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 .
Response to Amendment
2. In response to the office action mailed on 10/31/2025, applicant filed an amendment on 03/31/2026, amending claims 1, 4, 17, and 20. The pending claims are 1-20.
Response to Arguments
3. Applicant's arguments filed 03/31/2026 have been fully considered but they are not persuasive.
As per claim 1, applicant argues that the prior art of record does not teach wherein the vector database comprises a time-series vector database, wherein the query and each of the plurality of data items comprises temporal information, and wherein the vector representation of the query and the plurality of vector representations of the data items encode the temporal information into one or more vector representation values.
The examiner notes that the secondary prior art reference Osuala relates to a search system that uses machine-learned embeddings to find information related to a user’s query, wherein a trained embedding model produces an embedding for the query itself and also embeddings for related information such as an answer to the query (0004]-[0006], [0028]-[0034], [0035]-[0045], [0087]-[0089], [0090]-[0093]). Osuala teaches querying a data source represented by data object embeddings in a vector space ([0004]). According to paragraphs [0026] and [0118], the data object comprises time-series data. In order to process time-series data, it needs to be stored in a database. Therefore time-series vector database is necessarily disclosed by Osuala. Also, it is week-known in the art that time-series vector databases are a hybrid category that explicitly incorporates temporal information alongside high-dimensional vector data because Time-series vector databases do not store raw timestamps directly in the vector, but through techniques like deep learning embeddings, temporal information is effectively encoded into the vector representations. Therefore, it would have been obvious at the time the application was filed to use Osuala’s time-series vector database with the system of Madnani, in order to read on the claimed language.
As per the rest of the claims, and combinations of prior art reference, applicant has no further arguments beside the ones mentioned above. Therefore, all the combinations of prior art reference mentioned above are valid, and all other claims are rejected for the same reasons as set above.
Claim Rejections - 35 USC § 103
4. 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 (i.e., changing from AIA to pre-AIA ) 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 Madnani (US 2025/0045314) in view of Osuala (US 2024/0111794).
As per claim 1, Madnani teaches obtaining, by a computing system comprising one or more computing devices, a query embedding for a vector representation of a query (Fig. 1, [0015]- [0016], obtaining a created embedding of a query received from a user);
querying, by the computing system, a vector database with the query embedding to identify one or more result embeddings, wherein the vector database comprises a plurality of embeddings for a respective plurality of vector representations of data items ([0016], Fig, 1, step 130, the server may fetch similar embeddings, once the embedding is created in step 120. The similar embeddings may be taken from the embeddings store 140. The embeddings store 140 is a database capable of storing queries, responses, prompts, embeddings, or the like);
processing, by the computing system, a set of inputs with a machine-learned model to obtain a model output, the set of inputs comprising the query and one or more of: (a) one or more data items of the plurality of data items respectively associated with the one or more result embeddings; or (b) the one or more result embeddings ([0017]- [0021], Fig. 1, steps 150-160, processing by the server the query embedding and embedding fetched from the embeddings store to rank the embeddings based on their relevance, creating a new prompt with context from the closest embeddings in step 160 added to the user prompt 110, and processing the contextual prompt by a large language model (LLM) to generate a response to query ); and
providing, by the computing system, the model output for a requesting entity associated with the query (Fig. 1, [0021], providing a response to a user's queries).
Madnani may not explicitly disclose wherein the vector database comprises a time-series vector database, wherein the query and each of the plurality of data items comprises temporal information, and wherein the vector representation of the query and the plurality of vector representations of the data items encode the temporal information into one or more vector representation values. However, Osuala in the same field of endeavor relates to a search system that uses machine-learned embeddings to find information related to a user’s query, wherein a trained embedding model produces an embedding for the query itself and also embeddings for related information such as an answer to the query (0004]-[0006], [0028]-[0034], [0035]-[0045], [0087]-[0089], [0090]-[0093]). Osuala teaches querying a data source represented by data object embeddings in a vector space ([0004]). According to paragraphs [0026] and [0118], the data object comprises time-series data. In order to process time-series data, it needs to be stored in a database. Therefore time-series vector database is necessarily disclosed by Osuala. Also, it is week-known in the art that time-series vector databases are a hybrid category that explicitly incorporates temporal information alongside high-dimensional vector data because Time-series vector databases do not store raw timestamps directly in the vector, but through techniques like deep learning embeddings, temporal information is effectively encoded into the vector representations. Therefore, it would have been obvious at the time the application was filed to use Osuala’s time-series vector database with the system of Madnani, in order to facilitate real time analysis and allow quick identification of responses.
As per claim 2, Madnani teaches using the machine learning models of the program modules 416 of Fig. 4 is used to perform tasks or implement the described processes ([0002], [0003], [0052]). Madnani may not explicitly disclose processing, by the computing system, the vector representation of the query with a machine-learned embedding model to obtain the query embedding for the vector representation of the query. Osuala in the same field of endeavor teaches using a trained machine learning model to create meaningful query embedding ([0054]). Therefore, it would have been obvious at the time the application was filed to use Osuala’s machine learning model with the system of Madnani, in order to provide relevant results to a search query.
As per claim 3, Madnani teaches, prior to processing the vector representation of the query, the method comprises: determining, by the computing system, a vector representation for the query based on a particular encoding process ([0015], creating vector representation of the query using novel NLP algorithms). As to wherein in each of the plurality of vector representations of data items are determined based on the particular encoding process, it would have been obvious at the time the application was filed to use the particular process that was used in determining the vector representation for the query. This would increase consistency and efficiency.
As per claim 4, Madnani may not explicitly disclose wherein the particular encoding process is configured to encode temporal information into the one or more vector representation values. Osuala in the same field of endeavor teaches searching a data source using embeddings of vector space, wherein the data object such as text embeddings comprise time-series data ([0026]- [0027], [0118]). Therefore, it would have been obvious at the time the application was filed to use Osuala’s time-series vector database with the system of Madnani, in order to facilitate real time analysis and allow quick identification of responses.
As per claim 5, Madnani may not explicitly disclose wherein the temporal information of the query is most similar to the temporal information of each of the one or more data items of the plurality of data items. Osuala in the same field of endeavor teaches wherein the temporal information of the query is most similar to the temporal information of each of the one or more data items of the plurality of data items ([0038]). Therefore, it would have been obvious at the time the application was filed to use Osuala’s above feature with the system of Madnani, in order to facilitate real time analysis and allow quick identification of responses.
As per claim 6, Madnani may not explicitly disclose wherein the temporal information of the query is indicative of a period of time, and wherein the temporal information of each of the one or more data items is bounded within that period of time. Osuala in the same field of endeavor teaches searching a data source using embeddings of vector space, wherein the data object such as text embeddings comprise time-series data ([0026]- [0027], [0118]). Therefore, it would have been obvious at the time the application was filed for the temporal information of the query and data items to be bounded in a same period of time, as time-series vectors are sequences of multiple data points taken at specific time intervals. This would facilitate real time analysis and allow quick identification of responses.
As per claim 7, Madnani teaches wherein, prior to obtaining the query embedding, the method comprises: receiving, by the computing system, information indicative of the query from the requesting entity (Fig. 1 and [0014], receiving information indicative of the requesting entity, i.e. user).
As per claim 8, Madnani teaches wherein, prior to obtaining the query embedding, the method comprises: receiving, by the computing system, information from the requesting entity ([0014]); and generating, by the computing system, the query based on the information from the requesting entity (Fig. 1 and [0013]- [0014], wherein one or plurality of responses are generated based on the information from the requesting entity).
As per claim 9, Madnani teaches wherein, prior to obtaining the query embedding, the method comprises: receiving, by the computing system, a data stream comprising a first data item of the one or more data items; determining, by the computing system, a vector representation of the first data item based on the particular encoding process; processing, by the computing system, the vector representation of the first data item with the machine-learned embedding model to obtain a first result embedding of the one or more result embeddings associated with the first data item; and storing, by the computing system, the result embedding and the vector representation of the first data item in the vector database ([0016], in step 130, the server may fetch similar embeddings, once the embedding is created in step 120. The similar embeddings may be taken from the embeddings store 140. The embeddings store 140 is a database capable of storing queries, responses, prompts, embeddings, or the like. The embeddings store 140 may be continuously updated over time based on the queries being received in step 110).
As per claim 10, Madnani teaches wherein receiving the data stream comprising the first data item of the one or more data items comprises: receiving, by the computing system, a data stream comprising a plurality of data items; and aggregating, by the computing system, the plurality of data items to obtain the first data item of the one or more data items ([0016]- [0017], wherein the server ranks and stores the embeddings based on their relevance. The rankings may include a n-dimensional vector. The rankings may be based on how similar two embeddings are).
As per claim 11, Madnani teaches wherein querying the vector database comprises performing, by the computing system, a nearest neighbor search for the query embedding in an embedding space comprising the query embedding and at least some of the plurality of embeddings ([0020], performing a nearest neighbor search for the query embedding in an embedding space and identifying the closest embeddings. The closest embedding refers to the distance for similar prompts in the vector space). Madnani may not explicitly disclose a nearest neighbor search. Osuala in the same field of endeavor teaches the claimed nearest neighbor search ([0105], [0111]. Therefore, it would have been obvious at the time the application was filed to use the nearest neighbor search of Osuala with the system of Madnani, in order to reduce search times compared to exact methods, especially in high-dimensional spaces and real-time applications.
As per claim 12, Madnani may not explicitly disclose wherein performing the nearest neighbor search comprises performing, by the computing system, one or more Approximate Nearest Neighbor (ANN) search processes. Osuala in the same field of endeavor teaches using one or more Approximate Nearest Neighbor (ANN) search processes ([0105], [0111]. Therefore, it would have been obvious at the time the application was filed to use the nearest neighbor search of Osuala with the system of Madnani, in order to reduce search times compared to exact methods, especially in high-dimensional spaces and real-time applications.
As per claim 13, Madnani teaches wherein the one or more data items respectively comprise one or more of sets of textual content; and wherein processing the set of inputs comprising the query and the one or more data items comprises processing, by the computing system, the query and the one or more sets of textual content with a large language model (LLM) to obtain a textual output ([0013]- [0014], [0021]).
As per claim 14, Madnani teaches wherein querying the vector database with the query embedding comprises: generating, by the computing system, an accuracy filter based on at least one of: (a) the query; or (b) contextual information associated with the requesting entity; and applying, by the computing system, the accuracy filter to the plurality of embeddings to identify a subset of embeddings; and querying, by the computing system, the subset of embeddings with the query embedding to identify the one or more result embeddings ([0010], LLMs can be enriched with data from an embedding database, giving context to the LLM that enables the LLM to provide accurate responses to user inputs. [0012], wherein said, to provide more accurate and relevant responses, an embedding database may be used to enrich the raw user text and use similarity metrics to identify relevant context. By using the latest and most contextual information, the generated prompts may provide more accurate and useful responses to a user's query.).
As per claim 15, Madnani teaches wherein the one or more result embeddings comprises a plurality of result embeddings respectively associated with a plurality of data items; and wherein processing the query and the one or more data items with the machine-learned model comprises: determining, by the computing system, an optimization filter based on at least one of: (a) the query; or (b) contextual information associated with the requesting entity; applying, by the computing system, the optimization filter to either the plurality of embeddings or the plurality of data items to obtain one or more filtered result embeddings; and processing, by the computing system, the query and the one or more data items respectively associated with the one or more filtered result embeddings with the machine-learned model to obtain the model output ([0044]- [0045], wherein an adaptive filtering is necessarily disclosed when using contextual information to generate the most relevant response to the query. For example, the response for a query 112 about fashion trends may include the most relevant fashion trends such as cargo pants, culottes, or pinstripe tailoring for summer of 2023).
As per claim 16, Madnani teaches wherein querying the vector database with the query embedding comprises: querying, by the computing system, a plurality of instances of the vector database with the query embedding to identify the one or more result embeddings, wherein each of the plurality of instances of the vector database comprises at least some of the plurality of embeddings ([0041]- [0042], wherein a plurality of other embeddings are retrieved and ranked based on relevance to identify the one or more result embeddings).
As per claims 17-19, system claims 17-19 and method claims 1-3 are related as apparatus and the method of using same, with each claimed element's function corresponding to the claimed method step. Accordingly claims 17-19 are similarly rejected under the same rationale as applied above with respect to method claims 1-3. Furthermore, Madnani teaches one or more processors, as claimed ([0048]).
As per claim 20, Madnani teaches a computer readable medium ([0051]). The remaining steps are rejected under the same rationale as applied to the method steps of rejected claim 1.
Conclusion
5. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. The prior art Mavinakuli (US 2023/0012316) relates to processing a plurality of inputs with a machine-learned vector embedding model to generate a corresponding vector representation of a plurality of vector representations with embedded temporal information, and for each of the plurality of vector representations, mapping the vector representation to a corresponding location of a plurality of locations within an embedding portion of the hybrid time-series vector database based at least in part on the temporal information of the vector representation.
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ABDELALI SERROU whose telephone number is (571)272-7638. The examiner can normally be reached M-F 9 Am - 5 PM.
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, Pierre-Louis Desir can be reached at 571-272-7799. 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.
/ABDELALI SERROU/Primary Examiner, Art Unit 2659
Prosecution Insights