Heterogeneous system process automatic processing method and device based on RPA and artificial intelligence technology, terminal equipment and storage medium

Abstract

The invention relates to a heterogeneous system process automatic processing method and device based on RPA and artificial intelligence technology, terminal equipment and a storage medium, and the method comprises the steps: logging in an anti-fraud big data platform through a payment-stopping application program, and when any network fraud alarm information of an anti-fraud center system is monitored, executing the payment-stopping application program; opening a payment-stopping application page of the anti-fraud big data platform, dynamically filling the content of form fields according to the network fraud alarm information to obtain an application form, generating a payment-stopping letter based on the network fraud alarm information, sending a payment-stopping treatment application to the anti-fraud big data platform through the payment-stopping application page, receiving an approval task, and sending the approval task to the anti-fraud big data platform. And after the approval task passes the approval, a payment stop processing request is sent to the approval task, after the anti-fraud big data platform receives the payment stop processing request, a payment stop letter is analyzed, a fraud-related account is obtained, and a payment stop processing notification of the fraud-related account is sent to a payment institution. According to the method, the payment stop of the fraud-related account of the network fraud can be automatically handled, and the timeliness and the success rate of payment stop are improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, apparatus, terminal device and storage medium for automating heterogeneous system processes based on RPA and artificial intelligence technologies. Background Art

[0002] In recent years, with the rapid development of network technology, criminals have used diversified applications such as communication, social networking, payment, shopping, and games on the Internet to commit online fraud, making new types of network crimes such as telecommunications network fraud increasingly rampant, and the number of cases has increased dramatically. In response to this severe situation, the anti-fraud big data platform has established a fast contact channel with many commercial banks and payment institutions, providing the platform capability to carry out emergency and extended stop payment work on the victim's funds in the fraud-related accounts. Relying on this anti-fraud big data platform, it is possible to implement rapid stop payment of accounts involved in online fraud.

[0003] The existing emergency stop payment work mode mainly relies on manual information entry. The entire process is limited by the time consumption of multiple links, and may miss the best opportunity of the "golden half hour" to recover the defrauded funds, resulting in the inability to recover the losses in time. Summary of the invention

[0004] Based on this, it is necessary to provide a heterogeneous system process automation processing method, device, terminal equipment and storage medium based on RPA and artificial intelligence technology to address the above-mentioned technical problems, which can automatically handle the stop payment of fraudulent accounts involved in online fraud through RPA and artificial intelligence technology, quickly respond to online fraud, and improve the timeliness of fund stop payment.

[0005] An automated processing method for heterogeneous system processes based on RPA and artificial intelligence technologies, wherein the heterogeneous system includes a terminal device, an anti-fraud center system, and an anti-fraud big data platform, wherein the terminal device is installed with a stop payment application configured based on RPA and artificial intelligence technologies, wherein the stop payment application is written based on a cross-platform GUI automation tool in combination with a browser driver interface, and wherein a natural language processing program using artificial intelligence technology is encapsulated in the stop payment application; an automated processing method for heterogeneous systems based on RPA and artificial intelligence technologies is applied to the terminal device of the heterogeneous system, comprising: starting the stop payment application; opening and logging into the anti-fraud big data platform from a browser through the stop payment application; upon monitoring any network fraud alarm information of the anti-fraud center system, opening the stop payment application page of the anti-fraud big data platform through the stop payment application based on the applicant information, and using the web application testing tool The system can automatically locate the form fields of the stop payment application page, and dynamically fill in the content of the form fields according to the network fraud warning information to obtain the application form; read the preset template, generate a stop payment letter based on the preset template and the network fraud warning information, and configure the stop payment letter with an electronic official seal and an electronic signature; automatically send a stop payment disposal application to the anti-fraud big data platform through the stop payment application page, and the stop payment disposal application carries the stop payment letter and the application form; receive the approval task based on the feedback of the stop payment disposal application from the anti-fraud big data platform, and the approval task includes the stop payment letter and the application form; approve the approval task based on the approver information and through the stop payment application, and after the approval is passed, automatically send a stop payment disposal request to the anti-fraud big data platform. After receiving the stop payment disposal request, the anti-fraud big data platform parses the stop payment letter in the stop payment disposal application, obtains the fraud-related account, and sends the stop payment disposal notice of the fraud-related account to the payment institution.

[0006] In one of the embodiments, the form fields of the stop payment application page include a first field for the payment institution, a second field for the reason, and a third field for the person handling the matter; the contents of the form fields are dynamically filled in according to the online fraud warning information, including: extracting the payment institution and the reason for fraud from the online fraud warning information and extracting the user information of the person handling the matter from the system; filling the extracted payment institution into the first field, filling the extracted reason for fraud into the second field, and filling the user information of the person handling the matter into the third field.

[0007] In one embodiment, a stop payment letter is generated based on a preset template and online fraud warning information, including: extracting the case name and the fraud-related account from the online fraud warning information; and generating a stop payment letter based on the preset template, the case name and the fraud-related account.

[0008] In one of the embodiments, the approval task is approved based on the approver information and through a stop payment application, including: after confirming the approver's approval authority based on the approver information, extracting the relevant information of the fraudulent account and the approval unit information from the stop payment official letter of the approval task through the natural language processing program of the stop payment application, and extracting the relevant information of the fraudulent account and the approval unit information from the application form, comparing the relevant information of the fraudulent account and the approval unit information in the stop payment official letter with the relevant information of the fraudulent account and the approval unit information in the application form, and confirming the approval when the comparison results are the same.

[0009] In one of the embodiments, before the step of opening and logging into the anti-fraud big data platform from the browser through the stop payment application, it also includes: obtaining the version information of the operating system, the version information of the browser and the office software information of the terminal device; opening and logging into the anti-fraud big data platform from the browser through the stop payment application, including: when confirming that the version information of the stop payment application and the operating system and the version information of the browser are all compatible, opening and logging into the anti-fraud big data platform from the browser through the stop payment application, wherein the version information of the browser matches the driver of the browser; generating a stop payment official letter based on a preset template and network fraud warning information, including: when confirming that the document processing application has been installed based on the office software information, calling the document processing application and generating a stop payment official letter based on the preset template and the network fraud warning information.

[0010] In one of the embodiments, the office software information includes registry entries and / or program file directories; confirming that the document processing application has been installed based on the office software information includes: confirming that the document processing application has been installed based on the registry entries and / or program file directories; or, confirming that the document processing application has been installed by executing a specific command.

[0011] In one of the embodiments, a method for automating heterogeneous system processes based on RPA and artificial intelligence technology also includes: establishing a long connection with a back-end platform, and monitoring the online fraud warning information issued by the back-end platform in real time; obtaining the system time of the terminal device, and the system time is used to add a timestamp to the official letter of injunction; sending the system time to the back-end platform, and when the back-end platform confirms that the time difference between the system time and the server time is greater than the set time, the server time is sent to the terminal device; if the server time is received, the system time is calibrated based on the server time.

[0012] An automated processing device for heterogeneous system processes based on RPA and artificial intelligence technologies, wherein the heterogeneous system includes a terminal device, an anti-fraud center system, and an anti-fraud big data platform, wherein the terminal device is installed with a stop payment application configured based on RPA and artificial intelligence technologies, wherein the stop payment application is written based on a cross-platform GUI automation tool in combination with a browser driver interface, and wherein a natural language processing program using artificial intelligence technology is encapsulated in the stop payment application; an automated processing device for heterogeneous systems based on RPA and artificial intelligence technologies is applied to the terminal device of the heterogeneous system, comprising: a startup module for starting the stop payment application; a login module for opening and logging into the anti-fraud big data platform from a browser through the stop payment application; a form filling module for opening the stop payment application page of the anti-fraud big data platform through the stop payment application based on the applicant information when any network fraud warning information of the anti-fraud center system is monitored, and using a web application testing tool to automatically determine The invention relates to a method for automatically sending a stop payment disposal application to the anti-fraud big data platform through the stop payment application page, and dynamically filling in the content of the form fields according to the network fraud alarm information to obtain an application form; a generation module is used to read a preset template, generate a stop payment official letter based on the preset template and the network fraud alarm information, and configure an electronic official seal and an electronic signature for the stop payment official letter; a sending module is used to automatically send a stop payment disposal application to the anti-fraud big data platform through the stop payment application page, and the stop payment disposal application carries a stop payment official letter and an application form; a receiving module is used to receive an approval task from the anti-fraud big data platform based on the feedback of the stop payment disposal application, and the approval task includes a stop payment official letter and an application form; a stop payment disposal module is used to approve the approval task based on the approver information and through the stop payment application program, and after the approval is passed, automatically send a stop payment disposal request to the anti-fraud big data platform, and after receiving the stop payment disposal request, the anti-fraud big data platform parses the stop payment official letter in the stop payment disposal application, obtains the fraud-related account, and sends a stop payment disposal notice of the fraud-related account to the payment institution.

[0013] A terminal device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of any of the above-mentioned embodiments are implemented.

[0014] A computer-readable storage medium stores a computer program, which implements the steps of any of the above-mentioned method embodiments when the computer program is executed by a processor.

[0015] The above-mentioned heterogeneous system process automation processing method, device, terminal device and storage medium based on RPA and artificial intelligence technology, the heterogeneous system includes a terminal device, an anti-fraud center system and an anti-fraud big data platform, the terminal device is installed with a stop payment application configured based on RPA and artificial intelligence technology, the stop payment application is based on a cross-platform GUI automation tool and is written in combination with a browser driver interface, and the stop payment application is encapsulated with a natural language processing program of artificial intelligence technology; including: starting the stop payment application; when any network fraud warning information of the anti-fraud center system is monitored, the stop payment application page of the anti-fraud big data platform is opened through the stop payment application based on the applicant information, the form fields of the stop payment application page are automatically located using a web application testing tool, and the stop payment application page is automatically located according to the network fraud warning information. The information dynamically fills the content of the form fields to obtain the application form; reads the preset template, generates a stop payment letter based on the preset template and the network fraud alarm information, and configures the stop payment letter with an electronic official seal and an electronic signature; automatically sends a stop payment disposal application to the anti-fraud big data platform through the stop payment application page, and the stop payment disposal application carries the stop payment letter and the application form; receives the approval task based on the feedback of the stop payment disposal application from the anti-fraud big data platform, and the approval task includes the stop payment letter and the application form; approves the approval task based on the approver information and through the stop payment application, and after the approval is passed, automatically sends a stop payment disposal request to the anti-fraud big data platform. After receiving the stop payment disposal request, the anti-fraud big data platform parses the stop payment letter in the stop payment disposal application, obtains the fraud-related account, and sends the stop payment disposal notice of the fraud-related account to the payment institution. Therefore, when any network fraud warning information is monitored by the anti-fraud center system, the stop payment application is used to automatically log in to the anti-fraud big data platform and automatically submit a stop payment application. There is no need for manual operation to enter the network fraud warning information and manually send the stop payment application to the anti-fraud big data platform, as well as automatic approval and processing of the stop payment application based on artificial intelligence technology. The stop payment of accounts involved in network fraud is automatically handled, which quickly responds to network fraud and improves the timeliness of fund stop payment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is an application environment diagram of a heterogeneous system process automation processing method based on RPA and artificial intelligence technology in one embodiment; Figure 2 A flowchart of a heterogeneous system process automation processing method based on RPA and artificial intelligence technology in one embodiment; Figure 3 A schematic diagram of a process of automated application in a heterogeneous system process automation processing method based on RPA and artificial intelligence technology in one embodiment; Figure 4A schematic diagram of an automated approval process in a heterogeneous system process automation processing method based on RPA and artificial intelligence technology in one embodiment; Figure 5 It is a structural block diagram of a heterogeneous system process automation processing device based on RPA and artificial intelligence technology in one embodiment; Figure 6 FIG. 4 is a diagram showing the internal structure of a terminal device in an embodiment. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0018] This application provides a heterogeneous system process automation processing method based on RPA and artificial intelligence technology, which is applied to Figure 1 In the application environment shown. Figure 1 As shown, the terminal device 100 is used to execute a heterogeneous system process automation processing method based on RPA and artificial intelligence technology of the present application. Figure 1As shown, the heterogeneous system includes a terminal device 100, an anti-fraud center system 400 and an anti-fraud big data platform 200. A stop payment application and a browser are installed in the terminal device 100, and a web application testing tool is configured. Specifically, the terminal device 100 starts the stop payment application, which is written based on a cross-platform GUI automation tool and combined with the browser's driver interface. The stop payment application encapsulates a natural language processing program with artificial intelligence technology; the stop payment application is opened and logged in from the browser to the anti-fraud big data platform 200; when any network fraud alarm information of the anti-fraud center system 400 is monitored, the stop payment application page of the anti-fraud big data platform 200 is opened through the stop payment application based on the applicant information, the web application testing tool is used to automatically locate the form fields of the stop payment application page, and the content of the form fields is dynamically filled according to the network fraud alarm information to obtain an application form; the preset template is read, and based on the preset template and The network fraud warning information generates a stop payment letter, and the stop payment letter is configured with an electronic official seal and an electronic signature; a stop payment application is sent to the anti-fraud big data platform 200 through the stop payment application page, and the stop payment application carries the stop payment letter and the application form; the approval task based on the feedback of the stop payment application from the anti-fraud big data platform 200 is received, and the approval task includes the stop payment letter and the application form; the approval task is approved based on the approver information and through the stop payment application program; after the approval is passed, the stop payment request is automatically sent to the anti-fraud big data platform 200; after receiving the stop payment request, the anti-fraud big data platform 200 parses the stop payment letter in the stop payment application, obtains the fraud-related account, and sends the stop payment notification of the fraud-related account to the payment institution 300. Therefore, the automated stop payment processing of the fraud-related account of network fraud can be realized.

[0019] In one embodiment, Figure 2 As shown in the figure, a heterogeneous system process automation processing method based on RPA and artificial intelligence technology is provided. Figure 1 The terminal device 100 in FIG. 1 is taken as an example to illustrate the method, which includes the following steps: S202, start the stop payment application.

[0020] In this embodiment, the stop payment application is configured based on RPA and artificial intelligence technology, the stop payment application is written based on a cross-platform GUI automation tool and combined with a browser driver interface, and a natural language processing program with artificial intelligence technology is encapsulated in the stop payment application. The cross-platform GUI automation tool can be a PyAutoGUI tool. Through the mouse, keyboard and other automated operations of the PyAutoGUI class library, an automated script is written in combination with the browser driver interface to obtain the stop payment application. In addition, the stop payment application is configured based on artificial intelligence technology, and a natural language processing program is encapsulated in the stop payment application. The corresponding text content can be parsed and recognized through the named entity recognition (NER) and text parsing methods in the NLP (Natural Language Processing) technology.

[0021] S204, open and log in to the anti-fraud big data platform from the browser through the stop payment application.

[0022] In this embodiment, the anti-fraud big data platform is automatically opened through the stop payment application, and the user operation is simulated to complete the password input, so as to realize the quick login to the anti-fraud big data platform.

[0023] S206, when any network fraud warning information of the anti-fraud center system is monitored, the stop payment application page of the anti-fraud big data platform is opened through the stop payment application based on the applicant information, the form fields of the stop payment application page are automatically located using the web application testing tool, and the content of the form fields is dynamically filled in according to the network fraud warning information to obtain the application form.

[0024] It should be noted that: in this application, the stop payment application and the anti-fraud center system transmit data through a legal protocol to legally obtain any network fraud warning information of the anti-fraud center system. In addition, the stop payment application is pre-registered in the anti-fraud center system and obtains a legal account of the anti-fraud center system. After obtaining the authority granted by the anti-fraud center system, it monitors the network fraud warning information of the anti-fraud center system. That is, the anti-fraud center system grants the legal stop payment application the authority to monitor and download its internal network fraud warning information.

[0025] In this embodiment, after receiving any network fraud warning information from the anti-fraud center system, the stop payment application page of the anti-fraud big data platform is opened through the stop payment application based on the applicant information. Specifically, the stop payment application is configured with the role of the applicant and the role of the approver. The role of the applicant has the ability to open the stop payment application page of the anti-fraud big data platform to perform the stop payment application operation. The role of the approver has the ability to approve the stop payment application. Specifically, after confirming the corresponding application authority based on the applicant information, the stop payment application automatically opens the newly added stop payment application page in the anti-fraud big data platform, uses the Selenium library to automatically locate the form fields of the stop payment application page, and dynamically fills in the form according to the warning content in the network fraud warning information, including the automatic filling of information such as the stop payment bank, reason, and person in charge, and finally obtains the application form. In one example, the form fields of the stop payment application page include a first field for the payment institution, a second field for the reason, and a third field for the person handling the matter; the contents of the form fields are dynamically filled in according to the online fraud warning information, including: extracting the payment institution and the reason for fraud from the online fraud warning information and extracting the user information of the person handling the matter from the system; filling the extracted payment institution into the first field, filling the extracted reason for fraud into the second field, and filling the user information of the person handling the matter into the third field.

[0026] Specifically, the payment institution refers to the management institution of the fraudulent account. The cause can be a fraud cause generated based on the fraud information in the online fraud warning information. The handler refers to the user information of the handler set by the system. Through these field information, the payment institution of the fraudulent account can be directly determined in the generated application form, so that the anti-fraud big data platform can notify the payment institution to stop payment. In addition, the authenticity of the stop payment application can be verified through the fraud cause and the handler to avoid unreasonable stop payment operations.

[0027] S208, reading a preset template, generating a stop payment letter based on the preset template and the network fraud warning information, and configuring an electronic official seal and an electronic signature for the stop payment letter.

[0028] In this embodiment, a template, i.e., a preset template, is pre-set based on the features of the stop payment letter. After the document content required to be filled in the preset template is extracted from the online fraud warning information, the extracted document content is automatically filled into the preset template to generate a stop payment letter, and the generated stop payment letter is electronically signed and stamped with an electronic official seal.

[0029] Specifically, the python-docx document automation processing library is used to quickly generate a "Suspect's Stop Payment Official Letter" based on the preset template, automatically fill in the document content, stamp the electronic signature and electronic seal, and automatically upload it to the anti-fraud big data platform.

[0030] In one example, the above-mentioned generation of a stop payment letter based on a preset template and online fraud warning information includes: extracting the case name and the fraud-related account from the online fraud warning information; and generating a stop payment letter based on the preset template, the case name and the fraud-related account.

[0031] Specifically, the case name of the warning is used to verify the authenticity of the network fraud warning information. Since the stop payment application and the anti-fraud center system have established legal communication and data transmission in advance, the legal source of the fraud-related accounts in the network fraud warning information can be guaranteed, as well as the privacy and security of the fraud-related accounts.

[0032] S210, automatically sending a stop payment application to the anti-fraud big data platform through the stop payment application page, and the stop payment application includes a stop payment official letter and an application form.

[0033] In this embodiment, when the terminal device sends a stop payment application to the anti-fraud big data platform, the stop payment official letter and the application form are sent to the anti-fraud big data platform together, so that the anti-fraud big data platform can parse the stop payment application to obtain the fraud-related account and send the stop payment notification of the fraud-related account to the payment institution. Among them, the stop payment application is used to stop the fraud-related account to the anti-fraud big data platform. When the anti-fraud big data platform receives the stop payment application, it sends an approval task to the corresponding approver account, and the approval task contains the stop payment official letter and the application form, so that the approver can approve the stop payment application.

[0034] In one embodiment, after the above step of automatically sending the stop payment application to the anti-fraud big data platform through the stop payment application page, it also includes: reading the image information containing the verification code, locating the verification code image element in the image information through the Selenium browser automation tool, and capturing the verification code image element, pre-processing the captured verification code image element, using the OCR engine to identify the pre-processed verification code image element to extract the verification code, and filling the identified verification code into the verification code input box to complete the verification of the stop payment application.

[0035] Specifically, for the verification code that appears during the stop payment application submission process, Tesseract OCR technology is used to identify the verification code and automatically fill it in the corresponding position to ensure a smooth process. Specifically, it includes: 1) Captcha image capture: Use the Selenium browser automation tool to locate the captcha image element and capture its image.

[0036] 2) Preprocessing: The captured verification code image is preprocessed, including denoising, binarization, size adjustment, etc., to improve the accuracy of OCR recognition.

[0037] 3) OCR recognition: Use the Tesseract OCR engine to recognize the preprocessed verification code image and extract the text information.

[0038] 4) Automatic filling: If the recognition result is valid, the recognized verification code will be automatically filled into the corresponding input box through tools such as Selenium and pyautogui.

[0039] For verification codes that fail to be recognized, they are automatically refreshed and re-recognized, and the failed image samples are saved. The saved failed samples are manually annotated regularly, and the annotated data is used to train or fine-tune the OCR model to improve the model's recognition accuracy for verification codes and ensure that the success rate of the first recognition is ≥95%.

[0040] S212, receiving the approval task from the anti-fraud big data platform based on the stop payment disposal application feedback, the approval task includes the stop payment official letter and application form.

[0041] S214, based on the approver information and through the stop payment application, the approval task is approved. After the approval is passed, a stop payment processing request is automatically sent to the anti-fraud big data platform. After the anti-fraud big data platform receives the stop payment processing request, it parses the stop payment official letter in the stop payment processing application, obtains the fraud-related account, and sends a stop payment processing notification of the fraud-related account to the payment institution.

[0042] In this embodiment, as mentioned above, the stop payment application is encapsulated with a natural language processing program of artificial intelligence technology. Therefore, the stop payment official letter and application form in the approval task can be identified. Specifically, the stop payment application automatically queries the list of stop payment applications to be approved every minute, and the stop payment application list contains the approval tasks to be approved. After determining the approval task, the named entity recognition (NER) and text parsing method in the NLP technology are used to automatically extract key information from the stop payment official letter. Specifically, by learning the features of the stop payment official letter, the extraction rate of key information can reach 100%. The key information extracted from the stop payment official letter is automatically compared and verified with the content in the application form to ensure the consistency of the two contents. After the content comparison is correct, the approval opinion is automatically filled in according to the preset rules and templates to complete the entire approval process. For applications that fail to be reviewed, SMS notifications are automatically generated to notify the applicant and the reviewer for manual review as soon as possible to avoid the situation of untimely approval. Therefore, the accuracy of the stop payment application can be guaranteed by artificial intelligence technology.

[0043] Among them, after the anti-fraud big data platform receives the stop payment disposal request, the anti-fraud big data platform can parse out the fraudulent account from the stop payment official letter, or parse out the fraudulent account from the application form, or parse out the fraudulent account from both the stop payment official letter and the application form, and then check each other and determine the fraudulent account after the proofreading is passed. After the payment institution determines the fraudulent account, it will carry out stop payment disposal control on the fraudulent account.

[0044] The above-mentioned method for automating the process of heterogeneous systems based on RPA and artificial intelligence technology, the heterogeneous system includes a terminal device, an anti-fraud center system and an anti-fraud big data platform, the terminal device is installed with a stop payment application configured based on RPA and artificial intelligence technology, the stop payment application is based on a cross-platform GUI automation tool and is written in combination with a browser driver interface, and the stop payment application is encapsulated with a natural language processing program of artificial intelligence technology, including: starting the stop payment application; opening and logging into the anti-fraud big data platform from a browser through the stop payment application; when any network fraud alarm information of the anti-fraud center system is monitored, opening the stop payment application page of the anti-fraud big data platform through the stop payment application based on the applicant information, using the web application testing tool to automatically locate the form fields of the stop payment application page, and based on Dynamically fill in the form fields with the content according to the online fraud alarm information to obtain the application form; read the preset template, generate a stop payment letter based on the preset template and the online fraud alarm information, and configure the stop payment letter with an electronic official seal and an electronic signature; automatically send a stop payment disposal application to the anti-fraud big data platform through the stop payment application page, and the stop payment disposal application carries the stop payment letter and the application form; receive the approval task based on the feedback of the stop payment disposal application from the anti-fraud big data platform, and the approval task includes the stop payment letter and the application form; approve the approval task based on the approver information and through the stop payment application, and after the approval is passed, automatically send a stop payment disposal request to the anti-fraud big data platform. After receiving the stop payment disposal request, the anti-fraud big data platform parses the stop payment letter in the stop payment disposal application, obtains the fraud-related account, and sends the stop payment disposal notice of the fraud-related account to the payment institution. Therefore, when any network fraud warning information is monitored by the anti-fraud center system, the stop payment application is used to automatically log in to the anti-fraud big data platform and automatically submit a stop payment application. There is no need for manual operation to enter the network fraud warning information and manually send the stop payment application to the anti-fraud big data platform, as well as automatic approval and processing of the stop payment application based on artificial intelligence technology. The stop payment of accounts involved in network fraud is automatically handled, which quickly responds to network fraud and improves the timeliness of fund stop payment.

[0045] In one embodiment, the above-mentioned approval of the approval task based on the approver information and through the stop payment application includes: after confirming the approver's approval authority based on the approver information, extracting the relevant information and approval unit information of the fraudulent account from the stop payment official letter of the approval task through the natural language processing program of the stop payment application, and extracting the relevant information and approval unit information of the fraudulent account from the application form, and comparing the relevant information and approval unit information of the fraudulent account in the stop payment official letter with the relevant information and approval unit information of the fraudulent account in the application form, and confirming the approval when the comparison results are the same.

[0046] As in the above embodiment, the stop payment application is configured with the roles of the applicant and the approver. The role of the applicant has the function of opening the stop payment application page of the anti-fraud big data platform to apply for stop payment disposal. The role of the approver has the function of approving the stop payment disposal application. The approver role compares the information in the application form with the stop payment official letter, especially checks whether the content and the electronic official seal in the stop payment official letter are correct. After confirming that the approval is passed, the stop payment disposal request is sent to the anti-fraud big data platform. After receiving the stop payment disposal request, the anti-fraud big data platform sends a stop payment disposal notification to the payment structure.

[0047] Specifically, the stop payment application automatically queries the list of pending stop payment applications every minute, and the list of stop payment applications contains the pending approval tasks. After determining the approval tasks, the named entity recognition (NER) and text parsing methods in NLP technology are used to automatically extract key information from the stop payment official letter. Specifically, by learning the features of the stop payment official letter, the extraction rate of key information can reach 100%. The key information extracted from the stop payment official letter is automatically compared and verified with the content in the application form to ensure the consistency of the two contents. After the content is compared correctly, the approval opinion is automatically filled in according to the preset rules and templates to complete the entire approval process. For applications that fail to be reviewed, SMS notifications are automatically generated to notify the applicant and the reviewer for manual review as soon as possible to avoid the situation of delayed approval. Therefore, the accuracy of the stop payment application can be guaranteed.

[0048] In one embodiment, after the above step of sending a stop payment request to the anti-fraud big data platform, it also includes: regularly querying multiple stop payment results fed back by one or more payment institutions in the anti-fraud big data platform, performing statistical analysis on the multiple stop payment results, and outputting and displaying the statistical analysis results.

[0049] Specifically, we regularly query the bank's stop payment results fed back by the anti-fraud big data platform, collect statistics and analyze the stop payment results, and ensure that emergency stop payment is completed within the critical "golden half hour" to maximize the chance of recovering losses for victims. After the approval is completed, the anti-fraud big data platform will automatically send a request to the bank and payment institution for stop payment, but the stop payment result is not returned in real time. It is necessary to regularly poll the anti-fraud big data platform to query the stop payment results fed back by the bank, so as to know the stop payment results and statistical results.

[0050] In one embodiment, before the above S204, that is, before the above step of opening and logging into the anti-fraud big data platform from the browser through the stop payment application, it also includes: obtaining the version information of the operating system, the version information of the browser and the office software information of the terminal device; the above S204, opening and logging into the anti-fraud big data platform from the browser through the stop payment application, includes: when confirming that the version information of the stop payment application and the operating system and the version information of the browser are all adapted, opening and logging into the anti-fraud big data platform from the browser through the stop payment application, wherein the version information of the browser matches the driver of the browser; the above S208, generating a stop payment official letter based on a preset template and network fraud warning information, includes: when confirming that the document processing application has been installed based on the office software information, calling the document processing application and generating a stop payment official letter based on the preset template and the network fraud warning information.

[0051] In one example, the office software information includes registry entries and / or program file directories; the above-mentioned confirming that the document processing application has been installed based on the office software information includes: confirming that the document processing application has been installed based on the registry entries and / or program file directories; or, confirming that the document processing application has been installed by executing a specific command.

[0052] In this embodiment, key information such as the version information of the operating system of the terminal device, the version information of the browser, and the office software information is read. Specifically, the version information of the operating system of the terminal device: the version information of the operating system is obtained through the platform library or OS library of Python. The version information of the browser: the version information of the browser is obtained by using the selenium library in combination with a specific browser driver. The browser can be a Chrome browser. Office software information: confirm whether the document processing application has been installed by checking the registry entry, the program file directory, or executing a specific command. The document processing application can be WPS software.

[0053] Specifically, when a payment stop application, such as a payment stop smart assistant, is installed on different office computers, the operating systems of the computers are not unified, and the class libraries of the payment stop smart assistant are also different. For example, they are divided into 32-bit and 64-bit, and the corresponding class libraries need to be dynamically loaded according to the version of the operating system. In addition, the operating system must meet Windows 7 and above and pass the detection of the operating environment. At the same time, the versions of the Chrome browser installed on the office computer are different. Before the payment stop smart assistant runs, it is necessary to dynamically load the driver corresponding to the browser version according to the browser version. That is, the payment stop application is adapted to the version information of the operating system of the terminal device and the version information of the browser installed thereon.

[0054] For example, strictly verify whether the computer environment meets the software running conditions, ensure that the operating system is Windows 7 64-bit or above, Chrome browser version 80 or above, WPS office software has been installed, and the clock error is calibrated within 60 seconds. Use the web driver_manager library to intelligently match and automatically install the chrome driver that matches the current Chrome browser version. Furthermore, use the python-docx document automation processing library to quickly generate the "Suspect's Stop Payment Official Letter" based on the preset template.

[0055] In one embodiment, before the above S206, it also includes: establishing a long connection with the back-end platform, monitoring the network fraud warning information issued by the back-end platform in real time; obtaining the system time of the terminal device, and the system time is used to add a timestamp to the official letter of payment; sending the system time to the back-end platform, and when the back-end platform confirms that the time difference between the system time and the server time is greater than the set time, the server time is sent to the terminal device; if the server time is received, the system time is calibrated based on the server time.

[0056] Specifically, the terminal device establishes a long connection with its back-end platform through the stop payment application and receives the network fraud warning information issued by the back-end platform. In addition, the system time can be obtained through Python's datetime library and sent to the back-end platform. The back-end platform compares the system time with its internal server time. If the time difference between the two is greater than the set duration, such as a difference of 60 seconds, it is determined that there is an error in the system time of the terminal device. At this time, the server time is sent to the terminal device so that the terminal device is based on the system time inside the server time calibrator. Therefore, for terminal devices running on the intranet, such as office computers running on the public security intranet, when there is no automatic time synchronization, when the system time is prone to errors, the system time of the terminal device can be calibrated in time by calibrating the time through the back-end platform and issuing the benchmark server time to ensure the accuracy of the system time of the terminal device.

[0057] Furthermore, when the terminal device generates a stop payment letter, the system time is used as the timestamp of the stop payment letter. Therefore, ensuring the accuracy of the system time of the terminal device can ensure the accuracy of the time in the system service of the terminal device. The system service includes the time of the stop payment letter and other operation time.

[0058] In one embodiment, before the above S206, it also includes: monitoring the network fraud warning information from the business system, or monitoring the network fraud warning information imported into the stop payment application.

[0059] Specifically, the network fraud warning information can be sent to the client of the stop payment application after the platform is connected to the business system of the public security, or the network fraud warning information can be directly imported into the stop payment application. Therefore, multiple ways of monitoring network fraud warning information can be realized.

[0060] The above-mentioned embodiment is a heterogeneous system process automation processing method based on RPA and artificial intelligence technology, which significantly improves the efficiency and success rate of emergency stop payment of fraud-related accounts in telecommunications network fraud alerts. Through fully automatic data docking across systems, the automatic entry of information, intelligent identification of content, automatic generation of documents, and automatic approval of processes are realized. These automated and intelligent functions not only greatly reduce the time and cost of manual operations, but also reduce the risk of human errors, thereby greatly improving the success rate of recovering stolen goods. Completing emergency stop payment within the "golden half hour" provides a strong guarantee for victims to recover their losses.

[0061] The above embodiment is a heterogeneous system process automation processing method based on RPA and artificial intelligence technology, which is applied to a terminal device. The terminal device is installed with a stop payment application, namely, a stop payment intelligent assistant, which mainly realizes the two operations of automated application and automated approval of stop payment applications. The operation of automated application is as follows Figure 3 As shown in the figure, the operation of automated approval is as follows Figure 4 shown.

[0062] The present application discloses a heterogeneous system process automation processing method based on RPA and artificial intelligence technology, which has a wide range of application scenarios, including but not limited to the rapid suspension of payment and recovery of defrauded funds in telecommunications network fraud alerts, as well as automated and intelligent business process optimization processing between heterogeneous systems. By integrating the automated processing capabilities of RPA technology and the intelligent decision-making support of AI technology, it is possible to achieve rapid response and efficient processing of telecommunications network fraud, bringing innovative progress to the field of telecommunications fraud prevention.

[0063] It should be understood that, although the steps in the flowchart are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0064] This application also provides a heterogeneous system process automation processing device based on RPA and artificial intelligence technology. Figure 5As shown, an automated processing device for heterogeneous system processes based on RPA and artificial intelligence technologies, the heterogeneous system includes terminal equipment, an anti-fraud center system and an anti-fraud big data platform, the terminal equipment is installed with a stop payment application configured based on RPA and artificial intelligence technologies, the stop payment application is written based on a cross-platform GUI automation tool and combined with a browser driver interface, and the stop payment application is encapsulated with a natural language processing program using artificial intelligence technology; an automated processing device for heterogeneous systems based on RPA and artificial intelligence technologies is applied to terminal equipment of heterogeneous systems, including a startup module 502, a login module 504, a form filling module 506, a generation module 508, a sending module 510, a receiving module 512, and a stop payment disposal module 514. The start module 502 is used to start the stop payment application; the login module 504 is used to open and log in to the anti-fraud big data platform from the browser through the stop payment application; the form filling module 506 is used to open the stop payment application page of the anti-fraud big data platform through the stop payment application based on the applicant information when any network fraud warning information of the anti-fraud center system is monitored, use the web application testing tool to automatically locate the form fields of the stop payment application page, and dynamically fill in the content of the form fields according to the network fraud warning information to obtain the application form; the generation module 508 is used to read the preset template, generate a stop payment official letter based on the preset template and the network fraud warning information, and configure the electronic official seal and electronic signature for the stop payment official letter The name; the sending module 510 is used to automatically send the stop payment disposal application to the anti-fraud big data platform through the stop payment application page, and the stop payment disposal application carries the stop payment official letter and application form; the receiving module 512 is used to receive the approval task based on the feedback of the stop payment disposal application from the anti-fraud big data platform, and the approval task includes the stop payment official letter and application form; the stop payment disposal module 514 is used to approve the approval task based on the approver information and through the stop payment application program, and after the approval is passed, automatically send the stop payment disposal request to the anti-fraud big data platform, and after receiving the stop payment disposal request, the anti-fraud big data platform parses the stop payment official letter in the stop payment disposal application, obtains the fraud-related account, and sends the stop payment disposal notification of the fraud-related account to the payment institution.

[0065] In one of the embodiments, the form fields of the stop payment application page include a first field for the payment institution, a second field for the reason, and a third field for the person handling the matter; the contents of the form fields are dynamically filled in according to the online fraud warning information, including: extracting the payment institution and the reason for fraud from the online fraud warning information and extracting the user information of the person handling the matter from the system; filling the extracted payment institution into the first field, filling the extracted reason for fraud into the second field, and filling the user information of the person handling the matter into the third field.

[0066] In one embodiment, a stop payment letter is generated based on a preset template and online fraud warning information, including: extracting the case name and the fraud-related account from the online fraud warning information; and generating a stop payment letter based on the preset template, the case name and the fraud-related account.

[0067] In one of the embodiments, the approval task is approved based on the approver information and through a stop payment application, including: after confirming the approver's approval authority based on the approver information, extracting the relevant information of the fraudulent account and the approval unit information from the stop payment official letter of the approval task through the natural language processing program of the stop payment application, and extracting the relevant information of the fraudulent account and the approval unit information from the application form, comparing the relevant information of the fraudulent account and the approval unit information in the stop payment official letter with the relevant information of the fraudulent account and the approval unit information in the application form, and confirming the approval when the comparison results are the same.

[0068] In one of the embodiments, before opening and logging into the anti-fraud big data platform from a browser through a stop payment application, it also includes: obtaining the version information of the operating system, the version information of the browser, and the office software information of the terminal device; opening and logging into the anti-fraud big data platform from a browser through the stop payment application, including: when confirming that the version information of the stop payment application and the operating system and the version information of the browser are all compatible, opening and logging into the anti-fraud big data platform from a browser through the stop payment application, wherein the version information of the browser matches the driver of the browser; generating a stop payment official letter based on a preset template and network fraud warning information, including: when confirming that the document processing application has been installed based on the office software information, calling the document processing application and generating a stop payment official letter based on the preset template and the network fraud warning information.

[0069] In one of the embodiments, the office software information includes registry entries and / or program file directories; confirming that the document processing application has been installed based on the office software information includes: confirming that the document processing application has been installed based on the registry entries and / or program file directories; or, confirming that the document processing application has been installed by executing a specific command.

[0070] In one of the embodiments, before monitoring any network fraud warning information of the anti-fraud center system, it also includes: establishing a long connection with the back-end platform, monitoring the network fraud warning information issued by the back-end platform in real time; obtaining the system time of the terminal device, the system time is used to add a timestamp to the payment letter; sending the system time to the back-end platform, and when the back-end platform confirms that the time difference between the system time and the server time is greater than the set time, the server time is sent to the terminal device; if the server time is received, the system time is calibrated based on the server time.

[0071] For the specific definition of a heterogeneous system process automation processing device based on RPA and artificial intelligence technology, please refer to the definition of a heterogeneous system process automation processing method based on RPA and artificial intelligence technology above, which will not be repeated here. Each module in the above-mentioned heterogeneous system process automation processing device based on RPA and artificial intelligence technology can be implemented in whole or in part through software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0072] In one embodiment, a terminal device is provided, whose internal structure diagram can be as follows: Figure 6 As shown. The terminal device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a heterogeneous system process automation processing method based on RPA and artificial intelligence technology is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0073] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0074] In one embodiment, a terminal device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Start the stop payment application; open and log in to the anti-fraud big data platform from the browser through the stop payment application; when any network fraud alarm information of the anti-fraud center system is monitored, open the stop payment application page of the anti-fraud big data platform through the stop payment application based on the applicant information, use the web application testing tool to automatically locate the form fields of the stop payment application page, and dynamically fill in the content of the form fields according to the network fraud alarm information to obtain the application form; read the preset template, generate a stop payment letter based on the preset template and the network fraud alarm information, and configure the stop payment letter with an electronic official seal and an electronic signature; automatically send a stop payment disposal application to the anti-fraud big data platform through the stop payment application page, and the stop payment disposal application carries the stop payment letter and the application form; receive the approval task based on the feedback of the stop payment disposal application from the anti-fraud big data platform, and the approval task includes the stop payment letter and the application form; approve the approval task based on the approver information and through the stop payment application, and after the approval is passed, automatically send a stop payment disposal request to the anti-fraud big data platform, and after receiving the stop payment disposal request, the anti-fraud big data platform parses the stop payment letter in the stop payment disposal application, obtains the fraud-related account, and sends the stop payment disposal notification of the fraud-related account to the payment institution.

[0075] In one embodiment, the form fields of the stop payment application page include a first field for the payment institution, a second field for the reason, and a third field for the person handling the matter; when the processor executes a computer program to implement the above-mentioned step of dynamically filling in the content of the form fields according to the network fraud warning information, the following steps are specifically implemented: extracting the payment institution and the reason for fraud from the network fraud warning information and extracting the user information of the person handling the matter from the system; filling in the extracted payment institution into the first field, filling in the extracted reason for fraud into the second field, and filling in the user information of the person handling the matter into the third field.

[0076] In one embodiment, when the processor executes a computer program to implement the above-mentioned step of generating a stop payment letter based on a preset template and online fraud warning information, the following steps are specifically implemented: extracting the case name and the fraud-related account from the online fraud warning information; generating a stop payment letter based on the preset template, the case name and the fraud-related account.

[0077] In one of the embodiments, when the processor executes a computer program to implement the above-mentioned step of approving the approval task based on the approver information and through a stop payment application, the following steps are specifically implemented: after confirming the approver's approval authority based on the approver information, extract the relevant information of the fraudulent account and the approval unit information from the stop payment official letter of the approval task through the natural language processing program of the stop payment application, and extract the relevant information of the fraudulent account and the approval unit information from the application form, compare the relevant information of the fraudulent account and the approval unit information in the stop payment official letter with the relevant information of the fraudulent account and the approval unit information in the application form, and confirm the approval when the comparison results are the same.

[0078] In one of the embodiments, the processor executes a computer program to further implement the following steps: obtaining the version information of the operating system, the version information of the browser, and the office software information of the terminal device; when the processor executes the computer program to implement the above-mentioned step of opening and logging into the anti-fraud big data platform from the browser through the stop payment application, the following steps are specifically implemented: when it is confirmed that the stop payment application is compatible with the version information of the operating system and the version information of the browser, the anti-fraud big data platform is opened and logged into the anti-fraud big data platform from the browser through the stop payment application, wherein the version information of the browser matches the driver of the browser; when the processor executes the computer program to implement the above-mentioned step of generating a stop payment official letter based on a preset template and network fraud warning information, the following steps are specifically implemented: when it is confirmed based on the office software information that the document processing application has been installed, the document processing application is called and a stop payment official letter is generated based on the preset template and the network fraud warning information.

[0079] In one embodiment, the office software information includes registry entries and / or program file directories; when the processor executes a computer program to implement the above-mentioned step of confirming that the document processing application has been installed based on the office software information, the following steps are specifically implemented: confirming that the document processing application has been installed based on the registry entries and / or program file directories; or, confirming that the document processing application has been installed by executing a specific command.

[0080] In one of the embodiments, the processor executes the computer program to further implement the following steps: establish a long connection with the back-end platform, and monitor the network fraud warning information issued by the back-end platform in real time; obtain the system time of the terminal device, and the system time is used to add a timestamp to the official letter of payment; send the system time to the back-end platform, and when the back-end platform confirms that the time difference between the system time and the server time is greater than the set time, the server time is sent to the terminal device; if the server time is received, the system time is calibrated based on the server time.

[0081] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: starting a stop payment application; opening and logging into an anti-fraud big data platform from a browser through the stop payment application; when any network fraud warning information of an anti-fraud center system is monitored, opening a stop payment application page of the anti-fraud big data platform through the stop payment application based on applicant information, using a web application testing tool to automatically locate form fields on the stop payment application page, and dynamically filling in the content of the form fields according to the network fraud warning information to obtain an application form; reading a preset template, and based on the preset template and the network fraud warning information Generate a stop payment letter, configure the stop payment letter with an electronic official seal and electronic signature; automatically send a stop payment application to the anti-fraud big data platform through the stop payment application page, and the stop payment application includes the stop payment letter and application form; receive the approval task based on the feedback of the stop payment application from the anti-fraud big data platform, and the approval task includes the stop payment letter and application form; approve the approval task based on the approver information and through the stop payment application, and automatically send a stop payment request to the anti-fraud big data platform after the approval is passed. After receiving the stop payment request, the anti-fraud big data platform parses the stop payment letter in the stop payment application, obtains the fraud-related account, and sends the stop payment notification of the fraud-related account to the payment institution.

[0082] In one embodiment, the form fields of the stop payment application page include a first field for the payment institution, a second field for the reason, and a third field for the person handling the matter; when the computer program is executed by the processor to implement the above-mentioned steps of dynamically filling in the contents of the form fields according to the network fraud warning information, the following steps are specifically implemented: extracting the payment institution and the reason for fraud from the network fraud warning information and extracting the user information of the person handling the matter from the system; filling in the extracted payment institution into the first field, filling in the extracted reason for fraud into the second field, and filling in the user information of the person handling the matter into the third field.

[0083] In one embodiment, when the computer program is executed by the processor to implement the above-mentioned steps of generating a stop payment letter based on a preset template and online fraud warning information, the following steps are specifically implemented: extracting the case name and the fraud-related account from the online fraud warning information; generating a stop payment letter based on the preset template, the case name and the fraud-related account.

[0084] In one of the embodiments, when the computer program is executed by the processor to implement the above-mentioned steps of approving the approval task based on the approver information and through the stop payment application, the following steps are specifically implemented: after confirming the approver's approval authority based on the approver information, extract the relevant information and approval unit information of the fraudulent account from the stop payment official letter of the approval task through the natural language processing program of the stop payment application, and extract the relevant information and approval unit information of the fraudulent account from the application form, and compare the relevant information and approval unit information of the fraudulent account in the stop payment official letter with the relevant information and approval unit information of the fraudulent account in the application form, and confirm the approval when the comparison results are the same.

[0085] In one of the embodiments, the computer program is executed by the processor to further implement the following steps: obtaining the version information of the operating system, the version information of the browser, and the office software information of the terminal device; when the computer program is executed by the processor to implement the above-mentioned steps of opening and logging into the anti-fraud big data platform from the browser through the stop payment application, the following steps are specifically implemented: when it is confirmed that the stop payment application is compatible with the version information of the operating system and the version information of the browser, the anti-fraud big data platform is opened and logged into the anti-fraud big data platform from the browser through the stop payment application, wherein the version information of the browser matches the driver of the browser; when the computer program is executed by the processor to implement the above-mentioned steps of generating a stop payment official letter based on a preset template and network fraud warning information, the following steps are specifically implemented: when it is confirmed that the document processing application has been installed based on the office software information, the document processing application is called and a stop payment official letter is generated based on the preset template and the network fraud warning information.

[0086] In one embodiment, the office software information includes registry entries and / or program file directories; when the computer program is executed by the processor to implement the above-mentioned steps of confirming that the document processing application has been installed based on the office software information, the following steps are specifically implemented: confirming that the document processing application has been installed based on the registry entries and / or program file directories; or, confirming that the document processing application has been installed by executing a specific command.

[0087] In one of the embodiments, the computer program executed by the processor also implements the following steps: establishing a long connection with the back-end platform and monitoring the network fraud warning information issued by the back-end platform in real time; obtaining the system time of the terminal device, and the system time is used to add a timestamp to the official letter of payment; sending the system time to the back-end platform, and when the back-end platform confirms that the time difference between the system time and the server time is greater than the set time period, the server time is sent to the terminal device; if the server time is received, the system time is calibrated based on the server time.

[0088] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0089] In the embodiment of the present invention, the user information is obtained with the consent of the user, and all the user data obtained complies with the provisions of relevant policies and laws.

[0090] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0091] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A heterogeneous system process automation processing method based on RPA and artificial intelligence technology, characterized in that: The heterogeneous system includes a terminal device, an anti-fraud center system and an anti-fraud big data platform. The terminal device is installed with a stop payment application configured based on RPA and artificial intelligence technology. The stop payment application is written based on a cross-platform GUI automation tool and combined with a browser driver interface. The stop payment application is encapsulated with a natural language processing program of artificial intelligence technology; The method is applied to a terminal device of the heterogeneous system, and the method includes: initiating the stop payment application; Opening and logging into the anti-fraud big data platform from the browser through the stop payment application; When any network fraud warning information of the anti-fraud center system is monitored, the stop payment application page of the anti-fraud big data platform is opened through the stop payment application based on the applicant information, the form fields of the stop payment application page are automatically located using the web application testing tool, and the content of the form fields is dynamically filled according to the network fraud warning information to obtain an application form; Reading a preset template, generating a stop payment letter based on the preset template and the network fraud warning information, and configuring an electronic official seal and an electronic signature for the stop payment letter; Automatically sending a stop payment application to the anti-fraud big data platform through the stop payment application page, wherein the stop payment application carries the stop payment official letter and the application form; Receiving an approval task from the anti-fraud big data platform based on the stop payment processing application feedback, wherein the approval task includes the stop payment official letter and the application form; The approval task is approved based on the approver information and through the stop payment application. After the approval is passed, a stop payment processing request is automatically sent to the anti-fraud big data platform. After receiving the stop payment processing request, the anti-fraud big data platform parses the stop payment official letter in the stop payment processing application, obtains the fraud-related account, and sends a stop payment processing notification of the fraud-related account to the payment institution.

2. The method according to claim 1, characterized in that The form fields of the stop payment application page include a first field of the payment institution, a second field of the reason, and a third field of the person handling the matter; The content of the form field is dynamically filled according to the network fraud warning information, including: Extract the payment institution and the cause of the fraud from the network fraud warning information and extract the user information of the person handling the fraud from the system; The extracted payment institution is filled in the first field, the extracted fraud reason is filled in the second field, and the user information of the handler is filled in the third field.

3. The method according to claim 1 or 2, characterized in that: The generating of the stop payment letter based on the preset template and the network fraud warning information includes: Extract the case name and the fraud-related account from the network fraud warning information; A stop payment letter is generated based on the preset template, the case name, and the fraud-related account.

4. The method according to claim 1, characterized in that: The approving the approval task based on the approver information and through the stop payment application program includes: After confirming the approval authority of the approver based on the approver information, the relevant information of the fraudulent account and the approval unit information are extracted from the stop payment official letter of the approval task through the natural language processing program of the stop payment application, and the relevant information of the fraudulent account and the approval unit information are extracted from the application form. The relevant information of the fraudulent account and the approval unit information in the stop payment official letter are compared with the relevant information of the fraudulent account and the approval unit information in the application form, and the approval is confirmed when the comparison results are the same.

5. The method according to claim 1, characterized in that Before the step of opening and logging into the anti-fraud big data platform from the browser through the payment stop application, the step further includes: Obtaining version information of the operating system of the terminal device, version information of the browser, and office software information; The step of opening and logging into the anti-fraud big data platform from the browser through the stop payment application comprises: When confirming that the stop payment application is compatible with the version information of the operating system and the version information of the browser, opening and logging into the anti-fraud big data platform from the browser through the stop payment application, wherein the version information of the browser matches the driver of the browser; The generating of the stop payment letter based on the preset template and the network fraud warning information includes: When it is confirmed that the document processing application has been installed based on the office software information, the document processing application is called and a stop payment letter is generated based on a preset template and the network fraud warning information.

6. The method according to claim 5, characterized in that The office software information includes registration entries and / or program file directories; The step of confirming that the document processing application has been installed based on the office software information includes: confirming that the document processing application is installed based on the registry entry and / or program file directory; Alternatively, confirm that the document processing application is installed by executing a specific command.

7. The method according to claim 1, characterized in that The method further comprises: Establish a long connection with the back-end platform and monitor the online fraud warning information issued by the back-end platform in real time; Acquiring the system time of the terminal device, wherein the system time is used to add a timestamp to the stop payment letter; The system time is sent to the backend platform, and when the backend platform confirms that the time difference between the system time and the server time is greater than a set time period, the server time is sent to the terminal device; If the server time is received, the system time is calibrated based on the server time.

8. A heterogeneous system process automation processing device based on RPA and artificial intelligence technology, characterized in that: The heterogeneous system includes a terminal device, an anti-fraud center system and an anti-fraud big data platform. The terminal device is installed with a stop payment application configured based on RPA and artificial intelligence technology. The stop payment application is written based on a cross-platform GUI automation tool and combined with a browser driver interface. The stop payment application is encapsulated with a natural language processing program of artificial intelligence technology; The device is applied to a terminal device of the heterogeneous system, and the device includes: A starting module, used for starting the stop payment application; A login module, used to open and log in to the anti-fraud big data platform from the browser through the stop payment application; A form filling module is used to, when monitoring any network fraud warning information of the anti-fraud center system, open the stop payment application page of the anti-fraud big data platform through the stop payment application based on the applicant information, automatically locate the form fields of the stop payment application page using a web application testing tool, and dynamically fill in the content of the form fields according to the network fraud warning information to obtain an application form; A generation module, used for reading a preset template, generating a stop payment letter based on the preset template and the network fraud warning information, and configuring an electronic official seal and an electronic signature for the stop payment letter; A sending module, used for automatically sending a stop payment application to the anti-fraud big data platform through the stop payment application page, wherein the stop payment application carries the stop payment official letter and the application form; A receiving module, configured to receive an approval task from the anti-fraud big data platform based on the feedback of the stop payment disposal application, wherein the approval task includes the stop payment official letter and the application form; The stop payment processing module is used to approve the approval task based on the approver information and through the stop payment application. After the approval is passed, a stop payment processing request is automatically sent to the anti-fraud big data platform. After receiving the stop payment processing request, the anti-fraud big data platform parses the stop payment official letter in the stop payment processing application, obtains the fraud-related account, and sends a stop payment processing notification of the fraud-related account to the payment institution.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images