Paper-based file data processing method and device and computer equipment

Abstract

The application relates to the field of artificial intelligence technology, is applied to the field of smart cities, and discloses a data processing method and device based on paper files, a computer device and a storage medium. After a paper file is placed in an identification area, it is determined whether the interval layer in the paper file is detached. If the interval layer in the paper file is detached, an infrared flash and an ultraviolet flash are turned on. A first camera is turned on and a picture is taken to obtain a back picture. Flip processing is performed to obtain a flipped picture. Text recognition processing is performed to obtain first recognized text and second recognized text. A processing model is used to process the first recognized text and the second recognized text to obtain a processing result output by the processing model. The efficiency and accuracy of data processing based on paper files are improved. In addition, the application also relates to the field of blockchains, and the processing model can be stored in a blockchain.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, in particular to a data processing method and device based on paper files, a computer device and a storage medium. BACKGROUND

[0002] Data recording and processing are completed based on paper files, that is, relevant data are recorded in the paper files (for example, manually written). Data processing based on these paper files is not easy to perform. If manual processing is adopted, it is time-consuming, laborious and prone to errors. If a character recognition technology in a computer is used for processing, only data of equal value can be obtained (that is, different data cannot be distinguished), so it is difficult to further process the data. Therefore, the traditional scheme is difficult to complete data processing of paper files, especially to realize automatic data processing based on paper files. SUMMARY

[0003] The present application provides a data processing method and device based on paper files and a computer device, aiming to solve the technical problem of difficulty in data processing of paper files.

[0004] In order to achieve the above-mentioned application purpose, the present application first provides a data processing method based on paper files. The paper file is composed of a direct contact layer, an ink layer, a spacing layer and a character bearing layer in an original state. The direct contact layer, the ink layer, the spacing layer and the character bearing layer are sequentially laminated, and the spacing layer can be detached while ensuring that the relative positions of the direct contact layer, the ink layer and the character bearing layer remain unchanged. The ink layer includes a first region and a second region separated from each other. The first ink material in the first region presents a first color under infrared conditions. The second ink material in the second region presents a second color under ultraviolet conditions. The data processing method comprises:

[0005] A preset spacing layer detachment judgment method is used to judge whether the spacing layer in the paper file is detached. The unknown state refers to a state in which the direct contact layer, the ink layer and the spacing layer in the paper file are not detached, or a state in which one or more of the direct contact layer, the ink layer and the spacing layer in the paper file are detached.

[0006] If the spacing layer in the paper file is detached, a preset infrared flash lamp and ultraviolet flash lamp are turned on to make the paper file simultaneously in an infrared irradiation and ultraviolet irradiation environment.

[0007] turning the back picture over according to a preset left-right mirror image turning processing method, so as to obtain a turned picture corresponding to the back picture, wherein the turned picture comprises a first front text image corresponding to the first back text image and a second front text image corresponding to the second back text image;

[0008] turning the back picture over according to a preset left-right mirror image turning processing method, so as to obtain a turned picture corresponding to the back picture, wherein the turned picture comprises a first front text image corresponding to the first back text image and a second front text image corresponding to the second back text image;

[0009] turning the back picture over according to a preset left-right mirror image turning processing method, so as to obtain a turned picture corresponding to the back picture, wherein the turned picture comprises a first front text image corresponding to the first back text image and a second front text image corresponding to the second back text image;

[0010] turning the back picture over according to a preset left-right mirror image turning processing method, so as to obtain a turned picture corresponding to the back picture, wherein the turned picture comprises a first front text image corresponding to the first back text image and a second front text image corresponding to the second back text image;

[0011] Further, the direct contact layer, the ink layer, the spacing layer and the text bearing layer all have light transmission regions, the light transmission regions of the direct contact layer, the ink layer, the spacing layer and the text bearing layer are equal in spatial position in the vertical direction, and the light transmission of the light transmission region of the spacing layer is weaker than that of the light transmission regions of the other three layers; the step of judging whether the spacing layer in the paper document is detached by using a preset spacing layer detachment judgment method comprises:

[0012] generating a detection visible light above the light transmission region of the direct contact layer by using a preset visible light generator, so that the detection visible light passes through the light transmission region of the direct contact layer;

[0013] obtaining a light intensity signal sensed by a preset light intensity sensor below the text bearing layer;

[0014] judging whether the light intensity signal is greater than a preset light intensity threshold;

[0015] If the light intensity signal is greater than the preset light intensity threshold, it is determined that the spacing layer in the paper document is detached.

[0016] Further, the first camera is opened, and the back of the paper document is photographed by using the first camera to obtain a back picture, wherein the back picture includes a first back text image in a first color and a second back text image in a second color. After the step of obtaining the back picture and before the step of performing a flip processing on the back picture according to a preset left-right mirror flip processing method to obtain a flip picture corresponding to the back picture, the data processing method further includes:

[0017] detecting the back picture according to a preset writing fracture point detection method to obtain a number of writing fracture points;

[0018] determining whether the number of writing fracture points is less than a preset fracture point threshold;

[0019] if the number of writing fracture points is less than the preset fracture point threshold, a mirror flip instruction is generated, and the mirror flip instruction is used to instruct to perform a flip processing on the back picture according to a preset left-right mirror flip processing method.

[0020] Further, the first recognized text and the second recognized text each include a text part and a number part. The step of processing the first recognized text and the second recognized text by using the processing model to obtain a processing result output by the processing model includes:

[0021] the first recognized text is split into a first text and a first number by using the processing model, and the second recognized text is split into a second text and a second number by using the processing model;

[0022] a preset calculation formula is called, and the first number and the second number are input into the calculation formula to obtain a calculation result;

[0023] a preset table template is called, the first text and the second text are respectively filled into preset text positions in the table template, the calculation result is filled into a preset number position in the table template, and the filled table template is recorded as the processing result.

[0024] Further, the text bearing layer has a first shape area drawn by a second ink and a second shape area drawn by a first ink in advance, the first text is located in the first shape area in a direction perpendicular to a paper surface, and the first number is located in the second shape area in the direction perpendicular to the paper surface. The step of splitting the first recognized text into the first text and the first number by using the processing model includes:

[0025] acquire a first shape region in the flipped picture that appears to be the second color, and acquire a second shape region in the flipped picture that appears to be the first color;

[0026] record the first recognized text in the first shape region of the flipped picture as a first text, and record the first recognized text in the second shape region of the flipped picture as a first number.

[0027] The application provides a paper-based data processing device, the paper-based file in the original state is composed of a direct contact layer, an ink layer, a spacer layer and a text bearing layer, the direct contact layer, the ink layer, the spacer layer and the text bearing layer are sequentially stacked, and the spacer layer can be detached while ensuring that the relative positions of the direct contact layer, the ink layer and the text bearing layer remain unchanged; the ink layer comprises a first region and a second region separated from each other, a first ink material in the first region appears a first color under infrared light; a second ink material in the second region appears a second color under ultraviolet light; the device comprises:

[0028] a spacer layer judgment unit for judging whether the spacer layer in the paper-based file is detached by using a preset spacer layer detachment judgment method; wherein the unknown state refers to a state in which the direct contact layer, the ink layer and the spacer layer in the paper-based file are not detached, or a state in which one or more of the direct contact layer, the ink layer and the spacer layer in the paper-based file are detached;

[0029] a flash opening unit for opening a preset infrared flash and ultraviolet flash if the spacer layer in the paper-based file is detached, so that the paper-based file is simultaneously in an infrared irradiation and ultraviolet irradiation environment;

[0030] a back picture acquisition unit for opening a preset first camera and taking a picture of the back of the paper-based file by using the first camera, thereby obtaining a back picture, wherein the back picture comprises a first back text image appearing a first color and a second back text image appearing a second color;

[0031] a flipped picture acquisition unit for performing a flipping processing on the back picture according to a preset left-right mirror flipping processing method, thereby obtaining a flipped picture corresponding to the back picture, wherein the flipped picture comprises a first front text image corresponding to the first back text image, and a second front text image corresponding to the second back text image;

[0032] a recognized text acquisition unit for performing a text recognition processing on the flipped picture by using a preset text recognition method, thereby obtaining a first recognized text corresponding to the first front text image, and obtaining a second recognized text corresponding to the second front text image.

[0033] A processing result obtaining unit is configured to invoke a preset processing model and process the first recognized character and the second recognized character using the processing model to obtain a processing result output by the processing model.

[0034] Further, the direct contact layer, the ink layer, the spacing layer and the character bearing layer each have a light transmission region, the light transmission regions of the direct contact layer, the ink layer, the spacing layer and the character bearing layer are equal in spatial position in a vertical direction, and the light transmission region of the spacing layer has weaker light transmission than the light transmission regions of the other three layers; the spacing layer judging unit comprises:

[0035] A detection visible light generating subunit is configured to generate detection visible light above the light transmission region of the direct contact layer using a preset visible light generator so that the detection visible light passes through the light transmission region of the direct contact layer;

[0036] A light intensity signal obtaining subunit is configured to obtain a light intensity signal sensed by a preset light intensity sensor below the character bearing layer;

[0037] A light intensity threshold judging subunit is configured to judge whether the light intensity signal is greater than a preset light intensity threshold;

[0038] A spacing layer judging subunit is configured to judge that the spacing layer in the paper document is detached if the light intensity signal is greater than the preset light intensity threshold.

[0039] Further, the device further comprises:

[0040] A writing trace breaking point detecting unit is configured to detect the back picture according to a preset writing trace breaking point detection method to obtain a number of writing trace breaking points;

[0041] A breaking point number threshold judging unit is configured to judge whether the number of writing trace breaking points is less than a preset breaking point number threshold;

[0042] A mirror image flipping instruction generating unit is configured to generate a mirror image flipping instruction if the number of writing trace breaking points is less than the preset breaking point number threshold, the mirror image flipping instruction being used to instruct to flip the back picture according to a preset left-right mirror image flipping processing method.

[0043] The present application provides a computer device, comprising a memory and a processor, the memory stores a computer program, and the processor implements the steps of the data processing method of any one of the above when executing the computer program.

[0044] The application provides a computer readable storage medium, which stores a computer program, and the computer program realizes the steps of the data processing method when executed by a processor.

[0045] The paper-based data processing method, device, computer device and storage medium provided by the application adopt a preset interval layer separation judgment method to judge whether the interval layer in the paper file is separated; if the interval layer in the paper file is separated, a preset infrared flash and ultraviolet flash are turned on, so that different color texts are obtained, data is distinguished, and automatic data processing is possible; a preset first camera is turned on, and the back of the paper file is photographed by using the first camera, so that a back picture is obtained, and the situation that an accurate picture cannot be obtained due to the obstruction of the direct contact layer and the ink layer is eliminated, and the accuracy of subsequent data processing is ensured; the back picture is flipped, so that a flipped picture corresponding to the back picture is obtained, the front obstruction (i.e. the direct contact layer and the ink layer) is overcome, and the flipped picture recording the texts on the text bearing layer is obtained; the flipped picture is subjected to text recognition processing, so that first recognized texts corresponding to the first front text image and second recognized texts corresponding to the second front text image are obtained; a preset processing model is called, and the first recognized texts and the second recognized texts are processed by using the processing model, so that a processing result output by the processing model is obtained, the picture text recognition and the processing model are combined, and the efficiency and accuracy of the paper-based data processing are improved. BRIEF DESCRIPTION OF DRAWINGS

[0046] Figure 1 A flowchart of a paper-based data processing method according to an embodiment of the application is shown in FIG. 1.

[0047] Figure 2 A structural schematic block diagram of a paper-based data processing device according to an embodiment of the application is shown in FIG. 2.

[0048] Figure 3 A structural schematic block diagram of a computer device according to an embodiment of the application is shown in FIG. 3.

[0049] Figure 4 A structural schematic diagram of a paper file according to an embodiment of the application is shown in FIG. 4.

[0050] The reference signs are as follows: a direct contact layer 1, an ink layer 2, an interval layer 3 and a text bearing layer 4.

[0051] The implementation, functional features and advantages of the application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and not used to limit the present application.

[0053] With reference to Figure 1 The paper file in the original state is composed of a direct contact layer, an ink layer, a spacer layer and a text bearing layer. The direct contact layer, the ink layer, the spacer layer and the text bearing layer are sequentially stacked, and the spacer layer can be detached while ensuring that the relative positions of the direct contact layer, the ink layer and the text bearing layer remain unchanged. The ink layer includes a first region and a second region separated from each other. The first ink material in the first region exhibits a first color under infrared light and exhibits a third color under visible light. The second ink material in the second region exhibits a second color under ultraviolet light and exhibits a third color under visible light. The data processing method includes:

[0054] S1, using a preset spacer layer detachment judgment method to judge whether the spacer layer in the paper file is detached; wherein the unknown state refers to a state in which the direct contact layer, the ink layer and the spacer layer in the paper file are not detached, or a state in which one or more of the direct contact layer, the ink layer and the spacer layer in the paper file are detached;

[0055] S2, if the spacer layer in the paper file is detached, turn on the preset infrared flash and ultraviolet flash to make the paper file simultaneously in an infrared irradiation and ultraviolet irradiation environment;

[0056] S3, turn on a preset first camera and use the first camera to take a picture of the back of the paper file, thereby obtaining a back picture, wherein the back picture includes a first back text image exhibiting a first color and a second back text image exhibiting a second color;

[0057] S4, according to a preset left-right mirror image flipping processing method, flip the back picture to obtain a flipped picture corresponding to the back picture, wherein the flipped picture includes a first front text image corresponding to the first back text image, and a second front text image corresponding to the second back text image;

[0058] S5, using a preset text recognition method, performing text recognition processing on the flipped picture to obtain first recognized text corresponding to the first front text image, and second recognized text corresponding to the second front text image;

[0059] S6, calling a preset processing model, and processing the first recognized character and the second recognized character using the processing model, so as to obtain a processing result output by the processing model.

[0060] The present application is designed to automatically process data based on paper files. The specific design is introduced as follows:

[0061] 1. A special paper file is used, which is composed of a direct contact layer, an ink layer, a spacing layer and a character bearing layer in the original state (as shown in the figure). Figure 4 The direct contact layer, the ink layer, the spacing layer and the character bearing layer are sequentially stacked, and the spacing layer can be detached without changing the relative positions of the direct contact layer, the ink layer and the character bearing layer. The ink layer includes a first area and a second area separated from each other. The first ink material in the first area presents a first color under infrared light and a third color under visible light. The second ink material in the second area presents a second color under ultraviolet light and a third color under visible light. Thus, under normal conditions (under visible light), the paper file is no different from ordinary files and does not affect normal use. However, under infrared and ultraviolet conditions, the characters in different areas (if the paper file has written characters) present different colors, so that the data can be distinguished. Thus, without affecting normal use, data differentiation is realized, which provides the possibility for automatic data processing.

[0062] 2. The back picture collection method is used to avoid the defect that the front picture may not collect specific characters (because one or more layers of the direct contact layer and the ink layer of the paper file may not be detached, which will hinder the collection of the front picture).

[0063] 3. The last layer of the paper file, i.e. the character bearing layer, does not show characters under normal conditions (i.e. under visible light), which is conducive to improving information security, but will not hinder use (for computer recognition).

[0064] The present application can be applied to any feasible scenario, such as the financial field, etc. More specifically, the paper file is, for example, a bill in finance, etc. The direct contact layer can be written with a physical pen, and correspondingly, the character bearing layer will have characters that are invisible under visible light.

[0065] The direct contact layer, the ink layer, the spacing layer and the text bearing layer in the paper document of the present application are sequentially stacked, and can be connected or not connected in any feasible manner, such as sequentially stacked by clamping, bonding and the like. The first ink material presents a first color under infrared light, which means that the first ink material contains a substance capable of converting infrared light into visible light presenting a first color, such as a fluorine-oxygen-based compound doped with impurities, and the impurities are, for example, high-doped Er 3+ plasmas, thereby being capable of converting infrared light into green visible light; the second ink material presents a second color under ultraviolet light, which means that the second ink material contains a substance capable of converting ultraviolet light into visible light presenting a second color, such as a maleic anhydride copolymer-based resin and the like.

[0066] The process of writing text on the paper document is introduced as follows: the user first detaches the spacing layer (if not detached, the text bearing layer cannot accept ink), and then writes text on the direct contact layer using a physical pen, so that the direct contact layer has handwritten text, and at this time the ink layer prints the first ink material or the second ink material on the text bearing layer due to the pressure of the physical pen. It should be noted that after writing the text, the direct contact layer can be used for direct recognition by the human eye as daily use, and the text bearing layer cannot be recognized by the human eye and is used for computer recognition, thereby simultaneously recording information in two different forms.

[0067] As described in step S1 above, a preset spacing layer detachment judgment method is used to judge whether the spacing layer in the paper document is detached; wherein the unknown state refers to a state in which the direct contact layer, the ink layer and the spacing layer in the paper document are not detached, or a state in which one or more of the direct contact layer, the ink layer and the spacing layer in the paper document are detached. The paper document can be placed in the recognition area by manual placement or by mechanical hand placement, and the mechanical hand placement is preferred, thereby realizing the full automation of the overall scheme. The spacing layer detachment judgment method can use any feasible method, such as monitoring the thickness of the paper document to judge whether the spacing layer in the paper document is detached.

[0068] If the interval layer in the paper document is detached, as described in step S2, turn on the preset infrared flash and ultraviolet flash to make the paper document simultaneously in the environment of infrared irradiation and ultraviolet irradiation. If the interval layer in the paper document is detached, it indicates that the paper document may have been used, meaning that the ink on the text-bearing layer is likely to be printed, which can be used as the basis for further identification. The ink on the text-bearing layer is invisible under visible light, so the preset infrared flash and ultraviolet flash need to be turned on to make the ink on the text-bearing layer emit different colors of visible light.

[0069] As described in step S3, turn on the preset first camera and take a picture of the back of the paper document using the first camera to obtain a back picture, wherein the back picture includes a first back text image showing a first color and a second back text image showing a second color. The application takes a picture of the back of the paper document using the first camera instead of taking a picture of the front of the paper document because the paper document can be identified again after only the interval layer is detached, at which time the paper document has the direct contact layer, ink layer, and text-bearing layer stacked in turn. If the picture is taken from the front, it is not possible to obtain an accurate picture due to the obstruction of the direct contact layer and ink layer. In addition, since the ink layer and the text-bearing layer are adjacent, the ink layer may appear as a background color in the back picture, but since the ink on the text-bearing layer is pressed by the pressure of the physical pen, it has a certain indentation, which is reflected in the back picture and can be distinguished from other areas, so it can be identified. Further, the application also uses the design of the ink layer and the text-bearing layer stacked at a preset distance to improve the contrast of the images in the back picture. Further, the light transmittance of the text-bearing layer is greater than a preset light transmittance threshold to facilitate clearer acquisition of text in the back picture. Further, the thickness of the text-bearing layer is less than a preset thickness threshold to facilitate clearer acquisition of text in the back picture.

[0070] As described in step S4, flip the back picture according to a preset left-right mirror flip processing method to obtain a flip picture corresponding to the back picture, wherein the flip picture includes a first front text image corresponding to the first back text image and a second front text image corresponding to the second back text image. The text in the back picture is different from ordinary text pictures and is reversed, so further processing is needed. Therefore, the application flips the back picture according to the preset left-right mirror flip processing method, and the obtained flip picture has the same text as the front picture. Thus, the application overcomes the front obstacles (i.e., the direct contact layer and the ink layer) to obtain a flip picture recording the text on the text-bearing layer.

[0071] As described in step S5, the preset text recognition method is used to perform text recognition processing on the flipped picture, so as to obtain the first recognized text corresponding to the first front text image and the second recognized text corresponding to the second front text image. The text recognition method can be any available recognition method, such as an OCR recognition method. Since the flipped picture contains text images of different colors, i.e., the first front text image in the first color and the second front text image in the second color, the color is used as a basis to distinguish the data, thereby overcoming the difficulty of traditional schemes in completing data processing of paper files (because the traditional schemes are difficult to distinguish data).

[0072] As described in step S6, a preset processing model is called, and the first recognized text and the second recognized text are processed using the processing model, so as to obtain a processing result output by the processing model. The processing model can be any available model, and an example is given here. The processing model is, for example, a model including a calculation formula, the first recognized text and the second recognized text include a first numerical value and a second numerical value, respectively, the first numerical value and the second numerical value are input into the calculation formula to obtain a calculation result, and the calculation result is taken as the processing result output by the processing model. The processing model can be stored in a pre-set blockchain.

[0073] In one embodiment, the direct contact layer, the ink layer, the spacing layer, and the text bearing layer all have light transmission regions, the light transmission regions of the direct contact layer, the ink layer, the spacing layer, and the text bearing layer are equal in spatial position in the vertical direction, and the light transmission of the light transmission region of the spacing layer is weaker than that of the light transmission regions of the other three layers; the step S1 of judging whether the spacing layer in the paper file is detached by using a preset spacing layer detachment judgment method includes:

[0074] S101, above the light transmission region of the direct contact layer, a preset visible light generator is used to generate detection visible light, so that the detection visible light passes through the light transmission region of the direct contact layer;

[0075] S102, below the text bearing layer, a light intensity signal sensed by a preset light intensity sensor is obtained;

[0076] S103, whether the light intensity signal is greater than a preset light intensity threshold is judged;

[0077] S104, if the light intensity signal is greater than the preset light intensity threshold, it is determined that the spacing layer in the paper file is detached.

[0078] As described above, the preset interval layer separation judgment method is implemented to judge whether the interval layer in the paper document is separated. The light transmission region can be arranged at any feasible position of each layer, such as a central position, a side edge position, etc. When the paper document includes four layers, the light transmission region of the paper document has poor light transmission due to the interval layer. When the interval layer is separated, the light transmission region of the paper document has strong light transmission due to the removal of the interval layer with poor light transmission, which can be used as a judgment basis for whether the interval layer in the paper document is separated. Therefore, the preset visible light generator is arranged above the light transmission region of the direct contact layer to generate detection visible light, so that the detection visible light passes through the light transmission region of the direct contact layer. Below the text bearing layer, a preset light intensity sensor senses a light intensity signal. If the light intensity signal is greater than a preset light intensity threshold, it is determined that the interval layer in the paper document is separated. Thus, it is realized to accurately judge whether the interval layer is separated.

[0079] In one embodiment, after the step S3 of turning on a preset first camera and using the first camera to take a picture of the back of the paper document to obtain a back picture, wherein the back picture includes a first back text image with a first color and a second back text image with a second color, and before the step S4 of performing a flip processing on the back picture according to a preset left-right mirror flip processing method to obtain a flip picture corresponding to the back picture, the method further includes:

[0080] S31, detecting the back picture according to a preset writing fracture point detection method to obtain a number of writing fracture points;

[0081] S32, judging whether the number of writing fracture points is less than a preset fracture point number threshold;

[0082] S33, if the number of writing fracture points is less than the preset fracture point number threshold, generating a mirror flip instruction, wherein the mirror flip instruction is used to instruct to perform a flip processing on the back picture according to the preset left-right mirror flip processing method.

[0083] As described above, the mirror image flipping instruction is generated. The present application is to obtain the back picture to bypass the obstacle of the front picture being unavailable. However, the back picture is still hindered by the intrinsic text bearing layer, so the text clarity is inevitably poor. In the case of insufficient text clarity, the back picture may cause recognition errors, so it cannot be used as the basis for recognition. In the text of the present application, the insufficient text clarity is reflected by the fact that there are many broken points (i.e. part of the text on the front of the text bearing layer does not appear on the back picture, thus causing a break, so there are many broken points). Therefore, the present application detects the back picture according to the preset broken point detection method to obtain the number of broken points; then determines whether the back picture is available by judging whether the number of broken points is less than the preset threshold of the number of broken points. If the number of broken points is less than the preset threshold of the number of broken points, the mirror image flipping instruction is generated, thereby ensuring the accuracy of the final recognition and data processing.

[0084] In one embodiment, the first recognized text and the second recognized text each include a text part and a number part; the step S6 of processing the first recognized text and the second recognized text using the processing model to obtain the processing result output by the processing model includes:

[0085] S601, using the processing model to split the first recognized text into a first text and a first number, and to split the second recognized text into a second text and a second number;

[0086] S602, calling a preset calculation formula and inputting the first number and the second number into the calculation formula to obtain a calculation result;

[0087] S603, calling a preset table template, filling the first text and the second text into preset text positions in the table template respectively, and filling the calculation result into a preset number position in the table template, and recording the filled table template as the processing result.

[0088] As described above, the first recognized character and the second recognized character are processed using the processing model. The present application is particularly suitable for recognizing and processing data, such as numbers, recorded on a paper document. Specifically, the present application splits the first recognized character into a first character and a first number, and splits the second recognized character into a second character and a second number using the processing model; calls a preset calculation formula and inputs the first number and the second number into the calculation formula to obtain a calculation result; and fills the first character and the second character into preset character positions in the table template, and fills the calculation result into a preset number position in the table template to obtain a processing result. The paper document, for example, is a bill in the financial field, which contains characters and numbers (which are uniformly processed as recognized characters during the recognition process). The numbers, for example, are reimbursement amounts, and the characters, for example, are the names of the submitter. The numbers need to be calculated specifically, for example, for reimbursement amounts, which may need to be multiplied by a corresponding proportionality coefficient (previously set) and compared with a preset amount value to determine whether it exceeds the preset amount value. In addition, the numbers can also include any feasible numbers, such as advances. After the first number and the second number are recognized, a preset calculation formula is called to obtain a calculation result, wherein the calculation formula corresponds to the first number and the second number, i.e., the first number and the second number come from the bill in the financial field, and the calculation formula is a corresponding preset any feasible financial calculation formula. Finally, the completed table template is the final processing result of the paper document, realizing full-automatic data processing based on paper documents.

[0089] In one embodiment, the character-bearing layer is pre-drawn with a first shape region drawn by a second ink and a second shape region drawn by a first ink, the first character is located in the first shape region in a direction perpendicular to the paper surface, and the first number is located in the second shape region in a direction perpendicular to the paper surface. The step S601 of splitting the first recognized character into a first character and a first number using the processing model comprises:

[0090] S6011, obtaining the first shape region appearing as a second color in the flipped picture, and obtaining the second shape region appearing as a first color in the flipped picture;

[0091] S6012, recording the first recognized character in the first shape region of the flipped picture as a first character, and recording the first recognized character in the second shape region of the flipped picture as a first number.

[0092] As described above, the first recognized character is split into a first character and a first number by using the processing model. The present application adopts a special design to improve the speed of splitting the first recognized character. That is, the character bearing layer is pre-drawn with a first shape area drawn by a second ink and a second shape area drawn by a first ink, the first character is located in the first shape area in a direction perpendicular to the paper surface, and the first number is located in the second shape area in a direction perpendicular to the paper surface. It is emphasized here that the first shape area corresponding to the first character is drawn by the second ink, and the second shape area corresponding to the first number is drawn by the first ink, which is an important distinction. The reason is that after using this setting, the shape areas drawn by two different inks, different shape areas, and different recognized characters (presenting different colors) can achieve as much data differentiation as possible, thereby making it easier to achieve full-automatic data processing based on paper files, and can be applied to more scenarios of data categories (such as the need to further divide the first number into multiple sub-numbers, etc.).

[0093] The data processing method based on paper files of the present application uses a preset interval layer separation judgment method to judge whether the interval layer in the paper file is separated; if the interval layer in the paper file is separated, a preset infrared flash and ultraviolet flash are turned on; a preset first camera is turned on, and the back of the paper file is photographed by using the first camera, thereby obtaining a back picture; the back picture is flipped to obtain a flipped picture corresponding to the back picture; the flipped picture is subjected to character recognition processing to obtain first recognized characters corresponding to the first front character image and second recognized characters corresponding to the second front character image; a preset processing model is called, and the first recognized characters and the second recognized characters are processed by using the processing model, thereby obtaining a processing result output by the processing model. Thus, the efficiency and accuracy of data processing based on paper files are improved.

[0094] Reference Figure 2The embodiment of the present application provides a data processing device based on a paper file, the paper file is composed of a direct contact layer, an ink layer, a spacing layer and a text bearing layer in an original state, the direct contact layer, the ink layer, the spacing layer and the text bearing layer are sequentially stacked, and the spacing layer can be separated under the condition that the relative positions of the direct contact layer, the ink layer and the text bearing layer are unchanged; the ink layer comprises a first region and a second region separated from each other, a first ink material in the first region presents a first color under infrared light, and the first ink material presents a third color under visible light; a second ink material in the second region presents a second color under ultraviolet light, and the second ink material presents a third color under visible light; and the device comprises:

[0095] A spacing layer judging unit is used to judge whether the spacing layer in the paper file is separated by using a preset spacing layer separation judging method; wherein, the unknown state refers to a state that the direct contact layer, the ink layer and the spacing layer in the paper file are not separated, or a state that one or more of the direct contact layer, the ink layer and the spacing layer in the paper file are separated;

[0096] A flash opening unit is used to open a preset infrared flash and ultraviolet flash if the spacing layer in the paper file is separated, so that the paper file is simultaneously in an infrared irradiation and ultraviolet irradiation environment;

[0097] A back picture obtaining unit is used to open a preset first camera, and take a picture of the back of the paper file by using the first camera, so as to obtain a back picture, wherein the back picture comprises a first back text image presenting a first color and a second back text image presenting a second color;

[0098] A flip picture obtaining unit is used to flip the back picture according to a preset left-right mirror flip processing method, so as to obtain a flip picture corresponding to the back picture, wherein the flip picture comprises a first front text image corresponding to the first back text image, and a second front text image corresponding to the second back text image;

[0099] A recognized text obtaining unit is used to perform text recognition processing on the flip picture by using a preset text recognition method, so as to obtain first recognized text corresponding to the first front text image, and second recognized text corresponding to the second front text image;

[0100] A processing result obtaining unit is used to call a preset processing model, and process the first recognized text and the second recognized text by using the processing model, so as to obtain a processing result output by the processing model.

[0101] The operations performed by the units, sub-units or modules described above correspond to the steps of the paper-based document data processing method of the foregoing embodiments one by one, and will not be described herein again.

[0102] In one embodiment, the direct contact layer, the ink layer, the spacing layer and the text bearing layer each have a light transmission region, the light transmission regions of the direct contact layer, the ink layer, the spacing layer and the text bearing layer are equal in spatial position in the vertical direction, and the light transmission of the light transmission region of the spacing layer is weaker than that of the light transmission regions of the other three layers; the spacing layer judging unit comprises:

[0103] The detection visible light generating sub-unit is configured to generate detection visible light above the light transmission region of the direct contact layer by using a preset visible light generator, so that the detection visible light passes through the light transmission region of the direct contact layer.

[0104] The light intensity signal obtaining sub-unit is configured to obtain a light intensity signal sensed by a preset light intensity sensor below the text bearing layer.

[0105] The light intensity threshold judging sub-unit is configured to judge whether the light intensity signal is greater than a preset light intensity threshold.

[0106] The spacing layer judging sub-unit is configured to judge that the spacing layer in the paper-based document is detached if the light intensity signal is greater than the preset light intensity threshold.

[0107] The operations performed by the units, sub-units or modules described above correspond to the steps of the paper-based document data processing method of the foregoing embodiments one by one, and will not be described herein again.

[0108] In one embodiment, the device further comprises:

[0109] The writing fracture point detecting unit is configured to detect the back picture according to a preset writing fracture point detection method, so as to obtain a number of writing fracture points.

[0110] The fracture point number threshold judging unit is configured to judge whether the number of writing fracture points is less than a preset fracture point number threshold.

[0111] The mirror image flipping instruction generating unit is configured to generate a mirror image flipping instruction if the number of writing fracture points is less than the preset fracture point number threshold, the mirror image flipping instruction being used to instruct to perform flipping processing on the back picture according to a preset left-right mirror image flipping processing method.

[0112] The operations performed by the units, sub-units or modules described above correspond to the steps of the paper-based document data processing method of the foregoing embodiments one by one, and will not be described herein again.

[0113] In one embodiment, the first recognized character and the second recognized character each include a character part and a number part; the processing result obtaining unit comprises:

[0114] a character and number splitting subunit configured to split the first recognized character into a first character and a first number and split the second recognized character into a second character and a second number by using the processing model;

[0115] a calculation result obtaining subunit configured to call a preset calculation formula and input the first number and the second number into the calculation formula to obtain a calculation result;

[0116] a processing result obtaining subunit configured to call a preset table template, fill the first character and the second character into preset character positions in the table template respectively, fill the calculation result into a preset number position in the table template, and record the filled table template as the processing result.

[0117] The units, subunits or modules described above are respectively used to perform operations corresponding to the steps of the data processing method based on paper files in the foregoing embodiments, and thus will not be described herein again.

[0118] In one embodiment, the character bearing layer is previously drawn with a first shape area drawn by a second ink and a second shape area drawn by a first ink, the first character is located in the first shape area in a direction perpendicular to a paper surface, and the first number is located in the second shape area in the direction perpendicular to the paper surface; the character and number splitting subunit comprises:

[0119] a shape area obtaining module configured to obtain a first shape area appearing as a second color in the flipped picture and obtain a second shape area appearing as a first color in the flipped picture;

[0120] a character and number obtaining module configured to record a first recognized character in the first shape area of the flipped picture as a first character and record a first recognized character in the second shape area of the flipped picture as a first number.

[0121] The units, subunits or modules described above are respectively used to perform operations corresponding to the steps of the data processing method based on paper files in the foregoing embodiments, and thus will not be described herein again.

[0122] The paper-based data processing device of the application adopts a preset interval layer disassembly judgment method to judge whether the interval layer in the paper document is disassembled; if the interval layer in the paper document is disassembled, a preset infrared flash and ultraviolet flash are turned on; a preset first camera is turned on, and the back of the paper document is photographed by using the first camera, so as to obtain a back picture; the back picture is flipped to obtain a flipped picture corresponding to the back picture; text recognition processing is performed on the flipped picture, so as to obtain first recognized text corresponding to the first front text image and second recognized text corresponding to the second front text image; a preset processing model is called, and the first recognized text and the second recognized text are processed by using the processing model, so as to obtain a processing result output by the processing model. Thus, the efficiency and accuracy of paper-based data processing are improved.

[0123] Reference Figure 3 In the embodiments of the application, a computer device, which can be a server, is also provided, and the internal structure of the computer device can be as shown in the figure. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for running the operating system and the computer program in the non-volatile storage medium. The database of the computer device is configured to store data used by the paper-based data processing method. The network interface of the computer device is configured to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement the paper-based data processing method.

[0124] The processor executes the paper-based data processing method, and the steps included in the method correspond to the steps of executing the paper-based data processing method of the foregoing embodiments one by one, and will not be described herein.

[0125] Those skilled in the art can understand that the structure shown in the figure is only a block diagram of part of the structure related to the scheme of the application, and does not constitute a limitation on the computer device to which the scheme of the application is applied.

[0126] The computer device of the present application adopts a preset interval layer separation judgment method to judge whether the interval layer in the paper file is separated; if the interval layer in the paper file is separated, a preset infrared flash and ultraviolet flash are turned on; a preset first camera is turned on, and the back of the paper file is photographed by using the first camera to obtain a back picture; the back picture is flipped to obtain a flipped picture corresponding to the back picture; the flipped picture is subjected to character recognition processing to obtain first recognized characters corresponding to the first front character image and second recognized characters corresponding to the second front character image; a preset processing model is called, and the first recognized characters and the second recognized characters are processed by using the processing model to obtain a processing result output by the processing model. Thus, the efficiency and accuracy of data processing based on paper files are improved.

[0127] An embodiment of the present application also provides a computer readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement a data processing method based on paper files, wherein the steps of the method correspond to the steps of the data processing method based on paper files of the foregoing embodiments one by one, and details are not repeated here.

[0128] The computer readable storage medium of the present application adopts a preset interval layer separation judgment method to judge whether the interval layer in the paper file is separated; if the interval layer in the paper file is separated, a preset infrared flash and ultraviolet flash are turned on; a preset first camera is turned on, and the back of the paper file is photographed by using the first camera to obtain a back picture; the back picture is flipped to obtain a flipped picture corresponding to the back picture; the flipped picture is subjected to character recognition processing to obtain first recognized characters corresponding to the first front character image and second recognized characters corresponding to the second front character image; a preset processing model is called, and the first recognized characters and the second recognized characters are processed by using the processing model to obtain a processing result output by the processing model. Thus, the efficiency and accuracy of data processing based on paper files are improved.

[0129] Further, the computer readable storage medium can mainly include a storage program area and a storage data area, wherein the storage program area can store an operating system, at least one application required by a function, and the like; and the storage data area can store data created according to the use of a blockchain node and the like.

[0130] The blockchain referred to in the present application is a new application mode of distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm and other computer technologies. The blockchain is essentially a decentralized database, which is a series of data blocks associated using cryptographic methods, each data block containing information of a batch of network transactions, used to verify the validity of the information (anti-fake) and generate the next block. The blockchain can include a blockchain underlying platform, a platform product service layer, and an application service layer, etc.

[0131] The blockchain underlying platform can include user management, basic services, smart contracts, and operation monitoring processing modules. Among them, the user management module is responsible for the identity information management of all blockchain participants, including maintaining the generation of public and private keys (account management), key management, and the maintenance of the correspondence between the real identity of the user and the blockchain address (permission management), etc., and under authorization, supervising and auditing the transaction situation of certain real identities, providing rule configuration for risk control (risk audit); the basic service module is deployed on all blockchain node devices to verify the validity of business requests, and after completing the consensus for valid requests, it is recorded on the storage. For a new business request, the basic service first performs interface adaptation analysis and authentication processing (interface adaptation), then encrypts the business information through a consensus algorithm (consensus management), and after encryption, the complete and consistent transmission is transmitted to the shared ledger (network communication), and is recorded and stored; the smart contract module is responsible for the registration and issuance of contracts, the triggering and execution of contracts, and developers can define contract logic through a certain programming language, publish it to the blockchain (contract registration), call keys or other event triggers for execution according to the logic of the contract terms, complete the contract logic, and also provide contract upgrade and cancellation functions; the operation monitoring module is mainly responsible for the deployment, configuration modification, contract setting, cloud adaptation in the product release process, and the real-time state visualization output in the product operation, such as alarm, monitoring network condition, monitoring node device health status, etc.

[0132] The present application can be applied in the field of smart city, thereby promoting the construction of smart city.

[0133] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, storage, databases, or other media in this application and in examples provided herein, unless specifically stated otherwise, can include non-volatile and / or volatile memory. Non-volatile memory can include, for example, read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include, for example, random access memory (RAM), or external cache memory. As an illustration and not a limitation, RAM is available in many forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), Synchlink DRAM (SLDRAM), Rambus DRAM (RDRAM), direct Rambus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0134] It should be noted that the terms "comprising", "including", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, a device, an article or a method that comprises a list of elements does not include only those elements recited, but can also include other elements not expressly listed or inherent to such process, device, article or method. Without further limitation, an element defined by the phrase "comprising a" does not exclude the presence of additional identical elements in the process, device, article or method that includes the element.

[0135] The above description is only the preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation using the content of the specification and drawings, or direct or indirect application in other related technical fields, is also included in the patent protection scope of the present application.

Claims

1. A data processing method based on paper documents, characterized by, The paper document is composed of a direct contact layer, an ink layer, a spacing layer and a text bearing layer in the original state, and the direct contact layer, the ink layer, the spacing layer and the text bearing layer are sequentially stacked; the ink layer comprises a first region and a second region separated from each other, and a first ink material in the first region presents a first color under infrared conditions; a second ink material in the second region presents a second color under ultraviolet conditions; The data processing method comprises: using a preset spacing layer disassembly judgment method to judge whether the spacing layer in the paper document is disassembled; wherein the unknown state refers to a state in which the direct contact layer, the ink layer and the spacing layer in the paper document are not disassembled, or a state in which one or more of the direct contact layer, the ink layer and the spacing layer in the paper document are disassembled; if the spacing layer in the paper document is disassembled, turn on the preset infrared flash and ultraviolet flash to make the paper document simultaneously in the environment of infrared irradiation and ultraviolet irradiation; turn on the preset first camera and use the first camera to take a picture of the back of the paper document, thereby obtaining a back picture, wherein the back picture comprises a first back text image presenting a first color and a second back text image presenting a second color; according to a preset left-right mirror image flipping processing method, flip the back picture to obtain a flipped picture corresponding to the back picture, wherein the flipped picture comprises a first front text image corresponding to the first back text image, and a second front text image corresponding to the second back text image; using a preset text recognition method, perform text recognition processing on the flipped picture, thereby obtaining first recognized text corresponding to the first front text image, and obtaining second recognized text corresponding to the second front text image; call a preset processing model and use the processing model to process the first recognized text and the second recognized text, thereby obtaining a processing result output by the processing model.

2. The paper document-based data processing method according to claim 1, characterized by, The direct contact layer, the ink layer, the spacing layer and the text bearing layer all have light transmission regions, and the spatial positions of the light transmission regions of the direct contact layer, the ink layer, the spacing layer and the text bearing layer in the vertical direction are equal, and the light transmission of the light transmission region of the spacing layer is weaker than that of the light transmission regions of the other three layers; The step of using a preset spacing layer disassembly judgment method to judge whether the spacing layer in the paper document is disassembled comprises: above the light transmission region of the direct contact layer, using a preset visible light generator to generate detection visible light, so that the detection visible light passes through the light transmission region of the direct contact layer; below the text bearing layer, obtaining a light intensity signal sensed by a preset light intensity sensor; judging whether the light intensity signal is greater than a preset light intensity threshold; if the light intensity signal is greater than the preset light intensity threshold, it is determined that the spacing layer in the paper document is disassembled.

3. The paper document based data processing method according to claim 1, wherein, The first camera is opened, and the back of the paper document is photographed by using the first camera, so as to obtain a back picture, wherein the back picture includes a first back text image in a first color and a second back text image in a second color. After the step of obtaining the back picture and before the step of performing a flip processing on the back picture according to a preset left-right mirror flip processing method to obtain a flip picture corresponding to the back picture, the data processing method further comprises: detecting the back picture according to a preset handwriting breakpoint detection method, so as to obtain a number of handwriting breakpoints; determining whether the number of handwriting breakpoints is less than a preset breakpoint threshold; if the number of handwriting breakpoints is less than the preset breakpoint threshold, a mirror flip instruction is generated, and the mirror flip instruction is used to instruct to perform a flip processing on the back picture according to a preset left-right mirror flip processing method.

4. The paper document based data processing method according to claim 1, wherein, The first recognized text and the second recognized text each include a text part and a number part. The step of processing the first recognized text and the second recognized text by using the processing model to obtain a processing result output by the processing model comprises: splitting the first recognized text into a first text and a first number and splitting the second recognized text into a second text and a second number by using the processing model; calling a preset calculation formula and inputting the first number and the second number into the calculation formula, so as to obtain a calculation result; calling a preset table template, filling the first text and the second text into preset text positions in the table template respectively, filling the calculation result into a preset number position in the table template, and recording the filled table template as the processing result.

5. The paper document based data processing method according to claim 4, characterized by, The text bearing layer has a first shape area drawn by second ink and a second shape area drawn by first ink in advance, the first text is located in the first shape area in a direction perpendicular to a paper surface, and the first number is located in the second shape area in the direction perpendicular to the paper surface. The step of splitting the first recognized text into a first text and a first number by using the processing model comprises: obtaining a first shape area appearing as the second color in the flip picture and obtaining a second shape area appearing as the first color in the flip picture; recording the first recognized text in the first shape area of the flip picture as the first text and recording the first recognized text in the second shape area of the flip picture as the first number.

6. A paper document based data processing apparatus, characterized by comprising: The paper document in an original state comprises a direct contact layer, an ink layer, a spacing layer and a text bearing layer, the direct contact layer, the ink layer, the spacing layer and the text bearing layer are sequentially stacked, and the spacing layer can be detached while the relative positions of the direct contact layer, the ink layer and the text bearing layer remain unchanged. The ink layer includes a first area and a second area separated from each other, and a first ink material in the first area appears as a first color under infrared conditions. The second ink material in the second region exhibits a second color under ultraviolet conditions; the device comprises: The interval layer judgment unit is configured to judge whether the interval layer in the paper document is detached by using a preset interval layer detachment judgment method; wherein, the unknown state refers to a state in which the direct contact layer, the ink layer, and the interval layer in the paper document are not detached, or a state in which one or more of the direct contact layer, the ink layer, and the interval layer in the paper document are detached; The flash opening unit is configured to open a preset infrared flash and an ultraviolet flash if the interval layer in the paper document is detached, so that the paper document is simultaneously in an infrared irradiation and ultraviolet irradiation environment; The back picture acquisition unit is configured to open a preset first camera and take a picture of the back of the paper document by using the first camera, thereby obtaining a back picture, wherein the back picture includes a first back text image exhibiting a first color and a second back text image exhibiting a second color; The flip picture acquisition unit is configured to perform flip processing on the back picture according to a preset left-right mirror flip processing method, thereby obtaining a flip picture corresponding to the back picture, wherein the flip picture includes a first front text image corresponding to the first back text image, and a second front text image corresponding to the second back text image; The recognized text acquisition unit is configured to perform text recognition processing on the flip picture by using a preset text recognition method, thereby obtaining a first recognized text corresponding to the first front text image, and obtaining a second recognized text corresponding to the second front text image; The processing result acquisition unit is configured to call a preset processing model and use the processing model to process the first recognized text and the second recognized text, thereby obtaining a processing result output by the processing model.

7. The paper document based data processing apparatus according to claim 6, wherein The direct contact layer, the ink layer, the interval layer, and the text bearing layer all have light transmission regions, the spatial positions of the light transmission regions of the direct contact layer, the ink layer, the interval layer, and the text bearing layer in the vertical direction are equal, and the light transmission property of the light transmission region of the interval layer is weaker than that of the light transmission regions of the other three layers; The interval layer judgment unit comprises: The detection visible light generation subunit is configured to generate detection visible light above the light transmission region of the direct contact layer by using a preset visible light generator, so that the detection visible light passes through the light transmission region of the direct contact layer; The light intensity signal acquisition subunit is configured to acquire a light intensity signal sensed by a preset light intensity sensor below the text bearing layer; The light intensity threshold judgment subunit is configured to judge whether the light intensity signal is greater than a preset light intensity threshold; The interval layer determination subunit is configured to determine that the interval layer in the paper document is detached if the light intensity signal is greater than the preset light intensity threshold.

8. The paper document based data processing apparatus according to claim 6, wherein The device further comprises: The writing fracture point detection unit is configured to detect the back picture according to a preset writing fracture point detection method, thereby obtaining a number of writing fracture points. A breaking point quantity threshold judging unit is configured to judge whether the quantity of the breaking points of the handwriting is less than a preset breaking point quantity threshold. A mirror flipping instruction generating unit is configured to generate a mirror flipping instruction if the quantity of the breaking points of the handwriting is less than the preset breaking point quantity threshold, the mirror flipping instruction being used to instruct to perform a flipping processing on the back picture according to a preset left-right mirror flipping processing method. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The processor executes the computer program to implement the steps of the data processing method in any one of claims 1 to 5.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the data processing method in any one of claims 1 to 5.

Images