Table processing method and device, electronic equipment and storage medium

By receiving natural language text and using AI model to process it, the intelligent operation of spreadsheets is realized, the user operation complexity and error problems are solved, and the efficiency and user experience of table processing are improved.

CN118939643APending Publication Date: 2024-11-12ZHUHAI KINGSOFT OFFICE SOFTWARE +2

Patent Information

Application Number
CN202310535800.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-11
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The complex functions and operation requirements of existing spreadsheets make it difficult for ordinary users to use efficiently, especially those who need to master the functions of formula calculations, perspective charts and analysis reports, resulting in waste of functions, making users cumbersome operations and prone to errors.

Method used

By receiving target text in natural language, using table processing interfaces (including AI models) to perform target tasks, and displaying execution results and operation record lists, users can perform table operations through natural language descriptions, and the AI ​​model automatically processes and corrects errors, supporting undoing and modify operations to simplify user operations.

Benefits of technology

The task of target tables can be achieved without the need for users to master complex table operation skills, which improves the intelligence and efficiency of table processing, simplifies data processing and analysis processes, and lowers the operation threshold.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118939643A_ABST
    Figure CN118939643A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides a table processing method and device, electronic equipment and a storage medium. The table processing method comprises the following steps: receiving a target text of a natural language; wherein the target text is used for indicating to execute a target task for a target table; displaying an execution result, wherein the execution result is obtained based on the table processing interface; the execution result is related to the target table; in response to the operation record viewing operation, displaying an operation record list; wherein the operation record list comprises an operation record corresponding to the execution result, and the operation record corresponding to the execution result is used for cancelling the executed target task.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

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

[0002] People use spreadsheets in their work, study and daily life. Spreadsheets are particularly suitable for categorizing and counting various data due to their tabular characteristics. For example, teachers use spreadsheets to record and process students' grades. Companies use spreadsheets to record and manage employees' attendance and / or salary, etc.

[0003] With the development of technology, the functions and capabilities of electronic spreadsheets are becoming increasingly powerful. For example, electronic spreadsheets support formula calculations, pivot charts, and the generation of analytical reports. However, these functions have certain operational requirements for users, and users need to master these skills very well. Otherwise, errors are likely to occur and the capabilities of electronic spreadsheets will be wasted. Summary of the invention

[0004] Embodiments of the present disclosure provide a table processing method and device, an electronic device, and a storage medium.

[0005] A first aspect of an embodiment of the present disclosure provides a table processing method, including:

[0006] Receive a target text in natural language; wherein the target text indicates a target task for executing a target form;

[0007] Displaying the execution result, the execution result is obtained based on the table processing interface; the execution result is related to the target table;

[0008] In response to the operation record viewing operation, an operation record list is displayed; wherein the operation record list includes the operation record corresponding to the execution result, and the operation record corresponding to the execution result is used to cancel the executed target task.

[0009] It can be understood that the table processing interface includes: a first calling interface of an artificial intelligence AI model, wherein the execution result is obtained by executing the AI ​​model called by the first calling interface;

[0010] or,

[0011] The table processing interface includes: a second calling interface of the AI ​​model, wherein the execution result is obtained by executing the target code generated by the AI ​​model received by the second calling interface.

[0012] It is understandable that the method further comprises:

[0013] Displaying first prompt information related to the execution result;

[0014] Determine whether to save, cancel or modify the execution result according to a feedback operation acting on the first prompt information.

[0015] It is understandable that the method further comprises:

[0016] Displaying a first text for executing the target task;

[0017] In response to detecting a modification operation on the first text, updating the first text to obtain a second text;

[0018] According to the second text, the execution result is displayed.

[0019] It can be understood that the first text displayed to execute the target task includes at least one of the following:

[0020] Displaying the first text in an editable state in an editable text box;

[0021] Displaying a first part and a second part of the first text with different display parameters; wherein the first part is in an editable state and the second part is in a prohibited editing state;

[0022] When the first text is displayed, a modification option for modifying at least a portion of the content of the first text is displayed.

[0023] It can be understood that the operation record list also includes historical operation records;

[0024] The method further comprises:

[0025] In response to detecting an undo operation acting on the historical operation record, the corresponding historical operation is undoed.

[0026] It can be understood that in response to detecting an undo operation acting on the historical operation record, undoing the corresponding historical operation includes:

[0027] In response to detecting an undo operation acting on an nth historical operation, undoing the nth historical operation;

[0028] Determine whether there is an mth historical operation associated with the nth historical operation in the historical operation record;

[0029] In response to the existence of the mth historical operation, the mth historical operation is undone.

[0030] It is understandable that the method further comprises:

[0031] After canceling the nth historical operation and the mth historical operation, determining whether to re-execute the mth historical operation;

[0032] In response to re-executing the mth history operation, the mth history operation is re-executed.

[0033] It is understandable that the method further comprises:

[0034] Demonstrate execution animation according to the execution process of the execution instruction;

[0035] According to the feedback operation acting on the execution animation, it is determined to save, cancel or modify the execution result.

[0036] It can be understood that before receiving the target text in natural language, the method further includes:

[0037] Display the dialogue panel;

[0038] The receiving of the operation instruction in natural language includes:

[0039] The target text is acquired based on the dialog panel.

[0040] It can be understood that the acquiring the target text based on the dialogue panel includes:

[0041] When a user operation on a voice control on the dialogue panel is detected, the audio input module is started to collect input voice to obtain voice data;

[0042] The target text is obtained according to the voice data.

[0043] It is understandable that the method further comprises:

[0044] Detecting whether the candidate text received from the text input box or the candidate text converted from speech has a specified type of error, where the specified type of error at least includes: a form error;

[0045] When there are errors of a specified type, text error correction is performed on the alternative text to obtain the target text.

[0046] It can be understood that when there is a specified type of error, performing text error correction on the candidate text to obtain the target text includes:

[0047] When performing error correction on the candidate texts and the questionable words in the candidate texts have a plurality of error correction options, the text is corrected preferentially according to the error correction options related to the table task to obtain the target text.

[0048] It can be understood that obtaining the target text according to the voice data includes:

[0049] When the voice data has homophones, the voice data is preferentially converted into words related to table task processing to obtain the target text.

[0050] A second aspect of an embodiment of the present disclosure provides a table processing method, which is executed by a working node and includes:

[0051] A receiving module, configured to receive a target text in a natural language; wherein the target text indicates a target task for executing a target table;

[0052] A display module, used for displaying the execution result, wherein the execution result is obtained based on the table processing interface; the execution result is related to the target table;

[0053] The display module is further used to display an operation record list in response to an operation record viewing operation; wherein the operation record list includes the operation record corresponding to the execution result, and the operation record corresponding to the execution result is used to cancel the executed target task.

[0054] A third aspect of the present disclosure provides an electronic device, including:

[0055] processor;

[0056] a memory for storing processor-executable instructions;

[0057] Among them, the processor is configured to: implement the table processing method provided by any one of the technical solutions of the first aspect when running the executable instructions.

[0058] A fourth aspect of an embodiment of the present disclosure provides a computer-readable storage medium, wherein the readable storage medium stores an executable program, wherein when the executable program is executed by a processor, the table processing method provided by any one of the solutions of the first aspect described above is implemented.

[0059] The technical solution provided by the embodiment of the present disclosure is that the device supports the target text in natural language, and the execution result can be obtained through the assistance of the table processing interface, and the execution result is displayed to the user. The user does not need to master the operation skills of various tables, and can easily obtain the expected execution result of the target table, which simplifies the user operation and improves the probability of using the table capability. At the same time, when the operation record reference operation is checked, the execution cancellation of the target task can be realized through the display of the operation record list, which can meet the user's demand for canceling the target task and improve the intelligence of table processing.

[0060] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0062] Figure 1 It is a flowchart of a table processing method according to an exemplary embodiment.

[0063] Figure 2 The present invention is a schematic diagram showing a display effect of a user interface according to an exemplary embodiment.

[0064] Figure 3 It is a flowchart of a table processing method according to an exemplary embodiment.

[0065] Figure 4 The present invention is a schematic diagram showing a display effect of a user interface according to an exemplary embodiment.

[0066] Figure 5 It is a flowchart of a table processing method according to an exemplary embodiment.

[0067] Figure 6 The present invention is a schematic diagram showing a display effect of a user interface according to an exemplary embodiment.

[0068] Figure 7 The present invention is a schematic diagram showing a display effect of a user interface according to an exemplary embodiment.

[0069] Figure 8 The present invention is a schematic diagram showing a display effect of a user interface according to an exemplary embodiment.

[0070] Fig. 9 The present invention is a schematic diagram showing a display effect of a user interface according to an exemplary embodiment.

[0071] Fig. 10A The present invention is a schematic diagram showing a display effect of a user interface according to an exemplary embodiment.

[0072] Fig. 10B The present invention is a schematic diagram showing a display effect of a user interface according to an exemplary embodiment.

[0073] Fig.11 The present invention is a schematic diagram showing a display effect of a user interface according to an exemplary embodiment.

[0074] Fig.12 The present invention is a schematic diagram showing a display effect of a user interface according to an exemplary embodiment.

[0075] Fig.13 The present invention is a schematic diagram showing a display effect of a user interface according to an exemplary embodiment.

[0076] Fig.14 The present invention is a schematic diagram showing a display effect of a user interface according to an exemplary embodiment.

[0077] Fig.15 It is a schematic diagram showing an analysis report according to an exemplary embodiment.

[0078] Fig.16 The figure is a schematic diagram showing the structure of a table processing device according to an exemplary embodiment.

[0079] Fig.17 The diagram is a schematic structural diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0080] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the embodiments of the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the embodiments of the present disclosure as detailed in the appended claims.

[0081] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0082] like Figure 1 As shown, the embodiment of the present disclosure provides a table processing method, including:

[0083] S1110: Receive a target text in natural language; wherein the target text indicates a target task for executing a target table;

[0084] S1120: Displaying the execution result, wherein the execution result is obtained based on the table processing interface; the execution result is related to the target table;

[0085] S1130: In response to the operation record viewing operation, an operation record list is displayed; wherein the operation record list includes the operation record corresponding to the execution result, and the operation record corresponding to the execution result is used to cancel the executed target task.

[0086] The execution device of the table processing method can be any terminal device. The target table here can be any electronic table.

[0087] The terminal device may be a fixed terminal or a mobile terminal. The terminal device may run a client for processing the form. The client may be a web client or an application client running in the terminal device.

[0088] The target text in the natural language may be a target text received from a text input box of a user interface (UI). Alternatively, the target text in the natural language may be a target text converted based on voice data received by the electronic device. The language data may be target texts in various languages. Figure 2 As shown, the terminal device can display the target table and the dialog panel for receiving natural language text data in the same UI, and receive the natural language text data input by the user in the dialog panel. Figure 2 The goal table shown is a form of achievement table. Fig. 10A The following is a schematic diagram of the display effect of the target list and the dialog panel. One or more operation prompts may be displayed in the dialog panel.

[0089] That is, in some embodiments, before receiving the target text in natural language, the method further includes: displaying a dialogue panel; receiving an operation instruction in natural language, including: acquiring the target text based on the dialogue panel.

[0090] The above is an example of the target table being a score table. In actual implementation, the target table is not limited to the score table.

[0091] Exemplarily, the target table can be any table associated with the target task. The table can be a table in a table file drawn by various table-type applications, a table inserted in a text document, or a table embedded in a web page. In short, the target table can be any table of any form that needs to execute a table task.

[0092] Exemplarily, according to the table storage location, the target table may include a local table of the terminal device and an online table.

[0093] As another example, depending on whether the table is combined with a database, the target table may include: a light-dimensional table and a traditional table. A light-dimensional table is different from a traditional table. Traditional tables are based on cells, and cells can be arbitrarily operated and their styles can be modified. In multi-person collaboration scenarios, irregular formats and inconsistent styles often occur. In a light-dimensional table, the data in each column belongs to the same type. After selecting a field type, only data of the selected type can be entered in the column, such as entering a date in a date field or column, and entering a number in a number field or column. There is no need to worry about irregular data formats, which greatly improves the efficiency of information collection and data statistics.

[0094] In some embodiments, depending on whether the table is from a database, the target table may include a database table and a non-database table. The database table may be a table generated or derived from the content in the database. The table file of the non-database table is usually stored separately, and the change of the content of the table does not involve the change of the content of other tables. Of course, the above is only an example of the type of the target table, and the specific implementation is not limited to the above examples.

[0095] For example, the target task may include but is not limited to at least one of the following:

[0096] Insert columns and rows;

[0097] Merge columns and rows;

[0098] Hide rows and columns that meet the conditions;

[0099] The rows that meet the deletion conditions;

[0100] Sorting operations on tables;

[0101] Execute table formulas, for example, calculate the sum or average of a column or columns containing an element or multiple elements;

[0102] Filter rows or columns that meet the conditions;

[0103] Insert a chart;

[0104] Conduct pivot analysis;

[0105] Perform data verification;

[0106] Modify the format of the target table;

[0107] Modify the data format of some rows or columns, for example, modify the date data format of the date column in the target table. Another example is to modify the number of digits after the decimal point of the value in the target table.

[0108] The first structured data may be data reflecting a table structure of a target table and / or a file structure including the target table.

[0109] The first structured data is different from the content in the target table, which includes but is not limited to numerical values, text content and / or input and output images in the table.

[0110] Exemplarily, the table structure includes but is not limited to at least one of the following:

[0111] The row names of the table;

[0112] The table's column names;

[0113] The table header;

[0114] The name of the table.

[0115] The file structure includes at least one of the following:

[0116] File name;

[0117] File type, for example, a table in an Excel or WPS file can be edited directly, while a table in a PDF file may not be edited directly. Before editing the table, you need to generate an editable file based on the PDF file, and then edit it;

[0118] Table type, for example, whether a table in a document file such as a WPS file is a directly editable table or a table inserted into the document file via an image can be indicated by the table type.

[0119] Of course, the above is merely an example of the first structured data, and the specific implementation is not limited to the above example.

[0120] The execution of the target task may include one or more table operations, which may be referred to as operations.

[0121] The form processing interface may be any interface that can perform a target task based on a target text in a natural language, and may include but is not limited to an application programming interface (API).

[0122] Exemplarily, the table processing interface may include an AI model interface related to the AI ​​model, or a non-AI model interface.

[0123] After the AI ​​model interface is called, the execution result will be obtained based on the AI ​​model.

[0124] After the non-AI model interface is called, the encapsulated table processing capability can be called based on the rule matching or mapping of the target text to obtain the execution result. For example, when the target task is to summarize the scores of column B of the table, the non-AI model interface can traverse the data of the cells in column B and then summarize the data.

[0125] In some embodiments, the form processing interface may also be referred to as a form processing assistant. The AI ​​model interface may also be referred to as an AI assistant.

[0126] In summary, the form processing interface can obtain execution results based on the target text in natural language by calling the capability unit that can execute the form task.

[0127] like Figure 2As shown, the dialog panel may include a text input box and / or a voice input control. The text input box may receive text input by a user through a keyboard, a handwriting board, etc. The voice input control may receive a user's input voice to obtain voice data describing the form task.

[0128] Exemplarily, when converting voice data into text, the method includes:

[0129] If the voice data has homophones, the voice data is preferentially converted into words related to the table task processing. This method can reduce the error probability of the target text.

[0130] In some embodiments, the method comprises:

[0131] When a startup operation of the AI ​​assistant is detected, a dialog panel is displayed, and the dialog panel may be displayed in the application interface of the target table, or the dialog panel may be displayed in a floating window;

[0132] Detect the input text of the dialog panel and get the target text.

[0133] In some embodiments, the method further comprises:

[0134] When a user operation on a voice control on the dialogue panel is detected, the audio input module is started to collect input voice to obtain voice data;

[0135] The target text is obtained according to the voice data.

[0136] Acquire converted text according to the input speech;

[0137] Correct the converted text to obtain the target text. Convert the input speech into text through a speech-to-text conversion tool. After obtaining the converted text, text correction is performed to reduce text errors.

[0138] There are many ways to correct text, at least two of which are provided below:

[0139] Method 1: Manual correction method; display conversion text;

[0140] Detect modification operations on the converted text;

[0141] The conversion text is modified according to the modification operation to obtain the target text.

[0142] Method 2:

[0143] Use the AI ​​model to correct the converted text and obtain the text after the device automatically corrects the error. This text can be directly used as the target text or the generated text of the target text.

[0144] Different people have different pronunciation characteristics, which may lead to deviations between the speech provided by the converted text and the speech that the user wants to express. Therefore, allowing the converted text to be modified can ensure the correctness of the target text.

[0145] In some embodiments, the AI ​​model can be run locally on the terminal device or on a server. The terminal device receives the execution result from the server and displays it.

[0146] In some embodiments, the table processing interface includes: a first calling interface of an artificial intelligence (AI) model, wherein the execution result is obtained by executing the AI ​​model called by the first calling interface; or, the table processing interface includes: a second calling interface of the AI ​​model, wherein the execution result is obtained by executing the target code generated by the AI ​​model received by the second calling interface.

[0147] The method of obtaining the execution result may include at least one of the following:

[0148] When the AI ​​model is run locally on the terminal device, the target text and target table are input into the AI ​​model to obtain the execution result;

[0149] When the AI ​​model is run locally on the terminal device, the target text and the element information of the target table are input into the AI ​​model to obtain the target code; the target code is executed to obtain the execution result;

[0150] When the server runs the AI ​​model, it sends the target text and the element information of the target table to the server, receives the target code returned by the server, and executes the target code to obtain the execution result. The target code is generated by the server based on the target task and element information described in the target text.

[0151] The target code may be embedded in the target table for execution, or it may be executed by the operating system of the terminal device. There are many specific ways to execute the target code, which are not limited to any of the above.

[0152] That is, there are many ways for the terminal device to obtain the execution result, which are not limited to any of the above methods.

[0153] In some embodiments, the table processing interface such as the AI ​​assistant may have an error correction function, which may be an automatic error correction function that is automatically executed. The method also includes:

[0154] Detecting whether the candidate text received from the text input box or the candidate text converted from speech has a specified type of error, where the specified type of error at least includes: a form error;

[0155] When there are errors of a specified type, text error correction is performed on the alternative text to obtain the target text.

[0156] The formal errors here include but are not limited to at least one of the following:

[0157] Typos;

[0158] Illustrated sentence detection.

[0159] For example, when the user manually inputs, there may be editing errors. In this case, the text can also be corrected through the automatic error correction function of the device.

[0160] Exemplarily, when the user inputs voice, no modification operation on the converted text is detected. In this case, text correction can also be achieved through the automatic error correction function of the device.

[0161] In some embodiments, the method further comprises:

[0162] Before correcting text, display the correction prompt;

[0163] When a feedback operation acting on the error correction prompt is detected, it is determined whether to perform text error correction.

[0164] Exemplarily, when a feedback operation acting on an error correction prompt is detected, determining whether to perform text error correction includes:

[0165] When a confirmation operation acting on the error correction prompt is detected, automatic error correction of the alternative text is performed.

[0166] In some embodiments, when an ignore operation or a deny operation acting on the error correction prompt is detected, the alternative text is determined as the target text.

[0167] In some embodiments, in order to indicate the correction content, the corrected text and the uncorrected text may be displayed with different display parameters, for example, with different colors, different brightness, different fonts, different thicknesses, etc.

[0168] If the error still exists after correction, correction can be performed again based on user operations.

[0169] Exemplarily, the method further includes:

[0170] Displaying the alternative text in an editable text box; the editable text box may be included in the dialog panel or displayed floatingly on the dialog panel; at this time, the alternative text may include text input in the text box, text converted according to voice data, and text corrected based on an error correction function;

[0171] Error checking acts on modification operations of alternative texts;

[0172] The alternative texts are corrected according to the modification operation to obtain the target text.

[0173] In summary, in the embodiments of the present disclosure, multiple approaches can be provided to ensure the correctness of the acquired target text.

[0174] As another example, when performing error correction on an alternative text and the questionable word in the alternative text has a plurality of error correction options, the text is corrected preferentially according to the error correction options related to the table task to obtain the target text.

[0175] The AI ​​model can be a model for processing table tasks. Exemplarily, the AI ​​model can be a dedicated model for processing table tasks.

[0176] In some embodiments, the AI ​​model may be a single model trained end-to-end. In other embodiments, the AI ​​model may also be composed of multiple modules (or models), and different modules are trained separately.

[0177] The AI ​​model may include, but is not limited to: a deep learning model and / or a machine learning model.

[0178] Exemplarily, the AI ​​model includes but is not limited to at least one of the following:

[0179] Convolutional Neural Networks;

[0180] Feedback neural network;

[0181] Generative Adversarial Networks (GANs);

[0182] Large Language Models (LLMs).

[0183] Of course, the above is just an example of an AI model, and any of the above examples can be specifically implemented.

[0184] Figure 4 The target code generated by the AI ​​model is displayed in the dialog panel. The dialog panel is displayed to the right of the target table.

[0185] In some embodiments, a list of operation records is displayed. Fig. 10B The figure is a schematic diagram of the display effect of the target table and the operation record list. One or more operation records may be displayed in the operation record list. The operation record may include the current operation record and / or the historical operation record. If an undo operation acting on the operation record is detected, the execution result corresponding to the operation record may be revoked. For example, if an undo operation acting on the current operation record is detected, the execution result of the target task will be revoked.

[0186] like Figure 3 As shown, the embodiment of the present disclosure provides a table processing method, including:

[0187] S1210: receiving a target text in natural language; wherein the target text indicates a target task for executing a target table;

[0188] S1220: Displaying the execution result, wherein the execution result is obtained based on the table processing interface; the execution result is related to the target table.

[0189] S1230: Displaying first prompt information related to the execution result;

[0190] S1240: Determine whether to save, cancel or modify the execution result according to the feedback operation acting on the first prompt information.

[0191] In the embodiment of the present disclosure, the first prompt information and the execution result can be displayed at the same time. The execution result can be used to update the target table, that is, the execution result can be displayed through the updated target table. Fig.11 What is shown is a display effect of the first prompt information.

[0192] The first prompt information may be displayed in a dialog panel or a dialog box.

[0193] The feedback operation may include but is not limited to at least one of the following:

[0194] Confirmation operation, indicating that the execution result acting on the target table will take effect, that is, save the target table with the execution result applied, that is, save the updated target table;

[0195] Deny operation, indicating to cancel the execution result, that is, the target table is restored to the initial state;

[0196] The modification operation can obtain the modification instructions and update the execution results according to the target text and the modification instructions.

[0197] Exemplarily, the modification operation can achieve synchronous modification of other elements of the target table by modifying one element.

[0198] By displaying the first prompt information and executing the feedback operation, the accuracy of the execution result can be ensured.

[0199] In some embodiments, the method further comprises:

[0200] When the display time of the first prompt information reaches the maximum effective display time, the execution result is determined to be correct. That is, the execution result is finally determined to be applied to the target table. If the table content of the target table is updated, the target table with the updated content is saved. If the table attributes of the target table are updated, the updated attributes are saved.

[0201] In some other embodiments, the method further comprises:

[0202] If the next target text or the next table operation instruction is detected within the effective display time of the first prompt information, it is also determined that the execution result is correct.

[0203] like Figure 5 As shown, the embodiment of the present disclosure provides a table processing method, including:

[0204] S1310: receiving a target text in natural language; wherein the target text indicates a target task for executing a target table;

[0205] S1320: Displaying a first text of executing the target task;

[0206] S1330: In response to detecting a modification operation on the first text, updating the first text to obtain a second text;

[0207] S1340: Display the execution result according to the second text.

[0208] The execution steps of the target task can be broken down according to the target text, and the target task is described by a first text in natural language, for example, the first text describes each step.

[0209] Exemplarily, if the first text is a modifiable or editable text, a modification operation will be detected, and the modification operation can be used to update the first text, thereby obtaining an updated second text.

[0210] The AI ​​model can generate a target code for obtaining an execution result based on the second text, and the execution result is obtained by executing the target code. Figure 6 Shown is a schematic diagram of displaying a first text, where the first text is displayed in a dialog panel.

[0211] In one implementation, the first text displaying the execution of the target task includes at least one of the following:

[0212] refer to Figure 7 As shown, a first text in an editable state is displayed in the editable text box;

[0213] refer to Figure 8 As shown, the first part and the second part of the first text are displayed with different display parameters; wherein the first part is in an editable state (for example Figure 8 The text in bold) and the second part is in a non-editable state (for example Figure 8 (text not in bold)

[0214] refer to Fig. 9 As shown, when the first text is displayed, a modification option for modifying at least part of the content of the first text is displayed.

[0215] If the first text is displayed in an editable text box, the entire first text can be modified. In this way, when the semantics that the user wants to express differs from the semantics displayed by the first text, the user can modify the first text through text input or voice input to obtain the modified text.

[0216] In some embodiments, the first text may be displayed in an editable text box, or directly displayed in a dialog panel, etc. However, the first part and the second part are displayed separately with different display parameters.

[0217] The first part in the editable state can be modified, and the second part in the forbidden edit state cannot be edited. For example, the display parameters here include but are not limited to: font, color, font size, brightness, whether it is tilted, etc. to achieve the difference in visual effects between the first part and the second part, so as to facilitate user modification.

[0218] For example, the first part may be content that is more relevant to the target task execution than the second part. Specifically, the first part may indicate the operation type and / or operation parameter related to the target table. For example, "sum" or "sum" in "sum operation" in the first text may be the first part, and "operation" may be displayed as the second part.

[0219] To simplify the operation, when displaying the first text, displaying a modification option for modifying at least part of the content of the first text may include:

[0220] When the first text is displayed, a modification option is displayed at the end of each step description text;

[0221] or,

[0222] When the first text is displayed, modification options are displayed at the back end or front end of the modifiable words in the description text of each step.

[0223] In this case, the user can modify the first text based on the selection operation of the option to obtain the second text.

[0224] The method further includes:

[0225] Display historical operation records;

[0226] In response to detecting an undo operation acting on a historical operation record, the corresponding historical operation is undoed.

[0227] Exemplarily, displaying historical operation records may include:

[0228] The historical operation records are displayed from the last to the last time according to the historical operation. The historical operation records may include: operation type, operation time information, and / or user account information indicating the operation.

[0229] In the embodiment of the present disclosure, the historical operation record may be an operation record of any historical operation within a specified length of time before the current moment or a specified number of operations before the current operation.

[0230] Exemplarily, the historical operation may include but is not limited to at least one of the following:

[0231] Historical operation records based on table processing interface;

[0232] Historical operation records based on manual operations.

[0233] The historical operation records based on the table processing interface can also include:

[0234] Historical operation records based on AI model interface;

[0235] Historical operation records based on non-AI model interfaces.

[0236] In one scenario, the historical operation records may all be records of historical operations performed based on the AI ​​model.

[0237] Fig. 10B The diagram shown is a schematic diagram of displaying the operation records in the operation record list in the order of the operation records.

[0238] When displaying the historical operation records, an undo control will also be displayed to detect the undo operation; the undo operation can be used to execute the execution result of the historical operation.

[0239] Exemplarily, if an undo operation acting on the nth historical operation is detected, the execution result of undoing the nth historical operation is determined according to the operation type of the nth historical operation, or the execution results of the nth historical operation and one or more mth historical operations associated with the nth historical operation are undoed, where m is different from n. The mth historical operation here is to perform an execution table task on the execution result of the nth historical operation to obtain an execution result.

[0240] That is, in some embodiments, in response to detecting an undo operation acting on an nth historical operation, undoing the nth historical operation;

[0241] Determine whether there is an mth historical operation associated with the nth historical operation in the historical operation record;

[0242] In response to the existence of the mth historical operation, the mth historical operation is undone.

[0243] For example, if the execution of the mth historical operation depends on the execution result of the nth historical operation, then the mth historical operation is a historical operation associated with the nth historical operation.

[0244] In one embodiment, after undoing the historical execution result, the mth historical operation is re-executed.

[0245] In another embodiment, after undoing the execution result of the history, it is determined not to execute the mth history operation.

[0246] Whether to re-execute the mth historical operation may be determined according to a user input, or according to an association relationship between the mth historical operation and the nth historical operation.

[0247] For example, if the nth historical operation and the mth historical operation are associated operations for different contents, then after the execution result of the history is undone, it may be determined to execute the mth historical operation.

[0248] For example, the target table is a score table. If the nth historical operation is to modify the number of decimal places in the Chinese language score, and the mth historical operation is to calculate the average score, these are obviously for different contents of the table. After undoing the modification of the number of decimal places, you can re-calculate the average score and update the table.

[0249] For example, if the association between the mth historical operation and the nth historical operation makes it impossible to execute the mth historical operation after the execution result of the mth historical operation is revoked, the mth historical operation may not be executed. For example, if the nth historical operation is a creation operation, and the created table object is revoked, other operations acting on the table object cannot be executed, and at this time, it is determined that the mth historical operation will not be executed.

[0250] In short, by processing historical operation records, the intelligence of table processing is improved and the user experience is enhanced.

[0251] In some embodiments, in order to help the user determine whether the current execution result is accurate, or to provide a user experience while the user is waiting for the execution result, an execution animation may be demonstrated.

[0252] After the animation demonstration is completed, if a denial operation is detected, the execution result will be canceled.

[0253] In some embodiments, the method further comprises:

[0254] After the skip operation of executing the animation is detected, the aforementioned first prompt information is displayed.

[0255] The AI ​​model generation target code may include the following steps:

[0256] Determine the target task based on the target text in natural language;

[0257] Acquire the first structured data of the target table to be processed;

[0258] According to the target task and the first structured data of the target table, a target code for executing the target task is output; wherein after the target code is executed, the target task based on the target table is realized.

[0259] The target code may be a code of various types of programming languages, including but not limited to at least one of the following:

[0260] Scripting languages;

[0261] Advanced programming languages, including but not limited to JAVA, PHP, HTML5, C language, C++, etc.;

[0262] Machine assembly language, including but not limited to 8086 assembly, Win32 assembly, etc.

[0263] These languages ​​can be embedded in and executed by opening an object file containing an object table.

[0264] The target code can be used to execute the target task of the entire target table, and the target code can also be used to execute the target task of part of the content of the target table.

[0265] For example, the target scope involved in the target task is determined based on the target text. The target scope may include: the entire target table and / or the target part in the target table. The target scope is Fig. 9 The data range shown.

[0266] The target part may be a part selected when executing the target task, or a table part determined based on natural language data recognition.

[0267] In some embodiments, the AI ​​model includes: a first module.

[0268] A target text in natural language is input into the first module, and the first module outputs first task information indicating the target task.

[0269] Exemplarily, the first module may include one or more network layers. These network layers may have natural language processing capabilities, so that by recognizing the target text of the natural language, the target task indicated by the target text can be determined, and the first task information can be obtained.

[0270] Exemplarily, the first module may be a task classification module, which is used to determine the classification of the table task based on the natural language text data, that is, to determine the target task.

[0271] The first task information can at least be used to determine the task type. The first task information may include but is not limited to at least one of the following:

[0272] Task ID;

[0273] Task number;

[0274] Task type;

[0275] Task name, etc.

[0276] Exemplarily, the first module processes the target text in natural language, extracts keywords related to the table task from the target text, and determines the target task based on the keywords.

[0277] As another example, the first module determines the target task by processing the target text in natural language, matching task-related words, extracting semantics of combinations between different target texts, and other processes.

[0278] The above is only an example of determining the target task of the first module, and the specific implementation is not limited to the above processing.

[0279] In some embodiments, the element information of the first structured data target table is input into the first module to obtain the first prompt word output by the first module; wherein the first prompt word includes: the first structured data sorted in a predetermined order, which is used to obtain the target code.

[0280] The element information here may include various descriptive information that can determine the rows or columns of the target table, various information of the table file and / or the target table. Exemplarily, the element information may be attribute information of the table file and / or attribute information of the target table. The attribute information of the table file may include: at least one of the following: file type, how the table is presented in the file (for example, picture insertion), and applications supported by the file type. The attributes of the target table may include, but are not limited to, at least one of the following: whether the table supports editing, the table header, the name of the table, whether the content of the table is confidential, and other information.

[0281] By acquiring the element information, the aforementioned first structured data can be obtained. The first structured data is sorted in a preset order to obtain a first prompt word (Prompt). The first prompt word may include one or more prompt data, which are sorted in a predetermined order to facilitate the rapid processing of subsequent modules of the AI ​​model and improve the generation efficiency of the target code.

[0282] The prompt data may include, but are not limited to: target text and / or feature data after the target text is converted based on natural language. In some embodiments, the feature data may include, but are not limited to, various information contents of the first structured data represented by numerical values.

[0283] For example, the first prompt word may include a prompt word of a preset length. If the extraction of the nth first structured data from the first structured data fails, the first prompt word is generated according to the first structured data, and the corresponding prompt data in the first prompt word can be represented by "null".

[0285] In another exemplary embodiment, the prompt data corresponding to the first prompt word can be divided into a first type of prompt data and a second type of prompt data. The importance of the first type of prompt data is higher than that of the second type of prompt data. When the first prompt word lacks the first prompt data, the AI ​​model will output the first prompt information, the first prompt information, which is used to prompt the addition of element information related to the target table and / or table file. The table file here can be any file containing a table. The table in the table file can be a table inserted into a picture and / or a table in text format. When the first prompt word does not lack the first prompt data, the AI ​​model will continue to perform subsequent operations with the first prompt word to generate a target code that can execute the target task. That is, when the second type of prompt data is true, the AI ​​model can continue to perform subsequent operations of the target task, and when the first type of prompt data is missing, the AI ​​model will no longer continue to perform subsequent target tasks. Exemplarily, the first type of prompt data may include at least: the column name of at least one column of the target table.

[0286] In some embodiments, the AI ​​model further includes: a second module;

[0287] Inputting the target text of natural language into the second module to obtain text features;

[0288] Determine a target example related to the target task according to the text feature, the first prompt word and the first task information;

[0289] Generate target code based on the target sample.

[0290] In the embodiment of the present disclosure, the second module may also have the ability to process the target text of natural language. The second module may include a task execution module. The task execution module may be used for the ability scheduling of the completion of the table task, etc.

[0291] In the disclosed embodiment, the processing capability of the natural language target text of the second module may be stronger and more detailed than that of the first module. In the disclosed embodiment, the second module acquires the target text and obtains text features according to the target text.

[0292] The text feature may include but not contain feature values ​​of the semantics of the tabular text data.

[0293] After the text features are acquired, the target sample is determined by combining the text features, the first prompt word and the first task information. The target sample may be a sample that has performed the target task.

[0294] In some embodiments, determining a target example related to the target task according to the text feature, the first prompt word, and the first task information may include:

[0295] Determine alternative samples related to the target task based on the first task information;

[0296] Concatenate the text feature and the first prompt word to obtain concatenation information;

[0297] Mapping the splicing information to a specific feature space to obtain a first feature vector;

[0298] According to the similarity between the first feature vector of the candidate sample and the second feature vector of the candidate sample;

[0299] Select the candidate sample with the highest similarity or the one with a similarity greater than the similarity threshold as the target sample.

[0300] Of course, the above is only an example of a method for determining a target sample, and the specific implementation is not limited to the above example.

[0301] In some embodiments, the second module includes one or more alternative capability units; wherein different alternative capability units have different form processing capabilities and are configured with information of different alternative examples;

[0302] According to the text features, the first prompt word and the first task information, a target sample related to the target task is determined, including:

[0303] Determining, according to the first task information, a first unit for performing the target task from among the candidate capability units;

[0304] The text feature and the first prompt word are input into the first unit, so that the first unit outputs a second prompt word; wherein the second prompt word is generated according to the target sample and is used to generate the target code.

[0305] Exemplarily, an alternative capability unit may correspond to a capability unit of an application program interface (API) granularity. Different alternative capability units have different table processing capabilities. In the disclosed embodiment, different alternative capability units correspond to different task identification sets. When the first task information is included in the task identification set of a certain alternative capability unit, the alternative capability unit is the aforementioned first unit.

[0306] In some embodiments, the first task information may be an identifier of an alternative capability unit, and thus, the first task information is directly mapped to the corresponding alternative capability unit.

[0307] Exemplarily, the alternative capability units may include but are not limited to at least one of the following:

[0308] A first alternative unit is used to perform table tasks based on table formulas;

[0309] The second alternative unit is used to perform table tasks based on API calls;

[0310] A third alternative unit is used to execute a table task based on assembly language code logic. Exemplarily, the assembly language includes but is not limited to a scripting language (JS);

[0311] A fourth alternative unit for performing table-specific tasks;

[0312] The fifth alternative unit is used to execute macro language related table tasks.

[0313] Of course, the above is merely an example of the alternative capability unit. In a specific implementation, the alternative capability unit may also include the sixth alternative unit and / or the seventh alternative unit, etc.

[0314] For example, the sixth candidate unit may encapsulate the atomic capabilities specifically applied to table files, which may include: table creation capability, data deletion, addition, update, hiding and other related capabilities.

[0315] According to the first task information, after the first prompt word and the text feature are provided to the first unit, the first unit outputs the second prompt word. The second prompt word may at least include sample information of the target sample, and the sample information may be used to uniquely identify the target sample. Exemplarily, the sample information may include a sample identifier, etc.

[0316] Exemplarily, a first feature vector is constructed based on the first prompt word and text features, and the Euclidean distance and / or paradigm distance between the first feature vector and the second feature vector of the candidate sample are calculated to characterize similarity. The candidate sample with the highest similarity is selected as the target sample.

[0317] The target sample may also include: an incomplete preset code, which is also a preset code to be supplemented.

[0318] In this way, the target sample is determined according to the second prompt word, and the target code can be generated according to the incomplete preset code corresponding to the target sample.

[0319] In some embodiments, the AI ​​model further includes a third module;

[0320] Generate target code based on the target sample, including:

[0321] The second prompt word is input into the third module to generate the target code.

[0322] The third module may include, but is not limited to, LLMs.

[0323] Exemplarily, the third module may dynamically generate the target code according to the second prompt word.

[0324] The third module of the embodiment of the present disclosure may be LLM.

[0325] As another example, the third module may obtain the preset code to be supplemented of the target sample according to the second prompt word, and supplement the missing part of the preset code according to the first prompt word and / or the first structured data to generate the target code.

[0326] Based on the simulation capability of the third module, the code for executing the target task of the target sample is simulated to generate the target code for executing the target task for the target table.

[0327] In some embodiments, the method further comprises:

[0328] Outputting second prompt information according to the first task information and / or the target code;

[0329] According to the feedback operation acting on the second prompt information, it is determined whether to execute the target task according to the target code.

[0330] The feedback operation may be a manual operation and / or voice operation performed by the user on the second prompt information.

[0331] Exemplarily, the second prompt information is displayed in the form of a dialog box, and the feedback operation may be a user operation acting on an "OK" and / or "Cancel" control in the dialog box.

[0332] The feedback operation may include a confirmation operation to confirm the execution, and / or a denial operation to cancel the execution.

[0333] In this way, according to the feedback operation acting on the second prompt information, erroneous operations are reduced and the execution quality of the target task is improved.

[0334] Exemplarily, outputting the second prompt information according to the first task information and / or the target code may include:

[0335] According to the target code, determine the operations to be performed to complete the target task;

[0336] Generate execution text according to the operation to be executed;

[0337] Displays the execution text.

[0338] That is, the second prompt information is an execution text, so that it is convenient for the user to determine whether the target task that has not been executed is the task that the user needs to execute according to the execution text.

[0339] Figure 4 The dialog panel shown has a schematic diagram of the execution text for filtering the top three scores in the score table. The execution text describes the execution process of the target code step by step using natural language.

[0340] Figure 4 A schematic diagram of the target code is also shown.

[0341] In some cases, the terminal or server may display the target code or hide the target code. Whether to display the target code or hide the target code may be determined according to the table properties of the target table or the property settings of the application program that opens the target table.

[0342] In the embodiment of the present disclosure, the method further includes:

[0343] Determine the target scope of the target code, which may be part or all of the content in the target table;

[0344] Detection target range table content;

[0345] When it is detected that the table content within the target range is abnormal, a fourth prompt message is output and the execution of the target code is suspended.

[0346] Exemplarily, the fourth prompt information may be a separate abnormal prompt information, which is used to inform the user of the table content.

[0347] As another example, the fourth prompt information may be prompt information of the exception type and / or exception correction, which informs the user how to remove the abnormal content in the table.

[0348] Also exemplarily, abnormal content is highlighted or displayed in a different color, thereby facilitating the user to modify the table content.

[0349] In some embodiments, the fourth prompt information may also be displayed in the form of a dialog box.

[0350] When the fourth prompt information is displayed, when an ignore operation of ignoring abnormal table content is detected, the target code is executed.

[0351] Abnormal table contents may include but are not limited to at least one of the following:

[0352] Required content in the form is missing; for example, if the target form is an employee's attendance sheet, the attendance time of a certain job is missing in the attendance sheet, etc.

[0353] The values ​​in the table are beyond the normal range. Taking the student's academic performance as an example, the lowest score is 0, but a negative score is currently detected, which may be abnormal content.

[0354] Of course, the above is only a prompt for abnormal table content, and the specific implementation is not limited to this prompt.

[0355] In some embodiments, the method further comprises:

[0356] When it is detected that the table content within the target range is normal, the target code is executed.

[0357] Fig.15 The diagram shows a schematic diagram of generating an analysis report for the execution result of the target task. The analysis report can be added to the original page of the target table, or a new table page or a new file can be created for storage.

[0358] In conventional electronic spreadsheets, users need to manually complete operations on the spreadsheet based on their familiarity with the spreadsheet. Due to the complexity of electronic spreadsheets, some common functions may consume too much time of users due to their unfamiliarity with the spreadsheet. Some specific examples are:

[0359] 1. Use of formulas: Since there are so many formulas in a spreadsheet and the complexity of the formulas varies, users may not know which formula to use and how to use it. This may require users to spend a lot of time to find and learn.

[0360] 2. Use of functions: Spreadsheets have a wide range of functions, which may make it difficult for unfamiliar users. For example, when performing operations such as data filtering, sorting, and statistics, users may not know how to use the relevant functions and need to spend a lot of time learning.

[0361] 3. Data format and input: The data format and input method in the spreadsheet may also cause difficulties for unfamiliar users. For example, the date format, decimal places and other settings may require users to set them manually, which may make it difficult for unfamiliar users.

[0362] 4. Data analysis: It is necessary to use advanced features of spreadsheets, such as pivot tables, pivot charts, data validation, conditional formatting, etc. These require users to have certain professional knowledge and experience. At the same time, data analysis may require the use of multiple formulas and functions, and combine and nest them, which may make the formulas difficult to write and understand. In addition, the visualization of charts requires the selection of appropriate chart types, styles, colors, etc., which may make it difficult for users to implement some complex data analysis.

[0363] In addition, errors in spreadsheets may also cause difficulties, requiring users to carefully check and confirm the correctness of the input data and formulas. In order to solve these difficulties, general users need to go through a lot of learning or use search engines to find relevant solutions, or seek help from online forums, which will consume a lot of time and may not get an ideal result.

[0364] The disclosed embodiment provides a table task processing method based on an AI model. The table capabilities involved in the AI ​​model can be encapsulated as an API or SDK. The API or SDK can be called an AI assistant.

[0365] AI assistants can help lower the threshold for using spreadsheets, allowing more ordinary users to easily process and analyze data.

[0366] Users can describe their needs in natural language, and AI assistants use the power of the big prediction model behind them to call the function set. Therefore, AI assistants can help users process data directly in a conversational way. Users only need to confirm whether the results of AI operating data or the generated data reports meet expectations.

[0367] Users can describe their instructions in natural language, and the AI ​​assistant implements the user's instructions by automatically calling a set of functions. For the results returned by the AI ​​model, users can manually modify or modify the corresponding code, save or cancel; at the same time, they can also check whether the AI ​​operation is in line with expectations by viewing the AI ​​operation record.

[0368] The method provided by the embodiment of the present disclosure may include:

[0369] An operation instruction from a user is received, where the operation instruction is expressed in a target text of a natural language.

[0370] The AI ​​assistant recognizes the command information;

[0371] The AI ​​assistant displays the corresponding table operation steps and presents them for user confirmation. Users can use code to modify them, or directly click the "Execute" button to execute the target task without modifying the code.

[0372] The AI ​​assistant presents the specific operation animation of the table. The result after the operation requires the user to confirm twice to keep or cancel it, and the specific operation steps can also be modified:

[0373] 1) The operation animation of the table mainly shows the data range covered by the modification and the area where the change occurs; if the data is changed, the large range of the changed data is marked, and the specific changed data is marked with color.

[0374] 2) The correction operation steps include three methods (such as Figures 7 to 9 shown):

[0375] Mark the editable parts, and users can modify the text directly;

[0376] Directly allow all operation steps to be modified, or identify the editable parts and display them with specific controls. For example, the editable data columns can be selected by users in a drop-down list.

[0377] After the execution is completed, the operation record is stored in the collection of AI behavior records for users to view or restore. The AI ​​behavior record traces back the execution process of the AI ​​assistant. The AI ​​behavior record contains two entrances, one of which is the global entrance. After clicking it, you can view all the historical operation records executed by AI; the other entrance is used to assist users in confirming whether the operation of the current instruction is retained. After clicking it, you can view all AI operation records corresponding to a single operation.

[0378] Regarding manually clicking the "Execute" button, you can also let the large language model try several times in the background and execute the code with the highest probability. It can also be executed automatically without taking up too much user time.

[0379] Similarly, users describe their needs in natural language, and AI assistants use the power of the big prediction model behind them to call function sets, which can migrate to more application scenarios, such as:

[0380] Enter the command, AI will automatically build the table structure, as shown below: Fig.12 As shown; Fig.13 Completion prompt for creation;

[0381] Enter the command and AI will automatically create the application;

[0382] Input the command, AI will automatically output the data analysis report. For details, please refer to Fig.14 shown.

[0383] With the help of the Form AI Assistant, ordinary users can process and analyze data more easily, unleash the potential value of data processing and analysis, and enable more people to benefit. Fig.15 A schematic diagram of an analysis report based on an AI model.

[0384] like Fig.16 As shown, the embodiment of the present disclosure provides a table processing device, including:

[0385] The receiving module 110 is used to receive a target text in a natural language; wherein the target text indicates a target task for executing a target form;

[0386] Display module 120, used to display the execution result, the execution result is obtained based on the table processing interface; the execution result is related to the target table;

[0387] The display module 120 is further used to display an operation record list in response to an operation record viewing operation; wherein the operation record list includes the operation record corresponding to the execution result, and the operation record corresponding to the execution result is used to cancel the executed target task.

[0388] It can be understood that the table processing interface includes: a first calling interface of an artificial intelligence AI model, wherein the execution result is obtained by executing the AI ​​model called by the first calling interface;

[0389] or,

[0390] The table processing interface includes: a second calling interface of the AI ​​model, wherein the execution result is obtained by executing the target code generated by the AI ​​model received by the second calling interface.

[0391] It can be understood that the display module is further configured to display first prompt information related to the execution result;

[0392] The device also includes:

[0393] A determination module is used to determine whether to save, cancel or modify the execution result according to a feedback operation acting on the first prompt information.

[0394] It can be understood that the display module is also used to display a first text for executing the target task;

[0395] The device also includes:

[0396] An updating module, configured to update the first text to obtain a second text in response to detecting a modification operation on the first text;

[0397] The display module is used to display the execution result according to the second text.

[0398] It can be understood that the display module is used to perform at least one of the following:

[0399] Displaying the first text in an editable state in an editable text box;

[0400] Displaying a first part and a second part of the first text with different display parameters; wherein the first part is in an editable state and the second part is in a prohibited editing state;

[0401] When the first text is displayed, a modification option for modifying at least a portion of the content of the first text is displayed.

[0402] It can be understood that the operation record list also includes historical operation records;

[0403] The device also includes:

[0404] The undo module is used to, in response to detecting an undo operation acting on the historical operation record, undo the corresponding historical operation.

[0405] It can be understood that the undo module is used to undo the nth historical operation in response to detecting an undo operation acting on the nth historical operation; determine whether there is an mth historical operation associated with the nth historical operation in the historical operation record; and undo the mth historical operation in response to the existence of the mth historical operation.

[0406] It can be understood that the device also includes:

[0407] a determination module, configured to determine whether to re-execute the mth historical operation after canceling the nth historical operation and the mth historical operation;

[0408] An execution module is used for re-executing the mth historical operation in response to re-executing the mth historical operation.

[0409] It can be understood that the device also includes:

[0410] A demonstration module, used to demonstrate execution animation according to the execution process of the execution instruction;

[0411] The determination module is further used to determine whether to save, cancel or modify the execution result according to the feedback operation acting on the execution animation.

[0412] It can be understood that the display module is used to display the dialogue panel before receiving the target text in natural language;

[0413] The receiving module is further used to obtain the target text based on the dialogue panel.

[0414] It can be understood that the receiving module is used to start the audio input module to collect input voice to obtain voice data when detecting the user operation of the voice control acting on the dialogue panel; and obtain the target text according to the voice data.

[0415] It can be understood that the device also includes:

[0416] The detection module is used to detect whether the candidate text received from the text input box or the candidate text converted from speech has a specified type of error, and the specified type of error at least includes: a form error;

[0417] The error correction module is used to perform text error correction on the alternative text when there is a specified type of error to obtain the target text.

[0418] It can be understood that the error correction module is used to perform text correction according to the error correction options related to the table task when there are multiple error correction options for the questionable words in the alternative text to obtain the target text.

[0419] It can be understood that the receiving module is used to preferentially convert the voice data into words related to table task processing to obtain the target text when the voice data has homophones.

[0420] An embodiment of the present disclosure further provides an electronic device, including:

[0421] processor;

[0422] a memory for storing processor-executable instructions;

[0423] The processor is configured to implement the table processing method of any embodiment of the present disclosure when running the executable instructions.

[0424] The electronic device may at least be the aforementioned server, the first terminal and / or the second terminal.

[0425] The memory may include various types of storage media, which are non-transitory computer storage media that can continue to remember information stored thereon after the communication device loses power.

[0426] The processor can be connected to the memory through a bus or the like to read the executable program stored in the memory, for example, to implement the following Figure 1 , Figure 3 and / or Figure 5 The table processing method shown.

[0427] The embodiments of the present disclosure further provide a computer-readable storage medium, wherein the computer-readable storage medium stores an executable program, wherein when the executable program is executed by a processor, the table processing method of any embodiment of the present disclosure is implemented. Figure 1 , Figure 3 and / or Figure 5 The table processing method shown.

[0428] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0429] The present disclosure provides an electronic device, comprising: a processor; a memory for storing processor executable instructions; wherein the processor is configured to: when running the executable instructions, implement the table processing method provided by any of the above technical solutions, for example, Figures 1 to 7 The table processing method shown.

[0430] like Fig.14 As shown, an embodiment of the present disclosure shows a structure of an electronic device. For example, the electronic device 900 can be provided as a network side device. Fig.14 The electronic device 900 includes a processing component 922, which further includes one or more processors, and a memory resource represented by a memory 932 for storing instructions executable by the processing component 922, such as an application. The application stored in the memory 932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 922 is configured as an executable program to perform any of the aforementioned methods for applying to the access device, for example, Figure 1 , Figure 3 and / or Figure 5 The table processing method shown.

[0431] The electronic device 900 may also include a power supply component 926 configured to perform power management of the electronic device 900, a wired or wireless network interface 950 configured to connect the electronic device 900 to a network, and an input / output (I / O) interface 958. The electronic device 900 may operate based on an operating system stored in the memory 932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™ or the like.

[0432] In an exemplary embodiment, an embodiment of the present disclosure provides a computer-readable storage medium, which stores an executable program, wherein the executable program, when executed by a processor, implements the table processing method provided by any of the aforementioned technical solutions.

[0433] The computer-readable storage medium may specifically be: a non-temporary computer-readable storage medium.

[0434] Exemplarily, for example, the memory 932 includes an executable program, and the above instructions can be executed by the processing component 922 of the electronic device 900 to complete the above method.

[0435] The non-transitory computer-readable storage medium may be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0436] Those skilled in the art will readily appreciate other implementations of the disclosed embodiments after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosed embodiments, which follow the general principles of the disclosed embodiments and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and examples are to be considered as exemplary only, and the true scope and spirit of the disclosed embodiments are indicated by the following claims.

[0437] It should be understood that the embodiments of the present disclosure are not limited to the precise structures described above and shown in the drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the embodiments of the present disclosure is limited only by the appended claims.

Claims

1. A table processing method, characterized in that: include: Receiving a target text in a natural language; wherein the target text indicates a target task for executing a target form; Displaying the execution result, wherein the execution result is obtained based on the table processing interface; the execution result is related to the target table; In response to the operation record viewing operation, an operation record list is displayed; wherein the operation record list includes the operation record corresponding to the execution result, and the operation record corresponding to the execution result is used to cancel the executed target task.

2. The method according to claim 1, characterized in that The table processing interface includes: a first calling interface of an artificial intelligence AI model, wherein the execution result is obtained by executing the AI ​​model called by the first calling interface; or, The table processing interface includes: a second calling interface of the AI ​​model, wherein the execution result is obtained by executing the target code generated by the AI ​​model received by the second calling interface.

3. The method according to claim 1, characterized in that The method further comprises: Displaying first prompt information related to the execution result; Determine whether to save, cancel or modify the execution result according to a feedback operation acting on the first prompt information.

4. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: Displaying a first text for executing the target task; In response to detecting a modification operation on the first text, updating the first text to obtain a second text; According to the second text, the execution result is displayed.

5. The method according to claim 4, characterized in that The first text displayed to execute the target task includes at least one of the following: Displaying the first text in an editable state in an editable text box; Displaying a first part and a second part of the first text with different display parameters; wherein the first part is in an editable state and the second part is in a prohibited editing state; When the first text is displayed, a modification option for modifying at least a portion of the content of the first text is displayed.

6. The method according to any one of claims 1 to 5, characterized in that: The operation record list also includes historical operation records; The method further comprises: In response to detecting an undo operation acting on the historical operation record, the corresponding historical operation is undoed.

7. The method according to claim 6, characterized in that In response to detecting an undo operation acting on the historical operation record, undoing the corresponding historical operation includes: In response to detecting an undo operation acting on an nth historical operation, undoing the nth historical operation; Determine whether there is an mth historical operation associated with the nth historical operation in the historical operation record; In response to the existence of the mth historical operation, the mth historical operation is undone.

8. The method according to claim 7, characterized in that The method further comprises: After canceling the nth historical operation and the mth historical operation, determining whether to re-execute the mth historical operation; In response to re-executing the mth history operation, the mth history operation is re-executed.

9. The method according to any one of claims 1 to 8, characterized in that: The method further comprises: Demonstrate execution animation according to the execution process of the execution instruction; According to the feedback operation acting on the execution animation, it is determined to save, cancel or modify the execution result.

10. The method according to any one of claims 1 to 9, characterized in that: Before receiving the target text in natural language, the method further includes: Display the dialogue panel; The receiving of the operation instruction in natural language includes: The target text is acquired based on the dialog panel.

11. The method according to claim 10, characterized in that The acquiring the target text based on the dialogue panel includes: When a user operation on a voice control on the dialogue panel is detected, the audio input module is started to collect input voice to obtain voice data; The target text is obtained according to the voice data.

12. The method according to claim 11, characterized in that The method further comprises: Detecting whether the candidate text received from the text input box or the candidate text converted from speech has a specified type of error, where the specified type of error at least includes: a form error; When there are errors of a specified type, text error correction is performed on the alternative text to obtain the target text.

13. The method according to claim 12, characterized in that The step of performing text error correction on the candidate text when there is an error of the specified type to obtain the target text includes: When performing error correction on the candidate text and the questionable word in the candidate text has multiple error correction options, the text is corrected preferentially according to the error correction options related to the table task to obtain the target text.

14. The method according to claim 11, characterized in that The step of obtaining the target text according to the voice data comprises: When the voice data has homophones, the voice data is preferentially converted into words related to table task processing to obtain the target text.

15. A table processing device, characterized in that: include: A receiving module, configured to receive a target text in a natural language; wherein the target text indicates a target task for executing a target table; A display module, used for displaying the execution result, wherein the execution result is obtained based on the table processing interface; the execution result is related to the target table; The display module is further used to display an operation record list in response to an operation record viewing operation; wherein the operation record list includes the operation record corresponding to the execution result, and the operation record corresponding to the execution result is used to cancel the executed target task.

16. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to: implement the table processing method described in any one of claims 1 to 14 when running the executable instructions.

17. A computer-readable storage medium, characterized in that: The readable storage medium stores an executable program, wherein the executable program, when executed by a processor, implements the table processing method according to any one of claims 1 to 14.

Citation Information

Patent Citations

  • Performing an operation relative to tabular data based upon voice input

    CN105408890A

  • Method and device for processing spreadsheet data in web page

    CN112800371A

Cited By

  • Text error recognition method based on large model and related device

    CN119783660A

  • Multi-dimensional data management method and system based on spreadsheet

    CN120278134A

  • Spreadsheet-based multidimensional data management method and system

    CN120278134B