer implemented system of claim 1, fails to explicitly teach the claimed, receiving, from a user interface, a query in natural language describing challenges encountered by a user; obtaining, in runtime, one or more text segments that are semantically related to the query.
However, Addanki does teach the claimed, receiving, from a user interface, a query in natural language describing challenges encountered by a user ( Addanki: Para.[0066],Fig. 2, a user, via the interface provided on a device, may submit a user query 232 to the knowledge bot 200. The query may be a question in natural language format, such as "how do I reset my password," "how do I generate a document using your XYZ program," etc.);
obtaining, in runtime, one or more text segments that are semantically related to the query ( Addanki: Para.[0087], [0088], Fig. 3, the document retrieval module 204 may use the text-based retrieval module 302 and the semantic-based retrieval module 304 to retrieve documents, from the corpus of documents 312, that are relevant to the query).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Addanki’s teaching of a knowledge bot which includes a text-based search engine and a semantic-based search engine, configurable to interact with users across multiple domains , into the system and method generating a response to a query using large language models and based on a corpus of documents, taught by Vouitsis, because, this would improve the quality of the responses and the dialogue with the user (Addanki, Para.[0029]).
Claim 11 is a computer implemented method claim performing the steps in computer implemented system claim 1 above and as such, claim 11 is similar in scope and content to claim 1 and therefore, claim 11 is rejected under similar rationale as presented against claim 1 above.
Claim 20 is non-transitory computer readable media claim having encoded thereon computer-executable instructions causing one or more processors to perform a method ( Vouitsis: Para.[0022], [0149], Fig. 12, computer readable storage media that stores instructions executed or executable by the processor 1202, and input and output data used or generated during execution of the instructions. The memory 1204 may also include non-volatile memory used to store input and/or output data----e.g., within a database-along with program code containing executable instructions ), comprising the steps in computer implemented system claim 1 above and as such, claim 20 is similar in scope and content to claim 1 and therefore, claim 20 is rejected under similar rationale as presented against claim 1 above.
Regarding Claim 2, Vouitsis in view of Addanki teach the computing system of claim 1. Vouitsis further teaches, wherein the operation of obtaining one or more text segments semantically related to the query comprises converting the query into an input vector embedding ( Vouitsis: Para.[0124], Fig. 9, the query 902is converted into a plurality of embeddings (i.e., into a multi-dimensional vector) that mathematically represents the semantic meaning of the query 902).
Claim 12 is a computer implemented method claim performing the steps in computer implemented system claim 2 above and as such, claim 12 is similar in scope and content to claim 2 and therefore, claim 12 is rejected under similar rationale as presented against claim 2 above.
Regarding Claim 3, Vouitsis in view of Addanki teach the computing system of claim 2. Vouitsis further teaches, wherein the operation of obtaining one or more text segments semantically related to the query further comprises measuring similarities between the input vector embedding and a plurality of vector embeddings stored in a vector database ( Vouitsis: Para.[0124], Fig. 9, The search engine 910 compares the multi-dimensional vector for the query to the multi-dimensional vectors in all vector search fields of the vector search index 912 to identify the items (e.g., chunks) that are most relevant to the query).
Claim 13 is a computer implemented method claim performing the steps in computer implemented system claim 3 above and as such, claim 13 is similar in scope and content to claim 3 and therefore, claim 13 is rejected under similar rationale as presented against claim 3 above.
Regarding Claim 5, Vouitsis in view of Addanki teach the computing system of claim 3. Vouitsis further teaches, wherein the operations further comprise creating the vector database based on a set of documents collected from a plurality of data sources ( Vouitsis: Para.[0045],[0114],[0122], Figs 1, 9, vector search index 912 multiple vectors per item and the search engine 910 is configured to perform a multi-vector search on the vector search index to identify items that are relevant to a query. The vector search index 912 may be stored in the data store 908 ( vector database). Source database consists of one or more databases).
Claim 15 is a computer implemented method claim performing the steps in computer implemented system claim 5 above and as such, claim 15 is similar in scope and content to claim 5 and therefore, claim 15 is rejected under similar rationale as presented against claim 5 above.
Regarding Claim 6, Vouitsis in view of Addanki teach the computing system of claim 5. Vouitsis further teaches, wherein the operation of creating the vector database comprises cleaning the set of documents, wherein the cleaning removes duplicates and special characters from the set of documents, and organizes remaining text in the set of documents in respective text fields ( Vouitsis: Para.[0066],[0067], indexing a set of documents could be done by tokenization. In tokenization, a tokenizer divides the text in each field of each document into tokens and may discard some characters, such as punctuation, normalizing by removing stop-words, converting all text to small letters ( organizing the texts). The tokens may then be stored in an inverted index, which allows for fast, full-text search. An inverted index enables full-text search by mapping all of the unique terms to the document in which they were found. There may be an inverted index for each searchable field).
Claim 16 is a computer implemented method claim performing the steps in computer implemented system claim 6 above and as such, claim 16 is similar in scope and content to claim 6 and therefore, claim 16 is rejected under similar rationale as presented against claim 6 above.
Regarding Claim 7, Vouitsis in view of Addanki teach the computing system of claim 5. Vouitsis further teaches, wherein the operation of creating the vector data comprises dividing the set of documents into a plurality of text segments ( Vouitsis: Para.[0118], [0121],[0122], Fig. 9, plurality of text segments or chunks 914 are generated from a corpus of documents 920. Using an embedding model, 914 is converted into a set of embeddings and stored in the vector search index 912, which is stored in the data store 908 ( vector database)).
Regarding Claim 8, Vouitsis in view of Addanki teach the computing system of claim 7. Vouitsis further teaches, wherein the operation of creating the vector data further comprises converting the plurality of text segments into respective vector embeddings, and indexing the plurality of text segments and the respective vector embeddings in the vector database ( Vouitsis: Para.[0121], [0122], Fig. 9, the index engine 906 is configured to generate a vector search index 912 for a collection of items 914 ( collection of plurality of text segments). Specifically, the index engine 906 is configured to, for each item ( e.g., each chunk), convert, using an embedding model, that item (e.g., chunk) 914 into a set of embeddings (i.e., a multi-dimensional vector) and each piece of synthetic information for that item (e.g., chunk) 914 into a set of embeddings (i.e., a multi-dimensional vector). The vector search index 912 is stored in the data store 908 ( vector database)).
Regarding Claim 10, Vouitsis in view of Addanki teach the computing system of claim 1. Vouitsis further teaches, wherein the operations further comprise retrieving reference sources based on the response generated by the generative AI model, and presenting the reference sources on the user interface ( Vouitsis: Para.[0086],[0087],Figs, 2, 4, response 210 generated by LLM 218 and presented on the user interface, may comprise a list of documents which were relied on to generate the response 210. In other words, the response 210 may comprise citations. For example, the response 210 shown in FIG. 4 lists a single reference document 404-i.e., document "EBKM231147403918758.md").
Claim 19 is a computer implemented method claim performing the steps in computer implemented system claim 10 above and as such, claim 19 is similar in scope and content to claim 10 and therefore, claim 19 is rejected under similar rationale as presented against claim 10 above.
Regarding Claim 17 , Vouitsis in view of Addanki teach the computer implemented method of claim 15.T Vouitsis further teaches, wherein creating the vector data comprises dividing the set of documents into a plurality of text segments ( Vouitsis: Para.[0118], [0121],[0122], Fig. 9, plurality of text segments or chunks 914 are generated from a corpus of documents 920. Using an embedding model, 914 is converted into a set of embeddings and stored in the vector search index 912, which is stored in the data store 908 ( vector database)),
converting the plurality of text segments into respective vector embeddings, and indexing the plurality of text segments and the respective vector embeddings in the vector database ( Vouitsis: Para.[0121], [0122], Fig. 9, the index engine 906 is configured to generate a vector search index 912 for a collection of items 914 ( collection of plurality of text segments). Specifically, the index engine 906 is configured to, for each item ( e.g., each chunk), convert, using an embedding model, that item (e.g., chunk) 914 into a set of embeddings (i.e., a multi-dimensional vector) and each piece of synthetic information for that item (e.g., chunk) 914 into a set of embeddings (i.e., a multi-dimensional vector). The vector search index 912 is stored in the data store 908 ( vector database)).
Claims 4 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Vouitsis et al. ( US 20260056981 A1), hereinafter referenced as Vouitsis, in view of Addanki et al. (US 20250103625 A1), hereinafter referenced as Addanki, further in view of Divine et al. (US 20250371210 A1), hereinafter referenced as Divine.
Regarding Claim 4, Vouitsis in view of Addanki teach the computing system of claim 3. Vouitsis in view of Addanki fail to explicitly teach the claimed, wherein the operation of obtaining one or more text segments semantically related to the query further comprises ranking the similarities and identifying top N vector embeddings that are associated with highest similarities, wherein N is a predefined positive integer .
However, Divine does teach the claimed, wherein the operation of obtaining one or more text segments semantically related to the query further comprises ranking the similarities and identifying top N vector embeddings that are associated with highest similarities, wherein N is a predefined positive integer ( Divine: Para.[0194], [0196], [0202]-[0204], Figs. 17, 18, the set of relevant technical documents 1804 can be a highest similarity-scoring or top similarity-scoring subset of the set of potentially-relevant technical documents 1702, which is identified by comparing the embedding 704 (corresponding to the problem description 402) with the plurality of embeddings 1704 ( embedding from technical documents). The set of relevant technical documents 1804 can have a cardinality of u, for any suitable positive integer u<t, where t is the number of documents in the set of potentially-relevant technical documents 1702 ).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Divine’s teaching of automatic product support systems and methods via generative artificial intelligence (GAI) and customer interactions , into the system and method, taught by Vouitsis in view of Addanki, because, by detecting issues , shortcomings or limitation and providing product development suggestions, recommendation can improve customer/client satisfaction. (Divine, Para.[0003],[0060]).
Claim 14 is a computer implemented method claim performing the steps in computer implemented system claim 4 above and as such, claim 14 is similar in scope and content to claim 4 and therefore, claim 14 is rejected under similar rationale as presented against claim 4 above.
Claims 9 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Vouitsis et al. ( US 20260056981 A1), hereinafter referenced as Vouitsis, in view of Addanki et al. (US 20250103625 A1), hereinafter referenced as Addanki, further in view of Ajmera et al. (US 20260119539 A1), hereinafter referenced as Ajmera.
Regarding Claim 9, Vouitsis in view of Addanki teach the computing system of claim 5. Vouitsis in view of Addanki fail to explicitly teach the claimed, wherein the operations further comprise periodically updating the vector database, comprising scanning the plurality of data sources to detect whether there is an update to the set of documents.
However, Ajmera does teach the claimed, wherein the operations further comprise periodically updating the vector database, comprising scanning the plurality of data sources to detect whether there is an update to the set of documents ( Ajmera: Para.[0018]-[0020], Fig. 1, the server computing system includes the document improvement engine (102), the document discovery engine (110), the large language model (LLM) (114), an artificial intelligence (AI) assistant application (116), the data repository (120). The data repository includes a knowledge base (122), discoverable documents (123), raw documents (124), and raw document supplemental context(s) (129), a document vector store (125), user chat histories (128). Para.[0015],[0037],[0053], Fig. 2 illustrates the execution of two interconnected processing loops, or iterative processing sequences. An inner processing loop improves, or enhances, the content in the knowledge base. An outer processing loop creates vector embeddings for the improved, or enhanced, content. Updated document embeddings may be generated for the updated discoverable documents. The discoverable document embeddings may further be stored in the document vector store (125). In the feedback step that interconnects the inner processing loop and the outer processing loop, the user chat history of the current interaction session may be sent to the context which updater (206) , which may additionally receive discoverable document identifier(s). The identifiers may correspond to the discoverable document(s) and updated by the context updater. Further, updated document embeddings may be generated for the updated discoverable documents. Thus, the inner and outer processing loops together form a continuous cycle of improvement and usage).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Ajmera’s teaching of accelerated knowledge discovery for knowledge base , into the system and method, taught by Vouitsis in view of Addanki, because, by effective discoverability and updating of the knowledge sources, which can include content with diverse inconsistencies in format, structure, outdated, arcane, and low comprehensibility, the capability of the LLMs to manage the semantic content of the knowledge sources and response to the user query, can be improved. (Ajmera, Para.[0002],[0003]).
Claim 18 is a computer implemented method claim performing the steps in computer implemented system claim 9 above and as such, claim 18 is similar in scope and content to claim 9 and therefore, claim 18 is rejected under similar rationale as presented against claim 9 above.
Conclusion
Listed below are the prior arts made of record and not relied upon but are considered pertinent to applicant's disclosure.
Way et al. (US 20230037216 A1) teaches a system for database management for digitally storing item information. The system may include one or more memories and one or more processors coupled to the one or more memories. The one or more processors may be configured to receive an indication of an exchange associated with a user and a first entity. The one or more processors may be configured to store information associated with the exchange in a first block of a first blockchain associated with the user, wherein the first blockchain identifies information for a plurality of exchanges associated with the user. The one or more processors may be configured to determine a second entity associated with the exchange and an item associated with the exchange based at least in part on exchange information associated with the exchange. The one or more processors may be configured to identify a second block in a second blockchain associated with the second entity, wherein the second block identifies the item information associated with the item, and wherein the second blockchain identifies information for a plurality of items associated with the second entity. The one or more processors may be configured to map the first block to the second block to enable the item information associated with the item to be associated with the exchange. The one or more processors may be configured to transmit, to a device associated with the user, an indication of the item information based at least in part on detecting an event associated with the item.
Yates et al. (US 20250131042 A1) teaches methods and systems which provide content searching and retrieval using generative artificial intelligence (AI) Models. The system is configured to receive a user search for content, media or item listings. The user search is provided to a generative AI based search sub-system and to a traditional search sub-system. A first search result listing is generated by the generative AI based subsystem, and a second search result listing is generated by the traditional search sub-system. The first search result listing and the second search result listing are aggregated together and provided for display to a user client device.
Hudetz et al. (US 20240370479 A1) teaches techniques for an artificial intelligence (AI) platform to search a document collection. Embodiments may use AI and machine learning techniques within a framework of an electronic document management system to perform semantic searching of an electronic document or a collection of electronic documents for certain types of information. The AI platform may summarize the information in a natural language representation of a human language. Other embodiments are described and claimed.
Saxena et al. (Beyond Flashcards: Designing an Intelligent Assistant for USMLE Mastery and Virtual Tutoring in Medical Education (A Study on Harnessing Chatbot Technology for Personalized Step 1 Prep), arXiv:2409.10540v1 [cs.CY], 31 Aug, 2024 ) teaches an intelligent AI companion which will assist the students, with diverse learning styles and paces of individual students, by providing personalized and adaptive learning experiences and which will provide on-the-fly solutions to students’ questions in the context of not only USMLE Step 1 preparation but also the preparation of other similar examinations for local and international students in other countries. Generative Artificial Intelligence (Generative AI) was used for dynamic, accurate, human-like responses and for knowledge retention and application. Users were encouraged to employ prompt engineering, in particular, in-context learning, for response optimization and enhancing the model’s precision in understanding the intent of the user through the way the query is framed. The implementation of Retrieval Augmented Generation has enhanced the chatbot's ability to combine pre-existing medical knowledge with generative capabilities for efficient and contextually relevant support. Mistral was employed using Python to perform the needed functions.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NADIRA SULTANA whose telephone number is (571)272-4048. The examiner can normally be reached M-F,7:30 am-5:00pm.
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, Paras D. Shah can be reached on (571) 270-1650. 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.
/NADIRA SULTANA/Examiner, Art Unit 2653
Prosecution Insights