A chart processing method and device, a storage medium and an electronic device

Abstract

Embodiments of the present specification disclose a chart processing method and device, a storage medium and an electronic device, wherein the method comprises: obtaining a table data picture to be recognized input by a user, performing table data extraction on the table data picture by using a chart processing large model to obtain a picture extraction result, and performing table file conversion based on the picture extraction result to obtain a spreadsheet file, and displaying the picture extraction result and the spreadsheet file.

Description

Technical Field

[0001] This specification relates to the field of computer technology, and in particular to a chart processing method, apparatus, storage medium, and electronic device. Background Technology

[0002] In today's rapidly developing information and digital age, charts, as an intuitive way of expressing data, are widely used in business analysis, academic research, and public communication. Currently, the storage and display of chart data mostly rely on static images (such as PNG, JPEG, PDF, etc.). Charts based on static images often require manual editing of the chart data in charting software for reuse and reanalysis. Summary of the Invention

[0003] This specification provides a chart processing method, apparatus, storage medium, and electronic device, the technical solutions of which are as follows:

[0004] Firstly, embodiments of this specification provide a chart processing method, the method comprising:

[0005] Obtain the image of the table data to be recognized, input by the user;

[0006] A large-scale chart processing model is used to extract table data from the image data to obtain image extraction results, and then the table file is converted based on the image extraction results to obtain an electronic spreadsheet file;

[0007] The image extraction results and the spreadsheet file are displayed.

[0008] In one feasible implementation, the step of using a large-scale chart processing model to extract table data from the image to obtain an image extraction result, and then converting the image extraction result into a chart file to obtain a spreadsheet file, includes:

[0009] Input the image of the table data into the large chart processing model;

[0010] The table data category corresponding to the table data image is determined by the large chart processing model. Based on the table data category, the table data image is extracted to obtain the image extraction result. Based on the table data category and the image extraction result, the table data is edited and processed in a preset chart software to generate a spreadsheet file.

[0011] In one feasible implementation, the step of extracting table data from the table data image based on the table data category to obtain an image extraction result, and then performing table data editing processing in a preset charting software to generate a spreadsheet file based on the table data category and the image extraction result, includes:

[0012] If the table data category is a table type, then the table data in the table data image is extracted to obtain the first table data, and the first table data is used as the image extraction result;

[0013] If the table data category is a chart type, then the chart data in the table data image is subjected to chart semantic parsing to obtain chart parsing information, the chart parsing information is converted into a chart format to obtain second table data, and the second table data is used as the image extraction result.

[0014] In one feasible implementation, the step of generating a spreadsheet file by editing the table data in a preset charting software based on the table data category and the image extraction results includes:

[0015] If the table data category is a table type, then the table data is edited and processed based on the image extraction results in the preset chart software to obtain spreadsheet data, and a spreadsheet file is generated based on the spreadsheet data;

[0016] If the table data category is a chart type, then the table data is edited and processed based on the image extraction results in the preset chart software to obtain spreadsheet text data, and spreadsheet chart data is drawn based on the spreadsheet text data in the preset chart software, and a spreadsheet file is generated based on the spreadsheet data and the spreadsheet chart data.

[0017] In one feasible implementation, displaying the image extraction results and the spreadsheet file includes:

[0018] The user interface displays the image extraction results and the operation options for the image extraction results:

[0019] And display file operation options for the spreadsheet file in the user interface;

[0020] The method further includes:

[0021] In response to a first trigger operation for the result operation option, the image extraction result is processed by the result operation;

[0022] In response to a second triggered operation on the spreadsheet file, file operation processing is performed on the spreadsheet file.

[0023] In one feasible implementation, the method further includes:

[0024] The user interface displays editing options for the extracted image results.

[0025] In response to a third triggered operation for the result editing option, obtain the user's result adjustment information for the image extraction result, and adjust the chart data based on the result adjustment information.

[0026] In one feasible implementation, obtaining the user's adjustment information regarding the image extraction results, and adjusting the chart data based on the adjustment information, includes:

[0027] Obtain the user's adjustment information regarding the image extraction results;

[0028] If the result adjustment information contains table adjustment data for the image extraction result, then the result data of the image extraction result is adjusted based on the table adjustment data, and the table data of the spreadsheet file is adjusted based on the table adjustment data, to obtain the adjusted image extraction result and the spreadsheet file;

[0029] If the result adjustment information contains table data category conversion information for the table data image, then the target table data category is determined based on the result adjustment information. Based on the target table data category, the target spreadsheet image data of the target table data category is generated in the spreadsheet file using the image extraction results. The spreadsheet file is then updated based on the target spreadsheet image data.

[0030] Secondly, embodiments of this specification provide a chart processing apparatus, the apparatus comprising:

[0031] The image acquisition module is used to acquire images of the table data to be recognized, input by the user.

[0032] The chart processing module is used to extract the table data from the image using a large chart processing model, and then convert the image into a spreadsheet file based on the extracted image.

[0033] The data display module is used to display the image extraction results and the spreadsheet file.

[0034] In one feasible implementation, the chart processing module is configured to:

[0035] Input the image of the table data into the large chart processing model;

[0036] The table data category corresponding to the table data image is determined by the large chart processing model. Based on the table data category, the table data image is extracted to obtain the image extraction result. Based on the table data category and the image extraction result, the table data is edited and processed in a preset chart software to generate a spreadsheet file.

[0037] In one feasible implementation, the chart processing module is configured to:

[0038] If the table data category is a table type, then the table data in the table data image is extracted to obtain the first table data, and the first table data is used as the image extraction result;

[0039] If the table data category is a chart type, then the chart data in the table data image is subjected to chart semantic parsing to obtain chart parsing information, the chart parsing information is converted into a chart format to obtain second table data, and the second table data is used as the image extraction result.

[0040] In one feasible implementation, the chart processing module is configured to:

[0041] If the table data category is a table type, then the table data is edited and processed based on the image extraction results in the preset chart software to obtain spreadsheet data, and a spreadsheet file is generated based on the spreadsheet data;

[0042] If the table data category is a chart type, then the table data is edited and processed based on the image extraction results in the preset chart software to obtain spreadsheet text data, and spreadsheet chart data is drawn based on the spreadsheet text data in the preset chart software, and a spreadsheet file is generated based on the spreadsheet data and the spreadsheet chart data.

[0043] In one feasible implementation, the data display module is used for:

[0044] The user interface displays the image extraction results and the operation options for the image extraction results:

[0045] And display file operation options for the spreadsheet file in the user interface;

[0046] The device is also used for:

[0047] In response to a first trigger operation for the result operation option, the image extraction result is processed by the result operation;

[0048] In response to a second triggered operation on the spreadsheet file, file operation processing is performed on the spreadsheet file.

[0049] In one feasible implementation, the device is further used for:

[0050] The user interface displays editing options for the extracted image results.

[0051] In response to a third triggered operation for the result editing option, obtain the user's result adjustment information for the image extraction result, and adjust the chart data based on the result adjustment information.

[0052] In one feasible implementation, the device is further used for:

[0053] Obtain the user's adjustment information regarding the image extraction results;

[0054] If the result adjustment information contains table adjustment data for the image extraction result, then the result data of the image extraction result is adjusted based on the table adjustment data, and the table data of the spreadsheet file is adjusted based on the table adjustment data, to obtain the adjusted image extraction result and the spreadsheet file;

[0055] If the result adjustment information contains table data category conversion information for the table data image, then the target table data category is determined based on the result adjustment information. Based on the target table data category, the target spreadsheet image data of the target table data category is generated in the spreadsheet file using the image extraction results. The spreadsheet file is then updated based on the target spreadsheet image data.

[0056] Thirdly, embodiments of this specification provide a computer storage medium storing a plurality of instructions adapted for loading by a processor and executing the above-described method steps.

[0057] Fourthly, embodiments of this specification provide an electronic device that may include: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to execute the above-described method steps.

[0058] The beneficial effects of the technical solutions provided in some embodiments of this specification include at least the following:

[0059] In one or more embodiments of this specification, by acquiring a user-input image of table data to be identified, a large-scale chart processing model is used to extract table data from the image to obtain image extraction results. Based on these results, a spreadsheet file is generated, and the image extraction results and the spreadsheet file are displayed. This achieves efficient conversion from user-uploaded table data images to structured spreadsheet files. By leveraging the powerful processing capabilities of a pre-trained large-scale chart processing model, the image extraction results are accurately extracted from the charts, automatically generating editable spreadsheet files. A clear interface for displaying the extraction results is also provided. This significantly reduces the complexity of manual operations, improves the efficiency and accuracy of data extraction, and allows users to flexibly apply the extraction results in subsequent analysis and processing, greatly enhancing the value of data reuse. Attached Figure Description

[0060] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0061] Figure 1 This is a schematic diagram of a chart processing system provided in the embodiments of this specification;

[0062] Figure 2 This is a flowchart illustrating a chart processing method provided in the embodiments of this specification;

[0063] Figure 3 This is a schematic diagram of a front-end interface that supports user-uploaded images for chart processing, provided in the embodiments of this specification.

[0064] Figure 4 This is a schematic diagram of a display interface provided in an embodiment of this specification;

[0065] Figure 5 This is a schematic diagram of a large-scale chart processing model provided in the embodiments of this specification;

[0066] Figure 6 This is a schematic diagram of an interface display process provided in an embodiment of this specification;

[0067] Figure 7 This is a schematic diagram of an interface display process provided in an embodiment of this specification;

[0068] Figure 8 This is a schematic diagram of the structure of a chart processing device provided in the embodiments of this specification;

[0069] Figure 9 This is a schematic diagram of the structure of an electronic device provided in the embodiments of this specification;

[0070] Figure 10 This is a schematic diagram of the operating system and user space structure provided in the embodiments of this specification;

[0071] Figure 11 yes Figure 10 Architecture diagram of the Android operating system in China;

[0072] Figure 12 yes Figure 10 Architecture diagram of the iOS operating system. Detailed Implementation

[0073] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this specification.

[0074] In the description of this specification, it should be understood that the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. In the description of this specification, it should be noted that, unless otherwise expressly specified and limited, "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices. Those skilled in the art can understand the specific meaning of the above terms in this specification based on the specific circumstances. Furthermore, in the description of this specification, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship.

[0075] In related technologies, the storage and display of chart data mostly rely on static images (such as PNG, JPEG, PDF, etc.). Chart display based on static images often involves manually re-editing the chart data in chart software for data reuse and re-analysis.

[0076] Manual editing has the following limitations:

[0077] 1) Difficulty in data extraction

[0078] The core information in static charts is presented in the form of images. Directly reading the data requires manual operation, which is not only time-consuming and labor-intensive but also prone to errors. This is especially true when dealing with complex chart types (such as multidimensional bar charts or stacked pie charts), where manual extraction becomes even more difficult.

[0079] 2) Data conversion is limited

[0080] Even when data is obtained manually, quickly and accurately converting it into a foundational data table for further analysis and visualization remains a significant challenge. Existing tools offer limited support, especially for scenarios requiring precise calculations (such as proportional conversions and data merging).

[0081] 3) Insufficient data reuse capability

[0082] Many charts are only meaningful in specific display contexts, but users may want to reorganize and display data in other forms (such as converting a pie chart to a bar chart). Currently, users need to rely on multiple tools and complex procedures to achieve this, which is very unfriendly to the average user.

[0083] Given the aforementioned limitations, it's clear that current chart processing methods are not only time-consuming and labor-intensive but also prone to errors, especially when dealing with complex chart types. While existing OCR and visual technologies have made significant progress in text recognition, their support for the automatic extraction, transformation, and visualization of chart data remains insufficient. Users often need to rely on multiple tools to complete data processing and reuse. This technological limitation severely impacts the efficiency and flexibility of data analysis, necessitating an efficient and automated solution to overcome all or part of these limitations and achieve a complete workflow from images to structured data tables and diverse chart displays.

[0084] The present specification will now be described in detail with reference to specific embodiments.

[0085] Please see Figure 1 This is a schematic diagram of a chart processing system provided in an embodiment of this application. Figure 1 As shown, the chart processing system may include at least a client cluster and a service platform 100.

[0086] In some embodiments, the client cluster may include at least one client, such as Figure 1 As shown, it specifically includes client 1 corresponding to user 1, client 2 corresponding to user 2, ..., client n corresponding to user n, where n is an integer greater than 0.

[0087] Each client in a client cluster can be an electronic device with communication capabilities, including but not limited to: wearable devices, handheld devices, personal computers, tablets, in-vehicle devices, smartphones, computing devices, or other processing devices connected to a wireless modem. Electronic devices may have different names in different networks, such as: user equipment, access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication equipment, user agent or user device, cellular phone, cordless phone, personal digital assistant (PDA), and electronic devices in 5G networks or future evolved networks.

[0088] In some embodiments, the service platform 100 may be a single server device, such as a rack-mounted, blade, tower, or cabinet-type server device, or a workstation, mainframe, or other hardware device with strong computing power; or it may be a server cluster composed of multiple servers, wherein the servers in the service cluster may be composed in a symmetrical manner, wherein each server is functionally and hierarchically equivalent in the transaction link, and each server can provide services to the outside world independently, wherein providing services independently can be understood as not requiring the assistance of other servers.

[0089] In one or more embodiments of this specification, the service platform 100 may establish a communication connection with at least one client in the client cluster, and complete the data interaction during the chart processing based on the communication connection.

[0090] For example, service platform 100 provides search services to external parties. Users can send images of table data to be identified to service platform 100 through a client. Service platform 100 can obtain the image of table data to be identified input by the user, use a large chart processing model to extract table data from the image to obtain image extraction results, and convert the image extraction results into a spreadsheet file. Service platform 100 instructs the client to display the image extraction results and the spreadsheet file.

[0091] It should be noted that the service platform 100 establishes a communication connection with at least one client in the client cluster for interactive communication via a network. This network can be a wireless network or a wired network. Wireless networks include, but are not limited to, cellular networks, wireless LANs, infrared networks, or Bluetooth networks. Wired networks include, but are not limited to, Ethernet, universal serial bus (USB), or controller area networks. In one or more embodiments of the specification, technologies and / or formats including Hyper Text Markup Language (HTML), Extensible Markup Language (XML), etc., are used to represent data exchanged over the network (such as target compressed packets). Furthermore, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Network (VPN), and Internet Protocol Security (IPsec) can be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies can be used to replace or supplement the aforementioned data communication technologies.

[0092] The chart processing system embodiments provided in this specification and the chart processing methods described in one or more embodiments belong to the same concept. The execution entity corresponding to the chart processing methods involved in one or more embodiments of this specification can be an electronic device, which can be the aforementioned service platform 100 or the aforementioned client, depending on the actual application environment. The specific implementation process of the demonstration file generation system embodiment can be found in the following method embodiments, and will not be repeated here.

[0093] In one embodiment, such as Figure 2 As shown, a chart processing method is proposed, which can be implemented using a computer program and run on a chart processing device based on the von Neumann architecture. This computer program can be integrated into an application or run as a standalone utility application. The chart processing device can be an electronic device.

[0094] Specifically, the chart processing method includes:

[0095] S102: Obtain the image of the table data to be recognized input by the user;

[0096] Table data images: These refer to user-uploaded images (such as still images and animated images) that contain visual table data, such as tables and charts. Common formats for table data images include JPEG, PNG, PDF, and others.

[0097] As an illustration, the user selects or uploads an image of the table data to be processed to the service platform through the front-end interface. The service platform then receives the image of the table data to be recognized from the user's input. Optionally, it can validate the uploaded file format to ensure it is a supported type (such as JPEG or PNG). The image is then passed to the back-end processing module to proceed to the next step of the recognition process.

[0098] For example, such as Figure 3 As shown, Figure 3 This is a schematic diagram of a front-end interface that supports user-uploaded images for chart processing. Figure 3 The app displays the chart processing function description "One-click chart extraction, instantly convert to Excel download" and lists the supported image formats. Users can input the table data image to be recognized by dragging and dropping images, copying and pasting images, taking screenshots, or using image links.

[0099] S104: Use a large chart processing model to extract table data from the image of the table data to obtain the image extraction result, and convert the table file based on the image extraction result to obtain an electronic spreadsheet file;

[0100] Large-scale chart processing model: A deep learning-based artificial intelligence model specifically designed for parsing data in chart images, including visual feature extraction and data recognition. This may involve OCR technology, computer vision algorithms, and chart semantic understanding models.

[0101] Image extraction results: The original table data extracted from the image, including but not limited to the values ​​in the chart and the table text information (such as labels and titles).

[0102] Spreadsheet files: Structured tabular data files, in formats including but not limited to Excel and CSV files, to facilitate subsequent spreadsheet processing by users.

[0103] Large-scale graph processing model: A large-scale graph processing model is pre-trained and obtained by transferring the basic large-scale language model to graph processing scenarios. It can quickly apply the basic large-scale language model to a new graph processing domain. The basic large-scale language model itself has multimodal recognition capabilities, so there is no need to retrain a new model. Only fine-tuning training of the basic large-scale language model for graph processing scenarios is required. Transferring and transforming the basic large-scale language model (which can be called an LLM model) to graph processing scenarios can realize a multimodal large-scale language model (which can be called MLLM) that is compatible with multimodal data such as text and images. This multimodal large-scale language model can perform graph processing, and the target graph processing operation is used to generate model input data. The multimodal large-scale language model obtained by transfer training can be called a large-scale graph processing model.

[0104] For example, user-uploaded image files (such as bar charts) are preprocessed to generate multimodal input data in a format suitable for input to a large chart model (such as standardized images and associated preliminary OCR text). The multimodal input data includes: image data (such as pixel information of the chart), preliminarily extracted text data (such as labels and titles recognized using OCR preprocessing technology), and chart processing task prompts (such as the model task instruction: "parse the bar chart data in the image"). The multimodal input data is then input into the large chart processing model. The model analyzes the chart content based on the chart processing task prompts, combined with visual and textual features from the image data. It extracts key data elements (such as horizontal and vertical axis data, legend information, and data values ​​in the case of a chart image), parses the chart's logical structure to generate preliminary structured data, and converts the key data elements and preliminary structured data into structured data forms (such as two-dimensional tables or JSON objects) to obtain the image extraction results. The image extraction results are then converted into standardized table files (such as Excel or CSV files) and exported as spreadsheet files in common formats.

[0105] S106: Display the image extraction results and the spreadsheet file.

[0106] The extracted image results are displayed visually on the interface, such as the original data table and a preview of the generated Excel file. Users can verify and confirm the image extraction results. A "Download" button is provided, allowing users to save the generated spreadsheet file locally, and the file format matches the target user's needs (such as .xlsx, .csv).

[0107] For example, such as Figure 4 As shown, Figure 4 It is a schematic diagram of a display interface. Figure 4The image displayed shows the results of extracting images of table data input by the user, along with the spreadsheet file. The interface includes the table data categories of the extracted images (e.g., ...). Figure 4 The image is displayed as a table (or similar file). The image extraction results area shows the extracted image of the table data after chart processing, along with a "copy" button for the extracted results. This allows users to copy the extracted results with a single click. The spreadsheet file also includes control options such as... Figure 4 The "Download Excel File" option displayed allows users to save the generated spreadsheet file to their local machine by triggering the "Download Excel File" option.

[0108] In one or more embodiments of this specification, by acquiring a user-input image of table data to be identified, a large-scale chart processing model is used to extract table data from the image to obtain image extraction results. Based on the image extraction results, a spreadsheet file is generated, and the image extraction results and the spreadsheet file are displayed. This enables efficient conversion from user-uploaded table data images to structured spreadsheet files. By leveraging the powerful processing capabilities of a pre-trained large-scale chart processing model, image extraction results are accurately extracted from charts, automatically generating editable spreadsheet files. A clear interface for displaying the extraction results is also provided. This significantly reduces the complexity of manual operations, improves the efficiency and accuracy of data extraction, and allows users to flexibly apply the extraction results in subsequent analysis and processing stages, greatly enhancing the value of data reuse.

[0109] Please see Figure 5 , Figure 5 This is a flowchart illustrating a large-scale chart processing model proposed in this specification. The process involves using the large-scale chart processing model to extract table data from the image, obtaining the extracted image results, and then converting the extracted image results into a chart file to obtain a spreadsheet file. This can be achieved in the following ways:

[0110] S202: Input the table data image into the large chart processing model;

[0111] In some embodiments, user-uploaded image files (such as bar charts) are preprocessed to generate multimodal input data in a format suitable for input to a large model (such as standardized images and associated preliminary OCR text). The multimodal input data includes: image data (e.g., pixel information of the chart), preliminarily extracted text data (e.g., labels and titles recognized using OCR preprocessing technology), and chart processing task prompts (e.g., model task instructions: "parse the bar chart data in the image"). The multimodal input data is then input into the large chart processing model.

[0112] S204: Determine the table data category corresponding to the table data image through the chart processing model, extract table data from the table data image based on the table data category to obtain the image extraction result, and perform table data editing processing in a preset chart software based on the table data category and the image extraction result to generate a spreadsheet file.

[0113] Table data categories: The chart processing model determines the corresponding table data type in the chart based on the table data image. Table data categories mainly include table types and chart types, such as bar charts, line charts, pie charts, scatter plots, etc.

[0114] Image extraction results: Structured data extracted from the chart image, including labels, data values, units, etc.

[0115] Preset charting software: refers to tools used to generate and edit spreadsheet files, such as Excel tools, Sheets tools, and chart generators with custom formats.

[0116] In a schematic way, the large-scale control model for chart processing determines the table data category corresponding to the table data image based on the chart processing task prompts. Specifically, after determining the table data category, the parsing method for this table data category is selected for different table data categories. The parsing method combines visual and textual features in the image data to analyze the chart content, extracts key data elements (such as horizontal and vertical axis data, legend information, and data values ​​in the case of chart images), parses the chart's logical structure to generate preliminary structured data, and converts the key data elements and preliminary structured data into structured data forms (such as two-dimensional tables or JSON objects) to obtain the image extraction results.

[0117] Optional. Different data categories require different parsing methods. For example, the parsing method for a bar chart is to extract the horizontal and vertical axis labels and their corresponding values. The parsing method for a pie chart is to extract the labels of each sector and their percentage. The parsing method for a line chart is to extract time series data and numerical points, etc.

[0118] Furthermore, based on the table data categories and image extraction results, the table data is edited and processed in a preset charting software to generate a spreadsheet file. Typically, the preset charting software is initialized, and the image extraction results are imported into a preset table editor template based on the table data categories. For example, table headers and column names (such as "month" and "sales") are added to the table editor template, and the values ​​are formatted to ensure that the units are consistent. Then, a spreadsheet file (such as an Excel file) is generated.

[0119] In one feasible implementation, performing table data extraction based on the table data category to obtain image extraction results can be done in the following manner:

[0120] Step A2: If the table data category is a table type, the chart processing big model extracts the table data from the table data image to obtain the first table data, and uses the first table data as the image extraction result;

[0121] Table type: A two-dimensional table contained in the image, which usually organizes data in a grid format, similar to a table in Excel or a form.

[0122] The first table data consists of structured data extracted directly from the table image, typically including the specific content of rows and columns.

[0123] For illustrative purposes, if the table data is of a table type, the large-scale chart processing model uses a table parsing method: 1) First, table location and detection: The large-scale chart processing model first detects the position of the table area in the table data image, uses an image segmentation tool to separate the grid lines, and clarifies the boundaries of each cell. 2) Then, text recognition and extraction: Using OCR technology, the model recognizes the table data within each cell, aligns the rows and columns of the recognized table data, and restores the table structure. 3) Based on the table structure and table data, the model generates the first table data: The extracted table content is converted into a standardized structured format (such as a two-dimensional array or a JSON object). Then, the first table data is used as the image extraction result.

[0124] Step A4: If the table data category is a chart type, the chart processing big model performs chart semantic parsing on the chart data in the table data image to obtain chart parsing information, performs chart format conversion on the chart parsing information to obtain second table data, and uses the second table data as the image extraction result.

[0125] Chart types: Images containing visual charts such as bar charts, pie charts, and line charts.

[0126] Chart semantic parsing: The large-scale chart processing model performs semantic analysis on the elements of the chart in the image (such as coordinate axes, legends, data points, etc.) and converts them into data relationships.

[0127] The second table data consists of structured data obtained from the semantic parsing of the chart, which is usually in the form of the original data table of the chart content.

[0128] For illustrative purposes, if the table data category is a chart type, the large-scale chart processing model identifies the chart type (bar chart, pie chart, etc.) and performs semantic parsing on the chart data in the table data image according to the corresponding chart type to obtain chart parsing information. For example, 1) First, table data element detection is performed: detecting the titles and scales of the axes, extracting legend labels (such as "Product A", "Product B"), and locating data points (such as the values ​​of bars and pie chart sectors); 2) Then, data association is performed to establish the table data relationship between data points and their labels and axes; 3) Chart parsing information is generated based on the table data relationship and table data elements.

[0129] Then, the chart parsing information is converted into a chart format to obtain second table data, that is, the chart parsing information is converted into second table data of table type, and the second table data is used as the image extraction result.

[0130] Using the above methods, regardless of whether it is a table or a chart, the large-scale chart processing model can ultimately transform the data in the image into structured data that users can use, meeting diverse data processing needs.

[0131] In one feasible implementation, the step of editing and processing the table data in a preset charting software based on the table data category and the image extraction results to generate a spreadsheet file can be performed as follows:

[0132] Step B2: If the table data category is a table type, then the table data is edited and processed in the preset chart software based on the image extraction results to obtain spreadsheet data, and a spreadsheet file is generated based on the spreadsheet data;

[0133] According to some embodiments, the data in the image is arranged in a two-dimensional grid format with clearly defined rows and columns, such as an Excel table or HTML table. Spreadsheet data: The extracted table content is stored in a structured format and can be used in spreadsheet software (such as Excel). Spreadsheet file: A file generated from spreadsheet data, commonly in .xlsx or .csv format, supporting data analysis and editing.

[0134] To illustrate, if the table data category is a table type, the control chart processing model standardizes the table created and filled with table data in a preset charting software (such as Excel), supplements necessary information (such as missing headers and units), ensures row and column alignment, removes noisy data, and generates complete spreadsheet data; then, it formats the spreadsheet data to generate a spreadsheet file, such as adding headers (if there are no complete headers in the extraction results), adjusting column widths, fonts, and other visual parameters to make the table easier to read.

[0135] Step B4: If the table data category is a chart type, then in the preset chart software, the table data is edited based on the image extraction results to obtain spreadsheet text data, and spreadsheet chart data is drawn based on the spreadsheet text data in the preset chart software, and a spreadsheet file is generated based on the spreadsheet data and the spreadsheet chart data.

[0136] Spreadsheet text data: Tabular data of text type extracted from and standardized from charts, reflecting the data relationships in the charts.

[0137] Spreadsheet chart data: Visual charts redrawn from spreadsheet data in a spreadsheet file, generated based on extracted spreadsheet data.

[0138] In a schematic manner, based on the image extraction results, the table data is edited in a preset charting software to obtain spreadsheet text data. Then, the charting function of the preset charting software is used to draw a chart based on the extracted spreadsheet text data, ensuring that the generated chart type is consistent with the original chart or meets the user's needs (such as converting from a bar chart to a line chart). The spreadsheet text data and the redrawn spreadsheet chart data are integrated into one file and exported as a common spreadsheet file format (such as .xlsx) for users to edit and analyze.

[0139] In one or more embodiments of this specification, a large-scale chart processing model is used to accurately parse table data images. This not only efficiently identifies data categories (such as table types or chart types) but also performs specialized processing for different categories, extracting structured data and performing semantic transformation. For table type images, the system directly generates neat and standardized spreadsheet data; for chart type images, the system uses semantic parsing and format conversion to restore the chart content to a data table, supporting subsequent data analysis and display. This process significantly improves the accuracy and automation of table data extraction, reduces the complexity of manual operations, and ensures that users can quickly obtain high-quality spreadsheet files to meet data analysis needs in various scenarios.

[0140] Please see Figure 6 , Figure 6 This is a flowchart illustrating an interface display process as described in this specification. The display of the image extraction results and the spreadsheet file can be performed in the following ways:

[0141] S3002: Display the image extraction results and operation options for the image extraction results on the user display interface.

[0142] User interface: The interactive interface provided by the system for users, which at least displays the image extraction results and operation options.

[0143] Image extraction results: Structured data parsed from the image of the table data, including table data or chart parsing information.

[0144] Results operation options: Users can select function options for the image extraction results, such as editing, saving, re-recognition, etc.

[0145] This example illustrates how the image extraction results, parsed from the image, are presented in a clear format, and a set of operation options are provided on the interface where the image extraction results are located.

[0146] For example, table-type results are displayed in the form of a two-dimensional table, while chart-type results are presented in the form of a numerical list or a visual chart.

[0147] S3004: Display file operation options for the spreadsheet file on the user interface;

[0148] File operation options: Provides operation functions for the generated spreadsheet file, such as viewing, downloading, and sharing.

[0149] As an illustration, the user interface can display basic information about a spreadsheet file (such as filename, format, and size), provide a preview of the spreadsheet file's content, and offer file operation options such as viewing, downloading, and sharing.

[0150] S3006: In response to a first trigger operation for the result operation option, perform result operation processing on the image extraction result;

[0151] The first trigger action is the user's interaction with the result operation options, such as clicking the "Edit" or "Re-extract" button.

[0152] Processing the results of the first triggered operation: Based on the operation selected by the user, process the image extraction results accordingly.

[0153] This example illustrates how to monitor the user's first trigger action (such as clicking or dragging) on ​​the result operation options and perform corresponding result operations on the image extraction results. For example: Editing operation: The user can directly modify the numerical values ​​and text content in the extracted results; Re-extraction operation: Re-apply the chart processing model to re-identify the image data with higher accuracy; Download operation: Export the current extraction results to a specified format (such as JSON or CSV).

[0154] S3008: In response to a second trigger operation on the spreadsheet file, perform file operation processing on the spreadsheet file.

[0155] The second trigger action is the user's interactive behavior with file operation options, such as clicking the "Download" or "Share" button.

[0156] The second triggered operation involves file operation processing: based on the user's selected operation, the corresponding task is performed on the spreadsheet file.

[0157] Indicatively, the system monitors user actions triggered by file operation options on a spreadsheet file (such as clicking "Download"). In response to a second triggered action on the spreadsheet file, it performs file operation processing on the spreadsheet file. For example: viewing file operation processing: opening the file within the interface and displaying its contents; downloading file operation processing: providing the file to the user in .xlsx or .csv format; sharing file operation processing: generating a shareable link or sending the file via email or message.

[0158] In the embodiments described in this specification, users can view the image extraction results and the generated spreadsheet file in an intuitive interface, while also satisfying their needs for editing, downloading, and sharing through various operation options. The user-friendly interface design enhances interactivity and flexibility, allowing users to quickly process the extracted data according to their actual needs, significantly improving the practical value of data extraction and the user experience.

[0159] Please see Figure 7 , Figure 7 This is a flowchart illustrating an interface display process as described in this specification. The image extraction results can also be displayed using the following methods:

[0160] S4002: Display the result editing options for the image extraction results on the user display interface;

[0161] Results editing options: The results editing function controls provided on the interface allow users to manually adjust and edit the extracted results, such as modifying data, adding new items, and deleting erroneous items.

[0162] This example illustrates how the user interface provides result editing options, such as: Manual modification: users can directly click on cells or data points to make changes; Adding new data: users can insert new rows or columns; Deleting data: users can remove erroneous data points or cells.

[0163] S4004: In response to a third trigger operation for the result editing option, obtain the result adjustment information of the user for the image extraction result, and adjust the chart data based on the result adjustment information.

[0164] The third trigger action: the specific action performed by the user on the interface, such as clicking the "Edit" button, entering new data, or deleting data points.

[0165] Result adjustment information: Modifications provided by the user, such as corrected values, added data items, or deleted markers.

[0166] Chart data adjustment: Based on the user's adjustment information, the extraction results in the system are updated in real time and reflected on the interface.

[0167] This process illustratively monitors user actions on result editing options (such as clicking on a cell to make changes), recording the user-inputted adjustment information, such as modifying a cell value, adding a new row of data, or deleting a column of data. Based on this adjustment information, the original extracted results are modified, for example, replacing old values ​​with the new values ​​entered by the user. The data structure is updated to ensure the integrity of added or deleted items. The modified data is then regenerated into image extraction results and / or a spreadsheet file, and the adjustments are displayed on the interface in real time.

[0168] Users can flexibly adjust the image extraction results to ensure the accuracy and completeness of the data. The modified data and charts are updated immediately, making it convenient for users to verify the data and perform subsequent processing.

[0169] In one feasible implementation, obtaining the user's adjustment information regarding the image extraction results and adjusting the chart data based on the adjustment information can be achieved in the following way:

[0170] Step S2: Obtain the user's adjustment information for the image extraction results;

[0171] Step S4: If the result adjustment information contains table adjustment data for the image extraction result, then the result data of the image extraction result is adjusted based on the table adjustment data, and the table data of the spreadsheet file is adjusted based on the table adjustment data, to obtain the adjusted image extraction result and the spreadsheet file;

[0172] Results adjustment information: Operations performed by the user on the extracted results, including data modification, addition, deletion, or category conversion.

[0173] As an illustration, if the result adjustment information includes table adjustment data for the image extraction results, the user's modifications in the table adjustment data (e.g., modifying cell values, adding new rows, or deleting old rows) are directly applied to the image extraction results, and the spreadsheet file is updated synchronously. In other words, the original generated spreadsheet file is modified to ensure consistency with the updated extraction results. The updated image extraction results and spreadsheet file are provided for user verification.

[0174] Step S6: If the result adjustment information contains table data category conversion information for the table data image, then determine the target table data category based on the result adjustment information, generate the target spreadsheet image data of the target table data category in the spreadsheet file using the image extraction results based on the target table data category, and update the spreadsheet file based on the target spreadsheet image data.

[0175] Table data category conversion information: The user requests that the table data be converted from one visualization format (such as a bar chart) to another format (such as a line chart).

[0176] Target table data category: The new data visualization category selected by the user.

[0177] Target spreadsheet chart data: Chart data generated based on the target table data category.

[0178] This process is illustrative. Based on user actions, the target table data category to be transformed is determined (e.g., switching from a bar chart to a line chart). The results of the adjusted image extraction are used to create new chart data to generate graph data for the target table data category, such as adjusted data points, curves, or sectors. The old chart is replaced in the original spreadsheet file, the new target chart is inserted, and the adjusted spreadsheet file containing the new chart is output for the user to download or view.

[0179] This manual employs the aforementioned method to achieve a complete closed loop from user adjustments to result extraction and file updates, ensuring synchronized updates between image extraction results and spreadsheet files, avoiding inconsistencies caused by missed modifications; it also supports flexible adjustments to data and chart types to meet diverse needs, generating adjusted results and files in real time for easy user verification and use; and through category conversion functionality, it helps users present data in the best way, improving the intuitiveness and understandability of data presentation.

[0180] The following will combine Figure 8 This specification provides a detailed description of the chart processing apparatus provided in the embodiments. It should be noted that... Figure 8 The chart processing device shown is used to execute this specification. Figures 1 to 7 The methods shown in the embodiments are illustrated for ease of explanation, showing only the parts related to the embodiments of this specification. For specific technical details not disclosed, please refer to this specification. Figures 1 to 7 The example shown.

[0181] Please see Figure 8This diagram illustrates the structure of a chart processing device according to an embodiment of this specification. The chart processing device 1 can be implemented as all or part of a user terminal through software, hardware, or a combination of both. According to some embodiments, the chart processing device 1 includes an image acquisition module 11, a chart processing module 12, and a data display module 13, specifically used for:

[0182] Image acquisition module 11 is used to acquire images of the table data to be recognized input by the user;

[0183] The chart processing module 12 is used to extract the table data from the image using a large chart processing model to obtain the image extraction result, and to convert the image extraction result into a spreadsheet file.

[0184] The data display module 13 is used to display the image extraction results and the spreadsheet file.

[0185] In one feasible implementation, the chart processing module 12 is used for:

[0186] Input the image of the table data into the large chart processing model;

[0187] The table data category corresponding to the table data image is determined by the large chart processing model. Based on the table data category, the table data image is extracted to obtain the image extraction result. Based on the table data category and the image extraction result, the table data is edited and processed in a preset chart software to generate a spreadsheet file.

[0188] In one feasible implementation, the chart processing module 12 is used for:

[0189] If the table data category is a table type, then the table data in the table data image is extracted to obtain the first table data, and the first table data is used as the image extraction result;

[0190] If the table data category is a chart type, then the chart data in the table data image is subjected to chart semantic parsing to obtain chart parsing information, the chart parsing information is converted into a chart format to obtain second table data, and the second table data is used as the image extraction result.

[0191] In one feasible implementation, the chart processing module 12 is used for:

[0192] If the table data category is a table type, then the table data is edited and processed based on the image extraction results in the preset chart software to obtain spreadsheet data, and a spreadsheet file is generated based on the spreadsheet data;

[0193] If the table data category is a chart type, then the table data is edited and processed based on the image extraction results in the preset chart software to obtain spreadsheet text data, and spreadsheet chart data is drawn based on the spreadsheet text data in the preset chart software, and a spreadsheet file is generated based on the spreadsheet data and the spreadsheet chart data.

[0194] In one feasible implementation, the data display module 13 is used for:

[0195] The user interface displays the image extraction results and the operation options for the image extraction results:

[0196] And display file operation options for the spreadsheet file in the user interface;

[0197] The device 1 is also used for:

[0198] In response to a first trigger operation for the result operation option, the image extraction result is processed by the result operation;

[0199] In response to a second triggered operation on the spreadsheet file, file operation processing is performed on the spreadsheet file.

[0200] In one feasible implementation, the device 1 is further used for:

[0201] The user interface displays editing options for the extracted image results.

[0202] In response to a third triggered operation for the result editing option, obtain the user's result adjustment information for the image extraction result, and adjust the chart data based on the result adjustment information.

[0203] In one feasible implementation, the device 1 is further used for:

[0204] Obtain the user's adjustment information regarding the image extraction results;

[0205] If the result adjustment information contains table adjustment data for the image extraction result, then the result data of the image extraction result is adjusted based on the table adjustment data, and the table data of the spreadsheet file is adjusted based on the table adjustment data, to obtain the adjusted image extraction result and the spreadsheet file;

[0206] If the result adjustment information contains table data category conversion information for the table data image, then the target table data category is determined based on the result adjustment information. Based on the target table data category, the target spreadsheet image data of the target table data category is generated in the spreadsheet file using the image extraction results. The spreadsheet file is then updated based on the target spreadsheet image data.

[0207] It should be noted that the chart processing device provided in the above embodiments is only illustrated by the division of the above functional modules when executing the chart processing method. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the chart processing device and the chart processing method embodiments provided in the above embodiments belong to the same concept, and the implementation process is detailed in the method embodiments, which will not be repeated here.

[0208] The example numbers in this specification are for descriptive purposes only and do not represent the superiority or inferiority of the examples.

[0209] In one or more embodiments of this specification, by acquiring a user-input image of table data to be identified, a large-scale chart processing model is used to extract table data from the image to obtain image extraction results. Based on the image extraction results, a spreadsheet file is generated, and the image extraction results and the spreadsheet file are displayed. This enables efficient conversion from user-uploaded table data images to structured spreadsheet files. By leveraging the powerful processing capabilities of a pre-trained large-scale chart processing model, image extraction results are accurately extracted from charts, automatically generating editable spreadsheet files. A clear interface for displaying the extraction results is also provided. This significantly reduces the complexity of manual operations, improves the efficiency and accuracy of data extraction, and allows users to flexibly apply the extraction results in subsequent analysis and processing stages, greatly enhancing the value of data reuse.

[0210] This specification also provides a computer storage medium that can store multiple instructions adapted to be loaded and executed by a processor as described above. Figures 1 to 7 The chart processing method described in the illustrated embodiment can be found in the following document for a detailed execution process. Figures 1 to 7 The specific details of the illustrated embodiments will not be elaborated here.

[0211] This specification also provides a computer program product that stores at least one instruction, said at least one instruction being loaded and executed by the processor as described above. Figures 1 to 7 The chart processing method described in the illustrated embodiment can be found in the following document for a detailed execution process. Figures 1 to 7 The specific details of the illustrated embodiments will not be elaborated here.

[0212] Please refer to Figure 9 This diagram illustrates a structural block diagram of an electronic device provided in an exemplary embodiment of this specification. The electronic device in this specification may include one or more components such as a processor 110, a memory 120, an input device 130, an output device 140, and a bus 150. The processor 110, memory 120, input device 130, and output device 140 may be connected via the bus 150.

[0213] Processor 110 may include one or more processing cores. Processor 110 connects to various parts of the electronic device using various interfaces and lines, and performs various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory 120, and by calling data stored in memory 120. Optionally, processor 110 may be implemented using at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). Processor 110 may integrate one or more of the following: central processing unit (CPU), graphics processing unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into processor 110 and may be implemented separately using a communication chip.

[0214] The memory 120 may include random access memory (RAM) or read-only memory (ROM). Optionally, the memory 120 may include a non-transitory computer-readable storage medium. The memory 120 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 120 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), instructions for implementing the various method embodiments described below, etc. The operating system may be the Android system, including systems deeply developed based on the Android system, the iOS system developed by Apple Inc., including systems deeply developed based on the iOS system, or other systems. The data storage area may also store data created by the electronic device during use, such as phonebook data, audio and video data, chat log data, etc.

[0215] See Figure 10 As shown, the memory 120 can be divided into operating system space and user space. The operating system runs in the operating system space, while native and third-party applications run in the user space. To ensure that different third-party applications can achieve good running performance, the operating system allocates corresponding system resources for each application. However, different application scenarios within the same third-party application have different requirements for system resources. For example, in local resource loading scenarios, third-party applications have high requirements for disk read speed; in animation rendering scenarios, third-party applications have high requirements for GPU performance. Since the operating system and third-party applications are independent of each other, the operating system often cannot promptly perceive the current application scenario of a third-party application, resulting in the operating system's inability to adapt system resources accordingly to the specific application scenario of the third-party application.

[0216] In order for the operating system to distinguish the specific application scenarios of third-party applications, it is necessary to establish data communication between the third-party applications and the operating system. This would allow the operating system to obtain the current scenario information of the third-party applications at any time, and then perform targeted system resource adaptation based on the current scenario.

[0217] Taking the Android operating system as an example, the programs and data stored in memory 120 are as follows: Figure 11As shown, the memory 120 can store the Linux kernel layer 320, the system runtime library layer 340, the application framework layer 360, and the application layer 380. The Linux kernel layer 320, system runtime library layer 340, and application framework layer 360 belong to the operating system space, while the application layer 380 belongs to the user space. The Linux kernel layer 320 provides low-level drivers for various hardware components of the electronic device, such as display drivers, audio drivers, camera drivers, Bluetooth drivers, Wi-Fi drivers, and power management. The system runtime library layer 340 provides support for key features of the Android system through several C / C++ libraries. For example, the SQLite library provides database support, the OpenGL / ES library provides 3D graphics support, and the Webkit library provides browser kernel support. The system runtime library layer 340 also provides the Android runtime library, which mainly provides core libraries that allow developers to write Android applications using the Java language. The Application Framework Layer 360 provides various APIs that may be used when building applications. Developers can also use these APIs to build their own applications, such as activity management, window management, view management, notification management, content provider, package management, call management, resource management, and location management. At least one application runs in the Application Layer 380. These applications can be native applications that come with the operating system, such as contacts, SMS, clock, and camera apps; or third-party applications developed by third-party developers, such as games, instant messaging, and photo editing apps.

[0218] Taking the operating system as an example (iOS), the programs and data stored in memory 120 are as follows: Figure 12As shown, the iOS system includes: Core OS layer 420, Core Services layer 440, Media layer 460, and Cocoa Touch layer 480. Core OS layer 420 includes the operating system kernel, drivers, and low-level program frameworks. These low-level program frameworks provide hardware-level functionality for use by the program frameworks located in Core Services layer 440. Core Services layer 440 provides system services and / or program frameworks required by applications, such as Foundation framework, account framework, advertising framework, data storage framework, network connectivity framework, geolocation framework, motion framework, etc. Media layer 460 provides applications with audiovisual interfaces, such as interfaces related to graphics and images, audio technology, video technology, and AirPlay (wireless playback of audio and video transmission technologies). Cocoa Touch layer 480 provides various commonly used interface-related frameworks for application development and is responsible for user touch interaction on electronic devices. Examples include local notification services, remote push services, advertising frameworks, game tool frameworks, message user interface (UI) frameworks, UIKit user interface frameworks, map frameworks, and so on.

[0219] exist Figure 12 The framework shown includes, but is not limited to, the base framework in the core service layer 440 and the UIKit framework in the touchable layer 480. The base framework provides many basic object classes and data types, offering the most basic system services to all applications, and is independent of the UI. The UIKit framework, on the other hand, provides a basic UI class library for creating touch-based user interfaces. iOS applications can use the UIKit framework to provide their UI, thus providing the application's infrastructure for building user interfaces, drawing, handling user interaction events, responding to gestures, and so on.

[0220] The methods and principles for implementing data communication between third-party applications and the operating system in the iOS system can be found in the Android system, and will not be repeated here.

[0221] The input device 130 is used to receive input instructions or data, and includes, but is not limited to, a keyboard, mouse, camera, microphone, or touch device. The output device 140 is used to output instructions or data, and includes, but is not limited to, a display device and a speaker. In one example, the input device 130 and the output device 140 can be combined into a touch screen, which is used to receive touch operations from the user using a finger, stylus, or any suitable object on or near it, and to display the user interface of various applications. The touch screen is usually located on the front panel of the electronic device. The touch screen can be designed as a full-screen, curved screen, or irregularly shaped screen. The touch screen can also be designed as a combination of a full-screen and a curved screen, or a combination of an irregularly shaped screen and a curved screen; this specification does not limit this aspect.

[0222] In addition, those skilled in the art will understand that the structure of the electronic device shown in the above figures does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements. For example, the electronic device may also include radio frequency circuits, input units, sensors, audio circuits, wireless fidelity (WiFi) modules, power supplies, Bluetooth modules, etc., which will not be described in detail here.

[0223] In the embodiments of this specification, the executing entity for each step can be the electronic device described above. Optionally, the executing entity for each step can be the operating system of the electronic device. The operating system can be Android, iOS, or other operating systems; this specification does not limit this.

[0224] The electronic device described in this specification can also be equipped with a display device. This display device can be any device capable of displaying information, such as a cathode ray tube display (CR), a light-emitting diode display (LED), an e-ink screen, a liquid crystal display (LCD), or a plasma display panel (PDP). Users can use the display device on the electronic device to view displayed text, images, videos, and other information. The electronic device can be a smartphone, tablet computer, gaming device, AR (Augmented Reality) device, automobile, data storage device, audio playback device, video playback device, laptop, desktop computing device, or wearable device such as a smartwatch, smart glasses, smart helmet, smart bracelet, smart necklace, or smart clothing.

[0225] exist Figure 9 In the illustrated electronic device, the processor 110 can be used to call the application program stored in the memory 120 and specifically perform the following operations:

[0226] Obtain the image of the table data to be recognized, input by the user;

[0227] A large-scale chart processing model is used to extract table data from the image data to obtain image extraction results, and then the table file is converted based on the image extraction results to obtain an electronic spreadsheet file;

[0228] The image extraction results and the spreadsheet file are displayed.

[0229] In one embodiment, the processor 110 performs the following operations when executing the process of extracting table data from the image using a large chart processing model to obtain an image extraction result, and then converting the image extraction result into a chart file to obtain a spreadsheet file:

[0230] Input the image of the table data into the large chart processing model;

[0231] The table data category corresponding to the table data image is determined by the large chart processing model. Based on the table data category, the table data image is extracted to obtain the image extraction result. Based on the table data category and the image extraction result, the table data is edited and processed in a preset chart software to generate a spreadsheet file.

[0232] In one embodiment, the processor 110 performs the following operations when executing the step of extracting table data from the table data image based on the table data category to obtain an image extraction result, and then performs table data editing processing in a preset charting software based on the table data category and the image extraction result to generate a spreadsheet file: if the table data category is a table type, then extracting table data from the table data image to obtain first table data, and using the first table data as the image extraction result;

[0233] If the table data category is a chart type, then the chart data in the table data image is subjected to chart semantic parsing to obtain chart parsing information, the chart parsing information is converted into a chart format to obtain second table data, and the second table data is used as the image extraction result.

[0234] In one embodiment, when the processor 110 performs table data editing processing in a preset charting software based on the table data category and the image extraction result to generate a spreadsheet file, it performs the following operations: if the table data category is a table type, then the processor performs table data editing processing in the preset charting software based on the image extraction result to obtain spreadsheet data, and generates a spreadsheet file based on the spreadsheet data.

[0235] If the table data category is a chart type, then the table data is edited and processed based on the image extraction results in the preset chart software to obtain spreadsheet text data, and spreadsheet chart data is drawn based on the spreadsheet text data in the preset chart software, and a spreadsheet file is generated based on the spreadsheet data and the spreadsheet chart data.

[0236] In one embodiment, the processor 110 performs the following operations when executing the process of displaying the image extraction results and the spreadsheet file:

[0237] The user interface displays the image extraction results and the operation options for the image extraction results:

[0238] And display file operation options for the spreadsheet file in the user interface;

[0239] The method further includes:

[0240] In response to a first trigger operation for the result operation option, the image extraction result is processed by the result operation;

[0241] In response to a second triggered operation on the spreadsheet file, file operation processing is performed on the spreadsheet file.

[0242] In one embodiment, the processor 110 further includes the following when executing the icon processing method:

[0243] The user interface displays editing options for the extracted image results.

[0244] In response to a third triggered operation for the result editing option, obtain the user's result adjustment information for the image extraction result, and adjust the chart data based on the result adjustment information.

[0245] In one embodiment, the processor 110, when executing the process of obtaining the user's adjustment information for the image extraction result and adjusting the chart data based on the adjustment information, performs the following operations:

[0246] Obtain the user's adjustment information regarding the image extraction results;

[0247] If the result adjustment information contains table adjustment data for the image extraction result, then the result data of the image extraction result is adjusted based on the table adjustment data, and the table data of the spreadsheet file is adjusted based on the table adjustment data, to obtain the adjusted image extraction result and the spreadsheet file;

[0248] If the result adjustment information contains table data category conversion information for the table data image, then the target table data category is determined based on the result adjustment information. Based on the target table data category, the target spreadsheet image data of the target table data category is generated in the spreadsheet file using the image extraction results. The spreadsheet file is then updated based on the target spreadsheet image data.

[0249] In one or more embodiments of this specification, by acquiring a user-input image of table data to be identified, a large-scale chart processing model is used to extract table data from the image to obtain image extraction results. Based on the image extraction results, a spreadsheet file is generated, and the image extraction results and the spreadsheet file are displayed. This enables efficient conversion from user-uploaded table data images to structured spreadsheet files. By leveraging the powerful processing capabilities of a pre-trained large-scale chart processing model, image extraction results are accurately extracted from charts, automatically generating editable spreadsheet files. A clear interface for displaying the extraction results is also provided. This significantly reduces the complexity of manual operations, improves the efficiency and accuracy of data extraction, and allows users to flexibly apply the extraction results in subsequent analysis and processing stages, greatly enhancing the value of data reuse.

[0250] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory, or random access memory, etc.

[0251] The above-disclosed embodiments are merely preferred embodiments of this specification and should not be construed as limiting the scope of this specification. Therefore, any equivalent variations made in accordance with the claims of this specification shall still fall within the scope of this specification.

Claims

1. A chart processing method, characterized in that, The method includes: Obtain the image of the table data to be recognized, input by the user; A large-scale chart processing model is used to extract table data from the image data to obtain image extraction results, and then the table file is converted based on the image extraction results to obtain an electronic spreadsheet file; The image extraction results and the spreadsheet file are displayed.

2. The method according to claim 1, characterized in that, The process involves using a large-scale chart processing model to extract table data from the image, obtaining image extraction results, and then converting the extracted images into chart files to obtain spreadsheet files. This includes: Input the image of the table data into the large chart processing model; The table data category corresponding to the table data image is determined by the large chart processing model. Based on the table data category, the table data image is extracted to obtain the image extraction result. Based on the table data category and the image extraction result, the table data is edited and processed in a preset chart software to generate a spreadsheet file.

3. The method according to claim 2, characterized in that, The process of extracting table data from the image based on the table data category to obtain an image extraction result, and then editing and processing the table data in a preset charting software to generate a spreadsheet file based on the table data category and the image extraction result, includes: If the table data category is a table type, then the table data in the table data image is extracted to obtain the first table data, and the first table data is used as the image extraction result; If the table data category is a chart type, then the chart data in the table data image is subjected to chart semantic parsing to obtain chart parsing information, the chart parsing information is converted into a chart format to obtain second table data, and the second table data is used as the image extraction result.

4. The method according to claim 2, characterized in that, The step of generating a spreadsheet file by editing the table data in a preset charting software based on the table data categories and the image extraction results includes: If the table data category is a table type, then the table data is edited and processed based on the image extraction results in the preset chart software to obtain spreadsheet data, and a spreadsheet file is generated based on the spreadsheet data; If the table data category is a chart type, then the table data is edited and processed based on the image extraction results in the preset chart software to obtain spreadsheet text data, and spreadsheet chart data is drawn based on the spreadsheet text data in the preset chart software, and a spreadsheet file is generated based on the spreadsheet data and the spreadsheet chart data.

5. The method according to claim 1, characterized in that, The process of displaying the image extraction results and the spreadsheet file includes: The user interface displays the image extraction results and operation options for the image extraction results, as well as file operation options for the spreadsheet file. The method further includes: In response to a first trigger operation for the result operation option, the image extraction result is processed by the result operation; In response to a second triggered operation on the spreadsheet file, file operation processing is performed on the spreadsheet file.

6. The method according to claim 5, characterized in that, The method further includes: The user interface displays editing options for the extracted image results. In response to a third triggered operation for the result editing option, obtain the user's result adjustment information for the image extraction result, and adjust the chart data based on the result adjustment information.

7. The method according to claim 6, characterized in that, The step of obtaining the user's adjustment information for the image extraction results and adjusting the chart data based on the adjustment information includes: Obtain the user's adjustment information regarding the image extraction results; If the result adjustment information contains table adjustment data for the image extraction result, then the result data of the image extraction result is adjusted based on the table adjustment data, and the table data of the spreadsheet file is adjusted based on the table adjustment data, to obtain the adjusted image extraction result and the spreadsheet file; If the result adjustment information contains table data category conversion information for the table data image, then the target table data category is determined based on the result adjustment information. Based on the target table data category, the target spreadsheet image data of the target table data category is generated in the spreadsheet file using the image extraction results. The spreadsheet file is then updated based on the target spreadsheet image data.

8. A chart processing device, characterized in that, The device includes: The image acquisition module is used to acquire images of the table data to be recognized, input by the user. The chart processing module is used to extract the table data from the image using a large chart processing model, and then convert the image into a spreadsheet file based on the extracted image. The data display module is used to display the image extraction results and the spreadsheet file.

9. A computer storage medium, characterized in that, The computer storage medium stores a plurality of instructions, which are adapted to be loaded by a processor and executed as method steps as claimed in any one of claims 1 to 7.

10. An electronic device, characterized in that, include: A processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and executed the method steps as claimed in any one of claims 1 to 7.

Images