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 .
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
The IDS, filed June 05, 2025, has been considered.
Claims 1-20, filed December 13, 2024, are examined on the merits.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 1, line 2, recites “receiving a write request for writing target vector data…”, while, line 6 recites “writing the index update information…” causes the claim to be vague and indefinite. The claim is not clear as to whether the “adding index update information…”, “writing the index update information…”, and/or “converting the first index…” are all part of the “write request…” or only the step of “writing the index update information…” corresponds to the “write request…” in line 2. The same issue is present in claim 12. Claims 2-11 and 13-16 are rejected for being dependent from claim 1 or 12.
Claim 1, lines 6-7, recite “in response to flushing the memory table…”, wherein there is lack of antecedent basis for the limitation which causes the claim to be vague and indefinite. The claim is not clear as to whether the “flushing” occurred due to “receiving a write request…”, “adding index update information…”, or an unspecified step. The same issue is present in claim 12. Claims 2-11 and 13-16 are rejected for being dependent from claim 1 or 12.
Claim 1, lines 6-7, recite “writing the index update information of the first index…into a distributed file system, while, line 8, recites “converting the first index in the distributed file system…” which cause claim 1 to be vague and indefinite. Only the index update information is written into a distributed file system not actually the “first index”, while, line 8, refers to “the first index in the distributed file system” which causes the vague and indefinite issue. The same issue is present in claim 12. Claims 2-11 and 13-16 are rejected for being dependent from claim 1 or 12.
Claim 2, lines 2-3, recite “combining multiple second indexes…” wherein the antecedent from the “second indexes” is not clear because claim 1 only recite “a second index” no a plurality of “second indexes.” The same issue is present in claim 13. Claims 2-11 are rejected for being dependent from claim 1.
Claim 6, line 6, recites “the first index…stored in the distributed file system” which causes the claim to be vague and indefinite because only the index update information is written into a distributed file system not the first index which cause the confusion. The same issue is present in claim 16.
Claim 6, last line, recites “combining results obtained from the respective vector searches…” wherein the “vector searches” causes the claim to be vague and indefinite because only “a search request” is performed. The same issue is present in claim 8, line 4 and claim 9, line 4. The same issue is present in claims 9, 16 and 17. Claims 18-20 are rejected for being dependent from claim 16.
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 (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.
Claim(s) 1, 3, 4, 6, 7, 12, 14, 15, and 17-19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Li H. et al. (Li WO 2024065692 A1) in view of Li, J. (CN 115757967 A).
Claim 1, Li H. discloses a method, comprising:
adding index update information corresponding to the target vector data to a first index of the vector database in a memory table, wherein the first index (page 1, e.g. obtaining N vector identifiers corresponding to the query object by querying a first index, the first index being stored in a memory, N being a positive integer, the N vector identifiers including multiple first vector identifiers, the first vector identifier being an uncertainly recalled vector identifier) is a memory-based real-time read-write vector graph index (page 12, e.g. PQ quantized coding can adopt PQ16*8 coding mode. When performing vector retrieval in memory, the HNSW graph is responsible for selecting a certain number of inverted tables based on the query vector, traversing the PQ coded vectors in the selected inverted tables in turn, and calculating the similarity between the query vector and each PQ coded vector, determining N vector identifiers based on the similarity measurement results, and using the selected N vector identifiers as the recall results based on the first index retrieval);
in response to flushing the memory table to a disk, writing the index update information of the first index in the memory table into a distributed file system (page 5, e.g. the frequently accessed high-heat data in the second index data is stored in the cache, and if the cache hits the data, there is no need to access the persistent storage medium, further reducing the retrieval delay); and
converting the first index in the distributed file system into a second index, wherein the second index (page 2, e.g. determining second vector identifiers corresponding to the multiple first vector identifiers by querying index items corresponding to the multiple first vector identifiers in a second index, the second vector identifier being a determinedly recalled vector identifier, the second index being stored in a persistent storage medium, the compression ratio of the vector in the first index item being greater than that of the vector in the second index) is a disk-based vector graph index (page 8, a disk + memory hybrid storage solution using a graph vector retrieval method (such as DiskANN or Zoom retrieval algorithms). It uses the local neighbor relationship of the neighbor graph).
However, Li H. does not disclose receiving a write request for writing target vector data into a vector database. Li J. discloses receiving a write request for writing target vector data into a vector database (page 10, calling the vector collaborative service, writing the item vector to be written in the vector database into the vector search engine).
Li J. discloses application can reduce the calculation response time, at the same time, it can avoid resource waste, realizing vector cooperative management (Abstract). One of ordinary skill in the art at the time prior to the effective filing date of the instant invention would have been motivated by Li J. to improve the method of Li H. Therefore, it would have been obvious for one of ordinary skill in the art to use the method of Li H. with the writing request disclosed by Li J. The benefit would be to reduce the calculation response time, at the same time, it can avoid resource waste, realizing vector cooperative management.
Claim 3, Li H. as modified discloses the first index is a Hierarchical Navigable Small World (HNSW) index (Li H., page 12, e.g. PQ quantized coding can adopt PQ16*8 coding mode. When performing vector retrieval in memory, the HNSW graph is responsible for selecting a certain number of inverted tables based on the query vector), and the second index is a Disk Approximate Nearest Neighbor (DiskANN) index (Li H., page 8, a disk + memory hybrid storage solution using a graph vector retrieval method (such as DiskANN or Zoom retrieval algorithms)).
Claim 4, Li H. as modified discloses the index update information comprises update of an adjacency relationship in the HNSW index or adjustment of a hierarchical structure of multiple hierarchical graphs (Li H., page 12, e.g. PQ quantized coding can adopt PQ16*8 coding mode. When performing vector retrieval in memory, the HNSW graph is responsible for selecting a certain number of inverted tables based on the query vector).
Claim 6, Li H. as modified discloses receiving a search request for searching target vector data in a vector database (Li H. page 10, e.g. a query object input by the user is received, and the query object is input into the encoder, which encodes and outputs the query vector of the query object. The vector engine searches the vector index according to the query vector (for example, using approximate nearest neighbor search (ANN)) to obtain the identifiers of the topk similar vectors. The topk vector identifiers are the retrieved recall vectors. The object corresponding to the recall vector is then searched in the database); and performing searching based on the target vector data, wherein performing the searching comprises:
performing respective vector searches by using the first index stored in a memory (Li H., page 12, e.g. PQ quantized coding can adopt PQ16*8 coding mode. When performing vector retrieval in memory, the HNSW graph is responsible for selecting a certain number of inverted tables based on the query vector), and the first index and the second index stored in the distributed file system (Li H., page 8, a disk + memory hybrid storage solution using a graph vector retrieval method (such as DiskANN or Zoom retrieval algorithms)); and
combining results obtained from the respective vector searches as a matching result set (Li H., page 10, e.g. presented to the user as a retrieval result).
Claim 7, Li H. as modified discloses multiple data rows are stored in the vector database, wherein one data row comprises data columns corresponding to multiple types of data, and the multiple types of data comprise vector data and other types of data (Li H. page 10, e.g. the input query object in the online retrieval stage is the query image, and the database is an image database (image database) and a forward database (forward database)). It is noted that data rows and types of data are inherent features of a database.
Claims 12, 14, 15, and 17-19, Li H. as modified discloses a computer readable medium and system (Li H., page 18, e.g. the computing device 700 includes at least one processor 701, a memory 702, a communication interface 703, and a persistent storage medium 704.Among them, the processor 701, the memory 702, the communication interface 703,and the persistent storage medium 704 are communicatively connected, and the communication connection can be realized by a wired manner (such as a bus) or by a wireless manner) for implementing the above cited steps.
Claim(s) 2 and 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Li H. et al. (Li WO 2024065692 A1) in view of Li, J. (CN 115757967 A), as applied to claims 1, 3, 4, 6, 7, 12, 14, 15, and 17-19 above, in further view of Anwar et al. (US 11416465 B1).
Claims 2 and 13, Li H. as modified discloses the claimed invention except for “combining multiple second indexes whose data volumes are less than a target value into one second index whose data volume is greater than or equal to the target value.”
Anwar et al. discloses the bucket merge policy can indicate which buckets are candidates for a merge or which bucket to merge (e.g., based on time ranges, size, tenant, index, or other identifiers), the number of buckets to merge, size or time range parameters for the merged buckets, and/or a frequency for creating the merged buckets….As another non-limiting example, the bucket merge policy can indicate that multiple buckets are to be merged until a threshold bucket size is reached (e.g., 750 MB, or 1 GB, or more) (column 52, lines 18-32). It is noted that Anwar does not explicitly disclose “data volumes are less than a target value”, however, it is implied in Anwar that the candidate buckets are less than the target value before merging/combining.
Anwar discloses computational efficiency of searching large amounts of data can be improved (column 50, lines 1-8). One of ordinary skill in the art at the time prior to the effective filing date of the instant invention would have been motivated by Anwar to improve the method of Li H. as modified.
Therefore, it would have been obvious for one of ordinary skill in the art to use the method of Li H. as modified with the combing of indexes as described by Wang. The benefit would be to improve the efficiency of searching large amounts of data.
Claim(s) 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Li H. et al. (Li WO 2024065692 A1) in view of Li, J. (CN 115757967 A), as applied to claims 1, 3, 4, 6, 7, 12, 14, 15, and 17-19 above, in further view of Colgan (US 20250077793 A1).
Claim 8, Li H. as modified discloses the claimed invention except for a filtering search criterion for filtering the other types of data. Colgan discloses the computing system can filter the vector database prior to querying the vector database. For example, the computing system can generate an accuracy filter based on at least one of (a) the query, or (b) contextual information associated with the requesting entity, and can apply the accuracy filter to the plurality of embeddings to identify a subset of embeddings (Colgan, [0054]). One of ordinary skill in the art at the time prior to the effective filing date of the instant invention would have been motivated by Colgan to improve the method of Li H. as modified. Therefore, it would have been obvious for one of ordinary skill in the art to use the filter of Colgan with the method of Li H. as modified. The benefit would be for increase accuracy.
RELEVANT PRIOR ART
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Li et al. (US 2025/0225132 A1) discloses this application pro-vides a vector search method. The method includes: obtaining a query object; obtaining, by querying a first index, N vector identifiers corresponding to the query object, where the first index is stored in a memory, N is a positive integer, the N vector identifiers include a plurality of first vector identifiers, and the first vector identifier is a vector identifier that is not determined to be recalled; determining, by que-rying index entries that are in a second index and that correspond to the plurality of first vector identifiers, second vector identifiers corresponding to the plurality of first vector identifiers, where the second vector identifier is a vector identifier that is determined to be recalled, the second index is stored in a persistent storage medium, and a compression ratio of a vector in the first index is greater than that of a vector in the second index; and obtaining a query result of the query object based on the second vector identifiers ([0005]).
Liu (US 2025/0005896 A1) discloses 1) distribute from a vector store a plurality of batches of vectors of the image data respectively to a first set of nodes, wherein each of the first set of nodes receives a batch of vectors; 2) deduplicate vectors in the batch of the vectors in each of the first set of nodes by removing duplicated vectors to obtain a deduplicated vector batch, wherein the duplicated vectors have a similarity score with another vector in the batch of vectors that is equal to or greater than a similarity threshold ([0025]).
Zhu et al. (US 2025/0013620 A1) discloses determining a first parameter group and a second parameter group in response to receiving a query request for a first vector database and there being no available index for the first vector database, wherein a parameter value in the second parameter group is greater than a corresponding parameter value in the first parameter group; constructing a first index for the first vector database based on the first parameter group, and querying the first vector database based on the first index; constructing a second index for the first vector database based on the second parameter group in response to meeting a preset condition; and in response to determining that construction of the second index is completed, deleting the first index, and querying the first vector database based on the second index ([0006]-[0009]).
Wang, K. (CN 111797096 A) discloses combining the each node server index data amount, obtaining the total index data amount; if detecting that the total index data amount exceeds a preset value, then indexing in a preset mode (page 2).
Zhao, Jing-bo (CN 113656406 A) discloses the index page combining device detects the index page corresponding to the database base table corresponding to the index tree included in the index page is lower than the set threshold value (such as 50 %), the index page is determined as the index page to be combined; and attempting to combine the index page to be merged with the adjacent left side index page or right side index page (page 6). In another embodiment, the index page combining device also can be the index data to be merged into the index page is divided into at least two groups of index data. For example, assuming that the index data in the index page to be combined is 100, then the index page combining device can be the 100 index data in the index page to be merged into 4 batches; the number of each batch of index data is 25 (page 8).
STATUS OF THE PRIOR ART
Claims 5, 9-11, 16, and 20 are dependent claims but free of prior art but still rejected under 35 U.S.C. 112 (pre-AIA ), second paragraph.
CONCLUSION
Patent applicants with problems or questions regarding electronic images that can be viewed in the Patent Application Information Retrieval system (PAIR) can now contact the USPTO's Patent Electronic Business Center (Patent EBC) for assistance. Representatives are available to answer your questions daily from 6 am to midnight (EST). The toll free number is (866) 217-9197. When calling please have your application serial or patent number, the type of document you are having an image problem with, the number of pages and the specific nature of the problem. The Patent Electronic Business Center will notify applicants of the resolution of the problem within 5-7 business days. Applicants can also check PAIR to confirm that the problem has been corrected. The USPTO's Patent Electronic Business Center is a complete service center supporting all patent business on the Internet. The USPTO's PAIR system provides Internet-based access to patent application status and history information. It also enables applicants to view the scanned images of their own application file folder(s) as well as general patent information available to the public.
For all other customer support, please call the USPTO Call Center (UCC) at 800-786-9199. The USPTO's official fax number is 571-272-8300.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to C. Dune Ly, whose telephone number is (571) 272-0716. The examiner can normally be reached on Monday-Friday from 8 A.M. to 4 PM ET.
If attempts to reach the examiner by telephone are unsuccessful, the examiner's supervisor, Neveen Abel-Jalil, can be reached on 571-270-0474.
/Cheyne D Ly/
Primary Examiner, Art Unit 2152
1/22/2026