Abnormal business processing method, device, computer equipment and storage medium

Abstract

The present application relates to an abnormal business processing method, device, computer equipment and storage medium. The abnormal business processing method of the present application can be applied to the field of artificial intelligence or other fields. The method includes: obtaining target business records marked as abnormal status under the target type business; obtaining risk screening rules corresponding to the target type business; the risk screening rules are determined based on the business characteristics of historical non-risk business anomalies; based on the risk screening rules, the target business records are matched, and according to the matching results, it is determined whether to adjust the abnormal status of the target business records to a normal status. By using risk screening rules to match the target business records that are identified to be at risk, the business records of non-risk businesses can be adjusted from abnormal status to normal status in a timely manner, so as to achieve the normal circulation of business records, avoid their retention waiting for risk processing, and effectively improve business processing efficiency.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and in particular to an abnormal business processing method, apparatus, computer equipment, storage medium and computer program product. Background Art

[0002] With the development of computer technology and the improvement of financial markets, financial market operations continue to grow and become increasingly complex.

[0003] In the related technology, risks in financial business can be identified, and corresponding risk warning measures can be used to deal with the identified business in a timely manner to prevent business risks. However, due to the comprehensiveness of risk warning, some non-risk businesses are mistakenly identified as risky businesses, which reduces the efficiency of business processing. Summary of the invention

[0004] Based on this, it is necessary to provide an abnormal business processing method, device, computer equipment, computer-readable storage medium and computer program product that can improve business processing efficiency in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for handling abnormal services. The method comprises:

[0006] Obtaining a target business record marked as abnormal under a target type of business; the target business record is a business record obtained by matching business records under the target type of business based on a preset risk warning rule and satisfying the risk warning rule;

[0007] Obtaining risk screening rules corresponding to the target type of business; the risk screening rules are determined based on business characteristics of historical non-risk business anomalies;

[0008] Based on the risk screening rules, the target business record is matched, and according to the matching result, it is determined whether to adjust the abnormal state of the target business record to a normal state.

[0009] In one embodiment, matching the target business record based on the risk screening rule includes:

[0010] Acquire key data items corresponding to the target type business; the key data items are determined based on business features corresponding to the target type business and / or data structures corresponding to business records under the target type business;

[0011] Based on a preset automation script file, obtaining target data content corresponding to the key data item from the business data of the target business record;

[0012] Based on the risk screening rules, the target data content is matched to obtain a matching result of the target business record.

[0013] In one embodiment, the key data items include data items associated with the credibility of the target type of business, and the target data content is matched based on the risk screening rule to obtain the matching result of the target business record, including:

[0014] In the case where the target data content is a preset data content, it is determined that the target business record matches the risk screening rule; the preset data content indicates that the credibility reaches a preset credibility condition.

[0015] In one embodiment, the key data item includes a data item characterizing an association relationship between the target business record and other business records, and the target data content is matched based on the risk screening rule to obtain a matching result of the target business record, including:

[0016] Based on the target data content, acquiring an associated business record associated with the target business record;

[0017] If the associated business record is a business record in a normal state, it is determined that the target business record matches the risk screening rule.

[0018] In one embodiment, acquiring, based on the target data content, an associated business record associated with the target business record includes:

[0019] Based on the business identifier corresponding to the business, a historical business record corresponding to the business is obtained as an associated business record of the target business record; the business includes multiple business records, and the historical business record is a business record that occurs before the target business record.

[0020] In one embodiment, the method further comprises:

[0021] Receive adjustment information; the adjustment information is determined based on the review process corresponding to the historical target business records within a preset time;

[0022] Based on the adjustment information, the risk screening rules and the automation script file are adjusted.

[0023] In one embodiment, the risk screening rule is a plurality of risk screening rules, and determining whether to adjust the abnormal state of the target business record to a normal state according to the matching result includes:

[0024] If the target business record matches the current risk screening rule, adjusting the abnormal state of the target business record to a normal state;

[0025] If the target business record does not match any of the multiple risk screening rules, the abnormal state of the target business record is maintained.

[0026] In a second aspect, the present application also provides an abnormal service processing device. The device comprises:

[0027] A target business record acquisition module is used to acquire target business records marked as abnormal under target type business; the target business records are business records that meet the risk warning rules and are obtained by matching business records under the target type business based on preset risk warning rules;

[0028] A screening rule acquisition module is used to obtain risk screening rules corresponding to the target type of business; the risk screening rules are determined based on the business characteristics of historical non-risk business anomalies;

[0029] A matching module is used to match the target business record based on the risk screening rule, and determine whether to adjust the abnormal state of the target business record to a normal state according to the matching result.

[0030] In a third aspect, the present application further provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any of the above methods are implemented.

[0031] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0032] In a fifth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of any of the methods described above are implemented.

[0033] The above-mentioned abnormal business processing method, device, computer equipment, storage medium and computer program product can obtain the target business record marked as abnormal state under the target type business, and the target business record can be a business record obtained by matching the business record under the target type business based on the risk warning rule, and the risk screening rule corresponding to the target type business determined based on the business characteristics of the historical non-risk business abnormalities can be obtained, and the target business record can be matched based on the risk screening rule, and then it can be determined whether to adjust the abnormal state of the target business record to a normal state according to the matching result. In this scheme, by matching the target business record with risks identified by using the risk screening rule, the business record of the non-risk business can be adjusted from the abnormal state to the normal state in time, so as to realize the normal circulation of the business record, avoid its retention waiting for risk processing, and effectively improve the business processing efficiency, and the terminal automatically performs risk screening through the risk screening rule, which improves the processing quality and processing efficiency of business risks, and can achieve consistent and efficient identification of risk warning results. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A schematic diagram of a process of an abnormal service processing method in an embodiment;

[0035] Figure 2 A flowchart of another abnormal service processing method in one embodiment;

[0036] Figure 3 A schematic diagram of an abnormal service processing interface in an embodiment;

[0037] Figure 4 is a structural block diagram of an abnormal service processing device in one embodiment;

[0038] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0039] 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.

[0040] In one embodiment, Figure 1 As shown, a method for processing abnormal business is provided, which can be applied to the processing of abnormal business in the field of artificial intelligence, and can also be used in any field except the field of artificial intelligence. This application does not limit the application field of the method for processing abnormal business.

[0041] This embodiment uses the method applied to a terminal as an example. It is understandable that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Among them, the terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc.; the server can be implemented as an independent server or a server cluster consisting of multiple servers.

[0042] In this embodiment, the method includes the following steps:

[0043] Step 101: Obtain target business records marked as abnormal under target type business.

[0044] The target business record is obtained by matching the business records under the target type business based on the preset risk warning rules, and is a business record that meets the risk warning rules.

[0045] Specifically, risk warning rules can be rules for identifying various risk points in the business processing flow. In one example, corresponding risk warning rules can be generated for each information point and operation point that has risks in the entire business processing flow of a specified type of business, and then the risk warning rules can be used to identify all anomalies that may exist or appear in the business processing process as comprehensively as possible. Risk warning rules can be a rigorous and complete identification rule, and the content of the rules may not take into account the characteristics of individual businesses or individual business processing flows, but can be applied to risk warnings for any business under the same type of business.

[0046] The target type business may be a preset type of financial business to be screened for business risks. For example, the target type business may be any of the following types of financial business: foreign exchange trading business, foreign exchange lending business, foreign currency funds lending business, precious metal business, business corresponding to accounts with a zero balance at the end of the day, internal account overdraft business, cross-border RMB collection business, and transaction cancellation business.

[0047] In practical applications, due to the complexity and variability of financial services, multiple business records under the target type of business can be matched through risk warning rules, and business records that meet the risk warning rules can be marked as target business records in abnormal status.

[0048] When a business record with risk is identified through risk warning rules, it can be manually identified by staff and manually marked as abnormal. Of course, a risk warning model with risk warning rules can also be used.

[0049] Specifically, corresponding risk warning models can be configured for different target types of businesses, and multiple risk warning models can jointly form a risk monitoring system. For example, the risk warning models in the risk monitoring system may include at least two of the following models: foreign exchange trading business confirmation matching warning model, foreign exchange lending transaction confirmation matching warning model, foreign currency funds lending business monitoring model, precious metal business confirmation matching warning model, end-of-day balance of 0 internal account monitoring model, internal account overdraft monitoring model, cross-border RMB collection monitoring model, transaction cancellation business monitoring model. Among them, the risk monitoring system can be based on information data analysis and use the risk warning model as a risk identification engine to achieve risk warning monitoring, quality control management, transaction data matching, OCR (Optical Character Recognition) image recognition, risk event processing, driving factor analysis, and information statistical analysis.

[0050] When the terminal obtains a new business record, it can be input into the risk monitoring system and matched with the risk warning model corresponding to the business type of the input business record, and marked as abnormal when the business record meets the risk warning rules.

[0051] Step 102: Obtain risk screening rules corresponding to the target type of business.

[0052] As an example, the risk screening rules can be determined based on the business characteristics of historical non-risk business anomalies, where the business characteristics can be the characteristics of the business process and / or the business data in the business record. The risk screening rules can be used to filter out business records that have abnormal business characteristics in the target business record but are evaluated as normal.

[0053] In actual applications, when the business characteristics corresponding to a business are abnormal, they can be screened out through risk warning rules and risk warnings can be issued in a timely manner. However, although the business characteristics of some businesses are abnormal, that is, the business has abnormal business characteristics, such as the business records include business data that indicate that the business may be abnormal or the business processing flow is different from the normal business processing flow, after further risk assessment, the business can still be determined to be a non-risk business.

[0054] Risk screening rules can be partial exception rules for risky businesses within a preset time, which do not impact or change the risk monitoring model and risk warning rules. Risk screening rules are more temporary and specific than risk warning rules, and may change with changes in the business processing procedures of relevant institutions and the business specifications of the industry. When they change, the risk screening rules can be fine-tuned to adapt to the new trend of change, but it does not affect the perfection and prudence of the risk warning rules. In specific implementation, risk screening rules can be obtained based on non-risk businesses that have been manually reviewed and confirmed. For example, for risky businesses that are screened through risk warning rules and confirmed as non-risky businesses after manual review, the review process can be learned through machine learning to obtain corresponding risk screening rules.

[0055] In this embodiment, after the target business record is obtained, the risk screening rules corresponding to the target type of business can be obtained.

[0056] Step 103, based on the risk screening rules, the target business record is matched, and according to the matching result, it is determined whether to adjust the abnormal state of the target business record to a normal state.

[0057] After obtaining the risk screening rules, the target business records can be matched based on the risk screening rules to determine whether the target business records match the risk screening rules, and further determine whether there are non-risk businesses that match the risk screening rules among the business records currently assessed as having risks.

[0058] After matching the target business record, the corresponding matching result can be obtained, for example, whether the target business record matches or does not match the risk screening rule, and then it can be determined whether to adjust the abnormal state of the target business record to a normal state based on the matching result.

[0059] Specifically, when the target business record matches the risk screening rules, it can be determined that the business corresponding to the target business record currently identified as having risks is actually a non-risk business, and the abnormal state corresponding to the target business record can be adjusted to a normal state. After being adjusted to a normal state, the target business record can be pushed into the subsequent processing flow. When the target business record does not match the risk screening rules, it can be determined that the business corresponding to the target business record is not a non-risk business, and the abnormal state can be left unchanged.

[0060] In this embodiment, the target business record marked as abnormal state under the target type business can be obtained. The target business record can be a business record obtained by matching the business record under the target type business based on the risk warning rule, and the risk screening rule determined based on the business characteristics of the historical non-risk business abnormalities corresponding to the target type business can be obtained, and the target business record can be matched based on the risk screening rule, and then it can be determined whether to adjust the abnormal state of the target business record to a normal state according to the matching result. In this scheme, by matching the target business record with risks identified by using the risk screening rule, the business record of the non-risk business can be adjusted from the abnormal state to the normal state in time, so as to realize the normal circulation of the business record, avoid its retention waiting for risk processing, and effectively improve the business processing efficiency. In addition, the terminal automatically conducts risk screening through the risk screening rule, improves the processing quality and processing efficiency of business risks, and can achieve consistent and efficient identification of risk warning results.

[0061] Since different types of businesses use different data formats, the data formats corresponding to the business records used by the risk warning rules when performing risk warnings are also different, such as the data items covered in the business data, the arrangement positions of the data items (such as the fields of the message) or the specific business data. In one embodiment, Figure 2 As shown, matching the target business record based on the risk screening rule may include the following steps:

[0062] Step 201: Acquire key data items corresponding to the target type of business.

[0063] Among them, the key data items can be determined based on the business characteristics corresponding to the target type business and / or the data structure corresponding to the business records under the target type business.

[0064] Specifically, different types of businesses may have different business characteristics, such as differences in business processing procedures or differences in business data recorded during business processing. Therefore, matching key data items may be determined based on the business characteristics.

[0065] The data structure may be the arrangement of data items in a business record. The business data corresponding to different types of business may have different arrangement of data items. For example, data item A may be arranged in the mth column in the business data corresponding to type A business, and may be arranged in the nth column in the business data corresponding to type B business. In one example, the key data item may not only be a specified data item in a business record, but also a specified data item appearing at a specified position in the business record, such as the data item "CN" appearing at the specified position "BIC 5-6 digits of the transmitting line".

[0066] By determining key data items based on the business characteristics corresponding to the target type business or the data structure corresponding to the business records under the target type business, the current risk screening method can be flexibly set in combination with the differences in the data source structures of different risk warning rules.

[0067] In actual applications, corresponding key data items may be set in advance for different types of businesses, and then after obtaining a target business record, the corresponding key data items may be determined according to the target business type corresponding to the target business record.

[0068] Step 202 , based on a preset automation script file, obtain target data content corresponding to the key data item from the business data of the target business record.

[0069] As an example, the automation script file may be a Robotic Process Automation (RPA) script file. Through the automation script file, automatic login and click may be achieved.

[0070] In the relevant technology, business handlers (such as supervisory users of the risk control system and business handlers of the clearing system) need to log in to the corresponding page according to the case category for different risk warning models, check whether there are target business records every day, and check the details of each target business record. They identify the risk based on multiple information such as date, currency, amount, stakeholders, message details, etc., judge the risk level, and then execute inquiries and responses, notify specific business management personnel, and other processing.

[0071] In this embodiment, the manual operation process can be intervened by an automated script file while maintaining the stability of the risk warning rules and the business processing process. Specifically, a pre-set automated script file can be obtained, and based on the processing flow configuration in the automated script file, the target data content corresponding to the key data item can be obtained from the business data of the target business record.

[0072] For example, based on the configuration in the automation script file, you can log in to the business operation risk management system to query, and by clicking the following button menu options in sequence, you can query the specified target business records and obtain the target data content corresponding to the key data items: System Menu-Comprehensive Query-Unfinished Supervision Matters-Select the corresponding date range-Enter the detailed records.

[0073] Step 203, based on the risk screening rules, the target data content is matched to obtain a matching result of the target business record.

[0074] When the target data content corresponding to the key data item is obtained, the target data content can be matched based on the risk screening rules to determine the matching result corresponding to the target business record.

[0075] In this embodiment, the key data items corresponding to the target type of business can be obtained. The key data items can be determined based on the business characteristics corresponding to the target type of business or the data structure corresponding to the business records under the target type of business. Then, based on the pre-set automation script file, the target data content corresponding to the key data items can be obtained from the business data of the target business record, and the target data content can be matched based on the risk screening rules to obtain the matching results of the target business record. In this solution, by obtaining the key data items corresponding to the target type of business, the risk screening method can be flexibly adjusted, and non-risk events can be accurately identified for different types of business. At the same time, the target data content corresponding to the key data items can be obtained based on the automation script, and the intervention of automatic screening of non-risk business can be realized without interfering with the normal manual processing flow in the business processing system.

[0076] In one embodiment, the key data items may include data items associated with the credibility of the target type of business. In step 203, the target data content is matched based on the risk screening rules to obtain the matching result of the target business record, which may include:

[0077] When the target data content is the preset data content, it is determined that the target business record matches the risk screening rule.

[0078] As an example, the preset data content may be a representation that the credibility reaches a preset credibility condition.

[0079] In a specific implementation, since the key data items may include data indicating the credibility of the target type of business, it is possible to determine that the target business record matches the risk screening rule when the target data content is a preset data item representing that the credibility reaches a preset credibility condition.

[0080] For example, Figure 3 As shown, for completed transactions under the foreign exchange trading business type, when the 5-6 digits of the BIC of the reporting bank in the target business record are "CN", it can be determined that the target business record is a business that occurred in mainland China, and its credibility is high. Therefore, it can be determined that the target business record matches the risk screening rules and adjusts it from an abnormal state to a normal state. In order to facilitate the subsequent viewing of the processing history corresponding to the target business record, after adjusting to a normal state, risk driving factors and corresponding remarks can also be added to the target business record. For example, for the target business record, the risk driving factor can be marked as "other" and the risk driving factor remark is "post-transaction matching" to provide relevant information for subsequent statistics.

[0081] For the modified transaction, when the data content corresponding to the key data item at the specified position in the target business record is "AMND" (amend, modification), it can be adjusted from the abnormal state to the normal state, and the risk driver factor can be added as "other", and the risk driver factor remark is "modified transaction".

[0082] For a specified type of financial business, if ":17F:Y" appears in the target business record corresponding to the business, it can be adjusted from an abnormal state to a normal state, and the risk driver factor can be added as "other", and the risk driver factor remark can be "confirmation of a specified type of financial transaction".

[0083] In this embodiment, by comparing the data content recorded in the target business record, it is possible to quickly identify whether the target business record is a business record in a normal state, thereby effectively improving the identification speed.

[0084] In one embodiment, the key data items may include data items that characterize the association relationship between the target business record and other business records. In step 203, based on the risk screening rules, the target data content is matched to obtain the matching result of the target business record, including:

[0085] Based on the target data content, an associated business record associated with the target business record is obtained; if the associated business record is a business record in a normal state, it is determined that the target business record matches the risk screening rule.

[0086] In actual applications, it may not be possible to determine whether the business corresponding to the target business record is a non-risk business through the business data in the target business record. In this case, the associated business record associated with the target business record may be obtained based on the target data content.

[0087] After the associated business records are determined, it is possible to determine whether the business corresponding to the target business record has risks based on the status of the associated business records. Specifically, if the associated business records are business records in a normal state, it is possible to determine that the target business records are non-risky businesses, and it is possible to determine that the target business records match the risk screening rules. If the associated business records are business records in an abnormal state, the target business records do not match the risk screening rules.

[0088] In this embodiment, when the target business record does not include a direct indication of whether the business is a non-risk business, it is possible to quickly determine whether it matches the risk screening rule by associating the business record.

[0089] In one embodiment, based on the target data content, obtaining the associated business record associated with the target business record may include:

[0090] Based on the business identifier corresponding to the business, the historical business record corresponding to the business is obtained as the associated business record of the target business record.

[0091] The business includes multiple business records, and the historical business record is a business record that occurs before the target business record.

[0092] In a specific implementation, the data item representing the association relationship between the target business record and other business records may be a business identifier corresponding to the business. After obtaining the business identifier corresponding to the business, the historical business records corresponding to the business may be queried based on the business identifier, and the historical business records may be used as associated business records of the target business record.

[0093] Specifically, a business can correspond to a business record, that is, after completing a business processing flow and generating the corresponding business record, the business can be completed; or, a business can also correspond to multiple business records, for example, the business is completed after circulating multiple different business processing flows and generating business records corresponding to each business processing flow. When the business corresponding to the target business record involves multiple business records, the historical business records that occurred before the target business record can be queried based on the business identifier corresponding to the business. For example, the predecessor message of the target business record can be queried as a historical business record based on the business identifier of the "20 items" record in the target business record.

[0094] In actual applications, after the historical business records are used as associated business records, the key data items corresponding to the historical business records can be obtained, and based on whether the historical data content corresponding to the key data items of the historical business records is the preset data content, it is determined whether the historical business records are business records in a normal state.

[0095] For example, for the target business record that records the business cancellation process, if item 22A in the target business record is "CANC" (cancle, cancel), the business identifier recorded in the key data item "item 21" of the target business record can be obtained, and other target business records with the same business identifier can be queried through the business identifier. For example, it can be queried in other target business records whether the "item 20" record has the same business identifier as the key data item "item 21" of the current target business record. If so, it can be determined as a historical business record of the current target business record and used as an associated business record. If item 22A of the associated business record is "NEWT", it means that after the business process corresponding to the associated business record is completed, a new business processing process is created, that is, a business processing process for canceling the business. Therefore, the associated business record can be adjusted from an abnormal state to a normal state, and the processing of the current target business record also complies with the business processing process and is authentic, so it can be adjusted from an abnormal state to a normal state. In addition, the risk driver can be added as "other" and the risk driver remark is "cancel transaction".

[0096] In this embodiment, based on the business identifier corresponding to the business, the historical business records corresponding to the business can be obtained as associated business records of the target business records. When it is impossible to directly identify whether the corresponding business is a non-risk business based on the data content of the target business record, it can be quickly determined based on the associated business records.

[0097] In one embodiment, the data item characterizing the association relationship between the target business record and other business records may also be a business type. Through the business type recorded in the target business record, other business records with the same business type may be determined as associated business records, and when the associated business record is in a normal business state, the authenticity of the target business record may be determined, thereby adjusting the target business record from an abnormal state to a normal state.

[0098] For example, in a target business record, item 22A is "NEWT". A business type query is performed based on the "20 business identifiers" of the target business record, and it is determined that the business type of the target business record is "non-payment". In other business records, there are 300 business records with the same "20 business numbers" and the same business types. These 300 business records can be determined as associated business records. Since item 22A in the associated business records is "AMND", both the target business record and the associated business records can be adjusted to a normal state, and the risk driver factor can be added as "other", and the risk driver factor remark is "modify transaction".

[0099] In one embodiment, the target business record can also be compared with the records that have occurred within the preset time in the past, and the matched non-risk business can be excluded. For example, for an internal account with a balance of 0 at the end of the day, the processing record corresponding to the business record of the previous day can be exported and compared with the target business record of the day. For records with the same account number, account name, and currency, if the risk driving factor of the previous day's record is "confirmed", the abnormal state of the target business record can be adjusted to a normal state.

[0100] In addition, it is also possible to determine whether the target business record matches the risk screening rules based on the registration time and / or the current business status of the business corresponding to the business record. In this way, some reasonable non-risk events in the pending state can be excluded.

[0101] For example, for unprocessed cross-border RMB receipt business, if the data content corresponding to the data item representing the business status in the target business record is "position to be confirmed", the abnormal status of the target business record can be adjusted to the normal status, and the risk driving factor can be added as "other", and the risk driving factor remark can be "position to be confirmed".

[0102] If the data content corresponding to the data item representing the business status in the target business record is "Compliance check failed and pending", the abnormal status of the target business record can be adjusted to the normal status, and the risk driving factor can be added as "Other", and the risk driving factor remark is "Compliance check pending".

[0103] For example, if the data content corresponding to the data item representing the business status in the target business record is "pending remittance / sorting" and the registration time is greater than 17:00, the abnormal status of the target business record can be adjusted to the normal status, and the risk driving factor can be added as "others", and the risk driving factor remark is "exceeding the settlement deadline".

[0104] It should be noted that when matching the target business records based on the risk screening rules, the matching can be performed using each of the above matching methods alone, or multiple matching methods can be combined at the same time as a risk screening rule for matching.

[0105] In one embodiment, the method may further include the following steps:

[0106] Receive adjustment information; based on the adjustment information, adjust risk screening rules and automation script files.

[0107] The adjustment information may be determined based on a review process corresponding to a historical target business record within a preset time, and the historical target business record may be a processed target business record.

[0108] In the specific implementation, since the business characteristics of non-risk business are temporary and special to a certain extent, the staff can determine the changes in the abnormal business characteristics of the current non-risk business based on the review process of the historical target business records within the preset time, and then obtain the corresponding adjustment information based on the changes in the abnormal business characteristics. Of course, it is also possible to regularly learn the review process of the historical target business records at preset time intervals through machine learning and other methods to obtain the corresponding adjustment information.

[0109] Since the audit process of historical target business records has changed, it may involve changes in the audit process, audit content and corresponding risk investigation rules. Therefore, after obtaining the adjustment information, the risk investigation rules and automation scripts can be adjusted based on the adjustment information to obtain updated risk investigation rules and automation scripts. Therefore, when the target business records are subject to risk investigation for the next time, it can be determined whether to adjust the target business records obtained next time from an abnormal state to a normal state based on the updated risk investigation rules and automation scripts.

[0110] In this embodiment, by receiving adjustment information and adjusting the risk screening rules and automation script files based on the adjustment information, it is possible to combine the manual review experience for non-risk businesses within a preset time to timely update the risk screening rules and automation scripts, thereby providing a basis for subsequently accurately eliminating records corresponding to non-risk businesses from suspicious target business records, while not affecting the overall effectiveness of risk monitoring.

[0111] In one embodiment, the risk screening rule is a plurality of risk screening rules. In step 103, according to the matching result, it is determined whether to adjust the abnormal state of the target business record to a normal state, including:

[0112] If the target business record matches the current risk screening rule, the abnormal state of the target business record is adjusted to a normal state; if the target business record does not match any of the multiple risk screening rules, the abnormal state of the target business record is maintained.

[0113] In actual applications, due to the complexity and variability of financial services, multiple risk screening rules can be set in advance and matched with target business records based on the multiple risk screening rules.

[0114] Specifically, the current risk screening rule can be obtained from multiple risk screening rules, and the target business record can be matched with the risk screening rule. If the two match, the target business record can be adjusted from an abnormal state to a normal state, and subsequent risk screening rules will no longer be used for matching.

[0115] If the target business record does not match the current risk screening rule, the next risk screening rule can be obtained as the current risk screening rule for matching. After matching one by one, if the target business record does not match any of the multiple risk screening rules, the abnormal state of the target business record can be maintained and the subsequent risk processing process can be entered.

[0116] In this embodiment, the target business record can be matched with multiple risk screening rules. If it matches the current risk screening rules, the abnormal state can be adjusted to the normal state. When the target business record does not match any risk screening rules, the abnormal state will remain, and non-risk businesses can be quickly eliminated from suspicious events identified based on risk warning rules.

[0117] In one embodiment, parameters corresponding to the query reply can also be added to the automated script, and the parameters can include the sending time and recipient of the query reply, for example, the recipient can be the processing department or person processing the target business record. The terminal can generate query information in a preset format according to the parameters in the automated script and add it to the query content of the query reply.

[0118] For example, the preset format may be "data date + model name + account code + account name + account number + account name + generated + balance + currency (RMB minus the base currency) + pending account + please help confirm the reason". In one example, the query information may be as follows:

[0119] On May 18, the ending balance was 0 for internal account monitoring, 167099 transitional advances to be cleared, 0101054811100402201 Other types of temporary transitional funds to be recovered - GMOTRADEBONDACCTRECABLE generated RMB 160,428,975.34 in outstanding accounts. Please help confirm the reason.

[0120] After the query response book is generated, it can be sent to the corresponding recipient according to the parameters in the automation script, and the relevant personnel can be notified by email.

[0121] In one embodiment, the terminal may count the sent query reply forms at preset time intervals.

[0122] For example, all the inquiries and responses issued within the preset period can be exported and sent to relevant personnel. When doing statistics, the terminal can click the following options in the menu in sequence according to the automated script: "Monitoring Management System - Risk Event Processing - Supervisory Inquiry and Response Retrieval", and set the data date to "Query this Week", and the status of the query and response book to "All". After clicking the query, all the corresponding query and response books will be exported. After setting the file name of the exported file according to the preset naming rules, for example, in the format of "Query Start Date + Query End Date + Supervisory Query and Response Book", the exported file can be sent to relevant personnel by email.

[0123] In order to enable those skilled in the art to better understand the above steps, the embodiment of the present application is illustrated below by using an example, but it should be understood that the embodiment of the present application is not limited to this.

[0124] In the specific implementation, the terminal can log in to the system through roles such as the risk control system supervision and handling user, the clearing system business query user or the clearing system business payment user, obtain business records generated by different businesses, and identify each business record obtained through the risk warning model in the risk monitoring system to identify whether the business corresponding to the business record has risks. When conducting risk warnings, risk warnings can be issued for different types of businesses through the foreign exchange trading business confirmation matching warning model, foreign exchange borrowing and lending transaction confirmation matching warning model, foreign currency funds borrowing and lending business monitoring model, precious metal business confirmation matching warning model, day-end balance 0 internal account monitoring model, internal account overdraft monitoring model, cross-border RMB collection monitoring model, and transaction cancellation business monitoring model. When the corresponding business is identified to have risks, the business record can be marked as abnormal.

[0125] After risk identification through the risk warning model, multiple target business records marked as abnormal can be obtained. The multiple target business records can be checked by staff logging into the risk control system to supervise the handling users or the clearing system business handling users for risk investigation.

[0126] In order to improve the efficiency of risk investigation, the terminal can run the automated script at a preset time, such as once in the morning and once in the afternoon on weekdays, log in to the corresponding system, and query the target business records to be processed. When querying, you can query by category and date for unprocessed vouchers, unprocessed transaction flows, and unprocessed target business records waiting to be processed.

[0127] After obtaining the target business records to be processed, the target business records can be matched based on the risk screening rules to determine whether to adjust the abnormal status of the target business records to a normal status. After multiple target business records are processed, a query response book can be generated and sent to the terminals of relevant personnel.

[0128] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0129] Based on the same inventive concept, the embodiment of the present application also provides an abnormal business processing device for implementing the abnormal business processing method involved above. The device can be applied to the processing of abnormal business in the field of artificial intelligence, and can also be used in any field other than the field of artificial intelligence. The present application does not limit the application field of the abnormal business processing device. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more abnormal business processing devices provided below can refer to the limitations of the abnormal business processing method above, and will not be repeated here.

[0130] In one embodiment, Figure 4 As shown, an abnormal business processing device is provided, including: a target business record acquisition module 401, a troubleshooting rule acquisition module 402 and a matching module 403, wherein:

[0131] The target business record acquisition module 401 is used to acquire the target business record marked as abnormal under the target type business; the target business record is obtained by matching the business records under the target type business based on the preset risk warning rule, and the business record meets the risk warning rule;

[0132] A screening rule acquisition module 402 is used to acquire risk screening rules corresponding to the target type of business; the risk screening rules are determined based on the business characteristics of historical non-risk business anomalies;

[0133] The matching module 403 is used to match the target business record based on the risk screening rule, and determine whether to adjust the abnormal state of the target business record to a normal state according to the matching result.

[0134] In one embodiment, the matching module 403 includes:

[0135] A key data item acquisition submodule, used to acquire key data items corresponding to the target type business; the key data items are determined based on the business characteristics corresponding to the target type business and / or the data structure corresponding to the business record under the target type business;

[0136] A target data content acquisition submodule, configured to acquire target data content corresponding to the key data item from the business data of the target business record based on a preset automation script file;

[0137] The data content matching model module is used to match the target data content based on the risk screening rules to obtain the matching result of the target business record.

[0138] In one embodiment, the key data items include data items associated with the credibility of the target type business, and the data content matching model module includes:

[0139] A preset data comparison unit is used to determine that the target business record matches the risk screening rule when the target data content is preset data content; the preset data content indicates that the credibility reaches a preset credibility condition.

[0140] In one embodiment, the key data item includes a data item representing an association relationship between the target business record and other business records, and the data content matching model module includes:

[0141] an associated record acquisition unit, configured to acquire, based on the target data content, an associated business record associated with the target business record;

[0142] The associated record identification unit is used to determine that the target business record matches the risk screening rule if the associated business record is a business record in a normal state.

[0143] In one embodiment, the association record acquisition unit is specifically used to:

[0144] A business identifier corresponding to the business is obtained, and a historical business record corresponding to the business is obtained as an associated business record of the target business record; the business includes multiple business records, and the historical business record is a business record that occurs before the target business record.

[0145] In one embodiment, the apparatus further comprises:

[0146] An adjustment information receiving module, used to receive adjustment information; the adjustment information is determined based on the review process corresponding to the historical target business record within a preset time;

[0147] A rule adjustment module is used to adjust the risk screening rules and the automation script file based on the adjustment information.

[0148] In one embodiment, the risk screening rule is a plurality of risk screening rules, and the matching module 403 includes:

[0149] A normal state adjustment submodule, configured to adjust the abnormal state of the target business record to a normal state if the target business record matches the current risk screening rule;

[0150] A state maintaining module is used to maintain the abnormal state of the target business record if the target business record does not match any of the risk screening rules in the multiple risk screening rules.

[0151] Each module in the above-mentioned abnormal business processing device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module above.

[0152] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory, a communication 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 communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, an abnormal business processing method 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.

[0153] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the present application scheme, and does not constitute a limitation on the computer device to which the present application scheme is applied. The specific computer device may include Figure 5More or fewer components may be shown, or certain components may be combined, or may have a different arrangement of components.

[0154] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0155] Obtaining a target business record marked as abnormal under a target type of business; the target business record is a business record obtained by matching business records under the target type of business based on a preset risk warning rule and satisfying the risk warning rule;

[0156] Obtaining risk screening rules corresponding to the target type of business; the risk screening rules are determined based on business characteristics of historical non-risk business anomalies;

[0157] Based on the risk screening rules, the target business record is matched, and according to the matching result, it is determined whether to adjust the abnormal state of the target business record to a normal state.

[0158] In one embodiment, when the processor executes the computer program, the steps in the other method embodiments described above are also implemented.

[0159] 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:

[0160] Obtaining a target business record marked as abnormal under a target type of business; the target business record is a business record obtained by matching business records under the target type of business based on a preset risk warning rule and satisfying the risk warning rule;

[0161] Obtaining risk screening rules corresponding to the target type of business; the risk screening rules are determined based on business characteristics of historical non-risk business anomalies;

[0162] Based on the risk screening rules, the target business record is matched, and according to the matching result, it is determined whether to adjust the abnormal state of the target business record to a normal state.

[0163] In one embodiment, when the computer program is executed by a processor, the steps in the other method embodiments described above are also implemented.

[0164] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0165] Obtaining a target business record marked as abnormal under a target type of business; the target business record is a business record obtained by matching business records under the target type of business based on a preset risk warning rule and satisfying the risk warning rule;

[0166] Obtaining risk screening rules corresponding to the target type of business; the risk screening rules are determined based on business characteristics of historical non-risk business anomalies;

[0167] Based on the risk screening rules, the target business record is matched, and according to the matching result, it is determined whether to adjust the abnormal state of the target business record to a normal state.

[0168] In one embodiment, when the computer program is executed by a processor, the steps in the other method embodiments described above are also implemented.

[0169] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0170] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed 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 the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0171] 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.

[0172] The above-described 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 present application. 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 present application shall be subject to the attached claims.

Claims

1. A method for handling abnormal business, characterized in that: The method comprises: Obtaining a target business record marked as abnormal under a target type of business; the target business record is a business record obtained by matching business records under the target type of business based on a preset risk warning rule and satisfying the risk warning rule; Obtaining risk screening rules corresponding to the target type of business; the risk screening rules are determined based on the business characteristics of historical non-risk business anomalies, and the risk screening rules are used to screen out business records that have abnormal business characteristics in the target business records but are evaluated as normal; Based on the risk screening rules, the target business record is matched, and according to the matching result, it is determined whether to adjust the abnormal state of the target business record to a normal state; The matching of the target business record based on the risk screening rule includes: Acquire key data items corresponding to the target type business; the key data items are determined based on business features corresponding to the target type business and / or data structures corresponding to business records under the target type business; Based on a preset automation script file, obtaining target data content corresponding to the key data item from the business data of the target business record; Based on the risk screening rules, the target data content is matched to obtain a matching result of the target business record.

2. The method according to claim 1, characterized in that: The key data items include data items associated with the credibility of the target type of business, and the target data content is matched based on the risk screening rule to obtain the matching result of the target business record, including: In the case where the target data content is a preset data content, it is determined that the target business record matches the risk screening rule; the preset data content indicates that the credibility reaches a preset credibility condition.

3. The method according to claim 1, characterized in that The key data items include data items that characterize the association relationship between the target business record and other business records. The target data content is matched based on the risk screening rule to obtain the matching result of the target business record, including: Based on the target data content, acquiring an associated business record associated with the target business record; If the associated business record is a business record in a normal state, it is determined that the target business record matches the risk screening rule.

4. The method according to claim 3, characterized in that The acquiring, based on the target data content, an associated business record associated with the target business record comprises: Based on the business identifier corresponding to the business, a historical business record corresponding to the business is obtained as an associated business record of the target business record; the business includes multiple business records, and the historical business record is a business record that occurs before the target business record.

5. The method according to claim 1, characterized in that The method further comprises: Receive adjustment information; the adjustment information is determined based on the review process corresponding to the historical target business records within a preset time; Based on the adjustment information, the risk screening rules and the automation script file are adjusted.

6. The method according to claim 1, characterized in that The risk screening rule is a plurality of risk screening rules, and the determination of whether to adjust the abnormal state of the target business record to a normal state according to the matching result includes: If the target business record matches the current risk screening rule, adjusting the abnormal state of the target business record to a normal state; If the target business record does not match any of the multiple risk screening rules, the abnormal state of the target business record is maintained.

7. An abnormal business processing device, characterized in that: The device comprises: A target business record acquisition module is used to acquire target business records marked as abnormal under target type business; the target business records are business records that meet the risk warning rules and are obtained by matching business records under the target type business based on preset risk warning rules; A screening rule acquisition module is used to obtain risk screening rules corresponding to the target type of business; the risk screening rules are determined based on the business characteristics of historical non-risk business anomalies, and the risk screening rules are used to filter out business records that have abnormal business characteristics in the target business records but are evaluated as normal; A matching module, used to match the target business record based on the risk screening rule, and determine whether to adjust the abnormal state of the target business record to a normal state according to the matching result; The matching module is specifically used for: Acquire key data items corresponding to the target type business; the key data items are determined based on business features corresponding to the target type business and / or data structures corresponding to business records under the target type business; Based on a preset automation script file, obtaining target data content corresponding to the key data item from the business data of the target business record; Based on the risk screening rules, the target data content is matched to obtain a matching result of the target business record.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. 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 6 are implemented.

10. A computer program product, comprising a computer program, 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 6 are implemented.

Images