CN114186532A - Order examination processing method and device - Google Patents
Order examination processing method and device Download PDFInfo
- Publication number
- CN114186532A CN114186532A CN202111527362.2A CN202111527362A CN114186532A CN 114186532 A CN114186532 A CN 114186532A CN 202111527362 A CN202111527362 A CN 202111527362A CN 114186532 A CN114186532 A CN 114186532A
- Authority
- CN
- China
- Prior art keywords
- examination
- document
- column
- text information
- data corresponding
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/103—Formatting, i.e. changing of presentation of documents
- G06F40/109—Font handling; Temporal or kinetic typography
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/103—Formatting, i.e. changing of presentation of documents
- G06F40/117—Tagging; Marking up; Designating a block; Setting of attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/191—Automatic line break hyphenation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
Abstract
A method and a device for processing examination papers are used for improving the efficiency and the accuracy of examination paper processing in the technical field of artificial intelligence. The method comprises the following steps: determining text information in each line in text information corresponding to the columns according to a row and column rule corresponding to the columns for each column included in the examination order identification result, adding a line change symbol between any two adjacent lines of text information to obtain examination order data corresponding to the columns and meeting the row and column rule, further auditing the examination order data corresponding to each column, storing the examination order data corresponding to each column into a preset database, and after the auditing is successful, generating a message in a preset format according to the examination order data corresponding to each column stored in the preset database. The scheme can automatically generate the message meeting the column control rule, not only can save the complexity of manual operation, but also can reduce the accidental error influence caused by the manual operation, and effectively improves the efficiency and the accuracy of the examination processing.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a method and a device for processing examination orders.
Background
The intelligent examination system is a system which is based on an artificial intelligence technology and combines a natural language processing technology and a machine learning and deep learning technology to carry out intelligent structured processing on unstructured information in the examination process. Because the intelligent document examination system can automatically identify the document to be examined and automatically generate the examination document identification result, the intelligent document examination system is favorable for better liberation of labor force, and is gradually one of the most common systems in the field of examination documents at present.
In the field of intelligent document examination, a SWIFT message is also required to be generated based on a document examination recognition result generated by an intelligent document examination system, and the SWIFT message strictly specifies the row and column arrangement of characters which can be contained in each column in the message, and the specification is called a column control rule. However, in the current stage of intelligent document examination system, when generating a document examination recognition result, the column control rule specified in the SWIFT message is not considered, so that when generating a corresponding SWIFT message, only the document in the document examination recognition result can be analyzed by the document examiner, and each analyzed line of document is input in a manual input mode, so that the message meeting the position control rule can be generated. Obviously, the mode of artificially generating the message wastes time and labor, and also increases the probability of generating errors by the order examiners, which is not beneficial to improving the efficiency and the accuracy of order examination processing.
In summary, there is a need for a document examination processing method to improve the efficiency and accuracy of document examination processing.
Disclosure of Invention
The embodiment of the invention provides a method and a device for processing examination papers, which are used for improving the efficiency and the accuracy of examination paper processing.
The method for processing the examination order provided by the embodiment of the invention comprises the following steps: firstly obtaining an examination order recognition result, wherein the examination order recognition result comprises text information corresponding to N columns recognized from a document to be examined, N is a positive integer, then determining the text information in each line in the text information corresponding to the columns according to the row and column rule corresponding to the columns aiming at each column in the N columns, adding a line change symbol between any two adjacent lines of text information to obtain examination order data corresponding to the columns and meeting the row and column rule, then examining the examination order data corresponding to the N columns, after the examination is completed, storing the examination order data corresponding to the N columns into a preset database, and finally after the examination of the document to be examined is successful, generating a message in a preset format according to the examination order data corresponding to the N columns stored in the preset database.
In the design, the examination order recognition result is automatically converted into examination order data meeting the column control rule specified by the message (such as SWIFT message) according to the row and column rule corresponding to the column, the message meeting the requirement can be automatically generated according to the examination order data meeting the column control rule specified by the message, the message meeting the requirement can be generated without artificially wasting time and labor, the complexity of manual operation can be saved, accidental error influence caused by manual operation can be reduced, and the efficiency and the accuracy of examination order processing are effectively improved.
In one possible design, the document examination recognition result may further include at least one keyword recognized from the document to be examined and a style label corresponding to each keyword in the at least one keyword, where the keyword may include a character recognized incorrectly in the document to be examined and/or entity information in the document to be examined. Under this condition, examine the data of examining the order that N fence level corresponds, include: rendering the key characters in the examination order data corresponding to the N columns according to the style label corresponding to each key character in at least one key character, displaying the document to be examined and the examination order data corresponding to the rendered N columns, and then receiving the operation of examination completion triggered by an examination person when the document to be examined is matched with the examination order data corresponding to the N columns, and determining that the examination of the examination order data corresponding to the N columns is completed. Wherein rendering may include color labeling and/or font adjustment.
In the design, the key characters in the examination order recognition result are rendered, so that the key characters have a clearer display effect when the examination order recognition result is displayed, the visualization of the examination order recognition result is increased, the examination personnel can conveniently correct the key characters in the examination order recognition result, and the error correction probability of the examination personnel is further reduced.
In one possible design, when the document to be audited is not matched with the examination order data corresponding to the N columns, the text information re-input by the examination personnel can be obtained for the unmatched columns, and according to the column rule corresponding to the columns, when the text information re-input is determined to reach the maximum line number in the column rule, the line change symbol is automatically generated.
In the above design, considering that the document examination person may not pass the examination because the automatically generated document examination data cannot strictly satisfy the column control rule due to some reasons, in this case, by automatically obtaining the text information re-input by the document examination person and automatically generating the line feed according to the line position control rule, the error in generating the document examination data can be compensated, and further, by means of automatic correction, the stored document examination data is ensured to strictly satisfy the line position control rule specified by the message.
In one possible design, in the process of obtaining the text information re-input by the examination personnel, if the examination personnel is detected to press a preset key, a linefeed character can be generated.
In the design, the examination order data is comprehensively subjected to line changing by combining the line position control rule and the artificial requirement, and the line changing can be performed according to the maximum line number in the line position control rule, so that the individual requirements of different examination orders (for example, the preference that some examination orders like to perform line breaking at a specified position) are met, and the flexibility of examination order processing is effectively improved.
In one possible design, when it is determined that one line of text information corresponding to any one column needs to be edited again, target text information to be edited can be obtained, when the length of the target text information is larger than the maximum column number corresponding to the column, the target text information is split into at least two lines according to the maximum column number corresponding to the column, and when the length of the text information is smaller than the maximum column number corresponding to the column, the text information and the next line of text information corresponding to the column are merged and then rearranged according to the maximum column number corresponding to the column.
In the design, the re-edited text information is automatically changed by combining the column control rule, so that not only can any line of text information corresponding to any column be re-edited according to requirements, but also the re-edited text information can meet the column control rule, and the accuracy of examination processing is ensured on the basis of improving the flexibility of examination processing.
In a second aspect, the present application provides an examination order processing apparatus, comprising: the acquiring unit is used for acquiring an examination order identification result, wherein the examination order identification result comprises text information corresponding to N columns identified from the document to be examined, and N is a positive integer; the column control unit is used for determining text information in each line in the text information corresponding to the columns according to the row and column rules corresponding to the columns aiming at each column in the N columns, and adding a line change symbol between any two adjacent lines of text information to obtain examination order data corresponding to the columns and meeting the row and column rules; the auditing unit is used for auditing the examination order data corresponding to the N fence positions, and storing the examination order data corresponding to the N fence positions into a preset database after the auditing is finished; and the generating unit is used for generating a message in a preset format according to the examination order data corresponding to the N column positions stored in the preset database after the document to be examined is successfully examined.
In one possible design, the document examination recognition result may further include at least one keyword recognized from the document to be examined and a style label corresponding to each keyword in the at least one keyword, where the keyword includes a character recognized incorrectly in the document to be examined and/or entity information in the document to be examined. In this case, the auditing unit is specifically configured to: the method comprises the steps of rendering key characters in examination order data corresponding to N columns according to a style label corresponding to each key character in at least one key character, displaying a document to be examined and the examination order data corresponding to the N rendered columns, receiving an examination completion operation triggered by an examination person when the document to be examined is determined to be matched with the examination order data corresponding to the N columns, and determining that the examination order data corresponding to the N columns are examined and rendered to include color marking and/or font adjusting. Wherein rendering comprises color labeling and/or font adjustment.
In one possible design, the auditing unit is further configured to: when the document to be checked is not matched with the examination order data corresponding to the N columns, the text information re-input by the examination personnel is obtained for the unmatched columns, and according to the column rule corresponding to the columns, when the text information re-input is determined to reach the maximum line number in the column rule, the line change symbol is automatically generated.
In one possible design, the auditing unit is further configured to: and in the process of obtaining the text information re-input by the examination personnel, generating a line feed character when detecting that the examination personnel presses a preset key.
In one possible design, the auditing unit is further configured to: when it is determined that one line of text information corresponding to any one field needs to be edited again, target text information to be edited is obtained, when the length of the target text information is larger than the maximum column number corresponding to the field, the target text information is split into at least two lines according to the maximum column number corresponding to the field, and when the length of the text information is smaller than the maximum column number corresponding to the field, the text information and the next line of text information corresponding to the field are merged and then rearranged according to the maximum column number corresponding to the field.
In a third aspect, the present application provides an electronic device comprising at least one processor and interface circuitry for providing data or code instructions for the at least one processor, the at least one processor being configured to implement the method as designed in any one of the first aspects above by logic circuitry or executing the code instructions.
In a fourth aspect, the present application provides a computer readable storage medium having stored thereon a computer program/instructions which, when executed by a processor, implement a method as designed in any one of the above first aspects.
In a fifth aspect, a computer program product comprises computer programs/instructions which, when executed by a processor, implement the method as designed in any one of the first aspects above.
For the beneficial effects of the second aspect to the fifth aspect, please refer to the technical effects that can be achieved by the corresponding design in the first aspect, and the detailed description is omitted here.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 schematically illustrates an architecture diagram of an intelligent policy system provided by an embodiment of the present application;
fig. 2 is a schematic flow chart illustrating an examination order processing method provided by an embodiment of the present application;
fig. 3 is a schematic diagram illustrating a presentation effect of examination order data provided by an embodiment of the present application;
fig. 4 is a schematic diagram illustrating a presentation form of a message provided in an embodiment of the present application;
fig. 5 is a schematic structural diagram schematically illustrating an examination order processing apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Before describing particular embodiments, some of the terms used below are exemplified:
(1) and (4) a service node.
In the embodiment of the present application, a service node refers to a node capable of providing a service (also referred to as an interface or a function), and the node may be a hardware device, such as a server, a computer, or the like, or a software carrier, such as firmware, or the like.
(2) A SWIFT message.
In the embodiment of the application, the data after being audited by the intelligent auditing system needs to generate the SWIFT message and feed back the SWIFT message to the client. The SWIFT message is composed of fields, each of which represents a type of content, and the fields may also be referred to as layouts. And, each field corresponds to a format that specifies exactly how many letters, numbers, or characters there are in the field at most, and the maximum row and maximum column of those letters, numbers, or characters. For example, when a field corresponds to a format: 35 x 3 means that each row in the field contains 35 characters at most and 3 rows at most.
(3) A rich text box.
In the embodiment of the application, the rich text box is a text processing mode which is embedded in the browser and can perform higher-level rendering on the plain text to enable the text to present a richer sensory state, wherein the rendering mode can include colors and/or fonts and the like.
The embodiments of the present application will be described in detail with reference to the drawings in the embodiments of the present application.
Fig. 1 schematically illustrates an architecture of an intelligent document examination system according to an embodiment of the present invention, as shown in fig. 1, the intelligent document examination system 100 may include a preprocessing node 110 and a service node 120, and the service node 120 may include a backend 121 and a frontend 122. The backend 121 refers to a page invisible to a user, and is generally used to implement underlying business logic, and in the field of intelligent document examination, the backend may specifically include, but is not limited to, service platform design, service interface design, service function implementation, and the like of the intelligent document examination. The front end 122 is a user-visible interface, and is generally used to implement presentation development of a web page, and may specifically include development design of an audit page in the field of intelligent document examination.
In addition, as shown in fig. 1, the front-end processing node 110 and the back-end 121, and the back-end 121 and the front-end 122 may be connected to each other, and the connection may include, but is not limited to, wired or wireless, and the connection is used to implement interactive communication between the two ends.
Based on the system architecture illustrated in fig. 1, fig. 2 exemplarily shows a flowchart of an examination order processing method provided in an embodiment of the present application, and the method is applicable to a service node in an intelligent examination order system, such as the service node 120 illustrated in fig. 1. As shown in fig. 2, the method includes:
In the step 201, the document to be checked may be, for example, an electronic document generated by a customer through a bank counter scanning while a bank transacts business, and may be, for example, an electronic document of a credit card, or other financial or non-financial electronic documents, and the like, which is not specifically limited in this embodiment of the present application.
For example, as shown in fig. 1, the preprocessing node 110 may further be connected to a bank scanner, and each time the bank scanner obtains one document to be checked of the customer, the bank scanner may send the document to be checked to the preprocessing node 110. After the pre-processing node 110 receives each document to be audited, the document to be audited may be automatically identified to obtain an examination-order identification result of the document to be audited, and the document to be audited and the examination-order identification result are sent to the service node 120 together. The automatic recognition may include Optical Character Recognition (OCR), and may also include other recognition, such as image recognition.
In a specific example, the preprocessing node 110 may obtain the examination order recognition result through the following steps one to six:
firstly, the preprocessing node 110 performs OCR on a document to be checked to identify all characters contained in the document to be checked;
step two, the preprocessing node 110 performs language/semantic segmentation on all recognized characters to obtain words or phrases contained in the document to be audited;
and step three, the preprocessing node 110 corrects the recognized words or phrases according to a preset error correction relation table, and determines the words or phrases with wrong recognition in the recognized words or phrases and the corresponding words or phrases with corrected errors. The preset error correction relation table can be obtained by training according to an erroneous recognition result in a historical recognition process, for example, if time is recognized as time for many times in the past recognition, the corresponding relation between the erroneous time and the correct time can be added in the preset error correction relation table;
step four, the preprocessing node 110 finds out entity contents which are concerned relatively from the corrected words or phrases according to a preset dictionary link, wherein the entity contents include but are not limited to customer names, bank geology and the like;
step five, the preprocessing node 110 determines the word or phrase belonging to each field according to the corrected word or phrase and the content corresponding to each field specified by the SWIFT message specification;
and step six, the preprocessing node 110 takes the corrected word or phrase obtained in the third step and the entity content identified in the fourth step as key characters, takes the word or phrase belonging to each column determined in the fifth step as text information corresponding to each column, and generates an examination order identification result according to the key characters and the text information corresponding to each column.
It should be noted that the above-mentioned contents are only described by taking an example that the keyword includes a word or a phrase with a wrong recognition and an entity content, and in an actual operation, the keyword may further include other contents, such as a service type, and the like, which is not specifically limited in this embodiment of the application.
In the step 202, after receiving the document to be reviewed and the examination-order recognition result sent by the front-end processing node 110, the service node 120 may first obtain text information corresponding to each of N columns included in the examination-order recognition result, then determine text information in each line in the text information corresponding to each column according to the SWIFT message specification and the rank rule corresponding to each column, and add a line change symbol between any two adjacent lines of text information to obtain examination-order data corresponding to each column and meeting the rank rule.
For example, assuming that the line break is denoted as "/p", the number of characters of the text data corresponding to a certain field is 100, and the row and column rule corresponding to the field is 35 × 3, the front end 122 determines that the first line of text data in the examination data corresponding to the field includes 35 characters, the second line of text data includes 35 characters, and the third line of text data includes 30 characters, based on which the background code of the examination data corresponding to the field can be denoted as:
< p newine ═ 0 "> first line text data (35) </p >
< p newine ═ 0 "> second line text data (35) </p >
< p neweline ═ 0 "> third line text data (30) </p >
Therefore, in the background code, the line between any two adjacent lines of text data is changed through the line changing symbol, so that the examination order data can be represented into a line changing format when being displayed, and can be stored in a line changing format when being subsequently stored in a preset database. In this way, even if the examination data is subsequently obtained from the preset database, the service node 120 can automatically and smoothly generate the SWIFT message because the linefeed format of the examination data itself satisfies the format of the SWIFT message.
For example, as shown by continuing with fig. 1, the document to be audited and the examination-document recognition result sent by the pre-processing node 110 may be sent to the back end 121, after the back end 121 receives the two pieces of information, the error-corrected word or phrase included in the examination-document recognition result may be obtained first, then the spelling check is performed on the error-corrected word or phrase, whether each error-corrected word or phrase is correct is determined, then, according to the preset correspondence between the type of the key character and the style label, a first style label corresponding to the correct type of error correction is added to the determined correct word or phrase, a second style label corresponding to the error-corrected type is added to the determined incorrect word or phrase, a third style label corresponding to the type of entity is added to the entity content included in the examination-document recognition result, then the examination-document recognition result and the examination-document to be audited are sent to the front end 122 in the service node 120, so that the front end 122 performs the above-mentioned step 202 on the examination paper identification result added with the style label to obtain examination paper data corresponding to each field.
Further exemplarily, table 1 shows an illustration of a correspondence table between preset key character types and style labels provided in an embodiment of the present application:
TABLE 1
| Type of keyword | Style label | Rendering method |
| Error correction correct type | First style label | Red colour |
| Error correction error type | Second style label | Green colour |
| Entity type | Third style label | Blue color |
As shown in table 1, the preset correspondence between the keyword types and the style labels may include a plurality of keyword types, a style label corresponding to each keyword type in the plurality of keyword types, and a rendering manner corresponding to each style label, where the rendering manner may include, but is not limited to, color and/or font.
And 203, the service node audits the examination order data corresponding to the N fence positions, and after the audit is completed, the examination order data corresponding to the N fence positions are stored in a preset database.
For example, the preset correspondence between the type of the key character and the style label may be stored in the backend 121 and the frontend 122 in advance, and the intelligent document examination system 100 may be agreed with the document examiner in advance. Thus, after obtaining the examination order data satisfying the rank rule corresponding to the N columns, the front end 122 may add rendering to the error-corrected word or phrase, the correct word or phrase, and the text content of the entity type and other key characters according to the corresponding relationship indicated in table 1 and the style label corresponding to each key character in the examination order data to obtain rendered examination order data, and then display the rendered examination order data and the document to be examined to the examination staff together, so that the examination staff examines the key characters including the rendering characteristics in the examination order data according to the document to be examined, and determine whether the rank format displayed by the examination order data satisfies the SWIFT message specification. If the two audits pass, the order auditor can click the button that passes the audits, so that the front end 122 can store the order auditing data corresponding to the N columns in the preset database. Therefore, the key characters are rendered before the examination order data are displayed, so that the key characters have a clearer display effect when the examination order data are displayed, the visualization of the examination order data is increased, the examination order personnel can conveniently correct the key characters in the examination order data, and the error correction probability of the examination order personnel is further reduced.
For example, fig. 3 shows a schematic diagram of a presentation effect of the examination order data provided in the embodiment of the present application, as shown in fig. 3, in the examination order data corresponding to the field "Name", the front end 122 uses a blue rendering entity Name "interactive" and uses a red rendering error-correcting phrase "error", and in the examination order data corresponding to the field "Address", the front end 122 does not perform rendering.
Further exemplarily, when the document examination personnel fails to examine the keyword characters containing the rendering features in the document examination data or determines that the row and column format displayed by the document examination data does not satisfy the specification of the SWIFT message, the document examination personnel may further modify the examination data corresponding to the column to which the keyword characters which do not pass the examination or the column format does not satisfy. Specifically, the document examiner may click on the position of the field to be modified on the front end 122 and re-input the text information, and after receiving the text information, the front end 122 may automatically generate a line feed character according to the line and column rule corresponding to the current field every time it is determined that the re-input text information reaches the maximum line number in the line and column rule, and then restart counting the text information and repeat the above process until the document examiner finishes inputting. Therefore, by automatically obtaining the text information re-input by the examination order personnel and automatically generating the line feed character according to the position control rule, even if the examination order data automatically generated cannot strictly meet the column control rule due to some reasons and the examination order personnel cannot pass the examination order, the error in the generation of the examination order data can be made up in an automatic correction mode so as to ensure that the stored examination order data strictly meets the position control rule specified by the message.
Further exemplary, considering that the document examiners may also have their own behavior habits, for example, some document examiners tend to make a sentence break after a complete sentence position, and making a feed according to the maximum line in the line and row control rules is likely not to satisfy the complete sentence position sentence break rule. In this case, in order to satisfy the behavior habit of the document examiner while using the row and column control rule, the front end 122 may also generate a lineup symbol if it detects that the document examiner presses a preset button while obtaining the text information re-input by the document examiner. The preset key may be a key predetermined by the order taker and the front end 122, and may be any single key or a combination key on the keyboard. For example, assuming that the default key is an enter key, the row and column control rule corresponding to a certain field is 35 × 3, during the process of re-input by the examiner, the enter key is pressed when the 30 th character is input, the front end 122 may add a linefeed character after the 30 th character, then start to re-count from the 31 st character input by the examiner, before counting up to 65 characters, if the enter key is not detected all the time, until counting up to 65 characters, the front end 122 may add the next linefeed character after the 65 th character. In the example, the examination order data is comprehensively subjected to line changing by combining the line position control rule and the artificial requirement, and the line changing can be performed according to the maximum line number in the line position control rule, so that the individual requirements of different examination personnel are met, and the flexibility of examination order processing is effectively improved.
Further exemplarily, when the document auditor audits the displayed content, if a request sent by the client is received again, where the request is used to indicate that a line of text information corresponding to any one of the fields needs to be edited again, the document auditor may further modify audit data corresponding to the text information that needs to be edited again. Specifically, the document auditor may click the position of the field to be modified on the front end 122 and re-input the target text information to be edited, and at this time, after receiving the target text information to be edited, the front end 122 detects the maximum number of columns in the line position control rule corresponding to the target text information and the current field. When the length of the target text message is greater than the maximum column number corresponding to the field, the front end 122 may split the target text message into at least two rows according to the maximum column number corresponding to the field. And when the length of the text information is smaller than the maximum column number corresponding to the column, combining the text information and the next line of text information corresponding to the column, and then rearranging according to the maximum column number corresponding to the column. Of course, in this process, the front end 122 may also generate a lineup if the document auditor also presses a preset button after a certain input character. In the design, the re-edited text information is automatically changed by combining the column control rule, so that not only can any line of text information corresponding to any column be re-edited according to requirements, but also the re-edited text information can meet the column control rule, and the accuracy of examination processing is ensured on the basis of improving the flexibility of examination processing.
It should be noted that the rendering operation and the field control operation on the text message may be implemented by a rich text box component on the front end 122, or may also be implemented by other components capable of implementing the rendering function and the field control function, which is not specifically limited in this application.
And step 204, after the document to be checked is successfully checked, the service node generates a message in a preset format according to the check data corresponding to the N columns stored in the preset database.
In step 204, after the document to be audited and the document audit data corresponding to the N columns are completed, the document auditor may further perform other audits on the document to be audited, for example, determine whether the current service to be audited of the client is normal, and if so, click the button for generating the SWIFT message. After detecting that the document examiner clicks the button, the front end 122 can obtain document examination data corresponding to the N positions stored in the preset database, generate a SWIFT message based on the document examination data corresponding to the N positions, send the SWIFT message back to the rear end 121, and further forward the SWIFT message to the bank through the rear end 121, and inform the customer that the document examination is passed through the bank.
Based on the examination data illustrated in fig. 3, fig. 4 exemplarily shows a presentation form schematic diagram of a message provided in the embodiment of the present application, as shown in fig. 4, in this example, since the examination data satisfies the row and column control rule of the SWIFT message when being stored in the preset database, the message generated by the front end 122 based on the examination data stored in the preset database also satisfies the row and column control rule of the SWIFT message.
In the embodiment of the application, the examination order recognition result is automatically converted into the examination order data meeting the column control rule specified by the message (such as SWIFT message) according to the column rule corresponding to the column, so that the message meeting the requirement can be automatically generated according to the examination order data meeting the column control rule specified by the message, and the examination personnel does not need to manually change the line according to the number of the counted words, thereby greatly facilitating the operation of examining and verifying the examination order recognition result by the examination personnel and being beneficial to reducing the error probability of the SWIFT message sent subsequently by the system. Moreover, the examination order data can be visually supplemented by rendering before being displayed, the examination order data can be further improved in visual rendering, the examination and verification experience of the examination personnel can be further improved, the examination and verification process of the examination personnel can be facilitated, and the efficiency of examination order processing can be improved.
For the above method flow, an examination order processing apparatus is further provided in the embodiments of the present application, and the specific content of the apparatus may be implemented by referring to the above method.
Fig. 5 is a schematic structural diagram schematically illustrating an examination order processing apparatus according to an embodiment of the present invention, and as shown in fig. 5, the apparatus includes:
the acquiring unit 501 is configured to acquire an examination order identification result, where the examination order identification result includes text information corresponding to N columns identified from a document to be examined, where N is a positive integer;
a column control unit 502, configured to determine, for each column of the N columns, text information in each line in the text information corresponding to the column according to a row-column rule corresponding to the column, and add a line break between any two adjacent lines of text information to obtain examination order data corresponding to the column, where the examination order data satisfies the row-column rule;
the auditing unit 503 is configured to audit the examination order data corresponding to the N hurdle positions, and after the auditing is completed, store the examination order data corresponding to the N hurdle positions in a preset database;
the generating unit 504 is configured to generate a message in a preset format according to the examination order data corresponding to the N columns stored in the preset database after the document to be examined is successfully examined.
In one possible design, the document examination recognition result may further include at least one keyword recognized from the document to be examined and a style label corresponding to each keyword in the at least one keyword, where the keyword includes a character recognized incorrectly in the document to be examined and/or entity information in the document to be examined. In this case, the auditing unit 503 is specifically configured to: the method comprises the steps of rendering key characters in examination order data corresponding to N columns according to a style label corresponding to each key character in at least one key character, displaying a document to be examined and the examination order data corresponding to the N rendered columns, receiving an examination completion operation triggered by an examination person when the document to be examined is determined to be matched with the examination order data corresponding to the N columns, and determining that the examination order data corresponding to the N columns are examined and rendered to include color marking and/or font adjusting. Wherein rendering comprises color labeling and/or font adjustment.
In one possible design, the auditing unit 503 is further configured to: when the document to be checked is not matched with the examination order data corresponding to the N columns, the text information re-input by the examination personnel is obtained for the unmatched columns, and according to the column rule corresponding to the columns, when the text information re-input is determined to reach the maximum line number in the column rule, the line change symbol is automatically generated.
In one possible design, the auditing unit 503 is further configured to: and in the process of obtaining the text information re-input by the examination personnel, generating a line feed character when detecting that the examination personnel presses a preset key.
In one possible design, the auditing unit 503 is further configured to: when it is determined that one line of text information corresponding to any one field needs to be edited again, target text information to be edited is obtained, when the length of the target text information is larger than the maximum column number corresponding to the field, the target text information is split into at least two lines according to the maximum column number corresponding to the field, and when the length of the text information is smaller than the maximum column number corresponding to the field, the text information and the next line of text information corresponding to the field are merged and then rearranged according to the maximum column number corresponding to the field.
Based on the same inventive concept, the present application further provides an electronic device, which includes at least one processor and an interface circuit, where the interface circuit is configured to provide data or code instructions for the at least one processor, and the at least one processor is configured to implement the method according to fig. 2 by using logic circuits or executing the code instructions.
Based on the same inventive concept, the present application also provides a computer-readable storage medium, on which a computer program/instructions are stored, and when the computer program/instructions are executed by a processor, the computer program/instructions implement the method as described in fig. 2 above.
Based on the same inventive concept, the present application also provides a computer program product, which includes a computer program/instructions, and when the computer program/instructions are executed by a processor, the computer program/instructions implement the method as described in fig. 2 above.
From the above, it can be seen that: in the embodiment of the application, an examination order recognition result is obtained, the examination order recognition result includes text information corresponding to N columns recognized from a document to be examined, N is a positive integer, for each column of the N columns, text information in each line in the text information corresponding to the column is determined according to a column and row rule corresponding to the column, a line change symbol is added between any two adjacent lines of text information, examination order data corresponding to the column and meeting the column and row rule are obtained, then examination order data corresponding to the N columns are examined, after examination is completed, the examination order data corresponding to the N columns are stored in a preset database, and finally, after the examination of the document to be examined is successful, a message in a preset format is generated according to the examination order data corresponding to the N columns stored in the preset database. Therefore, the examination order recognition result is automatically converted into examination order data meeting the column control rule specified by the message (such as SWIFT message) according to the row and column rule corresponding to the column, the message meeting the requirement can be automatically generated according to the examination order data meeting the column control rule specified by the message, the message meeting the requirement can be generated without artificial time and labor waste, the complexity of manual operation can be saved, accidental error influence caused by the artificial operation can be reduced, and the efficiency and the accuracy of examination order processing are effectively improved.
It should be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A method of processing an order, the method comprising:
obtaining an examination order identification result, wherein the examination order identification result comprises text information corresponding to N columns identified from a document to be examined, and N is a positive integer;
for each column of the N columns, determining text information in each line in the text information corresponding to the column according to a line and row rule corresponding to the column, and adding a line break character between any two adjacent lines of text information to obtain examination data corresponding to the column and meeting the line and row rule;
auditing the examination order data corresponding to the N fence positions, and storing the examination order data corresponding to the N fence positions into a preset database after the auditing is finished;
and after the document to be audited is audited successfully, generating a message in a preset format according to the audit data corresponding to the N columns stored in the preset database.
2. The method according to claim 1, wherein the document examination recognition result further includes at least one keyword recognized from the document to be examined and a style label corresponding to each keyword in the at least one keyword, and the keyword includes a character which is recognized incorrectly in the document to be examined and/or entity information in the document to be examined;
the auditing the examination order data corresponding to the N column positions comprises:
rendering the key characters in the examination order data corresponding to the N columns according to the style label corresponding to each key character in the at least one key character, wherein the rendering comprises color marking and/or font adjustment;
displaying the document to be audited and the audited data corresponding to the N columns after the document to be audited and the document are rendered;
and when the document to be audited is matched with the examination data corresponding to the N banners, receiving the operation of auditing completion triggered by the examination personnel, and determining that the examination data corresponding to the N banners are audited completely.
3. The method of claim 2, wherein the method further comprises:
when the document to be audited is not matched with the audit data corresponding to the N columns, text information re-input by the audit staff is obtained for the unmatched columns, and according to the column and row rule corresponding to the columns, when the text information re-input is determined to reach the maximum line number in the column and row rule, a line change symbol is automatically generated.
4. The method of claim 3, wherein in obtaining the text information re-entered by the reviewer, the method further comprises:
and generating a line feed character when detecting that the order examiner presses a preset key.
5. The method of any of claims 2 to 4, further comprising:
when it is determined that one line of text information corresponding to any one field needs to be edited again, target text information to be edited is obtained, when the length of the target text information is larger than the maximum column number corresponding to the field, the target text information is split into at least two lines according to the maximum column number corresponding to the field, and when the length of the text information is smaller than the maximum column number corresponding to the field, the text information and the next line of text information corresponding to the field are merged and then rearranged according to the maximum column number corresponding to the field.
6. An apparatus for processing a document, the apparatus comprising:
the document examination device comprises an acquisition unit, a verification unit and a verification unit, wherein the acquisition unit is used for acquiring a document examination identification result, the document examination identification result comprises text information corresponding to N columns identified from a document to be verified, and N is a positive integer;
the column control unit is used for determining text information in each line in the text information corresponding to the column according to a row and column rule corresponding to the column aiming at each column in the N columns, and adding a line change symbol between any two adjacent lines of text information to obtain examination order data corresponding to the column and meeting the row and column rule;
the auditing unit is used for auditing the examination order data corresponding to the N fence positions, and storing the examination order data corresponding to the N fence positions into a preset database after the auditing is finished;
and the generating unit is used for generating a message in a preset format according to the examination data corresponding to the N columns stored in the preset database after the document to be examined is successfully examined.
7. The device of claim 6, wherein the document examination recognition result further includes at least one keyword recognized from the document to be examined and a style label corresponding to each keyword in the at least one keyword, and the keyword includes a character which is recognized incorrectly in the document to be examined and/or entity information in the document to be examined;
the auditing unit is specifically configured to:
rendering the key characters in the examination order data corresponding to the N columns according to the style label corresponding to each key character in the at least one key character, wherein the rendering comprises color marking and/or font adjustment;
displaying the document to be audited and the audited data corresponding to the N columns after the document to be audited and the document are rendered;
and when the document to be audited is matched with the examination data corresponding to the N banners, receiving the operation of auditing completion triggered by the examination personnel, and determining that the examination data corresponding to the N banners are audited completely.
8. An electronic device comprising at least one processor and interface circuitry for providing data or code instructions to the at least one processor, the at least one processor being configured to implement the steps of the method of any one of claims 1 to 5 by logic circuitry or executing code instructions.
9. A computer-readable storage medium, on which a computer program/instructions are stored, which, when executed by a processor, carry out the steps of the method according to any one of claims 1 to 5.
10. A computer program product comprising computer programs/instructions, characterized in that the computer programs/instructions, when executed by a processor, implement the steps of the method according to any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111527362.2A CN114186532A (en) | 2021-12-14 | 2021-12-14 | Order examination processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111527362.2A CN114186532A (en) | 2021-12-14 | 2021-12-14 | Order examination processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114186532A true CN114186532A (en) | 2022-03-15 |
Family
ID=80604984
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111527362.2A Pending CN114186532A (en) | 2021-12-14 | 2021-12-14 | Order examination processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114186532A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117132244A (en) * | 2023-10-26 | 2023-11-28 | 国网浙江省电力有限公司 | Classification processing method, device and storage medium for intelligent compliance management system |
-
2021
- 2021-12-14 CN CN202111527362.2A patent/CN114186532A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117132244A (en) * | 2023-10-26 | 2023-11-28 | 国网浙江省电力有限公司 | Classification processing method, device and storage medium for intelligent compliance management system |
| CN117132244B (en) * | 2023-10-26 | 2024-01-09 | 国网浙江省电力有限公司 | Classification processing method, device and storage medium for intelligent compliance management system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Stoica et al. | Re-tacred: Addressing shortcomings of the tacred dataset | |
| CN112631997B (en) | Data processing method, device, terminal and storage medium | |
| US8782516B1 (en) | Content style detection | |
| US20200004765A1 (en) | Unstructured data parsing for structured information | |
| Hopkins et al. | Visualint: Sketchy in situ annotations of chart construction errors | |
| US8387024B2 (en) | Multilingual software testing tool | |
| CN111274239B (en) | Test paper structuring processing method, device and equipment | |
| US20160140389A1 (en) | Information extraction supporting apparatus and method | |
| US20140136940A1 (en) | User function feedback | |
| CN109190630A (en) | Character identifying method | |
| CN110472234A (en) | Sensitive text recognition method, device, medium and computer equipment | |
| CN111475700A (en) | Data extraction method and related equipment | |
| CN113127621A (en) | Dialogue module pushing method, device, equipment and storage medium | |
| CN114186532A (en) | Order examination processing method and device | |
| CN111814779A (en) | Bill text recognition method, device, equipment and storage medium | |
| CN110347806A (en) | Original text discriminating method, device, equipment and computer readable storage medium | |
| CN113934834A (en) | Question matching method, device, equipment and storage medium | |
| CN109189372B (en) | Development script generation method of insurance product and terminal equipment | |
| CN109343844B (en) | Method for comparing and correcting data based on Flex bill | |
| CN116225956A (en) | Automated testing method, apparatus, computer device and storage medium | |
| CN115983202A (en) | Data processing method, device, equipment and storage medium | |
| US20230162517A1 (en) | Interactive visual representation of semantically related extracted data | |
| CN110532391B (en) | Text part-of-speech tagging method and device | |
| CN113177389A (en) | Text processing method and device, electronic equipment and storage medium | |
| CN112364632A (en) | Book checking method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |