阅读说明：本技术 信用报告自助解读设备 (Credit report self-service interpretation equipment ) 是由 李俊鹏 于 2020-12-23 设计创作，主要内容包括：本发明涉及一种信用报告自助解读设备,包括：触摸显示屏、柜体以及设置于柜体中的扫描仪和主机；触摸显示屏设置于柜体的上部并和主机连接；柜体上和扫描仪相适配的位置分别设有资料入口和资料出口,扫描仪用于对信用报告扫描,并向主机发送相应的扫描文件；主机用于对扫描文件进行解读,并将解读信息通过触摸显示屏进行展示。本发明的有益效果是：通过扫描仪对信用报告进行扫描,获得信用报告的扫描文件,再由主机对相应的扫描文件进行识别,从而解析出的解读信息通过触摸显示屏进行展示,实现了信用报告解析的自动化,从而提高了解析的效率,弥补了人工解析的不足。(The invention relates to a credit report self-service interpretation device, which comprises: the intelligent cabinet comprises a touch display screen, a cabinet body, a scanner and a host which are arranged in the cabinet body; the touch display screen is arranged at the upper part of the cabinet body and is connected with the host; a data inlet and a data outlet are respectively arranged at the positions on the cabinet body, which are matched with the scanner, and the scanner is used for scanning the credit report and sending corresponding scanning files to the host; the host is used for reading the scanning file and displaying reading information through the touch display screen. The invention has the beneficial effects that: the credit report is scanned through the scanner, the scanning file of the credit report is obtained, and then the corresponding scanning file is identified through the host, so that the analyzed reading information is displayed through the touch display screen, the automation of credit report analysis is realized, the analysis efficiency is improved, and the defect of manual analysis is overcome.)

1. A credit report self-interpretation device, comprising: the intelligent cabinet comprises a touch display screen, a cabinet body, a scanner and a host which are arranged in the cabinet body;

the touch display screen is arranged at the upper part of the cabinet body and is connected with the host;

a data inlet and a data outlet are respectively arranged at the positions, matched with the scanner, on the cabinet body, the scanner is used for scanning the credit report and sending corresponding scanning files to the host;

the host is used for reading the scanning file and displaying reading information through the touch display screen.

2. The credit report self-service interpretation device according to claim 1, further comprising a speaker disposed on the cabinet, wherein the speaker is connected to the host computer for broadcasting corresponding interpretation information.

3. The credit report self-service interpretation equipment according to claim 2, further comprising a camera arranged above the touch display screen, wherein the camera is connected with the host computer and used for acquiring a face image and identifying the identity.

4. The credit report self-service interpretation device of claim 3, wherein the host computer comprises a text recognition module for marking out the location information of each plate in the scan file.

5. The credit report self-service interpretation apparatus of claim 4, wherein the host further comprises a form identification module for marking out form field location information within each slab.

6. The credit report self-interpretation device of claim 5, wherein the host further comprises a configuration output module for assembling the marked location information of the plate and the table field location information into the structured data.

7. The credit report self-service interpretation apparatus of claim 6, wherein the host further comprises a data extraction module for extracting corresponding detailed data based on the data item name of each plate.

8. The credit report self-service interpretation apparatus of claim 7, wherein the host further comprises a data classification module for classifying different types of detailed data.

9. The credit report self-service interpretation device of claim 8, wherein the host further comprises a data cleaning module for deleting the same type of data, supplementing and replacing the identified logical error.

10. The credit report self-service interpretation apparatus of claim 9, further comprising: and the classification storage module is used for storing all data into the database for the calling of the data based on different types and different fields.

Technical Field

The invention belongs to the technical field of credit inquiry, and particularly relates to a credit report self-service interpretation device.

Background

At present, with the development of the domestic credit investigation market, the credit report query volume of the credit investigation center of the Chinese people's bank is increasing day by day, and the Chinese people's bank opens the credit report query in the online bank of the private bank of each province and the state.

With the increasing demand of credit report interpretation according to the needs of convenience and convenience of inquiry, users who inquire at the business network of people's bank can choose the staff seeking the business network to interpret. The users who inquire at the financial institution agent network and the internet do not have corresponding personnel to read.

And people's bank staff reads and also needs to read one by one after looking over page by page item by item, and is inefficient and long in consumed time.

Disclosure of Invention

In order to solve the problems of inconvenience in manual interpretation and low efficiency in the prior art, the invention provides a credit report self-service interpretation device which has the characteristics of no need of manual interpretation, high interpretation efficiency and the like.

The technical scheme adopted by the invention is as follows:

a credit report self-interpretation device, comprising: the intelligent cabinet comprises a touch display screen, a cabinet body, a scanner and a host which are arranged in the cabinet body;

the touch display screen is arranged at the upper part of the cabinet body and is connected with the host;

a data inlet and a data outlet are respectively arranged at the positions, matched with the scanner, on the cabinet body, the scanner is used for scanning the credit report and sending corresponding scanning files to the host;

the host is used for reading the scanning file and displaying reading information through the touch display screen.

Further, the credit report self-service interpretation equipment further comprises a loudspeaker arranged on the cabinet body, and the loudspeaker is connected with the host machine and used for broadcasting corresponding interpretation information.

Furthermore, the credit report self-service interpretation equipment further comprises a camera arranged above the touch display screen, and the camera is connected with the host and used for acquiring the face image and identifying the identity.

Further, the host computer includes a text recognition module for marking the position information of each plate in the scan file.

Further, the host computer further comprises a table identification module for marking the table field position information in each board block.

Further, the host further comprises a structure output module, configured to assemble the marked location information of the plate and the table field location information into structured data.

Further, the host computer further comprises a data extraction module, configured to extract corresponding detailed data based on the data item name of each plate.

Further, the host computer further comprises a data classification module for classifying different types of detailed data.

Further, the host computer further comprises a data cleaning module for deleting the same type of data and supplementing and replacing the identified logic error place.

Further, the credit report self-service interpretation device further comprises: and the classification storage module is used for storing all data into the database for the calling of the data based on different types and different fields.

The invention has the beneficial effects that: the credit report is scanned through the scanner, the scanning file of the credit report is obtained, and then the corresponding scanning file is identified through the host, so that the analyzed reading information is displayed through the touch display screen, the automation of credit report analysis is realized, the analysis efficiency is improved, and the defect of manual analysis is overcome.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

FIG. 1 is a block diagram of a cabinet provided in accordance with an exemplary embodiment;

FIG. 2 is a schematic diagram of a credit report self-interpretation device provided in accordance with an example embodiment;

FIG. 3 is a flow chart of the operation of a device provided in accordance with an exemplary embodiment.

Figure 1-camera; 2-data entry; 3-a loudspeaker; 4-data export.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the examples given herein without any inventive step, are within the scope of the present invention.

Referring to fig. 1 and 2, an embodiment of the present invention provides a credit report self-interpretation device, including: the intelligent cabinet comprises a touch display screen, a cabinet body, a scanner and a host which are arranged in the cabinet body;

the touch display screen is arranged at the upper part of the cabinet body and is connected with the host;

a data inlet 2 and a data outlet 4 are respectively arranged at the positions on the cabinet body matched with the scanner, and the scanner is used for scanning the credit report and sending corresponding scanning files to the host;

the host is used for reading the scanning file and displaying reading information through the touch display screen.

Specifically, the user passes through data entry 2 with the credit report of printing out, and the scanner can open the scanning function and be drawn into the credit report automatically and carry out scanning discernment when sensing that there is the paper to send out credit report data export 4 after the scanning, can set up corresponding accepting table in the exit and hold the credit report after the scanning convenience of customers takes. The scanner can generate a corresponding picture or PDF format of the credit report and send the picture or PDF format of the credit report to the host computer, the host computer can carry out corresponding classification identification and classification statistics according to the division of the forms on the basis of the picture recognition technology according to a preset induction format or according to the format of the credit report, and the credit report is generated by a plurality of statistical forms on the basis of the image recognition technology, and the statistical results after classification and analysis are displayed on the touch display screen for a user to select and view corresponding analysis data according to the requirement of the user, so that the analysis by special personnel is not needed, the automation of the analysis of the credit report is realized, and the analysis efficiency is improved, thereby providing convenience for the user and a bank.

In another embodiment of the present invention, the cabinet further includes a speaker 3 disposed on the cabinet, and the speaker 3 is connected to the host for broadcasting the corresponding interpretation information. Speaker 3 can cooperate touch display screen when showing corresponding data, can report corresponding content, provides convenience for the user that eyesight is not good. Meanwhile, the loudspeaker can be matched with the microphone to input voice, so that corresponding display and voice broadcasting can be realized according to voice instructions of users, and convenience in operation is provided for the users.

In some specific embodiments of the present invention, the mobile terminal further includes a camera 1 disposed above the touch display screen, and the camera 1 is connected to the host and is used for acquiring a face image and identifying an identity. Before a user uses the credit report self-service reading device to analyze, the user needs to collect face images through the camera, then carries out identity recognition through the background face recognition system, and after the identity recognition passes through, the user can start the touch display screen and the scanner to carry out work analysis, so that the use of the device is more accurately and effectively managed.

In other embodiments of the present invention and referring to the operational flow diagram of FIG. 3, the host computer includes a text recognition module for marking the location information of each plate in the scan file.

The host computer also includes a table identification module for marking table field location information within each board block.

The host computer also comprises a structure output module which is used for assembling the position information of the marked plate and the table field position information into structured data.

The host computer further comprises a data extraction module for extracting corresponding detailed data based on the data item name of each plate.

The host computer also comprises a data classification module which is used for classifying different types of detailed data.

The host computer also comprises a data cleaning module which is used for deleting the data with the same type and supplementing and replacing the identified logic error places.

Further comprising: and the classification storage module is used for storing all data into the database for the calling of the data based on different types and different fields.

As a specific implementation manner, the position information of each plate is identified and marked through character OCR; identifying the table field position marked in each board block through table OCR; the data identification marks are reassembled into structured data according to the original format; then extracting detailed data according to the name of the data item of each plate; classifying according to different types of data; processing the data according to the data type, deleting the data with the same type, and supplementing and replacing the identified logic error place; storing all data into a database according to different types and different fields; data can be called from the database and collected according to categories such as bad debt, overdue, loan, credit card, guarantee, credit granting institution, housing accumulation and the like; and finally, displaying all detail data according to the sequence of account staying, overdue, loan, credit card, guarantee, credit granting institution, housing accumulation fund and the like.

The process of OCR (Optical Character Recognition) refers to the process of an electronic device (such as a scanner or a digital camera) examining a Character printed on paper, determining its shape by detecting dark and light patterns, and then translating the shape into computer text by a Character Recognition method, including:

in the sub-steps of graying, binarization, noise reduction, tilt correction, character segmentation, etc., graying (gray processing) is performed first, and in the RGB model, if R is G or B, the color represents a grayscale color, where the value of R is G or B is called a grayscale value, so that each pixel of the grayscale image only needs one byte to store grayscale values (also called intensity values and luminance values), and the grayscale range is 0-255. The popular method is that a color picture is changed into a black and white picture, and the graying is generally carried out on the color picture by four methods, namely a component method, a maximum value method, an average value method and a weighted average method;

then, binarizing an image including a target object, a background and noise, and in order to directly extract the target object from a multi-valued digital image, the most common method is to set a threshold T and divide the image data into two parts by T: pixel groups larger than T and pixel groups smaller than T. The method is the most special method for researching gray level transformation, and the binary black-white picture does not contain gray, but only has two colors of pure white and pure black; the most important of binarization is the selection of threshold, which is generally divided into fixed threshold and adaptive threshold. The commonly used binarization methods are: bimodal, P-parametric, iterative, and OTSU.

In reality, digital images are often affected by interference of imaging equipment and external environment noise during digitization and transmission, and are called noisy images or noisy images. The process of reducing noise in digital images is called Image Denoising (Image Denoising) and the noise in images is originated from various aspects of Image acquisition, transmission, compression and the like. The types of noise are different, such as salt and pepper noise, gaussian noise, etc., and different processing algorithms are provided for different noises.

The image denoising method generally includes an average filter, an adaptive wiener filter, a median filter, a morphological noise filter, wavelet denoising, and the like.

The image needs to be rotated by a program to find a position which is considered to be the most possible horizontal position, and the cut-out image is probably the best effect.

The most common method for tilt correction is hough transform, which is based on the principle that an image is expanded to connect discontinuous characters into a straight line, thereby facilitating straight line detection. After the angle of the straight line is calculated, the inclined picture can be corrected to the horizontal position by utilizing a rotation algorithm.

Then, character segmentation is carried out, two characters on the same line are often close to each other during segmentation, overlapping in the vertical direction can occur sometimes, and the characters are considered as one character during projection, so that errors (most of the characters occur in English) during segmentation are caused; there is also a small gap in the projection of the left and right structures of the same character on the X-axis, and one character is mistakenly split into two characters (most of the characters occur in chinese language) during the splitting. Compared with line segmentation, the character segmentation is more difficult to preset an expected value of one character width, and if the projection of the cut character exceeds the expected value to be too large, the cut character is considered to be two characters; if the value is far less than the expected value, the gap is ignored, and the characters around the gap are combined into one character for recognition.

The characteristics are key information used for identifying characters, and each different character can be distinguished from other characters through the characteristics. For numeric and english letters, this feature extraction is relatively easy, with a total of 10+26 × 2 — 52 characters, and both small character sets. For Chinese characters, the difficulty of feature extraction is greater because the Chinese characters are a large character set at first; 3755 first-level Chinese characters which are most commonly used in national standard Chinese are used; finally, the Chinese characters have complex structures, many characters with similar shapes and larger characteristic dimensions.

Finally, extracting the characteristics of a character image, discarding the characteristics to a classifier, classifying the character image by the classifier, and telling the character which the characteristics should be recognized. The design of the classifier is our task. The design method of the classifier generally comprises the following steps: template matching, discriminant function, neural network classification, rule-based reasoning, etc., and will not be described herein. Before the actual recognition, the classifier is often trained, which is a process of supervised learning. There are also many mature classifiers, including SVM, CNN, etc.

Therefore, the spelling recognition is carried out according to the preset cutting mode such as the specific table area, and the contents which the user wants to view are finally presented.

The credit report self-service interpretation equipment provided by the embodiment of the invention realizes the automatic interpretation of the credit report, can effectively reduce the labor cost and the judgment error caused by manual interpretation, solves the problem of manual interpretation of the credit report, and effectively improves the interpretation efficiency.

In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

What has been described above includes examples of one or more embodiments. It is, of course, not possible to describe every conceivable combination of components or methodologies for purposes of describing the aforementioned embodiments, but one of ordinary skill in the art may recognize that many further combinations and permutations of various embodiments are possible. Accordingly, the embodiments described herein are intended to embrace all such alterations, modifications and variations that fall within the scope of the appended claims. Furthermore, to the extent that the term "includes" is used in either the detailed description or the claims, such term is intended to be inclusive in a manner similar to the term "comprising" as "comprising" is interpreted when employed as a transitional word in a claim. Furthermore, any use of the term "or" in the specification of the claims is intended to mean a "non-exclusive or".

The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.