A data processing method, device, apparatus, and storage medium

Abstract

This application provides a data processing method, apparatus, device, and storage medium. Specifically, data is first displayed to a user through a table. Then, the user can trigger a display command for a first data range in the table. Based on the user-triggered display command, a data processing component can be displayed. The data processing component includes a text input area. The user can input target text through the text input area. After receiving the data processing command for the data processing component, the data in the first data range can be processed according to the target text, and the adjustment result can be displayed. In this way, automatic data processing can be achieved without the user needing to understand the specific processing rules, lowering the barrier to entry and improving the user experience.

Description

Technical Field

[0001] This application relates to the field of computers, and more particularly to a data processing method, apparatus, device, and storage medium. Background Technology

[0002] With the development of computer technology, displaying data in tables has become a common technique. Tables allow data with the same attributes to be shown in the same row or column, making it easier for users to view.

[0003] Furthermore, while viewing the data, users can adjust the arrangement and display of the data in the table. For example, users can sort, filter, and highlight the data to adjust its presentation. These operations further highlight the characteristics of the data and make it easier for users to view it.

[0004] Currently, applications used to view tables can have various data processing functions pre-deployed. However, they are still quite difficult for users to use. Summary of the Invention

[0005] To address the problems of the prior art, this application provides a data processing method, apparatus, device, and storage medium.

[0006] Based on this, the technical solution provided in this application is as follows:

[0007] In a first aspect, this application provides a data processing method, the method comprising:

[0008] In response to a display instruction for a first data range in a table, a data processing component is displayed, the data processing component including a text input area;

[0009] In response to a data processing instruction for the data processing component, the data in the first data range is processed and the adjustment result is displayed based on the target text received through the text input area.

[0010] In some possible implementations, the target text includes target instruction text, which indicates a first operation instruction; the processing of the data in the first data range includes:

[0011] The first adjustment instruction is executed on the data within the first data range.

[0012] In some possible implementations, the target instruction text further includes conditional information text, which indicates first conditional information; the execution of the first adjustment instruction on the data in the first data range includes:

[0013] First target data is determined, and the first target data matches the first condition information;

[0014] The first target data is processed according to the first operation instruction.

[0015] In some possible implementations, processing the first target data according to the first operation instruction includes:

[0016] The first target data is displayed in the second data range within the first data range; or...

[0017] The first target data is displayed in a first display mode, and the target text further includes display mode indication text, which indicates the first display mode.

[0018] In some possible implementations, processing the first target data according to the first operation instruction includes displaying the first target data in a second data range within the first data range. Displaying the first target data in the second data range within the first data range includes:

[0019] Hide and display non-first target data within the first data range.

[0020] In some possible implementations, processing the data in the first data range based on the target text received through the text input area includes:

[0021] Add an instruction control to at least one cell corresponding to the first data range.

[0022] In some possible implementations, the method further includes, before processing the data in the first data range:

[0023] Send the target text to the target model;

[0024] Receive the first processing rule sent by the target model;

[0025] The processing of the data in the first data range includes:

[0026] The data in the first data range is processed according to the first processing rule.

[0027] In some possible implementations, before processing the data in the first data range according to the first processing rule, the method further includes:

[0028] The feasibility of the first processing rule is verified by processing the data within the first data range.

[0029] Secondly, this application provides a data processing method, which is applied to a server-side target software having table processing functionality. The method includes:

[0030] Obtain the target text, which is obtained by the client of the target software during the process of processing the data in the first data range of the table and sent to the server;

[0031] Send the target text to the target model;

[0032] The system receives a first processing rule from the target model, which is used to process the data within the first data range.

[0033] In some possible implementations, after sending the target text to the target model, the method further includes:

[0034] Receive instruction parsing information sent by the target model, wherein the instruction parsing information is obtained by semantic parsing the target text;

[0035] At least one intermediate processing rule is determined based on the instruction parsing information;

[0036] Information about at least one intermediate processing rule is sent to the target model, wherein the first processing rule is determined from the plurality of intermediate processing rules.

[0037] In some possible implementations, the instruction parsing information includes a first vector, which corresponds to the target text;

[0038] The step of determining multiple intermediate processing rules based on the first parsed information includes:

[0039] Obtain the feature vectors of multiple candidate processing rules;

[0040] Based on the first vector and the feature vector of the candidate processing rule, at least one intermediate processing rule is determined from the plurality of candidate processing rules.

[0041] Thirdly, this application provides a data processing apparatus, the apparatus comprising:

[0042] The display unit is configured to display a data processing component, which includes a text input area, in response to a display instruction for a first data range in a table.

[0043] The processing unit is configured to, in response to a data processing instruction for the data processing component, process the data in the first data range based on the target text received through the text input area;

[0044] The display unit is also used to display the adjusted data in the first range.

[0045] In some possible implementations, the target text includes target instruction text, which indicates a first operation instruction; the processing unit is specifically configured to execute the first adjustment instruction on the data in the first data range.

[0046] In some possible implementations, the target instruction text further includes condition information text, which indicates first condition information; the processing unit is specifically used to determine first target data, which matches the first condition information; and to process the first target data according to the first operation instruction.

[0047] In some possible implementations, the processing unit is specifically configured to display the first target data within a second data range in the first data range; or, to display the first target data in a first display mode, wherein the target text further includes display mode indication text, the display mode indication text indicating the first display mode.

[0048] In some possible implementations, processing the first target data according to the first operation instruction includes displaying the first target data in a second data range within the first data range; the display unit is specifically used to hide and display non-first target data within the first data range.

[0049] In some possible implementations, the processing unit is also used to add instruction controls to at least one cell corresponding to the first data range.

[0050] In some possible implementations, the apparatus further includes a sending unit and a receiving unit, wherein the sending unit is used to send the target text to the target model; the receiving unit is used to receive the first processing rule sent by the target model; and the processing unit is further used to process the data in the first data range according to the first processing rule.

[0051] In some possible implementations, the processing unit is further configured to perform a feasibility check on the first processing rule by processing the data in the first data range.

[0052] Fourthly, this application provides a data processing apparatus, wherein the method is applied to a server of target software, the target software having table processing functionality, and the apparatus includes: an acquisition unit for acquiring target text, the target text being acquired by the client of the target software during the processing of data in a first data range in a table and sent to the server; a sending unit for sending the target text to a target model; and a receiving unit for receiving a first processing rule fed back by the target model, the first processing rule being used to process data in the first data range.

[0053] In some possible implementations, the apparatus further includes a processing unit; the receiving unit is further configured to receive instruction parsing information sent by the target model, the instruction parsing information being obtained by semantic parsing the target text; the processing unit is configured to determine at least one intermediate processing rule based on the instruction parsing information; the sending unit is further configured to send information of the at least one intermediate processing rule to the target model, the first processing rule being determined from the plurality of intermediate processing rules.

[0054] In some possible implementations, the instruction parsing information includes a first vector corresponding to the target text; the processing unit is specifically used to obtain feature vectors of multiple candidate processing rules; and to determine at least one intermediate processing rule from the multiple candidate processing rules based on the first vector and the feature vectors of the candidate processing rules.

[0055] Fifthly, this application provides an electronic device, comprising:

[0056] One or more processors;

[0057] Storage device, on which one or more programs are stored,

[0058] When the one or more programs are executed by the one or more processors, the one or more processors implement any of the methods in the first aspect, or implement any of the methods in the second aspect.

[0059] In a sixth aspect, this application provides a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements any of the methods described in the first aspect, or implements any of the methods described in the second aspect.

[0060] In a seventh aspect, this application provides a computer program product that, when run on a device, causes the device to perform the method described in the first aspect or the method described in the second aspect.

[0061] Therefore, this application has the following beneficial effects:

[0062] This application provides a data processing method, apparatus, device, and storage medium. Specifically, data is first displayed to a user through a table. Then, the user can trigger a display command for a first data range in the table. Based on the user-triggered display command, a data processing component can be displayed. The data processing component includes a text input area. The user can input target text through the text input area. After receiving the data processing command for the data processing component, the data in the first data range can be processed according to the target text, and the adjustment result can be displayed. In other words, if a user needs to process the data in the first data range of a table, the user can first trigger a display command, then input the target text in the text input area, and then trigger a data processing command to process the data according to the command. Thus, automatic data processing can be achieved without the user needing to understand the specific processing rules, lowering the barrier to entry and improving the user experience. Attached Figure Description

[0063] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0064] Figure 1 A schematic diagram illustrating an application scenario provided in this application embodiment;

[0065] Figure 2 A flowchart illustrating a data processing method provided in an embodiment of this application;

[0066] Figure 3 A flowchart illustrating a data processing method provided in an embodiment of this application;

[0067] Figure 4 An interactive schematic diagram of a data processing method provided in an embodiment of this application;

[0068] Figure 5 A schematic diagram of a data processing apparatus provided in an embodiment of this application;

[0069] Figure 6 A schematic diagram of a data processing apparatus provided in an embodiment of this application;

[0070] Figure 7 This is a schematic diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0071] Embodiments of this application will now be described in more detail with reference to the accompanying drawings. While some embodiments of this application are shown in the drawings, it should be understood that this application can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this application. It should be understood that the drawings and embodiments of this application are for illustrative purposes only and are not intended to limit the scope of protection of this application.

[0072] It should be understood that the steps described in the method embodiments of this application may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this application is not limited in this respect.

[0073] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0074] It should be noted that the concepts of "first" and "second" mentioned in this application are only used to distinguish different objects, devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0075] It should be noted that the terms "a" and "a plurality of" used in this application are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0076] Data processing via tables is convenient and fast. Currently, more and more users are choosing to process data using tables. Therefore, many applications offer data processing functionality via tables. This functionality can be called table functionality, and software with table functionality can be called table-based software. For example, to facilitate data processing for users, table functionality can be integrated into instant messaging (IM) software. Correspondingly, IM software that inherits table functionality can be called table-based software.

[0077] When processing data using tables, users may need to perform calculations, transformations, and analyses on the data. In practice, these operations can be quite complex. Manually processing the data by users can lead to low efficiency and a poor user experience.

[0078] To facilitate user operation, the processing logic of some data processing functions can be integrated into spreadsheet software. This allows users to manipulate data by calling the integrated data processing functions within the spreadsheet software. For example, users can trigger operation controls to process data in the spreadsheet, or they can input commands to process the data. This improves data processing efficiency and enhances the user experience.

[0079] However, the processing logic of some data processing functions can be quite complex. When invoking these functions, users may need to not only invoke the functions via commands, but also make selections based on the actual data in the table, or even input auxiliary commands or reference information. This requires users to understand how to use the data processing functions, making it a relatively difficult task to learn.

[0080] Furthermore, as spreadsheet software adds more features, the data processing capabilities it offers also increase. While this enriches the functionality of spreadsheet software, it may also create issues that make it inconvenient for users.

[0081] On the one hand, users may be unaware of the data processing capabilities of spreadsheet software and therefore unable to utilize the necessary functions. In practical applications, users may use spreadsheet software simply as a data processing tool without having in-depth knowledge of it. Consequently, they may be unaware of its data processing capabilities. Even if the data processing functions provided by the spreadsheet software meet the user's operational needs, due to a lack of sufficient understanding, users may find it difficult to conceive of using these functions to process data.

[0082] On the other hand, even if users understand the functions of spreadsheet software, they may still be unable to use a certain function to process data because they cannot find out how to use it.

[0083] Specifically, in real-world scenarios, if the functions provided by spreadsheet software are triggered by operation controls, but the user cannot find the corresponding operation controls, then the user will also be unable to use the functions corresponding to those operation controls.

[0084] In real-world scenarios, spreadsheet software has limited display space. Therefore, to save display space, the controls for some less frequently used data processing functions may be placed in inconspicuous locations on the display interface, hidden in expandable menus, or displayed as small icons. Thus, even if a user is aware that the spreadsheet software provides a certain data processing function, they may not be able to find the corresponding controls and therefore cannot invoke the Giant data processing function to process the data.

[0085] It is evident that users may lack understanding of spreadsheet software and be unable to use its functions to process data, resulting in a poor user experience.

[0086] To address the problems of the prior art, this application provides a data processing method, which will be described in detail below with reference to the accompanying drawings.

[0087] First, exemplary application scenarios of the embodiments of this application will be introduced. See [link to relevant documentation]. Figure 1 This figure is a schematic diagram of an exemplary application scenario provided in an embodiment of this application. Figure 1 The implementation shown includes a client 110, a server 120, and a target model 130. The client 110 and the server 120 can be connected via a network. The server 120 and the target model 130 can also be connected via a network.

[0088] The client 110 can run on the user's terminal device, such as a mobile phone or computer. The server 120 can run on a server or server cluster to provide services to the client 110. The client 110 and the server 120 can interact with each other.

[0089] The target model 130 can run on a server or a server cluster. Optionally, the server (or server cluster) used to implement target 0 and the server (or server cluster) used to implement server 120 can be the same or different. The target model 130 is used to provide services for the target model to the outside world. For example, the target model can run within the target model 130. Server 120 can send data to be processed to the target model 130, and the target model 130 can process the data to be processed through the target model and send the processed data back to server 120. Optionally, the target model can be a language model (LM) or a large language model (LLM).

[0090] The exemplary application scenarios of the embodiments of this application have been introduced above. The data processing methods provided by the embodiments of this application will be described in an exemplary manner below.

[0091] See Figure 2 , Figure 2 This application provides a flowchart illustrating a data processing method, which is applicable to application scenarios where data is processed using tables. This data processing method can be executed by a data processing device, which can be implemented in software.

[0092] It should be noted that, Figure 3 The data processing device in the corresponding embodiment, and Figure 2 The data processing apparatus in the corresponding embodiments can be different apparatuses. For example, Figure 3 The data processing device in the corresponding embodiment can run on the server side of spreadsheet software, while Figure 2 The data processing device in the corresponding embodiment can run on the client side of spreadsheet software.

[0093] Optionally, the data processing device can be integrated into the client of spreadsheet software. The client runs on the user's terminal device, such as a mobile phone or computer. The client can be an application client or a web client for the spreadsheet software. The server can run on a server or server cluster to provide corresponding services to the software's clients. Optionally, the spreadsheet software can be instant messaging (IM) software with spreadsheet functionality. If the data processing device is integrated into the client, it can communicate with the server to use the target model through the server. Optionally, in Figure 1 In the application scenario shown, the data processing device can be integrated into the client 110. For ease of explanation, the following description uses the integration of the data processing device into the client as an example.

[0094] like Figure 2 As shown, the method specifically includes the following steps:

[0095] S201: In response to a display instruction for the first data range in the table, display the data processing component.

[0096] In this embodiment, the data processing device can display a data processing component according to a display instruction targeting a first data range in a table. The first data range is the range of data within the table, corresponding to a portion or the entire table. The display instruction is a user-triggered instruction. The data processing component includes a text input area. The text input area is used to receive text input by the user. For ease of explanation, the data within the first data range can be referred to as first data or target data.

[0097] In this embodiment, the data processing component can be displayed based on user actions. These actions correspond to display commands. Specifically, the data processing component can be hidden before a display command is received. After the display command is received, the data processing component can be displayed. The action corresponding to the display command can include a first action. The first action can include pressing a preset shortcut key, clicking a preset control, or issuing a voice command, etc. This embodiment does not limit the first action.

[0098] Furthermore, the display instruction is directed to a first data range within the table. Accordingly, the operation corresponding to the display instruction may also include an operation for determining the first data range. This operation for determining the first data range may be referred to as a second operation. Optionally, the second operation may, for example, include a box selection operation. The user can use the box selection operation to select the data to be processed to obtain the first data range.

[0099] Optionally, the second operation can be triggered before the first operation. That is, in order to trigger the display command, the user can first trigger the second operation by selecting the first data range corresponding to the target data to be processed in the table. Then, the user can trigger the first operation to bring up the hidden data processing component.

[0100] In other words, if a user wants to process target data using the target function, the user can trigger a first action. After receiving the user's first action, a data processing component can be displayed to the user. The data processing component includes a text input area. After displaying the data processing component, the user can enter the target text in the text input area.

[0101] Optionally, the data processing component may also include prompts. These prompts may correspond to a text input area, prompting the user to process the data in the table by entering text information in the text input area.

[0102] Optionally, the data processing component may also include data processing controls. These controls are used to trigger a third operation. The third operation corresponds to a data processing instruction. Further details regarding the third operation and data processing instructions can be found below and will not be repeated here.

[0103] In some possible implementations, the processing rules corresponding to the target text can be determined through a model. This model can be a model with Natural Language Processing (NLP) capabilities, such as a language model or a large language model. Optionally, the data processing component can correspond to a cloud service associated with the model. For ease of explanation, this cloud service can be referred to as the first cloud service.

[0104] In other words, users can invoke the first cloud service to process data within a first data range in a table using target text. Correspondingly, the data processing device can be a software module on the client side that implements the first cloud service. The data processing component can be the display area corresponding to the first cloud service. The data processing device can process the data by invoking the server-side of the first cloud service.

[0105] Thus, the first operation described above can be an operation using the first cloud service. For example, a user can first trigger the second operation to determine the display range of the first data, then trigger a right-click operation to bring up the menu, and then trigger a left-click operation on the operation control corresponding to the first cloud service in the menu.

[0106] In the above implementation, the data processing component is displayed based on display instructions. In other possible implementations, the data processing component can also be deployed in a specific area of ​​the client interface of the spreadsheet software, such as in the menu bar. Accordingly, when processing target data, if the user wants to process the target data, the user can switch the text input cursor to the data processing component and input the target text through the text input area of ​​the data processing component.

[0107] After demonstrating the data processing component to the user, the user can enter target text in the text input area and trigger a data processing instruction. The target text indicates the user's intention to process the target data, and the data processing instruction initiates the processing flow of the target data. Optionally, the user can obtain the data processing instruction by triggering a third operation. The third operation may include, for example, a click operation triggered by the user on the data processing control. That is, after completing the input of the target text, the user can trigger the third operation. Accordingly, the data processing device can obtain the data processing instruction based on the third operation and execute step S202 as described below.

[0108] S202: In response to a data processing instruction for the data processing component, the data in the first data range is processed according to the target text received through the text input area, and the adjustment result is displayed.

[0109] After receiving a data processing instruction triggered by the user, the data processing device can process the data in the first data range according to the target text received in the text input area and display the adjustment result. Optionally, the processing rule used to process the data in the first data range may be referred to as the first processing rule. That is, the first processing rule may include the first operation instruction, target condition information, and first display mode described below.

[0110] Optionally, the data processing device can send data processing instructions and target text to the server, so that the server can process the data in the first data range according to the target text. The data processing device can receive the adjusted data sent by the server and display it to the user. Optionally, the server can parse the target text using a model, and then adjust the data in the first data range according to the parsed data. Further details on this part can be found below and will not be repeated here.

[0111] The following describes some methods for adjusting the data within the first data range. Optionally, the data can be processed on the client side, or the client's data processing device can send the data to the server for processing. The implementation methods described below do not limit the entity responsible for adjusting the data.

[0112] In this embodiment, the adjustment of data within the first data range is performed according to the instruction of the target text. Optionally, the target text may include target instruction text, which is used to indicate a first operation instruction. The first operation instruction matches the adjustment performed on the data within the first data range. Optionally, the first operation instruction may be obtained by parsing the target instruction text by the model. That is, when processing the data within the first data range, a first adjustment instruction can be executed on the data within the first data range.

[0113] In real-world scenarios, users may need to process data based on certain conditions. Accordingly, the target text input by the user may also include conditional information text, which indicates the first condition. Consequently, when processing data within a first data range based on the target text, the target text can be parsed to obtain the first conditional information corresponding to the conditional information text, and then data processing can be performed based on the first conditional information. Optionally, the conditional information text and the aforementioned target instruction text can be the same text, for example, different parts of the same natural sentence.

[0114] When processing data within a first data range based on first condition information, data matching the first condition information can first be determined from the data within the first data range. This data matching the first condition information can be referred to as the first target data. After determining the first target data, it can be processed according to a first operation instruction.

[0115] Optionally, the first operation instruction may include a conditional filtering instruction, a conditional sorting instruction, and a conditional formatting instruction. These will be described in detail below.

[0116] In a first possible implementation, the first operation instruction includes a conditional filtering instruction. Accordingly, after determining the first target data, the first target data can be displayed in a second data range within the first data range. The second data range can be a pre-selected data range within the first data range, for example, the leftmost and topmost data range excluding the header within the first data range. Furthermore, non-first target data within the first data range can also be displayed abnormally.

[0117] In a second possible implementation, the first operation instruction includes a conditional sorting instruction. Accordingly, after determining the first target data, the data within the first data range can be sorted, and the first target data can be displayed before the non-first target data.

[0118] In a third possible implementation, the first operation instruction includes a conditional formatting instruction. Accordingly, after the target data is determined, the first target data can be displayed using a first display mode. The first display mode is a user-defined display mode for displaying the first target data. Optionally, the first display mode can be determined based on target text. For example, the target text may include display mode indicator text, which indicates the first display mode.

[0119] The third possible implementation method will be introduced below in conjunction with a practical use case. It is important to understand that the following description is only one implementation method and does not represent the only possible implementation.

[0120] Suppose the target data includes data of type A, type B, and type C, and the user wants to highlight the data of type A within the target data.

[0121] First, the user can trigger a first and second operation to control the display of the data processing component. For example, the user can select the target data and trigger a right-click operation. Based on the right-click operation triggered by the user, the client can display an operation menu to the user. The operation menu may include a first cloud service operation control. By triggering the first cloud service operation control, the user can control the client to display the data processing component. Next, the user can enter the text "Find data of type A and highlight it with a yellow background" in the text input area of ​​the data processing component and trigger a confirmation operation (i.e., the aforementioned third operation).

[0122] After receiving the text "Find data of type A and highlight it with a yellow background", the client can send this text to the target model via the server and receive information parsed by the model. This information may include information related to the first operation instruction, first condition information, and information related to the first display method. Specifically, the information related to the first operation instruction indicates that the first operation instruction is a condition-setting instruction; the first condition information includes information indicating "type A" data; and the information related to the first display method includes information indicating "yellow background".

[0123] Next, the data processing device can call the operation interface provided by the spreadsheet software for setting conditional formatting, setting the background color of the "Type A" data in the target data to "yellow," and then display it to the user through the client.

[0124] This application provides a data processing method. Specifically, data is first displayed to the user through a table. Then, the user can trigger a display command for a first data range in the table. Based on the user-triggered display command, a data processing component can be displayed. The data processing component includes a text input area. The user can input target text through the text input area. After receiving the data processing command for the data processing component, the data in the first data range can be processed according to the target text, and the adjustment result can be displayed. In other words, if the user needs to process the data in the first data range of the table, the user can first trigger the display command, then input the target text in the text input area, and then trigger the data processing command, so that the data can be processed according to the data processing command. In this way, automatic data processing can be achieved without the user needing to understand the specific processing rules, lowering the barrier to entry and improving the user experience.

[0125] In some possible implementations, the data processing device's processing of the data may deviate from the user's actual needs. That is, the processing of the target data based on the target text may not meet the user's requirements. In some possible implementations, to ensure correct processing of the target data, the user can trigger an operation to undo the processing of the target data.

[0126] Specifically, if a user wants to undo the processing of the target data, they can trigger the fourth operation. The fourth operation is used to undo the processing of the target data. After receiving the fourth operation, the modifications to the target data can be undone, and the target data will be displayed in the corresponding display area.

[0127] In some possible implementations, the fourth action can be triggered via existing keyboard shortcuts or control gestures. For example, a user can trigger the fourth action using the keyboard shortcut corresponding to the undo action. Alternatively, a user can trigger the fourth action by clicking the control gesture corresponding to the undo action.

[0128] In some other possible implementations, the user can also trigger the fourth operation through a control in the data processing component. Specifically, after processing the target data according to the first processing rule, a first control can be displayed in the data processing component. If the user wants to undo the processing of the target data, the user can trigger the fourth operation through the first control. Optionally, the first control may include a prompt message to indicate to the user that they can undo the processing of the target data through the first control.

[0129] The foregoing description outlines the data processing device in the client-side portion of the data processing method provided in this application's embodiments. In some possible implementations, the target text can be processed using a model.

[0130] The following is combined Figure 3 From the perspective of the server side of spreadsheet software, the data processing method provided in the embodiments of this application will be described exemplarily.

[0131] See Figure 3 , Figure 3 This application provides a flowchart illustrating a data processing method, which is applicable to application scenarios where data is processed through tables. This data processing method can be executed by a data processing device running on a server.

[0132] It should be noted that, Figure 3 The data processing device in the corresponding embodiment, and Figure 2 The data processing apparatus in the corresponding embodiments can be different apparatuses. For example, Figure 3 The data processing device in the corresponding embodiment can run on the server side of spreadsheet software, while Figure 2 The data processing device in the corresponding embodiment can run on the client side of spreadsheet software.

[0133] The data processing apparatus can be implemented in software. Optionally, the apparatus may include a model for processing target request data based on example data, or the apparatus may be associated with a model for processing target request data based on example data. Optionally, the model may include, for example, an LM model or an LLM model. In embodiments of this application, the model may be referred to as the target model.

[0134] Optionally, the data processing device can be integrated into the server-side of spreadsheet software. The server-side of the spreadsheet software can run on a server or server cluster to provide corresponding services to the software's clients. If the data processing device is integrated into the server-side, it can communicate with clients to obtain the target request data to be processed sent by the clients. Optionally, the data processing device can also communicate with the target model to send sample data and target request data to the target model. For ease of explanation, the following description uses the example of the data processing device being integrated into the server-side.

[0135] like Figure 3 As shown, the method specifically includes the following steps:

[0136] S301: Obtain the target text.

[0137] To process the target data, users can invoke the data processing component on the client side of the spreadsheet software and enter the target text through the text input box of the data processing component. Based on the data processing instructions for the data processing component, the client side of the spreadsheet software can send the target text to the server side of the spreadsheet software. Correspondingly, the data processing device running on the server side of the spreadsheet software can obtain the target text.

[0138] S302: Send the target text to the target model.

[0139] After obtaining the target text, the data processing device can send the target text to the target model. Optionally, the target model can be a model with semantic parsing capabilities, such as an LM or LLM. Accordingly, the target text is natural language text, and the first processing rule parsed from the target text can be implemented based on a structured language. For example, the first processing rule can be implemented based on JavaScript Object Notation (JSON).

[0140] Accordingly, the data processing device can send a prompt message to the target model. The prompt message may include the target text, and may also include other information. A detailed explanation of how to determine the first processing rule using the target model can be found later. Figure 4 The corresponding embodiments are described below. Further details will not be repeated here.

[0141] S303: The first processing rule for receiving feedback from the target model.

[0142] After obtaining the target text, the target model can parse the target text to determine the corresponding first processing rule. Then, the target model can send the first processing rule to the server so that the data in the first data range can be processed according to the first processing rule. Optionally, before processing the data in the first data range according to the first processing rule, a feasibility check can be performed on the first processing rule.

[0143] In this embodiment, the data processing device can be pre-configured with the ability to parse the first processing rule. Thus, after obtaining the first processing rule, it can be parsed to process the target data according to the corresponding processing flow. For example, as described above, the target model can be an LM or an LLM, and the first processing rule can be implemented based on JSON. Accordingly, the data processing device can be configured with the ability to parse JSON.

[0144] As mentioned earlier, spreadsheet software can have various preset data processing functions. Accordingly, when processing target data according to a first processing rule, the spreadsheet software can invoke the data processing functions provided by the first processing rule to process the target data. Specifically, the interface for invoking data processing functions can be configured in the spreadsheet software. After obtaining the first processing rule, the corresponding data processing interface can be invoked to process the target data according to the first processing rule.

[0145] In this embodiment of the application, the target data can be processed by a data processing device according to a first processing rule, or it can be processed by other modules or devices.

[0146] In some possible implementations, the client of the spreadsheet software has data processing capabilities. The data processing device can then invoke the client to process the target data according to a first processing rule. For example, if the data processing device runs on the client side, it can locally invoke the interface of the data processing function to process the target data according to the first processing rule. Alternatively, if the data processing device runs on the server side, it can send the first processing rule to the client, or send instruction information parsed from the first processing rule. The client of the spreadsheet software can then process the target data according to the first processing rule or the instruction information.

[0147] In some other possible implementations, the client-side of the spreadsheet software does not have the capability to process data; data processing is performed by the server-side of the spreadsheet software. For example, in some cloud service scenarios, the user's client does not have the ability to process data; data processing is performed by a server running in the cloud. In this case, the data processing device can run on the server to process the target data according to a first processing rule. Alternatively, if the data processing device runs on the client-side, it can send the first processing rule to the server to process the target data according to the first processing rule.

[0148] In the implementation method described above, the first processing rule can be determined by the target model based on the target text. The following example... Figure 1 Taking the implementation shown as an example, this paper introduces a method for determining the first processing rule through the target model.

[0149] In some possible implementations, client 110 can send target text to target model via server 120. Target model 130 can parse the target text to determine the user's intent, thereby determining the corresponding first processing rule, and then send the relevant information of the first processing rule to client 110 via server 120.

[0150] Optionally, if the target model 130 is a model with context learning capabilities, such as LM or LLM, then the target model 130 can first perform context learning on the relevant information of the processing rules, and then process the target text based on the results of the context learning. In this way, by performing context learning on the relevant information of the processing rules, the first processing rule determined by the target model 130 is more closely matched with the user's intent.

[0151] Optionally, relevant information about the processing rules can be pre-organized and stored. When the target model needs to determine the first processing rule, the server 120 can obtain relevant information about the processing rule and send it to the target model 130 via a prompt message, so that the target model 130 can perform contextual learning based on the relevant information about the processing rule.

[0152] As described above, the first processing rule corresponds to the data processing functions provided by spreadsheet software. Based on the first processing rule, the data processing functions provided by the spreadsheet software can be invoked to process the data. Therefore, in determining the first processing rule, the relevant information used for context learning can include information related to the data processing functions provided by the spreadsheet software. For example, it can include documents corresponding to the spreadsheet software that describe its data processing functions.

[0153] In real-world scenarios, spreadsheet software may offer a variety of data processing functions. Correspondingly, if the number of data processing functions is large, and the amount of data that a prompt message can carry is limited, then the prompt message may not be able to fully convey the relevant information for all the data processing functions in the spreadsheet software. Thus, the target model 130 cannot fully learn the contextual information related to the data processing functions of the spreadsheet software, and may be unable to accurately determine the first processing rule.

[0154] Therefore, in some possible implementations, multiple identifications can be performed using the target model 130. The following will combine... Figure 4 A detailed introduction will be provided.

[0155] See Figure 4 , Figure 4 This application provides a flowchart illustrating a method for determining a first processing rule. This application embodiment is applicable to... Figure 1 The network architecture shown illustrates the application scenario for the processing rules corresponding to the target text, determined through the target model 130. The target model 130 is a model with semantic recognition capabilities and can perform context learning. For example, the target model 130 may include an LM model or an LLM model.

[0156] like Figure 4As shown, the method specifically includes the following steps:

[0157] S401: Client 110 sends the target text to server 120.

[0158] For an introduction to the target text, please refer to the previous text; it will not be repeated here.

[0159] S402: Server 120 sends target text to target model 130.

[0160] After receiving the target text sent by client 110, server 120 can send the target text to target model 130. Optionally, server 120 can send the target text to target model 130 via a first prompt message.

[0161] It should be noted that before step S405, the target model 130 may not have performed context learning on the target text and may not have the ability to determine the first processing rule based on the target text.

[0162] S403: Target model 130 determines instruction parsing information based on the target text.

[0163] After acquiring the target text, the target model 130 can perform semantic parsing to determine the corresponding instruction parsing information. Optionally, the first prompt information mentioned above may include relevant information for semantic parsing, so that the target model 130 can perform context learning. In this way, by first performing context learning and then parsing the target text, the target model 130 can accurately determine the instruction parsing information.

[0164] In this embodiment, the instruction parsing information can be a vector. That is, the target model 130 can vectorize the target text (Embedding). For ease of explanation, the vector corresponding to the instruction parsing information can be referred to as the first vector.

[0165] S404: Target model 130 sends instruction parsing information to server 120.

[0166] After determining the instruction parsing information corresponding to the target text, the target model 130 can send the instruction parsing information to the server 120.

[0167] S405: Server 120 determines at least one intermediate processing rule based on the instruction parsing information.

[0168] After obtaining the instruction parsing information, the server 120 can determine at least one intermediate processing rule based on the instruction parsing information. Furthermore, the similarity between the intermediate processing rule and the first processing rule is higher than the similarity between the non-intermediate processing rule and the first processing rule.

[0169] In this embodiment, the intermediate processing rules are determined based on the data processing functions provided by the spreadsheet software. The intermediate processing rules can be processing rules used to invoke data processing functions. That is, the intermediate processing rules can correspond to a data processing function of the spreadsheet software. Processing data according to the intermediate processing rules is equivalent to using that data processing function to process the data.

[0170] Specifically, multiple candidate processing rules can be predetermined. These candidate processing rules correspond to the data processing functions provided by spreadsheet software. After obtaining the instruction parsing information, an intermediate processing rule can be determined from the multiple candidate processing rules based on the instruction parsing information. In this embodiment, the intermediate processing rule can be determined based on the feature vector of the candidate processing rule. For example, the intermediate processing rule can be determined based on the similarity between the feature vector of the candidate processing rule and the vector corresponding to the instruction parsing information.

[0171] Optionally, the feature vector of the aforementioned candidate processing rule can be obtained by vectorizing the descriptive information of the candidate processing rule. The descriptive information of the candidate processing rule refers to relevant information describing the candidate processing rule. For example, it may include the function of the candidate processing rule, the interface of the corresponding data processing function, and the relevant parameters required by the candidate processing rule. Optionally, the descriptive information of the processing rule can be determined through the introductory information of the spreadsheet software. The introductory information of the spreadsheet software may include, for example, the software's instruction manual or user manual.

[0172] In practical applications, the description information of candidate processing rules can be vectorized in advance to obtain the feature vector of each candidate processing rule. Then, the feature vectors of the candidate processing rules can be stored in database 140 (not shown in the figure). After obtaining the instruction parsing information, the feature vectors of the candidate processing rules can be retrieved from the database.

[0173] Next, the similarity between the first vector and the feature vector of each candidate processing rule can be calculated. For example, the cosine similarity and double dot (ddot) of the feature vectors of the first vector and the candidate processing rule can be calculated, and then at least one intermediate processing rule can be determined based on the calculation results.

[0174] S406: Server 120 sends information about at least one intermediate processing rule to target model 130.

[0175] After determining at least one intermediate processing rule, the server 120 can send information related to the intermediate processing rule to the target model 130. This information may include, for example, the expression of the intermediate processing rule, its description, and the vector corresponding to the rule.

[0176] Specifically, server 120 can generate a second prompt message and then send it to target model 130. The second prompt message may include information about intermediate processing rules. Optionally, the second prompt message may also include target text or instruction parsing information.

[0177] Before generating the second prompt message, one or more checks can be performed. For example, it can be determined whether the target text is irrelevant to the data processing functions of spreadsheet software, whether the number of tokens included in the second prompt message exceeds a preset threshold, and whether the intermediate processing rules are reasonably relevant to the target text. After passing these checks, the corresponding second prompt message can be generated.

[0178] S407: The target model 130 performs contextual learning on information from at least one intermediate processing rule and determines the first processing rule.

[0179] After obtaining information about at least one intermediate processing rule, the target model 130 can perform context learning based on the information of the intermediate processing rule, and process the target text (or instruction parsing information) after context learning to determine the information of the first processing rule corresponding to the target text.

[0180] S408: Target model 130 sends the information of the first processing rule to client 110 through server 120.

[0181] After determining the information of the first processing rule, the target model 130 can send the information of the first processing rule to the client 110 through the server 120. Accordingly, the data processing device can obtain the information of the first processing rule and display it.

[0182] In other words, if the relevant information of the processing rules is too much to be carried in the prompt information, the target model 130 can first perform preliminary parsing of the target text to determine the instruction parsing information corresponding to the target text. Then, the server 120 can perform preliminary screening of candidate processing rules based on the instruction parsing information to find intermediate processing rules with a high degree of relevance to the instruction parsing information. In this way, through the screening by the server 120, processing rules irrelevant to the target text can be filtered out, and intermediate processing rules with a high degree of relevance to the target text can be selected. Since the number of intermediate processing rules is less than the number of candidate processing rules, the prompt information can carry the relevant information of the intermediate processing rules. Furthermore, since the information of the intermediate processing rules is filtered based on the instruction parsing information, the correlation between the intermediate processing rules and the first processing rule is higher than the correlation between the non-intermediate processing rules and the first processing rule. Therefore, the target model 130's context learning based on the information of the intermediate processing rules will not affect the accuracy of the target model 130. Thus, while ensuring the accuracy of the first processing rule, the amount of data in the prompt information is reduced.

[0183] Based on the data processing method provided in the above embodiments, this application also provides two data processing devices, which run on the client and server sides of spreadsheet software, respectively. The data processing devices will now be described in conjunction with the accompanying drawings.

[0184] See Figure 5 As shown, this figure is a schematic diagram of the structure of a data device for a client running spreadsheet software, according to an embodiment of this application. Figure 5 As shown, the data processing apparatus 500 includes:

[0185] Display unit 510 is configured to display a data processing component, which includes a text input area, in response to a display instruction for a first data range in a table.

[0186] Processing unit 520 is configured to process data in the first data range according to the target text received through the text input area in response to a data processing instruction for the data processing component.

[0187] The display unit 510 is also used to display the adjusted data in the first range.

[0188] In some possible implementations, the target text includes target instruction text, which indicates a first operation instruction; the processing unit 520 is specifically used to execute the first adjustment instruction on the data in the first data range.

[0189] In some possible implementations, the target instruction text further includes condition information text, which indicates first condition information; the processing unit 520 is specifically used to determine first target data, which matches the first condition information; and to process the first target data according to the first operation instruction.

[0190] In some possible implementations, the processing unit 520 is specifically used to display the first target data in a second data range within the first data range; or, to display the first target data in a first display mode, wherein the target text further includes display mode indication text, the display mode indication text indicating the first display mode.

[0191] In some possible implementations, processing the first target data according to the first operation instruction includes displaying the first target data in a second data range within the first data range; the display unit 510 is specifically used to hide and display non-first target data within the first data range.

[0192] In some possible implementations, the processing unit 520 is also used to add an instruction control to at least one cell corresponding to the first data range.

[0193] In some possible implementations, the apparatus further includes a sending unit and a receiving unit, wherein the sending unit is used to send the target text to the target model; the receiving unit is used to receive the first processing rule sent by the target model; and the processing unit is further used to process the data in the first data range according to the first processing rule.

[0194] In some possible implementations, the processing unit is further configured to perform a feasibility check on the first processing rule by processing the data in the first data range.

[0195] See Figure 6 As shown, this figure is a schematic diagram of the structure of a data device running on a server side of spreadsheet software, according to an embodiment of this application. Figure 6 As shown, the data processing device 600 includes:

[0196] The acquisition unit 610 is used to acquire target text, which is acquired by the client of the target software during the process of processing the data in the first data range of the table and sent to the server.

[0197] The sending unit 620 is used to send target text to the target model;

[0198] The receiving unit 630 is used to receive the first processing rule fed back by the target model, the first processing rule being used to process the data in the first data range.

[0199] Optionally, the acquisition unit 610 and the receiving unit 630 can be the same unit or different units.

[0200] In some possible implementations, the apparatus further includes a processing unit; the receiving unit 630 is further configured to receive instruction parsing information sent by the target model, the instruction parsing information being obtained by semantic parsing the target text; the processing unit is configured to determine at least one intermediate processing rule based on the instruction parsing information; the sending unit 620 is further configured to send information of the at least one intermediate processing rule to the target model, the first processing rule being determined from the plurality of intermediate processing rules.

[0201] In some possible implementations, the instruction parsing information includes a first vector corresponding to the target text; the processing unit is specifically used to obtain feature vectors of multiple candidate processing rules; and to determine at least one intermediate processing rule from the multiple candidate processing rules based on the first vector and the feature vectors of the candidate processing rules.

[0202] Based on the data processing method provided in the above embodiments, this application also provides an electronic device, including: one or more processors; a storage device storing one or more programs thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the data processing method as described in any of the above embodiments.

[0203] The following is for reference. Figure 7 The illustration shows a structural diagram of an electronic device 700 suitable for implementing embodiments of this application. The terminal devices in the embodiments of this application may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Android Devices), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs (televisions), desktop computers, etc. The illustrated electronic device is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0204] like Figure 7As shown, the electronic device 700 may include a processing unit (e.g., a central processing unit, a graphics processor, etc.) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage device 708 into a random access memory (RAM) 703. The RAM 703 also stores various programs and data required for the operation of the electronic device 700. The processing unit 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0205] Typically, the following devices can be connected to I / O interface 705: input devices 706 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 707 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 708 including, for example, magnetic tapes, hard disks, etc.; and communication devices 709. Communication device 709 allows electronic device 700 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 7 An electronic device 700 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0206] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 709, or installed from storage device 708, or installed from ROM 702. When the computer program is executed by processing device 701, it performs the functions defined in the methods of embodiments of this application.

[0207] The electronic device provided in this application embodiment belongs to the same inventive concept as the data processing method and file sending method provided in the above embodiments. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0208] Based on the methods provided in the above embodiments, this application provides a computer storage medium storing a computer program thereon, wherein the program, when executed by a processor, implements the data processing method as described in any of the above embodiments.

[0209] It should be noted that the computer-readable medium described above in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0210] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0211] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0212] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the aforementioned data processing method.

[0213] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0214] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0215] The units described in the embodiments of this application can be implemented in software or in hardware. The name of the unit / module does not necessarily limit the unit itself; for example, a voice data acquisition module can also be described as a "data acquisition module".

[0216] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0217] In the context of this application, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0218] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems or apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and relevant parts can be referred to the method section.

[0219] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0220] It should also be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0221] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A data processing method, characterized in that, The method includes: In response to a display instruction for a first data range in a table, a data processing component is displayed, the data processing component including a text input area; In response to a data processing instruction for the data processing component, target text is sent to the target model; wherein the target text is received through the text input area, the target text is natural language text, the target text includes target instruction text, the target instruction text indicates a first operation instruction, the first operation instruction includes at least one of a conditional filtering instruction, a conditional sorting instruction, or a conditional formatting instruction, the first operation instruction is used to adjust the data in the first data range, the conditional formatting instruction is used to instruct data that meets the conditions to be displayed in a specified display manner; the target model is used to perform semantic parsing on the target text to obtain instruction parsing information corresponding to the target instruction text, the instruction parsing information is used to determine a first processing rule. Receive the first processing rule sent by the target model, the first processing rule corresponding to the data processing function provided by the spreadsheet software; The data within the first data range is processed according to the first processing rule, and the adjustment results are displayed.

2. The method according to claim 1, characterized in that, The target instruction text further includes conditional information text, which indicates first conditional information; the adjustment of data in the first data range includes: First target data is determined, and the first target data matches the first condition information; The first target data is processed according to the first operation instruction.

3. The method according to claim 2, characterized in that, The processing of the first target data according to the first operation instruction includes: The first target data is displayed in the second data range within the first data range; or... The first target data is displayed in a first display mode, and the target text further includes display mode indication text, which indicates the first display mode.

4. The method according to claim 3, characterized in that, The step of processing the first target data according to the first operation instruction includes displaying the first target data in a second data range within the first data range. Displaying the first target data in the second data range within the first data range includes: Hide and display non-first target data within the first data range.

5. The method according to claim 1, characterized in that, The step of processing the data in the first data range according to the first processing rule includes: Add an instruction control to at least one cell corresponding to the first data range.

6. The method according to claim 1, characterized in that, Before processing the data in the first data range according to the first processing rule, the method further includes: The feasibility of the first processing rule is verified based on the data in the first data range.

7. A data processing method, characterized in that, The method is applied to the server side of the target software, which has table processing functionality. The method includes: The target text is obtained by the client of the target software during the processing of the data in the first data range of the table and sent to the server. The target text is natural language text. The target text is sent to the target model; wherein the target text includes target instruction text, the target instruction text indicates a first operation instruction, the first operation instruction includes at least one of conditional filtering instruction, conditional sorting instruction, or conditional formatting instruction, the first operation instruction is used to adjust the data in the first data range, and the conditional formatting instruction is used to instruct data that meets the conditions to be displayed in a specified display mode; the target model is used to perform semantic parsing on the target text to obtain instruction parsing information corresponding to the target instruction text, and the instruction parsing information is used to determine a first processing rule; The system receives a first processing rule from the target model. This first processing rule is used to process the data within the first data range. The first processing rule corresponds to the data processing function provided by the spreadsheet software.

8. The method according to claim 7, characterized in that, After sending the target text to the target model, the method further includes: Receive instruction parsing information sent by the target model, wherein the instruction parsing information is obtained by semantic parsing the target text; At least one intermediate processing rule is determined based on the instruction parsing information; Information about the at least one intermediate processing rule is sent to the target model, wherein the first processing rule is determined from the at least one intermediate processing rule.

9. The method according to claim 8, characterized in that, The instruction parsing information includes a first vector, which corresponds to the target text; Determining at least one intermediate processing rule based on the instruction parsing information includes: Obtain the feature vectors of multiple candidate processing rules; Based on the first vector and the feature vector of the candidate processing rule, at least one intermediate processing rule is determined from the plurality of candidate processing rules.

10. A data processing apparatus, characterized in that, The device includes: The display unit is configured to display a data processing component, which includes a text input area, in response to a display instruction for a first data range in a table. A sending unit is configured to send target text to a target model in response to a data processing instruction for the data processing component; wherein the target text is received through the text input area, the target text is natural language text, the target text includes target instruction text, the target instruction text indicates a first operation instruction, the first operation instruction includes at least one of a conditional filtering instruction, a conditional sorting instruction, or a conditional formatting instruction, the first operation instruction is used to adjust data in the first data range, and the conditional formatting instruction is used to instruct data that meets the conditions to be displayed in a specified display manner; the target model is configured to perform semantic parsing on the target text to obtain instruction parsing information corresponding to the target instruction text, the instruction parsing information is used to determine a first processing rule. A receiving unit is used to receive a first processing rule sent by the target model, wherein the first processing rule corresponds to the data processing function provided by the spreadsheet software. The processing unit is configured to process the data in the first data range according to the first processing rule; The display unit is also used to display the adjusted data in the first data range.

11. A data processing apparatus, characterized in that, The device is applied to the server side of the target software, which has table processing functionality. The device includes: The acquisition unit is used to acquire target text, which is acquired by the client of the target software during the process of processing the data in the first data range of the table and sent to the server. The target text is natural language text. A sending unit is configured to send target text to a target model; wherein the target text includes target instruction text, the target instruction text indicating a first operation instruction, the first operation instruction including at least one of a conditional filtering instruction, a conditional sorting instruction, or a conditional formatting instruction, the first operation instruction being used to adjust data in the first data range, and the conditional formatting instruction being used to instruct data that meets the conditions to be displayed in a specified display manner; the target model is configured to perform semantic parsing on the target text to obtain instruction parsing information corresponding to the target instruction text, the instruction parsing information being used to determine a first processing rule; The receiving unit is used to receive the first processing rule fed back by the target model. The first processing rule is used to process the data in the first data range. The first processing rule corresponds to the data processing function provided by the spreadsheet software.

12. An electronic device, characterized in that, include: One or more processors; Storage device, on which one or more programs are stored, When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-9.

13. A computer-readable medium, characterized in that, It stores a computer program thereon, wherein the program, when executed by a processor, implements the method as described in any one of claims 1-9.

Images