A file naming method and system based on big data processing

Abstract

The application provides a file naming method and system based on big data processing, and relates to the technical field of file naming. The method comprises the following steps: obtaining a plurality of to-be-named video files; determining a representative frame of each to-be-named video file by processing the plurality of to-be-named video files based on a file analysis model; determining a plurality of alternative names of each to-be-named video file by using a convolutional neural network model based on the representative frame of each to-be-named video file; determining a file target name of each to-be-named video file based on the plurality of alternative names of each to-be-named video file and the content similarity between different representative frames; and naming each video file based on the file target name of each to-be-named video file. The method can accurately name a large number of video files received at one time.

Description

Technical Field

[0001] This invention relates to the field of file naming technology, and specifically to a file naming method and system based on big data processing. Background Technology

[0002] With the widespread use of the internet and mobile devices, users are receiving and sharing video files more and more frequently on social media platforms. Especially on social media, instant messaging tools, and file-sharing platforms, users often receive a large number of video files at once. These files are often unnamed or use inconsistent naming conventions, making it very difficult for users to manage and find them. Traditional file naming methods rely heavily on manual operation by users, which is not only time-consuming and labor-intensive but also prone to errors. Users may need to open each video file individually, view its content, and then manually name it, which is particularly inconvenient when dealing with large numbers of files. Furthermore, manual naming can lead to inconsistencies, further increasing the difficulty of file management.

[0003] Therefore, how to accurately name a large number of video files received at once is an urgent problem to be solved. Summary of the Invention

[0004] The main technical problem this invention addresses is how to accurately name a large number of video files received at once.

[0005] According to a first aspect, the present invention provides a file naming method based on big data processing, comprising: acquiring multiple video files to be named; processing the multiple video files to be named based on a file analysis model to determine a representative frame for each video file to be named; using a convolutional neural network model based on the representative frames of each video file to determine multiple alternative names for each video file to be named and the content similarity between different representative frames; determining a target file name for each video file to be named based on the multiple alternative names for each video file to be named and the content similarity between different representative frames; and naming each video file based on the target file name of each video file to be named.

[0006] In one possible implementation, determining the target file name for each video file to be named based on multiple alternative names for each video file to be named and the content similarity between different representative frames includes:

[0007] Construct a file naming graph structure, which includes multiple nodes and multiple edges between the nodes. Each node represents a video file. The node features of each node include a representative frame of each video file to be named and multiple alternative names for each video file to be named. The features of the edges between nodes represent the content similarity between different representative frames.

[0008] The file naming graph structure is processed using a graph convolutional network to determine the target file name for each video file to be named.

[0009] In one possible implementation, the file analysis model is a gated loop unit, the input of the file analysis model is the plurality of video files to be named, and the output of the file analysis model is a representative frame of each video file to be named.

[0010] In one possible implementation, the input to the graph convolutional network is the file naming graph structure, and the output of the graph convolutional network is the file target name for each video file to be named.

[0011] According to a second aspect, the present invention provides a file naming system based on big data processing, comprising:

[0012] The first acquisition module is used to acquire multiple video files to be named.

[0013] The representative frame determination module is used to process the multiple unnamed video files based on the file analysis model to determine the representative frame of each unnamed video file.

[0014] The alternative naming determination module is used to determine multiple alternative names for each video file to be named and the content similarity between different representative frames based on the representative frames of each video file to be named using a convolutional neural network model.

[0015] The target naming determination module is used to determine the target name of each video file to be named based on multiple alternative names for each video file to be named and the content similarity between different representative frames.

[0016] The naming module is used to name each video file based on the file target name of each video file to be named.

[0017] In one possible implementation, the target naming determination module is further configured to:

[0018] Construct a file naming graph structure, which includes multiple nodes and multiple edges between the nodes. Each node represents a video file. The node features of each node include a representative frame of each video file to be named and multiple alternative names for each video file to be named. The features of the edges between nodes represent the content similarity between different representative frames.

[0019] The file naming graph structure is processed using a graph convolutional network to determine the target file name for each video file to be named.

[0020] In one possible implementation, the file analysis model is a gated loop unit, the input of the file analysis model is the plurality of video files to be named, and the output of the file analysis model is a representative frame of each video file to be named.

[0021] In one possible implementation, the input to the graph convolutional network is the file naming graph structure, and the output of the graph convolutional network is the file target name for each video file to be named.

[0022] According to a third aspect, embodiments of the present invention provide an electronic device, including: a processor; a memory; and a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method as described above, the method including: acquiring a plurality of video files to be named; processing the plurality of video files to be named based on a file analysis model to determine a representative frame for each video file to be named; using a convolutional neural network model based on the representative frames of each video file to determine a plurality of alternative names for each video file to be named and content similarity between different representative frames; determining a target file name for each video file to be named based on the plurality of alternative names for each video file to be named and content similarity between different representative frames; and naming each video file based on the target file name for each video file to be named.

[0023] According to the fourth aspect, this embodiment provides a computer-readable storage medium storing a computer program thereon. When executed by a processor, the program implements the aforementioned file naming method based on big data processing. The method includes: acquiring multiple video files to be named; processing the multiple video files to be named based on a file analysis model to determine a representative frame for each video file to be named; using a convolutional neural network model based on the representative frames of each video file to determine multiple alternative names for each video file to be named and the content similarity between different representative frames; determining a target file name for each video file to be named based on the multiple alternative names for each video file to be named and the content similarity between different representative frames; and naming each video file based on the target file name for each video file to be named.

[0024] This invention provides a file naming method and system based on big data processing. The method includes: acquiring multiple video files to be named; processing the multiple video files to be named based on a file analysis model to determine representative frames for each video file; using a convolutional neural network model to determine multiple alternative names for each video file and the content similarity between different representative frames; determining the target name for each video file based on the multiple alternative names and the content similarity between different representative frames; and naming each video file based on the target name. This method can accurately name a large number of video files received at once. Attached Figure Description

[0025] Figure 1 This is a schematic diagram illustrating an application scenario of a file naming method based on big data processing, provided by an embodiment of the present invention.

[0026] Figure 2 A flowchart illustrating a file naming method based on big data processing provided in an embodiment of the present invention;

[0027] Figure 3 This is a flowchart illustrating a process for determining the probability value of a fuzzy test based on multiple data input by a user at different time points, as provided in an embodiment of the present invention.

[0028] Figure 4 A schematic diagram of a file naming system based on big data processing provided in an embodiment of the present invention;

[0029] Figure 5 A schematic diagram of an electronic device provided in an embodiment of the present invention;

[0030] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0031] The present invention will now be described in further detail with reference to specific embodiments and accompanying drawings. Similar elements in different embodiments are referred to by associated similar element reference numerals. In the following embodiments, many details are described to facilitate a better understanding of the invention. However, those skilled in the art will readily recognize that some features may be omitted in different situations, or may be replaced by other elements, materials, or methods. In some cases, certain operations related to the present invention are not shown or described in the specification. This is to avoid obscuring the core parts of the invention with excessive description. For those skilled in the art, detailed description of these related operations is not necessary; they can fully understand the related operations based on the description in the specification and general technical knowledge in the art.

[0032] Figure 1 This is a schematic diagram illustrating an application scenario of a file naming method based on big data processing, provided by an embodiment of the present invention. Figure 1 Application scenarios for file naming methods based on big data processing can include servers 11, networks 12, terminals 13, and storage devices 14.

[0033] In some embodiments, server 11 may be a single server or a group of servers. Server 11 can access information and / or data stored in terminal 13 or storage device 14 via network 12. In some embodiments, server 11 may be used to perform... Figure 2 The file naming method shown is based on big data processing.

[0034] Network 12 can facilitate the exchange of information and / or data. In some embodiments, network 12 can be any form of wired or wireless network, or any combination thereof.

[0035] Terminal 13 may refer to one or more terminal devices used by a user. In some embodiments, terminal 13 may include one or more combinations of mobile devices, tablet computers, laptop computers, etc.

[0036] Storage device 14 can store data and / or instructions, for example, storage device 14 can store data instructions based on file naming methods for big data processing.

[0037] In this embodiment of the invention, the following are provided: Figure 2 The above describes a file naming method based on big data processing, which includes steps S1 to S5:

[0038] Step S1: Obtain multiple video files to be named;

[0039] Multiple unnamed video files are multiple unnamed video files obtained from the video files received by the user. For example, if a user receives 10 video files through social media, the system will automatically retrieve these files.

[0040] Step S2: Based on the file analysis model, process the multiple unnamed video files to determine the representative frame of each unnamed video file;

[0041] The representative frames are extracted from each video file by processing it using a file analysis model, and these representative frames reflect the video content.

[0042] The file analysis model is a gated recurrent unit (GRU). The input to the file analysis model is the plurality of video files to be named, and the output is a representative frame of each video file to be named. The GRU is used to process sequence data and timing information. The GRU includes three components: a memory unit, an update gate, and a reset gate.

[0043] Video files consist of a series of consecutive frames, each representing an image at a specific point in time. These frames have temporal dependencies, meaning information from a previous frame may aid in the recognition of a subsequent frame. The frame order in a video file is crucial; different frame orders can lead to entirely different interpretations. For example, the start and end frames of an action have a clear temporal sequence. Gated recurrent units (GRUs) effectively capture the temporal dependencies between video frames, storing and transferring information through memory units to ensure the model can understand the dynamic changes in the video.

[0044] In some embodiments, the file analysis model includes a candidate frame extraction layer, a candidate frame correlation determination layer, a candidate frame analysis layer, and a representative frame determination layer. Each of these layers includes a gated loop unit structure. The input to the candidate frame extraction layer is the plurality of video files to be named, and the output is a plurality of candidate frames for each video file. The input to the candidate frame correlation determination layer is the plurality of candidate frames for each video file to be named, and the output is the correlation degree between each candidate frame and other candidate frames in the video file. The input to the candidate frame analysis layer is the plurality of candidate frames for each video file to be named, and the output is the character performance, background content richness, and color vividness of each candidate frame. The input to the representative frame determination layer is the character performance, background content richness, color vividness, and correlation degree between each candidate frame and other candidate frames in the video file to be named, and the output is a representative frame for each video file to be named.

[0045] By employing a candidate frame extraction layer, a candidate frame correlation determination layer, a candidate frame analysis layer, and a representative frame determination layer, video files are processed step by step to ensure that the representative frame of each video file best reflects the video content. This method not only improves the accuracy of representative frame selection but also significantly reduces the amount of data processed subsequently, thereby increasing overall processing efficiency.

[0046] Character performance score is used to evaluate the performance of a character in each candidate frame. For example, the more expressive a character is, the higher the performance score.

[0047] Background content richness is used to evaluate the richness of background content in each candidate frame. For example, the greater the number and variety of objects detected in the background, the greater the background content richness.

[0048] Color vividness is used to assess how vivid a color is.

[0049] Step S3: Based on the representative frames of each video file to be named, a convolutional neural network model is used to determine multiple alternative names for each video file to be named and the content similarity between different representative frames.

[0050] The input to the convolutional neural network model is a representative frame of each video file to be named, and the output of the convolutional neural network model is multiple alternative names for each video file to be named and the content similarity between different representative frames.

[0051] Each video file to be named has multiple alternative names generated by a convolutional neural network model based on the content of representative frames. For example, the alternative names for the video files include "Outdoor Activities," "Friends Gathering," and "Landscape Shooting."

[0052] Content similarity between different representative frames measures the degree of content similarity between representative frames of different video files.

[0053] Keyframes are keyframes extracted from video files that effectively reflect the video content. They typically contain the most typical and representative scene, summarizing the main content. Convolutional neural networks (CNNs) extract features from keyframes using convolutional and pooling layers. Fully connected layers map the extracted features to multiple categories, generating multiple candidate names. Based on the classification results, multiple possible filenames are generated. CNNs can extract features from each keyframe using convolutional and pooling layers. The content similarity between keyframes is evaluated by calculating the similarity of their feature vectors (e.g., Euclidean distance, cosine similarity).

[0054] Step S4: Determine the target name of each video file to be named based on multiple alternative names for each video file to be named and the content similarity between different representative frames;

[0055] In some embodiments, Figure 3 This invention provides a flowchart illustrating the process of determining the target file name for each video file to be named, comprising steps S21-S22:

[0056] Step S21: Construct a file naming graph structure. The file naming graph structure includes multiple nodes and multiple edges between the nodes. Each node represents a video file. The node features of each node include a representative frame of each video file to be named and multiple alternative names for each video file to be named. The features of the edges between nodes represent the content similarity between different representative frames.

[0057] The file naming graph structure is a graph data structure in which each node represents a video file. The features of each node include a representative frame and multiple alternative names. The features of the edges between nodes represent the content similarity between different representative frames.

[0058] Step S22: Process the file naming graph structure based on the graph convolutional network to determine the target file name for each video file to be named.

[0059] Graph Convolutional Network (GCN) is a deep learning model used to process graph-structured data. The input to the GCN is the file naming graph structure, and the output is the target name for each video file to be named.

[0060] By constructing a file naming graph structure, relationships between video files can be captured, ensuring consistency and logic in naming. Video files with high similarity typically have similar content, ensuring naming differentiation and avoiding naming confusion. The features of each node include a representative frame and multiple alternative names, providing comprehensive information that helps the model generate high-quality names. The features of the edges between nodes represent content similarity, providing information about the relationships between video files and helping the model make more reasonable naming decisions.

[0061] Graph convolutional networks (GCNNs) ensure that highly similar video files are not given the same name by capturing the relationships between nodes and aggregating neighbor information, thus avoiding naming conflicts. Through GCNN processing, the features of each node are richer and more accurate, better reflecting the content of different representative frames and highlighting the uniqueness of different video files.

[0062] By constructing a file naming graph structure, relationships between video files can be captured, providing rich contextual information and ensuring naming consistency and logic. Graph convolutional networks, by capturing relationships between nodes and aggregating neighbor information, can efficiently and accurately determine the target name for each video file to be named. This method not only avoids naming duplication but also highlights the content of different representative frames, improving naming accuracy and quality. Through such a graph structure and graph convolutional networks, a large number of video files can be effectively named, ensuring that each video file has a unique and accurate name.

[0063] Step S5: Name each video file based on the file target name of each video file to be named.

[0064] Once the target file name for each video file to be named is determined, then each video file is named.

[0065] Based on the same inventive concept Figure 4 This is a schematic diagram of a file naming system based on big data processing provided in an embodiment of the present invention. The file naming system based on big data processing includes:

[0066] The first acquisition module 41 is used to acquire multiple video files to be named;

[0067] The representative frame determination module 42 is used to process the multiple unnamed video files based on the file analysis model to determine the representative frame of each unnamed video file.

[0068] The alternative naming determination module 43 is used to determine multiple alternative names for each video file to be named and the content similarity between different representative frames based on the representative frames of each video file to be named using a convolutional neural network model.

[0069] The target naming determination module 44 is used to determine the target file name of each video file to be named based on multiple alternative names for each video file to be named and the content similarity between different representative frames.

[0070] The naming module 45 is used to name each video file based on the file target name of each video file to be named.

[0071] Based on the same inventive concept, embodiments of the present invention provide an electronic device, such as... Figure 5 As shown, it includes:

[0072] The system includes: a processor 51; a memory 52; and a computer program; wherein the computer program is stored in the memory 52 and configured to be executed by the processor 51 to implement the file naming method based on big data processing as described above, the method comprising: acquiring multiple video files to be named; processing the multiple video files to be named based on a file analysis model to determine representative frames of each video file to be named; using a convolutional neural network model to determine multiple alternative names for each video file to be named and the content similarity between different representative frames based on the representative frames of each video file to be named; determining the target name for each video file to be named based on the multiple alternative names for each video file to be named and the content similarity between different representative frames; and naming each video file based on the target name for each video file to be named.

[0073] Based on the same inventive concept, this embodiment provides a computer-readable storage medium storing a computer program. When executed by processor 51, the program implements the aforementioned file naming method based on big data processing. The method includes: acquiring multiple video files to be named; processing the multiple video files to be named based on a file analysis model to determine representative frames for each video file; using a convolutional neural network model to determine multiple alternative names for each video file and content similarity between different representative frames based on the representative frames of each video file; determining the target file name for each video file based on the multiple alternative names and content similarity between different representative frames; and naming each video file based on the target file name.

[0074] The file naming method based on big data processing provided in this application can be applied to terminal devices (such as mobile phones), tablets, laptops, ultra-mobile personal computers (UMPCs), handheld computers, netbooks, personal digital assistants (PDAs), wearable devices (such as smartwatches, smart glasses, or smart helmets), augmented reality (AR) / virtual reality (VR) devices, smart home devices, in-vehicle computers, and other electronic devices. This application does not impose any limitations on this.

[0075] Taking mobile phone 100 as an example of the aforementioned electronic devices, Figure 6 A structural schematic diagram of mobile phone 100 is shown.

[0076] like Figure 6As shown, the mobile phone 100 may include a processing module 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, a headphone jack 170D, a sensor module 180, buttons 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc.

[0077] The processing module 110 may include one or more processing units, such as an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). These different processing units may be independent devices or integrated into one or more processors.

[0078] Processing module 110 can be used to: acquire multiple video files to be named; process the multiple video files to be named based on a file analysis model to determine the representative frame of each video file to be named; use a convolutional neural network model to determine multiple alternative names for each video file to be named and the content similarity between different representative frames based on the representative frames of each video file to be named; determine the target name for each video file to be named based on the multiple alternative names for each video file to be named and the content similarity between different representative frames; and name each video file based on the target name for each video file to be named.

[0079] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0080] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0081] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0082] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0083] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A file naming method based on big data processing, characterized in that, include: Get multiple video files to be named; The file analysis model is used to process the multiple unnamed video files to determine the representative frame of each unnamed video file. The file analysis model is a gated loop unit. The input of the file analysis model is the multiple unnamed video files, and the output of the file analysis model is the representative frame of each unnamed video file. The file analysis model includes a candidate frame extraction layer, a candidate frame correlation determination layer, a candidate frame analysis layer, and a representative frame determination layer. Each of these layers includes a gated loop unit structure. The input of the candidate frame extraction layer is the multiple unnamed video files, and the output of the candidate frame extraction layer is the representative frame of each unnamed video file. The candidate frame correlation determination layer takes multiple candidate frames from each video file as input and outputs the correlation between each candidate frame and other candidate frames in the video file. The candidate frame analysis layer takes multiple candidate frames from each video file as input and outputs the character performance, background content richness, and color vividness of each candidate frame. The representative frame determination layer takes the character performance, background content richness, color vividness, and correlation between each candidate frame and other candidate frames in the video file as input and outputs the representative frame of each video file. Based on the representative frames of each video file to be named, a convolutional neural network model is used to determine multiple alternative names for each video file to be named and the content similarity between different representative frames. The target file name for each video file to be named is determined based on multiple alternative names and the content similarity between different representative frames. This determination includes: Construct a file naming graph structure, which includes multiple nodes and multiple edges between the nodes. Each node represents a video file. The node features of each node include a representative frame of each video file to be named and multiple alternative names for each video file to be named. The features of the edges between nodes represent the content similarity between different representative frames. The file naming graph structure is processed using a graph convolutional network to determine the target file name for each video file to be named. Each video file is named based on its target file name.

2. The file naming method based on big data processing as described in claim 1, characterized in that, The input to the graph convolutional network is the file naming graph structure, and the output of the graph convolutional network is the file target name for each video file to be named.

3. A file naming system based on big data processing, characterized in that, include: The first acquisition module is used to acquire multiple video files to be named. The representative frame determination module is used to process the plurality of unnamed video files based on a file analysis model to determine the representative frame of each unnamed video file. The file analysis model is a gated loop unit. The input of the file analysis model is the plurality of unnamed video files, and the output of the file analysis model is the representative frame of each unnamed video file. The file analysis model includes a candidate frame extraction layer, a candidate frame correlation determination layer, a candidate frame analysis layer, and a representative frame determination layer. Each of these layers includes a gated loop unit structure. The input of the candidate frame extraction layer is the plurality of unnamed video files, and the output of the candidate frame extraction layer is... For each video file to be named, there are multiple candidate frames. The input to the candidate frame correlation determination layer is the multiple candidate frames of each video file to be named. The output of the candidate frame correlation determination layer is the correlation degree between each candidate frame and other candidate frames in the video file to be named. The input to the candidate frame analysis layer is the multiple candidate frames of each video file to be named. The output of the candidate frame analysis layer is the character performance, background content richness, and color vividness of each candidate frame. The input to the representative frame determination layer is the character performance, background content richness, color vividness, and correlation degree between each candidate frame and other candidate frames in the video file to be named. The output of the representative frame determination layer is the representative frame of each video file to be named. The alternative naming determination module is used to determine multiple alternative names for each video file to be named and the content similarity between different representative frames based on the representative frames of each video file to be named using a convolutional neural network model. The target naming determination module is used to determine the target name of each video file to be named based on multiple alternative names for each video file to be named and the content similarity between different representative frames. The target naming determination module is also used for: Construct a file naming graph structure, which includes multiple nodes and multiple edges between the nodes. Each node represents a video file. The node features of each node include a representative frame of each video file to be named and multiple alternative names for each video file to be named. The features of the edges between nodes represent the content similarity between different representative frames. The file naming graph structure is processed using a graph convolutional network to determine the target file name for each video file to be named. The naming module is used to name each video file based on the file target name of each video file to be named.

4. The file naming system based on big data processing as described in claim 3, characterized in that, The input to the graph convolutional network is the file naming graph structure, and the output of the graph convolutional network is the file target name for each video file to be named.

5. An electronic device, characterized in that, include: processor; Memory; And a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the file naming method based on big data processing as described in any one of claims 1 to 2.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the file naming method based on big data processing as described in any one of claims 1 to 2.

Images