Table processing method and apparatus, and computer program product

Abstract

The invention relates to a table processing method and device and a computer program product. The method comprises the following steps: in response to a triggering operation on to-be-processed data, analyzing a preset number of first contents in the to-be-processed data, and determining at least one item title; respectively inputting sub-contents obtained by classifying contents in the to-be-processed data into cells corresponding to the item titles to obtain a target table; wherein the number of the sub-contents in each content is the same as the number of the item titles. Compared with a manual input mode, the data input efficiency can be improved; compared with classified entry based on a fixed identifier, data entry can be performed in combination with semantic information of the content and based on context information of the content, so that the accuracy of table entry is improved.

Description

Technical Field

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

[0002] As the functions of electronic devices become more and more abundant, more and more electronic devices have table processing functions to process different data in various usage scenarios. For example, various types of content can be classified and counted.

[0003] In the related art, after collecting the data, if you want to classify different data into a table, you need to enter the data manually or classify and enter based on a fixed identifier in the data. Manual data entry is only suitable for a small amount of data and has low data processing efficiency. Entry through fixed identifiers will result in low accuracy or the entry results will not be consistent with expectations. Summary of the invention

[0004] In order to overcome the problems existing in the related art, the present disclosure provides a table processing method, device and computer program product to improve the efficiency and accuracy of classifying and entering data into a table.

[0005] According to a first aspect of an embodiment of the present disclosure, a table processing method is provided, including:

[0006] In response to a triggering operation on the data to be processed, analyzing a preset number of first contents in the data to be processed to determine at least one item title;

[0007] Enter the sub-contents obtained by classifying each content in the data to be processed into the cells corresponding to each of the project titles to obtain a target table;

[0008] The number of the sub-contents in each of the contents is the same as the number of the project titles.

[0009] According to a second aspect of an embodiment of the present disclosure, there is provided a table processing device, including:

[0010] A first analysis module is configured to analyze a preset number of first contents in the data to be processed in response to a trigger operation on the data to be processed, and determine at least one project title;

[0011] An input module is configured to input sub-contents obtained by classifying each content in the data to be processed into cells corresponding to each of the project titles to obtain a target table;

[0012] The number of the sub-contents in each of the contents is the same as the number of the project titles.

[0013] According to a third aspect of the present disclosure, an electronic device is provided, including:

[0014] processor;

[0015] a memory for storing processor-executable instructions;

[0016] The processor executes the computer program or instructions to implement the steps of any one of the methods in the first aspect above.

[0017] According to a fourth aspect of an embodiment of the present disclosure, a non-temporary computer-readable storage medium is provided, wherein the storage medium stores a computer program or instructions. When the computer program or instructions in the storage medium are executed by a processor, the steps of the method described in any one of the first aspects are implemented.

[0018] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided, including a computer program or an instruction, wherein when the computer program or the instruction is executed by a processor, the steps of the method described in any one of the first aspects are implemented. The technical solution provided by the embodiment of the present disclosure may include the following beneficial effects:

[0019] When a trigger operation on the data to be processed is detected, the present invention can analyze a preset number of first contents in the data to be processed, determine at least one project title, and enter the sub-contents obtained by classifying each content in the data to be processed into the cells corresponding to each project title, so as to obtain a target table, wherein the number of sub-contents in each content is the same as the number of project titles.

[0020] In the process of entering data into a table, the project title can be determined based on semantic analysis of a preset number of first contents, and the sub-content obtained by classifying each content can be entered into the cell corresponding to each project title. On the one hand, compared with manual entry, the efficiency of data entry can be improved; on the other hand, compared with classification entry based on fixed identifiers, data entry can be performed based on the contextual information of the content in combination with the semantic information of the content, thereby improving the accuracy of table entry.

[0021] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0023] Figure 1The following is a flow chart of a table processing method according to an exemplary embodiment. Figure 1 .

[0024] Figure 2 is a schematic diagram of a classification result according to an exemplary embodiment Figure 1 .

[0025] Figure 3 is a schematic diagram of a classification result according to an exemplary embodiment Figure 2 .

[0026] Figure 4A The first table is shown according to an exemplary embodiment. Figure 1 .

[0027] Figure 4B The first table is shown according to an exemplary embodiment. Figure 2 .

[0028] Figure 5 is a schematic diagram of a first page and a second page according to an exemplary embodiment.

[0029] Figure 6 The following is a flow chart of a table processing method according to an exemplary embodiment. Figure 2 .

[0030] Figure 7 The figure is a block diagram of a table processing device according to an exemplary embodiment.

[0031] Figure 8 The diagram is a schematic structural diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0032] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0033] Figure 1 A table processing method according to an exemplary embodiment is shown in FIG. Figure 1 .like Figure 1 As shown, the method mainly includes the following steps:

[0034] In step 101, in response to a trigger operation on the data to be processed, a preset number of first contents in the data to be processed are analyzed to determine at least one item title;

[0035] In step 102, the sub-contents obtained by classifying each content in the data to be processed are respectively entered into the cells corresponding to each project title to obtain a target table; wherein the number of sub-contents in each content is the same as the number of project titles.

[0036] It should be noted that the table processing method proposed in the present disclosure can be applied to electronic devices or servers. Here, electronic devices may include: terminal devices, such as mobile terminals or fixed terminals. Among them, mobile terminals may include: mobile phones, tablet computers, laptop computers, etc. Fixed terminals may include: desktop computers, smart TVs, etc. As a type of computer, a server can provide computing or application services for other clients (such as computers, terminal devices such as smart phones, and even large devices such as train systems) in the network.

[0037] The table processing method in the embodiment of the present disclosure may be configured in a table processing device, and the table processing device may be set in a server, or may also be set in an electronic device, which is not limited in the embodiment of the present disclosure.

[0038] It should be noted that the execution subject of the embodiments of the present disclosure may be, for example, a central processing unit (CPU) in a server or electronic device in terms of hardware, or may be, for example, a related background service in a server or electronic device in terms of software, without limitation.

[0039] In some embodiments, the data to be processed may be any type of data. Exemplarily, the data to be processed may include text content and / or non-text content. For example, the data to be processed may include at least one of the following: data in text format, data in file format, data in picture format, data in video format, and data in graphic format.

[0040] In some embodiments, the data to be processed is the content of at least one cell in a table. The data to be processed may include at least one of the following: text content in a table and / or an inserted object in a table. The text content may be the content in any cell in a table, and the inserted object may be any type of object inserted into the table, and the inserted object may be different types of objects such as files, pictures, videos, graphics, formulas, etc. In some embodiments, the text content and the inserted object may exist in the same cell or in different cells.

[0041] It should be noted that the text content is composed of characters, and may include at least one of words, sentences and paragraphs, wherein the characters may include: letters, numbers, punctuation marks, etc., and each text sub-content in the text content may be arranged according to preset grammatical and semantic rules. For example, the data to be processed may be text in a table content, wherein the table content may be content including at least part of a table element. A table element is a basic unit constituting a table, for example, a table element may be any cell in a table, and the arbitrary cell may be a row or column in the table. Exemplarily, in the case where the content is located in a cell in a table, it may be determined that the content is a table content. Again exemplarily, in the case where the content is located in a row or a column of a table, it may be determined that the content is a table content. In other embodiments, the data to be processed may be data determined from a document. For example, the data to be processed may be data determined from a document in an image format; or the data to be processed may be data determined from a document in a text format (text document); or the data to be processed may be data determined from a document in a table format (table document). Among them, text documents are mainly text-based and are used to record and transmit information, mainly focusing on the expression of text content. Table documents mainly organize data in table form and are used to process and analyze data.

[0042] In some embodiments, in response to a trigger operation on an initial document, data to be processed may be determined from the initial document. For example, when a trigger operation on an initial document is detected, the area on which the trigger operation acts may be determined, and based on the area on which the trigger operation acts, data to be processed may be determined from the initial document. For example, if the initial document is a table document, the trigger operation acting on the table document may be an operation on a target cell in the table document, such as a selection operation on the target cell.

[0043] It should be noted that the target cell may be a cell in the initial document or multiple cells in the initial document. For example, it may be a column of cells in the initial document, or a row of cells in the initial document, or multiple cells distributed in the same area in the initial document. In some embodiments, when an operation on the target cell is detected, the content in the target cell may be determined as data to be processed.

[0044] In some embodiments, in response to a trigger operation on an initial document, data to be processed can be determined from the initial document, including: in response to a trigger operation on the initial document, determining whether the initial document includes table content; if the initial document includes table content, determining the data to be processed from the table content of the initial document.

[0045] It should be noted that the table content in the initial document can be in image format or table format. Taking the case where the table content in the initial document is in image format as an example, the table content can be converted first to obtain table content in table format, and then the data to be processed is determined based on the triggering operation of the table content in table format.

[0046] In some embodiments, the trigger operation may be a touch operation initiated based on the data to be processed. For example, a preset control may be displayed on a page displaying the data to be processed, and when an operation acting on the preset control is detected, it is determined that a trigger operation is detected. The operation acting on the preset control may be a click operation, a long press operation, a sliding operation, etc. on the preset control.

[0047] In the embodiment of the present disclosure, when a trigger operation on the data to be processed is detected, a preset number of first contents in the data to be processed may be analyzed to determine at least one project title. Here, the project titles may be arranged in the header of the table.

[0048] In some embodiments, a preset number of first contents in the data to be processed can be input into a pre-trained target model to determine at least one project title. The target model can be a pre-trained analysis model. The target model can be used to analyze different types of content, for example, at least one of the following can be analyzed: content in text format, content in file format, content in picture format, content in video format, content in graphic format, etc. The analysis model may include: an Artificial Intelligence Generated Content (AIGC) model, a pre-trained language based on a Transformer architecture (Generative Pre-trained Transformer, GPT) model, or a neural network model, such as a recurrent neural network (RNN), a long short-term memory network (LSTM), etc.

[0049] Exemplarily, after the first content is input into the target model, the first content may be semantically understood based on the target model, the context information of each sub-content in the first content may be determined, and based on the context information of each sub-content in the first content, the intention information of each sub-content may be determined, and the project title may be determined based on the intention information. The project title may be the category name of each sub-content.

[0050] Taking the preset quantity of 3 as an example, the first content is "300 pure cotton towels for 1,200 yuan", and the corresponding sub-contents are "pure cotton towels", "300 pieces", and "1,200 yuan"; the first content is "200 sets of ceramic bowls and plates for 2,000 yuan", and the corresponding sub-contents are "ceramic bowls and plates", "200 sets", and "2,000 yuan"; the first content is "100 plastic storage boxes for 500 yuan", and the corresponding sub-contents are "plastic storage boxes", "100 pieces", and "500 yuan". After semantic analysis of each first content, three item titles can be determined, and the item titles are "goods", "quantity", and "total price".

[0051] After obtaining the titles of each project, the sub-contents obtained by classifying each content in the data to be processed can be entered into the cells corresponding to each project title to obtain the target table. In some embodiments, the composition structure of each content is the same, and the number of sub-contents in each content is the same as the number of project titles. Among them, the composition structure of the content is used to indicate the various parts (sub-contents) that constitute the content and the relationship between each part (sub-content), and jointly determine the arrangement rules of each sub-content. Exemplarily, the first content "180 memory foam pillows for 3,600 yuan" and the first content "250 scented candles for 1,500 yuan" have the same composition structure, and the sub-contents in each first content are 3, and the number of corresponding determined project titles is also 3. As another example, if the composition structure of the two contents is text + picture, it can be determined that the composition structure of the two contents is the same.

[0052] It should be noted that the preset number can be determined as needed, and can be at least part of all the data in the data to be processed. In some embodiments, the content before the preset number of data to be processed can be determined as the first content, or the content after the preset number of data to be processed can be determined as the first content, or a preset number of contents randomly determined from the data to be processed can be determined as the first content. Exemplarily, if there are 100 lines of content in the data to be processed, the first content can be the first 5 lines of the data to be processed, or the last 5 lines of the data to be processed, or 5 random lines in the data to be processed.

[0053] In other embodiments, a preset number of contents may be determined from the data to be processed based on the attribute information of each content in the data to be processed, and the preset number of contents may be determined as the first content. The attribute information of the content includes at least one of the following: the type of the content, the number of sub-contents in the content, the length of the content, etc. Exemplarily, based on the type of each content in the data to be processed, a preset number of contents belonging to different types may be determined from the data to be processed, and the preset number of contents may be determined as the first content.

[0054] Due to the randomness of the selected content or the content with different attribute information, the selected content is representative of the data to be processed, so that based on the analysis results of a small number of data to be processed, the determined project titles and the classification methods obtained by analysis can be applied to all data to be processed.

[0055] In the disclosed embodiment, by selecting a portion of the data to be processed for analysis and determining the project title, the workload of data analysis can be reduced, thereby improving the efficiency of data analysis. Determining the first content from the data to be processed by different methods can not only improve the flexibility of data processing, but also make the selected first content more representative of the attributes of the data to be processed and meet user needs.

[0056] In some embodiments, when the data to be processed only includes text content, each text content in the data to be processed can be segmented to obtain text sub-contents. After obtaining each text sub-content, each text sub-content can be entered into a cell corresponding to each project title based on the category of each text sub-content. Exemplarily, each text content can be segmented based on a preset segmentation rule, for example, the text content can be segmented based on spaces, punctuation marks, etc., and then each text sub-content can be classified based on the segmentation result.

[0057] In other embodiments, each content in the data to be processed may be classified based on a preset classification rule to obtain sub-contents of each content. Exemplarily, each content may be classified by a fixed identifier, such as by separators, Chinese and English, etc. Figure 2 and Figure 3 As shown, the content can be classified based on numbers. For example, in "No. 456 XXX Road, XXX Building, 15th Floor, Room 1508", the numbers are detected and the columns are separated, and "XXX Road", "456", "No. XXX Building", "15", "Floor", "1508", "Room" can be obtained. In "300 pure cotton towels for 1200 yuan", the numbers are detected and the columns are separated, and "pure cotton towels", "300", "pieces", "1200", "yuan" can be obtained.

[0058] In other embodiments, each content in the data to be processed can be classified based on the target model to obtain sub-contents of each content. Exemplarily, each content in the data to be processed can be input into a pre-trained target model to obtain sub-contents of each content. The target model can be a semantic analysis model such as a content generation model.

[0059] In other embodiments, when the data to be processed includes content with different types of sub-contents, it can also be classified according to the type of each sub-content. Exemplarily, for the data of the inserted object, placeholders can be used to represent it. For example, if a column of cells contains only graphic and text structures, it can be split into one column for pictures and one column for text. Before inputting the data to be processed into the target model, the text content of preset types in the data to be processed can be converted. On the one hand, this is to simplify the data to be processed and reduce the classification time of the target model. On the other hand, it is to make the data to be processed meet the input requirements of the target model, such as some target models only support text input. For example, in the case where the target model only supports text input, the content in the cell is Figure 8 If the image and text in the content are [img], the sub-content in the content can be expressed as: Figure 8 , and then passed to the target model, where [img] represents the placeholder of the image. If the target model supports multimodal forms, the data to be processed can be directly input into the target model.

[0060] In some embodiments, after the sub-contents are classified, the sub-contents can be respectively entered into the cells corresponding to the project titles in the created table, and / or the sub-contents can be respectively entered into the corresponding cells in the table created based on the project titles.

[0061] Taking the example of entering each sub-content into the cell corresponding to each item title in the created table, it can be determined whether the table that needs to enter information is indicated based on the trigger operation of the data to be processed. Exemplarily, a preset control can be displayed on the page displaying the data to be processed, and the trigger operation can be performed based on the preset control. For example, in the case where an operation acting on the preset control is detected, it is determined that the trigger operation is detected, and the table that needs to enter information can be selected based on the operation acting on the preset control.

[0062] In other embodiments, the trigger operation may also be a collection of a series of operations. For example, after detecting a selection operation acting on the data to be processed, at least one preset control may be displayed based on the selection operation. When an operation acting on a target control in at least one preset control is detected, it is determined that the trigger operation is detected, and a table requiring information entry is selected based on the target control. For example, each preset control may correspond to a different table, wherein the target control may be a control corresponding to the table requiring information entry.

[0063] Taking the example of entering each sub-content into the corresponding cell in the table created based on each project title, after obtaining each project title, a table can be created based on each project title, and each sub-content can be entered into the table created based on each project title.

[0064] When a trigger operation on the data to be processed is detected, the present invention can analyze a preset number of first contents in the data to be processed, determine at least one project title, and enter the sub-contents obtained by classifying each content in the data to be processed into cells corresponding to each project title, respectively, to obtain a target table, wherein the composition structure of each content is the same, and the number of sub-contents in each content is the same as the number of project titles.

[0065] In the process of entering data into a table, the project title can be obtained based on semantic analysis of a preset number of first contents, and the sub-content obtained by classifying each content can be entered into the cell corresponding to each project title. On the one hand, compared with the manual entry method, the efficiency of data entry can be improved; on the other hand, compared with classification entry based on fixed identifiers, data entry can be performed based on the contextual information of the content in combination with the semantic information of the content, thereby improving the accuracy of table entry.

[0066] In some embodiments, analyzing a preset amount of first content in the data to be processed further includes:

[0067] Classify the first contents based on a preset classification rule to obtain first sub-contents of each first content;

[0068] Determining a degree of match between a first sub-content of a first content and the intent information indicated by the first content;

[0069] The sub-contents obtained by classifying each content in the data to be processed are entered into the cells corresponding to each item title to obtain the target table, including:

[0070] Based on the classification method corresponding to the matching degree, the sub-contents obtained by classifying each content in the data to be processed are respectively entered into the cells corresponding to each item title to obtain the target table.

[0071] In some embodiments, before a trigger operation on the data to be processed is detected, the first content can be classified based on a preset classification rule to obtain the first sub-content of each first content. Alternatively, after a trigger operation on the data to be processed is detected, each first content in the data to be processed is classified based on a preset classification rule to obtain the first sub-content of each first content. The preset classification rule may be a classification rule determined by a user, or one or more classification rules selected randomly, or a classification rule selected based on preset feature data in a preset number of data to be processed, and the preset feature data may be a fixed identifier used to separate sub-contents in each content in the data to be processed, such as, "," "-", ";" or a space, etc.

[0072] In some embodiments, while the first content is classified based on a preset classification rule to obtain the first sub-content of each first content, the first content is analyzed based on the target model to obtain the project title; or, while the first content is classified based on the target model to obtain the second sub-content of each first content, the first content is analyzed based on the target model to obtain the project title; or before the first content is classified based on the preset classification rule to obtain the first sub-content of each first content, the first content is analyzed based on the target model to obtain the project title, etc., as long as the analysis of the first content in the processed data can be achieved and the corresponding results can be obtained, the execution order of each step is not specifically limited here.

[0073] In one embodiment, the first content is analyzed based on the target model to obtain a project title, which may be a first sub-content obtained by classifying the first content and / or the first content based on a preset classification rule, and a prompt word is constructed. The prompt word is input into the target model for analysis to obtain the project title.

[0074] For example, the first sub-content (input1) obtained based on the preset classification rules of the first content in the data to be processed can be determined, spliced ​​in prompt word 1 (prompt1) and transmitted to the preset model (large model, such as the target model mentioned above), and then analyzed by the preset model to obtain the project title.

[0075] Exemplarily, prompt 1 may include data to be processed, processing requirements, output requirements, reference data, etc.

[0076] For example, prompt 1 (prompt1) can be composed of: ****{^input1^}****, task: summarize the project title of the above data, refer to the following information output#reference format: {"split_table_header":"xxx|xx|xx|..."}, #reference example****The data of the project title to be summarized:```json{"split_table_content":["Zhejiang Province|Hangzhou City|XX District|XX Building, 11th Floor, Room 1101, XX Road","Jiangsu Province|Nanjing City|XX District|XX Community, No. 11 XXX Road, Room 101, Building 1",]}```, ****The corresponding project title is:```json{"split_table_header":"Province|City|Region|Detailed Address"}```.

[0077] Among them, "****{^input1^}****" can be the first sub-content or the first content obtained by the first content in the data to be processed based on the preset classification rules; {"split_table_header":"xxx|xx|xx|..."} is the output format, which means outputting multiple item titles separated by "|".

[0078] It should be noted that the process of determining the degree of match between the first sub-content of the first content and the intent information indicated by the first content can be carried out simultaneously with the process of determining the project title, that is, the degree of match between the first sub-content of the first content and the intent information indicated by the first content can be determined while determining the project title; the degree of match between the first sub-content of the first content and the intent information indicated by the first content can also be determined before determining the project title; or the degree of match between the first sub-content of the first content and the intent information indicated by the first content can also be determined after determining the project title, and no specific limitation is made here.

[0079] The first sub-content is used to distinguish from the second sub-content. The first sub-content may be a sub-content obtained by classifying the content based on a preset classification rule, and the second sub-content may be a sub-content obtained by semantically analyzing the content and classifying it based on the semantic analysis result.

[0080] It should be noted that the preset classification rules may include at least one of the following: a classification rule based on a fixed identifier, wherein the fixed identifier may include a separator, Chinese or English, etc.; a classification rule based on a character extraction function, wherein the character extraction function may include a LEFT function, a RIGHT function, a MID function, etc.; a classification rule through a pre-configured classification function. In other embodiments, the preset classification rule may also be a user-defined classification rule. Taking the sorting of the data to be processed as an example, the preset classification rule may be a user-defined sorting rule.

[0081] In the embodiment of the present disclosure, after obtaining the first sub-content of the first content, the degree of matching between the first sub-content of the first content and the intention information indicated by the first content may be determined.

[0082] Exemplarily, the first sub-content of the first content and the first content may be input into a preset model, and the degree of match between the first sub-content of the first content and the intent information indicated by the first content may be determined based on the preset model. The preset model may include: an AIGC model, a GPT model based on a Transformer architecture, or a neural network model, such as a recurrent neural network, a long short-term memory network, etc. It should be noted that the preset model may be the same model as the target model in the above embodiment, or may be a separately trained model for determining the matching result.

[0083] In some embodiments, the degree of match between the first sub-content of the first content and the intent information indicated by the first content may be determined based on the correlation between the semantic information of the first sub-content of the first content and the intent information indicated by the first content. The degree of match between the first sub-content of the first content and the intent information indicated by the first content is positively correlated with the correlation between the semantic information of the first sub-content of the first content and the intent information indicated by the first content, that is, the greater the correlation, the higher the degree of match, and the smaller the correlation, the lower the degree of match.

[0084] Exemplarily, after the first sub-content of the first content and each first content are input into a preset model, the correlation between the semantic information of the first sub-content of the first content and the intent information indicated by the first content can be determined based on the preset model. Exemplarily, when the correlation between the semantic information of the first sub-content of the first content and the intent information indicated by the first content is less than a preset threshold, it is determined that the first sub-content of the first content and the intent information indicated by the first content have a first degree of match; when the correlation between the semantic information of the first sub-content of the first content and the intent information indicated by the first content is greater than or equal to a preset threshold, it is determined that the first sub-content of the first content and the intent information indicated by the first content have a second degree of match, wherein the first degree of match is less than the second degree of match.

[0085] The above is an exemplary description of determining the degree of match between the first sub-content of the first content and the intent information indicated by the first content. In other embodiments, the degree of match between the first sub-content of the first content and the intent information indicated by the first content may also be determined in other ways. For example, the degree of match between the first sub-content of the first content and the intent information indicated by the first content may be determined by determining whether the number of characters in the first content is the same as the number of characters in all the first sub-contents, etc., which will not be listed here one by one.

[0086] In the embodiment of the present disclosure, after determining the degree of match between the first sub-content of the first content and the intent information indicated by the first content, the sub-contents obtained by classifying each content in the processed data can be entered into the cells corresponding to each item title based on the classification method corresponding to the matching degree to obtain a target table. The corresponding classification method can be set according to different matching degrees, and the classification method can be associated with the matching degree to improve the accuracy of classification.

[0087] In some embodiments, based on the classification method corresponding to the matching degree, the sub-contents obtained by classifying each content in the data to be processed are respectively entered into the cells corresponding to each item title to obtain a target table, including:

[0088] When the matching degree is greater than a preset threshold, classifying each content in the data to be processed based on a preset classification rule to obtain a first sub-content of each content;

[0089] Enter the first sub-content of each content into the cells corresponding to each item title to obtain the target table.

[0090] Exemplarily, when the matching degree is high, the preset classification rule is determined as the classification method corresponding to the matching degree; when the matching degree is low, the semantic classification rule can be determined as the classification method corresponding to the matching degree. In other embodiments, different classification rules can also be superimposed so that the superimposed classification rule corresponds to the matching degree, such as the semantic rule and the fixed identifier classification rule are superimposed and used, which is not specifically limited here.

[0091] Taking the case where the triggering operation for the data to be processed is a click operation triggered by the user, and the data to be processed is arranged in the form of rows as an example, after detecting the click operation, the intelligent column sorting function can be triggered. After the intelligent column sorting function is triggered, the first content (input1) can be determined, and the first sub-content (input2) of each first content can be obtained, and the first sub-content and the first content of each first content can be spliced ​​in the prompt word 2 (prompt2) and transmitted to the preset model (large model, such as the target model mentioned above), and then the preset model determines whether the first sub-content (input2) of each first content is reasonable (whether the sorting result is reasonable), that is, determines the matching degree of the first sub-content of the first content and the intention information indicated by the first content, and then determines whether the first sub-content of each first content matches the intention information indicated by the first content based on the matching degree, and outputs the corresponding result.

[0092] Exemplarily, prompt 2 may include data to be processed, processing requirements, output requirements, reference data, etc.

[0093] For example, prompt 2 (prompt2) may include: data before classification {^input1^}# data after classification {^input2^}# output format: {"Reasoning": "Brief description of the judgment logic, for example: because of xxx, it is judged to be reasonable / unreasonable, there is a better classification method / no better classification method", "Conclusion": "The classification is reasonable, but there is a better classification method, output "0", "The classification is reasonable, and there is no better classification method, output "1", "The classification is unreasonable, output "0"}```.

[0094] In some embodiments, if the first sub-content of each first content matches the intention information indicated by the first content (the degree of match is greater than a preset threshold), that is, the classification result is reasonable, then "1" can be output; if the first sub-content of each first content does not match the intention information indicated by the first content (the degree of match is less than or equal to the preset threshold), that is, the classification result is unreasonable or the classification result is reasonable, but there is a better classification rule, then "0" can be output.

[0095] It should be noted that the degree of match greater than the preset threshold may mean that the degree of match between any first sub-content and the first content is greater than the preset threshold. Exemplarily, the degree of match between all first sub-contents in the first content and the first content is greater than the preset threshold, or the degree of match between any number of first sub-contents in the first content and the first content is greater than the preset threshold. The degree of match less than or equal to the preset threshold may mean that the degree of match between any first sub-content and the first content is greater than the preset threshold. Exemplarily, the degree of match between all first sub-contents in the first content and the first content is less than or equal to the preset threshold, or the degree of match between any number of first sub-contents in the first content and the first content is less than or equal to the preset threshold.

[0096] Taking the preset number of 5 as an example, the first 5 contents of the data to be processed (sorted data) (e.g., the first 5 rows of the data to be processed) can be used as input1, and the result of sorting the first 5 rows according to the preset classification rules can be used as input2, which are spliced ​​as input in the above prompt2, and the rationality of the sorting result according to the preset classification rules is judged by artificial intelligence AI. If the sorting is reasonable (the matching degree is greater than the preset threshold), the preset classification rules are used for sorting; if the sorting is unreasonable (the matching degree is less than or equal to the preset threshold), the target model is used for sorting.

[0097] In the embodiment of the present disclosure, when the first sub-content of each first content matches the intention information indicated by the first content, the first sub-content of each content obtained based on the preset classification rules can be directly entered into the cells corresponding to each item title to obtain the target table, which can improve the efficiency of obtaining the target table.

[0098] In some embodiments, based on the classification method corresponding to the matching degree, the sub-contents obtained by classifying each content in the data to be processed are respectively entered into the cells corresponding to each item title to obtain a target table, including:

[0099] When the matching degree is less than or equal to a preset threshold, based on analyzing a preset number of first contents, the first contents are classified to obtain second sub-contents of the first contents;

[0100] Based on the second sub-contents of the first contents, the second contents except the first contents in the data to be processed are analyzed to obtain a target table.

[0101] It should be noted that, when the first sub-content of the first content does not match the intention information indicated by the first content (the degree of match is less than or equal to the preset threshold), it means that the classification of the data to be processed based on the preset classification rule is unreasonable, or there is an alternative classification rule with higher accuracy than the preset classification rule. Taking the data to be processed as data in office software as an example, if it is determined based on the matching result that there is an alternative classification rule with higher accuracy than the preset classification rule, "0" can be output. After receiving this information, the office software can initiate a new request again to obtain the second sub-content of the first content by analyzing the first content based on the target model.

[0102] Specifically, for example, the first content (input1) in the data to be processed can be determined, prompt word 3 (prompt3) can be constructed and transmitted to a preset model (large model, such as the target model mentioned above), and then the first content is analyzed by the preset model to obtain the second sub-content of the first content.

[0103] Exemplarily, prompt 3 may include data to be processed, processing requirements, output requirements, reference data, etc.

[0104] For example, prompt 3 may consist of: ****{^input1^}****Task: Classify the above data and refer to the following information output#Reference format: {"split_table_header":"xxx|xx|xx|...","split_table_content":["xx|xxx|xx|...","xxx|xx|xx|...","xx|xx|xxx|..."]}#Reference content: ****{^input2^}****.

[0105] Among them, "****{^input1^}****" may correspond to the first content in the data to be processed; ****{^input2^}**** is the reference content. When the reference content is empty, it indicates that no reference content has been input.

[0106] In other embodiments, the reference content can also be set according to the needs of the user, for example, it can be set as: data to be classified: ****"address information","Room 1101, 11th Floor, Digital Building, No. 111, XX Road, XX District, Hangzhou City, Zhejiang Province","Room 101, Building 1, XX Community, No. 11, XXX Road, XX District, Nanjing City, Jiangsu Province",****Classified data:```json{"split_table_header":"Province|City|Region|Detailed address","split_table_content":["Zhejiang Province|Hangzhou City|XX District|XX Building, No. 111, XX Road, Room 1101, 11th Floor","Jiangsu Province|Nanjing City|XX District|XX Community, No. 11, XXX Road, Room 101, Building 1, XX Community",]}.

[0107] In addition, "split_table_header" in prompt3 indicates that the item title is obtained by analysis, so prompt3 can simultaneously analyze and obtain the second sub-content and the corresponding item title.

[0108] Taking the preset number of 5 as an example, the first content in the data to be processed can be taken as input1 and spliced ​​as input in the above prompt3, and the first content in the data to be processed can be sorted using the target model to obtain the second sub-content of the first content.

[0109] After obtaining the second sub-content of the first content, it can be provided to the user for preview. When the user determines the classification result, or the classification result is determined after the second sub-content of the first content is modified, it can be considered that the user approves the classification result. The second sub-content of the first content or the modified second sub-content of the first content can be used as input2 in the above prompt3, that is, as reference content for classification.

[0110] Specifically, for the second sub-content based on each of the first contents, the second content in the data to be processed except the first content is analyzed to obtain the step of the target table, which may be: changing input1 in prompt3 to the second content in the data to be processed, changing input2 to the second sub-content of the first content or the second sub-content of the modified first content, and inputting the changed prompt3 into the target model for analysis to obtain the second sub-content of the second content in the data to be processed, then obtaining the second sub-content of each content (first content and second content) in the data to be processed, and entering them into the cells corresponding to each of the item titles respectively to obtain the target table.

[0111] In other embodiments, the sub-contents obtained by classifying each content in the processed data based on the alternative classification rules can be respectively entered into the cells corresponding to each item title to obtain the target table. The accuracy of the alternative classification rules is higher than the accuracy of the preset classification rules.

[0112] When the preset classification rules are unreasonable for classifying the processed data or there are alternative classification rules with higher accuracy than the preset classification rules, the first contents can be classified based on the analysis of a preset number of first contents, or the first contents can be classified according to the alternative classification rules to obtain the second sub-contents of the first contents, and a target table can be obtained based on the second sub-contents of each first content, thereby improving the accuracy of the obtained target table.

[0113] In some embodiments, based on the second sub-contents of the first contents, the second contents other than the first contents in the data to be processed are analyzed to obtain the target table, including:

[0114] For each first content, the second sub-content of the first content is respectively entered into the cells corresponding to the project title to obtain a first table, and the first table is displayed on the first page;

[0115] In response to the first operation on the first table, based on the analysis of the second content except the first content in the data to be processed, the second content is classified to obtain the second sub-content of the second content;

[0116] The first table is updated based on the second sub-content of the second content to obtain a target table.

[0117] In the disclosed embodiment, after obtaining the second sub-content of the first content, the second sub-content of the first content can be respectively entered into the cells corresponding to the project title to obtain a first table, and the first table is displayed on the first page. Exemplarily, if the result output by the preset model is "0", a request is initiated again, and the second sub-content of the first content is respectively entered into the cells corresponding to the project title to obtain a first table (column results), and the first table is displayed to the user as preview content.

[0118] In some embodiments, the method further includes: in response to obtaining the first table, displaying the first control on the first page; based on the touch operation acting on the first control, displaying the first table and / or a third table generated based on the first sub-content of the first content on the first page.

[0119] like Figure 4B As shown, by displaying the first control 403 on the first page, the user can freely switch to preview the first table and / or the third table through the first control 403, and then determine the accuracy of the first table and / or the third table.

[0120] For example, when a first preset operation on a first control is detected, a first table is displayed on a first page; when a second preset operation on a first control is detected, a third table is displayed on the first page; when a third preset operation on a first control is detected, the first table and the third table are displayed on the first page. The preset operation may be a click operation of different frequencies, or the preset operation may be an operation of different types.

[0121] Taking the first table as an example of sorting the data to be processed, if you select the first table and click Continue Sorting, the data to be classified (user-selected content) can be transferred to the preset model in batches. At the same time, the AI ​​results confirmed by the user when previewing the content can be used as sample data to enhance the uniformity of subsequent output.

[0122] In some embodiments, the method further includes: in response to the second operation on the first table, adjusting the first table to obtain an adjusted first table; in response to the first operation on the first table, analyzing the second content in the processed data other than the first content, including: in response to the first operation on the adjusted first table, analyzing the second content.

[0123] Here, the adjustment of the first table may be: an operation of modifying the table content in the first table. For example, an operation of correcting the inaccurate content in the first table may be performed. Figure 4A and Figure 4B As shown, a first table 401 may be displayed on a first page.

[0124] In the disclosed embodiment, after obtaining the first table, the first table can be displayed and controlled to enter an editable state to facilitate the user to adjust the first table, thereby ensuring that the adjusted first table better meets user needs, supporting users to modify the column results as samples, indicating the column format expected by the model, and flexibly outputting expected results.

[0125] In response to a first operation on the first table or the adjusted first table, a second content other than the first content in the data to be processed is analyzed. The first operation may be a confirmation operation on the first table. Figure 4A and Figure 4B As shown, a confirmation control 402 may be displayed on the first page, and the confirmation control 402 may be identified. For example, the confirmation operation may be identified based on "continue sorting".

[0126] Exemplarily, after a first operation on the confirmation control is detected, second content other than the first content in the data to be processed is analyzed.

[0127] The present disclosure analyzes the second content, classifies the second content, obtains the second sub-content of the second content, and updates the first table based on the second sub-content of the second content to obtain the target table. The process of analyzing the second content to classify the second content to obtain the second sub-content of the second content can be the same as the process of analyzing the first content to classify the first content to obtain the second sub-content of the first content.

[0128] Exemplarily, after the second content is input into the target model, the second content can be semantically understood based on the target model to determine the context information of each sub-content in the second content, and based on the context information of each sub-content in the second content, the intention information of each sub-content can be determined, and then the second content is classified to obtain the second sub-content of the second content, and the first table is updated based on the second sub-content of the second content to obtain the target table.

[0129] It should be noted that the target table is updated based on the first table, and the item titles in the target table are the item titles in the first table. Updating the first table based on the second sub-content of the second content includes: entering the second sub-content of the second content into the cells corresponding to each item title in the first table.

[0130] In the disclosed embodiment, after the second sub-content of the first content is entered into the cells corresponding to the project title to obtain the first table, the first table can be displayed on the first page for the user to preview. When the first operation on the first table is detected, the first table is updated based on the second sub-content of the second content to obtain the target table. Since the first table is the content confirmed by the user, the first table is updated based on the second sub-content of the second content to obtain the target table, which can ensure that the obtained target table meets the user's needs.

[0131] In other embodiments, after determining at least one project title based on the target model, the second content other than the first content in the processed data can be analyzed, the second content can be classified to obtain the second sub-content of the second content, and then the second sub-content of the second content and the second sub-content of the first content can be respectively entered into the cells corresponding to the project title to obtain the target table.

[0132] By obtaining the target table directly based on the second sub-content of the second content and the second sub-content of the first content, the efficiency of generating the target table can be improved.

[0133] In some embodiments, the first table is updated based on the second sub-content of the second content to obtain a target table, including: in response to obtaining each K second sub-contents of the second content, entering the K second sub-contents of the second content into the first table to obtain a second table; wherein K is less than the total number of contents in the data to be processed; and displaying the second table on the first page until all the contents in the data to be processed are traversed to obtain the target table.

[0134] The value of K can be determined as needed, for example, it can be set to 20. If the contents in the data to be processed are arranged in rows, that is, there are 100 rows of contents in the data to be processed, then K can be 20 of them. For example, the K second contents can be 200 characters. The present disclosure can obtain the results of the columns in batches by concurrently requesting multiple times, and display them to the user in real time for decision making.

[0135] By entering the second sub-content of the second content in batches and dynamically displaying the results of the batch entry (second table) on the first page, on the one hand, batch / parallel processing can alleviate the pressure of single-line data analysis and reduce the situation of machine jams or data congestion caused by excessive data processing at one time; on the other hand, it can facilitate users to view the content entry status in real time.

[0136] In some embodiments, the method also includes: displaying a prompt message on the second page based on the number of classified contents in the data to be processed and / or the total number of contents in the data to be processed; and / or displaying a second control on the second page; wherein the second control is used to start or stop classification of the data to be processed.

[0137] During batch entry of the data to be processed, prompt information may be displayed on the second page based on the number of classified contents in the data to be processed and / or the total number of contents in the data to be processed; and / or a second control may be displayed on the second page.

[0138] like Figure 5 As shown, the prompt information 501 can be displayed on the second page, and / or the second control 502 can be displayed on the second page. In some embodiments, the second page can be displayed in a floating manner on the first page; or the second page is a partial area of ​​the first page.

[0139] The prompt information can facilitate the user to timely understand the progress of text entry, and displaying the second control on the second page can enable the user to promptly start or stop the classification of the data to be processed, thereby improving the convenience and flexibility of operation.

[0140] In some embodiments, the method further includes: displaying a third control on a third page; based on a touch operation on the third control, displaying a target table obtained based on the first sub-content of each content on the third page; and / or,

[0141] The target table obtained based on the second sub-content of each content is displayed on the third page.

[0142] By displaying the third control on the third page, the user can freely switch to preview different target tables through the third control, so that the user can compare and select the corresponding table according to the needs.

[0143] Exemplarily, when the fourth preset operation on the third control is detected, the target table obtained based on the first sub-content of each content is displayed on the third page; when the fifth preset operation on the third control is detected, the target table obtained based on the second sub-content of each content is displayed on the third page; when the sixth preset operation on the third control is detected, the target table obtained based on the first sub-content of each content and the target table obtained based on the second sub-content of each content are displayed on the third page. The preset operation can be a click operation of different frequencies, or the preset operation can be an operation of different types.

[0144] In other embodiments, when a target table obtained based on a first sub-content of each content is detected, the target table obtained based on the first sub-content of each content can be exported; and / or when a confirmation operation of a target table obtained based on a second sub-content of each content is detected, the target table obtained based on the second sub-content of each content can be exported.

[0145] In some embodiments, the method further comprises:

[0146] In response to a touch operation on the initial table, determining data to be processed from the initial table; wherein each content in the data to be processed is arranged in cells of the initial table in a row or column manner;

[0147] The sub-contents obtained by classifying each content in the data to be processed are entered into the cells corresponding to each item title to obtain the target table, including:

[0148] The sub-contents obtained by classifying each content in the data to be processed are respectively entered into the cells of the target row or target column of each item title to obtain a target table.

[0149] Taking the case where the contents in the data to be processed are arranged in the cells of the initial table in rows, since the composition structure of each content is the same, each content can be aligned and classified to obtain the sub-content of each content, and the sub-content of each content is respectively entered into the cells of the target column of each project title, thereby realizing the column division of the data to be processed. Among them, the number of columns of the target column is the same as the number of sub-contents in the content.

[0150] Taking the case where the contents in the data to be processed are arranged in the cells of the initial table in columns, since the composition structure of each content is the same, each content can be aligned and classified to obtain the sub-content of each content, and the sub-content of each content is respectively entered into the cells of the target row of each project title, thereby realizing the row division of the data to be processed. Among them, the number of target rows is the same as the number of sub-contents in the content.

[0151] In other embodiments, after the sub-contents are obtained by classifying the various contents in the data to be processed, the target row can be determined from the table to be entered. When the target row is determined, the sub-contents obtained by classifying the various contents in the data to be processed are respectively entered into the cells of the target row of each project title to obtain the target table; or, the target column can be determined from the table to be entered. When the target column is determined, the sub-contents obtained by classifying the various contents in the data to be processed are respectively entered into the cells of the target column of each project title to obtain the target table.

[0152] In some embodiments, determining a target row or a target column from a table to be entered includes: obtaining the contents of cells in each row of the table to be entered, and determining the target row from the table to be entered based on the contents of cells in each row; or obtaining the contents of cells in each column of the table to be entered, and determining the target column from the table to be entered based on the contents of cells in each column.

[0153] Exemplarily, a row without entered information is determined as a target row; or a column without entered information is determined as a target column. For example, a blank row adjacent to a row with entered information can be determined as a target row, or a blank column adjacent to a column with entered information can be determined as a target column.

[0154] As another example, the content in each row cell of the table to be entered and each sub-content may be compared, and the target row or target column may be determined based on the comparison result.

[0155] In some embodiments, when there is entered information in the cells of the target row, the entered information in the target row can be replaced based on the sub-content obtained by classifying the various contents in the data to be processed; when there is entered information in the cells of the target column, the entered information in the target column can be replaced based on the sub-content obtained by classifying the various contents in the data to be processed.

[0156] Figure 6 A table processing method according to an exemplary embodiment is shown in FIG. Figure 2 .like Figure 6 As shown, the method mainly includes the following steps:

[0157] In step 601, it is determined whether a degree of matching between a first sub-content of a first content and the intention information indicated by the first content is greater than a preset threshold.

[0158] When the degree of match between the first sub-content of the first content and the intention information indicated by the first content is greater than a preset threshold, execute step 602; when the degree of match between the first sub-content of the first content and the intention information indicated by the first content is less than or equal to the preset threshold, execute step 605.

[0159] In step 602, each content in the data to be processed is classified based on a preset classification rule to obtain the first sub-content of each content.

[0160] In step 603, the first sub-content of each content is entered into the cell corresponding to each item title.

[0161] In step 604, a target table obtained based on the first sub-content of each content is displayed.

[0162] In step 605, the second sub-content of the first content is obtained.

[0163] Here, for each of the first contents, the second sub-contents of the first contents are respectively entered into the cells corresponding to the item titles to obtain a first table.

[0164] In step 606 , a first table is displayed on a first page.

[0165] In step 607 , it is determined whether a first operation on the first table is detected.

[0166] In the case where the first operation on the first table is detected, step 608 is executed; in the case where the first operation on the first table is not detected, the current interface is stayed.

[0167] In step 608 , the first table is updated based on the second sub-content of the second content.

[0168] Here, after the first table is updated based on the second sub-content of the second content, a target table obtained based on the second sub-content of each content may be obtained.

[0169] In the disclosed embodiment, a more accurate column or row division method can be provided based on semantic analysis. On the one hand, compared with the manual entry method, the efficiency of data entry can be improved; on the other hand, compared with the classification entry based on fixed identifiers, data entry can be performed based on the contextual information of the content in combination with the semantic information of the content, thereby improving the accuracy of table entry.

[0170] Figure 7 FIG. 1 is a block diagram of a table processing device according to an exemplary embodiment. Figure 7 As shown, the table processing device 700 mainly includes:

[0171] The first analysis module 701 is configured to analyze a preset number of first contents in the data to be processed in response to a trigger operation on the data to be processed, and determine at least one project title;

[0172] An input module 702 is configured to input the sub-contents obtained by classifying each content in the data to be processed into cells corresponding to each of the project titles to obtain a target table;

[0173] The number of the sub-contents in each of the contents is the same as the number of the project titles.

[0174] In some embodiments, the first analysis module 701 is configured to:

[0175] Classify the first contents based on a preset classification rule to obtain first sub-contents of each of the first contents;

[0176] Determining a degree of match between a first sub-content of the first content and the intent information indicated by the first content;

[0177] The input module 702 is configured to:

[0178] Based on the classification method corresponding to the matching degree, the sub-contents obtained by classifying each content in the data to be processed are respectively entered into the cells corresponding to each of the project titles to obtain the target table.

[0179] In some embodiments, the input module 702 is configured to:

[0180] When the matching degree is greater than a preset threshold, classifying each content in the to-be-processed data based on the preset classification rule to obtain a first sub-content of each content;

[0181] The first sub-content of each of the contents is respectively entered into the cells corresponding to each of the item titles to obtain the target table.

[0182] In some embodiments, the input module 702 is configured to:

[0183] When the matching degree is less than or equal to a preset threshold, based on analyzing the preset number of first contents, classifying the first contents to obtain second sub-contents of the first contents;

[0184] Based on the second sub-contents of each of the first contents, the second contents except the first contents in the data to be processed are analyzed to obtain the target table.

[0185] In some embodiments, the input module 702 is configured to:

[0186] For each of the first contents, the second sub-contents of the first contents are respectively entered into the cells corresponding to the item titles to obtain a first table, and the first table is displayed on the first page;

[0187] In response to a first operation on the first table, based on an analysis of a second content in the to-be-processed data except the first content, the second content is classified to obtain a second sub-content of the second content;

[0188] The first table is updated based on the second sub-content of the second content to obtain the target table.

[0189] In some embodiments, the apparatus 700 further includes:

[0190] an adjustment module, configured to adjust the first table in response to a second operation on the first table to obtain an adjusted first table;

[0191] The input module 702 is configured to:

[0192] In response to the first operation on the adjusted first table, the second content is analyzed.

[0193] In some embodiments, the input module 702 is configured to:

[0194] In response to obtaining K second sub-contents of the second content each time, entering the K second sub-contents of the second content into the first table to obtain a second table; wherein K is less than the total number of the content in the data to be processed;

[0195] The second table is displayed on the first page until all the contents in the data to be processed are traversed to obtain the target table.

[0196] In some embodiments, the apparatus 700 further includes:

[0197] A first display module, configured to display a first control on the first page in response to obtaining the first table;

[0198] The second display module is configured to display the first table and / or a third table generated based on the first sub-content of the first content on the first page based on a touch operation acting on the first control.

[0199] In some embodiments, the apparatus 700 further includes:

[0200] A third display module is configured to display prompt information on the second page based on the number of classified contents in the data to be processed and / or the total number of contents in the data to be processed; and / or,

[0201] The fourth display module is configured to display a second control on the second page; wherein the second control is used to start or stop the classification of the data to be processed.

[0202] In some embodiments, the apparatus 700 further includes:

[0203] a fifth display module, configured to display a third control on a third page;

[0204] a sixth display module, configured to display, on the third page, a target table obtained based on the first sub-contents of each of the contents based on a touch operation acting on the third control; and / or,

[0205] A target table obtained based on the second sub-contents of each of the contents is displayed on the third page.

[0206] In some embodiments, the apparatus 700 further includes:

[0207] A determination module is configured to determine the data to be processed from the initial table in response to a touch operation on the initial table; wherein each of the contents in the data to be processed is arranged in cells of the initial table in a row or column manner;

[0208] The input module 702 is configured to:

[0209] The sub-contents obtained by classifying each content in the data to be processed are respectively entered into the cells of the target row or target column of each item title to obtain the target table.

[0210] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0211] Based on the same inventive concept, an embodiment of the present disclosure provides an electronic device, which may be a computer or a terminal in one or more of the above embodiments. Figure 8 FIG. 1 is a schematic diagram showing the structure of an electronic device according to an exemplary embodiment. Figure 8 As shown, the electronic device 800 adopts general computer hardware and includes a processor 801 , a memory 802 , a bus 803 , an input device 804 , and an output device 805 .

[0212] In some possible implementations, the memory 802 may include computer storage media in the form of volatile and / or non-volatile memory, such as read-only memory and / or random access memory. The memory 802 may store an operating system, application programs, other program modules, executable code, program data, user data, etc.

[0213] Input device 804 can be used to input commands and information to the electronic device, such as a keyboard or a pointing device, such as a mouse, trackball, touchpad, microphone, joystick, game pad, satellite TV antenna, scanner or similar device. Input device 804 can be connected to processor 801 via bus 803.

[0214] The output device 805 can be used to output information to the electronic device 800 . In addition to the monitor, the output device 805 can also be other peripheral output devices, such as a speaker and / or a printing device. The output device 805 can also be connected to the processor 801 through the bus 803 .

[0215] The electronic device 800 may be connected to a network, such as a local area network (LAN), via an antenna 806. In a networked environment, executable instructions may be stored in a remote storage device, rather than being limited to local storage.

[0216] When the processor 801 in the electronic device 800 executes the executable code or application stored in the memory 802, the electronic device 800 can implement the file processing method in the above embodiment. The specific execution process refers to the above embodiment and will not be repeated here.

[0217] The memory 802 may store information for implementing Figure 7 Executable instructions for the functions of the first analysis module 701 and the entry module 702. Figure 7 The functions / implementation processes of the first analysis module 701 and the input module 702 can be realized by Figure 8 The processor 801 in the embodiment calls the executable instructions stored in the memory 802 to implement the above-mentioned implementation process and functions.

[0218] Based on the same inventive concept, the embodiment of the present disclosure further provides a storage medium in which instructions are stored. When the instructions are executed on a computer, the table processing method in one or more of the above embodiments is executed.

[0219] Based on the same inventive concept, the embodiments of the present disclosure further provide a computer program or a computer program product. When the computer program product is executed on a computer, the computer implements the table processing method in one or more of the above embodiments.

[0220] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0221] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A table processing method, characterized in that: include: In response to a triggering operation on the data to be processed, analyzing a preset number of first contents in the data to be processed to determine at least one item title; Enter the sub-contents obtained by classifying each content in the data to be processed into the cells corresponding to each of the project titles to obtain a target table; The number of the sub-contents in each of the contents is the same as the number of the project titles.

2. The method according to claim 1, characterized in that The analyzing a preset number of first contents in the data to be processed also includes: Classify the first contents based on a preset classification rule to obtain first sub-contents of each of the first contents; Determining a degree of match between a first sub-content of the first content and the intent information indicated by the first content; The sub-contents obtained by classifying each content in the data to be processed are respectively entered into cells corresponding to each of the project titles to obtain a target table, including: Based on the classification method corresponding to the matching degree, the sub-contents obtained by classifying each content in the data to be processed are respectively entered into the cells corresponding to each of the project titles to obtain the target table.

3. The method according to claim 2, characterized in that The sub-contents obtained by classifying each content in the data to be processed based on the classification method corresponding to the matching degree are respectively entered into cells corresponding to each of the project titles to obtain the target table, including: When the matching degree is greater than a preset threshold, classifying each content in the to-be-processed data based on the preset classification rule to obtain a first sub-content of each content; The first sub-content of each of the contents is respectively entered into the cells corresponding to each of the item titles to obtain the target table.

4. The method according to claim 2, characterized in that: The sub-contents obtained by classifying each content in the data to be processed based on the classification method corresponding to the matching degree are respectively entered into cells corresponding to each of the project titles to obtain the target table, including: When the matching degree is less than or equal to a preset threshold, based on analyzing the preset number of first contents, classifying the first contents to obtain second sub-contents of the first contents; Based on the second sub-contents of each of the first contents, the second contents except the first contents in the data to be processed are analyzed to obtain the target table.

5. The method according to claim 4, characterized in that The step of analyzing the second contents except the first contents in the data to be processed based on the second sub-contents of the first contents to obtain the target table includes: For each of the first contents, the second sub-contents of the first contents are respectively entered into the cells corresponding to the item titles to obtain a first table, and the first table is displayed on the first page; In response to a first operation on the first table, based on an analysis of a second content in the to-be-processed data except the first content, the second content is classified to obtain a second sub-content of the second content; The first table is updated based on the second sub-content of the second content to obtain the target table.

6. The method according to claim 5, characterized in that The method further comprises: In response to a second operation on the first table, adjusting the first table to obtain an adjusted first table; The step of responding to the first operation on the first table and analyzing the second content of the data to be processed other than the first content includes: In response to the first operation on the adjusted first table, the second content is analyzed.

7. The method according to claim 5, characterized in that The updating of the first table based on the second sub-content of the second content to obtain the target table includes: In response to obtaining K second sub-contents of the second content each time, entering the K second sub-contents of the second content into the first table to obtain a second table; wherein K is less than the total number of the content in the data to be processed; The second table is displayed on the first page until all the contents in the data to be processed are traversed to obtain the target table.

8. The method according to claim 5, characterized in that The method further comprises: In response to obtaining the first table, displaying a first control on the first page; Based on a touch operation acting on the first control, the first table and / or a third table generated based on the first sub-content of the first content is displayed on the first page.

9. The method according to any one of claims 1 to 8, characterized in that: The method further comprises: Based on the number of classified contents in the data to be processed and / or the total number of contents in the data to be processed, displaying prompt information on the second page; and / or, A second control is displayed on the second page; wherein the second control is used to start or stop the classification of the data to be processed.

10. The method according to any one of claims 4 to 8, characterized in that: The method further comprises: Displaying a third control on a third page; Based on the touch operation acting on the third control, displaying a target table obtained based on the first sub-content of each of the contents on the third page; and / or, A target table obtained based on the second sub-contents of each of the contents is displayed on the third page.

11. The method according to any one of claims 1 to 8, characterized in that: The method further comprises: In response to a touch operation on an initial table, determining the data to be processed from the initial table; wherein each of the contents in the data to be processed is arranged in cells of the initial table in a row or column manner; The sub-contents obtained by classifying each content in the data to be processed are respectively entered into cells corresponding to each of the project titles to obtain a target table, including: The sub-contents obtained by classifying each content in the data to be processed are respectively entered into the cells of the target row or target column of each item title to obtain the target table.

12. A table processing device, characterized in that: include: A first analysis module is configured to analyze a preset number of first contents in the data to be processed in response to a trigger operation on the data to be processed, and determine at least one project title; An input module is configured to input sub-contents obtained by classifying each content in the data to be processed into cells corresponding to each of the project titles to obtain a target table; The number of the sub-contents in each of the contents is the same as the number of the project titles.

13. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 11 are implemented.

Images