False trade identification method, device and system

Abstract

The invention relates to a false trade identification method, device and system. The method comprises the following steps: in response to a monitored trade behavior, obtaining trade information associated with the trade behavior; performing feature extraction on the transaction information to obtain transaction features; inputting the transaction features into a trained bogus transaction recognition model to obtain a recognition result output after the bogus transaction recognition model recognizes the transaction features based on preset bogus transaction features; the bogus transaction features are pre-generated based on transaction rules; and generating a suspicious transaction report based on the identification result, and outputting early warning information based on the suspicious transaction report. According to the scheme, the efficiency and accuracy of false trade monitoring are improved.

Description

Technical Field

[0001] This disclosure relates to the field of information processing technology, and in particular to a method, apparatus and system for identifying fraudulent trade. Background Technology

[0002] In related technologies, fraudulent trade refers to business practices where companies, in order to obtain illegal profits, violate principles of honest operation and fair competition by concealing the truth and using methods such as internal misrepresentation and external false reporting to deceive customers and relevant authorities. This illegal behavior violates generally accepted business principles, constitutes unfair competition, severely damages market rules and commercial credit, and has serious social harm. Fraudulent trade is highly concealed and manifests in various forms, posing a significant obstacle to its identification.

[0003] Compared to identifying fraudulent trade in non-financial sectors, identifying fraudulent trade in the financial sector has more characteristics. These include typically high customs declaration amounts, false customs declaration locations, and involvement of more geographical regions and industries. Furthermore, fraudulent trade in the financial sector is often accompanied by financial fraud or has related characteristics. Current methods for identifying fraudulent trade in the financial sector are limited in their ability to comprehensively identify such trade. Summary of the Invention

[0004] To overcome the problems existing in related technologies, this disclosure provides a method, apparatus and system for identifying fraudulent trade.

[0005] According to a first aspect of the present disclosure, a method for identifying fraudulent trade is provided, comprising:

[0006] In response to the detection of a trade activity, transaction information associated with the trade activity is obtained;

[0007] The transaction information is subjected to feature extraction to obtain transaction features;

[0008] The transaction features are input into a trained fake transaction identification model to obtain the identification result output by the fake transaction identification model after identifying the transaction features based on preset fake transaction features; the fake transaction features are pre-generated based on transaction rules;

[0009] A suspicious transaction report is generated based on the identification results, and a warning message is output based on the suspicious transaction report.

[0010] In some embodiments of this disclosure, the transaction features may include any one or more of the following:

[0011] Characteristics of the behavior of both parties in the transaction, characteristics of the transaction process, characteristics of the transaction result, and characteristics of the customs declaration;

[0012] The trading rules include any one or more of the following:

[0013] Rules governing the behavior of both parties in a transaction, rules governing the transaction process, rules governing the transaction results, and rules governing customs declarations.

[0014] In some embodiments of this disclosure, the characteristics of the fraudulent transactions are generated through the following steps:

[0015] The trading rules are input into the trained feature generation model to obtain the fake trading features generated by the feature generation model based on the trading feature rules.

[0016] In some embodiments of this disclosure, the characteristics of the fraudulent transaction include any one or more of the following:

[0017] When the two parties to the transaction are Company A and Company B, the distance between the principal trading location of Company A and the principal trading location of Company B is less than or equal to the first preset distance;

[0018] Company A and Company B simultaneously shipped goods from the same warehouse on the same trading day;

[0019] Company A and Company B made payments to each other on the same trading day, and the amounts paid by Company A and Company B to each other were relative.

[0020] Company A and / or Company B make payments exceeding the preset value of goods in the short term, and the frequency of payments exceeds the preset frequency, and the rate of change in payment amount exceeds the preset rate of change.

[0021] The difference between the transaction price of goods between Company A and Company B and the average market price is greater than the first preset difference.

[0022] Company A and / or Company B receive more payments than a preset amount within a preset time period, and receive a higher frequency of different types of goods than the preset frequency, and the rate of change in the amount received is greater than the preset rate of change.

[0023] Company A and Company B imported goods of the same category in the same transaction report;

[0024] The similarity of the item categories of the goods imported by Company A and Company B on the same trading day is greater than a preset threshold.

[0025] The difference between the declared price and the actual price of the goods traded between Company A and Company B is greater than the second preset difference.

[0026] In some embodiments of this disclosure, the method further includes:

[0027] In response to receiving feedback from the user regarding the suspicious transaction report and / or the warning information;

[0028] The fake transaction identification model and the fake transaction features are optimized based on the feedback information.

[0029] In some embodiments of this disclosure, the fraudulent transaction identification model can be trained using the following steps:

[0030] Obtain historical transaction information and the true results of identifying fraudulent transactions corresponding to the historical transaction information;

[0031] Feature extraction is performed on the historical transaction information to obtain transaction feature samples;

[0032] The transaction feature samples are input into the machine learning model to be trained to obtain the predicted recognition result output by the machine learning model.

[0033] Based on the actual results of the fraudulent transaction identification, determine whether the predicted value of the identification result meets the preset conditions;

[0034] If the predicted value of the identification result does not meet the preset conditions, the parameters of the machine learning model are tuned, and the process returns to the step of inputting the transaction feature sample into the machine learning model to be trained, until the predicted value of the identification result meets the preset conditions, thus obtaining the fake transaction identification model.

[0035] According to a second aspect of the embodiments of this disclosure, a

[0036] The acquisition unit is used to acquire transaction information associated with the trade activity in response to the detected trade activity.

[0037] The extraction unit is used to extract features from the transaction information to obtain transaction features;

[0038] The identification unit is used to input the transaction features into a trained fake transaction identification model, and obtain the identification result output by the fake transaction identification model after identifying the transaction features based on preset fake transaction features; the fake transaction features are pre-generated based on transaction rules;

[0039] The early warning unit is used to generate a suspicious transaction report based on the identification results and output early warning information based on the suspicious transaction report.

[0040] According to a third aspect of the present disclosure, an electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method as described in any one of the first aspects.

[0041] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method as described in any one of the first aspects.

[0042] According to a fifth aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the method as described in any one of the first aspects.

[0043] The technical solutions provided by the embodiments of this disclosure can include the following beneficial effects: in response to the detection of trade activities, transaction information associated with the trade activities is obtained; features are extracted from the transaction information to obtain transaction features; the transaction features are input into a trained fraudulent transaction identification model to obtain an identification result output by the fraudulent transaction identification model after identifying the transaction features based on preset fraudulent transaction features; the fraudulent transaction features are pre-generated based on transaction rules; a suspicious transaction report is generated based on the identification result, and a warning message is output based on the suspicious transaction report. By comprehensively monitoring possible fraudulent trade activities during the transaction process through fraudulent transaction feature identification based on transaction rules, the efficiency and accuracy of fraudulent trade monitoring are improved.

[0044] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0045] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0046] Figure 1 This is a flowchart illustrating a method for identifying fraudulent trades according to an exemplary embodiment.

[0047] Figure 2 This is a block diagram illustrating a fraudulent trade identification device according to an exemplary embodiment.

[0048] Figure 3 This is a block diagram illustrating an apparatus for a method of identifying fraudulent trade, according to an exemplary embodiment. Detailed Implementation

[0049] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0050] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the present disclosure. The singular forms “a” and “the” as used in this disclosure and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0051] It should be understood that although the terms first, second, third, etc., may be used to describe various information in embodiments of this disclosure, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first information may also be referred to as second information without departing from the scope of embodiments of this disclosure, and similarly, second information may also be referred to as first information. Depending on the context, the words “if” and “suppose” as used herein may be interpreted as “when”, “when”, or “in response to a determination”.

[0052] Furthermore, various forms of processes shown in the embodiments of this disclosure can be used to reorder, add, or delete steps. For example, the steps described in this application can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0053] In related technologies, fraudulent trade refers to business practices where companies, in order to obtain illegal profits, violate principles of honest operation and fair competition by concealing the truth and using methods such as internal misrepresentation and external false reporting to deceive customers and relevant authorities. This illegal behavior violates generally accepted business principles, constitutes unfair competition, severely damages market rules and commercial credit, and has serious social harm. Fraudulent trade is highly concealed and manifests in various forms, posing a significant obstacle to its identification.

[0054] Compared to identifying fraudulent trade in non-financial sectors, identifying fraudulent trade in the financial sector has more characteristics. These include typically high customs declaration amounts, false customs declaration locations, and involvement of more geographical regions and industries. Furthermore, fraudulent trade in the financial sector is often accompanied by financial fraud or has related characteristics. Current methods for identifying fraudulent trade in the financial sector are limited in their ability to comprehensively identify such trade.

[0055] To address the aforementioned issues, this disclosure provides a method, apparatus, and system for identifying fraudulent trade. In response to detected trade activity, the system acquires transaction information associated with the activity; extracts features from the transaction information to obtain transaction features; inputs these features into a trained fraudulent trade identification model, resulting in an identification result output by the model after identifying the transaction features based on preset fraudulent trade features; these fraudulent trade features are pre-generated based on transaction rules; a suspicious transaction report is generated based on the identification result, and a warning message is output based on the suspicious transaction report. By identifying fraudulent trade features based on transaction rules, the system comprehensively monitors potential fraudulent trade activities during the transaction process, improving the efficiency and accuracy of fraudulent trade monitoring.

[0056] Figure 1 This is a flowchart illustrating a method for identifying fraudulent trade according to an exemplary embodiment, such as... Figure 1 As shown, it should be noted that the fraudulent trade identification method of this disclosure embodiment is applied in a fraudulent trade identification device. For example... Figure 1 As shown, the method may include the following steps:

[0057] Step 101: In response to the detected trade activity, obtain the transaction information associated with the trade activity.

[0058] In one embodiment, the aforementioned transaction information related to trade activities can be collected from public data channels, transaction records, third-party platforms, company internal systems, and counterparties. This includes, but is not limited to, the following information: counterparty name and address, transaction date, transaction amount, information on traded goods, transaction invoices, and customs declaration information.

[0059] As an example, data can be obtained from publicly available sources, including but not limited to e-commerce websites, transaction records, corporate annual reports, bidding information, and customs declaration records; it can also be obtained from transaction records, including but not limited to transaction flow, logistics information, and customs declaration information; it can also be obtained from third-party platforms, including but not limited to third-party financial platforms, logistics platforms, and capital platforms; and it can also be obtained from internal company systems, including but not limited to ERP systems, financial systems, and management systems.

[0060] As another example, transaction data can be downloaded from public data channels and cleaned and filtered using data cleaning and anomaly detection technologies; information on the trade process can also be obtained from transaction records, including but not limited to transaction amount, transaction time, transaction method, transaction location, and information on traded goods; transaction information can also be obtained from third-party platforms, including but not limited to information on fund flows and logistics; and relevant corporate information can also be obtained from the company's internal systems, including but not limited to corporate qualifications, credit ratings, and financial information.

[0061] Step 102: Extract features from the transaction information to obtain transaction features.

[0062] In one embodiment, the extracted transaction features can be standardized after they are obtained to make them comparable and uniform.

[0063] In some embodiments of this application, transaction features may include any one or more of the following:

[0064] Characteristics of the behavior of both parties in the transaction, characteristics of the transaction process, characteristics of the transaction result, and characteristics of the customs declaration;

[0065] The trading rules include any one or more of the following:

[0066] Rules governing the behavior of both parties in a transaction, rules governing the transaction process, rules governing the transaction results, and rules governing customs declarations.

[0067] As a possible example, based on data that has undergone data standardization, statistical analysis methods, machine learning algorithms, neural network algorithms, or decision tree algorithms can be used to generate features of fraudulent transactions.

[0068] In one example, key features can be predefined and filtered, and data cleaning and standardization techniques can be used to preprocess the extracted features; feature selection techniques can be used to select features that are important and representative.

[0069] The following methods can be used to standardize the data: use statistical methods to calculate the correlation and distance between variables; perform feature dimensionality reduction and deletion based on correlation and distance calculations; and select key features for data modeling and analysis.

[0070] Step 103: Input the transaction features into the trained fake transaction identification model to obtain the identification result output by the fake transaction identification model after identifying the transaction features based on the preset fake transaction features.

[0071] Among them, the characteristics of fake transactions are pre-generated based on transaction rules.

[0072] In one embodiment, the fraudulent transaction identification model can be a machine learning model or a deep learning model.

[0073] In another implementation, the fraudulent transaction identification model can be a decision tree model.

[0074] In some embodiments of this application, the characteristics of fraudulent transactions are generated through the following steps:

[0075] The trading rules are input into the trained feature generation model to obtain the fake trading features generated by the feature generation model based on the trading feature rules.

[0076] In some embodiments of this application, the characteristics of fraudulent transactions include any one or more of the following:

[0077] When the two parties to the transaction are Company A and Company B, the distance between the principal trading location of Company A and the principal trading location of Company B is less than or equal to the first preset distance;

[0078] Company A and Company B simultaneously shipped goods from the same warehouse on the same trading day;

[0079] Company A and Company B made payments to each other on the same trading day, and the amounts paid by Company A and Company B to each other were relative.

[0080] Company A and / or Company B make payments exceeding the preset value of goods in the short term, and the frequency of payments exceeds the preset frequency, and the rate of change in payment amount exceeds the preset rate of change.

[0081] The difference between the transaction price of goods between Company A and Company B and the average market price is greater than the first preset difference.

[0082] Company A and / or Company B receive more payments than the preset value of goods within a preset time period, receive more types of goods more frequently than the preset frequency, and experience a greater rate of change in the amount received than the preset rate of change.

[0083] Company A and Company B imported goods of the same category in the same transaction report;

[0084] The similarity of the item categories of the goods imported by Company A and Company B on the same trading day is greater than a preset threshold.

[0085] The difference between the declared price and the actual price of the goods traded between Company A and Company B is greater than the second preset difference.

[0086] For example, characteristics of fake transactions may include:

[0087] Feature 1: The distance between Company A's main trading location and Company B's main trading location is within 100km;

[0088] Feature 2: On the same trading day, Company A and Company B simultaneously ship goods from the same warehouse;

[0089] Feature 3: On the same trading day, Company A and Company B make payments to each other, with the amounts being relative;

[0090] Feature 4: The company makes large payments in a short period of time, frequently, and with unstable amounts;

[0091] Feature 5: Company A's goods prices are significantly lower than the market average and exceed a threshold;

[0092] Feature 6: The company receives large sums of money in a short period of time, frequently, and with unstable amounts;

[0093] Feature 7: On the same trading day, Company A and Company B respectively declared the import of the same category of goods;

[0094] Feature 8: On the same trading day, the goods imported by Company A and Company B, respectively, have a similarity exceeding the threshold when classified by category.

[0095] Feature 9: There is a significant gap between the declared price and the actual price of the goods.

[0096] Step 104: Generate a suspicious transaction report based on the identification results, and output early warning information based on the suspicious transaction report.

[0097] In one embodiment, suspicious transaction data can be collected, the authenticity and compliance of the data can be determined based on a fraudulent trade identification model, transactions determined to be suspicious can be marked and analyzed, and suspicious transaction reports can be generated.

[0098] In one embodiment, based on the generated suspicious transaction report, an early warning mechanism is triggered and a warning message is sent to relevant personnel. The corresponding actions are then taken according to the preset handling procedures, including but not limited to the following actions: suspending the transaction, investigating and verifying, and taking legal measures.

[0099] As an example of a possible implementation, warning thresholds and alarm rules can be set: Warning thresholds can be set based on historical transaction data and expert experience, including but not limited to the following parameters: amount, frequency, and number of transactions; alarm rules can be set, including but not limited to the following parameters: amount exceeding the warning threshold, number of transactions exceeding the warning threshold; handling plans can be set based on suspicious transaction reports: handling plans can be set based on suspicious transaction reports and expert experience, including but not limited to the following methods: suspending transactions, verifying transactions, taking legal action, etc.; warning information and handling suggestions can be sent to relevant personnel: according to the set alarm rules, a warning mechanism can be triggered when a transaction occurs or after a transaction is completed, sending warning information and handling suggestions to relevant personnel; follow-up processing can be carried out according to the set handling plan: according to the set handling plan, transactions can be suspended, transactions verified, investigations conducted, legal action taken, etc.

[0100] In some embodiments of this application, the method may further include:

[0101] In response to receiving feedback from users regarding suspicious transaction reports and / or alerts;

[0102] The fake transaction identification model and fake transaction characteristics are optimized based on feedback information.

[0103] In one embodiment, a pre-set warning threshold and alarm rules can be implemented: Warning thresholds are set based on historical transaction data and expert experience, including but not limited to the following parameters: amount, frequency, and number of transactions; alarm rules are set, including but not limited to the following parameters: amount exceeding the warning threshold, number of transactions exceeding the warning threshold; A handling plan is set based on suspicious transaction reports: A handling plan is set based on suspicious transaction reports and expert experience, including but not limited to the following methods: suspending transactions, verifying transactions, taking legal action, etc.; Warning information and handling suggestions are sent to relevant personnel: According to the set alarm rules, a warning mechanism is triggered when a transaction occurs or after a transaction is completed, sending warning information and handling suggestions to relevant personnel; Subsequent handling is carried out according to the set handling plan: According to the set handling plan, transactions are suspended, transactions are verified, investigations are conducted, legal action is taken, etc.

[0104] In some embodiments of this application, the fraudulent transaction identification model can be trained using the following steps:

[0105] Obtain historical transaction information and the true results of identifying fraudulent transactions corresponding to that historical transaction information;

[0106] Feature extraction is performed on historical transaction information to obtain transaction feature samples;

[0107] Input the transaction feature samples into the machine learning model to be trained, and obtain the predicted value of the recognition result output by the machine learning model;

[0108] Based on the actual results of fraudulent transaction identification, determine whether the predicted value of the identification result meets the preset conditions;

[0109] If the predicted value of the identification result does not meet the preset conditions, the parameters of the machine learning model are tuned, and the process of inputting the transaction feature sample into the machine learning model to be trained is repeated until the predicted value of the identification result meets the preset conditions, thus obtaining the fraudulent transaction identification model.

[0110] In some embodiments of this application, a fraudulent transaction identification model can be constructed based on machine learning and deep learning algorithms in the following ways: defining and screening key features; preprocessing the extracted features using data cleaning and data standardization techniques; selecting important and representative features using feature selection techniques; dividing the feature data into training and test sets; establishing a fraudulent transaction identification model using machine learning and deep learning algorithms; training the model based on the training set; testing and evaluating the model using the test set; and evaluating the accuracy and efficiency of the model.

[0111] This disclosure has extremely broad application prospects in the field, such as early warning and identification of fraudulent trade. Its applicability includes, but is not limited to, trade transactions and payment collection between enterprises, customs-supervised import and export of goods, tax supervision, audit supervision, internet finance, and cross-border e-commerce. This identification method can identify and warn of fraudulent trade, improving transaction security and fairness. Utilizing big data technology and machine learning algorithms for fraudulent trade identification can improve the efficiency and accuracy of identification, and enable real-time monitoring and early warning of transaction behavior. By establishing a feedback mechanism and continuous improvement and optimization, the efficiency and accuracy of fraudulent transaction identification can be continuously improved. This invention, by utilizing big data technology and machine learning algorithms to analyze and model transaction behavior and data, achieves the identification and early warning of fraudulent trade, improving the efficiency and accuracy of identification; based on artificial intelligence and machine learning technology, it can improve the efficiency and accuracy of identification; by implementing early warning and processing mechanisms, it reduces transaction risks and ensures the fairness and security of transactions; through continuous improvement and optimization, it improves the efficiency and accuracy of fraud identification; it has broad commercial value and application prospects for enterprises, customs, taxation, auditing, internet finance, and cross-border e-commerce industries.

[0112] According to the fraudulent trade identification method proposed in this disclosure, in response to the detection of trade activities, transaction information associated with the trade activities is obtained; features are extracted from the transaction information to obtain transaction features; the transaction features are input into a trained fraudulent trade identification model to obtain the identification result output by the fraudulent trade identification model after identifying the transaction features based on preset fraudulent trade features; the fraudulent trade features are pre-generated based on transaction rules; a suspicious transaction report is generated based on the identification result, and a warning message is output based on the suspicious transaction report. By identifying fraudulent trade features based on transaction rules, possible fraudulent trade activities in the transaction process can be comprehensively monitored, improving the efficiency and accuracy of fraudulent trade monitoring.

[0113] Figure 2 This is a block diagram illustrating a fraudulent trade identification device according to an exemplary embodiment. (Refer to...) Figure 2 The device includes an acquisition unit 201, an extraction unit 202, an identification unit 203, and an early warning unit 204.

[0114] The acquisition unit 201 is used to acquire transaction information associated with the trade activity in response to the detection of the trade activity.

[0115] Extraction unit 202 is used to extract features from transaction information to obtain transaction features;

[0116] The identification unit 203 is used to input transaction features into the trained fake transaction identification model to obtain the identification result output by the fake transaction identification model after identifying the transaction features based on the preset fake transaction features; the fake transaction features are pre-generated based on transaction rules;

[0117] The early warning unit 204 is used to generate a suspicious transaction report based on the identification results and output early warning information based on the suspicious transaction report.

[0118] In some embodiments of this application, transaction features may include any one or more of the following:

[0119] Characteristics of the behavior of both parties in the transaction, characteristics of the transaction process, characteristics of the transaction result, and characteristics of the customs declaration;

[0120] The trading rules include any one or more of the following:

[0121] Rules governing the behavior of both parties in a transaction, rules governing the transaction process, rules governing the transaction results, and rules governing customs declarations.

[0122] In some embodiments of this application, the apparatus further includes a generation module, specifically configured to generate fraudulent transaction characteristics through the following steps:

[0123] The trading rules are input into the trained feature generation model to obtain the fake trading features generated by the feature generation model based on the trading feature rules.

[0124] In some embodiments of this application, the characteristics of fraudulent transactions include any one or more of the following:

[0125] When the two parties to the transaction are Company A and Company B, the distance between the principal trading location of Company A and the principal trading location of Company B is less than or equal to the first preset distance;

[0126] Company A and Company B simultaneously shipped goods from the same warehouse on the same trading day;

[0127] Company A and Company B made payments to each other on the same trading day, and the amounts paid by Company A and Company B to each other were relative.

[0128] Company A and / or Company B make payments exceeding the preset value of goods in the short term, and the frequency of payments exceeds the preset frequency, and the rate of change in payment amount exceeds the preset rate of change.

[0129] The difference between the transaction price of goods between Company A and Company B and the average market price is greater than the first preset difference.

[0130] Company A and / or Company B receive more payments than the preset value of goods within a preset time period, receive more types of goods more frequently than the preset frequency, and experience a greater rate of change in the amount received than the preset rate of change.

[0131] Company A and Company B imported goods of the same category in the same transaction report;

[0132] The similarity of the item categories of the goods imported by Company A and Company B on the same trading day is greater than a preset threshold.

[0133] The difference between the declared price and the actual price of the goods traded between Company A and Company B is greater than the second preset difference.

[0134] In some embodiments of this application, the apparatus further includes:

[0135] The receiving unit is used to respond to feedback information received from the user regarding suspicious transaction reports and / or warning information;

[0136] The optimization unit is used to optimize the fraudulent transaction identification model and fraudulent transaction features based on feedback information.

[0137] In some embodiments of this application, the apparatus further includes a training unit for:

[0138] Obtain historical transaction information and the true results of identifying fraudulent transactions corresponding to that historical transaction information;

[0139] Feature extraction is performed on historical transaction information to obtain transaction feature samples;

[0140] Input the transaction feature samples into the machine learning model to be trained, and obtain the predicted value of the recognition result output by the machine learning model;

[0141] Based on the actual results of fraudulent transaction identification, determine whether the predicted value of the identification result meets the preset conditions;

[0142] If the predicted value of the identification result does not meet the preset conditions, the parameters of the machine learning model are tuned, and the process of inputting the transaction feature sample into the machine learning model to be trained is repeated until the predicted value of the identification result meets the preset conditions, thus obtaining the fraudulent transaction identification model.

[0143] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0144] According to the fraudulent trade identification device proposed in this disclosure, in response to detecting trade activities, it acquires transaction information associated with the trade activities; extracts features from the transaction information to obtain transaction features; inputs the transaction features into a trained fraudulent trade identification model to obtain the identification result output by the fraudulent trade identification model after identifying the transaction features based on preset fraudulent trade features; the fraudulent trade features are pre-generated based on transaction rules; a suspicious transaction report is generated based on the identification result, and a warning message is output based on the suspicious transaction report. By identifying fraudulent trade features based on transaction rules, the device comprehensively monitors possible fraudulent trade activities during the transaction process, improving the efficiency and accuracy of fraudulent trade monitoring.

[0145] Figure 3 This is a block diagram illustrating an apparatus for a method of identifying fraudulent trade, according to an exemplary embodiment. For example, apparatus 300 may be an electronic device, such as a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0146] Reference Figure 3 The device 300 may include one or more of the following components: a processing component 302, a memory 304, a power component 306, a multimedia component 308, an audio component 310, an input / output (I / O) interface 312, a sensor component 314, and a communication component 316.

[0147] Processing component 302 typically controls the overall operation of device 300, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 302 may include one or more processors 320 to execute instructions to perform all or part of the steps of the methods described above. Furthermore, processing component 302 may include one or more modules to facilitate interaction between processing component 302 and other components. For example, processing component 302 may include a multimedia module to facilitate interaction between multimedia component 308 and processing component 302.

[0148] Memory 304 is configured to store various types of data to support the operation of device 300. Examples of this data include instructions for any application or method operating on device 300, contact data, phonebook data, messages, pictures, videos, etc. Memory 304 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0149] The power supply component 306 provides power to the various components of the device 300. The power supply component 306 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power to the device 300.

[0150] Multimedia component 308 includes a screen that provides an output interface between device 300 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of touch or swipe actions but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 308 includes a front-facing camera and / or a rear-facing camera. When device 300 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0151] Audio component 310 is configured to output and / or input audio signals. For example, audio component 310 includes a microphone (MIC) configured to receive external audio signals when device 300 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 304 or transmitted via communication component 316. In some embodiments, audio component 310 also includes a speaker for outputting audio signals.

[0152] I / O interface 312 provides an interface between processing component 302 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0153] Sensor assembly 314 includes one or more sensors for providing status assessments of various aspects of device 300. For example, sensor assembly 314 may detect the on / off state of device 300, the relative positioning of components such as the display and keypad of device 300, changes in the position of device 300 or a component of device 300, the presence or absence of user contact with device 300, the orientation or acceleration / deceleration of device 300, and temperature changes of device 300. Sensor assembly 314 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 314 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 314 may also include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor.

[0154] Communication component 316 is configured to facilitate wired or wireless communication between device 300 and other devices. Device 300 can access wireless networks based on communication standards, such as WiFi, 2G, or 3G, or combinations thereof. In one exemplary embodiment, communication component 316 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 316 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0155] In an exemplary embodiment, the apparatus 300 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0156] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 304 including instructions, which can be executed by a processor 320 of the device 300 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0157] In an exemplary embodiment, a computer program product is also provided, including a computer program that implements the above-described method when executed by the processor 320 of the device 300.

[0158] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0159] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for identifying fraudulent trade, characterized in that, include: In response to the detection of a trade activity, transaction information associated with the trade activity is obtained; The transaction information is subjected to feature extraction to obtain transaction features; The transaction features are input into a trained fake transaction identification model to obtain the identification result output by the fake transaction identification model after identifying the transaction features based on preset fake transaction features; the fake transaction features are pre-generated based on transaction rules; A suspicious transaction report is generated based on the identification results, and a warning message is output based on the suspicious transaction report.

2. The method for identifying fraudulent trade according to claim 1, characterized in that, The transaction characteristics may include any one or more of the following: Characteristics of the behavior of both parties in the transaction, characteristics of the transaction process, characteristics of the transaction result, and characteristics of the customs declaration; The trading rules include any one or more of the following: Rules governing the behavior of both parties in a transaction, rules governing the transaction process, rules governing the transaction results, and rules governing customs declarations.

3. The method for identifying fraudulent trade according to claim 1, characterized in that, The characteristics of the fraudulent transaction are generated through the following steps: The trading rules are input into the trained feature generation model to obtain the fake trading features generated by the feature generation model based on the trading feature rules.

4. The method for identifying fraudulent trade according to claim 1, characterized in that, The characteristics of fraudulent transactions include any one or more of the following: When the two parties to the transaction are Company A and Company B, the distance between the principal trading location of Company A and the principal trading location of Company B is less than or equal to the first preset distance; Company A and Company B simultaneously shipped goods from the same warehouse on the same trading day; Company A and Company B made payments to each other on the same trading day, and the amounts paid by Company A and Company B to each other were relative. Company A and / or Company B make payments exceeding the preset value of goods in the short term, and the frequency of payments exceeds the preset frequency, and the rate of change in payment amount exceeds the preset rate of change. The difference between the transaction price of goods between Company A and Company B and the average market price is greater than the first preset difference. Company A and / or Company B receive more payments than a preset amount within a preset time period, and receive a higher frequency of different types of goods than the preset frequency, and the rate of change in the amount received is greater than the preset rate of change. Company A and Company B imported goods of the same category in the same transaction report; The similarity of the item categories of the goods imported by Company A and Company B on the same trading day is greater than a preset threshold. The difference between the declared price and the actual price of the goods traded between Company A and Company B is greater than the second preset difference.

5. The method for identifying fraudulent trade according to claim 1, characterized in that, Also includes: In response to receiving feedback from the user regarding the suspicious transaction report and / or the warning information; The fake transaction identification model and the fake transaction features are optimized based on the feedback information.

6. The method for identifying fraudulent trade according to claim 1, characterized in that, The fraudulent transaction identification model can be trained using the following steps: Obtain historical transaction information and the true results of identifying fraudulent transactions corresponding to the historical transaction information; Feature extraction is performed on the historical transaction information to obtain transaction feature samples; The transaction feature samples are input into the machine learning model to be trained to obtain the predicted recognition result output by the machine learning model. Based on the actual results of the fraudulent transaction identification, determine whether the predicted value of the identification result meets the preset conditions; If the predicted value of the identification result does not meet the preset conditions, the parameters of the machine learning model are tuned, and the process returns to the step of inputting the transaction feature sample into the machine learning model to be trained, until the predicted value of the identification result meets the preset conditions, thus obtaining the fake transaction identification model.

7. A device for identifying fraudulent trade, characterized in that, include: The acquisition unit is used to acquire transaction information associated with the trade activity in response to the detected trade activity. The extraction unit is used to extract features from the transaction information to obtain transaction features; The identification unit is used to input the transaction features into a trained fake transaction identification model, and obtain the identification result output by the fake transaction identification model after identifying the transaction features based on preset fake transaction features; the fake transaction features are pre-generated based on transaction rules; The early warning unit is used to generate a suspicious transaction report based on the identification results and output early warning information based on the suspicious transaction report.

8. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, The computer program, when executed by a processor, implements the method as described in any one of claims 1 to 6.

Images