DETAILED ACTION
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 Arguments
The previous rejection of the claim under 35 USC §112 has been withdrawn, in light of the amendments.
Applicants’ arguments, filed 8/26/2026, concerning the previous rejection of the claims under 35 USC §103 have been fully considered but they are not persuasive. The previous 35 USC §103 rejections of the claims have been maintained, with the addition of rejections of two new claims using the same art as the previous claims. This action is therefore made final.
The previous 35 USC §103 rejections of the claims have been mostly maintained (with a new rejection under 35 USC §103 set forth to address the newly amended language of claims 4 and 16). The previous 35 USC §112 rejections of claims 4 and 16 have been withdrawn, however new rejections have been set forth under 35 USC §112 to address the newly amended claim language of those claims.
Regarding the rejections of the independent claims under 35 USC §103, Applicants argue on pages 8-10 that the references do not teach the use of both context and query information.
The Office respectfully disagrees. For instance, in at least paragraphs 0024-0025 Saini discusses the use of models for the processing of combined query and metadata embeddings. And, it is also reasonable to conclude that the Saini reference at least suggested the use of some sort of criteria in the performance of the identification.
Therefore, the previous rejections of the claims under 35 USC §103, and the mapping to address the newly amended claims (25 and 26), are believed to be reasonable.
Allowable Subject Matter
Claims 12 and 24 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Reasons For Allowance
The cited references do not disclose wherein the processor is configured to use a top K-filter to select a subset of contextual data embedded vectors, from the at least one contextual embedded vector, to incorporate with the query for input into the LLM.
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.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-3, 5, 7-11, 13-15, 17, 19-23 and 25-26 are rejected under 35 U.S.C. §103 as being unpatentable over Saini et al (US Patent Application Publication No. 2025/0061136, hereafter referred to as “Saini”) in view of Ayed et al (US Patent Application Publication No. 2025/0245271, hereafter referred to as “Ayed”).
Regarding independent claim 1: Saini teaches An apparatus comprising: a processor (See Saini Fig. 14 #1404 teaching an exemplary computing environment, including hardware such as CPUs.) configured to: receive a query from a wireless transmit/receive unit (WTRU); (See Saini Figures 1 and 3 teaching a query input, in the context of 0091-0092 teaching the use of wireless communication links and Fig. 14 showing the exemplary use of wireless devices such as cell phones and tablets.) identify at least one contextual data embedded vector that is relevant to at least one portion of an embedded vector associated with the query based on a criteria; (See Saini 0024 discussing the use of a query embedding and a metadata embedding to produce an augmented query, and 0025 discussing the conversion of a query to a vector and creation of an augmented embedding “in yet another vector space”.) input the query or portions of the query and the at least one contextual data embedded vector, based on the criteria, to a … model …, wherein the at least one contextual data embedded vector is incorporated with the query based on the criteria; (See Saini Fig. 1 #110 and 0025 teaching the use of a model to generate an augmented query in a vector space.) receive a contextualized response to the query … based on the at least one contextual data embedded vector incorporated with the query, based on the criteria; (See Saini Fig. 1 #112 and #116 teaching the search/retrieval/reception of matching target items from an indexed repository #114, and 0025 discussing the creation of an augmented embedding in “yet another vector space”.) and transmit the contextualized response via a network to the WTRU. (See Saini Abstract and Fig. 1 #112 and “118 teaching the outputting of retrieved information/results from the execution of the augmented search query.)
However, Saini does not explicitly teach the remaining limitations as claimed. Ayed, though, teaches large language … (LLM); (See Ayed Abstract teaching the use of a large language model [LLM] in the creation of augmented queries.) … from the LLM …; (See Ayed Abstract teaching the use of a large language model [LLM] in the creation of augmented queries.)
It 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 to apply the teachings of Ayed for the benefit of Saini, because to do so provided a designer with options for implementing a system that facilitated augmented retrieval processes, as taught by Ayed in the Abstract. These references were all applicable to the same field of endeavor, i.e., search query augmentation.
Regarding claim 2: Saini teaches wherein the at least one contextual data embedded vector incorporated with the query or portions of the query comprises the at least one contextual data embedded vector appended as embeddings or tokens to the query or portions of the query. (See Saini Abstract and 0025 teaching the conversion of a query to a vector and the creation of an augmented embedding “in yet another vector space”. See also 0022-0023 discussing the exemplary ability to process tokens and embeddings, including text-based tokens.)
Regarding claim 3: Saini teaches wherein the LLM is trained on sample queries and contextual data embedded vectors identified as relevant to the received query. (See Saini 0079 discussing the use of training models. Note that in this particular example, the third model has been trained using input from the first two models.)
Regarding claim 5: Saini teaches wherein the processor is further configured to receive, at an embedding model, contextual data related to potential queries from a user for information at an embedding model, the contextual data comprising at least one of textual data, audio data, or video data, wherein the embedding model is trained to receive the contextual data and generate different contextual data embedded vectors each comprising a vector of values configured to identify semantic relationships between different contextual data via spatial relationships in a spatial domain. (See Saini 0023 teaching the processing of text data, in the context of 0139 teaching that text data may be lexically or semantically related. See also 0030 teaching the use of distance metrics to reflect semantic similarity between concepts associated with vectors. And, further refer to 0100 discussing the exemplary use of text metadata semantically/lexically related to a query, in the context of Fig. 1 the supplementing of input queries.)
Regarding claim 7: Saini teaches wherein the processor is further configured to decompose, at a query processing module, the query into a set of vectorized embeddings, wherein the set of vectorized embeddings comprises the embedded vector, wherein the processor is configured to decompose the query into the set of embedded vectors such that each embedded vector comprised in the set of embedded vectors is compatible with each contextual data embedded vector. (See Saini 0025 discussing the converting of query embeddings to queries and the matching of lookup vectors with metadata vectors. See also 0030 discussing the use of distance to determine vector concept similarity.)
Regarding claim 8: Saini teaches wherein the processor is further configured to calculate, at an information mapping module, relevance of each contextualized data embedded vector in the embedded datastore to each embedded vector or portions thereof of the query based on criteria to identify the at least one contextual data embedded vector that is relevant to the at least one portion of the embedded vector. (See Saini 0030 teaching the use of distance metrics to reflect semantic similarity between concepts associated with vectors. See also Fig. 9, especially #916, teaching the storage of vector information associated with metadata embeddings.)
Regarding claim 9: Saini teaches … and wherein the at least one contextual data embedded vector is appended as embeddings or tokens to the query or portions thereof when the relevance score associated with the at least one contextual embedded vector is above the threshold. (See Saini 0022-0023 discussing the exemplary ability to process tokens and embeddings, including text-based tokens.)
However, Saini does not explicitly teach the remaining limitations as claimed. Ayed, though, teaches wherein the criteria comprises a threshold and a relevance score, and wherein the processor is configured to determine the relevance of each contextual data embedded vector to the vectorized embeddings or portions thereof of the query based on whether the relevance score associated with each contextual data embedded vector is above the threshold, … . (See Ayed 0036 discussing the use of a similarity measure, comparison of similarity metrics between two vectors, and meeting/exceeding a similarity threshold.)
Regarding claim 10: Saini does not explicitly teach the remaining limitations as claimed. Ayed, though, teaches wherein the relevance score is determined based on a distance between a vectorized embedding of the query or portions thereof and a contextualized data embedded vector of the at least one contextual data embedded vector. (See Ayed 0036 discussing the comparison of similarity metrics between two vectors using exemplary techniques such as a Manhattan distance.)
Regarding claim 11: Saini teaches … the processor is configured to select the at least one contextual data embedded vector to incorporate with the query for input into the LLM. (See Saini Fig. 1 and 0025 teaching the matching on lookup vectors and metadata embeddings, which may be in different vector spaces.)
However, Saini does not explicitly teach the remaining limitations as claimed. Ayed, though, teaches wherein, when the relevance score of a contextual data embedded vector is above the threshold, … (See Ayed 0036 discussing the use of a similarity measure, comparison of similarity metrics between two vectors, and exceeding a similarity threshold.)
Regarding claim 25: Saini teaches wherein the criteria comprises a spatial distance between the at least one portion of the embedded vector associated with the query and the contextual data embedded vector in a common embedding space. (See Saini paragraph 0030 teaching the use of distance metrics to reflect semantic similarity between concepts associated with vectors. And, further refer to 0100 discussing the exemplary use of text metadata semantically/lexically related to a query, in the context of Fig. 1 the supplementing of input queries.)
Claims 13-15, 17, 19-23 and 26 are substantially similar to claims 1-3, 5, 7-11 and 25, respectively, and therefore likewise rejected.
Claims 4 and 16 are rejected under 35 U.S.C. §103 as being unpatentable over Saini et al (US Patent Application Publication No. 2025/0061136, hereafter referred to as “Saini”) in view of Ayed et al (US Patent Application Publication No. 2025/0245271, hereafter referred to as “Ayed”) and Samuel et al (US Patent Application Publication No. 2026/0119197, hereafter referred to as “Samuel ”).
Regarding claim 4: Although Saini teaches the use of distance metrics to reflect semantic similarity between concepts associated with vectors (See para 0030, for example), Saini does not explicitly teach the remaining limitations as claimed.
Samuel, though, teaches wherein the processor is configured to indicate spatial relationships of the at least one contextual data embedded vector via distances and angles. (See Samuel at para 0133 discussing the comparison of distance and angular differences between vectors to establish a contextual similarity value.)
It 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 to apply the teachings of Samuel for the benefit of Saini in view of Ayed, because to do so provided a designer with options for implementing a system that was capable of determining and correlating a user’s intent via taking into account the context/semantics of words used with the user’s query, as taught by Samuel in para 0080. These references were all applicable to the same field of endeavor, i.e., search query processing.
Claim 16 is substantially similar to claim 4, and therefore likewise rejected.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Relevance is provided in at least the Abstract of each cited document.
US Patent Application Publications
Marcus 2025/0390879
A device, system and method for machine-generated automatic fraud detection using a large language model to generate a human-readable summary to detect anomalies in a user's transaction history behavior. A prompt may be input into a large language model comprising a set of features of the user's current and past transactions and instructions to generate a summary explaining deviation in the user's behavior between the current and past transactions. The summary may be analyzed to detect if the deviation in the user's behavior is anomalous. When the analysis detects deviant behavior patterns between the user's current and past transactions, fraud may be suspected to automatically trigger a preventative anti-fraud action, e.g., to pre-emptive cancel, delay execution or escalate interrogation, of the current transaction. (Abstract). This vector may be stored in a vector database (e.g., a database for indexing and executing actions on vectors). The fraud detection system may query the vector DB for a predetermined number (e.g., five) historically validated fraudulent and/or legitimate transaction summaries that are the most semantically similar (e.g., past summaries represented by embedded vectors in the vector DB that are closest (e.g., using a distance measure such as a cosine similarity) to the vector embedding the summary of the current transaction. (para 0076).
Jain 2026/0037523
During the semantic search by the semantic search component 108 in FIG. 2, the semantic relevance is determined based on the relevance between an embedded vector representing the query and other embedded vectors, each of which represents a document or portion of a document (e.g., the first document 416A or the second document 416B). The query, in FIG. 4 query 403, is also embedded by embedding model 420 as a query vector 423 containing numerical entries denoted by Q.sub.i, where i=1, . . . , N, and represents a point in an N-dimensional space. (para 0051). The semantic relevance between the query vector Q.sub.i and other vectors may be determined based on the similarity or distance between the query vector Q.sub.i and each other vector. For example, the semantic relevance may be determined based on cosine similarity. The cosine similarity ranges between −1 and 1 and measures the degree of similarity between two vectors in an N-dimensional space, in this example, represented as cosine similarity 424 between second vector Y.sub.i and the query vector Q.sub.i. The closer the cosine similarity 424 is to “1”, the more semantically similar the second document 416B and the query. The cosine similarity may be used for comparing similarity of content of documents or sentences. This is because the cosine similarity ignores magnitude differences between the query and the embedded vector. Further, the cosine similarity may be less computationally expensive. Thus, in some embodiments, the cosine similarity may be used based on the type of content of a document and/or the query. (para 0052). As another example, the semantic relevance may be determined based on Euclidean distance. The Euclidean distance is the length of a line segment between two points. The closer the two points are, the shorter the Euclidean distance between them. Thus, the Euclidean distance indicates similarity between two embedded vectors, in this example, represented as distance 426 between the query vector Q.sub.i and the first vector X.sub.i. A lower, or shorter, distance indicates an increased semantic similarity between the query and the first document 416A. The Euclidean distance may be used for comparing overall length and word usage patterns between a document and the query. This is because Euclidean distance utilizes absolute magnitude differences in determining similarity. Moreover, the Euclidean distance may be more computationally expensive compared to other methods. Thus, in some embodiments, the Euclidean distance may be used based on the type of content of a document and/or the query. The semantic relevance between each document and the query may be indicated as a semantic score. (para 0053).
US Patents
Han 12,554,780
At block 840, the computing system outputs, to the vector database, a first vector database query to cause a vector similarity search of the one or more first relevant documents based on the first embedded representation of the first query. For example, the first vector database query can be constructed according to a format prescribed by the API provided by the vector database 520, such as web-based REST API. The vector database 520 can be caused, by the first vector database query, to execute a vector similarity search, such as cosine similarity or Euclidean distance, to identify documents or document chunks with embedded vector representations closest to the query vector. For instance, the first embedded representation of the first query can be matched against pre-indexed document or document chunk vectors, retrieving those with the smallest cosine distance, which can correspond to the most semantically relevant documents. (col. 25 lines 3-18).
All claims are drawn to the same invention claimed in the application prior to the entry of the submission under 37 CFR 1.114 and could have been finally rejected on the grounds and art of record in the next Office action if they had been entered in the application prior to entry under 37 CFR 1.114. Accordingly, THIS ACTION IS MADE FINAL even though it is a first action after the filing of a request for continued examination and the submission under 37 CFR 1.114. See MPEP § 706.07(b). 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 extension fee 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.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to examiner ROBERT STEVENS whose telephone number is (571) 272-4102. The examiner can normally be reached Mon - Fri 6:00 - 2:30.
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, Amy Ng can be reached on (571) 270-1698. 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.
/ROBERT STEVENS/Primary Examiner, Art Unit 2164
September 30, 2026
Prosecution Insights