Transaction risk identification method and device, equipment, storage medium and program product

Abstract

The embodiment of the invention provides a transaction risk identification method and device, equipment, a storage medium and a program product, and relates to the field of financial science and technology and the field of artificial intelligence. The transaction risk identification method comprises the steps that multiple pieces of feature data of the eyes of a user under a current transaction are collected, the multiple pieces of feature data comprise the tear secretion amount, the blinking frequency and the variable quantity of eyeball fixation point coordinates, and the risk value of the current transaction is determined based on the multiple pieces of feature data; updating the risk value of the current transaction according to the risk level of the previous transaction, and determining the risk level of the current transaction according to the updated risk value of the current transaction; according to the method, the accuracy of transaction risk identification is improved, and the risk level of the current transaction of the user is effectively identified.

Description

Technical Field

[0001] The present application relates to the fields of financial technology and artificial intelligence, and in particular to a transaction risk identification method, device, equipment, storage medium and program product. Background Art

[0002] When banks handle financial services for users, staff are usually required to observe the user's facial expressions and behavior when conducting transactions such as transfers and remittances to determine whether they are subject to potential transaction risks such as fraud and threats.

[0003] However, the above method relies on the personal experience and subjective judgment of the staff, has low accuracy, and cannot effectively identify whether the user's current transaction behavior involves transaction risks. Summary of the Invention

[0004] The embodiments of the present application provide a transaction risk identification method, apparatus, device, storage medium and program product to address the problem that existing transaction risk identification methods have low accuracy and cannot effectively identify whether the user's current transaction behavior involves transaction risks.

[0005] In a first aspect, an embodiment of the present application provides a transaction risk identification method, comprising:

[0006] Collect multiple feature data of the user's eyes during the current transaction, and determine the risk value of the current transaction based on the multiple feature data, wherein the multiple feature data include: tear secretion volume, blink frequency, and change in eye gaze point coordinates;

[0007] Update the risk value of the current transaction based on the risk level of the previous transaction;

[0008] The risk level of the current transaction is determined based on the updated risk value of the current transaction.

[0009] Optionally, determining the risk value of the current transaction based on the multiple feature data includes:

[0010] performing normalization processing on the plurality of feature data;

[0011] According to the respective weights of the multiple feature data, a weighted sum is performed on the multiple feature data after normalization to obtain the risk value of the current transaction.

[0012] Optionally, the method further includes:

[0013] Acquire multiple features of the user's eyes corresponding to each of a plurality of first historical transactions, and multiple features of the user's eyes corresponding to each of a plurality of second historical transactions, wherein the risk level of the first historical transactions indicates no risk and the risk level of the second historical transactions indicates risk;

[0014] For each feature data item in the plurality of feature data items, determining a correlation between each feature data item of the plurality of first historical transactions and each feature data item of the plurality of second historical transactions;

[0015] The weight of each feature data item is determined according to the relevance of each feature data item.

[0016] Optionally, determining the weight of each feature data item according to the relevance of each feature data item includes:

[0017] Determining the information content of each feature data according to the relevance of each feature data;

[0018] The weight of each feature data item is determined according to the information amount of each feature data item.

[0019] Optionally, updating the risk value of the current transaction according to the risk level of the previous transaction includes:

[0020] If the risk level of the previous transaction is the highest level, increase the risk value of the current transaction according to the mean risk value of historical risk-free transactions and the standard deviation of the risk values ​​of all historical transactions;

[0021] In a case where the risk level of the previous transaction is other than the highest level, the risk value of the current transaction is maintained.

[0022] Optionally, determining the risk level of the current transaction based on the updated risk value of the current transaction includes:

[0023] If the updated risk value of the current transaction is within the first interval, determining the risk level of the current transaction as no risk;

[0024] If the updated risk value of the current transaction is within the second interval, determining the risk level of the current transaction as the first risk level;

[0025] When the updated risk value of the current transaction is outside the first interval range and the second interval range, determining the risk level of the current transaction as the second risk level;

[0026] Among them, the second risk level is higher than the first risk level, the first interval range includes the first value to the second value, the first value is the mean of the risk values ​​of historical risk-free transactions minus the product of the standard deviation of the risk values ​​of all historical transactions and the first coefficient, the second value is the mean of the risk values ​​of the historical risk-free transactions plus the product of the standard deviation of the risk values ​​of all historical transactions and the first coefficient; the second interval range includes the third value to the first value and the second value to the fourth value, and does not include the first value and the second value, the third value is the mean of the risk values ​​of the historical risk-free transactions minus the product of the standard deviation of the risk values ​​of all historical transactions and the second coefficient, and the fourth value is the mean of the risk values ​​of the historical risk-free transactions plus the product of the standard deviation of the risk values ​​of all historical transactions and the second coefficient.

[0027] Optionally, also include:

[0028] If the risk level of the current transaction is the second risk level, setting the user account to a prohibited transaction state;

[0029] When the risk level of the current transaction is the first risk level, the transaction limit of the user account is reduced.

[0030] In a second aspect, an embodiment of the present application provides a transaction risk identification device, comprising:

[0031] A collection module, configured to collect multiple feature data of the user's eyes during the current transaction and determine the risk value of the current transaction based on the multiple feature data, wherein the multiple feature data include: tear secretion volume, blink frequency, and change in eye gaze point coordinates;

[0032] An update module is used to update the risk value of the current transaction based on the risk level of the previous transaction;

[0033] The determination module is used to determine the risk level of the current transaction based on the updated risk value of the current transaction.

[0034] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a memory, a processor;

[0035] The memory stores computer-executable instructions;

[0036] The processor executes the computer-executable instructions stored in the memory, so that the processor performs the transaction risk identification method as described in the first aspect above.

[0037] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the transaction risk identification method described in the first aspect above.

[0038] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the transaction risk identification method described in the first aspect above.

[0039] The transaction risk identification method, apparatus, device, storage medium, and program product provided in the embodiments of the present application collect multiple feature data of the user's eyes in the current transaction, including: tear secretion volume, blinking frequency, and change in eye gaze point coordinates, determine the risk value of the current transaction based on the multiple feature data, update the risk value of the current transaction based on the risk level of the previous transaction, and determine the risk level of the current transaction based on the updated risk value of the current transaction; this method improves the accuracy of transaction risk identification and effectively identifies the risk level of the user's current transaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0041] Figure 1 A schematic diagram of a scenario of a transaction risk identification method provided in an embodiment of the present application;

[0042] Figure 2 Schematic diagram of the process of the transaction risk identification method provided in the embodiment of the application Figure 1 ;

[0043] Figure 3 Schematic diagram of the process of the transaction risk identification method provided in the embodiment of the application Figure 2 ;

[0044] Figure 4 A schematic diagram of the structure of a transaction risk identification device provided in an embodiment of the present application;

[0045] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0046] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0047] To make the objectives, technical solutions, and advantages of this application more clear, the technical solutions in this application will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0048] The terms "first," "second," "third," "fourth," and so forth (if any) in the description and claims of the present invention and in the accompanying drawings are used to distinguish between similar objects and are not necessarily used to describe a particular order or sequential sequence. It should be understood that the terms used in this manner are interchangeable where appropriate, such that the embodiments of the present invention described herein can be practiced in sequences other than those illustrated or described herein.

[0049] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described in this application as "exemplary" or "for example" should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0050] 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, and the collection, use, processing, transmission, provision, disclosure and application of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0051] In addition, this application involves conducting big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, electronic terminal operation data, etc.), and using artificial intelligence technology to make automated decisions, and making technical solutions that have a significant impact on personal rights and interests based on the results of automated decisions. The application provides users with corresponding operation entrances for them to choose to agree or reject the results of automated decisions; if the user chooses to reject, the expert decision-making process will be entered.

[0052] It should be noted that the transaction risk identification method, device, equipment, storage medium and program product of the present application can be used in the field of financial technology, and can also be used in any field other than the field of financial technology. The application field of the transaction risk identification method, device, equipment, storage medium and program product of the present application is not limited.

[0053] Existing transaction risk identification methods usually rely on the personal experience and subjective judgment of staff, with low accuracy, and cannot effectively identify whether the user's current transaction behavior involves transaction risks.

[0054] In view of this, an embodiment of the present application provides a transaction risk identification method. First, multiple feature data of the user's eyes in the current transaction are collected, where the multiple feature data may include tear secretion volume, blinking frequency, change in eye gaze point coordinates, etc. Then, the initial risk value of the current transaction is determined based on the multiple feature data, and the initial risk value of the current transaction is updated according to the risk level of the previous transaction, and the risk level of the current transaction is determined according to the updated risk value; this method improves the accuracy of transaction risk identification and effectively identifies the risk level of the user's current transaction.

[0055] In response to the above problems, this application provides a transaction risk identification method. Figure 1 This is a scenario diagram of the transaction risk identification method provided in this application. It should be noted that Figure 1 What is shown are merely examples of application scenarios in which the transaction risk identification method of the present application can be applied, to help those skilled in the art understand the technical content of the present application, but it does not mean that the embodiments of the present application cannot be used in other devices, systems, environments or scenarios.

[0056] like Figure 1 As shown, the transaction risk identification system includes: a server 1, a terminal device 2 and a camera 3, wherein the terminal device 2 and the camera 3 are respectively connected to the server 1 for communication.

[0057] The camera 3 is used to collect eye feature data of the user 4 who is handling business, and send the collected eye feature data to the server 1.

[0058] The server 1 is used to receive the eye feature data sent by the camera 3, and based on the eye feature data of the user 4, determine the risk level of the current transaction and the corresponding processing measures, and then send the identification result of the risk level of the current transaction to the terminal device 2.

[0059] The terminal device 2 is used to display the risk level of the current transaction of the user 4 on the screen, so that the staff can check whether there is any risk in the current transaction, and if there is any risk in the current transaction, remind the user or reconfirm whether to continue the current transaction.

[0060] In some embodiments, the terminal device 2 and the camera 3 may be integrated or separately provided, which is not limited in this application.

[0061] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0062] Figure 2 Schematic diagram of the process of the transaction risk identification method provided in the embodiment of the application Figure 1 The execution subject of this embodiment can be, for example, Figure 1 The transaction risk identification system in the embodiment. Figure 2 As shown, the transaction risk identification method provided in this embodiment includes:

[0063] S201. Collect multiple feature data of the user's eyes in the current transaction, and determine the risk value of the current transaction based on the multiple feature data.

[0064] In the embodiment of the present application, multiple feature data may include: tear secretion volume, blinking frequency, and change in eye gaze point coordinates.

[0065] It is understandable that when a user is nervous, anxious or feels threatened, the body will produce a series of physiological changes, such as increased tear gland activity, which may lead to changes in tear secretion; faster blinking frequency in an attempt to relieve eye discomfort through rapid blinking; and distraction, manifested as frequent changes in eye gaze.

[0066] In some embodiments, the aforementioned multiple feature data can be obtained by analyzing and extracting the eye image of the current user using image processing technology and eye feature detection algorithms. For example, by analyzing the area of ​​the reflective region on the corneal surface, the tear secretion volume can be calculated; by locating the eye contour, the position coordinates of the upper and lower eyelids are obtained, and the eye aspect ratio, that is, the ratio of the distance between the upper and lower eyelids to the distance between the left and right eye corners, is calculated. If this value drops below a preset threshold and then rises back above the threshold, it indicates a blink. In this way, the blink frequency can be obtained by analyzing consecutive frames. In addition, by calculating the offset of the pupil center coordinates in consecutive frames, the change in the coordinates of the eyeball's gaze point can be obtained.

[0067] In some embodiments, multiple pieces of feature data may be normalized, and weighted summed based on their respective weights to obtain a risk value for the current transaction.

[0068] For example, the risk value of the current transaction can be determined using the following formula (1):

[0069]

[0070] in, is the normalized tear secretion volume, is the normalized blink frequency, is the change in the normalized eye gaze point coordinates, 、 and They are 、 、 The weight of .

[0071] S202: Update the risk value of the current transaction based on the risk level of the previous transaction.

[0072] In the embodiment of the present application, the risk status of the user's recent transactions can be obtained based on the risk level of the user's last transaction, thereby dynamically evaluating the risk value of the current transaction.

[0073] This is because if the user has recently made a suspicious transaction with a high risk level, the risk of this transaction will increase sharply. Conversely, if the user has recently made a risk-free transaction, the risk value of this transaction can be assessed normally.

[0074] S203: Determine the risk level of the current transaction according to the updated risk value of the current transaction.

[0075] In some embodiments, each risk level may correspond to a preset threshold range, and the updated risk value may be compared with each preset threshold range to determine the risk level of the current transaction, and corresponding measures may be taken based on the determined risk level.

[0076] The transaction risk identification method provided in the embodiment of the present application collects multiple feature data of the user's eyes in the current transaction, the multiple feature data including: tear secretion volume, blinking frequency, and change in eye gaze point coordinates, determines the risk value of the current transaction based on the multiple feature data, updates the risk value of the current transaction according to the risk level of the previous transaction, and determines the risk level of the current transaction according to the updated risk value of the current transaction; this method improves the accuracy of transaction risk identification and effectively identifies the risk level of the user's current transaction.

[0077] Figure 3 Schematic diagram of the process of the transaction risk identification method provided in the embodiment of the application Figure 2 ,like Figure 3 As shown, this embodiment Figure 2 Based on the embodiment, the transaction risk identification method is described in detail. The transaction risk identification method provided in this embodiment includes:

[0078] S301. Collect multiple feature data of the user's eyes in the current transaction.

[0079] Step S301 is similar to the above-mentioned step S201 and will not be described again here.

[0080] S302: Perform normalization processing on multiple feature data.

[0081] The following describes the normalization process of the tear secretion volume, blink frequency, and eye gaze point coordinate changes:

[0082] For example, the tear secretion volume can be calculated using the following formula (2): Perform normalization:

[0083]

[0084] in, and are the preset maximum and minimum values ​​of tear secretion, is the normalized tear secretion volume.

[0085] The blink frequency can be calculated using the following formula (3): Perform normalization:

[0086]

[0087] in, and They are the maximum and minimum values ​​of the preset blink frequency, is the normalized blink frequency.

[0088] The change in the eye gaze point coordinates can be calculated using the following formula (4): :

[0089]

[0090] in, is the coordinate of the mth eye gaze point, and are the average values ​​of the horizontal and vertical coordinates of the gaze points, respectively, and h is the total number of recorded points within the set time.

[0091] Then use the following formula (5) to calculate the change in the coordinates of the eyeball gaze point: Perform normalization:

[0092]

[0093] in, and are the maximum and minimum values ​​of the preset eye gaze point coordinate changes, is the normalized change in the eye gaze point coordinates.

[0094] S303: Perform weighted summation on the normalized multiple feature data according to their respective weights to obtain a risk value of the current transaction.

[0095] For example, here is an implementation method for determining the weight of each feature data:

[0096] Acquire multiple features of the user's eyes corresponding to each of the plurality of first historical transactions, and multiple features of the user's eyes corresponding to each of the plurality of second historical transactions, wherein the risk level of the first historical transactions indicates no risk and the risk level of the second historical transactions indicates risk;

[0097] For each feature data item in the plurality of feature data items, determining a correlation between each feature data item of the plurality of first historical transactions and each feature data item of the plurality of second historical transactions;

[0098] The weight of each feature data is determined according to the relevance of each feature data.

[0099] In an embodiment of the present application, user eye feature data corresponding to multiple historical transaction data can be obtained from a database, and then the multiple historical eye feature data can be standardized. Then, the risky historical eye feature data and the risk-free historical eye feature data can be separated from the standardized mixed eye feature data to calculate the correlation between each corresponding feature data in the risky historical eye feature data and the risk-free historical eye feature data.

[0100] For example, the user eye feature matrix corresponding to n groups of historical transactions is shown in the following formula (6):

[0101]

[0102] The following formula (7) is used to calculate the mean of the jth column in the above matrix: :

[0103]

[0104] The standard deviation of the jth column in the above matrix is ​​calculated using the following formula (8): :

[0105]

[0106] Then, use the mean and standard deviation , use the following formula (9) to calculate the above matrix Each data in To perform standardization:

[0107]

[0108] The normalized matrix is ​​as follows:

[0109]

[0110] From the above matrix The risk-free historical eye feature data and risk-prone historical eye feature data are extracted from the matrix to obtain a matrix containing only risk-free data. and a matrix containing only risk data :

[0111]

[0112]

[0113] Furthermore, the risk-free eye feature matrix is ​​calculated and risky eye feature matrix In , the correlation of the feature data of each column corresponding to the item is:

[0114]

[0115] In the above formula (13), is the average value of the k-th feature data in the risk-free eye feature matrix, is the average value of the kth feature data in the risky eye feature matrix, .

[0116] If the correlation The closer the value of is to 1, the stronger the correlation is, indicating that the distribution patterns of the K features in the risky eye feature data are highly similar to those in the risk-free eye feature data. In other words, the correlation between the K features and transaction risk is weak.

[0117] If the correlation The closer the value is to 0, the weaker the correlation, indicating a significant difference in the distribution patterns of the K features in the risky eye feature data compared to the non-risky eye feature data. In other words, the stronger the correlation between the K features and transaction risk, the stronger the risk-discriminating ability of the K features themselves, and the more likely they are to indicate a risk.

[0118] Optionally, the weight of each feature data is determined based on its relevance, including:

[0119] According to the relevance of each feature data, the information content of each feature data is determined; according to the information content of each feature data, the weight of each feature data is determined.

[0120] For example, the information content of each feature data can be calculated using the following formula (14):

[0121]

[0122] Among them, the correlation The smaller it is, the more information the feature data contains.

[0123] Then, based on the amount of information of each feature data, normalization processing is performed to obtain the weights of each feature:

[0124]

[0125] In this way, the weights of various feature data can be determined by the above formulas (6) to (15), and then the collected multiple feature data are normalized using formulas (2) to (5) respectively, and then the weighted sum is performed using the above formula (1), so that the risk value of the current transaction can be obtained.

[0126] S304: Determine whether the risk level of the previous transaction is the highest level; if so, execute step S305; if not, execute step S306.

[0127] The essence of this step is: when the risk level of the previous transaction is the highest level, increase the risk value of the current transaction based on the mean risk value of historical risk-free transactions and the standard deviation of the risk values ​​of all historical transactions; when the risk level of the previous transaction is other than the highest level, maintain the risk value of the current transaction.

[0128] This is because if the risk level of the user's previous transaction was the highest, the current transaction is more likely to be risky. Therefore, increasing the risk value of the current transaction allows the system to maintain a higher level of vigilance. If the risk level of the previous transaction was not the highest, the current risk value remains unchanged to avoid overreaction. In this way, the system can dynamically adjust the risk value of the current transaction based on the risk status of the user's most recent transaction, enhancing the system's adaptability and flexibility.

[0129] S305: Increase the risk value of the current transaction according to the mean risk value of historical risk-free transactions and the standard deviation of the risk values ​​of all historical transactions.

[0130] For example, the following formula (16) can be used to calculate the mean risk value of historical risk-free transactions:

[0131]

[0132] in, For the The risk value of a group of historical risk-free transactions, The matrix of risk-free data in the above formula (11) can be Each set of feature data in Substitute it into formula (1) and perform weighted sum calculation to obtain it.

[0133] Then, the standard deviation of the risk value of all historical transactions can be calculated using the following formula (17):

[0134]

[0135] in, is the mean of the risk assessment values ​​of all historical transaction data including risky and risk-free data, For the The risk value of a group of historical transaction data.

[0136] Finally, the following formula (18) can be used to increase the risk value of the current transaction:

[0137]

[0138] in, is the risk value directly calculated using the above formula (1), is the increased risk value, is the average risk value of historical risk-free transactions, is the standard deviation of the risk value of all historical transactions, and is the coefficient of standard deviation, The function is used to return an integer variable. , then return 0; if , then return 0; if , it returns 1.

[0139] It can be seen that using the above formula can increase the risk value of the current transaction.

[0140] S306. Maintain the risk value of the current transaction.

[0141] S307: Determine whether the updated risk value of the current transaction is within the first interval; if so, execute step S308; if not, execute step S309.

[0142] In the embodiment of the present application, the first interval range and the second interval range can be pre-set interval ranges based on the average performance of risk-free data in historical transaction data and the overall volatility of all transaction risk assessment values.

[0143] Exemplarily, the first interval range includes a first value to a second value, the first value is the mean of the risk values ​​of historical risk-free transactions minus the product of the standard deviation of the risk values ​​of all historical transactions and the first coefficient, and the second value is the mean of the risk values ​​of historical risk-free transactions plus the product of the standard deviation of the risk values ​​of all historical transactions and the first coefficient.

[0144] For example, the first interval range can be expressed as: .

[0145] in, is the first value, is the second value, is the average risk value of historical risk-free transactions, is the standard deviation of the risk value of all historical transactions, The first coefficient is used to limit the risk-free level assessment range to multiples of the standard deviation fluctuation based on the mean value.

[0146] The essence of this step is: when the updated risk value of the current transaction is within the first interval, the risk level of the current transaction is determined to be risk-free; when the updated risk value of the current transaction is not within the first interval, it is necessary to further determine whether the risk value falls within other preset intervals.

[0147] S308. Determine that the risk level of the current transaction is risk-free.

[0148] S309: Determine whether the updated risk value of the current transaction is within the second interval; if so, execute step S310; if not, execute step S311.

[0149] The essence of this step is: when the updated risk value of the current transaction is within the second interval, determining the risk level of the current transaction as the first risk level;

[0150] When the updated risk value of the current transaction is outside the first interval range and the second interval range, the risk level of the current transaction is determined to be the second risk level.

[0151] The second risk level is higher than the first risk level. The first risk level may indicate that the risk level of the current transaction is medium risk, and the second risk level may indicate that the risk level of the current transaction is high risk.

[0152] Exemplarily, the second interval range includes the third value to the first value and the second value to the fourth value, and does not include the first value and the second value. The third value is the mean of the risk values ​​of historical risk-free transactions minus the product of the standard deviation of the risk values ​​of all historical transactions and the second coefficient. The fourth value is the mean of the risk values ​​of historical risk-free transactions plus the product of the standard deviation of the risk values ​​of all historical transactions and the second coefficient.

[0153] For example, the second interval range can be expressed as: , .

[0154] in, is the third value, is the fourth value, is the second coefficient, which is used to limit the multiple of the standard deviation fluctuation of the first risk level assessment range based on the average value.

[0155] S310: Determine that the risk level of the current transaction is the first risk level.

[0156] In some embodiments, if the risk level of the current transaction is Level 1, the transaction limit of the user account is reduced. In this way, by limiting the transaction limit permissions of accounts with a medium risk level in the current transaction, economic losses caused by illegal activities such as fraud and money laundering can be effectively reduced.

[0157] S311. Determine that the risk level of the current transaction is the second risk level.

[0158] In some embodiments, if the risk level of the current transaction is the second risk level, the user account is set to a prohibited transaction status. In this way, for accounts marked as high risk, timely prohibition of transactions can prevent the user's funds from further risk or loss, and ensure the safety of the user's property.

[0159] The transaction risk identification method provided in the embodiment of the present application first normalizes the multiple feature data of the user's eyes collected, and then uses a formula to perform weighted summation to obtain the initial risk value of the current transaction. Then, it is determined whether the risk level of the previous transaction is the highest level, that is, the second risk level. If so, the initial risk value is substituted into the corresponding formula for increase processing, so that the increased risk value is used as the risk value of the current transaction; if not, the initial risk value is used as the risk value of the current transaction. Finally, based on the preset first interval range and second interval range, it is determined that the updated risk value of the current transaction falls within the interval range to determine the risk level of the current transaction and execute corresponding security measures. This method improves the accuracy of transaction risk identification and effectively identifies the risk level of the user's current transaction.

[0160] In the aforementioned embodiments, the transaction risk identification method provided in the embodiments of the present application has been introduced. To implement the various functions of the method provided in the embodiments of the present application, the electronic device serving as the execution subject may include hardware structures and / or software modules, and implement the aforementioned functions in the form of hardware structures, software modules, or hardware structures and software modules. Whether a particular function is implemented in the form of hardware structures, software modules, or hardware structures and software modules depends on the specific application and design constraints of the technical solution.

[0161] For example, Figure 4 A schematic diagram of the structure of the transaction risk identification device provided in the embodiment of the present application is shown as follows: Figure 4 As shown, the transaction risk identification device 400 provided in this embodiment includes:

[0162] Collection module 401, for collecting multiple feature data of the user's eyes during the current transaction, and determining the risk value of the current transaction based on the multiple feature data, the multiple feature data including: tear secretion volume, blink frequency, and change in eye gaze point coordinates;

[0163] An updating module 402 is used to update the risk value of the current transaction based on the risk level of the previous transaction;

[0164] The determination module 403 is configured to determine the risk level of the current transaction according to the updated risk value of the current transaction.

[0165] In some embodiments, the acquisition module 401 is further configured to perform normalization processing on the multiple feature data;

[0166] The acquisition module 401 is further configured to perform weighted summation on the normalized multiple feature data according to respective weights of the multiple feature data to obtain a risk value of the current transaction.

[0167] In some embodiments, the apparatus further includes: an acquisition module 404;

[0168] The acquisition module 404 is configured to acquire multiple features of the user's eyes corresponding to each of the plurality of first historical transactions, and multiple features of the user's eyes corresponding to each of the plurality of second historical transactions, wherein the risk level of the first historical transactions indicates no risk and the risk level of the second historical transactions indicates risk;

[0169] The determining module 403 is further configured to determine, for each of the plurality of feature data, a correlation between each feature data of the plurality of first historical transactions and each feature data of the plurality of second historical transactions;

[0170] The determining module 403 is further configured to determine the weight of each feature data item according to the relevance of each feature data item.

[0171] In some embodiments, the determining module 403 is further configured to determine the information content of each feature data item based on the correlation of each feature data item;

[0172] The determining module 403 is further configured to determine the weight of each feature data item according to the information amount of each feature data item.

[0173] In some embodiments, the updating module 402 is further configured to, when the risk level of the previous transaction is the highest level, increase the risk value of the current transaction based on the mean risk value of historical risk-free transactions and the standard deviation of the risk values ​​of all historical transactions;

[0174] The updating module 402 is further configured to maintain the risk value of the current transaction when the risk level of the previous transaction is a level other than the highest level.

[0175] In some embodiments, the determining module 403 is specifically configured to determine that the risk level of the current transaction is risk-free when the updated risk value of the current transaction is within the first interval;

[0176] The determining module 403 is specifically configured to determine that the risk level of the current transaction is the first risk level when the updated risk value of the current transaction is within the second interval;

[0177] The determining module 403 is specifically configured to determine that the risk level of the current transaction is the second risk level if the updated risk value of the current transaction is outside the first interval range and the second interval range;

[0178] Among them, the second risk level is higher than the first risk level, the first interval range includes the first value to the second value, the first value is the mean of the risk values ​​of historical risk-free transactions minus the product of the standard deviation of the risk values ​​of all historical transactions and the first coefficient, the second value is the mean of the risk values ​​of the historical risk-free transactions plus the product of the standard deviation of the risk values ​​of all historical transactions and the first coefficient; the second interval range includes the third value to the first value and the second value to the fourth value, and does not include the first value and the second value, the third value is the mean of the risk values ​​of the historical risk-free transactions minus the product of the standard deviation of the risk values ​​of all historical transactions and the second coefficient, and the fourth value is the mean of the risk values ​​of the historical risk-free transactions plus the product of the standard deviation of the risk values ​​of all historical transactions and the second coefficient.

[0179] In some embodiments, the apparatus further comprises: a processing module 405;

[0180] The processing module 405 is configured to set the user account to a prohibited transaction state when the risk level of the current transaction is the second risk level;

[0181] The processing module 405 is further configured to reduce the transaction limit of the user account when the risk level of the current transaction is the first risk level.

[0182] It should be noted that the specific implementation principles and effects of the above-mentioned transaction risk identification device can be found in the relevant descriptions and effects corresponding to the above-mentioned embodiments, and will not be elaborated here.

[0183] Figure 5 This is a schematic diagram of the structure of the electronic device provided in the embodiment of the present application. Figure 5 As shown, the present application provides an electronic device, which includes a receiver 501, a transmitter 502, a processor 503 and a memory 504.

[0184] Receiver 501, for receiving instructions and data;

[0185] Transmitter 502, used to send instructions and data;

[0186] Memory 504, for storing computer-executable instructions;

[0187] The processor 503 is configured to execute the computer-executable instructions stored in the memory 504 to implement the various steps of the transaction risk identification method in the above embodiment. For details, please refer to the relevant description in the above embodiment of the transaction risk identification method.

[0188] Optionally, the memory 504 may be independent or integrated with the processor 503 .

[0189] When the memory 504 is independently provided, the electronic device further includes a bus for connecting the memory 504 and the processor 503 .

[0190] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASICs), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly executed by a hardware processor or by a combination of hardware and software modules within the processor.

[0191] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage.

[0192] A bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be categorized as address buses, data buses, and control buses. For ease of illustration, the buses in the drawings of this application are not limited to just one bus or just one type of bus.

[0193] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the transaction risk identification method as described in any of the aforementioned embodiments of the present application.

[0194] An embodiment of the present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the transaction risk identification method described in any of the foregoing embodiments of the present application is implemented.

[0195] The readable storage medium may be implemented by any type of volatile or non-volatile memory 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. The readable storage medium may be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0196] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0197] The division of units is merely a logical functional division; actual implementations may employ alternative divisions, such as combining or integrating multiple units or components into another system, or omitting or disabling certain features. Furthermore, any direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or units, either through an interface, electrical, mechanical, or other means.

[0198] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0199] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0200] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0201] Those skilled in the art will appreciate that all or part of the steps in the above-described method embodiments can be implemented using hardware associated with program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0202] Finally, it should be noted that those skilled in the art will readily identify other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art not disclosed herein. The present invention is not limited to the precise structure described above and illustrated in the accompanying drawings, and various modifications and variations may be made without departing from the scope thereof. The scope of the present invention is limited solely by the appended claims.

Claims

1. A transaction risk identification method, characterized in that: include: Collect multiple feature data of the user's eyes during the current transaction, and determine the risk value of the current transaction based on the multiple feature data, wherein the multiple feature data include: tear secretion volume, blink frequency, and change in eye gaze point coordinates; Update the risk value of the current transaction based on the risk level of the previous transaction; The risk level of the current transaction is determined based on the updated risk value of the current transaction.

2. The method according to claim 1, characterized in that The determining of the risk value of the current transaction based on the plurality of feature data includes: performing normalization processing on the plurality of feature data; According to the respective weights of the multiple feature data, a weighted sum is performed on the multiple feature data after normalization to obtain the risk value of the current transaction.

3. The method according to claim 2, characterized in that Also includes: Acquire multiple features of the user's eyes corresponding to each of a plurality of first historical transactions, and multiple features of the user's eyes corresponding to each of a plurality of second historical transactions, wherein the risk level of the first historical transactions indicates no risk and the risk level of the second historical transactions indicates risk; For each feature data item in the plurality of feature data items, determining a correlation between each feature data item of the plurality of first historical transactions and each feature data item of the plurality of second historical transactions; The weight of each feature data item is determined according to the relevance of each feature data item.

4. The method according to claim 3, characterized in that Determining the weight of each feature data according to the relevance of each feature data includes: Determining the information content of each feature data according to the relevance of each feature data; The weight of each feature data item is determined according to the information amount of each feature data item.

5. The method according to claim 1, wherein The updating of the risk value of the current transaction according to the risk level of the previous transaction includes: If the risk level of the previous transaction is the highest level, increase the risk value of the current transaction according to the mean risk value of historical risk-free transactions and the standard deviation of the risk values ​​of all historical transactions; In a case where the risk level of the previous transaction is other than the highest level, the risk value of the current transaction is maintained.

6. The method according to claim 1, characterized in that Determining the risk level of the current transaction based on the updated risk value of the current transaction includes: If the updated risk value of the current transaction is within the first interval, determining the risk level of the current transaction as no risk; If the updated risk value of the current transaction is within the second interval, determining the risk level of the current transaction as the first risk level; When the updated risk value of the current transaction is outside the first interval range and the second interval range, determining the risk level of the current transaction as the second risk level; Among them, the second risk level is higher than the first risk level, the first interval range includes the first value to the second value, the first value is the mean of the risk values ​​of historical risk-free transactions minus the product of the standard deviation of the risk values ​​of all historical transactions and the first coefficient, the second value is the mean of the risk values ​​of the historical risk-free transactions plus the product of the standard deviation of the risk values ​​of all historical transactions and the first coefficient; the second interval range includes the third value to the first value and the second value to the fourth value, and does not include the first value and the second value, the third value is the mean of the risk values ​​of the historical risk-free transactions minus the product of the standard deviation of the risk values ​​of all historical transactions and the second coefficient, and the fourth value is the mean of the risk values ​​of the historical risk-free transactions plus the product of the standard deviation of the risk values ​​of all historical transactions and the second coefficient.

7. The method according to claim 6, characterized in that Also includes: If the risk level of the current transaction is the second risk level, setting the user account to a prohibited transaction state; When the risk level of the current transaction is the first risk level, the transaction limit of the user account is reduced.

8. A transaction risk identification device, characterized in that: include: A collection module, configured to collect multiple feature data of the user's eyes during the current transaction and determine the risk value of the current transaction based on the multiple feature data, wherein the multiple feature data include: tear secretion volume, blink frequency, and change in eye gaze point coordinates; An update module is used to update the risk value of the current transaction based on the risk level of the previous transaction; The determination module is used to determine the risk level of the current transaction based on the updated risk value of the current transaction.

9. An electronic device, characterized in that: include: Memory; processor; wherein the memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the transaction risk identification method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that The computer storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the transaction risk identification method according to any one of claims 1 to 7.

11. A computer program product, characterized in that The method comprises a computer program, which, when executed by a processor, implements the transaction risk identification method according to any one of claims 1 to 7.

Images