Data processing method and device based on generative large language model

Abstract

The embodiment of the invention discloses a data processing method and device based on a generative large language model. The method comprises the steps that a spreadsheet area and an assistant bar area are displayed on a target display interface; acquiring a spreadsheet operation description input by a user from the assistant bar area, and calling the target generative large language model to perform operation analysis processing on the spreadsheet operation description to obtain target table operation information; and determining a target editing script based on the target table operation information, and calling the target editing script to perform target table operation processing on the spreadsheet region. The steps of executing operation processing on the spreadsheet area by the user are simplified, the spreadsheet operation description is obtained through the assistant column area so as to identify the operation expected by the user, the operation is autonomously executed on the spreadsheet area, additional intervention of the user is not needed, continuous iteration updating of a spreadsheet software version is solved, and the user experience is improved. And the learning cost of the user is high.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and in particular, to a data processing method and apparatus based on a generative large language model. Background Art

[0002] With the rapid development of information technology, spreadsheet software has become a common table processing application in daily life. However, with the continuous iterative update of the spreadsheet software version, the interface functions of the spreadsheet software have become increasingly complex, resulting in a high learning cost for users to learn the spreadsheet interface. Summary of the Invention

[0003] Embodiments of this application provide a data processing method and apparatus based on a generative large language model, which can solve the technical problem that as the spreadsheet software version is continuously iteratively updated, the functions of the spreadsheet software become increasingly complex, resulting in a high learning cost for users to learn the spreadsheet interface.

[0004] In a first aspect, embodiments of this application provide a data processing method based on a generative large language model, the method including:

[0005] Display a spreadsheet area and an assistant bar area on a target display interface;

[0006] Obtain an input spreadsheet operation description from the assistant bar area, and call a target generative large language model to perform operation parsing processing on the spreadsheet operation description to obtain target table operation information for the user;

[0007] Determine a target editing script based on the target table operation information, and call the target editing script to perform target table operation processing on the spreadsheet area.

[0008] Optionally, the displaying a spreadsheet area and an assistant bar area on a target display interface includes:

[0009] Display a spreadsheet area and a table operation assistant control on a target display interface;

[0010] In response to a trigger operation on the table operation assistant control, display the assistant bar area.

[0011] Optionally, the in response to a trigger operation on the table operation assistant control, display the assistant bar area includes:

[0012] In response to a click operation on the table operation assistant control, display the assistant bar area, the assistant bar area including an input box area and a dialog box area;

[0013] Obtaining the spreadsheet operation description input by the user from the assistant bar area includes:

[0014] Receiving the spreadsheet operation description input by the user for the input box area;

[0015] In response to the input confirmation operation for the spreadsheet operation description, displaying the spreadsheet operation description in the dialog box area and obtaining the spreadsheet operation description from the dialog box area.

[0016] Optionally, after invoking the target editing script to perform target table operation processing on the spreadsheet area, it further includes:

[0017] Obtaining the table operation processing status information and displaying the table operation processing status information in the dialog box area.

[0018] Optionally, the assistant bar area further includes an instruction set area, and the method further includes:

[0019] In response to the first operation on the instruction set control, displaying an instruction set operation prompt area, where the instruction set operation prompt area includes at least one reference table operation item;

[0020] In response to the second operation on the target table operation item in the reference table operation items, displaying the target operation prompt information corresponding to the target table operation item in the dialog box area.

[0021] Optionally, the displaying the assistant bar area includes:

[0022] Displaying the assistant bar area and displaying assistant operation guidance information in the assistant bar area.

[0023] Optionally, invoking the target generative large language model to perform operation parsing processing on the spreadsheet operation description to obtain the target table operation information for the user includes:

[0024] Constructing an operation parsing prompt word based on the spreadsheet operation description and obtaining editing operation configuration information;

[0025] Inputting the operation parsing prompt word and the editing operation configuration information into the target generative large language model for operation parsing processing and outputting the target table operation information for the user.

[0026] Optionally, the inputting the operation parsing prompt word and the editing operation configuration information into the target generative large language model for operation parsing processing and outputting the target table operation information for the user includes:

[0027] Input the operation parsing prompt word and the editing operation configuration information into the target generative large language model, and perform information extraction processing on the operation parsing prompt word based on the target generative large language model to obtain user intention information;

[0028] Determine the target table operation from the editing operation configuration information based on the user intention information, and determine the editing execution script name and script parameters of the target table operation;

[0029] Output target table operation information including the editing execution script name and the script parameters based on the target generative large language model.

[0030] Optionally, the determining the target editing script based on the target table operation information includes:

[0031] Obtain the editing execution script name and script parameters from the target table operation information for the user in the target table operation information;

[0032] Determine the target editing script based on the editing execution script name and script parameters.

[0033] Optionally, the determining the target editing script based on the editing execution script name and script parameters includes:

[0034] Call the template editing script corresponding to the editing execution script name, and input the script parameters into the template editing script to obtain the target editing script.

[0035] In a second aspect, an embodiment of the present application provides a data processing device based on a generative large language model, and the device includes:

[0036] A display module, adapted to display a spreadsheet area and an assistant bar area on a target display interface;

[0037] A calling module, adapted to obtain the spreadsheet operation description input by the user from the assistant bar area, and call the target generative large language model to perform operation parsing processing on the spreadsheet operation description to obtain target table operation information for the user;

[0038] A processing module, adapted to determine a target editing script based on the target table operation information, and call the target editing script to perform target table operation processing on the spreadsheet area.

[0039] In a third aspect, an embodiment of the present application provides an electronic device, where the electronic device includes:

[0040] A processor; and

[0041] A memory arranged to store computer-executable instructions that, when executed, cause the processor to perform the method described in any of the above.

[0042] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs that, when executed by a processor, implement the method described in any of the above.

[0043] The beneficial effects brought by the technical solutions provided in some embodiments of the embodiments of the present application at least include:

[0044] Receive the user's spreadsheet operation description for the spreadsheet area through the assistant bar area, then extract the target table operation information corresponding to the processing that the user expects to perform on the spreadsheet area based on the user's spreadsheet operation description, and then automatically perform the target table operation processing on the spreadsheet area by the target editing script corresponding to the target table operation information. The present application simplifies the steps for the user to perform operation processing on the spreadsheet area based on the assistant bar area. By obtaining the spreadsheet operation description input by the user from the assistant bar area, the operation that the user expects to perform is identified, and then the corresponding operation is automatically performed on the spreadsheet area, which can be completed without the intervention of the user, solving the technical problem that as the version of the spreadsheet software is continuously iterated and updated, the functions of the spreadsheet software become more and more complex, resulting in a high learning cost for the user to the spreadsheet interface. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative efforts.

[0046] Figure 1 An exemplary system architecture diagram of a data processing method based on a generative large language model provided by an embodiment of the present application;

[0047] Figure 2 A flowchart of a data processing method based on a generative large language model provided by an embodiment of the present application;

[0048] Figure 3 An interface diagram of a spreadsheet area and an assistant bar area provided by an embodiment of the present application;

[0049] Figure 4 A flowchart of displaying a spreadsheet area and an assistant bar area on a target display interface provided by an embodiment of the present application;

[0050] Figure 5 A flowchart showing the process of displaying target operation prompt information corresponding to target table operation items provided by an embodiment of the present application;

[0051] Figure 6 A flowchart showing the process of swapping positions of spreadsheet areas in a spreadsheet operation description provided by an embodiment of the present application;

[0052] Figure 7 A flowchart showing the process of filtering data in a spreadsheet area in a spreadsheet operation description provided by an embodiment of the present application;

[0053] Figure 8 A flowchart showing the process of marking data in a spreadsheet area in a spreadsheet operation description provided by an embodiment of the present application;

[0054] Figure 9 A flowchart showing the process of sorting a spreadsheet area in a spreadsheet operation description provided by an embodiment of the present application;

[0055] Figure 10 A flowchart showing the process of performing a calculation operation on a spreadsheet area in a spreadsheet operation description provided by an embodiment of the present application;

[0056] Figure 11 A flowchart showing the process of performing a drawing operation on a spreadsheet area in a spreadsheet operation description provided by an embodiment of the present application;

[0057] Figure 12 A flowchart showing the process of obtaining target table operation information for a user provided by an embodiment of the present application;

[0058] Figure 13 A flowchart showing the process of outputting target table operation information for a user provided by an embodiment of the present application;

[0059] Figure 14 A schematic structural diagram of a data processing device based on a generative large language model provided by an embodiment of the present application;

[0060] Figure 15 A schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0061] To make the features and advantages of the embodiments of the present application more obvious and understandable, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all embodiments. Based on the embodiments in the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope protected by the embodiments of the present application.

[0062] With the development of the Internet, more and more people need to use spreadsheet software in office and daily life. However, with the continuous iteration and update of the spreadsheet software version, the interface functions of the spreadsheet software have become more and more complex. For novices, the time and energy costs required to learn the interface functions of the spreadsheet software are relatively high; at the same time, for skilled users, it also takes a certain amount of energy to complete an interface operation function.

[0063] To solve the above technical problems, the embodiments of the present application provide a data processing method. First, a spreadsheet area and an assistant bar area are displayed on a target display interface. Then, the spreadsheet operation description input by the user is obtained from the assistant bar area, and a target generative large language model is called to perform operation parsing processing on the spreadsheet operation description to obtain target table operation information for the user. Finally, a target editing script is determined based on the target table operation information, and the target editing script is called to perform target table operation processing on the spreadsheet area.

[0064] In the embodiments of the present application, the spreadsheet operation description of the user for the spreadsheet area is received through the assistant bar area. Then, the target table operation information corresponding to the processing that the user expects to perform on the spreadsheet area is extracted based on the user's spreadsheet operation description. After that, the target table operation processing on the spreadsheet area is automatically performed by the target editing script corresponding to the target table operation information. The present application simplifies the steps for the user to perform operation processing on the spreadsheet area based on the assistant bar area. By obtaining the spreadsheet operation description input by the user from the assistant bar area, the operation that the user expects to perform is identified, and then the corresponding operation is automatically performed on the spreadsheet area without the need for user intervention, solving the technical problem that as the spreadsheet software version is continuously iterated and updated, the functions of the spreadsheet software become more and more complex, resulting in a relatively high learning cost for users of the spreadsheet interface.

[0065] Please refer to Figure 1 , Figure 1 which is an exemplary system architecture diagram of a data processing method based on a generative large language model provided by the embodiments of the present application.

[0066] As shown in Figure 1As shown in the figure, the system architecture may include an electronic device 101, a network 102, and a server 103. The network 102 is used to provide a medium for the communication link between the electronic device 101 and the server 103. The network 102 may include various types of wired communication links or wireless communication links. For example, the wired communication links include optical fibers, twisted pairs, or coaxial cables, and the wireless communication links include Bluetooth communication links, Wireless-Fidelity (Wi-Fi) communication links, or microwave communication links, etc.

[0067] The electronic device 101 can interact with the server 103 through the network 102 to receive messages from the server 103 or send messages to the server 103. Or the electronic device 101 can interact with the server 103 through the network 102, and then receive messages or data sent by other users to the server 103. The electronic device 101 can be hardware or software. When the electronic device 101 is hardware, it can be various electronic devices, including but not limited to smart watches, smart phones, tablet computers, laptop portable computers, and desktop computers, etc. When the electronic device 101 is software, it can be installed in the above-listed electronic devices, and it can be implemented as multiple software or software modules (for example, used to provide distributed services), or it can be implemented as a single software or software module, which is not specifically limited here.

[0068] The server 103 can be a business server that provides various services. It should be noted that the server 103 can be hardware or software. When the server 103 is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or it can be implemented as a single server. When the server 103 is software, it can be implemented as multiple software or software modules (for example, used to provide distributed services), or it can be implemented as a single software or software module, which is not specifically limited here.

[0069] In the embodiment of this application, the electronic device 101 can display a spreadsheet area and an assistant bar area based on a target display interface; obtain the spreadsheet operation description input by the user from the assistant bar area, call a target generative large language model to perform operation parsing processing on the spreadsheet operation description, and obtain target table operation information for the user; determine a target editing script based on the target table operation information, and call the target editing script to perform target table operation processing on the spreadsheet area.

[0070] It should be understood that Figure 1 the numbers of the electronic devices, networks, and servers in

[0071] Please refer to Figure 2 , Figure 2Schematic flowchart of a data processing method based on a generative large language model provided by an embodiment of this application. The execution subject of the embodiment of this application can be an electronic device that executes the data processing method based on the generative large language model, or a processor in the electronic device that executes the data processing method based on the generative large language model, or a data processing service in the electronic device that executes the data processing method based on the generative large language model. For ease of description, hereinafter, taking the execution subject as the processor in the electronic device as an example, the specific execution process of the data processing method based on the generative large language model is introduced.

[0072] As Figure 2 shown, the data processing method based on the generative large language model includes:

[0073] S202: Display a spreadsheet area and an assistant bar area on a target display interface.

[0074] Among them, the target display interface includes but is not limited to a software display interface, an online display interface, etc. Specifically, when the target display interface is a software display interface, the software corresponding to the software display interface can be a spreadsheet software, and this spreadsheet software can be installed on the electronic device; when the target display interface is an online display interface, the software corresponding to the online display interface can be a browser, and this browser can be installed on the electronic device, and the online display interface can be accessed through the browser and interactive processing can be performed on the online display interface. At this time, multiple people can support simultaneous online editing.

[0075] Please refer to Figure 3 , Figure 3 which is a schematic diagram of an interface of a spreadsheet area and an assistant bar area provided by an embodiment of this application. As Figure 3 shown, the spreadsheet area corresponds to the 301 area in the figure, and the assistant bar area corresponds to the 302 area in the figure. The spreadsheet area displayed on the target display interface can display and manage spreadsheet data. This area can include one or more tables, and each table is composed of rows and columns for displaying various types of data, such as text, numbers, dates, etc. In the spreadsheet area, the user can perform various operations, such as adding new rows or columns, editing the content in the cells, adjusting the layout and style of the table, and applying various filtering and sorting conditions to sort and analyze the data, etc.

[0076] The assistant bar area displayed on the target display interface is associated with the spreadsheet area. The assistant bar area can be set on one side of the spreadsheet area, and the effect of controlling the spreadsheet area can be achieved by entering a spreadsheet operation description in the assistant bar area. At the same time, in order to distinguish the spreadsheet area from the assistant bar area, the background color of the spreadsheet area and the background color of the assistant bar area can be displayed differently.

[0077] S204: Obtain the spreadsheet operation description input by the user from the assistant bar area, and call the target generative large language model to perform operation parsing and processing on the spreadsheet operation description to obtain the target table operation information for the user.

[0078] Among them, the user can input the spreadsheet operation description in the assistant bar area. The spreadsheet operation description can be the natural language corresponding to the spreadsheet operation that the user expects to perform, such as "Sort the values in the first column in ascending order", "Swap columns A and B", etc.

[0079] After obtaining the spreadsheet operation description input by the user from the assistant bar area, the processor can call the target generative large language model to perform operation parsing and processing on the spreadsheet operation description. By means of the target generative large language model to perform operation parsing and processing on the spreadsheet operation description, it is possible to effectively identify the editing operation that the user wants to perform on the spreadsheet area. Here, the target generative large language model can understand natural language text. Specifically, the target generative large language model can be an LLM (Large Language Model). The LLM is a model based on machine learning and natural language processing technologies. It learns the ability of human language understanding and generation by training on a large amount of text data.

[0080] After the target generative large language model performs operation parsing and processing on the spreadsheet operation description, the target table operation information for the user can be obtained. Here, the target table operation information can be the computer language generated by the target generative large language model after identifying the spreadsheet operation description. Specifically, the target table operation information can be text in JSON (JavaScript Object Notation) format. JSON is a lightweight data interchange format, easy for humans to read and write, can be used for data interchange between multiple languages, and is also easy for machines to parse and generate. The target table operation information contains the operations that the user expects to perform on the spreadsheet area and the corresponding relevant parameters.

[0081] S206: Determine the target editing script based on the target table operation information, and call the target editing script to perform target table operation processing on the spreadsheet area.

[0082] Among them, after obtaining the target table operation information, a target editing script is generated based on the target table operation information. When the target editing script is called, it can perform target table operation processing on the spreadsheet area. The target table operation processing is the operation that the user expects to perform on the spreadsheet area by means of the spreadsheet operation description. The target editing script can be a JavaScript script.

[0083] In the embodiment of the present application, the spreadsheet operation description of the user for the spreadsheet area is received through the assistant bar area, and then the target table operation information corresponding to the processing that the user expects to perform on the spreadsheet area is extracted based on the user's spreadsheet operation description. Then, the target table operation processing is automatically performed on the spreadsheet area by the target editing script corresponding to the target table operation information. The present application simplifies the steps for the user to perform operation processing on the spreadsheet area based on the assistant bar area. By obtaining the spreadsheet operation description input by the user from the assistant bar area, the operation that the user expects to perform is identified, and then the corresponding operation is autonomously performed on the spreadsheet area, which can be completed without the intervention of the user, solving the technical problem that as the version of the spreadsheet software is continuously iterated and updated, the functions of the spreadsheet software become more and more complex, resulting in a relatively high learning cost for the user to the spreadsheet interface.

[0084] Please refer to Figure 4 , Figure 4 which is a schematic flowchart of displaying a spreadsheet area and an assistant bar area on a target display interface provided by an embodiment of the present application. In an embodiment provided by the present application, in S202, displaying the spreadsheet area and the assistant bar area on the target display interface includes:

[0085] S402: Display a spreadsheet area and a table operation assistant control on the target display interface.

[0086] After the user opens the spreadsheet, the spreadsheet area and the table operation assistant control will first be displayed on the target display interface. Among them, the table operation assistant control can move freely on the spreadsheet area under the operation of the user. For example, the table operation assistant control can move freely on the spreadsheet area under the control of a mouse, keyboard or other input devices.

[0087] When the transparency of the table operation assistant control can be adjusted correspondingly based on the state of the table operation assistant control. For example, when the table operation assistant control is selected, the table operation assistant control is in a selected state, and at this time, the transparency of the table operation assistant control can be 0%; when the table operation assistant control is not selected, the table operation assistant control is in an idle state, and at this time, the transparency of the table operation assistant control can be 50% - 70%. Through such a setting, it is possible to avoid the table operation assistant control blocking the spreadsheet area when the table operation assistant control is not operated.

[0088] S404: In response to a trigger operation on the table operation assistant control, display the assistant bar area.

[0089] When the user expects to display the assistant bar area, a trigger operation can be performed on the table operation assistant control. Specifically, the trigger operation can be a touch screen click operation, a mouse click operation, an air gesture operation, a voice control operation, etc. After the trigger operation is performed on the table operation assistant control, the assistant bar area can be displayed. After the assistant bar area is displayed, the table operation assistant control can be hidden and no longer displayed. When the assistant bar area is closed, the table operation assistant control can be displayed again.

[0090] During the process of displaying the assistant bar area, the spreadsheet area can gradually shrink, so that the assistant bar area is displayed in the reserved space formed by the shrinking of the spreadsheet area on the target display interface.

[0091] In the embodiment of the present application, by displaying the spreadsheet area and the table operation assistant control on the target display interface, when the user needs to further display the assistant bar area, the assistant bar area can be displayed by performing a trigger operation on the table operation assistant control, so that when the user does not need to further display the assistant bar area, there can be a larger area to display the spreadsheet area, providing a better user experience. And when the user expects to display the assistant bar area, a trigger operation can be performed on the table operation assistant control to display the assistant bar area.

[0092] In an embodiment provided by the present application, in S404, in response to a trigger operation on the table operation assistant control, displaying the assistant bar area includes:

[0093] In response to a click operation on the table operation assistant control, display the assistant bar area, where the assistant bar area includes an input box area and a dialog box area;

[0094] In S204, obtaining the spreadsheet operation description input by the user from the assistant bar area includes:

[0095] Receive the spreadsheet operation description input by the user for the input box area;

[0096] In response to an input confirmation operation for the spreadsheet operation description, display the spreadsheet operation description in the dialog box area and obtain the spreadsheet operation description from the dialog box area.

[0097] Among them, by performing a trigger operation on the table operation assistant control to display the assistant bar area, the assistant bar area includes an input box area and a dialog box area. As Figure 3 shown, the input box area is the 303 area in the figure, and the dialog box area is the 304 area in the figure.

[0098] Meanwhile, when the assistant bar area includes an input box area and a dialog box area, when the user wants to input a spreadsheet operation description, the user can click on the input box area, and then input the spreadsheet operation description in the input box area. After that, when the user performs an input confirmation operation on the input spreadsheet operation description displayed in the input box area, the spreadsheet operation description is displayed in the dialog box area. Here, the input confirmation operation can be a send operation that sends the spreadsheet operation description to the dialog box area. When the spreadsheet operation description is displayed in the dialog box area, the spreadsheet operation description can be obtained from the dialog box area.

[0099] In an embodiment provided by the present application, the display assistant bar area includes: a display assistant bar area that displays assistant operation guidance information in the assistant bar area.

[0100] Among them, as Figure 3 shown, assistant operation guidance information can be displayed in the dialog box area of the assistant bar area. The assistant operation guidance information is used to guide the user to input a standardized spreadsheet operation description to improve the recognition efficiency of the spreadsheet operation description.

[0101] Specifically, the assistant operation guidance information can be "Hello, how can I help you today? You can enter instructions or refer to the instruction set, for example: sort column B from largest to smallest; calculate the sum of data in column B greater than 10; generate a line chart for column F".

[0102] In an embodiment provided by the present application, after calling the target editing script to perform target table operation processing on the spreadsheet area in S206, it further includes:

[0103] Obtain table operation processing status information and display the table operation processing status information in the dialog box area.

[0104] Among them, after calling the target editing script to perform target table operation processing on the spreadsheet area, the table operation processing status information corresponding to the target table operation processing can be obtained. The table operation processing status information is used to visually display the processing status of the target table operation processing. Specifically, the table operation processing status information can include description statements such as "Processing, please wait" and "Operation completed, please check" that describe the processing status of the target table operation processing, so that the user can timely understand the processing progress of the target table operation processing.

[0105] Please refer to Figure 5 , Figure 5 which is a schematic flowchart of a process for displaying target operation prompt information corresponding to a target table operation item provided by an embodiment of the present application. As Figure 5 shown, in an embodiment provided by the present application, the assistant bar area further includes an instruction set area, and the data processing method further includes:

[0106] S502: In response to a first operation on an instruction set control, display an instruction set operation prompt area, where the instruction set operation prompt area includes at least one reference table operation item.

[0107] Among them, when the user wishes to display the instruction set operation prompt area, a first operation can be performed on the instruction set control. The first operation can be an operation of clicking the instruction set control with the cursor or a voice control operation, etc. After performing the first operation on the instruction set control, the instruction set operation prompt area can be displayed. As Figure 3 shown, the instruction set control is the control corresponding to 305 in Figure 3 and the instruction set operation prompt area is the area corresponding to 306 in Figure 3

[0108] In the instruction set operation prompt area, the instruction set operation prompt area includes at least one reference table operation item, and the reference table operation items in the instruction set operation prompt area can include at least one of an exchange position operation item, a mark data operation item, a filter data operation item, a sort operation item, a calculation operation item, and a drawing operation item.

[0109] S504: In response to a second operation on a target table operation item in the reference table operation items, display target operation prompt information corresponding to the target table operation item in the dialog box area.

[0110] Among them, when the click position of the second operation falls into the area corresponding to the exchange position operation item, determine and display exchange position operation prompt information that matches the click position based on the click position of the second operation;

[0111] when the click position of the second operation falls into the area corresponding to the mark data operation item, determine and display mark data operation prompt information that matches the click position based on the click position of the second operation;

[0112] when the click position of the second operation falls into the area corresponding to the filter data operation item, determine and display filter data operation prompt information that matches the click position based on the click position of the second operation;

[0113] when the click position of the second operation falls into the area corresponding to the sort operation item, determine and display sort operation prompt information that matches the click position based on the click position of the second operation;

[0114] when the click position of the second operation falls into the area corresponding to the calculation operation item, determine and display calculation operation prompt information that matches the click position based on the click position of the second operation;

[0115] ​When the click position of the second operation falls within the area corresponding to the drawing operation item, determine and display drawing operation prompt information that matches the click position based on the click position of the second operation.

[0116] It is easy to understand that the target operation prompt information includes at least one of swap position operation prompt information, mark data operation prompt information, filter data operation prompt information, sort operation prompt information, calculation operation prompt information, and drawing operation prompt information. The target operation prompt information is used to prompt the standard spreadsheet operation description corresponding to the target table operation item.

[0117] In addition, in the embodiments provided in this application, a schematic diagram of an interface for performing target table operation processing on a spreadsheet area based on the spreadsheet operation description input by the user is provided.

[0118] Please refer to Figure 6 , Figure 6 which is a schematic flowchart of a swap position operation on a spreadsheet area by a spreadsheet operation description provided in an embodiment of this application.

[0119] The swap position operation can swap row data or column data. The spreadsheet operation description corresponding to the swap position operation can be "swap column B and column D", "swap rows 1 and 2". As Figure 6 shown, for example, when the user inputs: swap column A and column B data, after obtaining the spreadsheet operation description input by the user from the assistant bar area, call the target generative large language model to perform operation parsing processing on the spreadsheet operation description, and JSON format data will be output, including two key-value pairs: "name" and "arguments". Specifically, the output is as follows:

[0120] {"name":"data_exchange","arguments":{"selected_area_type":"column","first_area":"A","second_area":"B"}}. The value of "name" is "data_exchange", indicating that the name of the edit execution script to be executed is "data_exchange", which is used to swap data; "arguments" are the parameters to be passed to the script. "selected_area_type" indicates whether the selected area belongs to a row or a column, and there are 2 optional values, column and row; "first_area" indicates the first area to be swapped, and "second_area" indicates the second area to be swapped.

[0121] After obtaining the output data in JSON format, the target editing script named data_exchange will be called and the corresponding script parameters will be passed in to complete the operation. It should be noted that when the target display interface is an online display interface, the output data in JSON format can be obtained based on the online server, and then the server will call the target editing script named data_exchange. Subsequent other operations can also be executed based on the online server, which will not be elaborated hereinafter. Finally, the execution effect is as Figure 6 shown, and the data positions in columns A and B are exchanged.

[0122] Please refer to Figure 7 , Figure 7 which is a schematic flowchart of the process of filtering data in a spreadsheet operation described in an embodiment of the present application for a spreadsheet area.

[0123] The data filtering operation can filter the data to obtain a data set that meets the conditions. The spreadsheet operation description corresponding to the data filtering operation can be "filter out those greater than 5 and not equal to 3 in column F", "filter those in the second row less than 3000". As Figure 7 shown, for example, the user enters: filter out the data in column C that is less than 5 or greater than 12. After obtaining the spreadsheet operation description entered by the user from the assistant bar area, the target generative large language model is called to perform operation parsing and processing on the spreadsheet operation description, and data in JSON format will be output:

[0124] {"name": "conditional_marker_colors", "arguments": {"selected_area_type": "column", "selected_area": ["C"], "comparison_operators": [["<"], [">"]], "comparable_values": [[5],

[12] ], "color_marking": false}}. The value of "name" is "conditional_marker_colors", indicating that this target editing script is used for conditional filtering. In the "arguments" parameter, "selected_area_type" indicates whether the selected area is a row or a column; "selected_area" indicates the specific selected area, which is an array and can be multiple area data. Here, it is the data in column C; "comparison_operators" indicates the comparison operators, which is a two-dimensional array. When representing an "and" relationship, the operators are in the same array. When representing an "or" relationship, the operators are in different arrays. In this example, it represents an "or" relationship, so "<" and ">" are in different arrays respectively. "comparable_values" indicates the target values for comparison, which is also a two-dimensional array, and its structure must be consistent with "comparison_operators". The "color_marking" parameter indicates whether to mark the filtered data with colors. Here, it is false, indicating that no color marking is required.

[0125] After obtaining the output JSON-formatted data, a template editing script named "conditional_marker_colors" will be called and the corresponding script parameters will be passed in to generate and execute the corresponding target editing script, thus completing the operation. The execution effect is as Figure 7 shown, and the data in column C that is less than 5 or greater than 12 is filtered out.

[0126] Please refer to Figure 8 , Figure 8 which is a schematic flowchart of the process of marking data in a spreadsheet operation described in an embodiment of this application for the spreadsheet area.

[0127] The data marking operation is used to mark the filtered data with colors for subsequent data viewing and processing. The spreadsheet operation description corresponding to the data marking operation can be "mark the cells in column D greater than 3 as red", "mark the cells in row 3 greater than or equal to 5 as red", "mark the cells in column F greater than 9 or less than 3 as blue". As Figure 8As shown, for example, when the user inputs: Mark the cells in column F that are greater than 9 or less than 6 as red. After obtaining the spreadsheet operation description input by the user from the assistant bar area, the target generative large language model is called to perform operation parsing on the spreadsheet operation description, and data in JSON format will be output:

[0128] {"name":"conditional_marker_colors","arguments":{"selected_area_type":"column","selected_area":["F"],"comparison_operators":[["<"],[">"]],"comparable_values":[["6"],["9"]],"color_marking":true,"color_value":"rgb(255,0,0)"}}. Here, the value of name is also conditional_marker_colors, and most of its parameters are the same as those of the data filtering function. The value of the 'color_marking' parameter is true, and there is an additional 'color_value' parameter. The value of the parameter is in RGB format and contains three numerical values. Here, the value is 'rgb(255,0,0)', indicating red.

[0129] After obtaining the output data in JSON format, a template editing script named conditional_marker_colors will be called and the corresponding script parameters will be passed in to generate and execute the corresponding target editing script, thereby completing the operation, so that the cells in column F that are greater than 9 or less than 6 are marked red.

[0130] Please refer to Figure 9 , Figure 9 which is a schematic flowchart of a process for sorting a spreadsheet area according to a spreadsheet operation description provided in an embodiment of the present application.

[0131] The sorting operation is used to sort data in ascending or descending order. The spreadsheet operation descriptions corresponding to the sorting operation can be "Sort column B from largest to smallest", "Sort column E from smallest to largest", as Figure 9 shown. For example, when the user inputs: Sort column B from largest to smallest. After obtaining the spreadsheet operation description input by the user from the assistant bar area, the target generative large language model is called to perform operation parsing on the spreadsheet operation description, and data in JSON format will be output:

[0132] {"name": "sort", "arguments": {"selected_area": "B", "method": "descending"}}

[0133] The value of 'name' is'sort', indicating a sorting script. In the 'arguments' parameter,'selected_area' represents the selected operation area, which is column B here.'method' indicates ascending or descending order, with 2 values: 'ascending' and 'descending'. Here, 'descending' means sorting from largest to smallest.

[0134] After obtaining the output JSON-formatted data, a template editing script named sort will be called and the corresponding script parameters will be passed in to generate and execute the corresponding target editing script, thus completing the operation. The execution effect is as Figure 9 shown, sorted from largest to smallest according to the values in column B.

[0135] Please refer to Figure 10 , Figure 10 which is a schematic flowchart of the process for calculating and operating on an electronic spreadsheet area provided by an embodiment of this application.

[0136] The calculation operation is used to generate formulas and perform calculation operations to achieve the functions of automatic data calculation and statistics. The electronic spreadsheet operation description corresponding to the calculation operation can be "calculate the sum of B2 to B9", "calculate the maximum value of D5 to D14", "count the number of values equal to 20 in E4 to E9".

[0137] As Figure 10 shown, for example, when the user inputs: calculate the average value of C2 to C5, after obtaining the electronic spreadsheet operation description input by the user from the assistant bar area, the target generative large language model is called to perform operation parsing and processing on the electronic spreadsheet operation description, and JSON-formatted data will be output:

[0138] {"name": "generate_formula", "arguments": {"formula": "=AVERAGE(C2:C5)"}}, the value of name is 'generate_formula', indicating that a formula calculation script is used. There is only one parameter 'formula' in 'arguments', and its value is an Excel formula starting with '='. Here, we are calculating the average value, so the Excel function is AVERAGE. After obtaining the output JSON-formatted data, a template editing script named generate_formula will be called and the corresponding script parameters will be passed in to generate and execute the corresponding target editing script to complete the operation. The execution effect is as Figure 10 shown, the average value of C2 to C5 is calculated and the value is saved to the cell K18 at the current mouse position. In addition, the calculation formula is also displayed in the assistant bar area on the right.

[0139] Please refer to Figure 11 , Figure 11 which is a schematic flow chart of an operation for drawing on a spreadsheet area provided by an embodiment of the present application.

[0140] The drawing operation is used to generate various types of charts, including bar charts, line charts, pie charts, 3D bar charts, area charts, and doughnut charts, for the visual display and analysis of data. The spreadsheet operation description corresponding to the drawing operation can be "draw a bar chart from area A2 to D5" or "draw a scatter chart from area B3 to J10".

[0141] As Figure 11 shown, for example, the user enters: draw a line chart from area A1 to D5. After obtaining the spreadsheet operation description entered by the user from the assistant bar area, the target generative large language model is called to perform operation parsing and processing on the spreadsheet operation description, and JSON-formatted data will be output:

[0142] {"name": "plot_chart", "arguments": {"start_point": "A1", "end_point": "D5", "chart_type": "line"}}, the value of name is 'plot_chart', indicating that a drawing script is used. The'start_point' and 'end_point' parameters respectively represent the starting and ending positions of the data area. Here, the data area is from A1 to D5. The 'chart_type' parameter represents the type of chart to be drawn. Here, the value is line, indicating a line chart.

[0143] After obtaining the output JSON-formatted data, a template editing script named plot_chart will be called and the corresponding script parameters will be passed in to generate and execute the corresponding target editing script, thus completing the operation. The execution effect is as Figure 11 shown. According to the user's instruction, the area from A1 to D5 is selected to draw a line chart. The first row of apples, pears, and peaches are marked on the abscissa, and the first column of level 1, level 2, level 3, and total are marked on the legend.

[0144] Please refer to Figure 12 , Figure 12 which is a schematic flowchart of a process for obtaining target table operation information for a user provided in an embodiment of the present application. In an embodiment provided by the present application, in S204, a target generative large language model is called to perform operation parsing processing on the spreadsheet operation description to obtain target table operation information for the user, including:

[0145] S1202: Construct an operation parsing prompt word based on the spreadsheet operation description and obtain editing operation configuration information.

[0146] Among them, by constructing an operation parsing prompt word for the spreadsheet operation description, the model can more accurately understand the meaning expression of the spreadsheet operation description. The operation parsing prompt word includes a prompt word and a parsing statement corresponding to the spreadsheet operation description. At the same time, the editing operation configuration information can include various pre-set table operation information, such as: swap position operation information, mark data operation information, filter data operation information, sorting operation information, calculation operation information, and drawing operation information, etc.

[0147] S1204: Input the operation parsing prompt word and the editing operation configuration information into the target generative large language model for operation parsing processing, and output the target table operation information for the user.

[0148] Among them, after obtaining the operation parsing prompt word and the editing operation configuration information, the operation parsing prompt word and the editing operation configuration information are input into the target generative large language model, and the target generative large language model performs parsing processing on the operation parsing prompt word and the editing operation configuration information, and outputs the target table operation information for the user.

[0149] Exemplarily, please refer to Figure 13 , Figure 13 which is a schematic flowchart of a process for outputting target table operation information for a user provided in an embodiment of the present application. In S1204, the operation parsing prompt word and the editing operation configuration information are input into the target generative large language model for operation parsing processing, and output the target table operation information for the user, including:

[0150] S1302: Input the operation parsing prompt and the editing operation configuration information into the target generative large language model. Based on the target generative large language model, perform information extraction processing on the operation parsing prompt to obtain user intention information.

[0151] Among them, the target generative large language model can perform information extraction processing on the operation parsing prompt, and the target generative large language model can also be Chat GPT (Chat Generative Pre-trained Transformer). The target generative large language model can parse the user intention based on the operation parsing prompt, so as to obtain user intention information.

[0152] S1304: Determine the target table operation from the editing operation configuration information based on the user intention information, and determine the editing execution script name and script parameters of the target table operation.

[0153] After obtaining the user intention information, the target table operation information can be determined from the editing operation configuration information, that is, the target table operation that best fits the user intention is selected from the editing operation configuration information through the user intention information. Then, based on the target table operation, the corresponding editing execution script name and script parameters are obtained.

[0154] S1306: Output the target table operation information including the script name and script parameters based on the target generative large language model.

[0155] Finally, output the target table operation information including the script name and script parameters through the target generative large language model.

[0156] In an embodiment provided by the present application, determining the target editing script based on the target table operation information in S206 includes:

[0157] Obtain the editing execution script name and script parameters from the target table operation information for the user in the target table operation information;

[0158] Determine the target editing script based on the editing execution script name and script parameters.

[0159] Among them, determining the target editing script based on the editing execution script name and script parameters includes: calling the template editing script corresponding to the editing execution script name, and inputting the script parameters into the template editing script to obtain the target editing script.

[0160] The embodiment of the present application also provides a computer storage medium, which can store multiple instructions, and the instructions are suitable for being loaded and executed by a processor to perform the steps of the method in any one of the above embodiments.

[0161] Please refer to Figure 14 ,Figure 14 Schematic diagram of a data processing device based on a generative large language model provided by an embodiment of the present application.

[0162] The data processing device 1400 includes:

[0163] A display module 1410, adapted to display a spreadsheet area and an assistant bar area on a target display interface;

[0164] An invocation module 1420, adapted to obtain a spreadsheet operation description input by a user from the assistant bar area, and invoke a target generative large language model to perform operation parsing processing on the spreadsheet operation description to obtain target table operation information for the user;

[0165] A processing module 1430, adapted to determine a target editing script based on the target table operation information, and invoke the target editing script to perform target table operation processing on the spreadsheet area.

[0166] In some embodiments, the display module 1410 includes:

[0167] A first display unit, adapted to display a spreadsheet area and a table operation assistant control on a target display interface;

[0168] A second display unit, adapted to display an assistant bar area in response to a trigger operation on the table operation assistant control.

[0169] In some embodiments, the second display unit is further adapted to display an assistant bar area in response to a click operation on the table operation assistant control, and the assistant bar area includes an input box area and a dialog box area;

[0170] The invocation module 1420 includes:

[0171] A receiving unit, adapted to receive a spreadsheet operation description input by a user in the input box area;

[0172] A response unit, adapted to display the spreadsheet operation description in the dialog box area and obtain the spreadsheet operation description from the dialog box area in response to an input confirmation operation on the spreadsheet operation description.

[0173] In some embodiments, the data processing device 1400 further includes:

[0174] An acquisition module, adapted to acquire table operation processing status information and display the table operation processing status information in the dialog box area.

[0175] In some embodiments, the assistant bar area further includes an instruction set area, and the data processing device 1400 further includes:

[0176] The first response module is adapted to display an instruction set operation prompt area in response to a first operation on an instruction set control. The instruction set operation prompt area includes at least one reference table operation item;

[0177] The second response module is adapted to display target operation prompt information corresponding to a target table operation item in a dialog box area in response to a second operation on the target table operation item in the reference table operation items.

[0178] In some embodiments, the second display unit is further adapted to display an assistant bar area and display assistant operation guidance information in the assistant bar area.

[0179] In some embodiments, the calling module 1420 includes:

[0180] The editing operation configuration information acquisition unit is adapted to construct an operation parsing prompt word based on a spreadsheet operation description and acquire editing operation configuration information;

[0181] The output unit is adapted to input the operation parsing prompt word and the editing operation configuration information into a target generative large language model for operation parsing processing and output target table operation information for the user.

[0182] In some embodiments, the output unit includes:

[0183] The user intention information acquisition subunit is adapted to input the operation parsing prompt word and the editing operation configuration information into a target generative large language model, perform information extraction processing on the operation parsing prompt word based on the target generative large language model, and obtain user intention information;

[0184] The determination subunit is adapted to determine a target table operation from the editing operation configuration information based on the user intention information, and determine the editing execution script name and script parameters of the target table operation;

[0185] The output subunit is adapted to output target table operation information including the editing execution script name and script parameters based on the target generative large language model.

[0186] In some embodiments, the processing module 1430 includes:

[0187] The script acquisition unit is adapted to obtain the editing execution script name and script parameters from the target table operation information for the user in the target table operation information;

[0188] The target editing script determination unit is adapted to determine a target editing script based on the editing execution script name and script parameters.

[0189] In some embodiments, the target editing script determination unit is further adapted to call the template editing script corresponding to the editing execution script name, input the script parameters into the template editing script, and obtain the target editing script.

[0190] Please refer to Figure 15 , Figure 15 which is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As Figure 15 shown, the electronic device 1500 may include: at least one processor 1501, at least one network interface 1504, a user interface 1503, a memory 1505, and at least one communication bus 1502.

[0191] Among them, the communication bus 1502 is used to realize the connection and communication between these components.

[0192] Among them, the user interface 1503 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 1503 may further include a standard wired interface and a wireless interface.

[0193] Among them, the network interface 1504 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0194] Among them, the processor 1501 may include one or more processing cores. The processor 1501 connects various parts within the entire electronic device 1500 through various interfaces and lines, and by running or executing instructions, programs, code sets or instruction sets stored in the memory 1505, and calling data stored in the memory 1505, it executes various functions of the electronic device 1500 and processes data. Optionally, the processor 1501 may be implemented in at least one of the following hardware forms: digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor 1501 may integrate one or several combinations of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communication. It can be understood that the above modem may not be integrated into the processor 1501 and may be implemented separately by a single chip.

[0195] Among them, the memory 1505 may include a Random Access Memory (RAM), or may include a Read-Only Memory (ROM). Optionally, the memory 1505 includes a non-transitory computer-readable storage medium. The memory 1505 can be used to store instructions, programs, code, code sets or instruction sets. The memory 1505 may include a program storage area and a data storage area. Among them, the program storage area can store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area can store the data involved in the above-mentioned method embodiments. Optionally, the memory 1505 may also be at least one storage device located far from the aforementioned processor 1501. As Figure 15 shown, the memory 1505, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a data processing program.

[0196] In Figure 15 the electronic device 1500 shown, the user interface 1503 is mainly used to provide an input interface for the user to obtain the data input by the user; and the processor 1501 can be used to call the data processing program stored in the memory 1505 based on the generative large language model and specifically perform the following operations:

[0197] Display a spreadsheet area and an assistant bar area on the target display interface;

[0198] Obtain the spreadsheet operation description input by the user from the assistant bar area, call the target generative large language model to perform operation parsing processing on the spreadsheet operation description, and obtain the target table operation information for the user;

[0199] Determine a target editing script based on the target table operation information, and call the target editing script to perform target table operation processing on the spreadsheet area.

[0200] Optionally, when the processor 1501 executes to display the spreadsheet area and the assistant bar area on the target display interface, it specifically performs the following steps:

[0201] Display a spreadsheet area and a table operation assistant control on the target display interface;

[0202] In response to a trigger operation on the table operation assistant control, display the assistant bar area.

[0203] Optionally, when the processor 1501 executes to display the assistant bar area in response to a trigger operation for the table operation assistant control, the following steps are specifically executed:

[0204] In response to a click operation on the table operation assistant control, display the assistant bar area, where the assistant bar area includes an input box area and a dialog box area;

[0205] When the processor 1501 executes to obtain the spreadsheet operation description input by the user from the assistant bar area, the following steps are specifically executed:

[0206] Receive the spreadsheet operation description input by the user for the input box area;

[0207] In response to an input confirmation operation for the spreadsheet operation description, display the spreadsheet operation description in the dialog box area and obtain the spreadsheet operation description from the dialog box area.

[0208] Optionally, after the processor 1501 executes to call the target editing script to perform target table operation processing on the spreadsheet area, the following steps are also specifically executed:

[0209] Obtain the table operation processing status information and display the table operation processing status information in the dialog box area.

[0210] Optionally, the assistant bar area further includes an instruction set area, and the processor 1501 also executes the following steps:

[0211] In response to a first operation on the instruction set control, display the instruction set operation prompt area, where the instruction set operation prompt area includes at least one reference table operation item;

[0212] In response to a second operation on the target table operation item in the reference table operation items, display the target operation prompt information corresponding to the target table operation item in the dialog box area.

[0213] Optionally, when the processor 1501 executes to display the assistant bar area, the following steps are specifically executed:

[0214] Display the assistant bar area and display the assistant operation guidance information in the assistant bar area.

[0215] Optionally, when the processor 1501 executes to call the target generative large language model to perform operation parsing processing on the spreadsheet operation description to obtain the target table operation information for the user, the following steps are specifically executed:

[0216] Build an operation parsing prompt word based on the spreadsheet operation description and obtain the editing operation configuration information;

[0217] Input the operation parsing prompt and editing operation configuration information into the target generative large language model for operation parsing processing, and output the target table operation information for the user.

[0218] Optionally, when the processor 1501 executes the operation of inputting the operation parsing prompt and editing operation configuration information into the target generative large language model for operation parsing processing and outputting the target table operation information for the user, the following steps are specifically executed:

[0219] Input the operation parsing prompt and editing operation configuration information into the target generative large language model, and perform information extraction processing on the operation parsing prompt based on the target generative large language model to obtain the user intention information;

[0220] Determine the target table operation from the editing operation configuration information based on the user intention information, and determine the editing execution script name and script parameters of the target table operation;

[0221] Output the target table operation information including the editing execution script name and script parameters based on the target generative large language model.

[0222] Optionally, when the processor 1501 executes the operation of determining the target editing script based on the target table operation information, the following steps are specifically executed:

[0223] Obtain the editing execution script name and script parameters from the target table operation information obtained from the target table operation information for the user;

[0224] Determine the target editing script based on the editing execution script name and script parameters.

[0225] Optionally, when the processor 1501 executes the operation of determining the target editing script based on the editing execution script name and script parameters, the following steps are specifically executed:

[0226] Call the template editing script corresponding to the editing execution script name, and input the script parameters into the template editing script to obtain the target editing script.

[0227] In several embodiments provided in the embodiments of the present application, it should be understood that the disclosed device and method can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces. The indirect coupling or communication connection of the device or module may be in an electrical, mechanical or other form.

[0228] The module described as a separation component may or may not be physically separated. The component shown as a module may or may not be a physical module, that is, it may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0229] In addition, in each embodiment of this application, each functional module can be integrated into a processing module, or each module can exist physically alone, or two or more modules can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module.

[0230] If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this embodiment of the application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of this application. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs and other various media that can store program codes.

[0231] It should be noted that for the foregoing method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the embodiments of this application are not limited by the described action sequence, because according to the embodiments of this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the embodiments of this application.

[0232] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0233] The above is the description of the data processing method and its device based on the generative large language model provided by the embodiments of this application. For those skilled in the art, according to the idea of the embodiments of this application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the embodiments of this application.

Claims

1. A data processing method based on a generative large language model, wherein, the method includes: displaying a spreadsheet area and an assistant bar area on a target display interface; obtaining the spreadsheet operation description input by the user from the assistant bar area, and invoking a target generative large language model to perform operation parsing processing on the spreadsheet operation description to obtain target table operation information for the user; determining a target editing script based on the target table operation information, and invoking the target editing script to perform target table operation processing on the spreadsheet area.

2. The method according to claim 1, wherein, the displaying the spreadsheet area and the assistant bar area on the target display interface includes: displaying a spreadsheet area and a table operation assistant control on the target display interface; responding to a trigger operation on the table operation assistant control to display the assistant bar area.

3. The method according to claim 2, wherein, the responding to a trigger operation on the table operation assistant control to display the assistant bar area includes: responding to a click operation on the table operation assistant control to display the assistant bar area, and the assistant bar area includes an input box area and a dialog box area; the obtaining the spreadsheet operation description input by the user from the assistant bar area includes: receiving the spreadsheet operation description input by the user for the input box area; responding to an input confirmation operation on the spreadsheet operation description, displaying the spreadsheet operation description in the dialog box area, and obtaining the spreadsheet operation description from the dialog box area.

4. The method according to claim 3, wherein, after invoking the target editing script to perform target table operation processing on the spreadsheet area, it further includes: obtaining table operation processing status information and displaying the table operation processing status information in the dialog box area.

5. The method according to claim 3, wherein, the assistant bar area further includes an instruction set area, and the method further includes: responding to a first operation on the instruction set control to display an instruction set operation prompt area, and the instruction set operation prompt area includes at least one reference table operation item; responding to a second operation on a target table operation item in the reference table operation items to display target operation prompt information corresponding to the target table operation item in the dialog box area.

6. The method according to claim 2, wherein, the displaying the assistant bar area includes: displaying the assistant bar area and displaying assistant operation guidance information in the assistant bar area.

7. The method according to claim 1, wherein, the invoking a target generative large language model to perform operation parsing processing on the spreadsheet operation description to obtain target table operation information for the user includes: constructing an operation parsing prompt word based on the spreadsheet operation description and obtaining editing operation configuration information; inputting the operation parsing prompt word and the editing operation configuration information into the target generative large language model for operation parsing processing, and outputting target table operation information for the user.

8. A data processing device based on a target generative large language model, wherein, The device includes: A display module, adapted to display a spreadsheet area and an assistant bar area on a target display interface; An invocation module, adapted to obtain the spreadsheet operation description input by the user from the assistant bar area, and invoke a target generative large language model to perform operation parsing processing on the spreadsheet operation description to obtain target table operation information for the user; A processing module, adapted to determine a target editing script based on the target table operation information, and invoke the target editing script to perform target table operation processing on the spreadsheet area.

9. An electronic device, wherein, the electronic device includes: A processor; and A memory arranged to store computer-executable instructions, which when executed cause the processor to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, wherein, the computer-readable storage medium stores one or more programs, which when executed by a processor, implement the method according to any one of claims 1 to 7.

Images