Data processing method, device, equipment and storage medium

Abstract

The present disclosure provides a data processing method, device, equipment and storage medium, which relate to the fields of artificial intelligence and generative models, and in particular to the field of intelligent search. The specific implementation scheme is: obtaining an initial data set, which includes pre-extracted data, a file identifier of the original file to which the pre-extracted data belongs, and a position identifier of the pre-extracted data in the original file; determining the target data from the pre-extracted file according to the received data processing request, and determining the style characteristics of the target data; determining the data to be processed from the corresponding original file according to the position identifier of the target data; processing the data to be processed according to the data processing request and the style characteristics to obtain the data processing result. The scheme provided by the present disclosure can effectively ensure the accuracy and completeness of data processing. At the same time, combining the style characteristics of the target data in the process of processing data can improve the intelligent effect of data processing.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, specifically to the field of artificial intelligence and generative model technology, and in particular to a data processing method, device, equipment and storage medium. Background Art

[0002] Currently, network disk products can only store original files or links, but cannot further process the data during storage, such as using generative models or large language models to process data. In addition, the application path for further processing of stored data is relatively simple. Summary of the invention

[0003] The present invention provides a data processing method, device, equipment and storage medium, which effectively improve the intelligent processing effect of data.

[0004] According to a first aspect of the present disclosure, there is provided a data processing method, comprising:

[0005] Acquire an initial data set, the initial data set including pre-extracted data, a file identifier of an original file to which the pre-extracted data belongs, and a position identifier of the pre-extracted data in the original file;

[0006] According to the received data processing request, target data is determined from the pre-extracted data, and style features of the target data are determined;

[0007] According to the location identifier of the target data, determine the data to be processed from the corresponding original file;

[0008] The data to be processed is processed according to the data processing request and style features to obtain the data processing result.

[0009] According to a second aspect of the present disclosure, there is provided a data processing method, comprising:

[0010] Obtain data extraction requests and candidate extraction data;

[0011] Determine the original file to which the candidate extracted data belongs and the position identifier of the candidate extracted data in the original file;

[0012] Process candidate extraction data according to the data extraction request to obtain pre-extracted data;

[0013] The pre-extracted data, the file identifier and the location identifier of the original file are associated and saved to obtain an initial data set.

[0014] According to a third aspect of the present disclosure, there is provided a data processing device, comprising:

[0015] A first acquisition module is configured to acquire an initial data set, wherein the initial data set includes pre-extracted data, a file identifier of an original file to which the pre-extracted data belongs, and a position identifier of the pre-extracted data in the original file;

[0016] A first determination module is configured to determine target data from pre-extracted data according to a received data processing request, and determine style features of the target data;

[0017] A second determination module is configured to determine the data to be processed from the corresponding original file according to the location identifier of the target data;

[0018] The first processing module is configured to process the data to be processed according to the data processing request and the style feature to obtain a data processing result.

[0019] According to a fourth aspect of the present disclosure, there is provided a data processing device, comprising:

[0020] A third acquisition module is configured to acquire a data extraction request and candidate extraction data;

[0021] A fourth determination module is configured to determine the original file to which the candidate extracted data belongs and a position identifier of the candidate extracted data in the original file;

[0022] A second processing module is configured to process candidate extraction data according to the data extraction request to obtain pre-extraction data;

[0023] The saving module is configured to save the pre-extracted data, the file identifier and the location identifier of the original file in association with each other to obtain an initial data set.

[0024] According to a fifth aspect of the present disclosure, there is provided an electronic device, including:

[0025] at least one processor; and

[0026] a memory communicatively connected to at least one processor; wherein,

[0027] The memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor to enable the at least one processor to perform the method provided by the first aspect or the second aspect.

[0028] According to a sixth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, where the computer instructions are used to cause a computer to execute the method provided in the first aspect or the second aspect.

[0029] According to a seventh aspect of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the computer program implements the method provided according to the first aspect or the second aspect.

[0030] 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

[0031] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0032] Figure 1 is an exemplary system architecture diagram to which the data processing method of the present disclosure can be applied;

[0033] Figure 2 is a schematic diagram of a first embodiment of a data processing method according to the present disclosure;

[0034] Figure 3 is a schematic diagram of a second embodiment of a data processing method according to the present disclosure;

[0035] Figure 4 is a schematic diagram of a third embodiment of a data processing method according to the present disclosure;

[0036] Figure 5a-5c is a schematic diagram of pre-extracting data in the data processing method according to the present disclosure;

[0037] Figure 6 is a schematic diagram of a first embodiment of a data processing device according to the present disclosure;

[0038] Figure 7 is a schematic diagram of a second embodiment of a data processing device according to the present disclosure;

[0039] Figure 8 It is a block diagram of an electronic device used to implement the data processing method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0040] 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.

[0041] The present disclosure provides a data processing method, which determines target data from pre-extracted data of an initial data set according to a data processing request, and obtains data to be processed from the original file to which it belongs according to the target data, effectively ensuring the integrity and accuracy of the processed data, thereby ensuring the integrity and accuracy of the data processing results; further, in the process of processing data, the style features of the target data are combined so that the style features are integrated into the data processing results, thereby improving the work style of the data processing results and improving the intelligence level of data processing.

[0042] Exemplarily, the data preprocessing, generation and other processes in the data processing method of the present disclosure can be implemented using a large language model. Large language models (LLM, Large Language Model, which is essentially a generative model), such as ChatGPT (Chat Generative Pre-trained Transformer, a chatbot program developed by OpenAI), can generate human-like fluent responses for many downstream tasks (such as task-oriented dialogue and question answering).

[0043] Figure 1 An exemplary system architecture 100 is shown to which embodiments of the data processing method or data processing apparatus of the present disclosure can be applied.

[0044] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The network 102 is used to provide a communication link between the terminal device 101 and the server 103, and may include various connection types, such as a wired communication link, a wireless communication link or an optical fiber cable.

[0045] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send information, etc. Various client applications can be installed on the terminal device 101.

[0046] The terminal device 101 can be hardware or software. When the terminal device 101 is hardware, it can be various electronic devices, including but not limited to independent electronic devices such as smart phones, tablet computers, laptop computers and desktop computers, and can also include electronic devices attached to vehicles such as vehicle-mounted terminals. When the terminal device 101 is software, it can be installed in the above electronic devices. It can be implemented as multiple software or software modules, or as a single software or software module. No specific limitation is made here.

[0047] The server 103 may be hardware or software. When the server 103 is hardware, it may be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When the server 103 is software, it may be implemented as multiple software or software modules (for example, for providing distributed services), or as a single software or software module. No specific limitation is made here.

[0048] The data processing method provided in the embodiment of the present disclosure is generally executed by the server 103 or the terminal device 101 , and accordingly, the data processing device is generally arranged in the server 103 or the terminal device 101 .

[0049] It should be noted that Figure 1 The number of terminal devices 101, networks 102 and servers 103 in the embodiment is only for illustration. Any number of terminal devices 101, networks 102 and servers 103 may be provided according to implementation requirements.

[0050] Figure 2 A process 200 of an embodiment of a data processing method according to the present disclosure is shown, referring to Figure 2 As shown, the data processing method includes the following steps:

[0051] Step S201 : acquiring an initial data set, wherein the initial data set includes pre-extracted data, a file identifier of an original file to which the pre-extracted data belongs, and a position identifier of the pre-extracted data in the original file.

[0052] In the embodiments of the present disclosure, the execution subject of the data processing method, for example Figure 1 The terminal device 101 or server 103 shown obtains an initial data set from other terminal devices or network servers connected to the communication, or from a local storage space, by wired or wireless means. The initial data set includes pre-extracted data, the original file to which the pre-extracted data belongs and / or the file identifier of the original file, and also includes a position identifier of the pre-extracted data in the original file to which it belongs.

[0053] In some optional implementations, the initial data set may be an initial data set pre-stored by the user on a terminal device or a server. For example, the initial data set is a data set stored by the user on a network disk through a terminal device such as a mobile phone or a computer, for example, a data set in a collection or clipping folder.

[0054] In some optional implementations, the data in the initial data set may also include data that has not been pre-collected or clipped, for example, data currently searched or obtained from other applications other than interactive software such as WeChat or web pages, or from other devices.

[0055] The pre-extracted data may be in various forms, for example, at least one of the following forms: documents, audio, video, images, text, etc., and may also include formulas, charts, etc. The documents, audio, video, and text may include any language content, for example, modern Chinese, classical Chinese, oracle bone script, etc., minority languages ​​such as Tibetan, and foreign languages ​​such as English and Italian.

[0056] Correspondingly, the original file to which the pre-extracted data belongs may include at least one of the following forms: document, audio, video, image, web link (that is, the original file is the content displayed in the web link), etc., and its content may include at least one of text, voice, image, video, formula, chart, etc.

[0057] The file identifier of the original file to which the pre-extracted data belongs may include at least one of the following: file name, file address (including network address, local storage address, etc.), publishing time, author, etc.

[0058] In some optional implementations, the pre-extracted data in the initial data set may include at least part of the original data in the original file, for example, data such as prompt words, sentences, paragraphs or chapters in a document file, or at least part of the material in a picture, or a screenshot or video clip in a video, or at least part of the audio clip in the voice data; it may also include regenerated data such as summary information generated based on at least part of the data in the original file, for example, a brief overview of the complete content of a document or a video, a summary of viewpoints, annotations on a role or character in a book or video file, etc.

[0059] The position identifier of the pre-extracted data in the original file to which it belongs includes: the page number or timestamp of the pre-extracted data in the original file, etc. For example, the page number or page number and line number of a sentence or a paragraph in its original document file; another example, the starting time position (for example, the position at 5 minutes and 8 seconds) or the starting and ending time positions of a sentence in its original video file; another example, the pixel position or orientation information of a certain image element in a certain image file, etc.

[0060] In some optional implementations, the pre-extracted data may be the entire original document or a summary of the entire original document, in which case the location identifier of the corresponding pre-extracted data in the original document is the identification information of the entire document or other information representing the entire document.

[0061] Step S202: determining target data from the pre-extracted data according to the received data processing request, and determining style features of the target data.

[0062] In the embodiments of the present disclosure, the execution subject of the data processing method, for example Figure 1The terminal device 101 or the server 103 shown determines the target data from the pre-extracted data of the initial data set obtained in step S201 according to the received data processing request, and determines the style features of the target data.

[0063] The data processing request may include at least one of the following processing requests: generating a document file associated with a certain subject or field, generating a video file associated with certain content, generating an image file of a preset scene theme, generating a text, etc.

[0064] Exemplarily, the data processing request received by the above-mentioned execution entity may be: writing a financial research report, or generating a growth video of XXX (name), or adjusting the color scheme of a photo album according to the shooting time, weather, etc., or generating a "document + voice" experience record for a product, etc.

[0065] In some optional implementations, the data processing request may also include: summarizing or extracting part of the content of the generated document or video. For example, generating a summary or review text for the generated document or video, and adding word count, language restrictions, etc. Another example is extracting a certain viewpoint or knowledge point in the generated document, video, audio, etc. to form a text.

[0066] The target data is at least part of the pre-extracted data in all the pre-extracted data in the initial data set.

[0067] Exemplarily, the execution subject may filter pre-extracted data that is compatible with the relevant identification information in the data processing request from the initial data set as the target data based on identification information such as the subject, field, and keyword in the data processing request.

[0068] In some optional implementations of the embodiments of the present disclosure, target data is determined from pre-extracted data based on a received data processing request, including: obtaining a data processing request; identifying a data content identifier in the data processing request; and determining the target data from the pre-extracted data based on the data content identifier.

[0069] In this implementation, after obtaining a data processing request, the execution subject identifies a data content identifier in the data processing request to determine the data content targeted by the data processing request; and then determines the target data from the pre-extracted data based on the data content identifier.

[0070] Among them, the data content identifier includes content identifiers such as data subject, data field, and data name. For example, the data processing request is "write a financial research report", and its data content identifier is "finance". The execution subject identifies the pre-extracted data related to "finance" from the pre-extracted data and determines it as the target data. For another example, the data processing request is "write an autumn tour of Wugong Mountain", and its data content identifiers are "Wugong Mountain" and "Autumn Tour". The execution subject selects the pre-extracted data such as text data, image data, video data, and voice data related to "Wugong Mountain" and "Autumn Tour" from the initial data set and determines it as the target data.

[0071] In the embodiment of the present disclosure, the execution subject selects the pre-extracted data associated with the data content identifier in the data processing request as the target data, thereby effectively improving the accuracy and relevance of the data processing.

[0072] In some optional implementations, target data is determined from pre-extracted data based on a data content identifier, including: obtaining an extracted content identifier of the pre-extracted data, and based on the correlation between the extracted content identifier and the data content identifier, screening, from an initial data set, pre-extracted data having a correlation greater than or equal to a preset correlation threshold as target data.

[0073] The execution entity effectively ensures the content correlation between the target data and the data processing request by determining the correlation between the extracted content identifier of the pre-extracted data and the data content identifier of the data processing request, thereby effectively ensuring that the screened target data meets the data requirements of the data processing request and improving the accuracy and correlation of data processing.

[0074] In some optional implementations of the embodiments of the present disclosure, determining the style features of the target data includes: inputting the target data into a pre-trained language model to obtain the style features of the target data.

[0075] In this implementation, the execution subject inputs the determined target data into a pre-trained language model to obtain the style features of the target data. The pre-trained language model can be a neural network model trained for different data types, or a large language model in related technologies.

[0076] Among them, the style features of the target data are used to characterize the work style of the target data, such as the language style, description style, etc. of text data, the composition style, color matching style, image parameter style, etc. of image data, the language and regional style, voice characteristics (such as loli voice, deep voice, high pitch, etc.) of voice data, and the scene style, shooting style, scene switching style, etc. of video data.

[0077] In this implementation, the execution subject identifies the style features of the target data and incorporates the style features into the data processing process to ensure that the data processing results have corresponding style features, improve the intelligence of the data processing process and the uniqueness of the data processing results, and make the data processing results closer to the expectations corresponding to the data processing request.

[0078] Step S203, determining the data to be processed from the corresponding original file according to the location identifier of the target data.

[0079] In the embodiments of the present disclosure, the execution subject of the data processing method, for example Figure 1 The terminal device 101 or the server 103 shown determines the data to be processed from the original file corresponding to the target data according to the location identifier of the target data.

[0080] Since the target data is determined from the pre-extracted data, the execution subject may determine the location identifier of the pre-extracted data corresponding to the target data as the location identifier of the target data.

[0081] After determining the target data from the pre-extracted data, the execution entity extracts the associated data from the original file to which the target data belongs according to the location identifier of the target data as the data to be processed to ensure the information integrity of the data to be processed, thereby improving the accuracy and completeness of the data processing results.

[0082] Exemplarily, the data to be processed includes at least one of the following: original pre-extracted data serving as target data, and associated data of the target data in the corresponding original file.

[0083] In some optional implementations, the original pre-extracted data serving as the target data is a partial chapter in the original file or a complete image in the original image file. After the pre-extracted data is determined as the target data, the above-mentioned execution entity may directly use the pre-extracted data as the data to be processed.

[0084] In some optional implementations, the original pre-extracted data serving as the target data is a summary of at least part of the content in the original file, such as a content overview generated for an original document file or a content summary of an original video file, etc. The execution entity may directly use the pre-extracted data as the data to be processed, or may use the pre-extracted data and the corresponding original file together as the data to be processed.

[0085] In some optional implementations, the original pre-extracted data used as the target data is the marked content in the original file, for example, a list of viewpoints, marked sentences or keywords generated for the original document file, or a partial plot description, a record of a certain shot or scene, etc. in the original video file. At this time, the execution subject obtains the associated data of the target data from the original file to which it belongs according to the location identifier of the target data (i.e., the location identifier of the original pre-extracted data), such as the original text of the viewpoint, the marked sentence or the context of the original text containing the keyword in the original document file, or a plot excerpt video in the original video file and its associated videos of a preset length before and after, or plot-related videos, character videos, video excerpts related to a certain scene, etc., and then the execution subject can use the target data and its associated data in the original file to which it belongs as data to be processed.

[0086] In the disclosed embodiment, the execution subject extracts the data to be processed from the corresponding original file according to the location identifier of the target location, which can effectively ensure the integrity of the data to be processed, thereby ensuring the integrity of the data processing result.

[0087] Step S204: Process the data to be processed according to the data processing request and the style features to obtain a data processing result.

[0088] In the embodiments of the present disclosure, the execution subject of the data processing method, for example Figure 1 The terminal device 101 or the server 103 shown processes the data to be processed according to the data processing request and the style characteristics of the target data to obtain a data processing result.

[0089] Since the target data is at least part of the pre-extracted data in the initial data set, the execution subject can consider that the style of the target data is the style recognized by the user. In this case, the execution subject processes the data to be processed according to the data processing request, which can effectively ensure that the data processing result meets the expectations of the data processing request; at the same time, combined with the style characteristics of the target data, the data style recognized by the user is simulated, which can effectively ensure that the data processing result meets the style characteristics of the target data, improve the personal creation characteristics of the data processing result, and improve the intelligence of data processing.

[0090] The data processing method provided by the embodiment of the present disclosure determines the target data from the pre-extracted data of the initial data set according to the received data processing request, and then obtains the related data from the original file to which it belongs as the data to be processed in combination with the location identifier of the target data, which can effectively ensure the accuracy and completeness of the processed data; at the same time, in the process of data processing, the style characteristics of the target data are combined to effectively ensure the work style of the data processing results, thereby improving the intelligence level of data processing and the uniqueness of the data processing results.

[0091] It should be pointed out that in the technical solution of the present disclosure, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0092] Figure 3 The process 300 of the second embodiment of the data processing method according to the present disclosure is shown. Figure 3 As shown, the data processing method includes the following steps:

[0093] Step S301 : acquiring an initial data set, which includes pre-extracted data, a file identifier of an original file to which the pre-extracted data belongs, and a position identifier of the pre-extracted data in the original file.

[0094] In the embodiments of the present disclosure, the execution subject of the data processing method, for example Figure 1 The terminal device 101 or server 103 shown obtains the initial data set from a network device or a network server, or from a local storage space, via a wired or wireless method.

[0095] Step S301 and Figure 2 Step S201 of the illustrated embodiment is basically the same, and the specific implementation method can refer to the above description of step S201, which will not be repeated here.

[0096] Step S302: determining target data from the pre-extracted data according to the received data processing request, and determining style features of the target data.

[0097] In the embodiments of the present disclosure, the execution subject of the data processing method, for example Figure 1 The terminal device 101 or the server 103 shown determines the target data from the pre-extracted data of the initial data set obtained in step S201 according to the received data processing request, and determines the style features of the target data.

[0098] Step S302 and Figure 2 Step S202 of the illustrated embodiment is basically the same, and the specific implementation method can refer to the above description of step S202, which will not be repeated here.

[0099] Step S303: determining the data to be processed from the corresponding original file according to the location identifier of the target data.

[0100] In the embodiments of the present disclosure, the execution subject of the data processing method, for example Figure 1 The terminal device 101 or the server 103 shown determines the data to be processed from the original file corresponding to the target data according to the location identifier of the target data.

[0101] Step S303 and Figure 2Step S203 of the illustrated embodiment is basically the same, and the specific implementation method can refer to the above description of step S203, which will not be repeated here.

[0102] Step S304: Identify the target type and operation type in the data processing request.

[0103] In the embodiments of the present disclosure, the execution subject of the data processing method, for example Figure 1 The terminal device 101 or the server 103 shown identifies the target type and the operation type in the received data processing request.

[0104] Exemplarily, the target type includes the data type of the expected result corresponding to the data processing request, such as a report, paper, video, atlas, voice, etc.

[0105] Exemplarily, the operation type includes the type of operation for processing data, such as writing, correcting, retouching, generating videos, capturing videos, generating audio corresponding to different roles based on text descriptions or introductions, etc.

[0106] In some optional implementations of the embodiments of the present disclosure, the target type includes at least one of the following: text type (such as text fragments, document files, etc.), image type, video type, audio type, chart type (such as mind maps, lists, etc.), etc.; and the operation type includes at least one of the following: text editing, text generation, image processing, image generation, video editing, video generation, audio extraction or audio generation, etc.

[0107] In some optional implementations, the target type and operation type may also include other achievable target types and operation types not mentioned above, which are not limited here.

[0108] Step S305, determining pre-processing data according to the target type and the data to be processed, wherein the data type of the pre-processing data is adapted to the target type.

[0109] In the embodiments of the present disclosure, the execution subject of the data processing method, for example Figure 1 The terminal device 101 or the server 103 shown pre-processes the data to be processed according to the target type in the data processing request to obtain pre-processed data whose data type is compatible with the target type.

[0110] In some optional implementations of the embodiments of the present disclosure, preprocessed data is determined based on a target type and data to be processed, including: based on the target type, determining a candidate type that is adapted to the target type; in response to an initial type of the data to be processed being compatible with the candidate type, determining the data to be processed as preprocessed data; in response to an initial type of the data to be processed being incompatible with the candidate type, identifying content to be processed of the data to be processed, and compiling the content to be processed into preprocessed data that conforms to the candidate type.

[0111] In this implementation, the process of preprocessing the data to be processed according to the target type by the execution subject is a process of adjusting the data type of the data to be processed to ensure that the data type of the preprocessed data after adjustment is compatible with the target type.

[0112] The execution subject determines the candidate types that match the target type according to the target type in the data processing request. For example, if the target type is a report in the text type, the candidate types that match the report include text, image, and chart.

[0113] Then the execution subject determines the initial type of the data to be processed. If the initial type of the data to be processed is compatible with the candidate type, for example, it meets at least one of the candidate types, then the data to be processed can be directly determined as preprocessed data; if the initial type of the data to be processed is not compatible with the candidate type, that is, the initial type of the data to be processed does not belong to or does not include any of the candidate types, then the content to be processed of the data to be processed is identified, and the content to be processed is compiled into preprocessed data that meets the candidate type.

[0114] Exemplarily, if the candidate types include text, images, icons, and formulas, and the initial type of the data to be processed is video, the execution entity confirms that the initial type of the data to be processed does not match the candidate type, and then identifies the content to be processed of the video, including identifying the image content and audio content of the video, compiling the image content into image data, compiling the audio content into text data, and using the compiled image data and text data as preprocessing data.

[0115] The process of the execution subject compiling the data type of the data to be processed can be executed using a pre-trained neural network model.

[0116] In this implementation, the execution subject pre-processes the data to be processed according to the target type in the data processing request to ensure that the data type of the pre-processed data is compatible with the target type, and adapts the data type of the data to be processed and the data processing request, which can effectively improve the accuracy and efficiency of data processing; especially when there are multiple pieces of data to be processed, the data type of the data to be processed can be adaptively adjusted to effectively improve the processing rate of the data content and the accuracy of the data processing results.

[0117] Step S306, processing the preprocessed data according to the operation type to obtain a data processing result.

[0118] In the embodiments of the present disclosure, the execution subject of the data processing method, for example Figure 1 The terminal device 101 or the server 103 shown processes the pre-processed data obtained in step S305 according to the operation type identified in step S304, thereby obtaining a data processing result.

[0119] Exemplarily, the processing of the pre-processed data by the execution subject may include sorting, splicing, polishing, etc. For example, a plurality of pre-processed text data, image data, etc. are sorted according to the relevance between adjacent data, and then spliced ​​in sequence, and corresponding transition sentences are polished at the splicing points, and summary sentences are adaptively added at the start and end of the spliced ​​file for polishing, so as to obtain the expected data processing results such as report files.

[0120] For another example, for multiple pre-processed image data, video data, text data and / or audio data, the image data and video data are sorted and spliced ​​according to the relevance of the content to obtain spliced ​​data, and the text data and / or audio data are adjusted based on the spliced ​​data, and then the text data and / or audio data are fused with the spliced ​​data to obtain a video file with subtitles and / or audio as a data processing result.

[0121] After preprocessing the data to be processed, the above-mentioned execution entity ensures that the data type of the preprocessed data is compatible with the target type of the data processing request, and then processes the preprocessed data according to the operation type in the data processing request, which can improve the data processing efficiency and the accuracy of the processing results.

[0122] Among them, the processing process of the pre-processed data by the execution subject can be implemented using a preset algorithm or a pre-trained neural network model, or it can be implemented using other technologies in related fields, which is not limited here.

[0123] In some optional implementations of the embodiments of the present disclosure, preprocessed data is processed according to the operation type to obtain a data processing result, including: determining a pretrained data processing model according to the operation type; and inputting the preprocessed data into the pretrained data processing model to obtain a data processing result.

[0124] In this implementation, the above-mentioned execution entity determines the pre-trained data processing model according to the operation type in the data processing request, and then inputs the pre-processed data book into the pre-trained data processing model to obtain the data processing result, which can effectively improve the data processing efficiency.

[0125] Among them, the data processing model can be a pre-trained special neural network model for corresponding data operation types such as text editing or video generation, or it can be a large language model in related technologies, which is not limited here.

[0126] In the data processing method provided by the embodiment of the present disclosure, the execution subject pre-processes the data to be processed according to the target type in the data processing request to obtain pre-processed data that is compatible with the target type, and then further processes the pre-processed data according to the operation type in the data processing request to obtain a data processing result of the target type. While ensuring that the data type of the data processing result meets the data processing request, the accuracy and efficiency of the data processing are effectively guaranteed.

[0127] Step S307, obtaining a data output request.

[0128] In the embodiments of the present disclosure, the execution subject of the data processing method, for example Figure 1 The terminal device 101 or server 103 shown may also obtain a data output request before or after executing steps S304 to S306, so as to output corresponding data in a timely manner for user use, such as browsing or consumption, according to user needs.

[0129] The data output request can be used to request the output of data in the initial data set, including pre-extracted data, the original file to which the pre-extracted data belongs, etc. It can also be used to request the output of data to be processed determined according to the data processing request, and it can also be used to request the output of data processing results. Therefore, the data output request can be received during any process of executing the above data processing method, or after the above data processing process is completed. At this time, the data at any stage of the above data processing process can be output according to the data output request.

[0130] Step S308: determining the target device according to the device identification in the data output request.

[0131] In the embodiments of the present disclosure, the execution subject of the data processing method, for example Figure 1 The terminal device 101 or the server 103 shown determines the target device for data output according to the device identification in the data output request obtained in step S307.

[0132] The data output request may include a device identifier for outputting data. The execution subject identifies the device identifier in the data output request to determine the target device for data output.

[0133] Exemplarily, the device identification may include device type, device name, device number, etc. For example, it may be a device name or device number in the past login history list of the network disk account, or a device identification in the same network cluster, or a device identification such as a device type or device name that has not been used or connected.

[0134] For device identifiers in the past login history list or historical connection list, the execution entity can directly determine the target device through the login history list or historical connection list; for device identifiers in the same network cluster or those that have not been used or connected, the execution entity first determines the target device through the device identifier, and then connects to the target device through the network cluster or other means.

[0135] Step S309: output the data to be processed and / or the data processing result to the target device.

[0136] In the embodiments of the present disclosure, the execution subject of the data processing method, for example Figure 1 The terminal device 101 or the server 103 shown outputs the data to be processed and / or the data processing result to the target device determined in step S308.

[0137] After determining the target device and establishing a connection with the target device, the execution subject outputs the requested data to the target device according to the received data output request. The data requested by the data output request may be at least one of the pre-extracted data in the initial data set, the original file to which the pre-extracted data belongs, the data to be processed determined according to the data processing request, the data processing result, etc.

[0138] Exemplarily, a user may send a data output request for pre-extracted data in an initial data set. After receiving the data output request, the execution entity determines the data to be output from the initial data set, determines the target device from the data output request, and then outputs the data to be output to the target device.

[0139] Exemplarily, a user can send a data output request for a data processing result, for example, a data output request for a generated research report. After receiving the data output request, the execution entity obtains the device identifier in the data output request, determines the target device, such as a laptop computer, mobile phone, television, etc., and then outputs the generated research report to the target device.

[0140] The user can check the data sent by the execution subject on the target device, and then browse, modify or consume it.

[0141] It should be noted that the device identification in the data output request may include one or more device identifications at the same time, that is, the execution subject may send data to multiple target devices at the same time for sharing and use.

[0142] Exemplarily, if the above-mentioned execution entity is a network disk server, the user can check and browse the received data through the corresponding network disk application on the target device. If there is no corresponding network disk application on the target device, the user can choose to install the network disk application or choose other corresponding applications to check and browse the received data. For example, for document files, the user can choose wps or Microsoft application to check and browse the document file; for video files, the user can choose other types of video players to check and browse; for image files, the user can choose image viewing or editing applications to check, browse or edit.

[0143] The data processing method provided by the embodiment of the present disclosure can receive a data output request before or after data processing, and output corresponding data to the target device according to the device identifier in the data output request, so as to improve the circulation and interactivity of the data, facilitate users to browse and consume the corresponding data on different devices, and improve the usage method and usage rate of the data.

[0144] The data processing methods in the above embodiments are all for processing the data in the initial data set and the data in the original files to which it belongs. The present disclosure also provides a data processing method for obtaining the initial data set so as to execute the above data processing process.

[0145] Figure 4 FIG. 4 shows a flow chart 400 of an embodiment of a data processing method according to the present disclosure, wherein the data processing method is a process of processing data to obtain an initial data set. Figure 4 As shown, the data processing method includes the following steps:

[0146] Step S401: obtaining a data extraction request and candidate extraction data.

[0147] In the embodiments of the present disclosure, the execution subject of the data processing method, for example Figure 1 The terminal device 101 or the server 103 shown obtains a data extraction request and candidate extraction data corresponding to the data extraction request.

[0148] In this solution, the candidate extraction data may be data in all terminals or applications within the data acquisition authority of the execution subject.

[0149] Exemplarily, taking the network disk as an example, the execution entity is the network disk server, and the corresponding candidate extraction data can be data stored in the network disk, or data in other applications outside the network disk, such as chat records, articles, videos and other data in interactive applications such as WeChat, and image data, video data, template data, etc. in image or video generation or editing software such as cameras, Bilibili, Meitu XiuXiu or Jianying, and can also be image data, text and / or chart data, etc. in various browsers, reading or note-taking applications.

[0150] Correspondingly, the data extraction request may include a collection request after a screenshot operation, a collection request after a video is edited, a clipping request after text data or a file is selected, a clipping request after audio data is generated or edited, etc.

[0151] In some optional implementations, the data extraction request may also include a compilation type data processing request. Exemplarily, the data extraction request includes generating general description data based on the selected data or files, such as an overall content summary, a viewpoint summary, or a role summary.

[0152] In some optional implementations, the data extraction request may also include a data processing request of a tagging type. Exemplarily, the data extraction request includes tagging keywords or key sentences from the candidate extraction data, such as key data or arrays, sentences expressing opinions, and the like.

[0153] Step S402, determining the original file to which the candidate extracted data belongs and the position identifier of the candidate extracted data in the original file.

[0154] In the embodiments of the present disclosure, the execution subject of the data processing method, for example Figure 1 The terminal device 101 or server 103 shown, after receiving the candidate extraction data, if the candidate extraction data is not a complete original file, such as a partial chapter of a file, a summary of part of the content, a key paragraph or sentence, etc., determines the original file to which the candidate extraction data belongs and the position identifier of the candidate extraction data in the original file.

[0155] The data types of the candidate extracted data and the original files to which they belong may be the same or different. For example, if the candidate extracted data is image data, the original files to which they belong may be document files, video files, or image files; for another example, if the candidate extracted data is audio data, the original files to which they belong may be video files or audio files.

[0156] In this solution, after receiving the candidate extraction data, the execution entity determines the original file to which the candidate extraction data belongs, and can also determine and mark the file identifier corresponding to the original file, such as the file name, file type, link or address of the file location, etc.

[0157] Exemplarily, the position identifier of the candidate extracted data in the original file includes the page number identifier of the candidate extracted data in the original document file to which it belongs, or the page number and paragraph identifier or the line number identifier, or the timestamp of the candidate extracted data in the original video file or the original audio file, such as the duration identifier of the position where the candidate extracted data appears in the video or audio, or the orientation identifier of the candidate extracted data in the original image data, etc.

[0158] Step S403: Process candidate extraction data according to the data extraction request to obtain pre-extraction data.

[0159] In the embodiments of the present disclosure, the execution subject of the data processing method, for example Figure 1 The terminal device 101 or the server 103 shown processes the candidate extraction data according to the data extraction request to obtain the pre-extraction data.

[0160] Exemplarily, the execution subject processes the candidate extraction data according to the extraction type in the received data extraction request to obtain the pre-extracted data. The extraction type in the data extraction request includes a data type and a processing type. Exemplarily, the data type is the data type of the pre-extracted data, and the processing type is the operation type corresponding to the data processing required to obtain the pre-extracted data based on the candidate extraction data.

[0161] In some optional implementations, the data type in the data extraction request is the same as the data type of the candidate extraction data. For example, the data type in the data extraction request and the data type of the candidate extraction data are both text type, video type, and audio type.

[0162] Exemplarily, in this implementation, the execution subject pre-processes the candidate extraction data according to the processing type in the data extraction request to obtain the pre-extracted data. For example, the processing type is summarization, marking, etc., and the execution subject obtains the pre-extracted data after performing corresponding processing on the candidate extraction data.

[0163] In some optional implementations, the data type in the data extraction request is different from the data type of the candidate extracted data. For example, the data type in the data extraction request is a text type, and the data type of the candidate extracted data is a video type or an audio type. For another example, the data type in the data extraction request is an image type, and the data type of the candidate extracted data is a video type.

[0164] In this implementation, the execution subject performs type conversion on the data content of the candidate extraction data to obtain converted data whose data type is consistent with the data type in the data extraction request, and then performs corresponding processing operations according to the processing type in the data extraction request to obtain corresponding pre-extracted data.

[0165] In some optional implementations of the embodiments of the present disclosure, candidate extraction data is processed according to a data extraction request to obtain pre-extracted data, including: in response to the data extraction request not including a preprocessing request, determining the candidate extraction data as pre-extracted data; in response to the data extraction request including a preprocessing request, determining the processing type of the preprocessing request; in response to the processing type being a compiled type, determining compiled data corresponding to the candidate extraction data, and determining the compiled data as pre-extracted data; in response to the processing type being a marked type, determining marked data in the candidate extraction data, and determining the marked data as pre-extracted data.

[0166] In this implementation, when the executing entity determines that the data extraction request does not include a preprocessing request, it is considered that there is no need to further process the candidate extracted data and it can be directly determined as pre-extracted data; when it is determined that the data extraction request includes a preprocessing request, the processing type of the preprocessing request is first determined, and the candidate extracted data is processed according to the processing type to obtain the corresponding pre-extracted data.

[0167] The execution entity preprocesses the candidate extraction data according to the preprocessing request and its processing type in the data extraction request, effectively ensuring the accuracy of the extracted data, avoiding excessive unnecessary data from occupying storage space, and saving resources.

[0168] Step S404: associate and save the pre-extracted data, the file identifier and the location identifier of the original file to obtain an initial data set.

[0169] In the embodiments of the present disclosure, the execution subject of the data processing method, for example Figure 1 The terminal device 101 or the server 103 shown associates and stores the pre-extracted data obtained in step S403 and the file identifier of the original file to which it belongs and the position identifier of the corresponding candidate extracted data in the original file to obtain an initial data set.

[0170] The data processing method provided by the disclosed embodiment determines the original file corresponding to the candidate extraction data and its position identifier in the original file according to the received data extraction request and the corresponding candidate extraction data, and pre-processes the candidate extraction data according to the data extraction request to obtain pre-extracted data, and associates and saves the pre-extracted data, the corresponding original file and its position identifier in the original file to obtain an initial data set. This solution not only saves the pre-extracted data, but also saves the original file corresponding to the pre-extracted data and its position identifier in the original file. Compared with the traditional solution of saving the full text of the original file, it can effectively reduce the demand for storage space and save resources. At the same time, it is convenient to understand the extracted content based on the pre-extracted data, to obtain the original file to which it belongs and the associated content in the original file, and to improve data utilization efficiency.

[0171] Figure 5a to Figure 5cSchematic diagrams of data in a data processing method provided according to an embodiment of the present disclosure are respectively shown, wherein: Figure 5a A schematic diagram for extracting content from a browsed web page. Figure 5b A schematic diagram for extracting relevant content from public account articles in interactive software; Figure 5c The figure is a schematic diagram of part of the data in the initial data set obtained according to the data processing method of the present disclosure.

[0172] As an implementation of the methods shown in the above figures, Figure 6 FIG. 6 shows an embodiment of a data processing device according to the present disclosure. Figure 2 , Figure 3 Corresponding to the method embodiment shown, the device can be applied to various electronic devices.

[0173] Reference Figure 6 As shown, the data processing device 600 provided by the embodiment of the present disclosure includes: a first acquisition module 601, a first determination module 602, a second determination module 603 and a first processing module 604. The first acquisition module 601 is configured to acquire an initial data set, which includes pre-extracted data, a file identifier of an original file to which the pre-extracted data belongs, and a position identifier of the pre-extracted data in the original file; the first determination module 602 is configured to determine target data from the pre-extracted data according to the received data processing request, and determine the style features of the target data; the second determination module 603 is configured to determine the data to be processed from the corresponding original file according to the position identifier of the target data; the first processing module 604 is configured to process the data to be processed according to the data processing request and the style features to obtain a data processing result.

[0174] In the data processing device 600 of the embodiment of the present disclosure, the specific processing of the first acquisition module 601, the first determination module 602, the second determination module 603 and the first processing module 604 and the technical effects thereof can be referred to in detail. Figure 2 The relevant descriptions of steps S201 to S204 in the corresponding embodiment are not repeated here.

[0175] In some optional implementations of the embodiments of the present disclosure, the first determination module includes: an acquisition unit, a first identification unit, and a first determination unit. The acquisition unit is configured to acquire a data processing request; the first unit is configured to identify a data content identifier in the data processing request; and the first determination unit is configured to determine target data from pre-extracted data according to the data content identifier.

[0176] In some optional implementations of the embodiments of the present disclosure, the first determination module further includes an obtaining unit, which is configured to input the target data into a pre-trained speech model to obtain style features of the target data.

[0177] In some optional implementations of the embodiments of the present disclosure, the first processing module includes a second identification unit, a second determination unit, and a processing unit. The second identification unit is configured to identify the target type and the operation type in the data processing request; the second determination unit is configured to determine the pre-processed data according to the target type and the data to be processed, and the data type of the pre-processed data is adapted to the target type; the processing unit is configured to process the pre-processed data according to the operation type to obtain the data processing result.

[0178] In the data processing device of the embodiment of the present disclosure, the specific processing of the second identification unit, the second determination unit and the processing unit and the technical effects brought about by them can be referred to respectively. Figure 3 The relevant descriptions of steps S304-S306 in the corresponding embodiment are not repeated here.

[0179] In some optional implementations of the embodiments of the present disclosure, the target type includes at least one of the following: text type, image type, video type, audio type; and the operation type includes at least one of the following: text editing, image processing, video editing, video generation, audio extraction or audio generation.

[0180] In some optional implementations of the embodiments of the present disclosure, the second determination unit is configured to: determine a candidate type that is adapted to the target type based on the target type; determine the data to be processed as preprocessed data in response to the initial type of the data to be processed being compatible with the candidate type; in response to the initial type of the data to be processed being incompatible with the candidate type, identify content to be processed of the data to be processed, and compile the content to be processed into preprocessed data that conforms to the candidate type.

[0181] In some optional implementations of the embodiments of the present disclosure, the processing unit is configured to: determine a pre-trained data processing model according to an operation type; and input pre-processed data into the pre-trained data processing model to obtain a data processing result.

[0182] In some optional implementations of the embodiments of the present disclosure, the data processing device further includes a second acquisition module, a third determination module and an output module. The second acquisition module is configured to acquire a data output request; the third determination module is configured to determine a target device according to a device identifier in the data output request; and the output module is configured to output the data to be processed and / or the data processing result to the target device.

[0183] In the data processing device of the embodiment of the present disclosure, the specific processing of the second acquisition module, the third determination module and the output module and the technical effects brought by them can be referred to. Figure 3 The relevant descriptions of steps S307-S309 in the corresponding embodiment are not repeated here.

[0184] Figure 7 FIG. 700 is a diagram showing an embodiment of a data processing device according to the present disclosure. Figure 4 Corresponding to the method embodiment shown, the device can be applied to various electronic devices.

[0185] Reference Figure 7 As shown, the data processing device 700 provided by the embodiment of the present disclosure includes: a third acquisition module, a fourth determination module, a second processing module and a storage module. The third acquisition module is configured to acquire a data extraction request and candidate extraction data; the fourth determination module is configured to determine the original file to which the candidate extraction data belongs and the position identifier of the candidate extraction data in the original file; the second processing module is configured to process the candidate extraction data according to the data extraction request to obtain pre-extracted data; the storage module is configured to associate and store the pre-extracted data, the file identifier and the position identifier of the original file to obtain an initial data set.

[0186] In the data processing device of the embodiment of the present disclosure, the specific processing of the third acquisition module, the fourth determination module, the second processing module and the storage module and the technical effects thereof can be referred to. Figure 4 The relevant descriptions of steps S401 to S404 in the corresponding embodiment are not repeated here.

[0187] In some optional implementations of the embodiments of the present disclosure, the second processing module is configured to: in response to the data extraction request not including a preprocessing request, determine the candidate extraction data as pre-extracted data; in response to the data extraction request including a preprocessing request, determine the processing type of the preprocessing request; in response to the processing type being a compilation type, determine the compiled data corresponding to the candidate extraction data, and determine the compiled data as pre-extracted data; in response to the processing type being a marking type, determine the marking data in the candidate extraction data, and determine the marking data as pre-extracted data.

[0188] 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.

[0189] Figure 8A schematic block diagram of an example electronic device 800 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.

[0190] like Figure 8 As shown, the device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The computing unit 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0191] A number of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0192] The computing unit 801 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 801 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 801 performs the various methods and processes described above, such as data processing methods. For example, in some embodiments, the data processing method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the data processing method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the data processing method in any other appropriate manner (e.g., by means of firmware).

[0193] 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), load 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.

[0194] 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.

[0195] 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.

[0196] 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).

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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 data processing method, comprising: Acquire an initial data set, the initial data set including pre-extracted data, a file identifier of an original file to which the pre-extracted data belongs, and a position identifier of the pre-extracted data in the original file; Determining target data from the pre-extracted data according to the received data processing request, and determining style features of the target data; According to the location identifier of the target data, determining the data to be processed from the corresponding original file; Identifying a target type and an operation type in the data processing request; According to the target type and the data to be processed, preprocessing data is determined, and the data type of the preprocessing data is compatible with the target type; the preprocessing data is processed according to the operation type and in combination with the style features of the target data to obtain a data processing result.

2. The method according to claim 1, wherein: The step of determining target data from the pre-extracted data according to the received data processing request includes: Get data processing request; Identifying a data content identifier in the data processing request; The target data is determined from the pre-extracted data according to the data content identifier.

3. The method according to claim 1, wherein: The determining of the style features of the target data includes: The target data is input into a pre-trained language model to obtain style features of the target data.

4. The method according to claim 1, wherein: The target type includes at least one of the following: text type, image type, video type, audio type; and The operation type includes at least one of the following: text editing, image processing, video clipping, video generation, audio extraction or audio generation.

5. The method according to claim 1, wherein: The step of determining the pre-processing data according to the target type and the data to be processed includes: According to the target type, determining a candidate type suitable for the target type; In response to the initial type of the data to be processed being compatible with the candidate type, determining the data to be processed as pre-processed data; In response to the initial type of the data to be processed not matching the candidate type, the content to be processed of the data to be processed is identified, and the content to be processed is compiled into pre-processed data matching the candidate type.

6. The method according to claim 1, wherein: The step of processing the pre-processed data according to the operation type to obtain a data processing result includes: Determining a pre-trained data processing model according to the operation type; The preprocessed data is input into the pretrained data processing model to obtain the data processing result.

7. The method according to any one of claims 1 to 6, further comprising: Get data output request; Determining a target device according to a device identifier in the data output request; The data to be processed and / or the data processing result are output to the target device.

8. A data processing method, comprising: Obtain data extraction requests and candidate extraction data; Determine the original file to which the candidate extracted data belongs and the position identifier of the candidate extracted data in the original file; Process the candidate extraction data according to the data extraction request to obtain pre-extraction data; The pre-extracted data, the file identifier of the original file and the location identifier are associated and saved to obtain an initial data set; Acquire the initial data set; Determining target data from the pre-extracted data according to the received data processing request, and determining style features of the target data; According to the location identifier of the target data, determining the data to be processed from the corresponding original file; Identifying a target type and an operation type in the data processing request; According to the target type and the data to be processed, preprocessing data is determined, and the data type of the preprocessing data is compatible with the target type; the preprocessing data is processed according to the operation type and in combination with the style features of the target data to obtain a data processing result.

9. The method according to claim 8, wherein: The step of processing the candidate extraction data according to the data extraction request to obtain pre-extraction data includes: In response to the data extraction request not including a pre-processing request, determining the candidate extraction data as pre-extraction data; In response to the data extraction request including a preprocessing request, determining a processing type of the preprocessing request; In response to the processing type being a compilation type, determining compiled data corresponding to the candidate extracted data, and determining the compiled data as pre-extracted data; In response to the processing type being a marking type, marking data in the candidate extracted data is determined, and the marking data is determined as pre-extracted data.

10. A data processing device, comprising: A first acquisition module is configured to acquire an initial data set, wherein the initial data set includes pre-extracted data, a file identifier of an original file to which the pre-extracted data belongs, and a position identifier of the pre-extracted data in the original file; A first determination module is configured to determine target data from the pre-extracted data according to the received data processing request, and determine style features of the target data; A second determination module is configured to determine the data to be processed from the corresponding original file according to the location identifier of the target data; The first processing module comprises: a second identification unit, configured to identify a target type and an operation type in the data processing request; A second determining unit is configured to determine pre-processing data according to the target type and the data to be processed, wherein the data type of the pre-processing data is adapted to the target type; The processing unit is configured to process the pre-processed data according to the operation type and in combination with the style features of the target data to obtain a data processing result.

11. The device according to claim 10, wherein: The first determining module comprises: an acquisition unit configured to acquire a data processing request; A first identification unit, configured to identify a data content identifier in the data processing request; The first determining unit is configured to determine the target data from the pre-extracted data according to the data content identifier.

12. The device according to claim 10, wherein: The first determining module comprises: The obtaining unit is configured to input the target data into a pre-trained language model to obtain the style features of the target data.

13. The device according to claim 10, wherein: The target type includes at least one of the following: text type, image type, video type, audio type; and The operation type includes at least one of the following: text editing, image processing, video clipping, video generation, audio extraction or audio generation.

14. The device according to claim 10, wherein: The second determining unit is configured to: According to the target type, determining a candidate type suitable for the target type; In response to the initial type of the data to be processed being compatible with the candidate type, determining the data to be processed as pre-processed data; In response to the initial type of the data to be processed not matching the candidate type, the content to be processed of the data to be processed is identified, and the content to be processed is compiled into pre-processed data matching the candidate type.

15. The device according to claim 10, wherein: The processing unit is configured to: Determining a pre-trained data processing model according to the operation type; The preprocessed data is input into the pretrained data processing model to obtain the data processing result.

16. The device according to any one of claims 10 to 15, further comprising: A second acquisition module is configured to acquire a data output request; A third determination module is configured to determine a target device according to a device identifier in the data output request; The output module is configured to output the data to be processed and / or the data processing result to the target device.

17. A data processing device, comprising: A third acquisition module is configured to acquire a data extraction request and candidate extraction data; A fourth determination module is configured to determine the original file to which the candidate extracted data belongs and a position identifier of the candidate extracted data in the original file; A second processing module is configured to process the candidate extraction data according to the data extraction request to obtain pre-extraction data; A saving module is configured to associate and save the pre-extracted data, the file identifier of the original file and the location identifier to obtain an initial data set; A first acquisition module is configured to acquire the initial data set; A first determination module is configured to determine target data from the pre-extracted data according to the received data processing request, and determine style features of the target data; A second determination module is configured to determine the data to be processed from the corresponding original file according to the location identifier of the target data; The first processing module comprises: a second identification unit, configured to identify a target type and an operation type in the data processing request; A second determining unit is configured to determine pre-processing data according to the target type and the data to be processed, wherein the data type of the pre-processing data is adapted to the target type; The processing unit is configured to process the pre-processed data according to the operation type and in combination with the style features of the target data to obtain a data processing result.

18. The device according to claim 17, wherein: The second processing module is configured as follows: In response to the data extraction request not including a pre-processing request, determining the candidate extraction data as pre-extraction data; In response to the data extraction request including a preprocessing request, determining a processing type of the preprocessing request; In response to the processing type being a compilation type, determining compiled data corresponding to the candidate extracted data, and determining the compiled data as pre-extracted data; In response to the processing type being a marking type, marking data in the candidate extracted data is determined, and the marking data is determined as pre-extracted data.

19. An electronic device comprising: 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 9.

20. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-9.

21. 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 9.

Images