Archive processing method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application provide a file processing method and device, electronic equipment and storage medium. The method comprises: determining a connected component to which each newly added sub-file belongs, any two sub-files belonging to the same connected component being able to form an association through direct or indirect relationship; performing file clustering on each sub-file under each connected component to obtain a plurality of file clustering groups, and determining a main file corresponding to each file clustering group, the main file corresponding to each file clustering group being a reference sub-file in each sub-file included in each file clustering group; and determining a file identifier of the reference sub-file as a file identifier associated with the file clustering group to which the reference sub-file belongs. The present scheme realizes local file clustering on each sub-file under each connected component, avoids error accumulation caused by file centroid deviation, and improves file merging efficiency.

Description

Technical Field

[0001] The present invention relates to the field of archival processing technology, and in particular to an archival processing method, apparatus, electronic device, and storage medium. Background Technology

[0002] In the security field, image clustering of captured targets plays a crucial role and is of paramount importance for public safety. Its working principle involves extracting feature vectors from captured images and comparing them, archiving images belonging to the same target to form an archive, and generating a mean feature as the centroid. When a newly added captured image reaches a specified threshold in comparison with the centroid, the new captured image is tagged and archived. As the number of tagged and archived captured images increases, centroid updates are performed periodically to enhance their representativeness.

[0003] In practical applications, with the increase in the number of files and the continuous updating of centroids, the phenomenon of one captured target corresponding to multiple files frequently occurs. Although a periodic file merging method is adopted, the new centroid may exhibit abnormal shifts after merging, causing the centroid to gradually deviate from the true characteristics of the captured target. More seriously, subsequent file merging operations may occur, at which point the shifted centroid will lead to more irrelevant captures being incorrectly labeled, further exacerbating the centroid shift and severely compromising the archiving accuracy of the captured target image. Summary of the Invention

[0004] This invention provides a file processing method, apparatus, electronic device, and storage medium to solve the problems of low efficiency in searching captured image files and centroid shift after file merging, which impairs the archiving accuracy of newly captured images.

[0005] In a first aspect, embodiments of the present invention provide a file processing method, the method comprising:

[0006] Determine the connected component to which each newly added sub-file belongs. Any two sub-files belonging to the same connected component can be associated with each other through direct or indirect relationships.

[0007] For each sub-file under each connected component, file clustering is performed to obtain multiple file cluster groups, and the master file corresponding to each file cluster group is determined. The master file corresponding to each file cluster group is the reference sub-file in each sub-file included in the file cluster group. The number of reference captured object images included in the reference sub-file is greater than the number of reference captured object images included in the remaining sub-files in the file cluster group where the reference sub-file is located.

[0008] The archival identifier of the benchmark sub-archive is determined as the archival identifier associated with the archival cluster group to which the benchmark sub-archive belongs.

[0009] Secondly, embodiments of the present invention also provide a file processing apparatus, the apparatus comprising:

[0010] The first determining module is used to determine the connected component to which each newly added sub-file belongs. Any two sub-files belonging to the same connected component can be associated with each other through direct or indirect relationships.

[0011] The file clustering module is used to cluster the sub-files under each connected component to obtain multiple file cluster groups, and to determine the master file corresponding to each file cluster group. The master file corresponding to each file cluster group is the reference sub-file among the sub-files included in each file cluster group. The number of reference captured object images included in the reference sub-file is greater than the number of reference captured object images included in the remaining sub-files in the file cluster group where the reference sub-file is located.

[0012] The second determination module is used to determine the archive identifier of the benchmark sub-archive as the archive identifier associated with the archive cluster group to which the benchmark sub-archive belongs.

[0013] Thirdly, this invention also provides an electronic device, which includes:

[0014] At least one processor; and

[0015] A memory that is communicatively connected to at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the file processing method of any embodiment of the present invention.

[0017] Fourthly, this invention also provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the file processing method of any embodiment of this invention.

[0018] The technical solution of this invention determines the connected component to which each newly added sub-file belongs. Any two sub-files belonging to the same connected component can be associated through direct or indirect relationships. This ensures that the centroid of the sub-file remains fixed after generation and does not change. Simultaneously, it maintains the similarity between sub-files and the connected component to which the newly added sub-file belongs in real time, facilitating effective management of the new sub-files. Multiple file clusters are obtained by clustering the sub-files under each connected component, and a master file corresponding to each file cluster group is determined. The master file corresponding to each file cluster group is the reference sub-file among the sub-files included in each file cluster group. The number of reference captured object images included in the reference sub-file is greater than... The number of reference captured object images included in the remaining sub-files within the file cluster group of the baseline sub-file enables local file clustering of each sub-file under each connected component. This avoids generating new file centroids, only marking merged sub-files as belonging to the same file cluster group. This prevents error accumulation caused by file centroid shift and improves file merging performance, enabling real-time file merging. The file identifier of the baseline sub-file is determined as the file identifier associated with the file cluster group to which the baseline sub-file belongs. This facilitates finding all sub-files contained in the file cluster group based on the file identifier associated with the file cluster group when displaying file image search results, and further finding the reference captured object images contained in the sub-file based on the file identifier of the sub-file.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] The above and other features, advantages, and aspects of the various embodiments of the present invention will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and the originals and elements are not necessarily drawn to scale.

[0021] Figure 1 A schematic flowchart of a file processing method provided in an embodiment of the present invention;

[0022] Figure 2 A flowchart illustrating another file processing method provided in an embodiment of the present invention;

[0023] Figure 3 This is a schematic diagram of the structure of an archive processing device provided in an embodiment of the present invention;

[0024] Figure 4 This is a schematic diagram of the structure of an electronic device that implements a file processing method according to an embodiment of the present invention. Detailed Implementation

[0025] Embodiments of the present invention will now be described in more detail with reference to the accompanying drawings. While some embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the invention. It should be understood that the accompanying drawings and embodiments are for illustrative purposes only and are not intended to limit the scope of protection of the invention.

[0026] It should be understood that the various steps described in the method embodiments of the present invention may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present invention is not limited in this respect.

[0027] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0028] It should be noted that the concepts of "first" and "second" mentioned in this invention are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0029] It should be noted that the terms "a" and "a plurality of" used in this invention are illustrative rather than restrictive. Those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0030] Figure 1 This is a flowchart illustrating a file processing method provided by an embodiment of the present invention. The technical solution of this embodiment is applicable to the merging and searching of files containing captured images of objects. This method can be executed by a file processing device, which can be implemented in the form of software and / or hardware, and is generally integrated into any electronic device with network communication capabilities, such as a mobile terminal, a PC, or a server.

[0031] like Figure 1 As shown, the file processing method of this embodiment of the invention may include the following processes:

[0032] S101. Determine the connected component to which each newly added sub-file belongs. Any two sub-files belonging to the same connected component can be associated through direct or indirect relationships.

[0033] In this embodiment of the invention, a capture device can be used to acquire several reference capture object images of different reference capture objects. Feature vectors are extracted and compared from these captured reference capture object images. Then, reference capture object images belonging to the same reference capture object are archived together to form a sub-file of the corresponding reference capture object. A reference capture object image can refer to an image captured in a specific scene that contains a reference capture object or features corresponding to a reference capture object. The reference capture object can be a person, vehicle, animal, or other subject moving in a specific environment. The reference capture object features can be the face of the reference capture object or texture features on the reference capture object that can be used to distinguish different reference capture objects. The capture device can refer to a front-end network camera, a camera on a terminal device, or a video surveillance device, etc. The capture device can capture images under certain triggering conditions to obtain the instantaneous state and features of the reference capture object.

[0034] A connected component can be a set of multiple interconnected sub-files, where any two sub-files belonging to the same connected component can be linked together through direct or indirect relationships. For example, multiple sub-files of a captured object at different times or locations can be linked together to form a connected component.

[0035] Specifically, in real-world scenarios, several images of captured objects are typically captured in real time and archived to form several new sub-files. Each new sub-file has a direct or indirect relationship with existing sub-files, belonging to corresponding connected components. Therefore, it is necessary to determine the connected components to which each new sub-file belongs in order to effectively manage each new sub-file when the number of new sub-files becomes too large.

[0036] S102. Perform file clustering on each sub-file under each connected component to obtain multiple file cluster groups, and determine the master file corresponding to each file cluster group. The master file corresponding to each file cluster group is the reference sub-file in each sub-file included in the file cluster group. The number of reference captured object images included in the reference sub-file is greater than the number of reference captured object images included in the remaining sub-files in the file cluster group where the reference sub-file is located.

[0037] In this embodiment of the invention, an archive clustering group can refer to a set of sub-archives belonging to the same connected component, and any two sub-archives belonging to the same archive clustering group satisfy a centroid similarity threshold. Here, the centroid can refer to the mean feature generated from all captured object images contained in the archive. For example, the centroid similarity between any two sub-archives belonging to the same archive clustering group is not less than 90%. It should be noted that archive clustering only groups multiple sub-archives belonging to the same connected component and satisfying the centroid similarity threshold together; it does not actually merge multiple sub-archives.

[0038] In this embodiment of the invention, the number of reference captured object images contained in all sub-files within the file cluster group can be calculated, and the sub-files can be sorted according to the number of reference captured object images contained in all sub-files, thereby selecting the sub-file containing the most reference captured object images as the base sub-file of the file cluster group. If there are at least two sub-files in the file cluster group that contain the most reference captured object images, then one of these at least two sub-files can be selected as the base sub-file.

[0039] Specifically, when the number of subfiles contained in a connected component exceeds a preset number of files, for each newly added subfile, community detection or clustering algorithms can be used to perform local file clustering on the connected component, generating multiple file cluster groups. For example, the preset number of files can be 3, and the clustering algorithm can be Louvain, Infomap, or KnnDBscan, etc. Then, from each generated file cluster group, the subfile containing the largest number of reference captured object images can be selected as the baseline subfile, and this baseline subfile becomes the master file of the file cluster group to which it belongs.

[0040] S103. The file identifier of the benchmark sub-file is determined as the file identifier associated with the file cluster group to which the benchmark sub-file belongs.

[0041] In this embodiment of the invention, a file identifier can refer to a set of codes or marks used to identify a sub-file, and it is unique. Typically, the file identifier can distinguish the sub-file corresponding to the file identifier from other sub-files, and can uniquely locate the sub-file corresponding to the file identifier. For example, the file identifier can be a unique number or file ID of the sub-file.

[0042] Specifically, after generating multiple file clusters by local file clustering of the sub-files contained in the connected components, the file identifier of the reference sub-file in each file cluster can be used as the file identifier associated with the file cluster to which the reference sub-file belongs. This allows the display of file search results to identify all sub-files contained in a file cluster based on the file identifier associated with the file cluster, and then to determine the reference captured object image contained in the sub-file based on the file identifier of the sub-file. For example, the file identifier associated with the file cluster can be the file ID of the reference sub-file.

[0043] As an optional but not limited implementation, the file processing method of this embodiment of the invention further includes the following steps A1-A3:

[0044] Step A1: Determine multiple first sub-files associated with the image to be searched. The image to be searched is the reference captured object image input when performing file search based on the image. Each first sub-file is a sub-file filtered by comparing similarity with the image to be searched.

[0045] Step A2: Determine the file cluster group to which each first sub-file belongs, and determine the similarity between the sub-files included in the file cluster group to which each first sub-file belongs and the image to be searched.

[0046] Step A3: Based on the similarity between the sub-files included in the file cluster group to which each first sub-file belongs and the image to be searched, determine the sub-files that the image to be searched will match from multiple first sub-files.

[0047] Specifically, the reference captured image input during image-based file search can be used as the search image. The search image is then compared with the sub-files under each connected component to determine their similarity. Based on the similarity comparison results, multiple sub-files exceeding a preset similarity threshold are selected as first sub-files associated with the search image. The preset similarity threshold indicates that the sub-files can be initially matched by the search image. The similarity comparison can refer to the centroid similarity comparison between the search image and the sub-files. Furthermore, the file cluster group to which each first sub-file belongs and the sub-files contained in each file cluster group are obtained. The sub-files contained in each file cluster group are then compared with the search image to determine the similarity between the sub-files in each file cluster group and the search image. Finally, the similarity between the file cluster to which each first sub-file belongs and the image to be searched is determined based on the similarity between the sub-files contained in the file cluster to which each first sub-file belongs and the image to be searched. This is used to determine the sub-files among multiple first sub-files that match the image to be searched, based on the similarity between the file cluster to which each first sub-file belongs and the image to be searched. For example, the first sub-file with the highest similarity to the image to be searched can be selected as the sub-file that matches the image to be searched.

[0048] As an optional but not limited implementation, the file processing method of this embodiment of the invention further includes the following steps B1-B4:

[0049] Step B1: Determine multiple first sub-files associated with the image to be searched. The image to be searched is the reference captured object image input when performing file search based on the image. Each first sub-file is a sub-file filtered by comparing similarity with the image to be searched.

[0050] Step B2: Determine the similarity between each third sub-file and the image to be searched. The third sub-file is a sub-file that does not belong to any of the first sub-files in the file clustering group.

[0051] Step B3: Determine the file cluster group to which each fourth sub-file belongs, and determine the similarity between the sub-files included in the file cluster group to which each fourth sub-file belongs and the image to be searched. The fourth sub-file is a sub-file that exists in a file cluster group among multiple first sub-files.

[0052] Step B4: Based on the similarity between each third sub-file and the image to be searched, and the similarity between the sub-files included in the file cluster group to which each fourth sub-file belongs and the image to be searched, determine the sub-files that the image to be searched has matched from multiple first sub-files.

[0053] Specifically, subfiles that do not belong to any of the first subfiles can be designated as third subfiles, and subfiles that belong to any of the first subfiles can be designated as fourth subfiles. Then, the subfiles within each fourth subfile's file cluster are compared with the image to be searched to obtain the similarity score. Based on the similarity scores of the subfiles within each fourth subfile's file cluster and the image to be searched, the similarity score of each fourth subfile's file cluster and the image to be searched is determined. Finally, based on the similarity scores of each third subfile and each fourth subfile's file cluster and the image to be searched, the subfiles that match the image to be searched are determined from the multiple first subfiles.

[0054] As an optional but not limited implementation, the sub-files that the search image will match are determined from multiple first sub-files based on the similarity between the sub-files included in the file cluster group to which each first sub-file belongs and the image to be searched, including the following steps C1-C3:

[0055] Step C1: For each first sub-file to which the file cluster group belongs, determine multiple second sub-files from the sub-files included in the file cluster group to which the first sub-file belongs, so that the sum of the number of reference captured object images in the multiple second sub-files is not less than a preset percentage of the sum of the number of reference captured object images in all sub-files of the file cluster group to which the first sub-file belongs.

[0056] Step C2: Determine the similarity between each first sub-file and the image to be searched based on the similarity between each second sub-file determined from each first sub-file and the image to be searched.

[0057] Step C3: Based on the similarity between each first sub-file and the image to be searched, determine the sub-files that the image to be searched has matched from the multiple first sub-files.

[0058] Specifically, multiple subfiles are selected from all subfiles in the file cluster group to which the first subfile belongs as multiple second subfiles. The sum of the number of reference captured object images in the multiple second subfiles must be no less than a preset percentage of the sum of the number of reference captured object images in all subfiles in the file cluster group. For example, the preset percentage can be 50%. Then, each second subfile is compared with the image to be searched to obtain the similarity score between each second subfile and the image to be searched. Based on the similarity score between each second subfile and the image to be searched, the similarity score between the file cluster group to which the first subfile belongs and the image to be searched is determined. This process is repeated to obtain the similarity score between the file cluster group to which each first subfile belongs and the image to be searched, thereby identifying the subfiles among the multiple first subfiles that match the image to be searched.

[0059] As an optional but not limited implementation, multiple second sub-files are determined from the sub-files included in the file cluster group to which the first sub-file belongs, including the following steps D1-D2:

[0060] Step D1: If the number of reference captured object images in the first sub-file of the file cluster to which the first sub-file belongs is not less than the preset percentage of the sum of the number of reference captured object images in all sub-files of the file cluster to which the first sub-file belongs, then the first sub-file of the file cluster to which the first sub-file belongs is directly determined as multiple second sub-files.

[0061] Step D2: If the sum of the number of reference captured object images in the first sub-file of the file cluster to which the first sub-file belongs is less than a preset percentage of the sum of the number of reference captured object images in all sub-files of the file cluster to which the first sub-file belongs, then select a sub-file to be supplemented from the sub-files of the file cluster to which the first sub-file belongs but not belonging to multiple first sub-files, and supplement the first sub-file of the file cluster to which the first sub-file belongs to obtain multiple second sub-files; wherein, the sub-file to be supplemented meets the following condition: when the sum of the number of reference captured object images in multiple second sub-files is not less than a preset percentage of the sum of the number of reference captured object images in all sub-files of the file cluster to which the first sub-file belongs, the number of reference captured object images in the sub-file to be supplemented participating in the file supplementation is less than the number of reference captured object images in other sub-files participating in the file supplementation, and other sub-files are at least one sub-file other than the sub-file to be supplemented among the sub-files of the file cluster to which the first sub-file belongs but not belonging to multiple first sub-files.

[0062] Specifically, if the file cluster to which the first sub-file belongs contains multiple first sub-files that were initially detected by the search, then the actual percentage of the number of reference captured object images in the multiple first sub-files contained in the file cluster to the total number of reference captured object images in all sub-files contained in the file cluster is calculated. Then, it is determined whether the actual percentage is not less than a preset percentage. If the actual percentage is not less than the preset percentage, then the multiple first sub-files contained in the file cluster to which the first sub-file belongs are treated as multiple second sub-files.

[0063] If the actual percentage is less than the preset percentage, then a sub-file that does not belong to multiple first sub-files is selected from the file cluster group to which the first sub-file belongs as a sub-file to be supplemented, and the sub-file to be supplemented and the multiple first sub-files contained in the file cluster group are selected as multiple second sub-files. Specifically, the percentage of the number of reference captured object images in the sub-file to be supplemented and the multiple first sub-files contained in the file cluster group relative to the total number of reference captured object images in all sub-files contained in the file cluster group is not less than the preset percentage, and the number of reference captured object images in the sub-file to be supplemented is less than the number of reference captured object images in at least one sub-file contained in the file cluster group other than the multiple first sub-files and the sub-file to be supplemented.

[0064] As an optional but not limited implementation, the similarity between each first sub-file and the image to be searched is determined based on the similarity between each second sub-file determined from each first sub-file and the image to be searched, including the following steps E1-E2:

[0065] Step E1: Determine the weighting weight of each second sub-file determined from each first sub-file. The weighting weight of each second sub-file is determined based on the proportion of the number of reference capture object images in each second sub-file to the total number of reference capture object images in all second sub-files.

[0066] Step E2: Based on the similarity between each second sub-file and the image to be searched, and the weighted weight of each second sub-file, determine the similarity between each first sub-file and the image to be searched; wherein, the similarity between the second sub-file corresponding to the supplementary sub-file and the image to be searched is the minimum similarity among the multiple first sub-files associated with the image to be searched and the image to be searched.

[0067] Specifically, the proportion of reference captured object images in each of the second sub-files within the archive cluster group to which the first sub-file belongs can be calculated as the sum of the total number of reference captured object images in all second sub-files within the archive cluster group. This weight is used as the weighted average of each second sub-file within the archive cluster group to which the first sub-file belongs. Then, the similarity between each second sub-file within the archive cluster group to which the first sub-file belongs and the image to be searched is calculated using a weighted average to obtain the similarity between the archive cluster group to which the first sub-file belongs and the image to be searched. This similarity is then used as the similarity between the first sub-file and the image to be searched. If a second sub-file contains sub-files to be supplemented, the similarity between the second sub-file corresponding to the supplemented sub-file and the image to be searched is the minimum similarity among the multiple similarities between the first sub-files associated with the image to be searched and the image to be searched. This avoids a small number or very small number of sub-files having an excessive impact on the similarity between the archive cluster group and the image to be searched, thereby improving the effectiveness of the archive image search. This process is repeated to obtain the similarity between each first sub-file and the image to be searched.

[0068] For example, the file cluster group includes sub-files A, B, C, D, and E, with reference captured object images numbering 10, 20, 20, 15, and 5 respectively. Sub-files A and B are the first sub-files associated with the image to be searched, and the total number of reference captured object images in all sub-files within the file cluster group is 70. When the preset percentage is 50%, sub-file E is selected as a supplementary sub-file, combined with sub-files A and B to form multiple second sub-files within the file cluster group. Simultaneously, the similarity between sub-files A and B and the image to be searched is 95% and 90% respectively, and the minimum similarity between the multiple first sub-files associated with the image to be searched and the image to be searched is 60%. Therefore, the similarity between the file cluster group and the image to be searched is:

[0069] The technical solution of this invention determines the connected component to which each newly added sub-file belongs. Any two sub-files belonging to the same connected component can be associated through direct or indirect relationships. This ensures that the centroid of the sub-file remains fixed after generation and does not change. Simultaneously, it maintains the similarity between sub-files and the connected component to which the newly added sub-file belongs in real time, facilitating effective management of the new sub-files. Multiple file clusters are obtained by clustering the sub-files under each connected component, and a master file corresponding to each file cluster group is determined. The master file corresponding to each file cluster group is the reference sub-file among the sub-files included in each file cluster group. The number of reference captured object images included in the reference sub-file is greater than... The number of reference captured object images included in the remaining sub-files within the file cluster group of the baseline sub-file enables local file clustering of each sub-file under each connected component. This avoids generating new file centroids, only marking merged sub-files as belonging to the same file cluster group. This prevents error accumulation caused by file centroid shift and improves file merging performance, enabling real-time file merging. The file identifier of the baseline sub-file is determined as the file identifier associated with the file cluster group to which the baseline sub-file belongs. This facilitates finding all sub-files contained in the file cluster group based on the file identifier associated with the file cluster group when displaying file image search results, and further finding the reference captured object images contained in the sub-file based on the file identifier of the sub-file.

[0070] Figure 2 This is a flowchart illustrating another file processing method provided by an embodiment of the present invention. The technical solution of this embodiment further optimizes the determination of the connected components to which each newly added sub-file belongs in the foregoing embodiments based on the technical solutions of the above embodiments. This embodiment can be combined with various optional solutions in one or more of the above embodiments.

[0071] like Figure 2As shown, the file processing method of this embodiment of the invention may include the following processes:

[0072] S201. For each newly generated sub-file after the aggregation is completed, determine multiple target sub-files associated with the newly generated sub-file from several candidate sub-files. The file similarity between the target sub-file and the newly generated sub-file is greater than the preset file similarity. The preset file similarity is the similarity threshold that needs to be met to determine whether the two files need to be merged.

[0073] Specifically, several captured images are clustered to generate multiple new sub-files. Each new sub-file is then compared for file similarity with several candidate sub-files. Candidate sub-files can refer to sub-files whose connected components have been identified, and file similarity can refer to the centroid similarity between two sub-files. Based on the file similarity comparison results, multiple target sub-files with file similarity greater than a preset file similarity threshold can be identified from the candidate sub-files. The preset file similarity threshold can be a file similarity threshold that must be met when merging new and target sub-files. For example, the file similarity between the new and target sub-files needs to be greater than 80%.

[0074] S202. Configure the connected components to which each of the multiple target subfiles associated with the newly added subfile belongs.

[0075] Specifically, the connected components of each of the multiple target subfiles associated with the new subfile are obtained from the candidate subfiles, so as to determine the connected components of each new subfile based on the connected components of the multiple target subfiles.

[0076] As an optional but not limited implementation, based on the connected components to which each of the multiple target subfiles associated with the newly added subfile belongs, the connected components are configured, including the following steps F1-F3:

[0077] Step F1: If multiple target subfiles associated with the newly added subfile belong to the same connected component, then configure the newly added subfile under the connected component to which the multiple target subfiles belong.

[0078] Step F2: If the multiple target subfiles associated with the newly added subfile do not belong to the same connected component, then determine the connected component to which the reference subfile belongs from the connected components to which the multiple target subfiles belong. The number of subfiles included in the connected component to which the reference subfile belongs is greater than the number of subfiles included in the connected components to which the multiple target subfiles belong, excluding the connected component to which the reference subfile belongs.

[0079] Step F3: Configure the newly added subfile to the connected component to which the reference subfile belongs, and configure the subfiles other than the reference subfile from multiple target subfiles to the connected component to which the reference subfile belongs.

[0080] Specifically, if multiple target subfiles associated with the new subfile, identified from candidate subfiles, belong to the same connected component, the new subfile is configured under the same connected component to which the multiple target subfiles belong; that is, the connected component to which the new subfile belongs is determined as the same connected component to which the multiple target subfiles belong. If multiple target subfiles associated with the new subfile, identified from candidate subfiles, belong to multiple different connected components, the connected component containing the most subfiles is determined from the multiple different connected components. Any target subfile contained in the connected component with the most subfiles can be used as a reference subfile. Furthermore, the new subfile is configured under the connected component to which the reference subfile belongs, and all target subfiles other than the reference subfile are also configured under the connected component to which the reference subfile belongs; that is, the connected component to which the new subfile belongs and the connected components to which the target subfiles other than the reference subfile belong are both determined as the connected components to which the reference subfile belongs.

[0081] S203. Perform file clustering on each sub-file under each connected component to obtain multiple file cluster groups, and determine the master file corresponding to each file cluster group. The master file corresponding to each file cluster group is the reference sub-file in each sub-file included in the file cluster group. The number of reference captured object images included in the reference sub-file is greater than the number of reference captured object images included in the remaining sub-files in the file cluster group where the reference sub-file is located.

[0082] S204. The file identifier of the benchmark sub-file is determined as the file identifier associated with the file cluster group to which the benchmark sub-file belongs.

[0083] As an optional but not limited implementation, the file processing method of this embodiment of the invention further includes the following steps G1-G2:

[0084] Step G1: If a first type of sub-file exists in each sub-file of each connected component after file merging, then the file image search index of the first type of sub-file is cleared. The file image search index is used to indicate the file index corresponding to the sub-file that needs to participate in the file image search comparison in the image search operation. The time difference between the archiving time of all reference captured object images included in the first type of sub-file and the time of execution of the image search operation is greater than the first preset time difference.

[0085] Step G2: If there are second-type sub-files in each sub-file of each connected component after file merging, then the file information of the second-type sub-files and the reference captured image information included in the file are cleared; the time difference between the archiving time of all reference captured object images included in the second-type sub-files and the time of the image search operation is greater than the second preset time difference, and the first preset time difference is less than the second preset time difference.

[0086] In this embodiment of the invention, the image search operation can refer to the operation of searching and comparing each sub-file under each connected component based on the image of the captured object to be searched and the image search index, and then hitting the sub-file. The image search index can refer to the file index corresponding to the sub-file that needs to be searched and compared with the image of the captured object when performing the image search operation. The file index can refer to the search and comparison guide established for the sub-file according to certain rules and standards.

[0087] In this embodiment of the invention, sub-files whose archive time and execution time of all reference captured images not found during the image search operation are both greater than a first preset time difference can be classified as first-type sub-files. Sub-files whose archive time and execution time of all reference captured images not found during the image search operation are both greater than a second preset time difference can be classified as second-type sub-files. The first and second preset time differences can refer to time differences that need to be preset when clearing sub-files, and the first preset time difference must be less than the second preset time difference to conform to the sub-file clearing logic. For example, the first preset time difference can be 3 months, and the second preset time difference can be 1 year.

[0088] Specifically, over time, the capture device continuously captures and archives numerous images of captured objects, leading to a continuous increase in the number of sub-files. This increases the performance pressure on image search operations. Therefore, it is necessary to clean up sub-files that have not been searched for a long time during image search operations. This cleanup can include clearing the image search indexes of the first type of sub-files and clearing the file information and all reference captured image information included in the second type of sub-files. It is important to note that clearing the image search indexes of the first type of sub-files is to prevent them from participating in the search comparison during image search operations, thereby reducing the performance pressure on image search operations. However, the first type of sub-files and all their reference captured image information are still retained and can be searched through the file cluster to which they belong. Cleaning up sub-files that have not been searched for a long time ensures that the retained sub-files are all active, thus maintaining a balance in the number of sub-files.

[0089] The technical solution of this invention, for each newly generated sub-file after file aggregation, determines multiple target sub-files associated with the new sub-file from a number of candidate sub-files. The file similarity between the target sub-files and the new sub-files is greater than a preset file similarity threshold, which is a similarity threshold required to determine whether two files need to be merged. Based on the connected components to which each of the multiple target sub-files associated with the new sub-file belongs, the connected components to which each new sub-file belongs are configured, realizing the determination of the connected components to which the new sub-file belongs based on the file similarity between the new sub-file and existing sub-files, thus improving the accuracy of configuring the connected components to which the new sub-file belongs. File clustering is performed on each sub-file under each connected component to obtain multiple file cluster groups, and the main file corresponding to each file cluster group is determined. Each file cluster group is associated with... The primary archive is the reference sub-archive within each sub-archive of each archive cluster group. The number of reference captured object images included in the reference sub-archive is greater than the number of reference captured object images included in the remaining sub-archives in the archive cluster group to which the reference sub-archive belongs. This achieves local archive clustering of each sub-archive under each connected component without generating new archive centroids. It only marks the merged sub-archives as belonging to the same archive cluster group, avoiding error accumulation caused by archive centroid offset and improving the performance of archive merging, enabling real-time archive merging. The archive identifier of the reference sub-archive is determined as the archive identifier associated with the archive cluster group to which the reference sub-archive belongs. This allows for the retrieval of all sub-archives contained in the archive cluster group based on the archive identifier associated with the archive cluster group when displaying the archive image search results. Furthermore, it allows the retrieval of reference captured object images contained in the sub-archive based on the archive identifier of the sub-archive.

[0090] Figure 3 This is a schematic diagram of the structure of an archive processing device provided in an embodiment of the present invention. The technical solution of the present invention is applicable to the merging and searching of archives containing captured images of objects. The archive processing device can be implemented in the form of software and / or hardware, and is generally integrated into any electronic device with network communication function, such as a mobile terminal, a PC, or a server.

[0091] like Figure 3 As shown, the file processing apparatus of this embodiment may include the following:

[0092] The first determining module 301 is used to determine the connected component to which each newly added sub-file belongs. Any two sub-files belonging to the same connected component can be associated with each other through direct or indirect relationships.

[0093] The file clustering module 302 is used to perform file clustering on each sub-file under each connected component to obtain multiple file clustering groups, and to determine the master file corresponding to each file clustering group. The master file corresponding to each file clustering group is the reference sub-file in each sub-file included in the file clustering group. The number of reference captured object images included in the reference sub-file is greater than the number of reference captured object images included in the remaining sub-files in the file clustering group where the reference sub-file is located.

[0094] The second determining module 303 is used to determine the archive identifier of the benchmark sub-archive as the archive identifier associated with the archive cluster group to which the benchmark sub-archive belongs.

[0095] Based on the above embodiments, optionally, determining the connected component to which each newly added sub-file belongs includes:

[0096] For each newly generated sub-file after the aggregation is completed, multiple target sub-files associated with the newly generated sub-file are determined from several candidate sub-files. The file similarity between the target sub-file and the newly generated sub-file is greater than the preset file similarity. The preset file similarity is the similarity threshold that must be met to determine whether the two files need to be merged.

[0097] Based on the connected components to which each of the multiple target subfiles associated with the newly added subfile belongs, the connected components to which each newly added subfile belongs are configured.

[0098] Based on the above embodiments, optionally, based on the connected components to which each of the multiple target subfiles associated with the newly added subfile belongs, the connected components to which each subfile belongs are configured, including:

[0099] If multiple target subfiles associated with the newly added subfile belong to the same connected component, then the newly added subfile will be configured under the connected component to which the multiple target subfiles belong.

[0100] If multiple target subfiles associated with a newly added subfile do not belong to the same connected component, then the connected component to which the reference subfile belongs is determined from the connected components to which each of the multiple target subfiles belongs. The number of subfiles included in the connected component to which the reference subfile belongs is greater than the number of subfiles included in the connected components to which each of the multiple target subfiles belongs, excluding the connected component to which the reference subfile belongs.

[0101] The new subfile is configured under the connected component to which the reference subfile belongs, and the subfiles other than the reference subfile from multiple target subfiles are configured under the connected component to which the reference subfile belongs.

[0102] Optionally, based on the above embodiments, the file processing apparatus of the present invention is further used for:

[0103] If a first-class sub-file exists in each sub-file under each connected component after file merging, the file image search index of the first-class sub-file is cleared. The file image search index is used to indicate the file index corresponding to the sub-file that needs to participate in the file image search comparison in the image search operation. The time difference between the archiving time of all reference captured object images included in the first-class sub-file and the time of execution of the image search operation is greater than the first preset time difference.

[0104] If a second type of sub-file exists in each sub-file of each connected component after file merging, the file information of the second type of sub-file and the reference captured image information included in the file are cleared; the time difference between the archiving time of all reference captured object images included in the second type of sub-file and the time of the image search operation is greater than the second preset time difference, and the first preset time difference is less than the second preset time difference.

[0105] Optionally, based on the above embodiments, the file processing apparatus of the present invention is further used for:

[0106] The first sub-files associated with the image to be searched are identified. The image to be searched is the reference captured object image input when performing file search based on the image. Each first sub-file is a sub-file filtered by comparing similarity with the image to be searched.

[0107] Determine the file cluster group to which each first sub-file belongs, and determine the similarity between the sub-files included in each file cluster group to which the first sub-file belongs and the image to be searched;

[0108] Based on the similarity between the subfiles included in the file cluster to which each first subfile belongs and the image to be searched, the subfiles that the image to be searched is matched are determined from multiple first subfiles.

[0109] Based on the above embodiments, optionally, the sub-files that the search image matches are determined from multiple first sub-files according to the similarity between the sub-files included in the file cluster group to which each first sub-file belongs and the image to be searched, including:

[0110] For each first sub-file to which the file cluster group belongs, multiple second sub-files are determined from the sub-files included in the file cluster group to which the first sub-file belongs, so that the sum of the number of reference captured object images in the multiple second sub-files is not less than a preset percentage of the sum of the number of reference captured object images in all sub-files of the file cluster group to which the first sub-file belongs.

[0111] Based on the similarity between each second sub-file and the image to be searched, the sub-files that the image to be searched is matched are determined from multiple first sub-files.

[0112] Based on the above embodiments, optionally, multiple second sub-files are determined from the sub-files included in the file cluster group to which the first sub-file belongs, including:

[0113] If the number of reference captured object images in the first sub-file of the file cluster group to which the first sub-file belongs is not less than the preset percentage of the sum of the number of reference captured object images in all sub-files of the file cluster group to which the first sub-file belongs, then the first sub-file of the file cluster group to which the first sub-file belongs is directly determined as multiple second sub-files.

[0114] If the sum of the number of reference captured object images in the first sub-file of the archive cluster to which the first sub-file belongs is less than the preset percentage of the sum of the number of reference captured object images in all sub-files of the archive cluster to which the first sub-file belongs, then the sub-files to be supplemented are selected from the sub-files of the archive cluster to which the first sub-file belongs but do not belong to multiple first sub-files, and the first sub-files of the archive cluster to which the first sub-file belongs are supplemented to obtain multiple second sub-files;

[0115] The sub-file to be supplemented meets the following conditions: provided that the number of reference captured object images in multiple second sub-files is not less than the sum of the number of reference captured object images in all sub-files of the file cluster to which the first sub-file belongs, the number of reference captured object images in the sub-file to be supplemented participating in the file supplementation is less than the number of reference captured object images in other sub-files participating in the file supplementation, and the other sub-files are at least one sub-file located in the file cluster to which the first sub-file belongs and not belonging to multiple first sub-files other than the sub-file to be supplemented.

[0116] Based on the above embodiments, optionally, the similarity between each first sub-file and the image to be searched is determined according to the similarity between each second sub-file determined from each first sub-file and the image to be searched, including:

[0117] The weighting weight of each second sub-file determined from each first sub-file is determined based on the proportion of the number of reference capture object images in each second sub-file to the total number of reference capture object images in all second sub-files.

[0118] Based on the similarity between each second sub-file and the image to be searched, and the weighted weight of each second sub-file, the similarity between each first sub-file and the image to be searched is determined; wherein, the similarity between the second sub-file corresponding to the supplementary sub-file and the image to be searched is the minimum similarity among the multiple first sub-files associated with the image to be searched and the image to be searched.

[0119] The technical solution of this invention determines the connected component to which each newly added sub-file belongs. Any two sub-files belonging to the same connected component can be associated through direct or indirect relationships. This ensures that the centroid of the sub-file remains fixed after generation and does not change. Simultaneously, it maintains the similarity between sub-files and the connected component to which the newly added sub-file belongs in real time, facilitating effective management of the new sub-files. Multiple file clusters are obtained by clustering the sub-files under each connected component, and a master file corresponding to each file cluster group is determined. The master file corresponding to each file cluster group is the reference sub-file among the sub-files included in each file cluster group. The number of reference captured object images included in the reference sub-file is greater than... The number of reference captured object images included in the remaining sub-files within the file cluster group of the baseline sub-file enables local file clustering of each sub-file under each connected component. This avoids generating new file centroids, only marking merged sub-files as belonging to the same file cluster group. This prevents error accumulation caused by file centroid shift and improves file merging performance, enabling real-time file merging. The file identifier of the baseline sub-file is determined as the file identifier associated with the file cluster group to which the baseline sub-file belongs. This facilitates finding all sub-files contained in the file cluster group based on the file identifier associated with the file cluster group when displaying file image search results, and further finding the reference captured object images contained in the sub-file based on the file identifier of the sub-file.

[0120] The document processing apparatus provided in the embodiments of the present invention can execute the document processing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the document processing method.

[0121] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of the present invention.

[0122] Figure 4 This is a schematic diagram of an electronic device implementing a file processing method according to an embodiment of the present invention. The following refers to... Figure 4 It illustrates an electronic device suitable for implementing embodiments of the present invention (e.g., Figure 4 The diagram below shows the structure of the terminal device or server 400. The terminal device in this embodiment may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and vehicle terminals (e.g., vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 4The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0123] like Figure 4 As shown, electronic device 400 may include a processing unit (e.g., central processing unit, graphics processor, etc.) 401, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 402 or a program loaded from storage device 408 into random access memory (RAM) 403. The RAM 403 also stores various programs and data required for the operation of electronic device 400. The processing unit 401, ROM 402, and RAM 403 are interconnected via bus 404. An edit / output (I / O) interface 405 is also connected to bus 404.

[0124] Typically, the following devices can be connected to I / O interface 405: input devices 406 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 407 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 408 including, for example, magnetic tapes, hard disks, etc.; and communication devices 409. Communication device 409 allows electronic device 400 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 4 An electronic device 400 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0125] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the file processing method shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 409, or installed from a storage device 408, or installed from a ROM 402. When the computer program is executed by the processing device 401, it performs the functions defined in the file processing method of the embodiments of the present invention.

[0126] The names of the messages or information exchanged between the multiple devices in the embodiments of the present invention are for illustrative purposes only and are not intended to limit the scope of these messages or information.

[0127] The electronic device provided in this embodiment of the invention and the file processing method provided in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0128] This invention provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the file processing method provided in the above embodiments.

[0129] It should be noted that the computer-readable medium described above in this invention can be a computer-readable signal medium, a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on a computer-readable storage medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0130] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0131] The aforementioned computer-readable storage medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0132] The aforementioned computer-readable storage medium carries one or more programs. When the aforementioned one or more programs are executed by the electronic device, the electronic device causes the following to occur: determine the connected component to which each newly added sub-file belongs, wherein any two sub-files belonging to the same connected component can be associated through a direct or indirect relationship; perform file clustering on each sub-file under each connected component to obtain multiple file cluster groups, and determine the master file corresponding to each file cluster group, wherein the master file corresponding to each file cluster group is the reference sub-file among the sub-files included in each file cluster group, and the number of reference captured object images included in the reference sub-file is greater than the number of reference captured object images included in the remaining sub-files in the file cluster group to which the reference sub-file belongs; and determine the file identifier of the reference sub-file as the file identifier associated with the file cluster group to which the reference sub-file belongs.

[0133] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0134] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0135] The units described in the embodiments of the present invention can be implemented in software or in hardware. The name of a unit does not necessarily limit the unit itself; for example, the first acquisition unit can also be described as "a unit that acquires at least two Internet Protocol addresses".

[0136] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0137] In the context of this invention, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0138] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this invention is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this invention.

[0139] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in sequential order. In certain circumstances, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the invention. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0140] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. A method for processing archives, characterized in that, The method includes: Determine the connected component to which each newly added sub-file belongs. Any two sub-files belonging to the same connected component can be associated with each other through direct or indirect relationships. For each sub-file under each connected component, file clustering is performed to obtain multiple file cluster groups, and the master file corresponding to each file cluster group is determined. The master file corresponding to each file cluster group is the reference sub-file in each sub-file included in the file cluster group. The number of reference captured object images included in the reference sub-file is greater than the number of reference captured object images included in the remaining sub-files in the file cluster group where the reference sub-file is located. The file identifier of the benchmark sub-file is determined as the file identifier associated with the file cluster group to which the benchmark sub-file belongs.

2. The method according to claim 1, characterized in that, Determine the connected components to which each newly added subfile belongs, including: For each newly generated sub-file after the aggregation is completed, multiple target sub-files associated with the newly generated sub-file are determined from a number of candidate sub-files. The file similarity between the target sub-files and the newly generated sub-files is greater than a preset file similarity. The preset file similarity is a similarity threshold that needs to be met to determine whether two files need to be merged. Based on the connected components to which the newly added sub-files belong, the connected components to which each newly added sub-file belongs are configured.

3. The method according to claim 2, characterized in that, Based on the connected components to which each of the multiple target subfiles associated with the newly added subfile belongs, the connected components to which each newly added subfile belongs are configured, including: If the newly added sub-file is associated with multiple target sub-files that all belong to the same connected component, then the newly added sub-file will be configured under the connected component to which the multiple target sub-files belong. If the multiple target subfiles associated with the newly added subfile do not belong to the same connected component, then the connected component to which the reference subfile belongs is determined from the connected components to which the multiple target subfiles belong. The number of subfiles included in the connected component to which the reference subfile belongs is greater than the number of subfiles included in the connected components to which the multiple target subfiles belong, excluding the connected component to which the reference subfile belongs. The newly added subfile is configured under the connected component to which the reference subfile belongs, and the subfiles other than the reference subfile among the multiple target subfiles are configured under the connected component to which the reference subfile belongs.

4. The method according to claim 1, characterized in that, The method further includes: If a first type of sub-file exists in each sub-file under each connected component after file merging, the file image search index of the first type of sub-file is cleared. The file image search index is used to indicate the file index corresponding to the sub-file that needs to participate in the file image search comparison in the image search operation. The time difference between the archiving time of all reference captured object images included in the first type of sub-file and the execution time of the image search operation is greater than the first preset time difference. If a second type of sub-file exists in each sub-file of each connected component after file merging, the file information of the second type of sub-file and the reference captured image information included in the file are cleared; the time difference between the archiving time of all reference captured object images included in the second type of sub-file and the time of the image search operation is greater than the second preset time difference, and the first preset time difference is less than the second preset time difference.

5. The method according to claim 1, characterized in that, The method further includes: A plurality of first sub-files associated with the image to be searched are determined. The image to be searched is a reference captured object image input when performing file search based on an image. Each first sub-file is a sub-file filtered by comparing similarity with the image to be searched. Determine the file cluster group to which each of the first sub-files belongs, and determine the similarity between the sub-files included in each file cluster group to which the first sub-file belongs and the image to be searched; Based on the similarity between the sub-files included in the file cluster to which each of the first sub-files belongs and the image to be searched, the sub-files that the image to be searched is matched are determined from multiple first sub-files.

6. The method according to claim 5, characterized in that, Based on the similarity between the sub-files included in the file cluster group to which each of the first sub-files belongs and the image to be searched, the sub-files that the image to be searched is matched are determined from multiple first sub-files, including: For each file cluster to which the first sub-file belongs, a plurality of second sub-files are determined from the sub-files included in the file cluster to which the first sub-file belongs, such that the number of reference captured object images in the plurality of second sub-files is not less than a preset percentage of the sum of the number of reference captured object images in all sub-files of the file cluster to which the first sub-file belongs. The similarity between each first sub-file and the image to be searched is determined based on the similarity between each second sub-file determined from each first sub-file and the image to be searched. Based on the similarity between each of the first sub-files and the image to be searched, the sub-files that the image to be searched is matched are determined from the multiple first sub-files.

7. The method according to claim 6, characterized in that, Multiple second sub-files are identified from the sub-files included in the file cluster group to which the first sub-file belongs, including: If the number of reference captured object images in the first sub-file of the file cluster group to which the first sub-file belongs is not less than a preset percentage of the sum of the number of reference captured object images in all sub-files of the file cluster group to which the first sub-file belongs, then the first sub-file of the file cluster group to which the first sub-file belongs is directly determined as the plurality of second sub-files. If the sum of the number of reference captured object images in the first sub-file of the file cluster group to which the first sub-file belongs is less than a preset percentage of the sum of the number of reference captured object images in all sub-files of the file cluster group to which the first sub-file belongs, then a sub-file to be supplemented is selected from the sub-files of the file cluster group to which the first sub-file belongs but not to the plurality of first sub-files, and the first sub-file of the file cluster group to which the first sub-file belongs is supplemented to obtain the plurality of second sub-files; The sub-file to be supplemented satisfies the following condition: when the number of reference captured object images in the plurality of second sub-files is not less than a preset percentage of the sum of the number of reference captured object images in all sub-files of the file cluster to which the first sub-file belongs, the number of reference captured object images in the sub-file to be supplemented participating in the file supplementation is less than the number of reference captured object images in other sub-files participating in the file supplementation, wherein the other sub-files are at least one sub-file located in the file cluster to which the first sub-file belongs and not belonging to the plurality of first sub-files other than the sub-file to be supplemented.

8. The method according to claim 7, characterized in that, Determining the similarity between each of the first sub-files and the image to be searched, based on the similarity between each of the second sub-files determined from each of the first sub-files and the image to be searched, includes: The weighting weight of each second sub-file determined from each first sub-file is determined based on the proportion of the number of reference capture object images in each second sub-file to the total number of reference capture object images in all second sub-files; Based on the similarity between each second sub-file and the image to be searched, and the weighted weight of each second sub-file, the similarity between each first sub-file and the image to be searched is determined; wherein, the similarity between the second sub-file corresponding to the supplementary sub-file and the image to be searched is the minimum similarity among the multiple first sub-files associated with the image to be searched and the image to be searched.

9. A file processing device, characterized in that, The device includes: The first determining module is used to determine the connected component to which each newly added sub-file belongs. Any two sub-files belonging to the same connected component can be associated with each other through direct or indirect relationships. The file clustering module is used to perform file clustering on each sub-file under each connected component to obtain multiple file cluster groups, and to determine the master file corresponding to each file cluster group. The master file corresponding to each file cluster group is the reference sub-file in each sub-file included in the file cluster group. The number of reference captured object images included in the reference sub-file is greater than the number of reference captured object images included in the remaining sub-files in the file cluster group where the reference sub-file is located. The second determining module is used to determine the file identifier of the benchmark sub-file as the file identifier associated with the file cluster group to which the benchmark sub-file belongs.

10. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the file processing method according to any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the file processing method according to any one of claims 1-8.

Images