Table creation method, device, and storage medium

Abstract

Embodiments of the present disclosure provide a method, device, and storage medium for creating a table. A first user input instruction is received through an interaction component in a table interface, where the first user input instruction includes table creation requirement information. According to the first user input instruction, a language model is called to create a target table that meets the table creation requirement information. The target table is presented in the table interface. In the embodiments of the present disclosure, users only need to input table creation requirement information, and then can automatically create a table that meets user requirements with the help of a language model, achieving efficient and flexible creation of the table, reducing labor costs, and providing convenience to users.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer and network communication technologies, and in particular, to a method, device, and storage medium for creating a table. Background Art

[0002] With the rapid development of technology and the increasing manifestation of data value, tables have become a common form of data presentation and data recording in all walks of life.

[0003] In the prior art, when creating a table, the creator usually designs the table according to his own needs, including the table theme, field names, formats, etc. However, the process of designing the table is inefficient. Especially for some scenarios with a large amount of information, designing a table requires a lot of time and effort, wasting human resources. Summary of the Invention

[0004] Embodiments of the present disclosure provide a method, device, and storage medium for creating a table to achieve efficient and flexible creation of the table, reduce labor costs, and provide convenience to users.

[0005] In a first aspect, embodiments of the present disclosure provide a method for creating a table, including:

[0006] Receiving a first user input instruction through an interaction component in a table interface, where the first user input instruction includes table creation requirement information;

[0007] According to the first user input instruction, calling a language model to create a target table that meets the table creation requirement information;

[0008] Presenting the target table in the table interface.

[0009] In a second aspect, embodiments of the present disclosure provide a table creation device, including:

[0010] An input unit for receiving a first user input instruction through an interaction component in a table interface, where the first user input instruction includes table creation requirement information;

[0011] A processing unit for calling a language model to create a target table that meets the table creation requirement information according to the first user input instruction;

[0012] A display unit for presenting the target table in the table interface.

[0013] In a third aspect, embodiments of the present disclosure provide an electronic device, including: at least one processor and a memory;

[0014] The memory stores computer execution instructions;

[0015] The at least one processor executes the computer-executable instructions stored in the memory, such that the at least one processor executes the table creation method as described in the first aspect above and various possible designs of the first aspect.

[0016] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the table creation method as described in the first aspect above and various possible designs of the first aspect.

[0017] In a fifth aspect, an embodiment of the present disclosure provides a computer program product including computer-executable instructions, which, when executed by a processor, implement the table creation method as described in the first aspect above and various possible designs of the first aspect.

[0018] The table creation method, device, and storage medium provided by the embodiments of the present disclosure receive a first user input instruction through an interaction component in a table interface, where the first user input instruction includes table creation requirement information; call a language model to create a target table that meets the table creation requirement information according to the first user input instruction; and present the target table in the table interface. In the embodiments of the present disclosure, the user only needs to input table creation requirement information, and then can automatically create a table that meets the user's needs with the help of the language model, realizing the efficient and flexible creation of the table, reducing the labor cost, and providing convenience for the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the following briefly introduces the drawings required to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0020] Figure 1 It is an example diagram of a table creation in the prior art;

[0021] Figure 2 It is a schematic flowchart of the table creation method provided by an embodiment of the present disclosure;

[0022] Figure 3 It is a schematic diagram of a table interface provided by an embodiment of the present disclosure;

[0023] Figure 4 It is a schematic diagram of a table interface provided by another embodiment of the present disclosure;

[0024] Figure 5 It is a schematic diagram of a table interface provided by another embodiment of the present disclosure;

[0025] Figure 6 Schematic diagram of a table interface provided by another embodiment of the present disclosure;

[0026] Figure 7 Schematic diagram of a table interface provided by another embodiment of the present disclosure;

[0027] Figure 8 Schematic diagram of a table interface provided by another embodiment of the present disclosure;

[0028] Figure 9 Block diagram of the structure of a table creation device provided by an embodiment of the present disclosure;

[0029] Figure 10 Schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present disclosure. Detailed implementation manners

[0030] To make the objectives, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Apparently, the described embodiments are some but not all of the embodiments of the present disclosure. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present disclosure without creative efforts shall fall within the protection scope of the present disclosure.

[0031] In the prior art when creating a table, usually the creator designs the table according to his own needs, including the table theme, field names, formats, etc. However, the process of designing a table is inefficient. Especially for some scenarios with a large amount of information, designing a table requires a lot of time and effort, wasting labor costs.

[0032] To solve the above technical problems, the present disclosure hopes to achieve automatic creation of a table. The user only needs to input the table creation requirements, and then a table that meets the table creation requirements can be automatically created. To achieve the above objective, considering that the table creation requirements input by the user are usually based on natural language, and the language model has the ability of natural language understanding and can perform specific processing tasks after training. Especially the large prediction model (Large Language Model, LLM) has very strong natural language understanding ability and shows a level close to or even exceeding that of humans in many natural language tasks. Therefore, in the present disclosure, a language model is used to automatically create a table that meets the user's needs, thus achieving efficient and flexible creation of the table, eliminating the need for manual table design, reducing labor costs, and providing convenience to the user.

[0033] The table creation method provided by the present disclosure may be executed by an electronic device such as a terminal device or a server. A language model is locally deployed on the electronic device such as the terminal device or the server. A first user input instruction is received through an interaction component in the table interface, where the first user input instruction includes table creation requirement information; according to the first user input instruction, the language model is called to create a target table that meets the table creation requirement information; and the target table is displayed in the table interface.

[0034] Optionally, the language model may not be deployed on the electronic device such as the terminal device or the server, and the language model is deployed on the server side. As Figure 1 shown, the electronic device such as the terminal device or the server can receive the first user input instruction through the interaction component in the table interface, where the first user input instruction includes table creation requirement information, and then send the first user input instruction to the server side. The server side calls the language model to obtain target table data that meets the table creation requirement information according to the first user input instruction, and sends the target table data to the electronic device; the electronic device creates a target table according to the target table data and displays it in the table interface.

[0035] It should be noted that the user information and data involved in this application are all information and data authorized by the user or fully authorized by all parties. The collection, use, and processing of relevant data need to comply with the relevant laws, regulations, and standards of relevant countries and regions, and corresponding operation entrances are provided for users to choose to authorize or refuse.

[0036] The table creation method of the present disclosure will be introduced in detail below with reference to specific embodiments.

[0037] Refer to Figure 2 , Figure 2 which is a schematic flowchart of the table creation method provided by an embodiment of the present disclosure. The method of this embodiment can be applied to an electronic device such as a terminal device or a server. The table creation method includes:

[0038] S201. Receive a first user input instruction through an interaction component in the table interface, where the first user input instruction includes table creation requirement information.

[0039] In this embodiment, an interaction component may be configured in the table interface. The interaction component is an interface for calling the function of automatically creating a table by the language model. The user can input an input instruction including various requirement information in the interaction component. When the user needs to create a table, the first user input instruction can be input through the interaction component. The first user input instruction includes table creation requirement information, and the table creation requirement information may include but is not limited to the theme information, format information, required fields, required data, etc. of the table. For example, the table creation requirement information may be to create a table with the theme of "recruitment management system".

[0040] In some embodiments of the present disclosure, the table may be a database table, an online table, a spreadsheet, or the like.

[0041] Optionally, an input box control may be provided in the interaction component, such as Figure 3 As shown, in the table interface 300, an input box control 311 may be provided in the interaction component 310. The user can input instruction content based on natural language in the input box control 311. For example, the user can input "Help me build a recruitment management system" in the input box control 311 and click to confirm. The electronic device can receive the instruction content based on natural language input in the input box control 311 and determine this instruction content as the above-mentioned first user input instruction. The ways of inputting instruction content in the input box control include but are not limited to keyboard input, voice input, handwriting input, etc.

[0042] Optionally, a preset shortcut instruction control may also be provided in the interaction component, such as Figure 3 As shown, a preset shortcut instruction control 312 is provided in the interaction component 300, including shortcut instruction controls such as "Create a business system" and "Create a questionnaire". The user can directly select and trigger the required preset shortcut instruction control. The electronic device responds to the triggering operation of the user on the preset shortcut instruction control and directly uses the preset shortcut instruction corresponding to this preset shortcut instruction control as the first user input instruction. The triggering operation may include but is not limited to triggering by an input device such as a mouse (such as clicking), voice triggering, gesture triggering, etc.

[0043] Optionally, some preset shortcut instruction controls also require the user to provide some parameters or information. When the user triggers these preset shortcut instruction controls, the electronic device responds to the triggering operation on these preset shortcut instruction controls and displays preset prompt language materials in the input box control in the interaction component. The preset prompt language materials are used to prompt the user for the content that needs to be input. The user can continue to input instruction content based on natural language in the input box control. After the user clicks to confirm, the electronic device can determine the preset prompt language materials and the instruction content input by the user as the first user input instruction. For example, a shortcut instruction control for "Create a data table" is provided in the interaction component. After the user triggers this shortcut instruction control for "Create a data table", preset prompt language materials "Create a data table, theme is:" can be displayed in the input box control in the interaction component. The user can continue to input the theme "Theme A" of the required data table in the data box. After the user clicks to confirm, all the content in the input box control, including the preset prompt language materials and the instruction content input by the user "Create a data table, theme is: Theme A", can be determined as the first user input instruction.

[0044] Optionally, during the process of the user entering instruction content based on natural language in the input box control, the electronic device can real-time search for matching preset shortcut instruction controls according to the current instruction content in the input box control, and display the matching preset shortcut instruction controls in the interaction component for the user to select. The user can stop entering in the input box control and directly select and trigger the required preset shortcut instruction control. In response to the user's trigger operation on the preset shortcut instruction control, the electronic device directly uses the preset shortcut instruction corresponding to the preset shortcut instruction control as the first user input instruction.

[0045] It should be noted that the interaction control can provide one or more of the above input methods without conflict to facilitate user input. In addition, the above input methods of the interaction control are not limited to obtaining the first user input instruction when creating a table, and are also applicable in other scenarios, and can collect any user input instruction, such as the second user input instruction, the third user input instruction, etc. in the following embodiments.

[0046] S202. According to the first user input instruction, call a language model to create a target table that meets the table creation requirement information.

[0047] In this embodiment, after obtaining the first user input instruction through the interaction component, a language model can be called to automatically create a target table that meets the table creation requirement information in the first user input instruction through the language model.

[0048] Among them, the language model can be a large language model (LLM). The large language model is a new type of language model based on deep learning in the natural language field. Its characteristics are that the parameter scale is very large (usually more than 1 billion), and it is trained using a very large natural language corpus. Thanks to these characteristics, the large language model has very strong natural language understanding ability and shows a level close to or even exceeding that of humans in many natural language tasks. In this embodiment, through training, the large language model can be enabled to automatically create a table based on the table creation requirement information.

[0049] Further, when calling a language model to create a target table that meets the table creation requirement information according to the first user input instruction in S202, it may specifically include:

[0050] S2021. According to the first user input instruction, generate model input data using a preset template;

[0051] S2022. Process the model input data based on the language model to obtain target table data that meets the table creation requirement information;

[0052] S2023: parse the target table data, and create the target table in the table interface according to the parsing result.

[0053] In this embodiment, since the first user input instruction may be a natural language or a preset shortcut instruction, in order to facilitate the understanding of the language model, a preset template may be used to process the first user input instruction to generate model input data. For example, for a large language model, a prompt word (prompt) template may be used to generate model input data according to the first user input instruction, wherein the prompt word is a structured text used as the input of the large language model, and the prompt word template specifies a fixed format of the prompt word, which contains some variable parts of replaceable content, and the variable parts in the prompt word template may be extracted from the first user input instruction and replaced to finally obtain the model input data. Of course, other feasible language models may also be used in this embodiment, which are not limited here.

[0054] Furthermore, the model input data is input into the language model, and the model input data is semantically understood with the help of the powerful natural language understanding ability of the language model, and the target table data that meets the table creation requirement information is obtained, where the target table data includes one or more of the following:

[0055] The target table includes the number of tables and the subject of each table, the field name in the table, the alternatives for at least one field, the sample data in the table, and the real data in the table.

[0056] For example, for a table creation requirement where the information is to create a table with the theme of "recruitment management system", the language model can determine to generate multiple tables centered around the theme of "recruitment management system". Each table can have its own theme respectively. For example, the first table is "Job List", the second table is "Candidate Resume Table", and the third table is "Interview Record Table". The language model can also determine the field names in each table. For example, in the "Job List" of the first table, it can include field names such as job ID, job name, job type, salary range, job description, etc. The "Candidate Resume Table" of the second table can include field names such as resume ID, name, job applied for, etc. The "Interview Record Table" of the third table can include field names such as record ID, candidate resume ID, interview time, interviewer, interview result, etc. In addition, for a certain field, the language model can also give alternatives. For example, the alternatives for the job applied for field include sales position, R & D position, management position, etc., and the alternatives for the interview result field include passed, not passed, pending, etc. In addition, the language model can also give several example data (several example records, and one record is a row of data in the table) for each table. For example, it can give several virtual data. Of course, for some table creation requirements, the language model can also give some real data. For example, if the table creation requirement is to create a comparison table of provinces and provincial capitals, the language model can give the real data of provinces and provincial capitals. Another example is that if the table creation requirement is to recommend 5 business management books, the language model can give the real data of 5 business management books based on the corpus.

[0057] The language model can output the target table data in a predetermined format. Further, it can parse the target table data and create the target table in the table interface according to the parsing result. In the specific creation process, a streaming process can be adopted. If there are multiple tables, they can be created one by one, that is, after creating one table, create the next table. In the process of creating any table, generate each field in the table one by one, and then fill in the example data or real data row by row in the table according to the fields to obtain the target table.

[0058] S203. Present the target table in the table interface.

[0059] In this embodiment, the final target table can be directly displayed in the table interface. For example Figure 4 as shown, if there are multiple tables, the name (or theme) of each table can be shown in a list manner, and one of the tables is displayed in the table interface. The user can also select the table to be displayed from the list.

[0060] Of course, the above streaming process can also be shown in the table interface, and the final target table is shown after the streaming process ends.

[0061] The table creation method provided in this embodiment receives a first user input instruction through an interaction component in a table interface, where the first user input instruction includes table creation requirement information; according to the first user input instruction, a language model is called to create a target table that meets the table creation requirement information; and the target table is presented in the table interface. In this embodiment, the user only needs to input the table creation requirement information, and then can use the language model to automatically create a table that meets the user's needs, realizing the efficient and flexible creation of the table, reducing the labor cost, and providing convenience for the user.

[0062] Based on any of the above embodiments, after presenting the target table in the table interface, it may further include:

[0063] Receiving a second user input instruction through the interaction component, where the second user input instruction includes field modification requirement information for the target table, and the field modification requirement information includes requirement information for modifying existing fields, requirement information for deleting existing fields, or requirement information for adding new fields;

[0064] According to the second user input instruction, the language model is called to modify the fields of the target table based on the field modification requirement information.

[0065] In this embodiment, after presenting the target table in the table interface, if the user needs to modify the fields in the target table, such as modifying existing fields, deleting existing fields, adding new fields, etc., the user can input a second user input instruction in the interaction component, where the second user input instruction includes any of the above field modification requirement information.

[0066] Among them, the method of receiving the second user input instruction through the interaction component is similar to the method of receiving the first user input instruction in the above embodiment. It can be that the user directly inputs the instruction content based on natural language in the input box control of the interaction component as the second user input instruction; it can also be that preset shortcut instruction controls related to field modification are set in the interaction component for the user to select, such as a preset shortcut instruction control for recommending a certain new field; it can also be that after triggering the preset shortcut instruction control related to field modification, preset prompt corpus is displayed in the input box control, and the user can continue to input instruction content in the input box control according to the preset prompt corpus, and use the preset prompt corpus and the instruction content input by the user as the second user input instruction, etc. The specific process will not be elaborated here. Among them, as Figure 5 described, the interaction component 310 can be expanded by triggering the thumbnail identifier 321 of the interaction component in the toolbar 320, or the interaction component can be triggered to be displayed in other ways.

[0067] Further, according to the second user input instruction, call the language model to modify the fields of the target table to meet the field modification requirement information. Specifically, similar to the above embodiments, according to the second user input instruction, use a preset model to generate model input data, process the model input data based on the language model, and update the target table data according to the field modification requirement information. For example, modify the existing fields of the target table, delete the existing fields, add new fields. Correspondingly, modify the example data or real data corresponding to the existing fields, delete the example data or real data corresponding to the existing fields, add the example data or real data corresponding to the new fields, and update the target table in the table interface based on the updated target table data.

[0068] Based on any of the above embodiments, after presenting the target table in the table interface, it further includes:

[0069] Receive a third user input instruction through the interaction component, where the third user input instruction includes data addition requirement information for the target table, and the data addition requirement information includes natural language-based data information to be added;

[0070] According to the third user input instruction, call the language model to add the data information to be added to a row of the target table according to the fields.

[0071] In this embodiment, when the user uses the target table and needs to add a row of data, it can also be achieved through the interaction component. The user can input a third user input instruction through the interaction component, which includes data addition requirement information for the target table, used to represent the data addition requirement for the target table and specifically what data to add. The data addition requirement information includes natural language-based data information to be added.

[0072] The way of receiving the third user input instruction through the interaction component is similar to the way of receiving the first user input instruction in the above embodiments. It can be that the user directly inputs natural language-based data information to be added as the third user input instruction in the input box control of the interaction component; it can also be that preset shortcut instruction controls related to adding data are set in the interaction component for the user to select. After the user triggers the preset shortcut instruction control related to adding data, a preset prompt corpus is displayed in the input box control, such as "Enter a row of records and disassemble them into corresponding fields". The user can continue to input natural language-based data information to be added in the input box control according to the preset prompt corpus, and use the preset prompt corpus and the natural language-based data information input by the user as the third user input instruction, etc. The specific process will not be elaborated here.

[0073] Further, according to the third user input instruction, the language model can be called to identify and split the data to be added according to the fields in the target table, and the data corresponding to each field obtained is added to the cells corresponding to each field in a row of the target table.

[0074] Optionally, when the user needs to add a row of data to the target table, the user can perform a trigger operation on any cell in any row of the target table. For example, the user can click on the index column cell of an empty row in the target table. In response to the user's trigger operation on the cell, the electronic device can display a thumbnail identifier of the interactive component in the cell. For example Figure 6 As shown, a thumbnail identifier 330 of the interactive component is displayed on the right or left side of the cell. After the user triggers the thumbnail identifier 330, the electronic device displays the interactive component 310 in response to the trigger operation on the thumbnail identifier 330. The user can further input the third user input instruction through the interactive component 310, and finally add a row of data to this row through the language model.

[0075] Optionally, when the user does not specify which row to add the data to be added, it can be defaulted to add the data to be added to the last row of the target table.

[0076] Based on any of the above embodiments, in the process of calling the language model to create a target table that meets the table creation requirement information according to the first user input instruction in S202, it further includes:

[0077] Display a creation status prompt message and a preset operation instruction control for this creation process in the interactive component, where the preset operation instruction control for the creation process includes a retry control and / or an interruption control.

[0078] Among them, as Figure 7 shown, a creation status prompt message 313 is displayed in the interactive component 310 to prompt the user that the target table is in the creation process. For example, the creation status prompt message can be "Creating a table for you". In addition, the preset operation instruction control for this creation process displayed in the interactive component is used to control this creation process, including but not limited to retry and / or interruption. That is, the preset operation instruction control for the creation process can include but not limited to a retry control and / or an interruption control. For example Figure 7 the interactive component 310 in includes a retry control 314 and an interruption control 315.

[0079] When the user triggers the retry control, the electronic device responds to the trigger operation on the retry control, stops the current creation process, cancels the generated target table, and then, according to the first user input instruction again, calls the language model to create a target table that meets the table creation requirement information. Since the language model has uncertainty, when the first user input instruction remains unchanged, different target tables may be created during retries.

[0080] When the user triggers the interruption control, the electronic device responds to the trigger operation on the interruption control, stops the current creation process, and can either retain the generated target table or cancel the generated target table. In addition, it can also close or hide the interactive component, or not close or hide the interactive component.

[0081] Based on any of the above embodiments, after presenting the target table in the table interface in S203, it further includes:

[0082] Display a preset operation instruction control for the target table in the interactive component, where the preset operation instruction control for the target table includes one or more of an adoption control, a retry control, and a discard control.

[0083] In this embodiment, the preset operation instruction control for the target table is used for the user to perform operations on the target table, including but not limited to adopting the target table, discarding the target table, regenerating the target table, etc. That is, the preset operation instruction control for the target table includes one or more of an adoption control, a retry control, and a discard control. As Figure 8 shown, the interactive component 310 includes an adoption control 316, a retry control 317, and a discard control 318.

[0084] Among them, if the user is satisfied with the target table, the adoption control can be triggered. The electronic device responds to the trigger operation on the adoption control, completes the creation of the target table, and exits the interactive component. Optionally, before the target table is adopted, it can be in a highlighted state. That is, S203 displays the target table in a highlighted state in the table interface after the target table is created. Before the user triggers the adoption control, the target table remains in the highlighted state until the user triggers the adoption control, and then the target table returns to the normal state, that is, changes from the highlighted state to the non-highlighted state, indicating that the creation of the target table is completed.

[0085] If the user is not satisfied with the target table, the retry control can be triggered. The electronic device responds to the trigger operation on the retry control, cancels the target table, and then, according to the first user input instruction again, calls the language model to create a target table that meets the table creation requirement information.

[0086] If the user is not satisfied with the target table, the discard control can also be triggered. In response to the triggering operation on the discard control, the electronic device cancels the target table and exits (or hides) the interactive component. Of course, the interactive component may not be closed or hidden.

[0087] Based on any of the above embodiments, during the process of creating the target table or after the target table is created, when the user triggers other areas outside the interactive component, the electronic device can respond to the triggering operation on other areas outside the interactive component and display a first prompt message. The first prompt message includes a prompt message for adopting or discarding the generated target table, or a prompt message for interrupting the current creation process. If the user triggers other areas outside the interactive component after the target table is created, the first prompt message is displayed to ask the user whether to adopt or discard the generated target table; if the user triggers other areas outside the interactive component during the process of creating the target table, the first prompt message is displayed to ask the user whether to interrupt the current creation process. Optionally, the first prompt message can be displayed in the form of a pop-up window, etc. The pop-up window may include a confirmation control or a rejection control for the first prompt message.

[0088] In addition, other exit methods can also be provided. For example, a specified key (such as the Esc key, etc.) is triggered on the keyboard, or a specified key (such as the Delete key, etc.) is triggered on the keyboard when the input box control is empty. Examples are not listed one by one here.

[0089] Based on any of the above embodiments, considering that the capabilities of the language model are limited and may not be able to process all user input instructions and obtain appropriate results, for any user input instruction based on natural language entered in the input box control in the interactive component, including but not limited to the above first user input instruction, second user input instruction, and third user input instruction, if it is determined that the language model cannot process (cannot be processed in the current table creation scenario), a second prompt message is displayed in the interactive component. The second prompt message is used to show that the user input instruction cannot be processed, or to prompt the user to enter other instructions. For example, in the scenario of table creation, if the user input instruction is to query the current weather and the language model determines that it cannot be processed in the current table creation scenario, the second prompt message can be displayed in the interactive component to inform the user that the user input instruction cannot be processed, or the user can also be prompted to enter other instructions, such as by asking questions to prompt the user to enter other instructions. Of course, the language model can also display the current weather in the interactive component. Through the above solution, it is applicable to the situation where the language model cannot process or the question-and-answer intention escapes.

[0090] In any of the above embodiments, the entry of the interactive component can be set for different situations in the table interface.

[0091] For example, in an alternative scenario, a thumbnail identifier of an interactive component can be displayed at a preset position in the table interface. For example, the thumbnail identifier of the interactive component can be displayed in the toolbar of the table interface. When the user triggers the thumbnail identifier of the interactive component displayed at the preset position, the electronic device responds to the trigger operation on the thumbnail identifier and displays the interactive component. The interactive component can be displayed at a preset fixed position, within a preset range near the thumbnail identifier, or floating above the table interface. Additionally, the user can also drag or scale the interactive component.

[0092] Again, in another alternative scenario, when creating a new table, the interactive component or its thumbnail identifier is displayed at the bottom of the blank table in the table interface.

[0093] Again, in another alternative scenario, when the user needs to add a row of data to be added in the target table, the thumbnail identifier of the interactive component can be displayed in the cell triggered by the user, or when the user triggers the index column cell of an empty row, the thumbnail identifier of the interactive component can be displayed in the index column cell of the empty row or in another cell of the empty row. When the user triggers the thumbnail identifier of the interactive component displayed at the preset position, the electronic device responds to the trigger operation on the thumbnail identifier and displays the interactive component. The interactive component can be displayed at a preset fixed position, within a preset range near the thumbnail identifier, or floating above the table interface. Additionally, the user can also drag or scale the interactive component.

[0094] Again, in another alternative scenario, during the process of creating the target table, the interactive component can be displayed below the target table. Optionally, the interactive component can follow the latest generated row of sample data or real data of the target table and be displayed below the latest generated row of sample data or real data (following below the field name row when generating fields). Optionally, the position of the interactive component on the Y-axis coordinate in the table interface changes continuously following the latest generated row of sample data or real data, while the X-axis coordinate remains unchanged. When the Y-axis coordinate reaches the bottom of the table interface, it no longer changes.

[0095] It should be noted that the different scenarios in the table interface are not limited to the above examples, and other alternative scenarios are not elaborated in this embodiment.

[0096] In addition, in any of the above embodiments, different preset shortcut instruction controls can be displayed in the interaction component according to different situations. For example, before creating a table (when the table interface displays a blank table), preset shortcut instruction controls for creating a table can be displayed in the interaction component, such as shortcut instruction controls for "building a business system" and "building a task management table"; for another example, after creating and displaying the target table, preset shortcut instruction controls related to field modification can be displayed in the interaction component, such as shortcut instruction controls for deleting existing fields and adding new fields; for another example, when the user needs to add a row of data to be added in the target table, preset shortcut instruction controls related to adding data can be displayed in the interaction component; for another example, during the process of generating the target table, preset operation instruction controls for this creation process can be displayed in the interaction component, including but not limited to retry controls and / or interruption controls; for another example, after generating the target table, preset operation instruction controls for the target table can also be displayed in the interaction component, including but not limited to one or more of an adoption control, a retry control, and a discard control, etc. It should be noted that the different situations in the table interface are not limited to the above examples, and the preset shortcut instruction controls in the interaction component in other alternative situations will not be elaborated in this embodiment.

[0097] Corresponding to the table creation method in the above embodiment, Figure 9 is a structural block diagram of a table creation device provided by an embodiment of the present disclosure. For ease of description, only parts related to the embodiments of the present disclosure are shown. Referring to Figure 9 the table creation device 900 includes: an input unit 901, a processing unit 902, and a display unit 903.

[0098] Among them, the input unit 901 is configured to receive a first user input instruction through an interaction component in the table interface, where the first user input instruction includes table creation requirement information;

[0099] The processing unit 902 is configured to call a language model to create a target table that meets the table creation requirement information according to the first user input instruction;

[0100] The display unit 903 is configured to present the target table in the table interface.

[0101] In one or more embodiments of the present disclosure, when the processing unit 902 calls a language model to create a target table that meets the table creation requirement information according to the first user input instruction, it is configured to:

[0102] Generate model input data using a preset template according to the first user input instruction;

[0103] Process the model input data based on the language model to obtain target table data that meets the table creation requirement information;

[0104] Parse the target table data, and create the target table in the table interface according to the parsing result.

[0105] In one or more embodiments of the present disclosure, the target table data includes one or more of the following:

[0106] The number of tables included in the target table, the theme of each table, the field names in the table, the alternative items of at least one field, the example data in the table, and the real data in the table.

[0107] In one or more embodiments of the present disclosure, when the input unit 901 receives a first user input instruction through an interaction component in the table interface, it is used for:

[0108] Receive the instruction content in natural language input in the input box control in the interaction component, and determine the instruction content as the first user input instruction; or

[0109] In response to a trigger operation on a preset shortcut instruction control in the interaction component, determine the preset shortcut instruction corresponding to the preset shortcut instruction control as the first user input instruction; or

[0110] In response to a trigger operation on a preset shortcut instruction control in the interaction component, display a preset prompt corpus in the input box control in the interaction component, and receive the instruction content in natural language input by the user for the preset prompt corpus in the input box control, and determine the preset prompt corpus and the instruction content as the first user input instruction; or

[0111] Receive the instruction content in natural language input in the input box control in the interaction component, display a preset shortcut instruction control matching the instruction content in the interaction component, and in response to a trigger operation on the preset shortcut instruction control, determine the preset shortcut instruction corresponding to the preset shortcut instruction control as the first user input instruction.

[0112] In one or more embodiments of the present disclosure, the input unit 901 is further configured to, after presenting the target table in the table interface, receive a second user input instruction through the interaction component, where the second user input instruction includes field modification requirement information for the target table, and the field modification requirement information includes requirement information for modifying existing fields, requirement information for deleting existing fields, or requirement information for adding new fields;

[0113] The processing unit 902 is further configured to, according to the second user input instruction, call the language model to modify the fields of the target table based on the field modification requirement information.

[0114] In one or more embodiments of the present disclosure, the input unit 901 is further configured to, after presenting the target table in the table interface, receive a third user input instruction through the interaction component, where the third user input instruction includes data addition requirement information for the target table, and the data addition requirement information includes to-be-added data information based on natural language;

[0115] The processing unit 902 is further configured to, according to the third user input instruction, call the language model to add the to-be-added data information to a row of the target table according to fields.

[0116] In one or more embodiments of the present disclosure, when receiving the third user input instruction through the interaction component, the input unit 901 is configured to:

[0117] In response to a trigger operation on any cell of any row in the target table, display a thumbnail identifier of the interaction component in the cell;

[0118] In response to a trigger on the thumbnail identifier, display the interaction component and receive the third user input instruction through the interaction component.

[0119] In one or more embodiments of the present disclosure, the input unit 901 is further configured to:

[0120] In response to a trigger operation on the thumbnail identifier of the interaction component displayed at a preset position in the table interface, display the interaction component.

[0121] In one or more embodiments of the present disclosure, during the process of calling the language model to create a target table that meets the table creation requirement information according to the first user input instruction, the input unit 901 is further configured to display creation status prompt information and preset operation instruction controls for the current creation process in the interaction component, where the preset operation instruction controls for the creation process include a retry control and / or an interruption control;

[0122] The processing unit 902 is further configured to, in response to a trigger operation on the retry control, stop the current creation process, revoke the generated target table, and re-call the language model to create a target table that meets the table creation requirement information according to the first user input instruction; or

[0123] The processing unit 902 is further configured to stop the current creation process and retain or revoke the generated target table in response to a triggering operation on the interruption control.

[0124] In one or more embodiments of the present disclosure, after presenting the target table in the table interface, the input unit 901 is further configured to display preset operation instruction controls for the target table in the interaction component, where the preset operation instruction controls for the target table include one or more of an adoption control, a retry control, and a discard control;

[0125] The processing unit 902 is further configured to complete the creation of the target table and exit the interaction component in response to a triggering operation on the adoption control; or

[0126] The processing unit 902 is further configured to revoke the target table and re - call the language model to create a target table that meets the table creation requirement information according to the first user input instruction in response to a triggering operation on the retry control; or

[0127] In response to a triggering operation on the discard control, revoke the target table.

[0128] In one or more embodiments of the present disclosure, the method further includes:

[0129] The input unit 901 is further configured to: display a first prompt message in response to a triggering operation on other areas outside the interaction component, where the first prompt message includes a prompt message for adopting or discarding the generated target table, or a prompt message for interrupting the current creation process.

[0130] In one or more embodiments of the present disclosure, the input unit 901 is further configured to, for any user input instruction based on natural language input in the input box control in the interaction component, if it is determined that the language model cannot process it, display a second prompt message in the interaction component, where the second prompt message is used to indicate that the user input instruction cannot be processed or to prompt the user to input other instructions.

[0131] The device provided in this embodiment can be used to execute the technical solutions of the above - mentioned method embodiments, and its implementation principle and technical effects are similar, which will not be elaborated here in this embodiment.

[0132] Reference Figure 10, which shows a schematic structural diagram of an electronic device 1000 suitable for implementing the embodiments of the present disclosure. The electronic device 1000 can be a terminal device or a server. Among them, the terminal device can include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers (PADs), portable media players (PMPs), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 10 The electronic device shown is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of the present disclosure.

[0133] As Figure 10 shown, the electronic device 1000 can include a processing device (such as a central processing unit, a graphics processing unit, etc.) 1001, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 1002 or the program loaded from the storage device 1008 into the random access memory (RAM) 1003. In the RAM 1003, various programs and data required for the operation of the electronic device 1000 are also stored. The processing device 1001, the ROM 1002, and the RAM 1003 are connected to each other through a bus 1004. The input / output (I / O) interface 1005 is also connected to the bus 1004.

[0134] Generally, the following devices can be connected to the I / O interface 1005: an input device 1006 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 1007 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1008 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the electronic device 1000 to communicate with other devices wirelessly or wirelessly to exchange data. Although Figure 10 the electronic device 1000 with various devices is shown, it should be understood that it is not required to implement or have all the shown devices. Instead, more or fewer devices can be implemented or had.

[0135] In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, an embodiment of the present disclosure includes a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes program code for performing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network via the communication device 1009, or installed from the storage device 1008, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the methods of the embodiments of the present disclosure are performed.

[0136] It should be noted that the above-mentioned computer-readable medium in the present disclosure can be a computer-readable signal medium, 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 of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, and the computer-readable signal medium can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0137] The above-mentioned computer-readable medium can be included in the above-mentioned electronic device; or it can exist separately and not be assembled into the electronic device.

[0138] The above-mentioned computer-readable medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device is caused to perform the methods shown in the above embodiments.

[0139] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0140] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0141] The units described in the embodiments of the present disclosure may be implemented in software or in hardware. Among them, the name of the unit does not constitute a limitation to the unit itself in some cases. For example, the first acquisition unit may also be described as "the unit for acquiring at least two Internet protocol addresses".

[0142] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, by way of non-limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), system on a chip (SOC), complex programmable logic devices (CPLD), and so on.

[0143] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium can include, 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 the machine-readable storage medium would 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.

[0144] In a first aspect, according to one or more embodiments of the present disclosure, there is provided a method for creating a table, including:

[0145] Receiving a first user input instruction through an interaction component in a table interface, where the first user input instruction includes table creation requirement information;

[0146] According to the first user input instruction, calling a language model to create a target table that meets the table creation requirement information;

[0147] Presenting the target table in the table interface.

[0148] According to one or more embodiments of the present disclosure, the step of, according to the first user input instruction, calling a language model to create a target table that meets the table creation requirement information includes:

[0149] According to the first user input instruction, generating model input data by using a preset template;

[0150] Processing the model input data based on the language model to obtain target table data that meets the table creation requirement information;

[0151] Parsing the target table data, and creating the target table in the table interface according to the parsing result.

[0152] According to one or more embodiments of the present disclosure, the target table data includes one or more of the following:

[0153] The number of tables included in the target table, the theme of each table, the field names in the table, alternative items for at least one field, example data in the table, and real data in the table.

[0154] According to one or more embodiments of the present disclosure, receiving the first user input instruction through the interaction component in the table interface includes:

[0155] Receiving the instruction content based on natural language input in the input box control in the interaction component, and determining the instruction content as the first user input instruction; or

[0156] In response to a triggering operation on the preset quick instruction control in the interaction component, determining the preset quick instruction corresponding to the preset quick instruction control as the first user input instruction; or

[0157] In response to a triggering operation on the preset quick instruction control in the interaction component, displaying preset prompt corpus in the input box control in the interaction component, and receiving the instruction content based on natural language input by the user for the preset prompt corpus in the input box control, and determining the preset prompt corpus and the instruction content as the first user input instruction; or

[0158] Receiving the instruction content based on natural language input in the input box control in the interaction component, displaying the preset quick instruction control matching the instruction content in the interaction component, and in response to a triggering operation on the preset quick instruction control, determining the preset quick instruction corresponding to the preset quick instruction control as the first user input instruction.

[0159] According to one or more embodiments of the present disclosure, after presenting the target table in the table interface, it further includes:

[0160] Receiving a second user input instruction through the interaction component, where the second user input instruction includes the field modification requirement information for the target table, and the field modification requirement information includes the requirement information for modifying existing fields, the requirement information for deleting existing fields, or the requirement information for adding new fields;

[0161] According to the second user input instruction, calling the language model to modify the fields of the target table based on the field modification requirement information.

[0162] According to one or more embodiments of the present disclosure, after presenting the target table in the table interface, it further includes:

[0163] Receiving a third user input instruction through the interaction component, where the third user input instruction includes the data addition requirement information for the target table, and the data addition requirement information includes the to-be-added data information based on natural language;

[0164] According to the third user input instruction, calling the language model to add the to-be-added data information to a row of the target table according to the fields.

[0165] According to one or more embodiments of the present disclosure, receiving the third user input instruction through the interaction component includes:

[0166] In response to a triggering operation on any cell in any row of the target table, a thumbnail identifier of the interaction component is displayed in the cell;

[0167] In response to a triggering operation on the thumbnail identifier, the interaction component is displayed, and the third user input instruction is received through the interaction component.

[0168] According to one or more embodiments of the present disclosure, the method further includes:

[0169] In response to a triggering operation on the thumbnail identifier of the interaction component displayed at a preset position in the table interface, the interaction component is displayed.

[0170] According to one or more embodiments of the present disclosure, in the process of calling the language model to create a target table that meets the table creation requirement information according to the first user input instruction, it further includes:

[0171] A creation status prompt message and a preset operation instruction control for this creation process are displayed in the interaction component, where the preset operation instruction control for the creation process includes a retry control and / or an interruption control;

[0172] In response to a triggering operation on the retry control, the current creation process is stopped, the generated target table is revoked, and the language model is called again according to the first user input instruction to create a target table that meets the table creation requirement information; or

[0173] In response to a triggering operation on the interruption control, the current creation process is stopped, and the generated target table is retained or revoked.

[0174] According to one or more embodiments of the present disclosure, after presenting the target table in the table interface, it further includes:

[0175] A preset operation instruction control for the target table is displayed in the interaction component, where the preset operation instruction control for the target table includes one or more of an adoption control, a retry control, and a discard control;

[0176] In response to a triggering operation on the adoption control, the creation of the target table is completed, and the interaction component is exited; or

[0177] In response to a trigger operation on the retry control, cancel the target table and recreate the target table that meets the table creation requirement information according to the first user input instruction again; or

[0178] In response to a trigger operation on the discard control, cancel the target table.

[0179] According to one or more embodiments of the present disclosure, the method further includes:

[0180] In response to a trigger operation on other areas outside the interaction component, display a first prompt message, where the first prompt message includes a prompt message for adopting or discarding the generated target table, or a prompt message for interrupting the current creation process.

[0181] According to one or more embodiments of the present disclosure, the method further includes:

[0182] For any user input instruction based on natural language input in the input box control in the interaction component, if it is determined that the language model cannot process it, display a second prompt message in the interaction component, where the second prompt message is used to indicate that the user input instruction cannot be processed, or to prompt the user to input other instructions.

[0183] In a second aspect, according to one or more embodiments of the present disclosure, a table creation device is provided, including:

[0184] An input unit, configured to receive a first user input instruction through an interaction component in a table interface, where the first user input instruction includes table creation requirement information;

[0185] A processing unit, configured to call a language model to create a target table that meets the table creation requirement information according to the first user input instruction;

[0186] A display unit, configured to present the target table in the table interface.

[0187] According to one or more embodiments of the present disclosure, when the processing unit calls a language model to create a target table that meets the table creation requirement information according to the first user input instruction, it is configured to:

[0188] Generate model input data using a preset template according to the first user input instruction;

[0189] Process the model input data based on the language model to obtain target table data that meets the table creation requirement information;

[0190] Parse the target table data and create the target table in the table interface according to the parsing result.

[0191] According to one or more embodiments of the present disclosure, the target table data includes one or more of the following:

[0192] The number of tables included in the target table, the theme of each table, the field names in the table, the alternative items of at least one field, the example data in the table, and the real data in the table.

[0193] According to one or more embodiments of the present disclosure, when the input unit receives a first user input instruction through an interaction component in the table interface, it is configured to:

[0194] Receive the instruction content based on natural language input in the input box control in the interaction component, and determine the instruction content as the first user input instruction; or

[0195] In response to a triggering operation on a preset shortcut instruction control in the interaction component, determine the preset shortcut instruction corresponding to the preset shortcut instruction control as the first user input instruction; or

[0196] In response to a triggering operation on a preset shortcut instruction control in the interaction component, display preset prompt corpus in the input box control in the interaction component, and receive the instruction content based on natural language input by the user for the preset prompt corpus, and determine the preset prompt corpus and the instruction content as the first user input instruction; or

[0197] Receive the instruction content based on natural language input in the input box control in the interaction component, display a preset shortcut instruction control matching the instruction content in the interaction component, and in response to a triggering operation on the preset shortcut instruction control, determine the preset shortcut instruction corresponding to the preset shortcut instruction control as the first user input instruction.

[0198] According to one or more embodiments of the present disclosure, the input unit is further configured to, after presenting the target table in the table interface, receive a second user input instruction through the interaction component, where the second user input instruction includes field modification requirement information for the target table, and the field modification requirement information includes requirement information for modifying an existing field, requirement information for deleting an existing field, or requirement information for adding a new field;

[0199] The processing unit is further configured to, according to the second user input instruction, call the language model to modify the fields of the target table based on the field modification requirement information.

[0200] According to one or more embodiments of the present disclosure, the input unit is further configured to, after presenting the target table in the table interface, receive a third user input instruction through the interaction component, where the third user input instruction includes data addition requirement information for the target table, and the data addition requirement information includes to-be-added data information based on natural language;

[0201] The processing unit is further configured to, according to the third user input instruction, call the language model to add the to-be-added data information to a row of the target table according to fields.

[0202] According to one or more embodiments of the present disclosure, when receiving the third user input instruction through the interaction component, the input unit is configured to:

[0203] In response to a trigger operation on any cell of any row in the target table, display a thumbnail identifier of the interaction component in the cell;

[0204] In response to a trigger on the thumbnail identifier, display the interaction component and receive a third user input instruction through the interaction component.

[0205] According to one or more embodiments of the present disclosure, the input unit is further configured to:

[0206] In response to a trigger operation on the thumbnail identifier of the interaction component displayed at a preset position in the table interface, display the interaction component.

[0207] According to one or more embodiments of the present disclosure, during the process of calling the language model to create a target table that meets the table creation requirement information according to the first user input instruction, the input unit is further configured to display a creation status prompt information and a preset operation instruction control for the current creation process in the interaction component, where the preset operation instruction control for the creation process includes a retry control and / or an interruption control;

[0208] The processing unit is further configured to, in response to a trigger operation on the retry control, stop the current creation process, revoke the generated target table, and re-call the language model to create a target table that meets the table creation requirement information according to the first user input instruction; or

[0209] The processing unit is further configured to, in response to a trigger operation on the interruption control, stop the current creation process and retain or revoke the generated target table.

[0210] According to one or more embodiments of the present disclosure, after presenting the target table in the table interface, the input unit is further configured to display preset operation instruction controls for the target table in the interaction component, where the preset operation instruction controls for the target table include one or more of an adoption control, a retry control, and a discard control;

[0211] The processing unit is further configured to, in response to a trigger operation on the adoption control, complete the creation of the target table and exit the interaction component; or

[0212] The processing unit is further configured to, in response to a trigger operation on the retry control, cancel the target table and re - call the language model to create a target table that meets the table creation requirement information according to the first user input instruction; or

[0213] In response to a trigger operation on the discard control, cancel the target table.

[0214] According to one or more embodiments of the present disclosure, the method further includes:

[0215] The input unit is further configured to: in response to a trigger operation on other areas outside the interaction component, display a first prompt message, where the first prompt message includes a prompt message for adopting or discarding the generated target table, or a prompt message for interrupting the current creation process.

[0216] According to one or more embodiments of the present disclosure, the input unit is further configured to, for any user input instruction in natural language input into the input box control in the interaction component, if it is determined that the language model cannot process it, display a second prompt message in the interaction component, where the second prompt message is used to indicate that the user input instruction cannot be processed, or to prompt the user to input other instructions.

[0217] In a third aspect, according to one or more embodiments of the present disclosure, there is provided an electronic device, including: at least one processor and a memory;

[0218] The memory stores computer - executable instructions;

[0219] The at least one processor executes the computer - executable instructions stored in the memory, so that the at least one processor executes the table creation method as described in the first aspect and various possible designs of the first aspect above.

[0220] Fourthly, according to one or more embodiments of the present disclosure, there is provided a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the table creation method as described in the first aspect above and various possible designs of the first aspect.

[0221] Fifthly, according to one or more embodiments of the present disclosure, there is provided a computer program product including computer-executable instructions, which, when executed by a processor, implement the table creation method as described in the first aspect above and various possible designs of the first aspect.

[0222] The above description is only a preferred embodiment of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of the disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosure concept. For example, the technical solutions formed by mutually replacing the above features with the technical features (but not limited to) having similar functions disclosed in the present disclosure.

[0223] In addition, although the operations are depicted in a particular order, this should not be construed as requiring that the operations be performed in the particular order shown or in sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, although a number of specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features described in the context of separate embodiments may also be implemented combinatorially in a single embodiment. Conversely, the various features described in the context of a single embodiment may also be implemented separately or in any suitable sub-combination in multiple embodiments.

[0224] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms for implementing the claims.

Claims

1. A method for creating a table, characterized in that, Including: Receiving a first user input instruction through an interactive component in a table interface, where the first user input instruction includes table creation requirement information; According to the first user input instruction, calling a language model to create a target table that meets the table creation requirement information; Presenting the target table in the table interface; During the process of calling a language model to create a target table that meets the table creation requirement information according to the first user input instruction, it further includes: Displaying creation status prompt information and preset operation instruction controls for this creation process in the interactive component, where the preset operation instruction controls for this creation process include a retry control and / or an interruption control; In response to a trigger operation on the retry control, stopping this creation process, canceling the generated target table, and then calling a language model again according to the first user input instruction to create a target table that meets the table creation requirement information; or In response to a trigger operation on the interruption control, stopping this creation process, and retaining or canceling the generated target table.

2. The method according to claim 1, wherein The calling a language model to create a target table that meets the table creation requirement information according to the first user input instruction includes: According to the first user input instruction, generating model input data using a preset template; Processing the model input data based on the language model to obtain target table data that meets the table creation requirement information; Parsing the target table data and creating the target table in the table interface according to the parsing result.

3. The method according to claim 2, wherein The target table data includes one or more of the following: The number of tables included in the target table, the theme of each table, the field names in the table, alternative options for at least one field, example data in the table, and real data in the table.

4. The method according to claim 1, wherein The receiving a first user input instruction through an interactive component in a table interface includes: Receiving instruction content in natural language input in an input box control in the interactive component and determining the instruction content as the first user input instruction; or In response to a trigger operation on a preset quick instruction control in the interactive component, determining the preset quick instruction corresponding to the preset quick instruction control as the first user input instruction; or In response to a trigger operation on a preset quick instruction control in the interactive component, displaying preset prompt corpus in the input box control in the interactive component and receiving instruction content in natural language input by the user for the preset prompt corpus in the input box control, and determining the preset prompt corpus and the instruction content as the first user input instruction; or Receiving instruction content in natural language input in an input box control in the interactive component, displaying a preset quick instruction control that matches the instruction content in the interactive component, and in response to a trigger operation on the preset quick instruction control, determining the preset quick instruction corresponding to the preset quick instruction control as the first user input instruction.

5. The method according to claim 1, characterized in that, After presenting the target table in the table interface, it further includes: Receive a second user input instruction through the interaction component, where the second user input instruction includes field modification requirement information for the target table, and the field modification requirement information includes requirement information for modifying existing fields, requirement information for deleting existing fields, or requirement information for adding new fields; According to the second user input instruction, call the language model to modify the fields of the target table based on the field modification requirement information.

6. The method according to claim 1, characterized in that, After presenting the target table in the table interface, it further includes: Receive a third user input instruction through the interaction component, where the third user input instruction includes data addition requirement information for the target table, and the data addition requirement information includes to-be-added data information based on natural language; According to the third user input instruction, call the language model to add the to-be-added data information to a row of the target table according to the fields.

7. The method according to claim 6, wherein The receiving the third user input instruction through the interaction component includes: In response to a trigger operation on any cell of any row in the target table, display a thumbnail identifier of the interaction component in the cell; In response to a trigger on the thumbnail identifier, display the interaction component and receive the third user input instruction through the interaction component.

8. The method according to any one of claims 1-6, characterized in that, The method further includes: In response to a trigger operation on the thumbnail identifier of the interaction component displayed at a preset position in the table interface, display the interaction component.

9. The method according to any one of claims 1-7, characterized in that, After presenting the target table in the table interface, it further includes: Display preset operation instruction controls for the target table in the interaction component, where the preset operation instruction controls for the target table include one or more of an adoption control, a retry control, and a discard control; In response to a trigger operation on the adoption control, complete the creation of the target table and exit the interaction component; or In response to a trigger operation on the retry control, cancel the target table and re-call the language model to create a target table that meets the table creation requirement information according to the first user input instruction; or In response to a trigger operation on the discard control, cancel the target table.

10. The method according to any one of claims 1-7, characterized in that, The method further includes: In response to a trigger operation on other areas outside the interaction component, display a first prompt message, where the first prompt message includes a prompt message for adopting or discarding the generated target table, or a prompt message for interrupting the current creation process.

11. The method according to claim 1, characterized in that, The method further includes: For any user input instruction based on natural language input in the input box control in the interaction component, if it is determined that the language model cannot process it, display a second prompt message in the interaction component, where the second prompt message is used to indicate that the user input instruction cannot be processed, or to prompt the user to input other instructions.

12. A table creation device, characterized in that, It includes: An input unit for receiving a first user input instruction through an interaction component in a table interface, where the first user input instruction includes table creation requirement information; A processing unit for calling a language model to create a target table that meets the table creation requirement information according to the first user input instruction; A display unit for presenting the target table in the table interface; During the process of calling a language model to create a target table that meets the table creation requirement information according to the first user input instruction, the input unit is further configured to display a creation status prompt message and a preset operation instruction control for the current creation process in the interaction component, where the preset operation instruction control for the current creation process includes a retry control and / or an interruption control; The processing unit is further configured to, in response to a trigger operation on the retry control, stop the current creation process, revoke the generated target table, and re-call the language model to create a target table that meets the table creation requirement information according to the first user input instruction; Or The processing unit is further configured to, in response to a trigger operation on the interruption control, stop the current creation process and retain or revoke the generated target table.

13. An electronic device, characterized in that, Comprising: At least one processor and a memory; The memory stores computer-executable instructions; The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the method according to any one of claims 1-11.

14. A computer-readable storage medium, characterized in that, Computer-executable instructions are stored in the computer-readable storage medium, and when the processor executes the computer-executable instructions, the method according to any one of claims 1-11 is implemented.

15. A computer program product, characterized in that, Comprising computer-executable instructions, and when the processor executes the computer-executable instructions, the method according to any one of claims 1-11 is implemented.

Images