File processing method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a file processing method and device, electronic equipment and a storage medium. The file processing method comprises the steps of determining a target style according to related information of a first file; increment information with the target style is generated, and the increment information is enhanced content different from the file content of the first file.

Description

Technical Field

[0001] The present disclosure relates to but is not limited to the field of file processing technology, and in particular to a file processing method and device, an electronic device and a storage medium. Background Art

[0002] With the continuous development of computer technology or Internet technology, the use of electronic files to handle work, life and other matters has become increasingly indispensable.

[0003] Electronic files may generally include but are not limited to presentation files, document files and / or spreadsheet files. Presentation files are generally used for presentations; document files are generally used to record information in the form of text and / or images; spreadsheet files can generally record information in the form of spreadsheets.

[0004] Currently, when an electronic file is displayed or played, the content of the electronic file is usually directly displayed or played, or the content related to the content of the electronic file is displayed or played. The electronic file content or the related content of the electronic file displayed or played is relatively fixed and single. For example, different content will not be displayed or played according to different scenarios and / or different audiences, which brings a bad experience to users. Summary of the invention

[0005] Embodiments of the present disclosure provide a file processing method and device, an electronic device, and a storage medium.

[0006] A first aspect of an embodiment of the present disclosure provides a file processing method, the method comprising:

[0007] Determine the target style based on the relevant information of the first file;

[0008] Incremental information having the target style is generated, wherein the incremental information is enhanced content different from the file content of the first file.

[0009] In some embodiments, determining the target style according to the relevant information of the first file includes:

[0010] The target style is determined according to at least one relevant information of the first file; wherein the relevant information includes at least one of the following: file content of the first file, audience information of the first file, and display scene information of the first file.

[0011] In some embodiments, determining the target style according to at least one relevant information of the first file includes:

[0012] In response to acquiring the plurality of related information of the first file, determining the priority of the plurality of related information;

[0013] The target style is determined according to the priority and the plurality of related information.

[0014] In some embodiments, determining the target style according to the priority and the plurality of related information includes:

[0015] Determining relevant weights according to the priorities of the plurality of relevant information;

[0016] Determining a style value according to the relevant weights and style parameters corresponding to the relevant information;

[0017] The target style is determined according to the style value.

[0018] In some embodiments, generating incremental information having the target style includes:

[0019] Pre-generate multiple incremental information applicable to multiple alternative display scenarios;

[0020] From the plurality of pre-generated incremental information, the incremental information adapted to the current target presentation scenario is selected for output.

[0021] In some embodiments, generating incremental information having the target style includes:

[0022] Generating the incremental information having the target style in the file content of the first file;

[0023] or,

[0024] A second file is generated containing the incremental information.

[0025] In some embodiments, the method further includes: storing the first file and the second file in association with each other.

[0026] In some embodiments, the method further comprises:

[0027] In response to detecting a start-up operation acting on the first file, displaying the first file on a document interface;

[0028] Determine whether to start the second file synchronously.

[0029] In some embodiments, the determining whether to synchronously start the second file includes:

[0030] In response to detecting a designated operation when starting the first file, determining to synchronously start the second file; wherein the designated operation includes: a confirmation operation acting on a prompt information displayed when the first file is started, or a user operation acting on a preset space in the first file;

[0031] or,

[0032] According to the startup status of the first file, it is determined whether to synchronously start the second file.

[0033] In some embodiments, determining whether to synchronously start the second file according to the start status of the first file includes at least one of the following:

[0034] In response to the first file being in a multi-file association preview mode, determining to synchronously start the second file;

[0035] In response to the first file being in the associated play mode, determining to synchronously start the second file;

[0036] In response to the first file entering an editing mode, it is determined to synchronously start the second file.

[0037] In some embodiments, generating incremental information having the target style includes:

[0038] Determining first content of the incremental information according to the file content of the first file;

[0039] Adjusting the text description of the first content to obtain second content with the target style;

[0040] The incremental information is obtained according to the second content and the type of the incremental information.

[0041] In some embodiments, obtaining the incremental information based on the second content and the type of the incremental information also includes: in response to the incremental information being a text type, inserting the second content into the first file or generating a second file containing the second content to obtain the incremental information.

[0042] In some embodiments, the incremental information of the text type includes at least one of the following:

[0043] Annotation information of the first file;

[0044] The remark information of the first file;

[0045] comment information of the first file;

[0046] the speech of the first document;

[0047] Barrage information of the first file;

[0048] Subtitle information presented by the first file;

[0049] The first file demonstrates the narration information.

[0050] In some embodiments, obtaining the incremental information according to the second content and the type of the incremental information further includes: in response to the incremental information being of an audio type, generating audio information that expresses the second content with audio parameters of the target style.

[0051] In some embodiments, obtaining the incremental information according to the second content and the type of the incremental information includes:

[0052] In response to the incremental information being a video type, generating a speech object having the target style;

[0053] According to the target style, video information of the speaker delivering a speech on the second content is generated.

[0054] A second aspect of an embodiment of the present disclosure provides a document processing device, the device comprising:

[0055] A determination module, used to determine a target style according to relevant information of the first file;

[0056] The processing module is used to generate incremental information having the target style, wherein the incremental information is enhanced content different from the file content of the first file.

[0057] A third aspect of the present disclosure provides an electronic device, including:

[0058] processor;

[0059] a memory for storing processor-executable instructions;

[0060] Wherein, the processor is configured to: implement any file processing method described in the first aspect when running the executable instructions.

[0061] A fourth aspect of an embodiment of the present disclosure provides a computer-readable storage medium, wherein the computer-readable storage medium stores an executable program, wherein when the executable program is executed by a processor, the file processing method described in any of the first aspects is implemented.

[0062] In the disclosed embodiment, the target style can be determined based on the relevant information of the first file, and incremental information with the target style can be generated. In this way, appropriate incremental information of the target style can be determined for the first file, which is conducive to realizing personalized display or playback of the first file, thereby improving user experience satisfaction.

[0063] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0065] Figure 1 The figure is a flowchart of a file processing method according to an exemplary embodiment.

[0066] Figure 2 The present invention is an intention of a file display interface shown according to an exemplary embodiment.

[0067] Figure 3 The figure is a flowchart of a file processing method according to an exemplary embodiment.

[0068] Figure 4 The present invention is an intention of a file display interface shown according to an exemplary embodiment.

[0069] Figure 5 The figure is a flowchart of a file processing method according to an exemplary embodiment.

[0070] Figure 6 The figure is a schematic diagram showing a virtual person giving a speech according to an exemplary embodiment.

[0071] Figure 7 The figure is a schematic diagram showing the structure of a file processing device according to an exemplary embodiment.

[0072] Figure 8 The diagram is a schematic structural diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0073] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the embodiments of the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the embodiments of the present disclosure as detailed in the appended claims.

[0074] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0075] like Figure 1 As shown, the present disclosure provides a file processing method, comprising the following steps:

[0076] 11: Determine the target style based on the relevant information of the first file;

[0077] 12: Generate incremental information with a target style, wherein the incremental information is enhanced content that is different from the file content of the first file.

[0078] The file processing method provided by the embodiment of the present disclosure may be executed by an electronic device, which may include various terminals or server ends. For example, the electronic device may include but is not limited to at least one of the following: a mobile phone, a computer, a tablet computer, a smart wearable device, a vehicle-mounted device, a smart home device, and a smart office device. For example, the server end may be an application server that generates a target application.

[0079] In some embodiments, the first file may be a file of various types; for example, the first file may be a presentation file, a document file, and / or a spreadsheet file. Exemplarily, the presentation file may be a slide; the slide may be one or more, etc. Exemplarily, the document file may be a WORD file, a WPS file, and / or a PDF file, etc. Exemplarily, the spreadsheet file may be an EXCEL file, etc.

[0080] In some embodiments, the target style can be various types of document styles and / or speech styles. For example, the target style can include but is not limited to at least one of the following: formal style or informal style, humorous style or non-humorous style, funny style or solemn style, gentle style, deep style, lively style, and exciting style.

[0081] In some embodiments, the target style may include at least one of the following: a timbre style, a volume style, and a pitch style. For example, the timbre style may be a style of various types of timbre, such as a low, high, soft, delicate, or crisp style. For example, the volume style may be a style of various volume sizes, such as a volume greater than or equal to a predetermined decibel. For example, the pitch style may be a style of various types of tones, such as a high-pitched style, a low-pitched style, an ethereal style, or a rough style.

[0082] In some embodiments, the relevant information of the first file may include at least one of the following: the file content of the first file, the audience information of the first file, and the display scene information of the first file. Exemplarily, the audience information is used to describe the audience (or viewer); for example, the audience information may include but is not limited to the age, gender, and identity of the audience (or viewer). Exemplarily, the display scene information is used to describe the display scene; for example, the display scene may be a serious scene, a heavy scene, an active scene, a formal scene, or an informal scene.

[0083] In some embodiments, step 11 includes: determining a target style based on at least one relevant information of the first file; wherein the relevant information includes at least one of the following: file content of the first file, audience information of the first file, and display scene information of the first file.

[0084] For example, if the audience information is that the audience is children, the style can be determined as lively; if the audience information is that the audience is the leaders of public institutions, the style can be determined as formal; if the display scene information is that the display scene is a government report, the style can be determined as formal; if the display scene is the elderly, the style can be determined as humorous; if the document content describes a happy New Year's Day, the style can be determined as lively; if the document content describes a memorial service for a hero, the style can be determined as solemn; for example, if the audience information is that the audience is children, the voice can be determined as gentle; if the audience information is that the audience is company employees, the voice can be determined as deep; and so on.

[0085] In some embodiments, step 11 includes: analyzing relevant information of the first file according to preset rules to determine the target style.

[0086] Optionally, the preset rule is used to indicate: a correspondence between at least one of the file content of the first file, the audience information of the first file, and the display scene of the first file and the target style.

[0087] In this way, the target style corresponding to the first file can be accurately determined according to the relevant information of the first file and the preset rules.

[0088] In some other embodiments, step 11 includes: analyzing relevant information of the first file according to a preset classification model to determine the target style.

[0089] Optionally, the preset classification model may be a model that has been trained to classify the target style of the first file; if the relevant information of the first file is input into the preset classification model, a classification of the target style of the first file may be obtained.

[0090] In this way, the target style of the first file can be automatically classified through the preset classification model to accurately determine the target style of the first file, and the intelligence can also be improved.

[0091] Exemplarily, the incremental information may be various types of enhanced content. For example, the incremental information may include: text type, audio type and / or video type. Exemplarily, the video type includes audio type and / or image type.

[0092] In some embodiments, the text-type incremental information may include at least one of the following: annotation information of the first file; remark information of the first file; comment information of the first file; speech of the first file; barrage information of the first file; subtitle information of the first file demonstration; and narration information of the first file demonstration. Exemplarily, the annotation information of the first file may be the remark information of the first file.

[0093] Exemplarily, the annotation information of the first file may be opinions and / or suggestions on the file content of the first file, etc. The remark information of the first file may be the remarks and / or prompt words of the speaker of the first file, etc.

[0094] Exemplarily, if the first file is a presentation file, such as a slide show, the incremental information may be the speech of the presentation file; if the first file is a document file, such as a review of a certain delicacy, the incremental information may be the comment information or barrage information of the document file; if the first file is a document file, such as a script of a certain drama, the incremental information may be the comment information or narration information; and so on.

[0095] Of course, the above is only an example of the first file and the corresponding incremental information, and the specific implementation is not limited to this example.

[0096] In the disclosed embodiment, the target style can be determined based on the relevant information of the first file; and incremental information with the target style can be generated. In this way, the incremental information of the appropriate target style can be determined for the first file, which is conducive to realizing personalized display or playback of the first file, thereby improving the satisfaction of the user experience. In some embodiments, before step 11, it includes: detecting natural language input acting on the conversation panel, determining the relevant information of the first file; the relevant information includes audience information and / or display scene information.

[0097] For example, Figure 2 As shown, in Figure 2 A document interface is displayed on the left side and a conversation panel is displayed on the right side. In the file interface, a presentation file can be displayed. In the conversation panel, an AI dialogue based on conversational language can be conducted. The AI ​​dialogue can be conducted by an AI model in natural language. For example, an input box is set in the conversation panel, and natural language can be entered in the input box; the AI ​​model in the electronic device can conduct a conversation by detecting the natural language entered in the input box. The natural language can describe the audience information and / or display scene information of the first file; for example, the natural language can be "a group of children participated", or "the participants are employees of Company A", etc.

[0098] In this way, the relevant information of the first file can be determined by the user inputting natural language in the conversation panel, which is conducive to determining the incremental information of the appropriate target style.

[0099] In some embodiments, before step 11, the process includes: analyzing the file content of the first file to determine the relevant information of the first file. Exemplarily, the electronic device analyzes the file content of the first file through an AI model to determine the relevant information of the first file.

[0100] In some embodiments, step 12 includes: analyzing the file content of the first file to generate incremental information with a target style. Exemplarily, the electronic device can analyze the file content of the first file through an AI model to generate incremental information with a target style.

[0101] The aforementioned AI model can be run on a terminal (or electronic device) or on a server, etc. An exemplary electronic device receives and obtains a first file, and puts the first file into a local AI model for processing; or sends the first file to a server, and the AI ​​model in the server performs various tasks on the first file, and then returns the result to the electronic device.

[0102] The aforementioned AI model may be various neural network models and / or machine learning models. For example, the AI ​​model may be, but is not limited to, a convolutional neural network (CNN) model, a recurrent neural network (RNN) model, a deep neural network (DNN) model, a large language model (LLM) or a large-scale language model, etc.

[0103] In some embodiments, determining the target style according to at least one relevant information of the first file includes:

[0104] In response to acquiring the plurality of related information of the first file, determining the priority of the plurality of related information;

[0105] Determine the target style based on priorities and multiple related information.

[0106] In some embodiments, determining the target style according to the priority and the multiple related information includes: determining the target style according to the candidate style corresponding to the related information with the highest priority among the multiple related information.

[0107] For example, the display scene information corresponds to the first priority; the audience information corresponds to the second priority; the file content corresponds to the third priority; the first priority is higher than the second priority, and the second priority is higher than the third priority. In this way, the display scene information can be given priority in determining the target style in some scenes, so that the appropriate target style in these scenes can be determined.

[0108] For example, the display scene information corresponds to the first priority; the audience information corresponds to the second priority; the file content corresponds to the third priority; the second priority is higher than the first priority, and the first priority is higher than the third priority. In this way, the audience information can be given priority in determining the target style in some scenes, so that the appropriate target style in these scenes can be determined.

[0109] Of course, in other examples, the third priority may be higher than the first priority, and the first priority may be higher than the second priority; or the third priority may be higher than the second priority, and the second priority may be higher than the first priority. In this way, in some scenarios, the target style may be determined by giving priority to the file content, so as to determine the appropriate target style in these scenarios.

[0110] In the disclosed embodiment, an alternative style corresponding to the priority information may be selected to determine a target style, so that a suitable target style may be determined according to which relevant information is relatively important, to adapt to scenarios where various relevant information has different importance.

[0111] In some embodiments, the target style is determined based on the priority and multiple related information, including:

[0112] Determine relevant weights according to the priorities of multiple relevant information;

[0113] Determine the style value according to the relevant weights and the style parameters corresponding to the relevant information;

[0114] Determine the target style based on the style value.

[0115] Exemplarily, determining the target style according to the style value includes: determining the target style according to a highest style value among multiple style values.

[0116] Exemplarily, if the priority of the audience information is higher than the priority of the display scene information, and the priority of the display scene information is higher than the priority of the file content, the priority of the audience information, the priority of the display scene information, and the priority of the file content can be determined to be 0.6, 0.3, and 0.1, respectively. If the style parameters of the formal style corresponding to the audience information, the display information, and the file content are 6, 6, and 4, respectively, and the style parameters of the informal style corresponding to the audience information, the display information, and the file content are 4, 4, and 6, respectively; then the style value of the formal style can be determined to be 0.6×6+0.3×6+0.1×4=5.8, and the style value of the informal non-style can be determined to be 0.6×4+0.3×4+0.1×6=4.2; the style parameter of the formal style is greater than the style parameter of the informal style, and the target style is determined to be the formal style.

[0117] In the above embodiment, more relevant parameters of the relevant information corresponding to more styles may be set, and the comparison may be made based on the style parameters of more styles; the above is only an exemplary example.

[0118] In the embodiment of the present disclosure, the target style may be determined based on the priorities of multiple related information and style parameters corresponding to the styles of multiple related parameters, so that a suitable target style may be determined based on overall considerations.

[0119] In some embodiments, one piece of related information may correspond to one piece of incremental information. The first file may generate different incremental information according to different related information.

[0120] In some embodiments, the incremental information with the target style is generated in step 12, including: generating the incremental information with the target style based on the AI ​​model.

[0121] Exemplarily, an AI model is first trained, such as an artificial intelligence content generator (AIGC), to generate incremental information with a target style based on the relevant information of the first file. Training an AI model (such as an AIGC model) includes at least one of the following steps:

[0122] Step 21, collect data. Collect data containing incremental information of the target style corresponding to the prompt word. The prompt word may be composed of the first information of the first file; or the prompt word may be composed of the first information and the second information of the first file. The first information may include the file content, audience information, display scene information, display purpose information and / or playback duration of the first file. The second information may be information indicating the generation of incremental information for at least part of the content in the first file; for example, the second information may be the generation of incremental information for the first page or the first content of the first file, etc. The prompt word can be used as a text prompt (or "instruction text") input to the AI ​​model.

[0123] Step 22: Prepare the data set. Organize the collected data into a data set for training. This ensures that the data set contains the input prompt words and the corresponding expected output.

[0124] Step 23: Build a model. Select a suitable machine learning model, such as a recurrent neural network (RNN) or a transformer model, and build the model structure according to the characteristics of the data set. The input of the model can be an instruction text; the output is the corresponding operation or response generated by the model. Exemplarily, the model is an AI model or an AIGC. Exemplarily, the input of the model can be a prompt word; the output of the model can be the generated incremental information.

[0125] Step 24: Train the model. Use the prepared dataset to train the model. By inputting prompt words into the model and comparing them with the expected output, the model parameters are continuously adjusted to improve its performance.

[0126] Step 25: Evaluate and tune the model. Use the test data to evaluate the trained model and check the accuracy and performance of the model when processing different prompt words. Based on the evaluation results, tune and improve the model.

[0127] Step 26: Deploy and apply the model. Once the model training is completed and meets the requirements, it is deployed to the corresponding platform or application so that the corresponding operation or response can be obtained by inputting the prompt word. Exemplarily, the model is deployed to an electronic device or to a server that has a communication connection with the electronic device; the electronic device can determine the prompt word according to the first information of the first file, etc., and input the prompt word into the model to output the incremental information corresponding to the prompt word.

[0128] In some embodiments, based on the AI ​​model, incremental information with a target style is generated, including: generating prompt words according to the first information of the first file; inputting the prompt words into the AI ​​model to generate incremental information; wherein the first information includes one of the following: the file content of the first file, the audience information of the first file, the display scene information of the first file, the display purpose information of the first file, and the playback time of the first file. Optionally, the AI ​​model is the AIGC model in the above embodiment, etc.

[0129] Optionally, the prompt word includes a first part; the first part is a part related to the first information of the first file. Exemplarily, the electronic device generates a prompt word including the first part according to the file content, audience information, display scene and / or playback time of the first file, which may be "My target audience is company employees, the display scene is a formal scene and the playback time is 1 hour. Please generate incremental information of the first file according to the above content."

[0130] Optionally, the prompt word includes a first part and a second part; the first part is a part related to the first information of the first file; the second part is a part related to the second information of the first file. Exemplarily, the electronic device generates a prompt word including the first part and the second part according to the file content, audience information, display scene and / or playback time of the first file, which may be "My audience is company employees, the display scene is a formal scene and the playback time is 1 hour. Please generate incremental information for the first page of the first file according to the above content", wherein "Please generate incremental information for the first page of the first file according to the above content" is the second part of the prompt word.

[0131] Thus, in the embodiment of the present disclosure, prompt words may be input into the AI ​​model to generate incremental information having a target style, thereby enabling automatic generation of incremental information of the target style of the first file.

[0132] Furthermore, prompt words can be generated based on first information such as the file content, display scene information and / or playback duration of the first file, so as to facilitate the generation of incremental information of the target style of the first file. Alternatively, prompt words can be generated based on the first information and second information indicating which part of the content of the first file to generate incremental information for, so as to facilitate the generation of incremental information of the target style for different contents of the first file, and to achieve flexible generation of incremental information of the target style of the first file.

[0133] In some embodiments, the method further includes: storing corresponding incremental information and prompt words of the target style.

[0134] Exemplarily, the incremental information of a style corresponds to a prompt word; the prompt word is preset or generated according to the AI ​​model. For example, the electronic device generates a prompt word according to the first information of the first file, or generates a prompt word according to the first information and the second information of the first file; and inputs the prompt word into the AI ​​model to generate incremental information of a style; the electronic device stores the incremental information of the style and the prompt word corresponding to the incremental information of the style in correspondence.

[0135] In this way, in the embodiment of the present disclosure, the incremental information and prompt words of the target style can be stored accordingly, so as to facilitate the subsequent acquisition of the corresponding incremental information of the target style according to the current prompt word.

[0136] like Figure 3 As shown, in some embodiments, generating incremental information with a target style in step 12 includes:

[0137] 1211: Pre-generate multiple incremental information applicable to multiple candidate display scenarios;

[0138] 1212: Select and output incremental information that is compatible with the current target display scenario from among the multiple incremental information generated in advance.

[0139] Exemplarily, both the candidate presentation scene and the target presentation scene may be the presentation scenes of the previous embodiments.

[0140] Exemplarily, one alternative presentation scenario may correspond to one incremental information.

[0141] In this way, different incremental information can be generated for the first file in different candidate display scenarios; so that when output or display is required, appropriate incremental information can be selected for output or display according to the current target display scenario.

[0142] In some embodiments, step 1211 includes: generating incremental information having a target style based on the file content of the first file; and adjusting the content in the incremental information based on multiple alternative display scenarios of the first file to generate incremental information corresponding to the multiple alternative display scenarios respectively.

[0143] Optionally, adjusting the content of the incremental information includes at least one of the following: adding the content of the incremental information, deleting the content of the incremental information, modifying the content of the incremental information, and adjusting the text description of the incremental information.

[0144] In this way, incremental information of the target style can be generated based on the file content of the first file, and then the incremental information can be adaptively adjusted according to multiple alternative display scenarios corresponding to the first file to generate incremental information that is compatible with the alternative display scenarios; in this way, suitable incremental information corresponding to the alternative display scenarios can be generated.

[0145] Of course, in other embodiments, it is not necessary to first generate incremental information based on the content of the first file and then adjust the incremental information according to different alternative display scenarios. Incremental information corresponding to the alternative display scenario can be directly generated based on the file content of the first file and the alternative display scenario. For example, step 1211 includes: based on the file content of the first file and the alternative display scenario, generating incremental information corresponding to the alternative display scenario; the incremental information corresponding to different alternative display scenarios has different partial contents and / or different content forms. For example, the content form of the incremental information can be annotation information, comment information, speech script, barrage information, subtitle information, or side information, etc.

[0146] In some other embodiments, step 1211 includes: based on a preset model, pre-generating a plurality of incremental information applicable to a plurality of alternative presentation scenarios.

[0147] Optionally, the preset model may be a trained model for generating incremental information for alternative display scenarios; the first file and multiple alternative display scenarios corresponding to the first file are input into the preset model to obtain incremental information corresponding to the multiple alternative display scenarios of the first file.

[0148] In this way, the embodiment of the present disclosure can analyze the first file in different alternative display scenarios through a pre-trained AI model to obtain appropriate incremental information in different alternative display scenarios; and determine the incremental information in different alternative scenarios based on the preset model, which can also improve the intelligence of obtaining incremental information.

[0149] In some embodiments, after step 1211, the method further includes: storing corresponding incremental information of at least one candidate presentation scene of the first file.

[0150] Exemplarily, the electronic device stores mapping information; the mapping information includes at least one alternative presentation scene of the first file and incremental information corresponding to the alternative scene.

[0151] Exemplarily, the electronic device stores the mapping information in a local database, or the electronic device sends the mapping information to a server or other device for storage.

[0152] In this way, the incremental information of the first file in different candidate presentation scenarios can be saved, which facilitates the subsequent determination of the incremental information for different presentation scenarios.

[0153] In some embodiments, step 1112 includes: determining and outputting incremental information of the candidate presentation scene that is the same as the target presentation scene from the plurality of incremental information generated in advance. Here, the incremental information of the candidate presentation scene that is the same as the target presentation scene is the incremental information adapted to the current target presentation.

[0154] Optionally, if the electronic device stores mapping information, the mapping information includes at least one alternative display scene of the first file and corresponding incremental information; after the current target display scene of the electronic device, based on the target display scene and the mapping information, the alternative display scene that is the same as the target display scene is determined as the first alternative display scene; and the incremental information corresponding to the first alternative display scene is determined as the incremental information of the target display scene.

[0155] In this way, the incremental information related to the current target display scene can be selected from the multiple incremental information of the multiple candidate display scenes for output, thereby meeting the current needs of the user and improving the user's experience satisfaction.

[0156] In some other embodiments, step 12 includes:

[0157] Pre-generate multiple incremental information applicable to multiple types of candidate audiences;

[0158] From the multiple pre-generated incremental information, select the incremental information output that is suitable for the current target audience.

[0159] Exemplarily, the candidate audiences and the target audience may be the audiences in the previous embodiments.

[0160] Exemplarily, one category of candidate audiences may correspond to one incremental information.

[0161] In this way, different incremental information can be generated for different audiences of the first file; so when output or display is required, appropriate incremental information can be selected for output or display according to the current target audience.

[0162] Optionally, pre-generating multiple incremental information applicable to multiple categories of alternative audiences is similar to pre-generating multiple incremental information applicable to multiple alternative display scenarios in the above embodiment; for example, based on the file content of the first file, incremental information with a target style can be generated; based on the multiple categories of alternative audiences of the first file, the content in the incremental information is adjusted to generate incremental information corresponding to the multiple categories of alternative audiences; for example, based on a preset model, multiple incremental information applicable to multiple categories of alternative audiences can be pre-generated; the preset model can be a trained incremental information generation model for alternative audiences; it will not be repeated here.

[0163] Optionally, selecting the incremental information output that is adapted to the current target audience from multiple pre-generated incremental information is similar to selecting the incremental information output that is adapted to the current target display scenario from multiple pre-generated incremental information; for example, the incremental information output of the alternative audience that is the same as the target audience can be determined from multiple pre-generated incremental information; this will not be repeated here.

[0164] In some embodiments, step 12 includes: generating incremental information having a target style based on the file content of the first file.

[0165] Exemplarily, when the electronic device detects natural language input acting on the conversation panel, the electronic device generates incremental information having the target text based on the natural language input and the file content of the first file; the natural language input indicates the generated incremental information.

[0166] Exemplarily, the electronic device generates incremental information having a target style based on the file content and related information of the first file.

[0167] Thus, in the disclosed embodiment, the incremental information corresponding to the first file can be determined based on the file content of the first file, the natural language input by the user and / or related information, etc.; thus, it is convenient to generate diversified incremental information with a target style.

[0168] In some embodiments, generating incremental information having a target style in step 12 includes:

[0169] Generate incremental information with a target style from the file content of the first file;

[0170] or,

[0171] A second file is generated containing the delta information.

[0172] For example, Figure 4 As shown, in Figure 4A document interface is displayed on the left side of the document, and the document interface displays the file content of the first file; incremental information with a target style is generated in the file content of the first file. For example, the file content of the first file can be covered with barrage information; for another example, comment information or annotation information can be generated in the blank space of the file content of the first file; for another example, the file content of the first file can be annotated with annotation information; and so on.

[0173] Exemplarily, the electronic device may also generate a second file including incremental information; for example, a second file including text-type incremental information, another example, a second file including audio-type incremental information, and another example, a second file including video-type incremental information.

[0174] Thus, in the disclosed embodiments, incremental information may be generated before the file content of the first file, or incremental information in the form of a file (e.g., a second file) may be generated, thereby realizing the generation of personalized incremental information. Furthermore, if incremental information is generated in the first file content, it may be convenient for users to feel the incremental information more intuitively, thereby improving user experience satisfaction. Alternatively, if a second file including incremental information is generated, it may be convenient to save incremental information of audio type or incremental information of video type, thereby reducing the probability of losing the incremental information; for incremental information of a larger document type, it may also reduce the probability of loss or reduce the probability of the file content of the first file not being displayed due to a large amount of text content.

[0175] In some embodiments, the method further includes: storing the first file and the second file in association with each other.

[0176] Exemplarily, the electronic device stores the first file and the second file in association with each other; for example, the first file and the second file are stored in the same folder; for another example, the second file is hyperlinked in the first file; and so on.

[0177] Exemplarily, the electronic device may store a first file in association with a plurality of second files.

[0178] In this way, the associated storage of the first file and the second file can be achieved, which is conducive to selecting appropriate incremental information or second information including incremental information under different audiences and / or different display scenarios.

[0179] In some embodiments, the method further comprises: displaying a file icon of the first file; or, displaying a file icon of the first file and a file icon of the second file;

[0180] The file icon of the first file is used to start the first file; the file icon of the second file is used to start the second file.

[0181] Exemplarily, displaying a file icon of a first file and a file icon of a second file includes one of the following: displaying the file icon of the first file and the file icon of the second file side by side and adjacent to each other; displaying the file icon of the first file and displaying the file icon of the second file at a predetermined position of the file icon of the first file.

[0182] Exemplarily, the distance between the file icon of the first file and the file icon of the second file is smaller than the distance between the file icon of the first file and the file icon of the third file; wherein the third file is irrelevant to the first file.

[0183] In this way, the first file and / or the second file can be conveniently started by displaying the file icon of the first file and / or the file icon of the second file. If the file icon of the first file and the file icon of the second file are displayed at the same time, it is also beneficial to realize the associated startup of the first file and the second file.

[0184] If the file icon of the first file and the file icon of the second file are associated and displayed adjacently, the file icon of the second file can be quickly found based on the first file icon, or the file icon of the first file can be quickly found based on the file icon of the second file, which is conducive to quickly starting the first file and the second file at the same time.

[0185] Furthermore, by further setting the distance between the file icon of the first file and the file icon of the second file to be smaller than the distance between the first file and other unrelated files, the file icon of the first file and the file icon of the second file can be displayed adjacent to each other, making it easier to find the other icon from one of the icons and to start the association between the first file and the second file.

[0186] In some embodiments, the method further comprises:

[0187] In response to detecting a start-up operation acting on the first file, displaying the first file on the document interface;

[0188] Determine whether to start the second file synchronously.

[0189] In some embodiments, determining whether to synchronously start the second file includes: in response to detecting a specified operation when starting the first file, determining to synchronously start the second file; wherein the specified operation includes: a confirmation operation acting on the prompt information displayed when the first file is started, or a user operation acting on a preset space within the first file.

[0190] For example, when the first file is started, the electronic device displays a prompt message, which is used to prompt whether to start the second file; if a confirmation operation acting on the prompt message is detected, it is determined to start the second file. The prompt message can be a pop-up window popped up on the session panel, and the pop-up window includes a first button and a second button; the first button is used to indicate to start the second file, and the second button is used to indicate not to start the second file.

[0191] Based on the above embodiment, if the electronic device does not detect a confirmation operation on the prompt information within a predetermined time, for example, does not detect an operation on the first file, then the second file is determined not to be started. Alternatively, if the electronic device detects an operation on the second button, then the second file is determined not to be started.

[0192] Optionally, the preset space may be any space for displaying the file content of the first file and / or a blank space in the first file, etc. For example, after the first file is started, if the electronic device detects a user operation on the preset space in the first file, such as clicking on the file content of the first file, selecting the file content of the first file, or clicking on the blank space in the first file, etc., it determines to start the second file.

[0193] In this way, it can be determined that the second file is started synchronously by detecting the designated operation, so that it can be accurately determined whether to start the second file.

[0194] In some embodiments, determining whether to synchronously start the second file includes: determining whether to synchronously start the second file according to the start status of the first file. For example, the start status includes but is not limited to at least one of the following: multi-file association preview mode, association play mode, and edit mode.

[0195] In some embodiments, determining whether to synchronously start the second file according to the start status of the first file includes at least one of the following:

[0196] In response to the first file being in a multiple-file association preview mode, determining to synchronously start the second file;

[0197] In response to the first file being in the associated play mode, determining to synchronously start the second file;

[0198] In response to the first file entering the edit mode, it is determined to synchronously start the second file.

[0199] If the electronic device determines that the first file and the second file need to be previewed in association, the electronic device determines to start reading the second file synchronously when the preview of the first file is started.

[0200] If the electronic device determines that the first file and the second file need to be played in association, the electronic device determines to start playing the second file synchronously when the first file starts to be displayed.

[0201] If the electronic device determines that the first file needs to be edited, then when the first file enters the editing mode, the second file is started synchronously but the second file is not triggered to enter the editing mode.

[0202] If the electronic device determines that the first file needs to be edited, it determines to synchronously start the second file and synchronously edit the second file when the first file enters the editing mode. For example, when the first file enters the editing mode, the second file is synchronously started to enter the editing mode; if the first part of the file content of the first file is edited, the incremental information corresponding to the first part in the second file is synchronously edited.

[0203] Of course, the above is merely an example for determining whether to start the second file synchronously, and the specific implementation is not limited to this example.

[0204] In this way, the second file can be automatically started, thereby facilitating user operation and improving user satisfaction.

[0205] Furthermore, when the first file is being edited, the second file can also be edited synchronously, so that the content of the second file can be changed as the content of the first file changes, thereby ensuring the correctness of the second file.

[0206] Of course, in other embodiments, if the electronic device enters the editing mode in response to the first file, the second file may not be synchronized; and after the first file is edited, the second file is automatically regenerated based on the edited first file. In this way, the second file can be regenerated after the first file is changed, thereby eliminating the need to edit the second file multiple times and simplifying the operation of generating the second file.

[0207] like Figure 5 As shown, in some embodiments, generating incremental information with a target style in step 12 includes:

[0208] 1221: Determine first content of incremental information according to the file content of the first file;

[0209] 1222: Adjust the text description of the first content to obtain the second content with the target style;

[0210] 1223: Obtain incremental information according to the second content and the type of incremental information.

[0211] In some embodiments, the first content of the incremental information is determined based on the file content of the first file. For example, the first content is a summary, conclusion and / or comment on the file content; or, the first content can also be a presentation of the summary, conclusion and / or comment in the form of narration, barrage, or subtitles; or the first content can also be a story or example associated with the file content of the first file added to the summary, conclusion and / or comment. For another example, the first content is an extraction of key information of the file content.

[0212] Of course, the above is merely an example of obtaining the first content of the incremental information from the file content of the first file, and the specific implementation is not limited to this example.

[0213] In some embodiments, adjusting the text description of the first content in step 1222 to obtain the second content with a target style may include but is not limited to at least one of the following: adjusting the text of the first content by line breaks or paragraph breaks; converting the sentence structure, subject-predicate structure, etc. of the sentences of the first content; and adding modifiers, adding modal particles, etc. to the sentences of the first content.

[0214] In some embodiments, adjusting the text description of the first content in step 1222 to obtain the second content with the target style can be adjusted according to user operations or by inputting an AI model.

[0215] Optionally, the electronic device detects a user operation, and adjusts the text description of the first content according to the user operation to obtain the second content with the target style. The user operation may be re-editing at least part of the first content, deleting part of the first content, adding part of the first content, changing the word order of the first content, and / or summarizing, simplifying or generalizing the first content.

[0216] Optionally, the electronic device inputs the first content into a preset model to obtain second content with a target style. The preset model is a trained adjustment model for the behavior description of the first content.

[0217] In this way, the description of the first content can be adjusted in a variety of ways to obtain suitable second content with a target style, thereby facilitating the generation of suitable incremental content.

[0218] Of course, the above is merely an example of obtaining the second content from the first content, and the specific implementation is not limited to this example.

[0219] In some embodiments, step 1223 includes: in response to the incremental information being of text type, inserting the second content into the first file or generating a second file containing the second content to obtain the incremental information.

[0220] In this way, the incremental information of the text type can be determined to determine appropriate incremental information for the first file of the text type.

[0221] In some embodiments, step 1223 includes: in response to the incremental information being of an audio type, generating audio information that expresses the second content using audio parameters of a target style.

[0222] Exemplarily, the audio parameters include, but are not limited to, voiceprint information, timbre, volume and / or pitch, etc.

[0223] Exemplarily, the incremental information is audio information; before step S1223, the method further includes: obtaining target voiceprint information of the speaker; step S1223 further includes generating audio information expressing the second content of the target voiceprint information; after step S1223, the method further includes: playing the audio information based on the target voiceprint. The target voiceprint information is used to describe the target voiceprint.

[0224] The speech object can be the person himself or a specific person. For example, if the first document is about legal system, the specific person can be a legal worker, etc.; if the first document is about medical system, the specific person can be a doctor, etc.

[0225] In this way, audio information with the voiceprint characteristics of the speaker can be virtualized, so that the played audio information seems to be the speaker himself giving the speech, thereby improving the audience's experience of listening to the speech.

[0226] In some embodiments, step 1223 includes: in response to the incremental information being a video type, generating a speech object having a target style; and generating video information of the speech object giving a speech on a second content according to the target style.

[0227] Exemplarily, the speech object is a virtual person; the virtual person can be the person himself or a specific person. The person refers to the person who created the first file, or the person who requested the speech of the first file. The specific person can be a person corresponding to the target style of the incremental information or a person corresponding to the file content of the first file; for example, if the file content of the first file is a legal topic, the specific person can be a policeman or a legal worker, etc.; for another example, if the target style of the incremental information is an efficient style, the specific person can be a drama worker, etc.

[0228] In this way, a virtual person who actually delivers the first file can be simulated, so that it seems that the person who actually delivers the first file is delivering the first file, thereby improving the user's experience satisfaction. Alternatively, the speech object can be determined as a specific person, so as to match the style and / or content of the first file.

[0229] When the aforementioned incremental information is of audio type or video type, subtitles can be displayed synchronously during the speech.

[0230] If the audio of the first file is presented, subtitles corresponding to the audio information can be displayed on the display interface where the first file is located when the audio information is presented. The display interface can be the document interface in the above embodiment; or, the display interface can be a screen interface.

[0231] If you are speaking to the video of the first file, Figure 6 As shown, when the video information is being presented, subtitles corresponding to the video information may be displayed on the display interface where the first file is located, or subtitles corresponding to the video information may be displayed on a virtual person.

[0232] In this way, when the audio information or video information is being presented, by displaying the subtitles corresponding to the audio information or video information, the user can better understand the content of the presentation, thereby improving the user experience. Moreover, when presenting a video, subtitles can be displayed in a variety of ways to provide a variety of subtitle display options. If subtitles are displayed on a virtual person, on the one hand, it can reduce the interference caused to the user by displaying subtitles on the display interface displaying the first file, and on the other hand, the content of the subtitles can be more intuitively felt, thereby further improving the user experience.

[0233] In some embodiments, the method further includes: regenerating prompt words according to the content modified to the first file; and inputting the regenerated prompt words into the AI ​​model to regenerate the incremental information. Optionally, the AI ​​model can be the AI ​​model or AIGC model used to generate incremental information in the above embodiments.

[0234] Optionally, regenerating the prompt word according to the modified content of the first file includes: if the content of the first file is modified to generate a third file, regenerating the prompt word according to the third file.

[0235] Optionally, the third file may be the second file in the previous embodiment; that is, the third file may also be the second file containing the incremental information. Of course, the third file may also be a file obtained by modifying at least part of the content of the first file.

[0236] Optionally, regenerating the prompt word according to the modified content of the first file includes: if the first content of the first file is modified to the second content, regenerating the prompt word according to the second content of the first file.

[0237] Optionally, the regenerated prompt word may be generated based on the first information of the prompt word being unchanged and the second information being changed; or, the regenerated prompt word may be generated based on the first information and the second information in the prompt word being changed.

[0238] Exemplarily, the electronic device adjusts part of the text of the first file to generate a third file; if the previous prompt words for the first file were "My audience is company employees, the display scene is a formal scene, and the playback time is 1 hour, please generate incremental information for the first file based on the above content", then the regenerated prompt words can modify "Generate incremental information for the first file" to "Generate incremental information for the third file", and the regenerated prompt words can be "My audience is company employees, the display scene is a formal scene, and the playback time is 1 hour, please generate incremental information for the third file based on the above content".

[0239] Based on the above example, a page in the first file can also be modified, such as the second page of the first file; the regenerated prompt words can also be "My audience is company employees, the display scene is a formal scene, and the playback time is 1 hour. Please generate incremental information for the second page of the first file based on the above content" and so on.

[0240] Thus, in the disclosed embodiment, after modifying the first file, for example, generating a second file containing incremental information, etc., the prompt words may be regenerated, and the regenerated prompt words may be input into the AI ​​model to generate new incremental information; thus, the automatic generation of incremental information of the target style of the modified first file may be achieved.

[0241] The present disclosure also provides a model training method for training the AI ​​model in the document processing method. The method includes:

[0242] Based on the alternative model, the training samples marked with the target label are trained to obtain the predicted label of the training samples;

[0243] Determining a loss value of the candidate model based on a difference between the target label and the predicted label; wherein the target label indicates a predetermined object to which the first file is adapted;

[0244] If the loss value meets the training stop condition, stop training the candidate model, and determine the candidate model when the training is stopped as the target model; or, if the loss value does not meet the training stop condition, continue training the candidate model.

[0245] Exemplarily, the loss value satisfies the training stop condition, including: the loss value is less than or equal to a predetermined value. The predetermined value may be an extremely small value, such as 0.001 or 0.000001.

[0246] Exemplarily, the predetermined object may be the aforementioned incremental information, related information (such as audience information, display scene information), voiceprint information, or target style, etc.

[0247] The disclosed embodiment also provides a document processing method, which uses a trained target model; the method includes: inputting a first file into the target model to generate target content. Depending on the target model, the generated target content is different. The target content can be a target style, incremental information, related information, or voiceprint information.

[0248] Exemplarily, the target model may be one or more, or the target model may be a collection of multiple models. For example, the target model may be a natural language processing model, an incremental information generation model, a related information generation model, a voiceprint information generation model, and / or a predetermined style generation model.

[0249] The aforementioned incremental information generation model, related information generation model, voiceprint information generation model, predetermined style generation model and subsequent models of the natural language processing model can be used in combination or in a cascade manner.

[0250] Of course, the above is only an example of the model for processing the first file, and the specific implementation is not limited to this example.

[0251] like Figure 7 As shown, the present disclosure provides a file processing device, the device comprising:

[0252] A determination module 21, configured to determine a target style based on relevant information of the first file;

[0253] The processing module 22 is used to generate incremental information with a target style, wherein the incremental information is enhanced content different from the file content of the first file.

[0254] In some embodiments, the determination module 21 is used to determine the target style based on at least one relevant information of the first file; wherein the relevant information includes at least one of the following: file content of the first file, audience information of the first file, and display scene information of the first file.

[0255] In some embodiments, the determination module 21 is used to determine the priority of the multiple related information in response to obtaining the multiple related information of the first file; and determine the target style according to the priority and the multiple related information.

[0256] In some embodiments, the determination module 21 is used to determine the target style according to the candidate styles corresponding to the highest priority related information among the multiple related information.

[0257] In some embodiments, the determination module 21 is used to determine the relevant weight according to the priority of the plurality of relevant information;

[0258] Determine the style value according to the relevant weights and the style parameters corresponding to the relevant information;

[0259] Determine the target style based on the style value.

[0260] In some embodiments, display scene information corresponds to a first priority; audience information corresponds to a second priority; and file content corresponds to a third priority; wherein the first priority is higher than the second priority, and the second priority is higher than the third priority; or, the second priority is higher than the first priority, and the first priority is higher than the third priority.

[0261] In some embodiments, the processing module 22 is used to pre-generate multiple incremental information applicable to multiple candidate presentation scenarios; and select the incremental information that is adapted to the current target presentation scenario from the pre-generated multiple incremental information for output.

[0262] In some embodiments, the processing module 22 is used to generate incremental information having a target style from the file content of the first file; or, the processing module 22 is used to generate a second file containing the incremental information.

[0263] In some embodiments, the device further includes: a storage module, configured to store the first file and the second file in an associated manner.

[0264] In some embodiments, the device also includes: a display module for displaying a file icon of the first file; or, a display module for displaying a file icon of the first file and a file icon of the second file side by side and adjacent to each other; wherein the file icon of the first file is used to launch the first file; and the file icon of the second file is used to launch the second file.

[0265] In some embodiments, a distance between a file icon of the first file and a file icon of the second file is smaller than a distance between a file icon of the first file and a file icon of a third file; wherein the third file is unrelated to the first file.

[0266] In some embodiments, the display module, in response to detecting a start-up operation acting on the first file, displays the first file on the document interface;

[0267] The processing module 22 is used to determine whether to start the second file synchronously.

[0268] In some embodiments, the processing module 22 is used to determine to synchronously start the second file in response to detecting a specified operation when starting the first file; wherein the specified operation includes: a confirmation operation acting on the prompt information displayed when the first file is started, or a user operation acting on a preset space in the first file; or

[0269] The processing module 22 is used to determine whether to start the second file synchronously according to the start status of the first file.

[0270] In some embodiments, the processing module 22 is configured to perform at least one of the following:

[0271] In response to the first file being in a multiple-file association preview mode, determining to synchronously start the second file;

[0272] In response to the first file being in the associated play mode, determining to synchronously start the second file;

[0273] In response to the first file entering the edit mode, it is determined to synchronously start the second file.

[0274] In some embodiments, the processing module 22 is used to determine the first content of the incremental information based on the file content of the first file; adjust the text description of the first content to obtain the second content with the target style; and obtain the incremental information based on the second content and the type of the incremental information.

[0275] In some embodiments, the processing module 22 is used to insert the second content into the first file or generate a second file containing the second content in response to the incremental information being of text type, so as to obtain the incremental information.

[0276] In some embodiments, the text type incremental information includes at least one of the following: annotation information of the first file, remark information of the first file, comment information of the first file, speech of the first file, barrage information of the first file, subtitle information of the first file presentation, and narration information of the first file presentation.

[0277] In some embodiments, the processing module 22 is configured to generate audio information expressing the second content using audio parameters of a target style in response to the incremental information being of an audio type.

[0278] In some embodiments, the processing module 22 is used to generate a speech object with a target style in response to the incremental information being a video type; and generate video information of the speech object giving a speech on a second content according to the target style.

[0279] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0280] An embodiment of the present disclosure further provides an electronic device, including:

[0281] processor;

[0282] a memory for storing processor-executable instructions;

[0283] The processor is configured to implement the file processing method of any embodiment of the present disclosure when running the executable instructions.

[0284] The electronic device can at least be a server and / or a terminal. One or more servers can constitute a service end.

[0285] The memory may include various types of storage media, which are non-transitory computer storage media that can continue to remember information stored thereon after the communication device loses power.

[0286] The processor can be connected to the memory through a bus or the like to read the executable program stored in the memory, for example, to implement the following Figure 1 , Figure 3 and Figure 5 Any of the file processing methods shown.

[0287] like Figure 8 FIG. 4 is a diagram showing a structure of an electronic device 40 according to an exemplary embodiment. For example, the electronic device 40 may be provided as a network side device. Figure 8 The electronic device 40 includes a processing component 41, which further includes one or more processors, and a memory resource represented by a processor 42 for storing instructions executable by the processing component 41, such as an application. The application stored in the processor 42 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 41 is configured to execute instructions to perform any method of the aforementioned method applied in the base station.

[0288] The electronic device 40 may further include a power supply component 43 configured to perform power management of the electronic device 40, a wired or wireless network interface 44 configured to connect the electronic device 40 to a network, and an input / output (I / O) interface 45. The electronic device 40 may operate based on an operating system stored in the processor 42, such as Windows Server TM, MacOS XTM, UnixTM, LinuxTM, FreeBSDTM or the like.

[0289] The embodiments of the present disclosure further provide a computer-readable storage medium storing an executable program, wherein the executable program, when executed by a processor, implements the file processing method of any embodiment of the present disclosure. Figure 1 , Figure 3 and Figure 5 Any of the file processing methods shown.

[0290] An embodiment of the present disclosure provides a computer-readable storage medium, which stores an executable program. When the executable program is executed by a processor, the file processing method provided by any one of the above-mentioned technical solutions is implemented.

[0291] The computer-readable storage medium may specifically be: a non-temporary computer-readable storage medium.

[0292] Exemplarily, such as a memory including an executable program, the above instructions can be executed by the processing component 41 of the electronic device to complete the above method.

[0293] The non-transitory computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0294] Those skilled in the art will readily appreciate other implementations of the disclosed embodiments after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosed embodiments, which follow the general principles of the disclosed embodiments and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and examples are to be considered as exemplary only, and the true scope and spirit of the disclosed embodiments are indicated by the following claims.

[0295] It should be understood that the embodiments of the present disclosure are not limited to the precise structures described above and shown in the drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the embodiments of the present disclosure is limited only by the appended claims.

Claims

1. A file processing method, characterized in that: The method comprises: Determine the target style based on the relevant information of the first file; Incremental information having the target style is generated, wherein the incremental information is enhanced content different from the file content of the first file.

2. The method according to claim 1, characterized in that Determining the target style according to the relevant information of the first file includes: The target style is determined according to at least one relevant information of the first file; wherein the relevant information includes at least one of the following: file content of the first file, audience information of the first file, and display scene information of the first file.

3. The method according to claim 2, characterized in that The determining the target style according to at least one relevant information of the first file includes: In response to acquiring the plurality of related information of the first file, determining the priority of the plurality of related information; The target style is determined according to the priority and the plurality of related information.

4. The method according to claim 3, characterized in that Determining the target style according to the priority and the plurality of related information includes: Determining relevant weights according to the priorities of the plurality of relevant information; Determining a style value according to the relevant weights and style parameters corresponding to the relevant information; The target style is determined according to the style value.

5. The method according to claim 1 or 2, characterized in that: The generating of incremental information having the target style includes: Pre-generate multiple incremental information applicable to multiple alternative display scenarios; From the plurality of pre-generated incremental information, the incremental information adapted to the current target presentation scenario is selected for output.

6. The method according to claim 1 or 2, characterized in that: The generating of incremental information having the target style includes: Generating the incremental information having the target style in the file content of the first file; or, A second file is generated containing the incremental information.

7. The method according to claim 6, characterized in that The method further comprises: The first file and the second file are stored in association.

8. The method according to claim 7, characterized in that The method further comprises: In response to detecting a start-up operation acting on the first file, displaying the first file on a document interface; Determine whether to start the second file synchronously.

9. The method according to claim 8, characterized in that The determining whether to synchronously start the second file includes: In response to detecting a designated operation when starting the first file, determining to synchronously start the second file; wherein the designated operation includes: a confirmation operation acting on a prompt information displayed when the first file is started, or a user operation acting on a preset space in the first file; or, According to the startup status of the first file, it is determined whether to synchronously start the second file.

10. The method according to claim 9, characterized in that The step of determining whether to synchronously start the second file according to the start status of the first file includes at least one of the following: In response to the first file being in a multi-file association preview mode, determining to synchronously start the second file; In response to the first file being in the associated play mode, determining to synchronously start the second file; In response to the first file entering an editing mode, it is determined to synchronously start the second file.

11. The method according to claim 1 or 2, characterized in that: The generating of incremental information having the target style includes: Determining first content of the incremental information according to the file content of the first file; Adjusting the text description of the first content to obtain second content with the target style; The incremental information is obtained according to the second content and the type of the incremental information.

12. The method according to claim 11, characterized in that The obtaining the incremental information according to the second content and the type of the incremental information further includes: In response to the incremental information being of text type, the second content is inserted into the first file or a second file containing the second content is generated to obtain the incremental information.

13. The method according to claim 12, characterized in that The incremental information of the text type includes at least one of the following: Annotation information of the first file; Remarks on the first document received; comment information of the first file; the speech of the first document; Barrage information of the first file; Subtitle information presented by the first file; The first file demonstrates the narration information.

14. The method according to claim 11, characterized in that The obtaining the incremental information according to the second content and the type of the incremental information further includes: In response to the incremental information being of an audio type, audio information expressing the second content using audio parameters of the target style is generated.

15. The method according to claim 11, characterized in that The obtaining the incremental information according to the second content and the type of the incremental information includes: In response to the incremental information being a video type, generating a speech object having the target style; According to the target style, video information of the speaker delivering a speech on the second content is generated.

16. A document processing device, characterized in that: The device comprises: A determination module, used to determine a target style according to relevant information of the first file; The processing module is used to generate incremental information having the target style, wherein the incremental information is enhanced content different from the file content of the first file.

17. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to: implement the file processing method described in any one of claims 1 to 15 when running the executable instructions.

18. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores an executable program, wherein the executable program, when executed by a processor, implements the file processing method according to any one of claims 1 to 15.

Images