File naming method and apparatus
By automatically selecting file naming patterns on electronic devices and generating filenames using server-side or local models, the inefficiency caused by users manually selecting models is solved, achieving efficient and convenient file naming processing.
Patent Information
- Application Number
- CN202510939457.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-08
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2045-07-08
AI Technical Summary
In existing technologies, users need to manually select an algorithm model to name files, resulting in low efficiency in file naming.
The file naming pattern is determined by electronic devices, and file names are automatically generated using server-side or local models under different patterns, reducing the number of manual selection steps for users.
It improves the efficiency and ease of use of file naming, allowing users to automatically adapt to network quality and user preferences without worrying about model selection, generating filenames that meet their needs.
Smart Images

Figure CN120723732B_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of computer technology, specifically relating to a file naming method and apparatus. Background Technology
[0002] With the acceleration of digitalization, the explosive emergence of multimodal data files has posed a severe challenge to traditional file management methods that rely on time-series naming rules (such as "20230901_003.txt"). This has created an urgent need for intelligent file naming technology with multimodal data parsing capabilities.
[0003] Intelligent naming is a technique that uses algorithmic models to independently process different types of files to generate filenames, relying on the text analysis capabilities of these models. In related technologies, the algorithmic models used for file naming are deployed on the client or server, requiring users to manually select the appropriate model, resulting in relatively low efficiency in file naming processing. Summary of the Invention
[0004] The purpose of this application is to provide a file naming method and apparatus that can solve the problem in related technologies where users need to manually select the algorithm model used to perform file naming, resulting in low efficiency in file naming processing.
[0005] In a first aspect, embodiments of this application provide a file naming method, executed by an electronic device, the method comprising:
[0006] Determine the file naming pattern;
[0007] When the file naming mode is the first mode, the naming feature information of the first file is input to the first model located on the server, the first name of the first file output by the first model is received, and the name of the first file is named the first name.
[0008] When the file naming mode is the second mode, the naming feature information of the first file is input to the second model located in the electronic device, the second name of the first file output by the second model is received, and the name of the first file is named the second name.
[0009] Secondly, embodiments of this application provide a file naming device applied to an electronic device, the device comprising:
[0010] The first determining module is used to determine the file naming pattern;
[0011] The first processing module is configured to, when the file naming mode is the first mode, input the naming feature information of the first file to the first model located on the server, receive the first name of the first file output by the first model, and name the first file as the first name; when the file naming mode is the second mode, input the naming feature information of the first file to the second model located on the electronic device, receive the second name of the first file output by the second model, and name the first file as the second name.
[0012] Thirdly, embodiments of this application provide an electronic device including a processor and a memory, wherein the memory stores programs or instructions executable on the processor, and the programs or instructions, when executed by the processor, implement the steps of the method described in the first aspect.
[0013] Fourthly, embodiments of this application provide a readable storage medium on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect.
[0014] Fifthly, embodiments of this application provide a chip, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the method as described in the first aspect.
[0015] In a sixth aspect, embodiments of this application provide a computer program product stored in a storage medium, which is executed by at least one processor to implement the method described in the first aspect.
[0016] In this embodiment, the electronic device determines the file naming mode. When the file naming mode is a first mode, the naming feature information of the first file is input to a first model located on the server, and the first name of the first file output by the first model is received, and the first file is named using the first name. When the file naming mode is a second mode, the naming feature information of the first file is input to a second model located on the electronic device, and the second name of the first file output by the second model is received, and the first file is named using the second name. This embodiment eliminates the need for users to manually select a model, reducing user operation steps. Users only need to focus on the file content and do not need to worry about model selection, thus improving ease of use and file naming processing efficiency. Attached Figure Description
[0017] Figure 1 This is one of the flowcharts of the file naming method in the embodiments of this application;
[0018] Figure 2This is one of the schematic diagrams of the file naming settings interface in the embodiments of this application;
[0019] Figure 3 This is the second schematic diagram of the file naming settings interface in the embodiments of this application;
[0020] Figure 4 This is a schematic diagram of the file generation interface in an embodiment of this application;
[0021] Figure 5 This is one of the schematic diagrams of the file naming interface in the embodiments of this application;
[0022] Figure 6 This is the second schematic diagram of the file naming interface in the embodiments of this application;
[0023] Figure 7 This is the second flowchart of the file naming method in the embodiments of this application;
[0024] Figure 8 This is a structural block diagram of the file naming device in an embodiment of this application;
[0025] Figure 9 This is a structural block diagram of the electronic device in the embodiments of this application;
[0026] Figure 10 This is a schematic diagram of the hardware structure of the electronic device in the embodiments of this application. Detailed Implementation
[0027] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.
[0028] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.
[0029] The file naming method provided in this application will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.
[0030] See Figure 1 This application provides a file naming method for use in electronic devices, comprising the following steps:
[0031] Step 101: Determine the file naming pattern.
[0032] Optionally, the file naming pattern can be determined based on at least one of the following: network quality of the electronic device, user preferences, file content type, etc. User preferences include, but are not limited to, at least one of the following: privacy preferences, naming format preferences, file type preferences, naming complexity preferences, naming frequency preferences, and naming style preferences.
[0033] Step 102: When the file naming mode is the first mode, input the naming feature information of the first file to the first model located on the server, receive the first name of the first file output by the first model, and name the first file as the first name.
[0034] When the file naming mode is the second mode, the naming feature information of the first file is input to the second model located in the electronic device, the second name of the first file output by the second model is received, and the name of the first file is named the second name.
[0035] It should be noted that the first model can be understood as an online model, and the second model can be understood as an offline model. Due to the limitation of computing resources, the naming quality of the offline model is far lower than that of the online model, while the online model involves data transmission to the server, thus posing a risk of privacy leakage.
[0036] The types of the first file include, but are not limited to: text files, video files, audio files, images, etc.
[0037] In the above embodiments, the electronic device determines the file naming mode. When the file naming mode is the first mode, the naming feature information of the first file is input to the first model located on the server, the first name of the first file output by the first model is received, and the first file is named using the first name. When the file naming mode is the second mode, the naming feature information of the first file is input to the second model located on the electronic device, the second name of the first file output by the second model is received, and the first file is named using the second name. This embodiment eliminates the need for the user to manually select a model, reducing user operation steps. Users only need to focus on the file content and do not need to worry about model selection, thus improving ease of use and file naming processing efficiency.
[0038] In practice, the intelligent naming service provides a client SDK that encapsulates multimodal file content analysis and naming logic, offering a unified interface for application software to call naming capabilities. Its core function is to semantically understand the content of the file to be named by calling a local or cloud-based second model, generating a name that matches the file content.
[0039] It's worth noting that various applications on electronic devices that require naming, such as documents, notes, notifications, emails, recordings, and scanned documents, can all use the intelligent naming service to rename files. The intelligent naming service supports multimodal input, such as text, voice, images, and videos, and can adapt to the naming needs of different file types.
[0040] In some application scenarios, applications that access the intelligent naming service need to add "intelligent naming" and "intelligent naming service" function entries in the application settings.
[0041] For example, the smart naming feature is disabled by default, and users can customize it based on factors such as... Figure 2 The "Smart Naming" function entry in the settings interface shows how to enable or disable the smart naming function; based on Figure 2 The "Intelligent Naming Service" function entry shown below leads to... Figure 3 The selection interface shown; the intelligent naming service is online by default, and users can choose to use it based on... Figure 3 In the selection interface shown, select online file naming (i.e. Figure 3 The "online" option) or offline file naming (i.e. Figure 3 The "Offline" option in the settings.
[0042] In some embodiments of this application, determining the file naming pattern includes:
[0043] If the generation of the first file is completed, a file naming pattern is determined; or, a first input from the user regarding the first file is received; in response to the first input, a file naming pattern is determined.
[0044] For example, such as Figure 4 and Figure 5 As shown, taking a recorder as an example, in response to the recording completion event, the intelligent naming service is automatically invoked to name the recording file, and the intelligent naming result waiting interface is displayed, such as... Figure 5 The text displays "Intelligent naming in progress...". This example enables the automatic triggering of the intelligent file naming function.
[0045] For example, such as Figure 6Taking an audio recording as an example, when a user long-presses on a previously generated "New Recording 3," a function selection window (a) is displayed in response to the long-press input. This window includes a "Smart Naming" control and may also include the following controls: "Delete," "Rename," and "Share." In response to user input on the "Smart Naming" control, the smart naming service is automatically invoked, and the following is displayed: Figure 5 The interface shown is for waiting for the intelligent naming result. This example allows users to manually trigger intelligent file naming for already generated audio files.
[0046] In the above embodiments, users are provided with two ways to trigger the intelligent naming function: manually and automatically. This allows users to quickly access the file naming function and improve file management efficiency.
[0047] In some embodiments of this application, the method for determining a file naming pattern includes: determining the file naming pattern based on the grid quality of the electronic device.
[0048] Optionally, if the network quality meets a first network condition, the file naming pattern is determined to be the first pattern; if the network quality meets a second network condition, the file naming pattern is determined to be the second pattern; the first network condition is superior to the second network condition. In the first pattern, the filename is generated by a first model located on the server; in the second pattern, the filename is generated by a second model located in the electronic device.
[0049] In practical implementation, the file naming pattern can be determined based on the network quality of the electronic device. This can include: sending a Transmission Control Protocol (TCP) idle probe packet every 300ms via port 61000, recording the precise sending timestamp of the probe packet and the arrival timestamp of the received ACK, and using the difference between the sending timestamp and the arrival timestamp as the round-trip time (RTT); if the RTT is less than a preset number of times (e.g., 3 times) and the preset duration (e.g., 200ms), the file name generated by the first model will be used; if the RTT is greater than or equal to the preset duration (e.g., 200ms) and the file name generated by the second model will be used.
[0050] It should be noted that the above method of network quality detection based on RTT is merely an example and does not limit the acquisition of network quality through other methods. For example, network quality can also be judged by one or more of other factors such as network connectivity status, data transmission rate, and packet loss rate.
[0051] In this implementation, the electronic device automatically selects the appropriate model for file naming based on network quality and conditions. When network quality is good, it uses the first model to generate the filename for the first file, leveraging cloud resources and high-performance computing capabilities to ensure efficient file naming. When network quality is poor, it uses the second model to generate the filename for the first file, reducing the reliance on network resources and ensuring the timeliness and reliability of file naming, avoiding file management chaos caused by network issues. This dynamically balances the computing resources of online and offline models, eliminating latency and jitter caused by network fluctuations, ensuring smooth file naming, and improving the efficiency of civilized file naming. Furthermore, the dynamic switching between the first and second models based on network quality eliminates the need for manual selection by the user, reducing user steps. Users only need to focus on the file content, without needing to worry about network status or model selection, thus improving ease of use.
[0052] In some embodiments of this application, the file naming pattern is determined based on the network quality of the electronic device, including:
[0053] When the smart naming function is enabled and the first mode is selected for smart file naming, the electronic device detects the network quality and switches between the first and second modes based on the network quality. When the smart naming function is enabled and the second mode is selected for smart file naming, the electronic device does not need to detect the network quality and always uses the second model to generate file names.
[0054] In the above embodiments, based on privacy protection needs, users may always choose to generate filenames using offline mode. When users choose to generate filenames using offline mode, there is no need to consider the network quality of the electronic device. When users choose to generate filenames using online mode, switching between the first mode and the second mode based on network quality can avoid naming delays caused by network quality fluctuations and improve file naming efficiency.
[0055] In some embodiments of this application, the method for determining a file naming pattern includes: determining a file naming pattern based on user preferences.
[0056] User preferences can be collected through methods such as questionnaires, user behavior analysis, or device usage records. User preferences include, but are not limited to, at least one of the following: privacy preferences, naming format preferences, file type preferences, naming complexity preferences, naming frequency preferences, and naming style preferences.
[0057] For example, privacy preferences can be inferred through user behavior analysis. Frequent file name changes or deletions by a user may indicate privacy concerns; similarly, setting "encrypted" or "read-only" permissions for certain folders or file types may suggest privacy sensitivity. Based on these privacy preferences, determining file naming patterns involves: for non-sensitive files, using the first pattern (server-side model to generate more complex names) when the user is sensitive to privacy; and for sensitive files, using the second pattern (local model to generate simpler names) to avoid data leakage risks.
[0058] For example, if it is determined that the user's file naming quality requirements are high based on at least one of the following: naming format preference, file type preference, naming complexity preference, naming frequency preference, and naming style preference, then the file naming mode is determined to be the first mode, that is, the server-side first mode is used to generate the file name for the first file.
[0059] In this implementation, selecting a file naming pattern based on user preferences ensures that filenames that meet user needs are generated, reducing manual input.
[0060] In some embodiments of this application, the method for determining a file naming pattern includes: determining a file naming pattern based on user preferences and file content type.
[0061] For example, if a user repeatedly uploads a file named "Financial Statements.xlsx" without changing the filename, it is determined that the user is not sensitive to privacy. If the first file is identified as containing sensitive information (such as financial data, ID card information, bank statements, medical information, etc.), based on the user's historical behavioral preferences (the behavior of not changing the filename of the financial statements), it is inferred that the user may want to simplify the naming process but does not want data to be uploaded. Therefore, the file naming pattern is determined to be the second pattern, that is, the local second model is selected to generate the filename for the first file, avoiding the call to the server-side model and preventing the file content from being analyzed or stored.
[0062] In this implementation, selecting a file naming pattern based on user preferences and file type ensures that filenames that meet user needs are generated, reduces manual input, and avoids the leakage of sensitive information.
[0063] It should be noted that the methods for determining file naming patterns listed above are only some optional implementation methods, and the embodiments of this application are not limited thereto. For example, in specific implementations, file naming patterns can also be determined based on other information, such as business scenarios and uses, language preferences, user geographical location, etc.
[0064] In some embodiments of this application, the above file naming method further includes: obtaining text feature information corresponding to the first file; obtaining a keyword weight vector of the first file based on the text feature information, and using the keyword weight vector as the naming feature information.
[0065] For example, suppose the textual feature information in the first file includes the following: "The application of artificial intelligence in medical imaging is showing a rapid growth trend (see...)" Figure 1 , Figure 1 The description includes: CT scan image showing lung nodules; OCR text: Patient ID: 2023-IMG-017]. The main technological breakthroughs are concentrated in… (followed by the main text). Based on text feature information, the extracted keyword weight vector is: “[AI Medical: 0.91, CT Image: 0.87, Deep Learning: 0.85, 2023: 0.82, Segmentation Algorithm: 0.79]”, where 0.19, 0.87, 0.85, 0.82, and 0.79 are the weight coefficients for the keywords “AI Medical”, “CT Image”, “Deep Learning”, and “Segmentation Algorithm”, respectively.
[0066] In this embodiment, the multimodal files to be named are uniformly converted into text feature information, and the text feature information is converted into a keyword weight vector in a unified format. The files to be named are named based on the keyword weight vector. Compared with the prior art, which uses independent processing procedures for different types of files and does not have a unified feature expression system, this embodiment can improve the naming efficiency and ensure the accuracy of naming by expressing the features of the same different types of files.
[0067] In some embodiments of this application, the input information of the first model or the second model includes: a keyword weight vector and constraints, the constraints including:
[0068] Forced inclusion of feature words: For example, force the inclusion of the first two high-weight feature words, with low-weight words as optional supplementary information;
[0069] File name length requirement: File names must be ≤ 30 Chinese characters or 60 English characters;
[0070] Formatting requirements: Can be customized according to business needs, such as <Year>, <Technology Field>, <Core Methods>.
[0071] In the above embodiments, by inputting constraint information into the first model or the second model, it can be ensured that the file name conforms to a specific specification, which facilitates the classification and retrieval of files.
[0072] In some embodiments of this application, the above file naming method further includes:
[0073] Multiple candidate filenames are generated using either the first or second model;
[0074] If the currently generated filename is found to be duplicated with a previous filename, the process will automatically continue to the next filename.
[0075] Use the filename that passes the verification as the first or second name.
[0076] The above embodiments, by verifying filenames, can avoid file overwriting or file confusion, ensure the uniqueness of file names, and prevent users from having to manually modify filenames due to duplicate filenames.
[0077] In some embodiments of this application, obtaining the keyword weight vector of the first document based on the text feature information includes:
[0078] The text feature information is segmented and stop words are filtered to obtain multiple keywords included in the text feature information;
[0079] Determine the frequency of occurrence of each keyword in the text feature information;
[0080] Determine the inverse document frequency of each keyword in the corpus;
[0081] The weight value corresponding to each keyword is determined based on the product of the occurrence frequency and the inverse document frequency;
[0082] After removing keywords whose weight values are lower than a preset threshold, the remaining keywords and their corresponding weight values constitute the keyword weight vector of the first document.
[0083] For example, suppose the text feature information S of the first document includes the following content: "2023 product strategy focuses on AI medical imaging, and breakthrough progress has been made in CT image segmentation algorithm based on deep learning". Based on this text feature information S, the step of obtaining the keyword weight vector of the first document may include:
[0084] Step 1: Perform word segmentation on the text feature information.
[0085] Using the jieba algorithm, the text feature information S is divided into a list of words. For example, the word segmentation result of the text feature information S = "2023 products will focus on AI medical imaging" is: ["2023", "year", "of", "product", "strategy", "will", "focus", "in", "AI", "medical", "imaging"].
[0086] Step 2: Filter the word segmentation results for stop words.
[0087] Initialize a general stop word list (such as "de", "shi", "yu", etc.), and perform stop word filtering on the word segmentation result obtained in step 1. After filtering, the result is: ["2023", "year", "product", "strategy", "focus", "AI", "medical", "imaging"].
[0088] Step 3: Determine the occurrence frequency of each of the keywords in the text feature information.
[0089] The occurrence frequency may also be referred to as the term frequency factor TF, which represents the occurrence frequency of the keyword t in the text feature information S, that is, the ratio of the number of occurrences to the total number of words. The TF of the keyword t can be calculated by the following formula (1):
[0090]
[0091] Where N(t) is the number of occurrences of the keyword t in the text feature information S, and M(S) is the total number of words in the text feature information S. For example, "AI" occurs 1 time, and the total number of words in the text is 8, then TF("AI") = 0.125.
[0092] Step 4: Determine the inverse document frequency of each keyword in the corpus.
[0093] Where the inverse document frequency IDF reflects the scarcity of the keyword t in the corpus, and a word with higher scarcity indicates that the word can better represent the features of the text feature information S. The calculation of IDF depends on pre-trained corpus information. The corpus may adopt currently common corpora, such as the Wikipedia dataset, and the calculation formula (2) of IDF is as follows:
[0094]
[0095] Where Z is the total number of documents in the corpus, and R(t) is the number of documents containing the keyword t.
[0096] Step 5: Calculate the weight coefficient corresponding to each keyword.
[0097] For example, the weight coefficient of the keyword t may be the product of TF and IDF, as shown in the following formula (3):
[0098] TF-IDF(t) = TF(t) × IDF(t) (3)
[0099] Where TF-IDF(t) is the weight coefficient of the keyword t, TF(t) is the term frequency factor of the keyword t, and IDF(t) is the inverse document frequency of the keyword t.
[0100] Step 6: Perform normalization processing on the weights, filter out keywords with weights lower than a preset threshold (such as 0.5), and generate a keyword weight vector.
[0101] For example, the input text feature information S = "2023 product strategy focuses on AI medical imaging, and breakthrough progress has been made in CT image segmentation algorithm based on deep learning...", the converted output keyword weight vector is: "[AI medical: 0.91, CT image: 0.87, deep learning: 0.85, 2023: 0.82, segmentation algorithm: 0.79]".
[0102] In the above embodiments, word segmentation, stop word filtering, and weight calculation ensure that the extracted keywords accurately reflect the core content of the first document. Filtering keywords based on weight coefficients and preset thresholds removes redundant information, retaining only keywords strongly related to the first document, thus ensuring the stability and reliability of keyword extraction. This embodiment transforms files (such as text files, images, audio, and video) into machine-parseable structured semantic vectors through structured feature extraction. This allows large models to focus resources on parsing core semantic features without processing the original file data, improving the efficiency of file naming processing.
[0103] In some embodiments of this application, obtaining the text feature information corresponding to the first file includes:
[0104] The file type of the first file is determined based on the file type identification information of the first file; wherein the file type identification information includes at least one of the following: file format identifier (such as PDF, DOCX, etc.), hexadecimal feature byte sequence (also known as magic number) in the file header, the starting position of the hexadecimal feature byte sequence in the file header (i.e., the starting offset of the magic number), and a list of file extensions.
[0105] Based on the file type, determine the text feature extraction method;
[0106] Based on the text feature extraction method, the text feature information corresponding to the first file is determined.
[0107] In practice, the first file can be converted into a binary representation, and the first 32 bytes can be converted into a hexadecimal string (e.g., 25504446...). Based on the hexadecimal string, the hexadecimal feature byte sequence (also known as the magic number) in the file header and the starting position of the feature byte sequence in the file header (i.e., the starting offset of the magic number) can be determined. The starting offset of the magic number represents the starting position of the hexadecimal feature byte sequence in the binary file representation (in bytes), and the special value -1 indicates no feature code.
[0108] It's important to note that magic numbers are special byte sequences stored in the header of binary files to identify the file format, typically represented in hexadecimal. For example, the magic number for a PDF file is 25504446, and for a PNG file it's 89504E47. Plain text files like TXT files don't have fixed magic numbers and require their file extension for identification. When offset = -1, the file extension is used for identification; for example, TXT files require their file extension to help identify the file format.
[0109] In specific implementation, determining the file type of the first file based on its file type identification information includes performing the following identification operations according to the identification rules for each file type:
[0110] Anomaly detection: If the offset of the current rule exceeds the file data length, it is determined that "the file is corrupted";
[0111] Feature matching: Checks whether the specified offset position contains the corresponding hexadecimal feature byte sequence. If the match is successful, the corresponding file format is returned.
[0112] Extension matching: For types with offset = -1 (such as TXT), check if the file extension is in the extension list.
[0113] For example, the rules for identifying file types are as follows:
[0114] (1) For PDF format files, start matching from byte 0 to the magic number "25504446";
[0115] (2) For DOCX format files: start matching from byte 0 to the magic number "504B0304";
[0116] (3) For TXT files, since there is no fixed magic number (offset=-1), the file type is identified only by checking whether the extension is ".txt".
[0117] If none of the above rules are matched, an indication message "This file format is not supported" will be returned; if a match is successful, the corresponding file format identifier will be returned.
[0118] In specific implementation, the text feature extraction method is determined based on the file type of the first file; based on the text feature extraction method, the text feature information corresponding to the first file is determined, including:
[0119] For text files (TXT): Parse the file text content, automatically filter out formatting symbols and garbled data, and output the text feature information S as the complete original text;
[0120] For audio files (MP3, WAV): the audio stream is parsed and silent segments and background noise are automatically filtered out. The text is then transcribed using an ASR model, and the text feature information S is the transcribed content.
[0121] For video (MP4) files: extract keyframe images, use the edge model to describe the keyframe images, extract audio information and transcribe it into text using the ASR model, and merge the two text segments as text feature information S;
[0122] For image files (JPEG, PNG): The edge model is used to describe the image and preserve its visual features, and OCR is used to recognize the text information in the image. The two text segments are merged as text feature information S.
[0123] For comprehensive (PDF, DOCX) files: For documents with both text and images, firstly, the main text content is parsed, and headers, footers, and annotations are automatically filtered; secondly, embedded images are extracted from the document, text in the images is recognized using OCR, and visual descriptive text is generated using an edge-side model; finally, the image information is inserted into the main text in its original position to generate complete text feature information S. An example is shown below: "The application of artificial intelligence in medical imaging shows a rapid growth trend (see...)" Figure 1 ), Figure 1 The description includes: CT scan images showing lung nodules; OCR text: PatientID:2023-IMG-017. The main technological breakthroughs are concentrated in… (followed by the main text).
[0124] In the above embodiments, multimodal feature compression of files to be named can be achieved, and a unified feature representation system can be established.
[0125] In some embodiments of this application, when the file naming pattern is the second pattern, after naming the first file with the second name, the method further includes:
[0126] When the file naming mode is switched from the second mode to the first mode, the naming feature information of the first file is input into the first model, and the first name of the first file output by the first model is received;
[0127] The second model is quantitatively evaluated based on the first name and the second name to obtain the quantitative evaluation results.
[0128] For example, when the user accesses the system via, such as Figure 2When the "Intelligent Naming Service" function entry point is selected in online mode (i.e., the first mode) for file naming, the iterative update process of the second model can include: when the electronic device detects poor network quality, it switches from the first mode to the second mode, uses the second model to name the first file, and the second model returns the file naming result to the user immediately, while caching the key-value pair {naming feature information: second name} in local memory; after the network quality recovers, the electronic device switches from the second mode back to the first mode, and the system automatically triggers the online model reprocessing process, using the first model to generate the first name for the first file as the standard answer set, obtaining the dataset {naming feature information, second name, first name}. Here, the first name and second name in the dataset can be used for quantitative evaluation of the second model, and the naming feature information and the first name can be used for iterative training of the second model.
[0129] In some embodiments of this application, the second model is quantitatively evaluated based on the first name and the second name to obtain a quantitative evaluation result, including:
[0130] Obtain the first word segmentation result set corresponding to the first name and the second word segmentation result set corresponding to the second name;
[0131] Based on the first word segmentation result set and the second word segmentation result set, determine the vocabulary coverage of the second model execution file naming;
[0132] Based on the first word segmentation result set and the second word segmentation result set, determine the redundant word penalty value for the naming of the second model execution file;
[0133] The quantitative evaluation result of the second model is determined based on the difference between the vocabulary coverage rate and the redundant word penalty value.
[0134] Optionally, the quantitative evaluation result of the second model can be calculated using formula (4) based on the difference between the vocabulary coverage rate and the redundant word penalty value:
[0135]
[0136] Among them, W onlinee W represents the set of the first word segmentation results. offline This represents the set of results from the second word segmentation. Indicates vocabulary coverage. This represents the redundant word penalty value. The difference between the vocabulary coverage rate and the redundant word penalty value is the naming ability evaluation result of the second model. If the score is less than 0, it is recorded as 0 points. The 0.2 here is a scalar value and can be adjusted according to actual needs.
[0137] In the above embodiments, if the vocabulary coverage is low, it indicates that the second model has failed to accurately capture key information; if the redundant word penalty value is high, it indicates that the file name generated by the model is not concise enough; the accuracy and conciseness of the file name generated by the model can be quantitatively evaluated through vocabulary coverage and redundant word penalty value.
[0138] In some embodiments of this application, the above file naming method further includes:
[0139] The dataset consisting of the naming feature information of the first file and the first name is used as training samples;
[0140] If the number of training samples is greater than or equal to a preset threshold and / or the quantitative evaluation result meets a preset condition, the second model is iteratively trained based on the training samples to obtain a third model.
[0141] The second model in the electronic device is replaced with the third model.
[0142] For example, a set of data {naming feature information, first name} whose quantitative evaluation score is lower than a first preset score (e.g., 80 points) is used as a valid training sample. After accumulating 200 valid training samples, iterative training of the second model is initiated to achieve daily updates of the second model. When the naming quality of a consecutive preset number (e.g., 10) first files is lower than the second preset score, background optimization is immediately triggered to achieve an emergency update of the second model. The values 200, 10, 80, and 50 here are just examples and are not limited to these values.
[0143] The following example uses determining a file naming pattern based on network quality as an example, through appendix... Figure 7 An exemplary description of a file naming method provided in an embodiment of this application is given below.
[0144] See Figure 7 The file naming method provided in this application may include the following steps:
[0145] Step 701: Enable smart naming.
[0146] For example, the smart naming feature is disabled by default, and users can customize it based on factors such as... Figure 2 The "Smart Naming" function can be accessed in the settings interface to enable or disable the smart naming function.
[0147] Step 702: Identify the file type of the first file.
[0148] The file type of the first file is determined based on at least one of the following identification information:
[0149] File format identifier;
[0150] The hexadecimal signature byte sequence (i.e., magic number) in the file header;
[0151] The starting position of the hexadecimal feature byte sequence in the file header (i.e., the starting offset of the magic number);
[0152] List of file extensions.
[0153] Step 703: Obtain the keyword weight vector of the first file.
[0154] Step 703 includes: obtaining text feature information corresponding to the first file; performing word segmentation on the text feature information and filtering stop words to obtain multiple keywords included in the text feature information; determining the frequency of occurrence of each keyword in the text feature information; determining the inverse document frequency of each keyword in the corpus; determining the weight value corresponding to each keyword based on the product of the frequency of occurrence and the inverse document frequency; removing keywords with weight values lower than a preset threshold, and constructing the keyword weight vector of the first file with the remaining keywords and the corresponding weight values of the keywords.
[0155] Step 704: Select the intelligent naming service mode.
[0156] For example, users can base on Figure 2 The "Intelligent Naming Service" function entry shown below leads to... Figure 3 The selection interface shown; the intelligent naming service function defaults to obtaining filenames online, and users can choose to use it based on... Figure 3 In the selection interface shown, select online file naming (i.e. Figure 3 The "online" option function) or offline file naming (i.e. Figure 3 The "Offline" option in the settings.
[0157] If you choose online file naming, proceed to step 705; if you choose offline file naming, proceed to step 708.
[0158] Step 705: Network quality assessment.
[0159] If the RTT is less than 200ms for 3 consecutive times, proceed to step 706; if the RTT is greater than 200ms for 3 consecutive times, proceed to step 707.
[0160] Step 706: Generate filenames using the first model.
[0161] In this step, the keyword weight vector of the first file is input into the first model, the first name output by the first mode is received, and the name of the first file is named after the first name.
[0162] Step 707: Generate filenames using the second model.
[0163] In this step, the keyword weight vector of the first file is input into the second model, the second name output by the second model is received, and the name of the first file is renamed as the second name.
[0164] Step 708: Generate a filename using the second model, and continue to step 709.
[0165] In this step, the keyword weight vector of the first file is input into the second model, the second name output by the second model is received, and the name of the first file is renamed as the second name.
[0166] Step 709: Evaluate and optimize the second model.
[0167] In step 709, the second model can be evaluated based on the first and second names; the second model is then trained using a lightweight method based on the keyword weight vector and the first name to obtain the optimized third model. This allows the second model to continuously evolve dynamically, improving the file naming quality of its output.
[0168] The above embodiments improve file processing efficiency and naming quality for multimodal files by establishing a unified feature representation system; dynamically balancing online and offline model resources eliminates latency jitter caused by network fluctuations, improving the smoothness of file naming; and continuously optimizing the local second model enhances file naming quality in the second mode. Thus, the challenges of coordinating efficiency, service stability, and privacy protection in traditional solutions involving manually selecting a single offline or online model are resolved, enabling intelligent file naming management.
[0169] The file naming method provided in this application can be executed by a file naming device. This application uses an example of a file naming device executing the file naming method to illustrate the file naming device provided in this application.
[0170] See Figure 8 This application provides a file naming device for use in electronic devices. The device 800 includes:
[0171] The first determining module 801 is used to determine the file naming pattern;
[0172] The first processing module 802 is configured to, when the file naming mode is the first mode, input the naming feature information of the first file to the first model located on the server, receive the first name of the first file output by the first model, and name the first file as the first name; when the file naming mode is the second mode, input the naming feature information of the first file to the second model located on the electronic device, receive the second name of the first file output by the second model, and name the first file as the second name.
[0173] In some optional embodiments of this application, the device 800 further includes:
[0174] The first acquisition module is used to acquire text feature information corresponding to the first file;
[0175] The second acquisition module is used to obtain the keyword weight vector of the first file based on the text feature information and use the keyword weight vector as the naming feature information.
[0176] In some optional embodiments of this application, the second acquisition module includes:
[0177] The first acquisition unit is used to perform word segmentation on the text feature information and filter stop words to obtain multiple keywords included in the text feature information;
[0178] The second acquisition unit is used to determine the frequency of occurrence of each keyword in the text feature information;
[0179] The third acquisition unit is used to determine the inverse document frequency of each keyword in the corpus;
[0180] The fourth acquisition unit is used to determine the weight value corresponding to each keyword based on the product of the occurrence frequency and the inverse document frequency;
[0181] The fifth acquisition unit is used to remove the keywords whose weight values are lower than a preset threshold, and then use the remaining keywords and their corresponding weight values to form the keyword weight vector of the first document.
[0182] In some optional embodiments of this application, the first acquisition module includes:
[0183] The sixth acquisition unit is used to determine the file type of the first file based on the file type identification information of the first file; wherein the file type identification information includes at least one of the following: file format identifier, hexadecimal feature byte sequence in the file header, the starting position of the hexadecimal feature byte sequence in the file header, and a list of extensions;
[0184] The seventh acquisition unit is used to determine the text feature extraction method based on the file type;
[0185] The eighth acquisition unit is used to determine the text feature information corresponding to the first file according to the text feature extraction method.
[0186] In some optional embodiments of this application, device 800 further includes:
[0187] The second processing module is used to input the naming feature information of the first file into the first model when the file naming mode is switched from the second mode to the first mode, and to receive the first name of the first file output by the first model.
[0188] The third processing module is used to obtain the first word segmentation result set corresponding to the first name and the second word segmentation result set corresponding to the second name;
[0189] The fourth processing module is used to determine the vocabulary coverage of the second model execution file name based on the first word segmentation result set and the second word segmentation result set;
[0190] The fifth processing module is used to determine the redundant word penalty value for naming the second model execution file based on the first word segmentation result set and the second word segmentation result set;
[0191] The sixth processing module is used to determine the quantitative evaluation result of the second model based on the difference between the vocabulary coverage rate and the redundant word penalty value.
[0192] In some optional embodiments of this application, device 800 further includes:
[0193] The seventh processing module is used to use the dataset consisting of the naming feature information of the first file and the first name as training samples.
[0194] The eighth processing module is used to iteratively train the second model based on the training samples to obtain the third model when the number of training samples is greater than or equal to a preset number threshold and / or the quantitative evaluation result meets the preset conditions.
[0195] The ninth processing module is used to replace the second model in the electronic device with the third model.
[0196] In some optional embodiments of this application, the first determining module 801 includes:
[0197] The first determining unit is configured to determine a file naming pattern upon detecting a completion event of the generation of the first file; or,
[0198] The second determining unit is configured to receive a first input from the user regarding the first file; and in response to the first input, determine a file naming pattern.
[0199] It should be noted that the file naming device 800 is a device corresponding to the above-described file naming method. All implementation means in the above method embodiments are applicable to the embodiments of the file naming device and can achieve the same technical effect.
[0200] The file naming device in this application embodiment can be an electronic device or a component within an electronic device, such as an integrated circuit or a chip. The electronic device can be a terminal or other devices besides a terminal. For example, the electronic device can be a mobile phone, tablet computer, laptop computer, PDA, in-vehicle electronic device, mobile internet device (MID), augmented reality (AR) / virtual reality (VR) device, robot, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc. It can also be network attached storage (NAS), personal computer (PC), television (TV), ATM, or self-service machine, etc. This application embodiment does not specifically limit the device.
[0201] The file naming device in this application embodiment can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit it.
[0202] The file naming device provided in this application embodiment can achieve... Figures 1 to 7 The various processes implemented in the method implementation examples will not be described again here to avoid repetition.
[0203] Optionally, such as Figure 9 As shown, this application embodiment also provides an electronic device 900, including a processor 901 and a memory 902. The memory 902 stores a program or instructions that can run on the processor 901. When the program or instructions are executed by the processor 901, they implement the various steps of the above-described file naming method embodiment and can achieve the same technical effect. To avoid repetition, they will not be described again here.
[0204] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.
[0205] Figure 10 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of this application.
[0206] The electronic device 1000 includes, but is not limited to, components such as: radio frequency unit 1001, network module 1002, audio output unit 1003, input unit 1004, sensor 1005, display unit 1006, user input unit 1007, interface unit 1008, memory 1009, and processor 1010.
[0207] Those skilled in the art will understand that the electronic device 1000 may also include a power supply (such as a battery) for supplying power to various components. The power supply may be logically connected to the processor 1010 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 10 The electronic device structure shown does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.
[0208] The processor 1010 is configured to determine a file naming mode; when the file naming mode is a first mode, it inputs the naming feature information of the first file to a first model located on the server, receives the first name of the first file output by the first model, and names the first file as the first name; when the file naming mode is a second mode, it inputs the naming feature information of the first file to a second model located on the electronic device, receives the second name of the first file output by the second model, and names the first file as the second name.
[0209] Optionally, the processor 1010 is further configured to obtain text feature information corresponding to the first file; obtain a keyword weight vector of the first file based on the text feature information, and use the keyword weight vector as the naming feature information.
[0210] Optionally, the processor 1010 is further configured to perform word segmentation on the text feature information and filter stop words to obtain multiple keywords included in the text feature information;
[0211] Determine the frequency of occurrence of each keyword in the text feature information;
[0212] Determine the inverse document frequency of each keyword in the corpus;
[0213] The weight value corresponding to each keyword is determined based on the product of the occurrence frequency and the inverse document frequency;
[0214] After removing keywords whose weight values are lower than a preset threshold, the remaining keywords and their corresponding weight values constitute the keyword weight vector of the first document.
[0215] Optionally, the processor 1010 is further configured to determine the file type of the first file based on the file type identification information of the first file; wherein the file type identification information includes at least one of the following: file format identifier, hexadecimal feature byte sequence in the file header, the starting position of the hexadecimal feature byte sequence in the file header, and a list of extensions;
[0216] Based on the file type, determine the text feature extraction method;
[0217] Based on the text feature extraction method, the text feature information corresponding to the first file is determined.
[0218] Optionally, the processor 1010 is also used for:
[0219] When the file naming mode is switched from the second mode to the first mode, the naming feature information of the first file is input into the first model, and the first name of the first file output by the first model is received;
[0220] Obtain the first word segmentation result set corresponding to the first name and the second word segmentation result set corresponding to the second name;
[0221] Based on the first word segmentation result set and the second word segmentation result set, determine the vocabulary coverage of the second model execution file naming;
[0222] Based on the first word segmentation result set and the second word segmentation result set, determine the redundant word penalty value for the naming of the second model execution file;
[0223] The quantitative evaluation result of the second model is determined based on the difference between the vocabulary coverage rate and the redundant word penalty value.
[0224] Optionally, the processor 1010 is further configured to use the dataset consisting of the naming feature information of the first file and the first name as training samples; when the number of training samples is greater than or equal to a preset number threshold and / or the quantization evaluation result meets a preset condition, iteratively train the second model based on the training samples to obtain a third model; and replace the second model in the electronic device with the third model.
[0225] Optionally, the processor 1010 is further configured to determine a file naming pattern upon detecting a completion event of the generation of the first file; or,
[0226] Receive the user's first input on the first file; in response to the first input, determine the file naming pattern.
[0227] In the above embodiments, users do not need to manually select models, which reduces user operation steps. Users only need to focus on the file content and do not need to worry about model selection, thus improving ease of use and efficiency of file naming.
[0228] It should be understood that, in this embodiment, the input unit 1004 may include a graphics processing unit (GPU) 10041 and a microphone 10042. The GPU 10041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 1006 may include a display panel 10061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like. The user input unit 1007 includes a touch panel 10071 and at least one of other input devices 10072. The touch panel 10071 is also called a touch screen. The touch panel 10071 may include a touch detection device and a touch controller. Other input devices 10072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be described in detail here.
[0229] The memory 1009 can be used to store software programs and various data. The memory 1009 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 1009 may include volatile memory or non-volatile memory, or both. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 1009 in this embodiment includes, but is not limited to, these and any other suitable types of memory.
[0230] The processor 1010 may include one or more processing units; optionally, the processor 1010 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into the processor 1010.
[0231] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described file naming method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.
[0232] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.
[0233] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-described file naming method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.
[0234] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.
[0235] This application provides a computer program product that is stored in a storage medium and executed by at least one processor to implement the various processes of the file naming method embodiment described above, and achieves the same technical effect. To avoid repetition, it will not be described again here.
[0236] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.
[0237] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.
[0238] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.
Claims
1. A method of naming a file, characterized by, Performed by an electronic device, the method includes: Determine the file naming pattern; When the file naming mode is the first mode, the naming feature information of the first file is input to the first model located on the server, the first name of the first file output by the first model is received, and the name of the first file is named the first name. When the file naming mode is the second mode, the naming feature information of the first file is input to the second model located in the electronic device, the second name of the first file output by the second model is received, and the name of the first file is named the second name; When the file naming pattern is the second pattern, after naming the first file with the second name, the method further includes: When the file naming mode is switched from the second mode to the first mode, the naming feature information of the first file is input into the first model, and the first name of the first file output by the first model is received; Obtain the first word segmentation result set corresponding to the first name and the second word segmentation result set corresponding to the second name; Based on the first word segmentation result set and the second word segmentation result set, determine the vocabulary coverage of the second model execution file name; Based on the first word segmentation result set and the second word segmentation result set, determine the redundant word penalty value for the naming of the second model execution file; The quantitative evaluation result of the second model is determined based on the difference between the vocabulary coverage rate and the redundant word penalty value.
2. The file naming method of claim 1, wherein, The method further includes: Obtain the text feature information corresponding to the first file; Based on the text feature information, the keyword weight vector of the first file is obtained, and the keyword weight vector is used as the naming feature information.
3. The file naming method of claim 2, wherein, The step of obtaining the keyword weight vector of the first file based on the text feature information includes: The text feature information is segmented and stop words are filtered to obtain multiple keywords included in the text feature information; Determine the frequency of occurrence of each keyword in the text feature information; Determine the inverse document frequency of each keyword in the corpus; The weight value corresponding to each keyword is determined based on the product of the occurrence frequency and the inverse document frequency; After removing keywords whose weight values are lower than a preset threshold, the remaining keywords and their corresponding weight values constitute the keyword weight vector of the first document.
4. The file naming method of claim 2, wherein, The step of obtaining the text feature information corresponding to the first file includes: The file type of the first file is determined based on the file type identification information of the first file; wherein the file type identification information includes at least one of the following: file format identifier, hexadecimal feature byte sequence in the file header, starting position of the hexadecimal feature byte sequence in the file header, and a list of file extensions; Based on the file type, determine the text feature extraction method; Based on the text feature extraction method, the text feature information corresponding to the first file is determined.
5. A file naming device, characterized in that, Applied to electronic devices, the device includes: The first determining module is used to determine the file naming pattern; The first processing module is configured to, when the file naming mode is the first mode, input the naming feature information of the first file to the first model located on the server, receive the first name of the first file output by the first model, and name the first file as the first name; when the file naming mode is the second mode, input the naming feature information of the first file to the second model located on the electronic device, receive the second name of the first file output by the second model, and name the first file as the second name. The device further includes: The second processing module is used to input the naming feature information of the first file into the first model when the file naming mode is switched from the second mode to the first mode, and to receive the first name of the first file output by the first model. The third processing module is used to obtain the first word segmentation result set corresponding to the first name and the second word segmentation result set corresponding to the second name; The fourth processing module is used to determine the vocabulary coverage of the second model execution file name based on the first word segmentation result set and the second word segmentation result set; The fifth processing module is used to determine the redundant word penalty value for naming the second model execution file based on the first word segmentation result set and the second word segmentation result set; The sixth processing module is used to determine the quantitative evaluation result of the second model based on the difference between the vocabulary coverage rate and the redundant word penalty value.
6. The file naming device according to claim 5, characterized in that, The device further includes: The first acquisition module is used to acquire text feature information corresponding to the first file; The second acquisition module is used to obtain the keyword weight vector of the first file based on the text feature information, and to use the keyword weight vector as the naming feature information.
7. The file naming device according to claim 6, characterized in that, The second acquisition module includes: The first acquisition unit is used to perform word segmentation on the text feature information and filter stop words to obtain multiple keywords included in the text feature information; The second acquisition unit is used to determine the frequency of occurrence of each keyword in the text feature information; The third acquisition unit is used to determine the inverse document frequency of each keyword in the corpus; The fourth acquisition unit is used to determine the weight value corresponding to each keyword based on the product of the occurrence frequency and the inverse document frequency; The fifth acquisition unit is used to remove the keywords whose weight values are lower than a preset threshold, and then use the remaining keywords and their corresponding weight values to form the keyword weight vector of the first document.
8. The file naming device according to claim 6, characterized in that, The first acquisition module includes: The sixth acquisition unit is used to determine the file type of the first file based on the file type identification information of the first file; wherein the file type identification information includes at least one of the following: file format identifier, hexadecimal feature byte sequence in the file header, the starting position of the hexadecimal feature byte sequence in the file header, and a list of extensions; The seventh acquisition unit is used to determine the text feature extraction method based on the file type; The eighth acquisition unit is used to determine the text feature information corresponding to the first file according to the text feature extraction method.
Citation Information
Patent Citations
Named entity recognition method, device and system
CN108255816A
File naming method and device, electronic equipment, storage medium and program product
CN119377175A
