DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This action is responsive to application filed on 21 February 2024. Claims 1-20 are pending in the case. Claims 1, 10, and 18 are the independent claims. This action is non-final.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on November 13th, 2025 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 § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1, 3-10, 12-18, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Li et al. (US 2025/0225132 A1) in view of Wu et al. (US 2019/0347256 A1).
Regarding claim 1, Li teaches a method for performing a computing task based on a user content, the method comprising:
extracting one or more features from the user content, the one or more features corresponding to a search request indicated in the user content (see Li, Paragraph [0071], “Feature extraction is performed on the query object input by the user, to obtain a vector representation of the query object, where the vector representation is a query vector. For example, the query vector is input into a trained encoder, to output a query vector corresponding to the query object.” [Features may be extracted from the query object input by the user (i.e., user content).]);
However, Li does not explicitly teach:
converting the one or more features to a floating point query vector;
Wu teaches:
converting the one or more features to a floating point query vector (see Wu, Paragraph [0029], “A vector may be thought of as an array of floating point numbers with a dimensionality of d, or in other words an array with d positions.” [The vector may be a floating point query vector.]);
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined Li (teaching vector search method and apparatus) in view of Wu (teaching efficient inner product operations), and arrived at a method that incorporates a floating point query vector. One of ordinary skill in the art would have been motivated to make such a combination for the purposes of providing high quality results (see Wu, Paragraph [0030]). In addition, both the references (Li and Wu) teach features that are directed to analogous art and they are directed to the same field of endeavor, such as vector quantization. The close relation between both the references highly suggests an expectation of success.
The combination of Li, and Wu further teaches:
quantizing the floating point query vector to obtain a quantized query vector (see Li, Paragraphs [0076], [0093], “The first vector is a vector after quantization of the original vector, and may also be referred to as a quantized vector. …The original vector corresponding to the image in the database is used as a query vector to perform a vector search, to obtain vector identifiers of the second index that is stored in the solid state disk and that is to be finally accessed;” [A quantized query vector may be obtained.]);
obtaining a database vector based on the one or more features, the database vector comprising one or more floating point feature vectors (see Li, Paragraph [0076], “The original vector is a vector representation of an image in an image database output by the encoder. The first vector is a vector after quantization of the original vector, and may also be referred to as a quantized vector.” [The original vector (i.e., database vector based on the one more features) is obtained.]);
determining a compensation vector based on a data distribution of the floating point query vector (see Wu, Paragraph [0032], “A residual vector represents the difference between the original data record and its corresponding quantized vector.” [The residual vector (i.e., compensation vector) may be obtained.]);
quantizing the one or more floating point feature vectors to obtain one or more quantized feature vectors (see Li, Paragraph [0076], “The original vector is a vector representation of an image in an image database output by the encoder. The first vector is a vector after quantization of the original vector, and may also be referred to as a quantized vector.” [The first vector is quantized.]);
determining an error function based on a difference between data distributions of i) the quantized query vector compensated with the compensation vector, and ii) the floating point query vector; determining, based on the error function, one or more values of the compensation vector corresponding to the one or more quantized feature vectors; combining the one or more quantized query vectors and the one or more values of the compensation vector to obtain one or more compensated query vectors; and performing the computing task using the one or more compensated query vectors and the one or more quantized feature vectors to obtain an output (see Wu, Paragraph [0032], “A residual vector represents the difference between the original data record and its corresponding quantized vector. In some implementations, the system 100 may generate the residual index for the dense portions by calculating the residuals for the dense portions of the data records 130, applying product quantization to the residuals to generate a second set of codebooks in codebooks 134, and storing the quantized residual record for each residual vector. As will be explained in more detail below, the residuals can be used to select a final search result from a superset of database items found similar to a query item.” [The difference between the quantized vector and the original data record (i.e., floating point query vector) may be determined. A residual index may be generated for the dense portions by calculating the residuals for the dense portions of the data records (i.e., determining one or more values). The residuals can be used to select a final search result from a superset of database items (i.e., combining the one or more quantized query vectors, and performing a task in order to obtain an output).]).
Regarding claim 3, Li in view of Wu teaches all the limitations of claim 1. Li further teaches:
wherein the computing task comprises performing at least one of a multiply-and-accumulate operation, general matrix multiplication (GeMM), fully connected layer computing, or k-nearest neighbors computing (see Li, Paragraph [0063], “The vector engine searches (for example, searches using approximate nearest neighbor (approximate nearest neighbor, ANN)) a vector index based on the query vector to obtain identifiers of topK similar vectors, where the topK vector identifiers are recalled vector identifiers obtained through a search.” [Approximate nearest neighbor (i.e., k-nearest neighbor) may be performed.]).
Regarding claim 4, Li in view of Wu teaches all the limitations of claim 1. Li further teaches:
wherein the computing task comprises computing a plurality of vector distances (see Li, Paragraph [0079], “A specific similarity calculation method is not limited in this embodiment of this application. Based on an actual situation, an appropriate similarity calculation method may be selected, for example, a Euclidean distance, a cosine distance or cosine similarity, an inner product, and a Hamming distance.” [A similarity calculation may be performed (i.e., computing a plurality of vector distances).]).
Regarding claim 5, Li in view of Wu teaches all the limitations of claim 4. Li further teaches:
wherein the plurality of vector distances comprises at least one of: a plurality of cosine similarity distances, a plurality of Euclidean distances, or a plurality of Hamming distances (see Li, Paragraph [0079], “A specific similarity calculation method is not limited in this embodiment of this application. Based on an actual situation, an appropriate similarity calculation method may be selected, for example, a Euclidean distance, a cosine distance or cosine similarity, an inner product, and a Hamming distance.” [A similarity calculation such as Euclidean distance, cosine distance or cosine similarity, or Hamming distance may be performed.]).
Regarding claim 6, Li in view of Wu teaches all the limitations of claim 4. Li further teaches:
generating a response to the user content based on the output, wherein generating the response comprises sorting the plurality of vector distances in a descending order or an ascending order (see Li, Paragraph [0106], “the K target vectors are first sorted in descending order based on the similarity result, that is, a higher similarity is ranked higher. Then, images in a forward database that correspond to the K target vectors are re-sorted based on the condition input by the user, and are output and displayed to the user.” [The response may be sorted in a descending order.]).
Regarding claim 7, Li in view of Wu teaches all the limitations of claim 1. Li further teaches:
wherein the user content comprises at least one of: graphical information, textual information, geographical information, or temporal information (see Li, Paragraph [0069], “A query object input by a user is received. The query object may be various modalities such as a text, an image, a voice, and a video.” [The query object input by a user (i.e., user content) may be a text (i.e., textual information).]).
Regarding claim 8, Li in view of Wu teaches all the limitations of claim 1. Li further teaches:
receiving the user content from at least one of: a text-based search engine, a graph-based search engine, a brute force search engine, or a behavior-based content recommendation system (see Li, Paragraph [0067], “The method may be applied to the vector engine and the vector model of the search system shown in FIG. 2 , to implement high accuracy and a low delay of a vector search.” [A vector engine (i.e., text-based search engine) may be implemented.]).
Regarding claim 9, Li in view of Wu teaches all the limitations of claim 1. Li further teaches:
wherein performing the computing task comprises performing the computing task using an in-memory computing (IMC) circuit, and wherein the IMC circuit comprises a plurality of memory cells comprising at least one of NAND flash cells, NOR flash cells, phase change memory (PCM), Magnetoresistive random-access memory (MRAM), Ferroelectirc random-access memory (FeRAM), or Spin-Transfer-Torque random-access memory (STT-RAM) (see Li, Paragraph [0129], “a flash memory” [A flash memory (i.e., NAND flash cells, NOR flash cells) may be used.]).
Regarding claims 10, 12-18, and 20, Li in view of Wu teaches all of the limitations of claims 1, and 3-9, in method form rather than in system form and non-transitory computer-readable medium form. Li also discloses a system [0042] and non-transitory computer-readable medium [0039]. Therefore, the supporting rationale of the rejection to claims 1, and 3-9, applies equally as well to those elements of claims 10, 12-18, and 20.
Claims 2, 11, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Li in view of Wu, further in view of Sakai et al. (US 2023/0123756 A1).
Regarding claim 2, Li in view of Wu teaches all the limitations of claim 1. However, the combination of Li, and Wu do not explicitly teach:
wherein determining the one or more values of the compensation vector comprises: determining the one or more values of the compensation vector such that a difference in magnitude between the quantized query vector compensated with the compensation vector and each of the one or more quantized feature vectors, is below a known threshold value.
Sakai teaches:
wherein determining the one or more values of the compensation vector comprises: determining the one or more values of the compensation vector such that a difference in magnitude between the quantized query vector compensated with the compensation vector and each of the one or more quantized feature vectors, is below a known threshold value (see Sakai, Paragraph [0055], “The quantization execution unit 104 compares a quantization error calculated by the quantization error calculation unit 102 to be described later with a threshold for the element to be quantized, and determines a quantization bit width of the tensor to carry out the quantization when the error is smaller than the threshold. Note that the threshold is set by the threshold setting unit 103 to be described later.” [The quantization error is compared with a threshold to determine if the quantization error is below the threshold.]);
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined Li (teaching vector search method and apparatus) in view of Wu (teaching efficient inner product operations), further in view of Sakai (teaching tensor quantization apparatus, tensor quantization method, and storage medium), and arrived at a method that incorporates comparing a quantization error with a threshold. One of ordinary skill in the art would have been motivated to make such a combination for the purposes of reducing computation time (see Sakai, Paragraph [0152]). In addition, both the references (Li, Wu, and Sakai) teach features that are directed to analogous art and they are directed to the same field of endeavor, such as vector quantization. The close relation between both the references highly suggests an expectation of success.
Regarding claims 11 and 19, Li in view of Wu, further in view of Sakai teaches all of the limitations of claim 2, in method form rather than in system form and non-transitory computer-readable medium form. Li also discloses a system [0042] and non-transitory computer-readable medium [0039]. Therefore, the supporting rationale of the rejection to claim 2, applies equally as well to those elements of claims 11 and 19.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HUSAM TURKI SAMARA whose telephone number is (571)272-6803. The examiner can normally be reached on Monday - Thursday, Alternate Fridays.
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, Apu Mofiz can be reached on (571)-272-4080. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
HUSAM TURKI SAMARA/Examiner, Art Unit 2161
/APU M MOFIZ/Supervisory Patent Examiner, Art Unit 2161