CN111783636B - OCR-based international balance network application data processing method and device - Google Patents
OCR-based international balance network application data processing method and device Download PDFInfo
- Publication number
- CN111783636B CN111783636B CN202010611831.8A CN202010611831A CN111783636B CN 111783636 B CN111783636 B CN 111783636B CN 202010611831 A CN202010611831 A CN 202010611831A CN 111783636 B CN111783636 B CN 111783636B
- Authority
- CN
- China
- Prior art keywords
- ocr
- declaration
- technology
- result
- screenshot
- 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.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 20
- 238000005516 engineering process Methods 0.000 claims abstract description 66
- 238000012545 processing Methods 0.000 claims abstract description 40
- 238000000034 method Methods 0.000 claims abstract description 33
- 238000012795 verification Methods 0.000 claims abstract description 13
- 238000012550 audit Methods 0.000 claims description 25
- 238000003860 storage Methods 0.000 claims description 21
- 238000004590 computer program Methods 0.000 claims description 18
- 238000012552 review Methods 0.000 claims description 18
- 230000011218 segmentation Effects 0.000 claims description 13
- 239000013598 vector Substances 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 4
- 238000012790 confirmation Methods 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000004801 process automation Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Technology Law (AREA)
- Marketing (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention provides an OCR-based international balance network application data processing method and device, wherein the method comprises the following steps: acquiring a declaration data screenshot filled in by a client on a network declaration system by adopting an RPA technology; intelligent recognition is carried out on the screenshot by utilizing an OCR technology to obtain the declaration data; performing key point verification on the declaration data according to a preset verification rule; examining the declaration data according to a pre-trained intelligent examination model; and feeding back the checking result and the checking result to the business terminal so as to facilitate the check of business personnel. The system comprises an RPA technology, a screenshot technology, an OCR technology, a device intelligent examination and an auxiliary confirmation of business personnel, wherein the RPA technology and the screenshot technology are used for automatically extracting the information screenshot which is declared to be not audited on a network declaration system by a client, the OCR technology is used for identifying the information screenshot, the data acquisition speed is improved, in addition, the device intelligent examination is used for outputting the examination result, the auxiliary confirmation of the business personnel is used for improving the processing efficiency and the rechecking accuracy, the timeliness is ensured, and the banking personnel does not need to log in the system repeatedly for a plurality of times.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method and an apparatus for processing international balance network data, an electronic device, and a storage medium.
Background
According to the foreign exchange management policy, when the personnel and enterprises in the house generate foreign exchange payment business through the banks, the international deposit and withdrawal statistics reporting is carried out through the sponsored banks, and the banks fulfill the responsibilities of auditing, sending the information related to the international deposit and withdrawal statistics reporting and the like, so that the timeliness, accuracy and integrity of the reporting data are ensured. The reporting mode is divided into paper reporting and network reporting. The paper declaration is submitted to the sponsor bank by the client, the banking staff performs data input through the banking system and is submitted to the digital outer tube platform (ASOne) of the national foreign exchange management office in a system docking mode; after the client logs in the ASOne system directly to fill out the declaration information, the banking staff logs in the ASOne system to audit the information declared on the client network, if the manual audit is passed, the declaration is successful, and if the manual audit is not passed, the client is returned to be modified again.
At present, in order to ensure timeliness, banking staff need to log in a system repeatedly for a plurality of times in a day, and in addition, manual auditing efficiency is low, error point auditing careless mistakes of declaration data easily occur, and the declaration error data is caused.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides an OCR-based international balance net application data processing method, an OCR-based international balance net application data processing device, electronic equipment and a storage medium, which can at least partially solve the problems in the prior art.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
in a first aspect, an international balance network application data processing method based on OCR is provided, including:
acquiring a declaration data screenshot filled in by a client on a network declaration system by adopting an RPA technology;
intelligent recognition is carried out on the screenshot by utilizing an OCR technology to obtain the declaration data;
performing key point verification on the declaration data according to a preset verification rule;
examining the declaration data according to a pre-trained intelligent examination model;
and feeding back the checking result and the checking result to the business terminal so as to facilitate the check of business personnel.
Further, the intelligent audit model is a FastText model.
Further, the auditing of the declaration data according to the pre-trained intelligent audit model includes:
word segmentation is carried out on the declaration data;
and inputting the word sequence obtained by word segmentation as a feature vector into a pre-trained FastText model to obtain an examination result.
Further, the international balance network application data processing method based on OCR further comprises the following steps:
acquiring a service personnel rechecking result;
and registering the rechecking result as a final auditing result to the network application system by using an RPA technology.
In a second aspect, there is provided an OCR-based international balance and balance data processing apparatus, comprising:
the network application data RPA acquisition module acquires application data screenshot filled in by a client on a network application system by adopting an RPA technology;
the OCR recognition module is used for intelligently recognizing the screenshot by utilizing an OCR technology to obtain the declaration data;
the key point checking module performs key point checking on the declaration data according to a preset checking rule;
the intelligent examination module examines the declaration data according to a pre-trained intelligent examination model;
and the auditing result output module feeds back the gist auditing result and the auditing result to the service terminal so as to facilitate the rechecking of service personnel.
Further, the intelligent audit model is a FastText model.
Further, the intelligent audit module includes:
an analysis unit for word segmentation of the declaration data;
and the intelligent examination unit inputs the word sequence obtained by word segmentation as a feature vector into a pre-trained FastText model to obtain an examination result.
Further, the OCR-based international balance and net application data processing device further includes:
the rechecking result acquisition module is used for acquiring a rechecking result of the service personnel;
and the network application data RPA automatic rechecking module registers the rechecking result as a final checking result to the network application system by utilizing an RPA technology.
In a third aspect, there is provided an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the OCR-based international balance and balance network data processing method described above when the program is executed.
In a fourth aspect, a computer readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, implements the steps of the above-described OCR-based international balance and balance data processing method.
The invention provides an OCR-based international balance network application data processing method, an apparatus, an electronic device and a storage medium, wherein the method comprises the following steps: acquiring a declaration data screenshot filled in by a client on a network declaration system by adopting an RPA technology; intelligent recognition is carried out on the screenshot by utilizing an OCR technology to obtain the declaration data; performing key point verification on the declaration data according to a preset verification rule; examining the declaration data according to a pre-trained intelligent examination model; and feeding back the checking result and the checking result to the business terminal so as to facilitate the check of business personnel. The system comprises an RPA technology, a screenshot technology, an OCR technology, a device intelligent examination and an auxiliary confirmation of business personnel, wherein the RPA technology and the screenshot technology are used for automatically extracting the information screenshot which is declared to be not audited on a network declaration system by a client, the OCR technology is used for identifying the information screenshot, the data acquisition speed is improved, in addition, the device intelligent examination is used for outputting the examination result, the auxiliary confirmation of the business personnel is used for improving the processing efficiency and the rechecking accuracy, the timeliness is ensured, and the banking personnel does not need to log in the system repeatedly for a plurality of times.
The foregoing and other objects, features and advantages of the invention will be apparent from the following more particular description of preferred embodiments, as illustrated in the accompanying drawings.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
FIG. 1 is a schematic diagram of an application architecture in an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a method for processing international balance network data according to an embodiment of the present invention;
fig. 3 shows a specific step of step S300 in fig. 2;
FIG. 4 is a second flow chart of the method for processing international balance network data according to the embodiment of the present invention;
FIG. 5 shows a block diagram of a robot based on RPA technology used in an embodiment of the invention;
FIG. 6 is a block diagram showing the structure of an international balance network data processing apparatus according to an embodiment of the present invention;
FIG. 7 is a block diagram showing a second configuration of an international balance network application data processing apparatus according to an embodiment of the present invention;
fig. 8 is a block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, 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.
It should be noted that the terms "comprises" and "comprising," and any variations thereof, in the description and claims of the present application and in the foregoing figures, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
In the current online reporting bank auditing link, after the ASOne system completes reporting information filling, a client cannot inform banking staff in real time to audit, and the banking staff needs to log in the ASOne system to actively inquire whether the recorded information which is not audited by the client exists or not, and in order to ensure timeliness, the client needs to log in the system repeatedly in a compartment for a plurality of times; when the reporting information is rechecked, each piece of reporting information is manually checked, the efficiency is low, the manual checking link depends on the skills of all banking personnel, the related system of foreign exchange business and the standard grasping degree of data acquisition of an outer office, and error point checking and missing of reporting data are easy to occur, so that the reporting of error data is caused. There is a need for
The invention provides an intelligent auditing technology for the declaration data of an international balance network based on RPA, which utilizes RPA (Robotic Process Automation) robot flow automation and artificial intelligence algorithm to support the automatic extraction of declaration information which is declared to be not audited on a client network by the RPA technology, and the auditing result is output for a business person to confirm through the auditing of the intelligent algorithm, and the final result after confirmation is automatically finished by the RPA to review actions, so that the invention can replace some established repeated actions in a bank auditing link, provide the intelligent auditing result for the review person to refer, and improve the processing efficiency and auditing accuracy of the bank auditing link.
In addition, a screenshot technology is utilized to automatically extract a declared and unverified screenshot of declaration information of a client on a network declaration system, recognition is carried out through an OCR technology, the data acquisition speed is improved, the data acquisition speed is effectively improved, and the auditing time is shortened.
FIG. 1 is a schematic diagram of an application architecture in an embodiment of the present invention; as shown in fig. 1, a client logs in an ASOne system S1 (a digital outer tube platform of a national foreign exchange administration) through a client device B1, after the completion of the filling of the reporting information, an international balance network reporting data processing server S2 (a bank end, i.e. a server executing the method provided by the invention) based on OCR is automatically logged in the ASOne system at intervals according to a set time interval by an RPA technology, a screen capturing technology is used for acquiring a reporting data screenshot of the client which is not yet reported, intelligent recognition is performed through the OCR technology to obtain structured data information, intelligent audit is performed, a preliminary audit result is pushed to a service terminal B2 for a service personnel to review, the review result is fed back to an international balance network reporting data processing server S2 based on OCR, the international balance network reporting data processing server S2 based on OCR is realized through an RPA technology, the ASOne system is automatically logged in at intervals according to the set time interval, the reporting data which is not yet reported by the client is queried, and the audit result registration is completed according to a final result.
It is understood that the client device B1 and the service terminal B2 may include a smart phone, a tablet electronic device, a portable computer, a desktop computer, and the like.
Any suitable network protocol may be used for communication between the ASOne system server and the client device, between the ASOne system server and the OCR-based international balance and balance network data processing server S2, and between the OCR-based international balance and balance network data processing server S2 and the service terminal B2, including network protocols not yet developed at the filing date of the present application. The network protocols may include, for example, TCP/IP protocol, UDP/IP protocol, HTTP protocol, HTTPS protocol, etc. Of course, the network protocol may also include, for example, RPC protocol (Remote Procedure Call Protocol ), REST protocol (Representational State Transfer, representational state transfer protocol), etc. used above the above-described protocol.
FIG. 2 is a schematic flow diagram of an OCR-based International Business machines application data processing method in accordance with an embodiment of the present invention; as shown in fig. 2, the OCR-based international balance application data processing method may include the following:
step S100a: acquiring a declaration data screenshot filled in by a client on a network declaration system by adopting an RPA technology;
step S100b: intelligent recognition is carried out on the screenshot by utilizing an OCR technology to obtain the declaration data;
and automatically logging in an ASOne system at intervals according to a set time interval by an RPA technology, acquiring a declaration data screenshot which is declared to be unchecked by a client by a screen capturing technology, and intelligently identifying by an OCR technology to obtain structured data information.
It is worth to describe that, the scheme of acquiring the declaration data by combining the screenshot technology and the OCR technology provided by the embodiment of the invention has greatly improved efficiency and speed compared with the mode of completing the acquisition of the data by copying and pasting field information one by one after the declaration information is queried.
The structure of the information about the online declaration, which relates to standard format elements required by the related data acquisition specification formulated by the national foreign exchange management bureau, such as "the information about the foreign income declaration" is shown in table 1:
TABLE 1
Step S200: performing key point verification on the declaration data according to a preset verification rule;
specifically, extracting problem points according to a preset checking rule; for example, when the client declares that the transaction code 2 is filled but the relevant amount 2 is not filled, a prompt is output that if the transaction code 2 is filled, the relevant amount 2 must be filled; if the sum of the corresponding amounts of the two transaction codes is not equal to the income amount of the basic information, a prompt is output, wherein the sum of the corresponding amounts of the two transaction codes is required to be equal to the income amount. "
Wherein, the checking rule is set by the developer according to the relevant rule.
Step S300: examining the declaration data according to a pre-trained intelligent examination model;
specifically, for information without explicit rules, such as transaction statement 1 and transaction statement 2, the information is a detailed description of the transaction property corresponding to the transaction code 1 by the reporting subject, when the reporting subject fills out, the reporting subject has a difference in expression, and needs to check whether there is a discrepancy with the transaction code one by one, in which case, the discrepancy between the reporting information transaction statement and the transaction code needs to be identified through an intelligent checking model.
The accuracy and integrity verification of the declared information elements is completed through the step S200 and the step S300, and the error point details and the verification results are registered.
Step S400: and feeding back the checking result and the checking result to the business terminal so as to facilitate the check of business personnel.
And actively pushing result information of the reporting information audit to service personnel, wherein the result information comprises whether the reporting information is missing, the reporting information is filled in errors and detailed information of the errors. The pushing mode can be various modes such as mail or business system.
Specifically, the result of the intelligent audit, the error point, the transaction statement and the transaction code disagreement point are displayed to the bank personnel for auxiliary confirmation, and the modification description when the client is returned to modify the declaration information is shown in table 2.
TABLE 2
By adopting the technical scheme, the RPA technology, the screen capturing technology and the OCR technology are utilized to automatically extract the non-audited reporting information of the clients on the network reporting system, and the device intelligently reviews and outputs the auditing result, so that the business personnel assist in confirmation, the processing efficiency and the accuracy of review are improved, the timeliness is ensured, and the banking personnel do not need to log in the system repeatedly for a plurality of times.
In an alternative embodiment, the intelligent audit model is a FastText model.
Among other things, the FastText model can be invoked in Python.
The FastText model inputs a word sequence (obtained by word segmentation of declaration data) and outputs probabilities that the word sequence belongs to different categories, namely probabilities corresponding to different point-different prompt messages. Words and phrases in the sequence form feature vectors, which are mapped to intermediate layers by linear transformation, which are mapped to tags.
In an alternative embodiment, a data preprocessing step may be further included before step S200. Specifically, the method comprises the processes of data filtering, data normalization and the like, such as screening out bad point data, missing data and the like.
In an alternative embodiment, referring to fig. 3, the step S300 may include the following technical contents:
step S310: word segmentation is carried out on the declaration data;
step S320: and inputting the word sequence obtained by word segmentation as a feature vector into a pre-trained FastText model to obtain an examination result.
In an alternative embodiment, the step S300 may further include: a data preprocessing step;
specifically, preprocessing includes data cleaning; the data cleaning is to transfer all letters to be transcribed, remove punctuation marks and remove part of English stop words.
In an alternative embodiment, the method for processing international balance network application data based on OCR may further include a model training step, specifically including:
(1) Sample data is acquired.
Specifically, the current stock network application data (i.e. training samples) and the disagreement prompt information (i.e. corresponding labels) are extracted;
where the data is not canonical, labeling is required, for example as follows: the transaction code is included 822030, and the transaction statement does not include the words "non-resident outbound payment" or "non-resident outbound payment sink" or "non-resident outbound remittance", labeled as "the transaction statement is not in agreement with the transaction code: the transaction code 822030 lower transaction statement should include "non-resident outbound payment"/"non-resident outbound payment glossary"/"non-resident outbound remittance"; for another example, a record that the transaction statement matches the declaration subject name is labeled "the transaction statement cannot be replaced with the declaration subject name".
(2) And (5) preprocessing data.
Specifically, the sample data is processed and corrected. For example: since the trade legend and the trade code disagree prompt are used for identifying the trade legend under the given scene of the trade code, the trade legend of the sample data needs to be split.
(3) And (5) model training.
Specifically, the sample data is segmented to obtain a word sequence, a feature vector formed by the word sequence is input into a pre-established Fasttext model, and the probability that the word sequence belongs to different categories is output.
(4) And (5) evaluating a model.
And predicting samples on the verification set or the test set by using the trained model, and judging whether the trained model meets the requirements, if so, obtaining a trained model for data processing, and if not, modifying model parameters or updating the training sample set and then retraining.
In an alternative embodiment, referring to fig. 4, the OCR-based international balance application data processing method may further include:
step S500: acquiring a service personnel rechecking result;
and the banking staff confirms according to the intelligent audit output audit result points, and feeds back the audit result as pass or fail.
Step S600: and registering the rechecking result as a final auditing result to the network application system by using an RPA technology.
Specifically, by using the RPA technology, the ASOne system is automatically logged in at intervals according to a set time interval, and according to a final auditing result, reporting data which is not audited by a client is queried, so as to complete an automatic rechecking action, i.e. the final auditing result is registered in the network reporting system (namely, the ASOne system).
In an alternative embodiment, the robot using the RPA technology to acquire the declaration technology and to register the review result to the web-declaration system using the RPA technology, has a structure shown in fig. 5, and includes: script unit 1, flow unit 2 and task unit 3.
The script unit 1 is responsible for carrying out script design on each independent flow unit of the invention. The RPA script simulates daily manual operations of a user, such as mouse clicking, keyboard input, copying/pasting, screen capturing and the like, according to the established steps, a series of automatic operations are completed, and automatic processing of a single working step is realized.
The flow unit 2 is used for connecting all script units 1 designed by the invention to form a complete automatic working flow, and the automatic acquisition and the automatic rechecking processing of the network application data can be realized by executing the flow.
The task unit 3 is configured to design an operation policy of the flow unit 2, and may set the flow unit 2 to be a task triggered by time timing or event, and automatically execute the task. The user can configure the information such as triggering time, event, execution times and the like by himself, for example, the task is set to be executed every 12:00 of workdays or every 1 hour; automatically running each time the user logs in the RPA, etc.
Based on the same inventive concept, the embodiment of the present application also provides an OCR-based international balance network application data processing device, which can be used to implement the method described in the above embodiment, as described in the following embodiment. Since the principle of the OCR-based international balance and balance application data processing apparatus for solving the problem is similar to that of the above method, the implementation of the OCR-based international balance and balance application data processing apparatus can refer to the implementation of the above method, and the repetition is omitted. As used below, the term "unit" or "module" may be a combination of software and/or hardware that implements the intended function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
FIG. 6 is a block diagram of an OCR-based international balance and balance data processing apparatus in accordance with an embodiment of the present invention; as shown in fig. 6, the OCR-based international balance and balance data processing apparatus specifically includes: the system comprises a network application data RPA acquisition module 10a, an OCR recognition module 10b, a main point checking module 20, an intelligent checking module 30 and a checking result output module 40.
The network application data RPA acquisition module 10a adopts RPA technology to acquire application data screenshot filled in by a client on a network application system;
the OCR recognition module 10b uses OCR technology to intelligently recognize the screenshot to obtain the declaration data;
the key point checking module 20 performs key point checking on the declaration data according to a preset checking rule;
the intelligent examination module 30 examines the declaration data according to a pre-trained intelligent examination model;
the audit result output module 40 feeds back the gist audit result and audit result to the service terminal for review by service personnel.
By adopting the technical scheme, the RPA technology, the screen capturing technology and the OCR technology are utilized to automatically extract the non-audited reporting information of the clients on the network reporting system, and the device intelligently reviews and outputs the auditing result, so that the business personnel assist in confirmation, the processing efficiency and the accuracy of review are improved, the timeliness is ensured, and the banking personnel do not need to log in the system repeatedly for a plurality of times.
In an alternative embodiment, the intelligent audit model is a FastText model.
In a further embodiment, the intelligent audit module includes: an analysis unit and an intelligent examination unit.
The analysis unit is used for word segmentation of the declaration data;
the intelligent examination unit is used for inputting the word sequence obtained by word segmentation as a feature vector into a pre-trained intelligent examination model to obtain an examination result.
In an alternative embodiment, referring to fig. 7, the OCR-based international balance application data processing apparatus may further include: the review result acquisition module 50 and the web application data RPA automatic review module 60.
The review result acquisition module 50 acquires a business person review result;
the network application data RPA automatic review module 60 registers the review result as a final review result to the network application system using RPA technology.
The apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. A typical implementation device is an electronic device, which may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
In a typical example the electronic device comprises in particular a memory, a processor and a computer program stored on the memory and executable on the processor, said processor implementing the steps of the above described OCR based international balance application data processing method when said program is executed.
Referring now to fig. 8, a schematic diagram of an electronic device 600 suitable for use in implementing embodiments of the present application is shown.
As shown in fig. 8, the electronic apparatus 600 includes a Central Processing Unit (CPU) 601, which can perform various appropriate works and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage section 608 into a Random Access Memory (RAM)) 603. In the RAM603, various programs and data required for the operation of the system 600 are also stored. The CPU601, ROM602, and RAM603 are connected to each other through a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, mouse, etc.; an output portion 607 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The drive 610 is also connected to the I/O interface 605 as needed. Removable media 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on drive 610 as needed, so that a computer program read therefrom is mounted as needed as storage section 608.
In particular, according to embodiments of the present invention, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, an embodiment of the present invention includes a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the above-described OCR-based International Business machines application data processing method.
In such an embodiment, the computer program may be downloaded and installed from a network through the communication portion 609, and/or installed from the removable medium 611.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in one or more software and/or hardware elements when implemented in the present application.
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 flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations 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.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application 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 application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.
Claims (10)
1. An international balance network application data processing method based on OCR, which is characterized by comprising the following steps:
acquiring a declaration data screenshot filled in by a client on a network declaration system by adopting an RPA technology;
intelligent recognition is carried out on the screenshot by utilizing an OCR technology to obtain the declaration data;
performing key point verification on the declaration data according to a preset verification rule;
for information without clear rules, examining the declaration data according to a pre-trained intelligent examination model;
feeding back the checking result and the checking result to the business terminal so as to facilitate the business personnel to check;
the method for acquiring the declaration data screenshot filled in by the client on the network declaration system by adopting the RPA technology comprises the following steps:
automatically logging in an ASOne system at intervals according to a set time interval by an RPA technology, and acquiring a declaration data screenshot which is declared to be unchecked by a client by a screen capturing technology;
the main point checking of the declaration data according to a preset checking rule comprises the following steps:
extracting a problem point according to a preset checking rule, wherein:
when the client declares, the transaction code 2 is filled, but the related amount 2 is not filled, a prompt is output, if the transaction code 2 is filled, the related amount 2 must be filled;
if the sum of the corresponding amounts of the two transaction codes is not equal to the income amount of the basic information, a prompt is output, wherein the sum of the corresponding amounts of the two transaction codes is necessarily equal to the income amount.
2. The OCR-based international balance application data processing method of claim 1, wherein the intelligent censoring model is a FastText model.
3. The OCR-based international balance application data processing method of claim 2, wherein the auditing of the declaration data according to a pre-trained intelligent auditing model includes:
word segmentation is carried out on the declaration data;
and inputting the word sequence obtained by word segmentation as a feature vector into a pre-trained FastText model to obtain an examination result.
4. The OCR-based international balance application data processing method of claim 1, further comprising:
acquiring a service personnel rechecking result;
and registering the rechecking result as a final auditing result to the network application system by using an RPA technology.
5. An OCR-based international balance and net application data processing device, comprising:
the network application data RPA acquisition module acquires application data screenshot filled in by a client on a network application system by adopting an RPA technology;
the OCR recognition module is used for intelligently recognizing the screenshot by utilizing an OCR technology to obtain the declaration data;
the key point checking module performs key point checking on the declaration data according to a preset checking rule;
the intelligent examination module examines the declaration data according to a pre-trained intelligent examination model for the information without clear rules;
the audit result output module feeds back the gist audit result and the audit result to the service terminal so as to facilitate the rechecking of service personnel;
wherein the web-application data RPA acquisition module is further configured to:
automatically logging in an ASOne system at intervals according to a set time interval by an RPA technology, and acquiring a declaration data screenshot which is declared to be unchecked by a client by a screen capturing technology;
wherein the gist checking module is further configured to:
extracting a problem point according to a preset checking rule, wherein:
when the client declares, the transaction code 2 is filled, but the related amount 2 is not filled, a prompt is output, if the transaction code 2 is filled, the related amount 2 must be filled;
if the sum of the corresponding amounts of the two transaction codes is not equal to the income amount of the basic information, a prompt is output, wherein the sum of the corresponding amounts of the two transaction codes is necessarily equal to the income amount.
6. The OCR based international balance application data processing device of claim 5, wherein the intelligent censoring model is a FastText model.
7. The OCR-based international balance application data processing device of claim 6, wherein the intelligent review module comprises:
the analysis unit is used for word segmentation of the declaration data;
and the intelligent examination unit inputs the word sequence obtained by word segmentation as a feature vector into a pre-trained FastText model to obtain an examination result.
8. The OCR based international balance application data processing device of claim 5, further comprising:
the rechecking result acquisition module is used for acquiring a rechecking result of the service personnel;
and the network application data RPA automatic rechecking module registers the rechecking result to the network application system by using an RPA technology as a final checking result.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the OCR-based international balance application data processing method of any one of claims 1 to 4 when the program is executed.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the OCR-based international balance and balance data processing method of any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010611831.8A CN111783636B (en) | 2020-06-30 | 2020-06-30 | OCR-based international balance network application data processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010611831.8A CN111783636B (en) | 2020-06-30 | 2020-06-30 | OCR-based international balance network application data processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111783636A CN111783636A (en) | 2020-10-16 |
| CN111783636B true CN111783636B (en) | 2024-03-29 |
Family
ID=72761492
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010611831.8A Active CN111783636B (en) | 2020-06-30 | 2020-06-30 | OCR-based international balance network application data processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111783636B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112767138B (en) * | 2021-02-10 | 2024-02-06 | 中国工商银行股份有限公司 | International balance reporting data missing report detection method and system |
| CN113642831A (en) * | 2021-06-24 | 2021-11-12 | 国网上海市电力公司 | Data rapid acquisition method, medium and equipment based on process automation processing |
| CN113822749A (en) * | 2021-08-10 | 2021-12-21 | 北京来也网络科技有限公司 | Merchant settlement and payment processing method, device, equipment and medium based on RPA and AI |
| CN115271970A (en) * | 2022-09-28 | 2022-11-01 | 珠海金智维信息科技有限公司 | Intelligent auditing system, method and device for security business |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108921510A (en) * | 2018-06-27 | 2018-11-30 | 中国建设银行股份有限公司 | Banking remote auto checking method and system |
| CN109993505A (en) * | 2019-04-10 | 2019-07-09 | 鼎信信息科技有限责任公司 | Checking method, device, computer equipment and the storage medium of expense reimbursement |
| CN110414512A (en) * | 2019-07-31 | 2019-11-05 | 中国工商银行股份有限公司 | Letter of credit audit terminal |
| CN111091350A (en) * | 2019-12-12 | 2020-05-01 | 中国银行股份有限公司 | Method, device and equipment for auditing and processing service data and storage medium |
-
2020
- 2020-06-30 CN CN202010611831.8A patent/CN111783636B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108921510A (en) * | 2018-06-27 | 2018-11-30 | 中国建设银行股份有限公司 | Banking remote auto checking method and system |
| CN109993505A (en) * | 2019-04-10 | 2019-07-09 | 鼎信信息科技有限责任公司 | Checking method, device, computer equipment and the storage medium of expense reimbursement |
| CN110414512A (en) * | 2019-07-31 | 2019-11-05 | 中国工商银行股份有限公司 | Letter of credit audit terminal |
| CN111091350A (en) * | 2019-12-12 | 2020-05-01 | 中国银行股份有限公司 | Method, device and equipment for auditing and processing service data and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111783636A (en) | 2020-10-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111783636B (en) | OCR-based international balance network application data processing method and device | |
| US10984483B2 (en) | Cognitive regulatory compliance automation of blockchain transactions | |
| AU2017297271B2 (en) | System and method for automatic learning of functions | |
| CA3033859C (en) | Method and system for automatically extracting relevant tax terms from forms and instructions | |
| CN111782809A (en) | International reimbursement network data processing method, device, electronic equipment and storage medium | |
| CN109345417B (en) | Online assessment method and terminal equipment for business personnel based on identity authentication | |
| CN115017288A (en) | Model training method, model training device, equipment and storage medium | |
| WO2023284505A1 (en) | Method and apparatus for code-scanning payment | |
| CN115238688A (en) | Electronic information data association relation analysis method, device, equipment and storage medium | |
| US20210349920A1 (en) | Method and apparatus for outputting information | |
| CN111091408A (en) | User identification model creating method and device and identification method and device | |
| CN116484836B (en) | Questionnaire generation system and method based on NLP model, electronic equipment and medium | |
| CN115859128B (en) | Analysis method and system based on interaction similarity of archive data | |
| CN117033431A (en) | Work order processing method, device, electronic equipment and medium | |
| CN116738293A (en) | Service evaluation processing method and device and electronic equipment | |
| CN116628163A (en) | Customer service processing method, customer service processing device, customer service processing equipment and storage medium | |
| CN114445095A (en) | Material detection method, material detection device, storage medium and electronic equipment | |
| CN114444040A (en) | Authentication processing method, authentication processing device, storage medium and electronic equipment | |
| CN113822313A (en) | Method and device for detecting abnormity of graph nodes | |
| US20210224303A1 (en) | Searching device and searching program | |
| CN110085234A (en) | Access automatic speech recognition system | |
| CN112767138B (en) | International balance reporting data missing report detection method and system | |
| CN117172632B (en) | Enterprise abnormal behavior detection method, device, equipment and storage medium | |
| US12001422B2 (en) | Accuracy of QA systems by normalizing logical queries | |
| CN115270748B (en) | File generation method, device, electronic equipment and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |