Table generation text processing method, system and equipment and medium

Abstract

The invention provides a processing method, system and equipment for generating a text from a table and a medium, and the processing method comprises the steps: obtaining voice and / or character input, extracting table selection information used for determining the specific content of the table, and determining the specific content of the table; according to voice and / or character input, task information used for defining task types and task control is extracted, and task configuration is determined; and based on the specific content of the table and the task configuration, performing text conversion through a pre-trained large model to generate a corresponding output text. According to the method, the requirement of manual intervention is reduced, the user can describe the requirement more conveniently and visually, complex interface operation is not needed, more efficient table content selection and task generation are achieved, the flexibility of the system, the use experience of the user and the working efficiency are greatly improved, and the user experience is improved. Therefore, the generated text better meets the expected and actual requirements of the user, and the text generation accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a processing method, system, device and medium for generating text from a table. Background Art

[0002] In the field of data processing, tables are widely used in data management and analysis in various industries as a way to store and display structured data. As the amount of data continues to grow, how to efficiently convert the data in tables into natural language text that is easy to understand and spread has become an important challenge in the field of data processing.

[0003] In related technologies, large models, as machine learning models with a large number of parameters and complex architecture, have realized automatic table generation text processing due to their powerful data processing capabilities and wide applications in natural language processing, computer vision, speech recognition and other fields. However, when processing complex tables or performing specific tasks, users still need to perform a lot of manual intervention and adjustments, which affects the conversion efficiency.

[0004] In addition, due to the diversity and complexity of tabular data, related technologies may find it difficult to ensure the accuracy and readability of the results when generating text, and may not be able to generate ideal text that meets the specific needs of users. Summary of the invention

[0005] The present invention provides a processing method, system, device and medium for generating text from a table, which solves the problems of how to improve the efficiency of generating text from a table and how to effectively generate an ideal text that meets the requirements.

[0006] In order to achieve the above objectives, this application adopts the following technical solutions:

[0007] In a first aspect, a method for processing text generated from a table is provided, comprising:

[0008] Acquiring voice and / or text input, extracting form selection information for determining form-specific content, and determining the form-specific content;

[0009] Extracting task information for defining task type and task control according to the voice and / or text input, and determining task configuration;

[0010] Based on the table-specific content and the task configuration, text conversion is performed through a pre-trained large model to generate corresponding output text.

[0011] In a first possible implementation manner of the first aspect, the method for processing text generated from a table further includes:

[0012] Get the historical generation record, take the selected historical output text as subparts and perform a merge operation;

[0013] The priority setting of each of the sub-parts is obtained, and a comprehensive text is generated based on the merged text content according to the priority.

[0014] In a second possible implementation manner of the first aspect, the acquiring of voice and / or text input and extracting table selection information for determining specific content of the table specifically includes:

[0015] Acquire speech, convert it into corresponding text through speech recognition technology, and extract the table selection information based on the text;

[0016] The input text is acquired through the text box, and the table selection information is extracted based on the text.

[0017] In a third possible implementation manner of the first aspect, determining the table-specific content further includes:

[0018] Directly select specific content of the table through the interface tool;

[0019] The specific content of the table is determined by combining voice input and interface tool selection and / or the specific content of the table is determined by combining text input and interface tool selection.

[0020] In a fourth possible implementation manner of the first aspect, the determining of the task configuration further includes:

[0021] The task configuration is determined by a control component and / or by selecting from a predefined tag list or inputting a custom tag.

[0022] In a second aspect, a system for processing text generated from a table is provided, comprising:

[0023] a form selection module, for acquiring voice and / or text input, extracting form selection information for determining form-specific content, and determining the form-specific content;

[0024] A task configuration module, for extracting task information for defining task type and task control according to the voice and / or text input, and determining task configuration;

[0025] The text conversion module is used to perform text conversion based on the table-specific content and the task configuration through a pre-trained large model to generate corresponding output text.

[0026] In a first possible implementation manner of the second aspect, the system for processing text generated from a table further includes:

[0027] A history text module, used to obtain the history generation records, take the selected history output text as sub-parts and perform the merge operation;

[0028] The comprehensive text module is used to obtain the priority setting of each of the sub-parts and generate a comprehensive text based on the merged text content according to the priority.

[0029] In a second possible implementation manner of the second aspect, the table selection module is specifically configured to:

[0030] Acquire speech, convert it into corresponding text through speech recognition technology, and extract the table selection information based on the text;

[0031] The input text is acquired through the text box, and the table selection information is extracted based on the text.

[0032] According to a third aspect, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the method for processing text generated from a table as described in the first aspect are implemented.

[0033] In a fourth aspect, a readable storage medium is provided, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the processing method for generating text from a table as described in the first aspect are implemented.

[0034] This application reduces the need for manual intervention by introducing voice or text input, allowing users to describe their needs more conveniently and intuitively without complex interface operations, and more efficiently select table content and generate tasks, greatly improving the flexibility of the system and the user experience and work efficiency. This application supports merging and collating text results generated multiple times, and allows users to set priority requirements, so that the generated text is more in line with the user's expectations and actual needs, and improves the accuracy of text generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 A schematic flow chart of a method for processing a table to generate text provided in an embodiment of the present application;

[0036] Figure 2 An operation interface diagram of a process of selecting table content provided in an embodiment of the present application;

[0037] Figure 3 An operation interface diagram of a task configuration process provided in an embodiment of the present application;

[0038] Figure 4 An operation interface diagram for generating a comprehensive text provided in an embodiment of the present application;

[0039] Figure 5 A structural block diagram of a processing system for generating text from a table provided in an embodiment of the present application;

[0040] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined purpose, the technical solutions in the embodiments of the present application are clearly described. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the present application.

[0042] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0043] The description of the method flow in the specification of the present application and the steps of the flowchart in the drawings of the present specification do not have to be strictly executed according to the step numbers, and the method steps can be executed in a different order. Moreover, some steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps.

[0044] The following is a detailed description of a table-generated text processing method, system, device and medium provided in an embodiment of the present application in conjunction with the accompanying drawings and preferred embodiments.

[0045] First, the application scenario of the method for processing table-generated text in the embodiment of the present application is described in detail.

[0046] In the application scenarios of daily office software, when selecting rows, columns or cells in a table, office software usually uses the keyboard (such as the Ctrl key) combined with mouse clicks to achieve multiple selections or multiple row selections. Although this selection method is intuitive and easy to use, it is obviously inefficient when facing large-scale data tables. Users need to click on the target rows or columns one by one, which is not only time-consuming, but also prone to errors when handling complex tasks.

[0047] In addition, the related technical solutions for converting table content to text often rely on preset task types and lack the user's direct control over the task output results. If there is no clear task description, the system will generate text in a pre-set manner, which will result in a single generated text content that may not meet the user's specific needs.

[0048] For the scale control of generated text, existing technologies usually set certain restrictions to avoid the output content being too large. However, such restrictions are often fixed, and users cannot adjust the text length according to actual needs. Therefore, the generated text may be either too short to cover all the required information, or too long and contain many unnecessary details. This situation is particularly inconvenient when multiple generated results need to be comprehensively sorted. Due to the lack of automated merging and sorting functions, users have to spend a lot of time and energy to read and manually integrate these texts one by one, and simple merging may result in disorganized text content, lack of hierarchy and logic.

[0049] Based on this, the present application provides a processing method for generating text from a table, aiming to improve the flexibility, efficiency and result quality of table-to-text conversion, so as to more effectively generate ideal text that meets the needs. Among them, for selecting which contents of the table to generate text, part of the table content can be selected by voice, text input and manual method. When issuing a task description, it can be quickly formed by voice or text input, or by selecting through task tags and text style tags. In terms of restrictions on the generated text, the system can be limited to give the corresponding text scale through requirements such as the number of words and paragraphs. By issuing priority instruction requirements to the system, it supports the merging and sorting of text results generated multiple times in the history to generate the final comprehensive text.

[0050] See also Figure 1 , the present application embodiment provides a method for processing a table to generate text, such as Figure 1 As shown, the processing method of the embodiment of the present application includes:

[0051] Step S1, obtaining voice and / or text input, extracting table selection information for determining table specific content, and determining the table specific content.

[0052] Table selection information used to determine specific table content, such as column names and row numbers in the table. Specifically, this step includes:

[0053] Step S101, acquiring speech, converting it into corresponding text through speech recognition technology, and extracting table selection information based on the text.

[0054] In specific implementation, users can click the voice input button and start speaking to describe the required task or selection requirements of the form content. The system captures the voice and converts it into text through speech recognition technology, and then the system parses the text to extract the above key information.

[0055] Step S102, obtaining input text through the text box, and extracting table selection information based on the text.

[0056] In specific implementation, the user can click a text input button to start inputting text for the required task or table content selection requirements. The system then parses the input text and extracts the above key information.

[0057] In some possible implementations, step S1 may still use a traditional manual method, namely, interface tool selection, that is, directly selecting specific content in the table through tools on the user interface (such as mouse click, drag, etc.).

[0058] It is worth noting that when selecting part of the table content, the table specific content can be determined by combining voice input and interface tool selection and / or by combining text input and interface tool selection. In other words, the voice input, text input and interface tool selection methods can be used in combination to provide users with flexible selection methods and quickly select content.

[0059] Step S2: extracting task information for defining task type and task control according to voice and / or text input, and determining task configuration.

[0060] Specific text used to define the task type, such as "summary", "comparison", "analysis", "letter of praise", "report", "summary", etc. Specific text used for task control, such as "word count", "paragraph", "style", etc.

[0061] In some possible implementations, the task configuration may also be determined directly by controlling components such as controlling the number of words, paragraphs, and style components.

[0062] In some possible implementations, a custom tag may also be selected from a predefined tag list or input to determine the task configuration.

[0063] It is worth noting that, when determining the task configuration, voice input, text input and control component methods can be used in combination to provide users with flexible task configuration methods and quickly form tasks.

[0064] Step S3, based on the table-specific content and task configuration, text conversion is performed through the pre-trained large model to generate corresponding output text.

[0065] According to the user's input and selection, the system extracts the corresponding data from the table and uses the text generation engine to convert the extracted data into natural language text. The text expression is adjusted according to task information such as task type and task control to achieve text generation.

[0066] In some possible implementations, the present application also includes:

[0067] Step S4, obtaining the historical generation record, taking the selected historical output text as a sub-part and performing a merging operation.

[0068] Step S5, obtaining the priority setting of each sub-part, and generating a comprehensive text based on the merged text content according to the priority.

[0069] The merged text content is reordered or restructured according to priority, and ultimately a complete text that meets all user requirements is output.

[0070] For example, see Figure 2-4 , the operation flow of the processing method of the embodiment of the present application is further explained below.

[0071] See also Figure 2 When selecting table content, you can click the microphone icon on the interface to input voice commands, including selecting cell content and controlling task targets, or you can directly enter text commands in the text box, such as "select rows 6, 10, and 14 of sheet1 in table 1, and sheet2 in table 2". When selecting part of the table content, you can combine voice input, text input, and mouse selection.

[0072] See also Figure 3 After selecting the content, you can use voice or text input when configuring the task. For example, after voice inputting "generate an 800-word summary", "800" will automatically appear in the text input box of the word count component, and "Summary" will automatically appear in the drop-down menu of the style component. You can also control the task directly by controlling the word count, paragraph, and style components.

[0073] See also Figure 4 When automatic merging and sorting is required, voice or text input is used to merge and sort the text results generated multiple times in history to generate the final comprehensive text. This process supports issuing priority instructions to the system, such as "generating a 500-word summary of all the generated records today in reverse order of the time of generation."

[0074] In the process of automatically generating text from table file content, this application can improve the efficiency of selection through voice or text input and manual selection of part of the table content. Tasks can be quickly formed by issuing task descriptions through voice or text input, or by selecting task tags and text style tags. The text content given by the system through word count and paragraph restrictions can more effectively achieve the required text content. It supports merging and organizing text results generated multiple times, giving priority requirements, and can more effectively generate ideal text.

[0075] See also Figure 5 , corresponding to the above-mentioned table-generated text processing method embodiment, the present application embodiment provides a table-generated text processing system, the processing system comprising:

[0076] a form selection module, for acquiring voice and / or text input, extracting form selection information for determining form-specific content, and determining the form-specific content;

[0077] A task configuration module, for extracting task information for defining task type and task control according to the voice and / or text input, and determining task configuration;

[0078] The text conversion module is used to perform text conversion based on the table-specific content and the task configuration through a pre-trained large model to generate corresponding output text.

[0079] Furthermore, it also includes:

[0080] A history text module, used to obtain the history generation records, take the selected history output text as sub-parts and perform the merge operation;

[0081] The comprehensive text module is used to obtain the priority setting of each of the sub-parts and generate a comprehensive text based on the merged text content according to the priority.

[0082] Furthermore, the table selection module is specifically used to:

[0083] Acquire speech, convert it into corresponding text through speech recognition technology, and extract the table selection information based on the text;

[0084] The input text is acquired through the text box, and the table selection information is extracted based on the text.

[0085] The above-mentioned table-generated text processing system implements the steps and various processes of the above-mentioned table-generated text processing method embodiment and can achieve the same technical effect. To avoid repetition, they are not described here.

[0086] See also Figure 6, corresponding to the embodiment of the processing method for generating text from a table mentioned above, an embodiment of the present application provides an electronic device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of the embodiment of the processing method for generating text from a table mentioned above and the various processes of the embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0087] The memory 1009 can be used to store software programs and various data. The memory 1009 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instructions required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory 1009 may include a volatile memory or a non-volatile memory, or the memory 1009 may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM). The memory 1009 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0088] The processor 1010 may include one or more processing units; optionally, the processor 1010 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor 1010.

[0089] Corresponding to the above-mentioned embodiment of the processing method for generating text from a table, the embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by the processor, the steps of the embodiment of the processing method for generating text from a table and the various processes of the embodiment are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0090] The processor is the processor in the electronic device described in the above embodiment of the present application. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0091] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0092] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0093] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A method for processing text generated from a table, characterized in that: include: Acquiring voice and / or text input, extracting form selection information for determining form-specific content, and determining the form-specific content; Extracting task information for defining task type and task control according to the voice and / or text input, and determining task configuration; Based on the table-specific content and the task configuration, text conversion is performed through a pre-trained large model to generate corresponding output text.

2. The method for processing text generated from a table according to claim 1, characterized in that: Also includes: Get the historical generation record, take the selected historical output text as subparts and perform a merge operation; The priority setting of each of the sub-parts is obtained, and a comprehensive text is generated based on the merged text content according to the priority.

3. The method for processing text generated from a table according to claim 1, characterized in that: The obtaining of voice and / or text input and extracting table selection information for determining specific content of the table specifically includes: Acquire speech, convert it into corresponding text through speech recognition technology, and extract the table selection information based on the text; The input text is acquired through the text box, and the table selection information is extracted based on the text.

4. The method for processing text generated from a table according to claim 1, characterized in that: The determining of the specific content of the form also includes: Directly select specific content of the table through the interface tool; The specific content of the table is determined by combining voice input and interface tool selection and / or the specific content of the table is determined by combining text input and interface tool selection.

5. The method for processing text generated from a table according to claim 1, characterized in that: The determining of task configuration further includes: The task configuration is determined by a control component and / or by selecting from a predefined tag list or inputting a custom tag.

6. A system for processing text generated from a table, characterized in that: include: a form selection module, for acquiring voice and / or text input, extracting form selection information for determining form-specific content, and determining the form-specific content; A task configuration module, for extracting task information for defining task type and task control according to the voice and / or text input, and determining task configuration; The text conversion module is used to perform text conversion based on the table-specific content and the task configuration through a pre-trained large model to generate corresponding output text.

7. The table-generated text processing system according to claim 6, characterized in that: include: Also includes: A history text module, used to obtain the history generation records, take the selected history output text as sub-parts and perform the merge operation; The comprehensive text module is used to obtain the priority setting of each of the sub-parts and generate a comprehensive text based on the merged text content according to the priority.

8. The table-generated text processing system according to claim 6, characterized in that: The table selection module is specifically used for: Acquire speech, convert it into corresponding text through speech recognition technology, and extract the table selection information based on the text; The input text is acquired through the text box, and the table selection information is extracted based on the text.

9. An electronic device, characterized in that: The electronic device comprises: a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, the steps of the method for processing text generated from a table as claimed in any one of claims 1 to 5 are implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a program or an instruction, and when the program or the instruction is executed by a processor, the steps of the method for processing a table to generate a text as claimed in any one of claims 1 to 5 are implemented.

Images