File management method and device, electronic equipment and medium

By using the operating system's voice recognition function in the file management client, monitoring user voice input and converting it into command text, the problem of low efficiency of the existing file management system is solved, efficient file management operations are realized, and multiple input methods are supported. , improves user experience and management efficiency.

CN119088767APending Publication Date: 2024-12-06BEIJING BAIDU NETCOM SCI & TECH CO LTD

Patent Information

Application Number
CN202411171207.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-23
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing file management system is inefficient, especially in scenarios where the number of files is large and the types of files is diverse. Users need to manually select files and perform operations, resulting in low management efficiency.

Method used

By using the operating system's voice recognition function in the file management client, it monitors the user's voice input, converts it into command text, determines the information and performs operations of the files to be operated, and then realizes file management operations, supporting voice, keyboard, templates and images Scan the input method to simplify user operations.

Benefits of technology

Improves the efficiency of file management, simplifies user operations, supports multiple input methods, improves the reputation of user experience and file management client, reduces the cost of interaction between users and terminals, and has high accuracy of voice recognition functions, optimizes and updates. More convenient.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119088767A_ABST
    Figure CN119088767A_ABST
Patent Text Reader

Abstract

The invention provides a file management method and device, electronic equipment and a medium, and relates to the technical field of artificial intelligence, in particular to the technical field of natural language processing, intelligent searching and cloud computing. According to the specific implementation scheme, when it is detected that a user triggers a voice input instruction, voice sent by the user is monitored through a voice recognition function of an operating system, and voice conversion is conducted on the monitored voice to obtain an instruction text. And then determining file information of a to-be-operated file and to-be-executed operation based on the instruction text. And based on the file information, obtaining an operation result obtained by executing the to-be-executed operation on the to-be-operated file, and displaying the operation result. The file management efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and in particular to the field of natural language processing, intelligent search, and cloud computing technology. Background Art

[0002] With the popularization of digital information, various types of files can be converted into computer-readable digital formats and stored in electronic devices. For example, text can be stored in formats such as plain text (txt) or Extensible Markup Language (XML); pictures can be stored in formats such as Joint Photographic Experts Group (JPEG) or Graphics Interchange Forma (GIF); videos can be stored in formats such as Moving Picture Experts Group-4 (MP4) or Advanced Streaming Format (ASF). The types and numbers of files stored in electronic devices are increasing, which brings challenges to file management. Summary of the invention

[0003] The present disclosure provides a file management method, device, electronic device and medium.

[0004] A first aspect of the embodiments of the present disclosure provides a file management method, including:

[0005] When a user triggers a voice input command, the voice recognition function of the operating system is used to monitor the voice of the user, and the monitored voice is converted into a command text;

[0006] Based on the instruction text, determine the file information of the file to be operated and the operation to be performed;

[0007] Based on the file information, obtaining an operation result obtained by performing the operation to be performed on the file to be operated;

[0008] The operation result is displayed.

[0009] A second aspect of the embodiments of the present disclosure provides a file management device, including:

[0010] The conversion module is used to monitor the voice of the user through the voice recognition function of the operating system when detecting that the user triggers the voice input command, and perform voice conversion on the monitored voice to obtain the command text;

[0011] A determination module, used to determine file information of a file to be operated and an operation to be performed based on the instruction text obtained by the conversion module;

[0012] An acquisition module, configured to acquire, based on the file information determined by the determination module, an operation result obtained by performing the operation to be performed on the file to be operated;

[0013] A display module is used to display the operation result obtained by the obtaining module.

[0014] According to a third aspect of the embodiments of the present disclosure, there is provided an electronic device, including:

[0015] at least one processor; and

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform any method according to the first aspect.

[0018] According to a fourth aspect of an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute a method according to any one of the first aspects.

[0019] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided, including a computer program, wherein when the computer program is executed by a processor, the method according to any one of the first aspects is implemented.

[0020] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0022] Figure 1 is a flow chart of a file management method provided by an embodiment of the present disclosure;

[0023] Figure 2 is an exemplary schematic diagram of a first display interface of a file management client provided by an embodiment of the present disclosure;

[0024] Figure 3 is an exemplary schematic diagram of a second display interface of a file management client provided by an embodiment of the present disclosure;

[0025] Figure 4 is an exemplary schematic diagram of a third display interface of a file management client provided by an embodiment of the present disclosure;

[0026] Figure 5 is an exemplary schematic diagram of a fourth display interface of a file management client provided by an embodiment of the present disclosure;

[0027] Figure 6 is an exemplary schematic diagram of a fifth display interface of a file management client provided by an embodiment of the present disclosure;

[0028] Figure 7 is an exemplary schematic diagram of a sixth display interface of a file management client provided by an embodiment of the present disclosure;

[0029] Figure 8 is an exemplary schematic diagram of a seventh display interface of a file management client provided by an embodiment of the present disclosure;

[0030] Fig. 9 is a flow chart of another file management method provided by an embodiment of the present disclosure;

[0031] Fig.10 is a structural diagram of a file management device provided by an embodiment of the present disclosure;

[0032] Fig.11 The block diagram is a block diagram of an electronic device used to implement the file management method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0033] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0034] At present, the existing file management system only supports manual file management operations by users, that is, users need to manually select the file to be operated, and then select the operation to be performed on the file. For example, the user first manually searches for the file to be deleted in the cloud storage client, selects the file, and then selects the delete operation, after which the cloud storage client deletes the file. However, this method that requires users to manually perform file management operations is inefficient, especially in scenarios with a large number of files and a variety of file types. This traditional file management method can no longer meet user needs.

[0035] In order to improve the efficiency of file management, the present disclosure provides a file management method, which is applied to a file management client, such as a network disk client. The file management client is installed in a terminal, such as a mobile phone, a tablet computer, or a laptop computer. Figure 1 As shown, the file management method provided by the embodiment of the present disclosure includes the following steps:

[0036] S101. When it is detected that a user triggers a voice input command, the voice of the user is monitored through the voice recognition function of the operating system, and the monitored voice is converted into a command text.

[0037] The display interface of the file management client can display a voice input control. When it is detected that the user triggers the voice input control, it is determined that the user triggers the voice input command. After that, the file management client calls the automatic speech recognition (Automatic Speech Recognition, ASR) application programming interface (Application Programming Interface, API) provided by the operating system of the terminal where it is located, so that the operating system monitors the voice emitted by the user, converts the monitored voice into a command text, and then returns the converted command text to the file management client.

[0038] For example, Figure 2 A display interface 200 of a file management client includes: a voice input control 201, a keyboard input control 202, and other controls 203. The voice input control 201 is used to trigger a voice input command, the keyboard input control 202 is used to trigger a keyboard input command, and the other controls 203 are used to trigger instructions for displaying other controls. When the file management client detects that a user clicks on the voice input control 201 in the display interface 200, it determines that the user has triggered a voice input command. Figure 3 As shown, the file management client can display the voice input interface 300 and call the voice recognition API provided by the operating system of the terminal where it is located, so that the operating system monitors the voice of the user, converts the monitored voice into a command text, and then returns the converted command text to the file management client. The file management client can display the command text returned by the operating system in real time in the voice input interface 300, for example Figure 3 The instruction text returned by the operating system is "Help me find XX movie".

[0039] The operating system of the terminal may be an open source operating system or an operating system independently developed by the terminal manufacturer, etc., which supports the voice recognition function. With the development of AI technology, most terminal operating systems can currently support the voice recognition function, and all have high accuracy. Therefore, the embodiments of the present disclosure can be applied to a wide variety of terminals, making the embodiments of the present disclosure have a wide range of applications.

[0040] S102: Determine the file information of the file to be operated and the operation to be performed based on the instruction text.

[0041] The file management client can perform semantic analysis on the instruction text, thereby obtaining file information of the files to be operated that the user needs to manage, and the operations to be performed on the files to be operated.

[0042] For example, the file information of the file to be operated may include at least one of the following: file name, file upload time, file format, and folder where it is located, etc. The operation to be performed includes at least one of the following: search, translation, summary, summary generation, and image generation document, etc.

[0043] S103: Based on the file information, obtain an operation result obtained by performing the operation to be performed on the file to be operated.

[0044] S104: Display the operation result.

[0045] In the disclosed embodiment, the file management client can monitor the voice of the user through the voice recognition function of the operating system, and perform voice conversion on the monitored voice to obtain the instruction text, and then determine the file information of the file to be operated and the operation to be performed based on the instruction text, and perform the operation to be performed on the file to be operated. That is, the disclosed embodiment supports the user to perform file management operations through voice, without the need for the user to manually select files and manually select file operations, thereby simplifying the user operation and improving the efficiency of file management.

[0046] The following is a detailed description of the file management method provided by the embodiment of the present disclosure:

[0047] In general, various operating systems disclose APIs for various artificial intelligence (AI) functions that they can provide, such as ASR API, optical character recognition (OCR) API, etc. Therefore, the embodiments of the present disclosure are described in detail in the following sections. Figure 1Previously, for different versions of the file management client, various AI function APIs provided by the operating system of the terminal applicable to the version can be configured in advance in the client code of the version. When the subsequent file management client executes S101, it can call the ASR API recorded in the client code when detecting that the user triggers a voice input command, so that the operating system monitors the voice emitted by the user, converts the monitored voice into a command text, and returns the command text to the file management client.

[0048] If the file management client directly monitors the voice of the user and sends the monitored voice to the cloud, the cloud converts the voice into instruction text, and then sends the converted instruction text to the file management client, then the speed at which the file management client receives the instruction text is affected by the network transmission speed, thereby affecting the speed of obtaining the operation results of the file management operation.

[0049] Alternatively, if the file management client directly monitors the voice of the user and directly converts the monitored voice into a command text, then the file management client needs to have a voice recognition function. However, the voice recognition function is generally more complex and involves a huge amount of code. If the code for implementing the voice recognition function is configured in the file management client code, each time the voice recognition function code is modified, it is necessary to modify the entire file management client code, resulting in high complexity in modifying the voice recognition function, which is not conducive to the optimization and update of the voice recognition function.

[0050] The embodiment of the present disclosure uses the voice recognition function provided by the terminal's operating system to convert the user's voice into instruction text, and the communication between the file management client and the operating system is not affected by the network transmission speed, so the file management client can obtain the instruction text converted from the voice more quickly. Moreover, the code that implements the voice recognition function is not in the file management client code, which is more conducive to the optimization and update of the voice recognition function. In addition, since the native voice recognition functions of various operating systems currently have extremely high accuracy, the embodiment of the present disclosure uses the native voice recognition function of the operating system to obtain voice recognition results with higher accuracy.

[0051] In the disclosed embodiment, the file management client supports not only voice input but also other input methods, such as keyboard input, template input or image scanning input.

[0052] That is, before the above S102, the file management client can also obtain the instruction text input by the user through the keyboard through the keyboard input function of the operating system when detecting that the user triggers the keyboard input instruction.

[0053] The display interface of the file management client may display a keyboard input control, and when it is detected that the user triggers the keyboard input control, it is determined that the user triggers a keyboard input command. After that, the file management client calls the keyboard input API provided by the operating system of the terminal where it is located, so that the operating system receives the command text entered by the user on the keyboard and returns the command text to the file management client.

[0054] For example, Figure 2 A display interface 200 of a file management client. When the file management client detects that a user clicks a keyboard input control 202 in the display interface 200, it is determined that the user triggers a keyboard input instruction, and then the keyboard input API provided by the operating system can be called. Figure 4 Thus, the keyboard control 204 is displayed in the display interface 200, so that the user can input the instruction text by operating the keyboard control 204, and then the operating system returns the instruction text to the file management client.

[0055] It can be seen that in addition to supporting voice input, the file management client in the embodiment of the present disclosure can also support keyboard input, so that users can choose more input methods, enrich the user's input forms, meet the operation needs of different users, reduce the interaction cost between users and terminals, improve the user experience, and improve user stickiness and the reputation of the file management client.

[0056] Alternatively, before the above S102, the file management client may also obtain the instruction text corresponding to the template triggered by the user when detecting that the user triggers the template input instruction.

[0057] The file management client may display a template input control in the display interface. When it is detected that a user triggers the template input control, it is determined that the user triggers the template input instruction. Then, the file management client uses the text corresponding to the template triggered by the user as the instruction text from the text corresponding to each template input control. The text corresponding to each template input control may be a commonly used hotspot instruction text.

[0058] For example, Figure 5 A display interface 500 of a file management client includes: a voice input control 201, a keyboard input control 202, other controls 203 and three template input controls 205. Each template input control 205 corresponds to a text, such as Figure 5As shown, in order from top to bottom, the text corresponding to the first template input control 205 is "check the pictures uploaded last week", the text corresponding to the second template input control 205 is "recommend a new energy vehicle", and the text corresponding to the third template input control 205 is "help me write a weekly report". Assuming that the file management client detects that the user clicks the first template input control 205, it obtains "check the pictures uploaded last week" as the instruction text. Figure 5 The functions of other controls in the can refer to the above description and will not be repeated here.

[0059] It can be seen that the file management client in the disclosed embodiment can support template input in addition to voice input, so that users can quickly manage files with one click, simplifying user operations and improving file management efficiency. In addition, since the file management client supports multiple input methods, users can choose more input methods, enriching the user's input form, meeting the operation needs of different users, reducing the interaction cost between users and terminals, improving user experience, and improving user stickiness and the reputation of the file management client.

[0060] Alternatively, before the above S102, the file management client may also recognize the instruction text in the image selected by the user through the OCR function of the operating system when detecting that the user triggers the image scanning input instruction.

[0061] The image scanning input control can be displayed in the display interface of the file management client. When it is detected that the user triggers the image scanning input control, it is determined that the user has triggered the image scanning input instruction. After that, the file management client calls the OCR API provided by the operating system of the terminal where it is located, so that the operating system recognizes the instruction text in the picture selected by the user, and returns the instruction text recognized from the picture to the file management client. Among them, the picture selected by the user can be: a picture selected by the user from the local album of the terminal, or a picture selected by the user from the pictures stored in the file management client, or a picture taken by the user in real time through a camera, etc.

[0062] For example, the file management client detects that a user is Figure 2 Click other controls 203 in the display interface 200 shown in FIG. Figure 6 As shown, an image scanning input control 206 is displayed in the display interface 200. Then the file management client calls the OCR API provided by the operating system, so that the operating system recognizes the instruction text in the picture selected by the user and returns the recognized instruction text to the file management client.

[0063] In addition, if Figure 2As shown, the default display style of the other control 203 is a circle containing a "+" inside. When the other control 203 is clicked, as shown in Figure 6 As shown, when the file management client displays the image scanning input control 206, it can also modify the display style of other controls 203, that is, modify the display style of other controls 203 to a circle containing "∧" inside. Figure 6 When other controls 203 are clicked in the display interface 200 shown, the image scanning input control 206 is hidden, and the display style of other controls 203 is modified to the default style. Figure 6 The functions of other controls in the can refer to the above description and will not be repeated here.

[0064] The above input methods are only examples provided in the embodiments of the present disclosure, and the input methods supported by the file management client are not limited thereto.

[0065] It can be seen that in addition to supporting voice input, the file management client in the embodiment of the present disclosure can also support image scanning input, so that users can choose more input methods, enrich the user's input forms, meet the operation needs of different users, reduce the interaction cost between users and terminals, improve the user experience, and improve user stickiness and the reputation of the file management client.

[0066] After obtaining the instruction text, the file management client executes the above S102 to determine the file information of the file to be operated and the operation to be performed based on the instruction text, which can be implemented as follows: using a preset natural language processing model to determine the file information of the file to be operated and the operation to be performed based on the instruction text.

[0067] That is, the file management client can input the instruction text into the preset natural language processing model to obtain the file information of the file to be operated and the operation to be performed output by the natural language processing model. For example, the natural language processing model can be: a transformer, bidirectional encoder representations from transformers (Bidirectional Encoder Representations from Transformers, BERT) or a large language model (Large Language Model, LLM), etc.

[0068] The format of the output result of the natural language processing model can be preset, including two parameters, namely, the file information of the file to be operated and the operation to be performed. For example, the output result of the natural language processing model is:

[0069] “Files to be operated: 2024.8.1, upload, picture;

[0070] Action to be performed: Search. "

[0071] Through the above method, the embodiment of the present disclosure can utilize the natural language processing model to perform natural language processing on the instruction text, thereby accurately identifying the meaning of the instruction text, obtaining the file information of the file to be operated and the operation to be performed, and ensuring the accuracy of subsequent file operations.

[0072] In the embodiment of the present disclosure, when a user inputs an operation instruction for a file by voice, keyboard, or template, the display interface of the file management client may include a file, such as a document, an image, or a video. At this time, the operation instruction issued by the user, such as a voice instruction, a text instruction, or a template instruction, may not include description information for the file, or include words referring to the currently displayed file. For example, the voice instruction issued by the user is: "summarize the video" or "summarize the currently playing video."

[0073] Based on this, the above-mentioned method of using a preset natural language processing model to determine the file information of the file to be operated and the method of the operation to be performed based on the instruction text can be implemented as follows: the file management client inputs the instruction text into the natural language processing model to obtain the file data and the operation to be performed output by the natural language processing model. If the file data is a preset text, the file information of the file displayed in the current page is used as the file information of the file to be operated. If the file data is not a preset text, the file data is used as the file information of the file to be operated.

[0074] When the file data output by the natural language processing model is a preset text, it means that the file that the user instructs to operate is the file currently displayed by the file management client, and the file management client can display the file, which means that the file management client stores the metadata of the file. Therefore, the file management client can obtain the metadata of the file as the file information of the file to be operated. For example, the metadata of the file includes: file name, file type, folder to which it belongs, and upload or download time, etc.

[0075] For example, if the instruction text is "Summarize the currently playing video", the output of the natural language processing model is:

[0076] "Files to be operated: Currently displaying files;

[0077] Action to be performed: Summarize the contents of the file."

[0078] At this time, the file management client uses the file information displayed in the current page as the file information of the file to be operated; the operation to be performed is to summarize the file content.

[0079] For another example, if the command text is "Find the pictures I uploaded on August 1, 2024", the output of the natural language processing model is:

[0080] “Files to be operated: 2024.8.1, upload, picture;

[0081] Action to be performed: Search. "

[0082] At this time, the file information of the file to be operated is: 2024.8.1, upload, picture; the operation to be performed is a search operation.

[0083] For example, see Figure 7 , Figure 7 The display interface 700 of the file management client shown includes a video display area 207, and a video describing the transformation of the starry sky is displayed in the video display area 207. The file management client supports the user to input instructions through the voice input control 201, the keyboard input control 202 or other controls 203 in the display interface 700. Assume that the file management client detects that the user clicks the voice input control 201, and obtains the instruction text: "Summarize this video" through the voice recognition function of the operating system, and then displays the instruction text in the instruction display control 208. After that, the file management client obtains the output result of the natural language processing model for the instruction text: "File to be operated: currently displayed file; operation to be performed: summarize the file content.", and then uses the metadata of the currently displayed video as the file information of the file to be operated, and then obtains the operation result obtained by performing the operation to be performed on the file to be operated: "This video describes the transformation of the starry sky: ... It belongs to a large-scale natural, geographical, and humanities documentary", and then displays the operation result in the answer display control 209. Figure 7 The functions of other controls in the can refer to the above description and will not be repeated here.

[0084] Through the above method, the embodiment of the present disclosure not only supports the user to indicate the operation of the currently displayed file, but also supports the user to indicate the operation of the currently not displayed file, which can bring a more convenient and richer file management experience to the user.

[0085] In the disclosed embodiment, the operation to be performed indicated by the user may be a search operation. In this case, the instruction text generally includes at least one metadata of the file to be searched. In this case, the natural language processing model can extract keywords from the instruction text to obtain file information of the file to be operated. That is, the file information includes at least one metadata. The metadata includes the file name and / or other file attributes. For example, other file attributes include at least one of the following: operation behavior, execution time of the operation behavior, folder and file type to which it belongs, etc. Among them, the operation behaviors include: upload, download, transfer, backup, preview and play, etc. File types include: pictures, text, portable document format (PDF), presentation (PowerPoint, PPT), video and audio, etc.

[0086] When the instruction text includes the file name but does not include other file attributes, the instruction text can be called a simple query; when the instruction text includes other file attributes, the instruction text can be called a complex query.

[0087] For example, a simple query is: "Help me find a TV series."

[0088] Complex query with behavior: "Find the postgraduate entrance examination mathematics materials I uploaded", where "upload" is the operation behavior and "postgraduate entrance examination mathematics materials" is the file name.

[0089] Complex query with time: "PDF transferred on June 23", where "transfer" is the operation behavior, "June 23" is the execution time of the operation behavior, and "PDF" is the file type.

[0090] Complex query with location: "Search for audio in the current folder", where "current folder" is the folder to which the file belongs, and "audio" is the file type.

[0091] When the operation to be performed is a search operation, the above-mentioned S103 file management client obtains the operation result obtained by performing the operation to be performed on the file to be operated based on the file information. The method can be implemented as follows: from the metadata sets of each stored file, search for the target metadata set that matches the file information, and then obtain the file to be operated corresponding to the target metadata set.

[0092] The stored files include at least one of the following files: files stored in the file management client, files stored in the terminal where the file management client is located, and files stored in the cloud through the file management client.

[0093] The file management client stores a metadata set of stored files. When performing a search operation, the file management client can sequentially search whether the metadata set of each stored file matches the file information of the file to be operated. If they match, the file is used as the file to be operated.

[0094] When matching metadata, for each metadata included in the file information of the file to be operated, if the metadata is the same as a metadata in a metadata set, or the metadata includes a metadata in the metadata set, it is determined that the metadata included in the file information is matched successfully; otherwise, it is determined that the metadata included in the file information is matched unsuccessfully. If each metadata included in the file information is successfully matched with the same metadata set, the metadata set is determined to be the target metadata set.

[0095] For example, the file information of the file to be operated includes: 2024.8, upload, picture. Metadata set A includes: pet growth record, 2024.8.1, upload, JPEG. Since 2024.8.1 belongs to 2024.8, upload is the same as upload, and JPEG belongs to picture, the file information of the file to be operated matches metadata set A.

[0096] Through the above method, the disclosed embodiment can realize the search operation for files, and supports not only searching based on file names, but also searching based on various metadata such as file types. Moreover, since the file management client has a metadata set of stored files, the file management client does not need to interact with the cloud during the file search process, that is, the search operation can be completed in an offline environment without relying on the network, thereby supporting more practical usage scenarios.

[0097] In the disclosed embodiments, the operation to be performed may be a complex operation that is complex in process and consumes more computing resources. For example, the complex operation includes at least one of the following: translating, polishing, generating abstracts, summarizing, adding annotations, adding tags, and converting formats of documents, adding filters, beautifying and slimming, background replacement, and image repair to pictures, generating subtitles and summarizing videos, etc.

[0098] When the operation to be performed is a complex operation, the method of obtaining the operation result obtained by performing the operation to be performed on the file to be performed based on the file information in the above S103 file management client can be implemented as follows: the file management client sends a file processing request to the cloud, wherein the file processing request includes the file information and the operation to be performed, so that the cloud determines the file to be performed based on the file information, and performs the operation to be performed on the file to be performed to obtain the operation result. Then, the file management client receives the operation result sent by the cloud.

[0099] The file management client may be a network disk client that can communicate with the cloud to manage files stored in the cloud. The file management client may be pre-configured with cloud file processing APIs corresponding to various complex operations, so that the subsequent file management client can call the cloud file processing API corresponding to the operation to be executed after determining the operation to be executed, thereby sending a file processing request to the cloud.

[0100] Since the file processing request sent by the file management client to the cloud includes the file information of the file to be operated, the cloud can find the file to be operated based on the file information, perform the operation to be performed on the file to be operated, and then return the operation result to the file management client. The cloud can find the file to be operated by referring to the above-mentioned method of finding the file to be operated by the file management client, or can also find it by other methods, which is not specifically limited in the embodiments of the present disclosure.

[0101] The cloud can use artificial intelligence algorithms to execute pending operations on operation files. For example, artificial intelligence algorithms include: large language models, deep learning models, or machine learning models.

[0102] Conventional file management clients only support relatively simple file management functions, such as manually searching for files. In the embodiments of the present disclosure, the file management client can use the file processing capabilities of the cloud to provide users with more abundant file processing operations, greatly improving the user experience. Moreover, these complex file operations are processed by the cloud instead of in the terminal, so they do not consume the computing resources of the terminal, reducing the requirements for the computing resources of the terminal. Therefore, it can be applied to more types of terminals, making the application scope of the embodiments of the present disclosure wider.

[0103] In the embodiment of the present disclosure, the operation to be performed may be a simple operation with a relatively simple process and less computing resources consumed, for example, the simple operation includes at least one of the following: recognizing text from a picture and generating a document, or recognizing speech and generating a document.

[0104] When the operation to be performed is a simple operation, the above-mentioned S103 file management client obtains the operation result obtained by performing the operation to be performed on the file to be operated based on the file information. It can be implemented as follows: obtain the file to be operated based on the file information, perform the operation to be performed on the file to be operated through the file processing function of the operating system, and obtain the operation result.

[0105] The file management client can check whether it has the file to be operated based on the file information. If so, it obtains the file to be operated. If not, it obtains the file to be operated from the cloud. After that, the file management client calls the file processing API of the operating system corresponding to the operation to be performed, so that the operating system performs the operation to be performed on the file to be operated and obtains the operation result.

[0106] The file management client pre-records the correspondence between each simple operation and the file processing API of the operating system, so that after the subsequent file management client determines the operation to be executed, it can obtain the file processing API corresponding to the operation to be executed based on the correspondence. For example, the operation of scanning a picture and generating a document corresponds to the ASR API of the operating system, and the operation of recognizing a voice and generating a document corresponds to the OCR API of the operating system.

[0107] Through the above method, the embodiment of the present disclosure can utilize the native file processing capabilities of the operating system to perform operations on the files to be operated without using the cloud to perform file operations, thereby avoiding the impact of network delays on obtaining operation results and improving the speed of obtaining operation results. Moreover, since there is no need to use the cloud to perform file operations, the files to be operated do not need to be uploaded to the cloud, that is, the files to be operated can be files stored in the terminal, thereby avoiding data leakage problems that may occur during the file upload process, protecting the user's data privacy, and improving the security of file processing. In addition, with the development of AI technology, the native file processing capabilities of the operating system have a high degree of accuracy and can meet the needs of file operations in most scenarios. Therefore, the embodiment of the present disclosure improves the efficiency and accuracy of file management.

[0108] In the disclosed embodiment, the file management client may support a conversation function in addition to the file management function. That is, the above instruction text may not be used to instruct file management, but may be used to request recommendations, request document generation, ask questions, or chat. In this case, after the file management client inputs the instruction text into a preset natural language processing model, the natural language processing model cannot obtain the file information of the file to be operated or the operation to be performed from the instruction text.

[0109] At this time, if the file management client does not obtain the file information of the file to be operated or the operation to be performed, it sends the instruction text to the cloud, so that the cloud inputs the instruction text into the large language model and obtains the answer text output by the large language model. Then the file management client receives the answer text sent by the cloud and displays the answer text.

[0110] For example, Figure 8A display interface 800 of a file management client is shown. Assume that the file management client detects that a user clicks on a voice input control 201, and obtains a command text through the voice recognition function of the operating system: "Please help me write a short essay about the beautiful spring scenery, the location is in the botanical garden, no less than 50 words", and then displays the command text in the command display control 208. After that, the file management client inputs the command text into the natural language processing model, and at this time, the file information of the file to be operated or the operation to be performed is not obtained. Therefore, the file management client sends the command text to the cloud, and the cloud generates an answer text of the command text using a large language model: "In spring, ..., the botanical garden also becomes very beautiful." and returns the answer text, and then the file management client displays the answer text in the answer display control 209. Figure 8 The functions of other controls in the can refer to the above description and will not be repeated here.

[0111] Through the above method, the cloud management client not only supports the file management function, but also supports other dialogue functions, so that the application scenarios supported by the embodiment of the present disclosure are richer and the user experience is improved.

[0112] See also Fig. 9 The following is an example of the overall process of the file management method provided by the embodiment of the present disclosure in combination with actual application scenarios:

[0113] S901. When the file management client detects that the user clicks the voice input control in the display interface, the file management client calls the ASR API of the operating system of the terminal where the file management client is located.

[0114] S902: The operating system monitors the voice uttered by the user, and performs voice conversion on the monitored voice to obtain a command text.

[0115] S903: The operating system sends a command text to the file management client.

[0116] S904: The file management client inputs the instruction text into a natural language processing model, and obtains file information of the operation file and the operation to be executed output by the natural language processing model.

[0117] S905: The file management client sends a file processing request to the cloud, wherein the file processing request includes file information and operations to be performed.

[0118] S906. The cloud determines the file to be operated based on the file information, and performs the operation to be performed on the file to be operated to obtain the operation result.

[0119] S907: The cloud sends the operation result to the file management client.

[0120] S908. The file management client displays the operation result.

[0121] The disclosed embodiments can not only utilize the native AI function of the terminal operating system to perform voice recognition or simple file operations, but also utilize the file processing function of the cloud to perform complex file operations, thereby combining the advantages of the operating system and the cloud, allowing the file management client to provide richer file management operations and improving the user experience.

[0122] In the technical solution disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of the file information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0123] Based on the same inventive concept, corresponding to the above method embodiment, the present disclosure embodiment also provides a file management device, such as Fig.10 As shown, the device includes: a conversion module 1001, a determination module 1002, an acquisition module 1003 and a display module 1004;

[0124] The conversion module 1001 is used to monitor the voice of the user through the voice recognition function of the operating system when detecting that the user triggers the voice input command, and perform voice conversion on the monitored voice to obtain the command text;

[0125] The determination module 1002 is used to determine the file information of the file to be operated and the operation to be performed based on the instruction text obtained by the conversion module 1001;

[0126] An acquisition module 1003 is used to acquire an operation result obtained by performing the operation to be performed on the file to be operated based on the file information determined by the determination module 1002;

[0127] The display module 1004 is used to display the operation result obtained by the obtaining module 1003.

[0128] In some embodiments of the present disclosure, the determining module 1002 is specifically configured to:

[0129] Using a preset natural language processing model, based on the instruction text, the file information of the file to be operated and the operation to be performed are determined.

[0130] In some embodiments of the present disclosure, the determining module 1002 is specifically configured to:

[0131] Input the instruction text into the natural language processing model to obtain the file data and operations to be executed output by the natural language processing model;

[0132] If the file data is a preset text, the file information of the file displayed in the current page is used as the file information of the file to be operated;

[0133] If the file data is not a preset text, the file data is used as the file information of the file to be operated.

[0134] In some embodiments of the present disclosure, the file information includes at least one metadata, and the operation to be performed is a search operation; the acquisition module 1003 is specifically used to:

[0135] Searching for a target metadata set matching the file information from the metadata sets of each stored file;

[0136] Get the file to be operated corresponding to the target metadata collection.

[0137] In some embodiments of the present disclosure, the acquisition module 1003 is specifically used to:

[0138] Sending a file processing request to the cloud, the file processing request including file information and the operation to be performed, so that the cloud determines the file to be operated based on the file information, and performs the operation to be performed on the file to be operated to obtain the operation result;

[0139] Receive operation results sent by the cloud.

[0140] In some embodiments of the present disclosure, the acquisition module 1003 is specifically used to:

[0141] Obtain the file to be operated based on the file information;

[0142] Through the file processing function of the operating system, the operation to be executed is performed on the file to be operated to obtain the operation result.

[0143] In some embodiments of the present disclosure, the device further comprises:

[0144] A sending module, configured to send the instruction text to the cloud after inputting the instruction text into the natural language processing model, if the file information of the file to be operated or the operation to be performed is not obtained, so that the cloud inputs the instruction text into the large language model to obtain the answer text output by the large language model;

[0145] The receiving module is used to receive the answer text sent by the cloud and display the answer text.

[0146] In some embodiments of the present disclosure, the acquisition module 1003 is further used to:

[0147] Before determining the file information of the file to be operated and the operation to be performed based on the instruction text, when it is detected that the user triggers a keyboard input instruction, the instruction text input by the user through the keyboard is obtained through the keyboard input function of the operating system.

[0148] In some embodiments of the present disclosure, the determination module 1002 is also used to: before determining the file information of the file to be operated and the operation to be performed based on the instruction text, when it is detected that the user triggers the template to input the instruction, use the text corresponding to the template triggered by the user as the instruction text.

[0149] In some embodiments of the present disclosure, the device further comprises:

[0150] The recognition module is used to determine the file information of the file to be operated and the operation to be performed based on the instruction text, and when it is detected that the user triggers the image scanning input instruction, recognize the instruction text in the picture selected by the user through the optical character recognition function of the operating system.

[0151] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0152] Fig.11 A schematic block diagram of an example electronic device 1100 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0153] like Fig.11 As shown, the electronic device 1100 includes a computing unit 1101, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1102 or a computer program loaded from a storage unit 1108 into a random access memory (RAM) 1103. In the RAM 1103, various programs and data required for the operation of the electronic device 1100 can also be stored. The computing unit 1101, the ROM 1102, and the RAM 1103 are connected to each other via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0154] Multiple components in the electronic device 1100 are connected to the I / O interface 1105, including: an input unit 1106, such as a keyboard, a mouse, etc.; an output unit 1107, such as various types of displays, speakers, etc.; a storage unit 1108, such as a disk, an optical disk, etc.; and a communication unit 1109, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1109 allows the electronic device 1100 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0155] The computing unit 1101 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1101 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 1101 performs the various methods and processes described above, such as a file management method. For example, in some embodiments, the file management method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 1108. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 1100 via ROM 1102 and / or communication unit 1109. When the computer program is loaded into RAM 1103 and executed by the computing unit 1101, one or more steps of the file management method described above may be performed. Alternatively, in other embodiments, the computing unit 1101 may be configured to perform the file management method in any other appropriate manner (e.g., by means of firmware).

[0156] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0157] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0158] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0159] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0160] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0161] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0162] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0163] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A file management method, include: When a user triggers a voice input command, the voice recognition function of the operating system is used to monitor the voice of the user, and the monitored voice is converted into a command text; Based on the instruction text, determine the file information of the file to be operated and the operation to be performed; Based on the file information, obtaining an operation result obtained by performing the operation to be performed on the file to be operated; The operation result is displayed.

2. The method according to claim 1, in, The determining, based on the instruction text, file information of the file to be operated and the operation to be performed includes: Using a preset natural language processing model, based on the instruction text, the file information of the file to be operated and the operation to be performed are determined.

3. The method according to claim 2, in, The using a preset natural language processing model to determine the file information of the file to be operated and the operation to be performed based on the instruction text includes: Inputting the instruction text into the natural language processing model to obtain the file data output by the natural language processing model and the operation to be executed; If the file data is a preset text, the file information of the file displayed in the current page is used as the file information of the file to be operated; If the file data is not the preset text, the file data is used as the file information of the file to be operated.

4. The method according to any one of claims 1 to 3, in, The file information includes at least one metadata, and the operation to be performed is a search operation; and obtaining an operation result obtained by performing the operation to be performed on the file to be operated based on the file information includes: Searching for a target metadata set matching the file information from the metadata sets of each stored file; Obtain the file to be operated corresponding to the target metadata set.

5. The method according to any one of claims 1 to 3, in, The acquiring, based on the file information, an operation result obtained by performing the operation to be performed on the file to be operated, includes: Sending a file processing request to the cloud, the file processing request including the file information and the operation to be performed, so that the cloud determines the file to be operated based on the file information, and performs the operation to be performed on the file to be operated to obtain an operation result; Receive the operation result sent by the cloud.

6. The method according to any one of claims 1 to 3, in, The acquiring, based on the file information, an operation result obtained by performing the operation to be performed on the file to be operated, includes: Acquire the file to be operated based on the file information; The operation to be performed is performed on the file to be operated through the file processing function of the operating system to obtain an operation result.

7. The method according to claim 3, after inputting the instruction text into the natural language processing model, further comprising: include: If the file information of the file to be operated or the operation to be performed is not obtained, sending the instruction text to the cloud, so that the cloud inputs the instruction text into the large language model to obtain the answer text output by the large language model; Receive the answer text sent by the cloud, and display the answer text.

8. The method according to any one of claims 1 to 7, before determining the file information of the file to be operated and the operation to be performed based on the instruction text, further comprising: include: When it is detected that the user triggers a keyboard input instruction, the instruction text input by the user through the keyboard is obtained through the keyboard input function of the operating system.

9. The method according to any one of claims 1 to 7, before determining the file information of the file to be operated and the operation to be performed based on the instruction text, further comprising: include: When it is detected that a user triggers a template input instruction, the text corresponding to the template triggered by the user is used as the instruction text.

10. The method according to any one of claims 1 to 7, before determining the file information of the file to be operated and the operation to be performed based on the instruction text, further comprising: include: When it is detected that the user triggers an image scanning input instruction, the instruction text in the picture selected by the user is recognized through the optical character recognition function of the operating system.

11. A file management device, include: The conversion module is used to monitor the voice of the user through the voice recognition function of the operating system when detecting that the user triggers the voice input command, and perform voice conversion on the monitored voice to obtain the command text; A determination module, used to determine file information of a file to be operated and an operation to be performed based on the instruction text obtained by the conversion module; An acquisition module, configured to acquire, based on the file information determined by the determination module, an operation result obtained by performing the operation to be performed on the file to be operated; A display module is used to display the operation result obtained by the obtaining module.

12. The device according to claim 11, in, The determination module is specifically used for: Using a preset natural language processing model, based on the instruction text, the file information of the file to be operated and the operation to be performed are determined.

13. The device according to claim 12, in, The determination module is specifically used for: Inputting the instruction text into the natural language processing model to obtain the file data output by the natural language processing model and the operation to be executed; If the file data is a preset text, the file information of the file displayed in the current page is used as the file information of the file to be operated; If the file data is not the preset text, the file data is used as the file information of the file to be operated.

14. The device according to any one of claims 11 to 13, in, The file information includes at least one metadata, the operation to be performed is a search operation; and the acquisition module is specifically used to: Searching for a target metadata set matching the file information from the metadata sets of each stored file; Obtain the file to be operated corresponding to the target metadata set.

15. The device according to any one of claims 11 to 13, in, The acquisition module is specifically used for: Sending a file processing request to the cloud, the file processing request including the file information and the operation to be performed, so that the cloud determines the file to be operated based on the file information, and performs the operation to be performed on the file to be operated to obtain an operation result; Receive the operation result sent by the cloud.

16. The device according to any one of claims 11 to 13, in, The acquisition module is specifically used for: Acquire the file to be operated based on the file information; The operation to be performed is performed on the file to be operated through the file processing function of the operating system to obtain an operation result.

17. The device according to claim 13, further comprising: include: A sending module, configured to send the instruction text to the cloud if the file information of the file to be operated or the operation to be performed is not obtained after the instruction text is input into the natural language processing model, so that the cloud inputs the instruction text into the large language model to obtain the answer text output by the large language model; The receiving module is used to receive the answer text sent by the cloud and display the answer text.

18. The device according to any one of claims 11 to 17, wherein the acquisition module is further configured to: Before determining the file information of the file to be operated and the operation to be performed based on the instruction text, when it is detected that the user triggers a keyboard input instruction, the instruction text input by the user through the keyboard is obtained through the keyboard input function of the operating system.

19. The apparatus according to any one of claims 11 to 17, wherein the determining module is further configured to: Before determining the file information of the file to be operated and the operation to be performed based on the instruction text, when it is detected that a user triggers a template to input an instruction, the text corresponding to the template triggered by the user is used as the instruction text.

20. The device according to any one of claims 11 to 17, further comprising: include: The recognition module is used to recognize the instruction text in the picture selected by the user through the optical character recognition function of the operating system when it is detected that the user triggers the image scanning input instruction before determining the file information of the file to be operated and the operation to be performed based on the instruction text.

21. An electronic device, include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 10.

22. A non-transitory computer-readable storage medium storing computer instructions, in, The computer instructions are used to cause the computer to execute the method according to any one of claims 1-10.

23. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 10.

Citation Information

Patent Citations

  • Network disk searching method based on intelligent voice and related products

    CN111241235A

  • File management method, cloud file management system and terminal

    CN111475467A

  • File operation method and system based on voice recognition and mobile terminal

    CN111782600A

  • Voice control method and device, electronic equipment and storage medium

    CN115762509A

  • Intelligent file processing system based on large language model and processing method thereof

    CN117668231A

Cited By

  • File interaction method and device, equipment, medium and product

    CN122331805A