CN115439247A

CN115439247A - Transaction data processing method and device

Info

Publication number: CN115439247A
Application number: CN202211032395.4A
Authority: CN
Inventors: 单长胜; 刘畅; 艾兰英; 罗彬�; 王鑫伟
Original assignee: China Unionpay Co Ltd
Current assignee: China Unionpay Co Ltd
Priority date: 2022-08-26
Filing date: 2022-08-26
Publication date: 2022-12-06

Abstract

The embodiment of the application provides a transaction data processing method and a device, which are suitable for a robot process automation system, wherein the method comprises the following steps: receiving abnormal transaction data sent by an abnormal transaction detection system, wherein the abnormal transaction data comprises a user account and an activity identifier; determining an electronic commerce platform to which the abnormal transaction data belongs according to the activity identifier, and acquiring a history relevant record corresponding to the user account from the electronic commerce platform; determining the risk level of the user account according to the history relevant record; and processing the abnormal transaction data according to the risk level. The method can automatically complete transaction data processing, and carry out risk grade grading and corresponding processing on abnormal users in abnormal transactions.

Description

Transaction data processing method and device

Technical Field

The present application relates to the field of network technologies, and in particular, to a method and an apparatus for processing transaction data.

Background

With the rapid technological transformation process of the financial industry, the business related to the financial industry can be basically completed on line at present. For example, the promotion and marketing, transaction processing, personnel management and the like of commodities can be completed on line. Behind the marketing business, a cattle arbitrage phenomenon exists, and particularly along with the popularization and application of computer technology and network technology in the financial industry, cattle user groups present the remarkable characteristics of technicalization, clustering and multi-place distribution, and the healthy development of the industry is seriously influenced.

In the prior art, a cattle prevention method is mainly used for extracting transaction characteristics of transaction information based on the transaction characteristics of the transaction information, and after multi-factor verification, if a user of the transaction information is determined to be a suspicious user. Further, whether the suspicious user is a cattle user or not is determined through manual identification. This method requires a lot of manual operations, and is inefficient and costly.

Therefore, there is a need for a transaction data processing method and apparatus, which can automatically complete transaction data processing, rank the risk level of the abnormal user of the abnormal transaction, and perform corresponding processing.

Disclosure of Invention

The embodiment of the application provides a transaction data processing method and device, which can automatically complete transaction data processing, and carry out risk level grading and corresponding processing on abnormal users in abnormal transactions.

In a first aspect, an embodiment of the present application provides a transaction data processing method, which is applied to a robot process automation system, and the method includes:

receiving abnormal transaction data sent by an abnormal transaction detection system, wherein the abnormal transaction data comprises a user account and an activity identifier;

determining an electronic commerce platform to which the abnormal transaction data belongs according to the activity identifier, and acquiring a history relevant record corresponding to the user account from the electronic commerce platform;

determining the risk level of the user account according to the history relevant records;

and processing the abnormal transaction data according to the risk level.

According to the method, the electronic commerce platform to which the abnormal transaction data belongs is determined according to the activity identification of the abnormal transaction data, the history relevant record corresponding to the user account of the abnormal transaction data is obtained from the electronic commerce platform, and further, the risk level of the user account is determined according to the history relevant record. Compared with the prior art that whether a suspicious user is an abnormal user or not is judged based on manual operation, the method and the system for judging the abnormal user can automatically acquire the historical related records of the user account from the electronic commerce platform for carrying out activities according to the activities to which the abnormal transaction data belongs, determine the risk level of the user account according to the historical related records, namely automatically judge the abnormality of the user account, and divide the risk caused by the abnormal degree of the user. Therefore, the abnormal transaction data are processed according to the risk level corresponding to the user account, the abnormal transaction data processing mode can be further refined, and the processing accuracy is improved.

Optionally, before determining the risk level of the user account according to the history related record, the method further includes: acquiring risk related information corresponding to the user account from a big data platform;

determining a risk level of the user account according to the history relevant record, including:

and judging the risk level of the user account according to the abnormal transaction data, the history related records and the risk related information.

According to the method, the risk level of the user account can be judged according to the risk related information acquired from the big data platform, the abnormal transaction data and the history related records. Therefore, the accuracy of the risk level judgment of the user account is improved.

Optionally, the risk level is a low risk level, and processing the abnormal transaction data according to the risk level includes:

determining speech emotion elements according to the abnormal transaction data;

and generating warning information according to the abnormal transaction data and the voice emotion element, and sending the warning information to a user corresponding to the user account through a short message platform or an outbound system, wherein the voice emotion element is used for expressing warning intensity in the warning information.

In the method, when the risk level of the current user account is determined to be a low risk level, the voice emotion element can be determined according to the transaction behavior characteristics in the abnormal transaction data, and the voice emotion element can be used for adding the emotion of voice alarm when the alarm information is used for voice alarm of the user through the outbound system. For example, the speech emotion elements of the abnormal transaction behaviors with different degrees have different degrees of severity, the abnormal transaction behaviors with different degrees may be determined according to the related information such as the intensity of transaction time, the size of transaction amount, and the like, and the specific degree determination of the abnormal transaction behaviors is not limited and may be set according to specific needs. The alarm information can be generated according to the abnormal transaction data to alarm the user, and if the user passes through the voice alarm mode, the voice emotion elements of the voice alarm can be added into the voice alarm. Therefore, the warning effect of voice warning can be improved.

Optionally, the risk level is a medium risk level, and processing the abnormal transaction data according to the risk level includes:

generating an interception instruction according to the abnormal transaction data, and sending the interception instruction to a transfer clearing system;

extracting user basic information from the abnormal transaction data, history related records and the risk related information;

and sending the user basic information to an abnormal list management system, wherein the abnormal list management system is used for maintaining an abnormal user list, and the abnormal user list is used as a basis for detecting abnormal transaction data by the abnormal transaction detection system.

In the method, if the risk level of the abnormal transaction data is determined to be the middle risk level, an interception instruction is generated according to the abnormal transaction data, and the interception instruction is sent to the transfer clearing system. Therefore, the transaction processing flow in the transfer clearing system is intercepted, and the safety and the accuracy of transaction clearing are ensured. Extracting user basic information (transaction data can be included) from the abnormal transaction data, the history relevant records and the risk relevant information and sending the user basic information (transaction data can be included) to the abnormal list management system, so that the abnormal list management system maintains the user basic information (transaction data can be included) to the abnormal user list. Therefore, the subsequent abnormal transaction detection system can detect the transaction according to the abnormal user name list so as to obtain abnormal transaction data.

Optionally, the risk level is a high risk level, and processing the abnormal transaction data according to the risk level includes:

and sending the user basic information to an abnormal list management system, and degrading the user reputation corresponding to the user basic information.

In the method, if the risk level of the abnormal transaction data is determined to be a high risk level, an interception instruction is generated according to the abnormal transaction data, and the interception instruction is sent to the transfer clearing system. Therefore, the transaction processing flow in the transfer clearing system is intercepted, and the safety and the accuracy of transaction clearing are ensured. Extracting user basic information (transaction data can be included) from the abnormal transaction data, the history relevant records and the risk relevant information and sending the user basic information (transaction data can be included) to the abnormal list management system, so that the abnormal list management system maintains the user basic information (transaction data can be included) to the abnormal user list. Therefore, the subsequent abnormal transaction detection system can detect the transaction according to the abnormal user name list so as to obtain abnormal transaction data. And downgrades the user reputation of the user. Therefore, other systems, mechanisms and the like which process the related transaction of the user according to the user credit can process the transaction according to the accurate user credit, and the reliability of transaction processing is ensured.

Optionally, the method further includes:

receiving complaint information of a user, and analyzing the complaint information to generate response information;

sending the response information to the user, wherein the response information is used for indicating the user to upload evidence information;

receiving the evidence information, analyzing the evidence information, judging whether the evidence information accords with a preset matching condition, if so, generating an abnormal removing instruction and sending the abnormal removing instruction to an abnormal list management system;

and generating an exception-removing processing result and sending the exception-removing processing result to a user.

In the method, the complaint information of the user is received, the complaint information is analyzed to generate the response information, and the response information is sent to the user to instruct the user to upload the evidence information. And analyzing the evidence information, and deleting the user from the abnormal user list of the abnormal list management system if the evidence information is determined to meet the preset matching condition. Compared with the prior art, the customer complaint processing method and device have the advantages that the customer complaint is processed in a mode of manually analyzing information such as black and white lists, the customer complaint information is automatically processed, the abnormal user list is automatically maintained, and the customer complaint processing efficiency and accuracy can be improved. After the user is deleted from the abnormal user list of the abnormal list management system, the user can be maintained in the abnormal filing list. Therefore, the method can be used as a basis for judging the abnormity of the subsequent user, and the accuracy of judging the risk level of the user is improved.

Optionally, the method further includes:

counting abnormal user rate under the activity identification aiming at the activity identification, and if the abnormal user rate exceeds a set threshold, analyzing abnormal transaction data of various abnormal users to obtain activity abnormal characteristics, wherein the activity abnormal characteristics comprise an activity abnormal area and activity abnormal commercial tenants;

and generating terminal activity alarm information according to the activity abnormal characteristics, and sending the terminal activity alarm information to the electronic commerce platform, wherein the terminal activity alarm information comprises a proposal coping scheme.

In the method, if the abnormal user rate of the event exceeds the set threshold, it is determined that the event needs to be stopped, a final event warning message is generated and sent to the electronic commerce platform corresponding to the event identifier, the event host is prompted to stop the event, in order to enable the host to be clear of the current event condition, an event abnormal feature can be carried in the final event warning message, and in order to enable the host to quickly respond, a suggested response scheme can be added in the event abnormal feature.

Optionally, the method further includes: aiming at the activity identification, acquiring transaction data of each user under the activity identification; analyzing the transaction characteristics of the transaction data of each user to generate an activity report, wherein the activity report comprises user abnormal rate, user suspicious rate, transaction characteristic distribution and abnormal user concentrated area, and the transaction characteristics comprise: user transaction time, transaction behavior characteristics, transaction occurrence areas and transaction merchant information; and sending the activity report to an electronic commerce platform corresponding to the activity identifier.

According to the method, the transaction data of each user under the activity identification is obtained, and the transaction characteristics of the transaction data of each user are analyzed to obtain the user abnormal rate, the user suspicious rate, the transaction characteristic distribution, the abnormal user concentrated area and other related information to generate the activity report. The activity report is sent to the activity host (which may be the electronic commerce platform corresponding to the activity identifier, or the activity hosted by the activity host may be the activity hosted by the electronic commerce platform corresponding to the activity identifier, and the activity report is obtained through the electronic commerce platform accordingly, and there is no specific limitation on how the activity is hosted by the activity host, and how the activity report is obtained through the electronic commerce platform). Thus, the event host can clearly know the event host condition.

Optionally, the method further includes: determining that the number of the current active users exceeds a first set threshold value, generating a capacity expansion request and sending the capacity expansion request to the virtual machine management system, or determining that the number of the current active users is lower than a second set threshold value, generating a capacity reduction request and sending the capacity reduction request to the virtual machine management system.

According to the method, according to the number of the current active users, the robot process automation system can generate a capacity expansion request to be sent to the virtual machine management system when the number of the current active users exceeds a first set threshold value, so that capacity expansion is achieved through the virtual machine management system, and the system can operate reliably when the transaction volume is large. The robot process automation system can generate a capacity reduction request and send the capacity reduction request to the virtual machine management system when the number of the current active users is lower than a second set threshold value, so that capacity reduction is realized through the virtual machine management system, and when the transaction amount is small, the rest resources cannot be idle and wasted.

In a second aspect, an embodiment of the present application provides a robot process automation system, where the robot process automation system includes a rule command library and independent sub-process modules;

any one of the independent sub-process modules is used for receiving abnormal transaction data sent by an abnormal transaction detection system, matching an analysis rule corresponding to the abnormal transaction data through the rule command library, analyzing the abnormal transaction data according to the analysis rule, and determining a command group of the abnormal transaction data, wherein the abnormal transaction data comprises a user account and an activity identifier;

any one of the independent sub-process modules is used for determining an electronic commerce platform to which the abnormal transaction data belongs according to the activity identifier when receiving the command in the command group, and acquiring a history related record corresponding to the user account from the electronic commerce platform; determining the risk level of the user account according to the history relevant record; and processing the abnormal transaction data according to the risk level.

In the system, the robot process automation system comprises a rule command library and each independent sub-process module. After the robot process automation system receives the abnormal transaction data, a command group can be obtained according to the analysis of the rule command library, corresponding independent sub-process modules are sequentially called through the commands in the command group and the execution sequence of the commands, the risk grade judgment of the user account of the abnormal transaction data is completed, and the corresponding processing is further carried out. Therefore, the system can automatically judge the abnormality of the user account, and divide and correspondingly process the risk caused by the abnormality degree of the user. Compared with the prior art that whether the suspicious user is the abnormal user or not is judged based on manual operation, the efficiency and the accuracy of abnormal transaction data processing are improved, and the processing cost is reduced. In addition, because the sub-process modules are independent from each other, and the plurality of independent sub-process modules are called by the command group in the rule command library to respectively complete corresponding processing, the corresponding completion of the business process processing is realized. The mode is convenient for the change processing of the subsequent system and improves the simplicity of the change.

Optionally, the first independent sub-process module is configured to receive a first command in the command group, determine, according to the activity identifier, an electronic commerce platform to which the abnormal transaction data belongs, and obtain, from the electronic commerce platform, a history related record corresponding to the user account;

the second independent sub-process module is used for receiving a second command in the command group and determining the risk level of the user account according to the history relevant record;

and the third independent sub-process module is used for receiving a third command in the command group and processing the abnormal transaction data according to the risk level.

In the system, in the transaction data processing process, a first independent sub-process module, a second independent sub-process module and a third independent sub-process module can be respectively called through a command group of a first command, a second command and a third command, so that the processing flow of acquiring historical relevant records corresponding to the user account from the corresponding electronic commerce platform according to the activity identification, determining the risk level of the user account according to the historical relevant records and processing abnormal transaction data according to the risk level is respectively completed. Therefore, the whole business process of transaction data processing is completed in a segmented mode, each segment is processed by the corresponding independent sub-process module, the independent sub-process modules are in a loose coupling state, changing operation can be conveniently conducted on the independent sub-process modules, and other independent sub-process modules cannot be affected.

Optionally, the robot process automation system further includes a visualization configuration module;

the visual configuration module is used for receiving a configuration request sent by a client, matching an analysis rule corresponding to the configuration request through the rule command library, analyzing the configuration request according to the analysis rule and determining a command group of the configuration request;

the visual configuration module is further configured to change, based on a fourth command in the command group, an analysis rule and a command group in the rule command library according to the configuration information of the configuration request, and/or change related configurations in each independent sub-process module.

In the system, the robot process automation system further comprises a visual configuration module, the visual configuration module provides a configuration change channel for a user, and analysis rules and command groups in a rule command library can be changed and/or relevant configurations in each independent sub-process module can be changed after a configuration request of a client is received. Therefore, convenience and flexibility of configuration change are improved, and simplicity of system change is improved.

In a third aspect, an embodiment of the present application provides a transaction data processing apparatus, which is suitable for a robot process automation system, and includes:

the receiving and sending module is used for receiving abnormal transaction data sent by the abnormal transaction detection system, and the abnormal transaction data comprises a user account and an activity identifier;

the processing module is used for determining an electronic commerce platform to which the abnormal transaction data belongs according to the activity identifier and acquiring a history related record corresponding to the user account from the electronic commerce platform;

the processing module is further used for determining the risk level of the user account according to the history relevant records;

the processing module is further configured to process the abnormal transaction data according to the risk level.

In a fourth aspect, an embodiment of the present application further provides a computing device, including: a memory for storing a program; a processor for calling the program stored in said memory and executing the method as described in the various possible designs of the first aspect according to the obtained program.

In a fifth aspect, the present embodiments also provide a computer-readable non-volatile storage medium, which includes a computer-readable program, and when the computer-readable program is read and executed by a computer, the computer is caused to perform the method as described in the various possible designs of the first aspect.

These and other implementations of the present application will be more readily understood from the following description of the embodiments.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.

Fig. 1 is a schematic architecture diagram of a service system according to an embodiment of the present application;

fig. 2 is a schematic architecture diagram of a service system according to an embodiment of the present application;

fig. 3 is a schematic diagram of an architecture of a server cluster of a robot process automation system according to an embodiment of the present disclosure;

fig. 4 is a schematic diagram of an architecture of a robot process automation system according to an embodiment of the present disclosure;

fig. 5 is a schematic diagram of an architecture of a robot process automation system according to an embodiment of the present disclosure;

FIG. 6 is a schematic flow chart illustrating a transaction data processing method according to an embodiment of the present application;

fig. 7 is a schematic diagram of a transaction data processing apparatus according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be described in further detail with reference to the accompanying drawings, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.

Fig. 1 is a system architecture of a service system provided in an embodiment of the present application, where a service system 106 includes: an abnormal transaction detection system 101, an abnormal list management system 102, a big data platform 103, a transfer clearing system 104, and a robot process automation system 105, and fig. 1 also shows external systems 107 of a business system 106, including: a customer service platform, a short message platform, an outbound call system, an electronic commerce platform and the like. It should be noted that, the service system 106 and the external systems 107 of the service system 106 are only an example, and the service system 106 and the external systems 107 of the service system 106 in the present embodiment are not limited. For example, the service system 106 may further include a customer service platform of the service system 106 itself, and the external systems 107 may further include a TB e-commerce platform, a JD e-commerce platform, a card-issuing transaction system, and the like. For another example, in a system architecture of a service system provided in the embodiment of the present application shown in fig. 2, a service system 205 includes: an abnormal transaction detection system 201, an abnormal list management system 202, a big data platform 203, a robot process automation system 204, and fig. 2 also shows external systems 206 of a business system 205, including: customer service platform, short message platform, transfer clearing system, outbound system and electronic commerce platform. The service system 205 communicates with each client 207 through the internet or an intranet. The service system 205 in fig. 2 may also be externally connected to an external transit clearing system when operating, but this does not mean that the service system 205 does not necessarily include its own transit clearing system, such as that in fig. 1, which illustrates that the system architectures in fig. 1 and fig. 2 given herein are only an embodiment for clearly explaining the present solution, and do not limit the present solution.

Since each system or platform in the business system 106 may perform the same or different processing functions in different business processing stages, for ease of understanding, the introduction of the business system 106 is divided into a multi-stage description, including:

an abnormal transaction data processing stage:

anomalous transaction detection system 101: the abnormal user list is used for calling the abnormal user list in the abnormal list management system 102, acquiring user basic information and transaction characteristics in the transaction process according to the abnormal user list, and judging whether the transaction is abnormal transaction data or not according to the transaction characteristics. For example, the transaction may be a transaction of a cattle user or a cattle merchant. If the abnormal transaction detection system 101 determines that the user information and/or transaction characteristics of the transaction data of the transaction conform to the abnormal user list, the abnormal transaction data is sent to the robot process automation system 105. The abnormal user list can maintain the user basic information and the transaction characteristics of the transaction of the user. In this way, the abnormal transaction detection system 101 may detect abnormal transaction data according to the user basic information and the transaction characteristics in the abnormal user list.

Robotic process automation system 105: the system is used for receiving abnormal transaction data (including user basic information and transaction information such as a user account number and an activity identifier) sent by the abnormal transaction detection system 101 and automatically processing the abnormal transaction data according to the business rules. For example, according to the activity identifier of the abnormal transaction data, a history related record corresponding to the user account of the abnormal transaction data is obtained from an electronic commerce platform (an electronic commerce platform corresponding to the activity host of the activity identifier) corresponding to the activity identifier in each external system 107 (the history related record may include list information uploaded to the electronic commerce platform by the activity host, the list information may include a commitment book, user information, transaction information, a record of whether the user history is mistaken for an abnormal user, and the like, and in an example, the abnormal user may be a cattle user). And determining the risk level of the user account according to the history related record, and performing corresponding processing according to the risk level.

The method comprises the following steps: if the risk level of the user account is a low risk level, determining a voice emotion element according to the abnormal transaction data; generating warning information according to the abnormal transaction data and the voice emotion elements, sending the warning information to the user corresponding to the user account through a short message platform, a customer service platform or an outbound system and the like in each externally-connected system 107, and adding the emotion of voice warning when the warning information is used for voice warning of the user through the outbound system (the system with the voice playing function) (the warning emotion can be set to be played at different levels by different abnormal degrees of the abnormal transaction data).

If the risk level of the user account is an intermediate risk level, processing the abnormal transaction data according to the risk level, generating an interception instruction according to the abnormal transaction data, and sending the interception instruction to the transfer clearing system 104, so that the transfer clearing system 104 stops the transaction clearing processing flow corresponding to the abnormal transaction data; extracting user basic information and/or transaction data from the abnormal transaction data and the historical related records; the user basic information and/or the transaction data are sent to the abnormal list management system 102, so that the abnormal list management system 102 adds or updates the user basic information and/or the transaction data in the abnormal user list, and further, the accuracy of the abnormal transaction detection system 101 for detecting abnormal transactions based on the abnormal user list is improved.

If the risk level of the user account is a high risk level, generating an interception instruction according to the abnormal transaction data, and sending the interception instruction to the transfer clearing system 104, so that the transfer clearing system 104 stops a transaction clearing processing flow corresponding to the abnormal transaction data; extracting user basic information and/or transaction data from the abnormal transaction data and the historical related records; the user basic information and/or transaction data are sent to the abnormal list management system 102, so that the abnormal list management system 102 adds or updates the user basic information and/or transaction data in the abnormal user list, and further, the accuracy of the abnormal transaction detection system 101 for detecting abnormal transactions based on the abnormal user list is improved. And the user reputation of the user is degraded, so that higher reliability of corresponding transaction based on the user reputation is ensured.

Based on the system architecture in the foregoing embodiment, in an embodiment, when the robot flow automation system 105 acquires the history related record from the e-commerce platform, the risk related information may also be acquired from the big data platform 103, and accordingly, when corresponding processing is performed according to the risk level of the user account, the processing accuracy may be improved. For example, user base information and/or transaction data may be extracted from anomalous transaction data, history-related records, and risk-related information. Therefore, the acquired user basic information and/or transaction data are more accurate, and the abnormal user list is more accurate, so that the abnormal transaction detection system 101 is more accurate when detecting according to the abnormal user list. In an example, the risk related information may be related information such as user basic information, user transaction records, risk prompt information, merchant basic information, POS machine numbers, judicial expertise, and collaborative public opinion management. The setting of the risk related information is not particularly limited here, and may be one or more of the risk related information in the above examples, and is not limited to the information items in the risk related information in the above examples.

Based on the foregoing embodiments, in one embodiment, the robot flow automation system 105 may further generate a confirmation request according to the activity identifier of the abnormal transaction data, and send the confirmation request to the e-commerce platform corresponding to the activity identifier in the external systems 107, where the e-commerce platform may display a corresponding confirmation interface according to the confirmation request, and a worker of the e-commerce platform may perform a confirmation operation on the confirmation interface corresponding to the e-commerce platform (in an embodiment, the confirmation request may include related information such as transaction characteristics and a user account number in the abnormal transaction data, and may be displayed on the confirmation interface). The robot process automation system 105 determines the risk level of the user account according to the response information, and performs corresponding processing according to the risk level.

The big data platform 103: the system is used for maintaining the risk related information such as user basic information, user transaction records, risk prompt information, merchant basic information, POS machine numbers, judicial expertise, cooperative public opinion management and the like.

Transfer clearance system 104: the method is used for clearing the transaction and completing normal transaction processing.

Each client 108: abnormal transaction data corresponding to the activity identifier in the robot process automation system 105, basic information of each user related to the abnormal transaction data, risk level, transaction characteristics, and other related information can be queried.

Customer complaint phase (whether complaint users in the abnormal user list of the abnormal list management system 102 are eliminated):

robotic process automation system 105: the system is further configured to receive complaint information of a user, and analyze the complaint information (in an example, if the complaint information is obtained through a voice channel, a voice may be recognized through an ASR voice-to-text technique, and according to a recognition result, a reply database is matched to obtain a corresponding reply statement, and a response message is generated according to the reply statement (the reply statement may also include a reason for setting the user in an abnormal user list and related certification information)); sending the response information to the user (if the response information is displayed on a platform in a text mode such as a customer service platform, the response information can be directly displayed, and if the response information is played on a platform in a voice mode such as an outbound system, the response information can be converted into response voice for playing through a TTS technology (text-to-speech technology, technology for converting text into voice through a mechanical and electronic method)), wherein the response information is used for indicating the user to upload evidence information; the robot flow automation system 105 receives and downloads the evidence information, analyzes the evidence information (if a document in the evidence information is a file in a picture or PDF format, character recognition may be performed through an OCR technology, character information of the evidence information is obtained, and techniques such as OCR recognition, artificial intelligence may also be used to autonomously intercept, recognize, and determine a material such as evidence information submitted by a user, a certificate of insurance, and the like), determines whether the evidence information meets a preset matching condition, if so, generates an exception resolution instruction to be sent to the exception list management system 102, deletes the user from the exception user list of the exception list management system 102, and may also maintain the user in an exception docket list. Therefore, when abnormal transaction data are formed again in the subsequent transaction of the user, the judgment of the risk level of the user account of the user and the judgment of whether the user account is deleted from the abnormal user list are taken as one of the measurement bases, so that the accuracy of transaction data processing is improved. And generating an exception removal processing result and sending the exception removal processing result to a user.

If the evidence information does not meet the preset matching condition, the user in the abnormal list management system 102 is not processed. And generating an abnormal unreleased processing result and sending the abnormal unreleased processing result to a user.

The robot flow automation system 105 may further automatically feed back the exception resolution processing result/exception non-resolution processing result to a customer service platform externally connected to each system 107 through a TTS technology, or send the processing result to a short message platform according to a short message account of the short message platform or an outbound account of the outbound platform in the user basic information of the user, or convert the processing result into a result voice and send the result voice to a voice platform or a call platform through the TTS and play the result voice to the user.

In addition, the evidence information of the user may also be maintained in an abnormal user list, and for each abnormal user, the abnormal user list may maintain one or more items of user basic information, transaction data, and evidence information. Therefore, the subsequent robot process automation system 105 can conveniently acquire the evidence information of the abnormal user from the abnormal list management system 102, and the evidence information is used as one of the bases for judging whether the evidence information subsequently submitted by the abnormal user meets the rule. The clients 108 may also be enabled to obtain the user basic information, transaction data and evidence information of the abnormal user in the abnormal list management system 102.

Whether the activity detection phase is terminated:

robotic process automation system 105: the system is also used for counting the abnormal user rate under the activity identification aiming at any activity identification, and if the abnormal user rate exceeds a set threshold, analyzing the abnormal transaction data of various abnormal users to obtain activity abnormal characteristics, wherein the activity abnormal characteristics comprise an activity abnormal area and an activity abnormal merchant; and generating terminal activity alarm information according to the activity abnormal characteristics, and sending the terminal activity alarm information to the electronic commerce platform corresponding to the activity identifier, wherein the terminal activity alarm information can comprise a suggested coping scheme. In one example, the abnormal user rate = abnormal user number/total user number corresponding to the activity identifier may further present the terminal activity alarm information to the host by means of a short message platform or an outbound call system (if the robot flow automation system 105 acquires the contact information of the host from the e-commerce platform). And if the terminal activity alarm information is sent to the mailbox platform, the terminal activity alarm information is displayed to the host through the mailbox platform in a mail mode.

And (3) an activity report generation phase:

robotic process automation system 105: and is also used for, in the abnormal transaction data processing stage: in the customer appeal stage and the activity termination detecting stage, aiming at one user or a plurality of users (corresponding to the same activity or a plurality of users corresponding to the same host), respectively processing stages according to abnormal transaction data: and the customer complaint stage and whether the processing information related in the processing process of the activity detection stage is ended or not generate corresponding activity reports according to respective report templates and send the corresponding activity reports to the host. The processing information includes: transaction time, user handling conditions, transaction characteristics, transaction related areas, merchants and other information of abnormal transaction data during the activity.

If yes, in the stage of detecting whether the activity is ended, aiming at any activity mark, obtaining transaction data of each user under the activity mark; analyzing the transaction characteristics of the transaction data of each user to generate an activity report, wherein the activity report comprises user abnormal rate, user doubtful rate, transaction characteristic distribution and abnormal user concentrated area, and the transaction characteristics comprise: user transaction time, transaction behavior characteristics, transaction occurrence areas and transaction merchant information; and sending the activity report to an electronic commerce platform corresponding to the activity identifier.

And (3) a resource dynamic configuration stage:

robotic process automation system 105: and is further configured to automatically trigger a capacity expansion request or a capacity reduction request when receiving a capacity expansion request or a capacity reduction request of a management client (a client that may play a role in management among the clients 108, which may correspond to the client in fig. 3), or automatically trigger a capacity expansion request when determining that the current active user amount is large and exceeds a first set threshold, or automatically trigger a capacity reduction request when determining that the current active user amount is small and is lower than a second set threshold. The robot flow automation system 105 sends a capacity expansion request or a capacity reduction request to the virtual machine management system, so that the virtual machine management system may perform capacity expansion according to the capacity expansion request or perform capacity reduction on the server cluster of the robot flow automation system 105 shown in fig. 3 according to the capacity reduction request. The capacity expansion request and the capacity reduction request may include a capacity expansion degree and a capacity reduction degree, respectively, and the capacity expansion degree and the capacity reduction degree may be determined according to related information, such as resources, remaining resources, and the number of current active users, of the current robot process automation system 105 in use.

A configuration stage:

robotic process automation system 105: and is also used to receive configuration information from the management client and to change the various configurations in the robotic process automation system 105. Or receiving the edit of the management client to the code or the process of the independent sub-process module in the robot process automation system 105, and correspondingly updating the code or the process to the independent sub-process module. The business personnel can implement the process creation or update of the fully automatic process flow of the robotic process automation system 105, as well as the creation and update of the unique business rules for the processing of the anomalous transaction data (which in one example can be the creation and update of the unique business rules for the processing of the cattle transaction data) through page flow configuration and rule configuration.

The management client in each client 108 may set the relevant parameters in the robot flow automation system 105, and may also perform operations such as code optimization and flow optimization on the corresponding independent sub-flow modules in the robot flow automation system 105. User information, account information, risk level, transaction characteristics, activity report, abnormal user handling report (the robot flow automation system 105 may generate an abnormal user handling report for each abnormal transaction data or processing procedure of the user, and the abnormal user handling report may include user basic information, transaction time, transaction area, processing mode (for example, removing the user from the abnormal user list or adding the user to the abnormal user list), and the like, which are used for querying abnormal users in the robot flow automation system 105, may also be obtained.

Based on the system architecture of each service system, the embodiment of the present application further provides a robot process automation system, as shown in fig. 4, including: a rule command library and each independent sub-flow module; any one of the independent sub-process modules is used for receiving abnormal transaction data sent by an abnormal transaction detection system, matching an analysis rule corresponding to the abnormal transaction data through the rule command library, analyzing the abnormal transaction data according to the analysis rule, and determining a command group of the abnormal transaction data, wherein the abnormal transaction data comprises a user account and an activity identifier; any one of the independent sub-process modules is used for determining an electronic commerce platform to which the abnormal transaction data belongs according to the activity identifier when receiving the command in the command group, and acquiring a history related record corresponding to the user account from the electronic commerce platform; determining the risk level of the user account according to the history relevant record; and processing the abnormal transaction data according to the risk level. In the system, the robot flow automation system comprises a rule command library and each independent sub-flow module. After the robot process automation system receives the abnormal transaction data, a command group can be obtained according to the analysis of the rule command library, corresponding independent sub-process modules are sequentially called through the commands in the command group and the execution sequence of the commands, the risk grade judgment of the user account of the abnormal transaction data is completed, and the corresponding processing is further carried out. Therefore, the system can automatically judge the abnormality of the user account, and divide and correspondingly process the risk caused by the abnormal degree of the user. Compared with the prior art that whether the suspicious user is the abnormal user or not is judged based on manual operation, the efficiency and the accuracy of abnormal transaction data processing are improved, and the processing cost is reduced. In addition, because the sub-process modules are independent from each other, and the plurality of independent sub-process modules are called through the command group in the rule command library to respectively complete corresponding processing, the corresponding completion of business process processing is realized. The method is convenient for the change processing of the subsequent system and improves the simplicity of change.

Based on the system architecture of the robot flow automation system, the embodiment of the application further provides a robot flow automation system, wherein the first independent sub-flow module is configured to receive a first command in the command group, determine an electronic commerce platform to which the abnormal transaction data belongs according to the activity identifier, and acquire a history related record corresponding to the user account from the electronic commerce platform; the second independent sub-process module is used for receiving a second command in the command group and determining the risk level of the user account according to the history related record; and the third independent sub-process module is used for receiving a third command in the command group and processing the abnormal transaction data according to the risk level. Correspondingly, each processing step in the abnormal transaction data processing stage, the customer complaint stage and the activity detection stage of whether to terminate may be completed by one independent sub-process module or by a plurality of independent sub-process modules, which may be set as required and is not particularly limited.

Based on the system architecture of the robot flow automation system, the embodiment of the application also provides a robot flow automation system, as shown in fig. 5, the robot flow automation system further includes a visual configuration module;

the visual configuration module is further configured to change, based on a fourth command in the command group, an analysis rule and a command group in the rule command library according to the configuration information of the configuration request, and/or change related configurations in each independent sub-process module. That is to say, the robot process automation system can receive the configuration information sent by the client, configure the configuration parameters or codes in the robot process automation system according to the configuration information, and simply and quickly complete the parameter change or the independent sub-process module change in the robot process automation system.

Based on the system architecture of the robot flow automation system, the embodiment of the application further provides a robot flow automation system, and any one of the independent sub-flow modules may be a functional unit for implementing data processing, and the functional unit may include data retrieval, data migration, data entry, data analysis, and the like. The functional unit may be a functional unit of the process engine, and the functional unit may include interface call, sub-process configuration, manual process flow allocation, command library, etc. externally connected to each system. Which may be a functional element of a rules engine that may include a rules calculation library, a command component library, key data tag management, rule configuration, and a rules library. Functional elements of artificial intelligence may be used that may include TTS speech transcription functionality, ASR recognition functionality, image review and analysis, a reply database, OCR recognition functionality, and the like. May be a functional module of reporting the run, which may include report management, abnormal user or abnormal transaction trend analysis, reporting the run task, etc. That is to say, the independent sub-process module may be different process modules encapsulated according to the service attribute or the service function, and the visual configuration module may implement a front-end page corresponding to the client, and implement visual configuration in a dragging and pulling manner. The packaging of the particular independent sub-flow modules is not limited herein.

In addition, the robot process automation system 105 may also summarize and judge various abnormal transaction data transmitted in the abnormal transaction detection system 101 for a long time based on technologies such as machine learning and deep learning, and summarize transaction characteristics that need to be handled or do not need to be handled. In this way, the transaction characteristics are sent to the abnormal transaction detection system 101, so as to optimize and perfect the processing model of the abnormal transaction detection system 101.

Based on the above system architectures, an embodiment of the present application provides a transaction data processing method, which is applicable to a robot process automation system, and as shown in fig. 6, the method includes:

601, receiving abnormal transaction data sent by an abnormal transaction detection system, wherein the abnormal transaction data comprises a user account and an activity identifier;

here, the abnormal transaction detection system is configured to detect each transaction data in the transaction processing process according to the user basic information, the transaction characteristics, and other related information of the abnormal user, and determine the abnormal transaction data. The abnormal transaction detection system can obtain the user basic information, transaction characteristics and other related information of the abnormal user from the abnormal list management system. Or some rule information for detecting abnormal transaction data may be maintained by itself, and the manner of detecting abnormal transaction data by the abnormal transaction detection system is not particularly limited herein.

Step 602, determining an electronic commerce platform to which the abnormal transaction data belongs according to the activity identifier, and acquiring a history related record corresponding to the user account from the electronic commerce platform;

here, the campaign identifier may be a campaign identifier of a marketing benefit campaign, or a sales campaign identifier of a special product, and the like, and the campaign identifier is not limited in detail here. For example, a home appliance in a home appliance store on-line is fully deactivated. As another example, a certain automobile official may limit the sales activities of automobiles, and so on.

Step 603, determining the risk level of the user account according to the history relevant record;

here, the history-related records may include transaction information, user information, promissory notes, etc. of the user, and in a special case, may also include a risk level set by the event host of the e-commerce platform for the user.

And step 604, processing the abnormal transaction data according to the risk level.

Based on the above method flow, an embodiment of the present application provides a transaction data processing method, before determining the risk level of the user account according to the history relevant record in step 604, the method further includes: acquiring risk related information corresponding to the user account from a big data platform; determining a risk level of the user account according to the history relevant record, including: and judging the risk level of the user account according to the abnormal transaction data, the history relevant records and the risk relevant information. That is to say, the robot process automation system may further obtain risk related information corresponding to the user account from the big data platform, so as to determine the risk level of the user account according to the abnormal transaction data, the history related records, and the risk related information. In this way, the more comprehensive the data is, the more accurate the result of the risk level determination is. The risk related information may include: if the user account in the abnormal transaction data corresponds to a merchant, the risk related information may further include a merchant number, a POS machine number, basic information of the merchant, judicial and collaborative public opinion management, and the like. The information specifically included in the risk-related information is not limited herein.

Based on the above method flow, an embodiment of the present application provides a transaction data processing method, where in step 604, in processing the abnormal transaction data according to the risk level, if the risk level is a low risk level, the method includes: determining speech emotion elements according to the abnormal transaction data; and generating warning information according to the abnormal transaction data and the voice emotion element, and sending the warning information to a user corresponding to the user account through a short message platform or an outbound system, wherein the voice emotion element is used for expressing warning intensity in the warning information. That is, the speech emotion element of the abnormal transaction data can be determined according to the abnormal transaction data, the speech emotion element represents the warning intensity of the warning information, and the speech emotion element of different warning intensities can correspond to different or different combinations of related information such as transaction time, transaction amount and the like in the abnormal transaction data.

Based on the above method flow, an embodiment of the present application provides a transaction data processing method, where in step 604, in processing the abnormal transaction data according to the risk level, if the risk level is a medium risk level, the method includes: generating an interception instruction according to the abnormal transaction data, and sending the interception instruction to a transfer clearing system; extracting user basic information from the abnormal transaction data, the history related records and the risk related information; and sending the user basic information to an abnormal list management system, wherein the abnormal list management system is used for maintaining an abnormal user list, and the abnormal user list is used as a basis for detecting abnormal transaction data by the abnormal transaction detection system. That is, if the risk level of the abnormal transaction data is a medium risk level, the transaction processing flow of the abnormal transaction data is intercepted, so that the user of the abnormal transaction data cannot participate in the activity, and the user basic information (which may also include transaction data) corresponding to the abnormal transaction data is maintained in the abnormal user list, thereby facilitating the subsequent abnormal transaction detection system to detect the abnormal transaction data.

Based on the above method flow, an embodiment of the present application provides a transaction data processing method, where in step 604, in processing the abnormal transaction data according to the risk level, if the risk level is a high risk level, the method includes: generating an interception instruction according to the abnormal transaction data, and sending the interception instruction to a transfer clearing system; extracting user basic information from the abnormal transaction data, history related records and the risk related information; and sending the user basic information to an abnormal list management system, and degrading the user reputation corresponding to the user basic information. That is, if the risk level of the anomalous transaction data is a high risk level, the user reputation may also be degraded. Therefore, other corresponding services performed according to the user credit can be reasonably developed.

The embodiment of the present application further provides a method for processing a user complaint, further including: receiving complaint information of a user, and analyzing the complaint information to generate response information; sending the response information to the user, wherein the response information is used for indicating the user to upload evidence information; receiving the evidence information, analyzing the evidence information, judging whether the evidence information accords with a preset matching condition, if so, generating an abnormal removing instruction and sending the abnormal removing instruction to an abnormal list management system; and generating an exception-removing processing result and sending the exception-removing processing result to a user. In an example, the robot flow automation system may include a response database/reply database, and may communicate with a user on a text interaction platform (such as the above-mentioned short message platform and the above-mentioned customer service platform) or a voice interaction platform (such as the above-mentioned outbound system and the above-mentioned customer service platform) through an OCR technology, an ASR voice-to-text technology, a TTS technology, and the like, and the robot flow automation system may further generate a reason that the user is on an abnormal user list in response to an inquiry of the user in a communication process, where the reason may be obtained from user basic information, transaction characteristics, evidence information, and the like of the abnormal user in the abnormal list management system, or may be generated from related information stored by the robot flow automation system itself, which is not limited specifically here. And after the robot process automation system acquires the evidence information uploaded by the user, updating the evidence information to an abnormal user list of the abnormal user. If the user is determined to be removed from the abnormal user list in the complaint processing flow, the related information of the user in the abnormal user list and the evidence information uploaded by the user can be maintained in the abnormal filing list.

The embodiment of the application further provides a method for terminating activities, which further includes: counting abnormal user rate under the activity identification according to the activity identification, and if the abnormal user rate exceeds a set threshold, analyzing abnormal transaction data of different users to obtain activity abnormal characteristics, wherein the activity abnormal characteristics comprise an activity abnormal area and an activity abnormal merchant; and generating final activity alarm information according to the activity abnormal characteristics, and sending the final activity alarm information to the electronic commerce platform, wherein the final activity alarm information comprises a suggested coping scheme. That is to say, the robot flow automation system may monitor the abnormal user rate of each activity identified by the activity, and if the abnormal user rate of the activity exceeds a set threshold, analyze abnormal transaction data of each abnormal user to obtain an activity abnormal characteristic, and analyze and generate a corresponding proposal response scheme to obtain the terminal activity alarm information and send the terminal activity alarm information to the electronic commerce platform, so that the activity host may further know the activity hosting status, and whether to adopt the proposal response scheme, etc.

The embodiment of the application further provides a method for terminating activities, which further includes: aiming at the activity identification, acquiring transaction data of each user under the activity identification; analyzing the transaction characteristics of the transaction data of each user to generate an activity report, wherein the activity report comprises user abnormal rate, user doubtful rate, transaction characteristic distribution and abnormal user concentrated area, and the transaction characteristics comprise: user transaction time, transaction behavior characteristics, transaction occurrence areas and transaction merchant information; and sending the activity report to an electronic commerce platform corresponding to the activity identifier. In an example, the activity report may be for each user transaction data under the activity identifier, may also be for the abnormal user's processing procedure, and may also be for the abnormal user's processing procedure only for the abnormal user with a high/medium risk level, where the robot process automation system generates the activity report according to those processes specifically and without limitation.

The embodiment of the application further provides a method for dynamically adjusting resources of a robot process automation system, which further comprises the following steps: determining that the number of the current active users exceeds a first set threshold value, generating a capacity expansion request and sending the capacity expansion request to the virtual machine management system, or determining that the number of the current active users is lower than a second set threshold value, generating a capacity reduction request and sending the capacity reduction request to the virtual machine management system. That is to say, the robot flow automation system may enable the virtual machine management system to perform capacity expansion or capacity reduction on the server cluster corresponding to the robot flow automation system according to the number of the current active users.

In addition, it should be noted that the data acquisition, storage, use, processing, and the like in any of the above system architectures and method flows all conform to relevant regulations of national laws and regulations.

Based on the same concept, an embodiment of the present application provides a transaction data processing apparatus, which is suitable for a robot process automation system, as shown in fig. 7, and includes:

the receiving and sending module 701 is configured to receive abnormal transaction data sent by an abnormal transaction detection system, where the abnormal transaction data includes a user account and an activity identifier;

a processing module 702, configured to determine, according to the activity identifier, an electronic commerce platform to which the abnormal transaction data belongs, and obtain, from the electronic commerce platform, a history related record corresponding to the user account;

the processing module 702 is further configured to determine a risk level of the user account according to the history related record;

the processing module 702 is further configured to process the abnormal transaction data according to the risk level.

Optionally, the processing module 702 is further configured to obtain risk related information corresponding to the user account from a big data platform; the processing module 702 is specifically configured to determine a risk level of the user account according to the abnormal transaction data, the history related record, and the risk related information.

Optionally, the risk level is a low risk level, and the processing module 702 is specifically configured to determine a speech emotion element according to the abnormal transaction data; and generating warning information according to the abnormal transaction data and the voice emotion elements, sending the warning information to a user corresponding to the user account through a short message platform or an outbound system, wherein the voice emotion elements are used for expressing warning intensity in the warning information.

Optionally, the risk level is an intermediate risk level, and the processing module 702 is specifically configured to generate an interception instruction according to the abnormal transaction data, and send the interception instruction to a transfer clearing system; extracting user basic information from the abnormal transaction data, history related records and the risk related information; and sending the user basic information to an abnormal list management system, wherein the abnormal list management system is used for maintaining an abnormal user list, and the abnormal user list is used as a basis for detecting abnormal transaction data by the abnormal transaction detection system.

Optionally, the risk level is a high risk level, and the processing module 702 is specifically configured to generate an interception instruction according to the abnormal transaction data, and send the interception instruction to a transfer clearing system; extracting user basic information from the abnormal transaction data, history related records and the risk related information;

Optionally, the transceiver module 701 is further configured to receive complaint information of a user, and analyze the complaint information to generate response information; the processing module 702 is further configured to send the response information to the user through the transceiver module 701, where the response information is used to instruct the user to upload evidence information;

the transceiver module 701 is further configured to receive the evidence information, and the processing module 702 is further configured to analyze the evidence information, determine whether the evidence information meets a preset matching condition, and if so, generate an exception removing instruction to be sent to an exception list management system through the transceiver module 701;

the processing module 702 is further configured to generate an exception release processing result, and send the exception release processing result to a user through the transceiver module 701.

Optionally, the processing module 702 is further configured to, for an activity identifier, count an abnormal user rate under the activity identifier, and if the abnormal user rate exceeds a set threshold, analyze abnormal transaction data of each abnormal user to obtain an activity abnormal feature, where the activity abnormal feature includes an activity abnormal area and an activity abnormal merchant; and generating terminal activity alarm information according to the activity abnormal characteristics, and sending the terminal activity alarm information to the e-commerce platform through the transceiver module 701, wherein the terminal activity alarm information comprises a proposal coping scheme.

Optionally, the processing module 702 is further configured to, for the activity identifier, obtain transaction data of each user under the activity identifier; analyzing the transaction characteristics of the transaction data of each user to generate an activity report, wherein the activity report comprises user abnormal rate, user doubtful rate, transaction characteristic distribution and abnormal user concentrated area, and the transaction characteristics comprise: user transaction time, transaction behavior characteristics, transaction occurrence areas and transaction merchant information; and sending the activity report to the e-commerce platform corresponding to the activity identifier through the transceiver module 701.

Optionally, the processing module 702 is further configured to determine that the number of current active users exceeds a first set threshold, generate an expansion request and send the expansion request to the virtual machine management system, or determine that the number of current active users is lower than a second set threshold, generate a contraction request and send the contraction request to the virtual machine management system through the transceiver module 701.

As will be appreciated by one skilled in the art, 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 so forth) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

Claims

1. A transaction data processing method, adapted for use in a robotic process automation system, comprising:

determining the risk level of the user account according to the history relevant record;

and processing the abnormal transaction data according to the risk level.

2. The method of claim 1, wherein prior to determining the risk level of the user account from the historical correlation record, further comprising:

acquiring risk related information corresponding to the user account from a big data platform;

determining the risk level of the user account according to the history relevant record, wherein the risk level comprises the following steps:

3. The method of claim 2, wherein the risk level is a low risk level, and processing the anomalous transaction data according to the risk level comprises:

determining speech emotion elements according to the abnormal transaction data;

and generating warning information according to the abnormal transaction data and the voice emotion elements, sending the warning information to a user corresponding to the user account through a short message platform or an outbound system, wherein the voice emotion elements are used for expressing warning intensity in the warning information.

4. The method of claim 2, wherein the risk level is a medium risk level, and processing the anomalous transaction data according to the risk level comprises:

extracting user basic information from the abnormal transaction data, the history related records and the risk related information;

5. The method of claim 1, wherein the risk level is a high risk level, and processing the anomalous transaction data according to the risk level comprises:

6. The method of claim 1, further comprising:

and generating an exception removal processing result and sending the exception removal processing result to a user.

7. The method of claim 1, further comprising:

and generating final activity alarm information according to the activity abnormal characteristics, and sending the final activity alarm information to the electronic commerce platform, wherein the final activity alarm information comprises a suggested coping scheme.

8. The method of any one of claims 1-7, further comprising:

aiming at the activity identification, acquiring transaction data of each user under the activity identification;

analyzing the transaction characteristics of the transaction data of each user to generate an activity report, wherein the activity report comprises user abnormal rate, user doubtful rate, transaction characteristic distribution and abnormal user concentrated area, and the transaction characteristics comprise: user transaction time, transaction behavior characteristics, transaction occurrence areas and transaction merchant information;

and sending the activity report to an electronic commerce platform corresponding to the activity identifier.

9. The method of claim 1, further comprising:

determining that the number of current active users exceeds a first set threshold value, generating a capacity expansion request and sending the capacity expansion request to a virtual machine management system, or determining that the number of current active users is lower than a second set threshold value, generating a capacity reduction request and sending the capacity reduction request to the virtual machine management system.

10. A robot process automation system is characterized in that the robot process automation system comprises a rule command library and independent sub-process modules;

any one of the independent sub-process modules is used for determining an electronic commerce platform to which the abnormal transaction data belongs according to the activity identifier when receiving the command in the command group, and acquiring a history related record corresponding to the user account from the electronic commerce platform; determining the risk level of the user account according to the history relevant records; and processing the abnormal transaction data according to the risk level.

11. The system of claim 10,

the first independent sub-process module is used for receiving a first command in the command group, determining an electronic commerce platform to which the abnormal transaction data belongs according to the activity identifier, and acquiring a history related record corresponding to the user account from the electronic commerce platform;

the second independent sub-process module is used for receiving a second command in the command group and determining the risk level of the user account according to the history related record;

12. The system of claim 10, further comprising a visualization configuration module in the robotic process automation system;

13. A transaction data processing apparatus adapted for use in a robotic process automation system, comprising:

14. A computing device, comprising:

a memory for storing program instructions;

a processor for invoking program instructions stored in said memory for executing the method of any of claims 1 to 9 in accordance with the obtained program.

15. A computer readable non-transitory storage medium comprising computer readable instructions which, when read and executed by a computer, cause the computer to perform the method of any one of claims 1 to 9.