Intelligent table data automatic input method

Abstract

The application provides a kind of intelligent table data automatic entry method, including the following steps: by image acquisition equipment, the paper form to be identified is converted into table image, the table image is segmented, obtains first image area, second image area, third image area, the first image area, second image area, third image area include the cell of different area;The cell recognition result obtained to first image area, second image area, third image area is established with multiple identification codes, while the corresponding relationship of multiple identification codes is established;Select electronic form in electronic form library, based on cell recognition result and the corresponding relationship of multiple identification codes, fill in corresponding electronic cell with cell recognition result, finally realize the entry of electronic form.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of digital cinema technology, and in particular to a method for automatically inputting intelligent table data. BACKGROUND

[0002] With the advent of the information age, paper documents are large in size and time-consuming and laborious to search, so many enterprises are trying to find a way to digitize paper documents, especially the table data in paper documents, because the data in the table is usually condensed and key data with important significance. There are mainly two ways to digitize existing paper table documents: one is to take a photo of the paper document, and then manually create an electronic document based on the actual content of the paper document and save it in the database. This digitization method has two disadvantages: first, manual analysis of table content and establishment of documents still require a large amount of repetitive manual work; second, the digitized document is saved as an image file, which cannot extract structured information based on the document content, nor can it perform intelligent search based on the document content, but only based on the document name when the document is manually created. SUMMARY

[0003] The present application aims to provide a method for automatically inputting intelligent table data to solve the problems raised in the background art.

[0004] The present application is achieved by the following technical solution: a method for automatically inputting intelligent table data, comprising the following steps:

[0005] Converting a paper table to be recognized into a table image by an image acquisition device, segmenting the table image to obtain a first image area, a second image area and a third image area, and the first image area, the second image area and the third image area comprising cells in different areas;

[0006] Establishing a plurality of identification codes for the cell recognition results obtained from the first image area, the second image area and the third image area, and establishing a correspondence relationship between the plurality of identification codes;

[0007] Selecting an electronic table in an electronic table library, filling the cell recognition results into the corresponding electronic cells based on the cell recognition results and the correspondence relationship between the plurality of identification codes, and finally realizing the input of the electronic table.

[0008] Optionally, a plurality of identification codes are established for the cell recognition results obtained from the first image area, the second image area and the third image area, and a correspondence relationship between the plurality of identification codes is established, which specifically comprises:

[0009] Performing OCR-based vertical table recognition on the first image area, and labeling the obtained first cell recognition result as a sub-recognition result A;

[0010] performing OCR-based vertical table recognition on the second image region, marking the obtained first cell recognition result as a sub-recognition result B, and marking the obtained second cell recognition result in the vertical table recognition as a sub-recognition result C;

[0011] performing OCR-based vertical table recognition on the second image region, marking the obtained first cell recognition result as a sub-recognition result B, and marking the obtained second cell recognition result in the vertical table recognition as a sub-recognition result C;

[0012] Optionally, if the sub-recognition result A is consistent with the sub-recognition result B and the sub-recognition result C is consistent with the sub-recognition result D, the sub-recognition result A is marked with a first identification code, and other cell recognition results of the first image region are sequentially marked with other identification codes according to the order of recognition.

[0013] Optionally, sequentially marking the other cell recognition results of the first image region with the other identification codes includes recording the order of recognition, then performing multiple times of plus one processing on the first identification code to obtain multiple first processing results, sequentially marking the other cell recognition results of the first image region with the multiple first processing results according to the order of recognition, and simultaneously associating the first identification code with the multiple first processing results.

[0014] Optionally, the association rule of the first identification code and the plus one processing result is that the multiple first processing results are located to the right of the first identification code.

[0015] Optionally, the sub-recognition result C is marked with a second identification code, and other cell recognition results of the second image region are sequentially marked with other identification codes according to the order of recognition, and simultaneously associating the first identification code with the second identification code.

[0016] Optionally, sequentially marking the other cell recognition results of the second image region with the other identification codes includes recording the order of recognition, then performing multiple times of plus one processing on the second identification code to obtain multiple second processing results, sequentially marking the other cell recognition results of the second image region with the multiple second processing results according to the order of recognition, and simultaneously associating the second identification code with the multiple second processing results.

[0017] Optionally, the association rule of the second identification code and the plus one processing result is that the multiple second processing results are located below the second identification code.

[0018] Optionally, the coexistence rule of the first identification code and the second identification code is that the second identification code is below the position of the first identification code.

[0019] Optionally, the second identification code is used to identify the identification result of each cell in the third image region of the plurality of second processing results.

[0020] Compared with the prior art, the present application has the following beneficial effects:

[0021] The intelligent table data automatic input method provided by the present application can identify the data in the paper table as electronic data, establish the contact relationship between each cell, input the corresponding electronic data into the corresponding electronic table template based on the contact relationship, and finally realize the data input of the electronic table. BRIEF DESCRIPTION OF DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only preferred embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0023] Figure 1 The flow chart of the intelligent table data automatic input method provided by the present application. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solutions and advantages of the present application more obvious, the following will describe the example embodiments according to the present application with reference to the drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described here. Based on the embodiments of the present application described in the present application, all other embodiments obtained by those skilled in the art without creative labor should fall within the protection scope of the present application.

[0025] In the following description, a large number of specific details are given in order to provide a more thorough understanding of the present application. However, it is obvious for those skilled in the art that the present application can be implemented without one or more of these details. In other examples, in order to avoid obscuring the present application, some technical features known in the art are not described.

[0026] It should be understood that the present application can be implemented in different forms, and should not be interpreted as being limited to the embodiments presented here. On the contrary, these embodiments are provided to make the disclosure complete and complete, and to fully convey the scope of the present application to those skilled in the art.

[0027] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising", when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. As used herein the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0028] For a thorough understanding of the present application, reference will be made to the following detailed description, in conjunction with the accompanying drawings, in which:

[0029] Referring to Figure 1 An intelligent table data automatic input method, comprising the following steps:

[0030] S1, converting a paper table to be identified into a table image through an image acquisition device, segmenting the table image to obtain a first image region, a second image region and a third image region, the first image region, the second image region and the third image region comprising cells in different regions.

[0031] The first image region mainly comprises a table header region of the table, the second image region mainly comprises a first column region of the table, and the third image region is a remaining table region.

[0032] Performing longitudinal table recognition based on OCR on the first image region, i.e. obtaining a recognition result of each cell in the table header region, and marking the obtained first cell recognition result as a first table header as a sub-recognition result A;

[0033] Performing vertical table recognition based on OCR on the second image region, marking the obtained first cell recognition result as a sub-recognition result B, and marking a second cell recognition result obtained in the vertical table recognition as a sub-recognition result C;

[0034] The third image region is subjected to OCR-based longitudinal table recognition, the obtained first cell recognition result is labeled as a sub-recognition result D, the sub-recognition result A should be in a region of repeated recognition with the sub-recognition result B, and the sub-recognition result C is in a region of repeated recognition with the sub-recognition result D, therefore, the sub-recognition result A is compared with the sub-recognition result B, and the sub-recognition result C is compared with the sub-recognition result D, whether consistent is judged, and based on the judgment result, whether the image segmentation region is incorrect is confirmed, if there is an inconsistent case, the table image is re-segmented to obtain a new first image region, a second image region and a third image region.

[0035] S2, a plurality of identification codes are established for the cell recognition results obtained from the first image region, the second image region and the third image region, and a corresponding relationship of the plurality of identification codes is established.

[0036] Specifically, if the sub-recognition result A is consistent with the sub-recognition result B, and the sub-recognition result C is consistent with the sub-recognition result D, the sub-recognition result A is labeled with a first identification code, and other cell recognition results of the first image region are labeled with other identification codes in the order of recognition.

[0037] Specifically, the other cell recognition results of the first image region are labeled with other identification codes in turn, including recording the order of recognition, then the first identification code is subjected to multiple plus one processing to obtain a plurality of first processing results, for example, selecting "1" as the first identification code, and after the first identification code is subjected to plus one processing, other identification codes "2" are obtained, and "2" is used as the identification code of the next cell recognition result. The plurality of first processing results are labeled in turn for the other cell recognition results of the first image region according to the order of recognition, and the first identification code is associated with the plurality of first processing results.

[0038] Specifically, the association rule of the first identification code and the plus one processing result is that the plurality of first processing results are located on the right side of the first identification code.

[0039] Specifically, the sub-recognition result C is labeled with a second identification code, and other cell recognition results of the second image region are labeled with other identification codes in the order of recognition, and the first identification code is associated with the second identification code.

[0040] Specifically, the other cell recognition results of the second image region are labeled with other identification codes in turn, including recording the order of recognition, then the second identification code is subjected to multiple plus one processing to obtain a plurality of second processing results, the plurality of second processing results are labeled in turn for the other cell recognition results of the second image region according to the order of recognition, and the second identification code is associated with the plurality of second processing results.

[0041] Specifically, the coexistence rule of the second identification code and the result of the plus one processing is that the plurality of second processing results are below the position of the second identification code.

[0042] Specifically, the coexistence rule of the first identification code and the second identification code is that the second identification code is below the position of the first identification code.

[0043] Specifically, the second identification code is used to identify the recognition result of each cell in the third image region of the plurality of second processing results.

[0044] S3, selecting an electronic form in an electronic form library, filling the cell recognition result into the corresponding electronic cell based on the correspondence between the cell recognition result and the plurality of identification codes, and finally realizing the entry of the electronic form.

[0045] In specific implementation, the data of each cell in the paper form is converted into electronic data. Firstly, the sub-recognition result A is taken as the data of the first cell in the first row and the first column of the electronic form. Meanwhile, based on the coexistence of the first identification code and the plurality of first processing results, the recognition results corresponding to the identification codes are filled in the second cell, the third cell,..., the n-th cell in the first row of the electronic form, so as to obtain the header data of the electronic form.

[0046] The recognition result C is taken as the data of the second cell in the first column. Meanwhile, based on the coexistence of the second identification code and the plurality of second processing results, the recognition results corresponding to the identification codes are filled in the third cell, the fourth cell,..., the n-th cell in the first column of the electronic form, so as to obtain the first column data of the electronic form.

[0047] Since the identification code of the recognition result of each cell in each row in the third image region is consistent with the second identification code and the second processing result, for example, after the corresponding recognition result is filled in the third cell in the first column (and the first cell in the third row) of the electronic form, the same recognition result is found in the database according to the order of recognition, and the same recognition result is sequentially filled in the second cell in the third row, the third cell in the third row, the n-th cell in the third row, and so on, so as to finally realize the data entry of the electronic form.

[0048] The above only describes the preferred embodiments of the present application and is not used to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for automatic entry of data into an intelligent form, characterized by, The method comprises the following steps: The paper form is converted into a form image by an image acquisition device, the form image is segmented to obtain a first image region, a second image region and a third image region, and the first image region, the second image region and the third image region comprise cells in different regions; The first image region mainly comprises a header region of the form, the second image region mainly comprises a first column region of the form, and the third image region is a remaining form region; A plurality of identification codes are established based on the cell recognition results obtained by the first image region, the second image region and the third image region, and a corresponding relationship of the plurality of identification codes is established; An electronic form is selected in an electronic form library, the cell recognition results are filled into corresponding electronic cells based on the cell recognition results and the corresponding relationship of the plurality of identification codes, and finally the electronic form is inputted; The plurality of identification codes are established based on the cell recognition results obtained by the first image region, the second image region and the third image region, and the corresponding relationship of the plurality of identification codes is established, and specifically comprising: The first image region is subjected to vertical form recognition based on OCR, and a first cell recognition result obtained is marked as a sub-recognition result A; The second image region is subjected to vertical form recognition based on OCR, and a first cell recognition result obtained is marked as a sub-recognition result B, and a second cell recognition result obtained in the vertical form recognition is marked as a sub-recognition result C; The third image region is subjected to vertical form recognition based on OCR, and a first cell recognition result obtained is marked as a sub-recognition result D, the sub-recognition result A is compared with the sub-recognition result B, the sub-recognition result C is compared with the sub-recognition result D, and it is judged whether they are consistent; if there is inconsistency, the form image is segmented again to obtain new first image region, second image region and third image region; If the sub-recognition result A is consistent with the sub-recognition result B, and the sub-recognition result C is consistent with the sub-recognition result D, the sub-recognition result A is marked with a first identification code, and other cell recognition results of the first image region are sequentially marked with other identification codes in the order of recognition.

2. The method of claim 1, wherein, The other cell recognition results of the first image region are sequentially marked with other identification codes, The order of recognition is recorded, then the first identification code is subjected to a plurality of times of plus one processing to obtain a plurality of first processing results, the first image region is sequentially marked with the other cell recognition results in the order of recognition, and the first identification code is associated with the plurality of first processing results.

3. The method of claim 2, wherein, The association rule of the first identification code and the plus one processing result is that the plurality of first processing results are located on the right side of the first identification code.

4. The method of claim 3, wherein, The sub-recognition result C is marked with a second identification code, and other cell recognition results of the second image region are sequentially marked with other identification codes in the order of recognition, and the first identification code is associated with the second identification code.

5. The method of claim 4, wherein, The other cell recognition results of the second image region are sequentially marked with other identification codes, The method comprises the following steps: recording the order of the identification, then performing multiple plus one processing on the second identification code to obtain multiple second processing results, and sequentially marking the identification results of other cells in the second image region according to the order of the identification, while associating the second identification code with the multiple second processing results.

6. The method of claim 5, wherein, The association rule between the second identification code and the plus one processing result is that the multiple second processing results are below the position of the second identification code.

7. The method of claim 6, wherein, The association rule between the first identification code and the second identification code is that the second identification code is below the position of the first identification code.

8. The method of claim 7, wherein, The identification results of each cell in the third image region are marked by using the second identification code and the multiple second processing results.

Images