Risk assessment method, device, equipment, storage medium and product

Abstract

The application discloses a risk assessment method and device, equipment, storage medium and product, relates to the technical field of big data, and the risk assessment method comprises the following steps: obtaining the unavailable coefficient of each subinterval according to the data loss coefficient, the data tampering coefficient and the data update delay coefficient corresponding to each subinterval of a target time interval; establishing an abnormal coefficient set according to the unavailable coefficient of each subinterval, and determining a target standard deviation value corresponding to the abnormal coefficient set; determining a target data state according to the target standard deviation value and a preset standard deviation value; when the target data state is a data available state, performing risk assessment on the stored user data, and determining a risk assessment result of the user. By judging whether the data stored by the operator about the target user is available, the stored user data is further risk assessed, so that the final risk assessment of the target user is more accurate, and the influence of the problem of the data storage of the operator on the risk assessment is reduced.

Description

Technical Field

[0001] This application relates to the field of big data technology, and in particular to risk assessment methods, apparatus, equipment, storage media and products. Background Technology

[0002] Current methods for conducting intelligent financial risk control based on telecom operators' big data generally assume that the user data stored by the operators is accurate, and risk assessments are directly based on this data. However, if the operators' data storage is compromised, continuing to assess user risk based on this data may lead to inaccurate risk assessments, increasing financial risk. Therefore, ensuring the accuracy of financial risk assessments when telecom operators' data storage is compromised has become a pressing issue. Summary of the Invention

[0003] The main purpose of this application is to provide a risk assessment method, apparatus, equipment, storage medium, and product, which aims to solve the technical problem of ensuring the accuracy of financial risk assessment when data storage problems occur in operators.

[0004] To achieve the above objectives, this application proposes a risk assessment method, which includes:

[0005] The unavailability coefficient of each sub-interval is obtained based on the data loss coefficient, data tampering coefficient, and data update delay coefficient corresponding to each sub-interval of the target time interval;

[0006] An abnormal coefficient set is established based on the unavailability coefficients of each sub-interval, and the target standard deviation corresponding to the abnormal coefficient set is determined.

[0007] The target data status is determined based on the target standard deviation and the preset standard deviation;

[0008] When the target data is in a data-available state, a risk assessment is performed on the stored user data to determine the user's risk assessment result.

[0009] In one embodiment, before the step of obtaining the unavailability coefficient of each sub-interval based on the data loss coefficient, data tampering coefficient, and data update delay coefficient corresponding to each sub-interval of the target time interval, the method further includes:

[0010] Obtain the current amount of stored data, the time period of data loss, and the amount of critical data loss for each sub-interval of the target time interval;

[0011] The data loss coefficient is obtained based on the current amount of stored data and the preset amount of stored data.

[0012] The data loss time coefficient is obtained based on the data loss time period and the preset loss time period.

[0013] The key data loss coefficient is obtained based on the key data loss amount and the total data loss amount.

[0014] The data loss coefficient is determined based on the data loss quantity coefficient, the data loss time coefficient, and the data key quantity loss coefficient.

[0015] In one embodiment, before the step of obtaining the unavailability coefficient of each sub-interval based on the data loss coefficient, data tampering coefficient, and data update delay coefficient corresponding to each sub-interval of the target time interval, the method further includes:

[0016] Obtain the amount of tampered data, the total amount of data in the interval, the number of times data was tampered, and the total number of data detected for each sub-interval of the target time interval;

[0017] The tampering quantity coefficient is obtained based on the amount of tampered data and the total amount of data in the interval.

[0018] The tampering frequency coefficient is obtained based on the number of data tamperings and the total number of data detections.

[0019] The data tampering coefficient is determined based on the tampering quantity coefficient, the tampering frequency coefficient, the preset tampering impact level, and the preset importance coefficient.

[0020] In one embodiment, before the step of obtaining the unavailability coefficient of each sub-interval based on the data loss coefficient, data tampering coefficient, and data update delay coefficient corresponding to each sub-interval of the target time interval, the method further includes:

[0021] Obtain the number of times the target data is updated and the total number of target data corresponding to each sub-interval of the target time interval;

[0022] Data is filtered based on the target data update count and the preset data update count to obtain the total number of filtered data.

[0023] The data update delay coefficient is determined based on the total number of target data and the total number of filtered data.

[0024] In one embodiment, the step of establishing an anomaly coefficient set based on the unavailability coefficients of each sub-interval and determining the target standard deviation corresponding to the anomaly coefficient set includes:

[0025] Establish a set of unavailability coefficients based on the unavailability coefficients of each sub-interval;

[0026] The unusable coefficient set is filtered according to a preset unusable coefficient threshold to obtain multiple abnormal coefficients;

[0027] An abnormal coefficient set is established based on multiple abnormal coefficients, and the target standard deviation corresponding to the abnormal coefficient set is determined.

[0028] In one embodiment, the step of determining the target data state based on the target standard deviation and a preset standard deviation includes:

[0029] The target standard deviation is compared with the preset standard deviation to obtain the standard deviation comparison result;

[0030] When the standard deviation comparison result shows that the target standard deviation is greater than or equal to the preset standard deviation, the target data status is determined to be unavailable, and a data unavailable alarm message is generated.

[0031] When the standard deviation comparison result shows that the target standard deviation is less than the preset standard deviation, the target data status is determined to be a data usable status.

[0032] Furthermore, to achieve the above objectives, this application also proposes a risk assessment device, which includes:

[0033] The processing module is used to obtain the unavailability coefficient of each sub-interval based on the data loss coefficient, data tampering coefficient, and data update delay coefficient corresponding to each sub-interval of the target time interval;

[0034] A module is established to build an abnormal coefficient set based on the unavailability coefficients of each sub-interval, and to determine the target standard deviation value corresponding to the abnormal coefficient set;

[0035] The processing module is also used to determine the target data status based on the target standard deviation and the preset standard deviation;

[0036] The assessment module is used to perform a risk assessment on the stored user data when the target data status is data available, and to determine the user's risk assessment result.

[0037] In addition, to achieve the above objectives, this application also proposes a risk assessment device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the risk assessment method as described above.

[0038] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and which, when executed by a processor, implements the steps of the risk assessment method described above.

[0039] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the risk assessment method described above.

[0040] This application obtains the unavailability coefficient of each sub-interval based on the data loss coefficient, data tampering coefficient, and data update delay coefficient corresponding to each sub-interval of the target time interval; establishes an anomaly coefficient set based on the unavailability coefficient of each sub-interval, and determines the target standard deviation corresponding to the anomaly coefficient set; determines the target data status based on the target standard deviation and a preset standard deviation; and when the target data status is a data availability status, performs a risk assessment on the stored user data to determine the user's risk assessment result. By determining whether the data about the target user stored by the operator is available, and then performing a risk assessment on the stored user data, the final risk assessment of the target user is more accurate, reducing the impact of data storage problems of the operator on the risk assessment. Attached Figure Description

[0041] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0042] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a flowchart illustrating the risk assessment method of this application in Implementation Example 1.

[0044] Figure 2 This is a flowchart illustrating Embodiment 2 of the risk assessment method of this application;

[0045] Figure 3 A simplified flowchart illustrating the risk assessment method provided in Embodiment 1 of this application;

[0046] Figure 4 This is a schematic diagram of the module structure of the risk assessment device according to an embodiment of this application;

[0047] Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the risk assessment method in the embodiments of this application.

[0048] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0049] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0050] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0051] The main solution of this application embodiment is as follows: Obtain the unavailability coefficient of each sub-interval based on the data loss coefficient, data tampering coefficient, and data update delay coefficient corresponding to each sub-interval of the target time interval; establish an abnormal coefficient set based on the unavailability coefficient of each sub-interval, and determine the target standard deviation corresponding to the abnormal coefficient set; determine the target data state based on the target standard deviation and a preset standard deviation; when the target data state is a data available state, perform a risk assessment on the stored user data and determine the user's risk assessment result.

[0052] Current methods for conducting intelligent financial risk control based on telecom operators' big data generally assume that the user data stored by the operators is accurate, and risk assessments are directly based on this data. However, if the operators' data storage is compromised, continuing to assess user risk based on this data may lead to inaccurate risk assessments, increasing financial risk. Therefore, ensuring the accuracy of financial risk assessments when telecom operators' data storage is compromised has become a pressing issue.

[0053] This application obtains the unavailability coefficient of each sub-interval based on the data loss coefficient, data tampering coefficient, and data update delay coefficient corresponding to each sub-interval of the target time interval; establishes an anomaly coefficient set based on the unavailability coefficient of each sub-interval, and determines the target standard deviation corresponding to the anomaly coefficient set; determines the target data status based on the target standard deviation and a preset standard deviation; and when the target data status is a data availability status, performs a risk assessment on the stored user data to determine the user's risk assessment result. By determining whether the data about the target user stored by the operator is available, and then performing a risk assessment on the stored user data, the final risk assessment of the target user is more accurate, reducing the impact of data storage problems of the operator on the risk assessment.

[0054] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or a risk assessment device capable of performing the above functions. The following description uses a risk assessment device as the executing entity, such as a terminal device corresponding to an operator, to illustrate this embodiment and the subsequent embodiments.

[0055] Based on this, embodiments of this application provide a risk assessment method, referring to Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the risk assessment method of this application.

[0056] In this embodiment, the risk assessment method includes steps S10 to S40:

[0057] Step S10: Obtain the unavailability coefficient of each sub-interval based on the data loss coefficient, data tampering coefficient, and data update delay coefficient corresponding to each sub-interval of the target time interval;

[0058] It should be noted that the financial intelligent risk control method based on telecom operator big data in this embodiment integrates a large amount of user data from telecom operators, including call records, SMS interactions, internet browsing behavior, consumption habits, and location information, for in-depth analysis and modeling. Using this data in conjunction with machine learning and artificial intelligence technologies, user behavioral profiles and credit assessment models are built to evaluate their credit risk and financial status, thereby providing a more comprehensive risk analysis. This helps financial institutions identify potential default risks and fraudulent activities during loan approval and credit card issuance processes, thus improving the accuracy and efficiency of risk control decisions and effectively reducing financial risks.

[0059] It is understandable that the target time interval refers to the time period from the time of the target user's data stored by the operator to the current time. The sub-interval refers to the time interval obtained by dividing the target time interval according to the preset window. The preset window is set by professionals according to the actual situation, and its specifics are not limited or elaborated. The data loss coefficient refers to the degree of data loss of the target user stored by the operator. The data tampering coefficient refers to the degree to which the data is illegally modified or destroyed within a specific time period. The update delay coefficient refers to the time difference coefficient from the generation of data to the time when the data is correctly stored and can be used for querying. The unavailability coefficient is used to evaluate the overall performance of the data service within a specific time period.

[0060] In practical implementation, the unavailability coefficient of each sub-interval is obtained based on the data loss coefficient, data tampering coefficient, and data update delay coefficient within that sub-interval, specifically as follows:

[0061]

[0062] In the formula, Yfdx is the unavailability coefficient, Dsx, Bak, and BC are the data loss coefficient, data tampering coefficient, and data update delay coefficient, respectively, and f1, f2, and f3 are the preset proportional coefficients of the data loss coefficient, data tampering coefficient, and data update delay coefficient, respectively, and f1, f2, and f3 are all greater than 0. f1, f2, and f3 are set by professionals according to the actual situation. Generally, the sum of f1, f2, and f3 is 1. For example, f1, f2, and f3 can be 0.3, 0.3, and 0.4, respectively, or other numbers. This embodiment does not limit the specific values.

[0063] In one feasible implementation, steps A11 to A15 may be included before step S10:

[0064] Step A11: Obtain the current amount of stored data, the time period of data loss, and the amount of critical data loss for each sub-interval of the target time interval;

[0065] It should be noted that the current stored data volume refers to the actual amount of data about the target user stored by the operator at different times within each sub-interval; the data loss period refers to consecutive time periods in the operator's stored data where no data records are recorded. This can be analyzed through the operator's log system to identify which time periods the system did not receive user data. For example, by comparing the intervals between different data records using timestamps, consecutive loss periods can be identified; the critical data loss volume refers to specific sets of user data stored by the operator, which are usually critical data that are essential for financial risk assessment, such as high-value consumption and credit records. If this data is lost, the risk assessment may be significantly affected; by classifying user data, it is possible to identify which data is critical. Operators may label different types of user behavior, financial data, etc.

[0066] Step A12: Obtain the data loss coefficient based on the current stored data volume and the preset stored data volume;

[0067] Understandably, the preset storage data volume refers to the amount of data that should theoretically be stored at that moment, based on the user behavior data volume specified by the operator's system design or protocol. This represents all the data that the system should store under ideal conditions, without data loss and with complete transmission. It can be set based on the operator's protocol, such as the network communication data and behavior logs that should be received at each moment, and can be preset in the system design phase. The data loss coefficient refers to the proportion of the amount of data lost in a specific time period to the total amount of data that should be there.

[0068] In practical implementation, the actual amount of data about the target user stored by the operator at different times within each sub-interval and the corresponding preset amount of stored data are obtained, and the actual amount of data and the corresponding preset amount of stored data are respectively marked as G. 实 l and G 预 l Let l represent the sequential number of the time points, l = 1, 2, 3, 4, ..., L, and L represent the total number of time points, where L is a positive integer. The data loss coefficient DF is calculated using the following formula:

[0069] Step A13: Obtain the data loss time coefficient based on the data loss time period and the preset loss time period;

[0070] It is understandable that the preset data loss period refers to the maximum allowed period of continuous data loss specified by the system. Data loss exceeding this period may have a serious impact on the system's risk assessment. It can be set by specific experts and will not be limited or elaborated upon. The data loss time coefficient refers to the proportion of the duration of data loss to the entire assessment period.

[0071] In practice, the operator obtains several time periods of continuous data loss of the target user stored in each sub-interval, compares each time period with the preset longest continuous data loss time period, adds the time periods corresponding to the longest continuous data loss time period to obtain the continuous loss time, and divides the length of the continuous loss time by the length of the corresponding sub-interval to obtain the data loss time coefficient RH.

[0072] Step A14: Obtain the data key quantity loss coefficient based on the key data loss amount and the total data loss amount;

[0073] It is understandable that the total amount of data lost refers to the total amount of all data lost within a certain period of time. The amount of all lost data can be determined through data storage logs or transmission records. The data criticality loss coefficient refers to the proportion of critical data lost within a specific period of time to the total amount of data lost.

[0074] In practice, the amount of key data lost in the data about the target user within each sub-interval is obtained, and the key data loss coefficient PH is calculated in combination with the total data loss. The calculation formula is: PH = xd / xc, where xd and xc are the amount of key data lost and the total data loss, respectively.

[0075] Step A15: Determine the data loss coefficient based on the data loss quantity coefficient, the data loss time coefficient, and the data key quantity loss coefficient.

[0076] In practical implementation, the data loss coefficient is calculated based on the data loss quantity coefficient (DF), data loss time coefficient (RH), and data criticality loss coefficient (PH). The formula is: Dsx = a1 × DF + a2 × RH + a3 × PH; where Dsx is the data loss coefficient, and a1, a2, and a3 are preset weighting coefficients for the data loss quantity coefficient (DF), data loss time coefficient (RH), and data criticality loss coefficient (PH), and a1, a2, and a3 are all greater than 0. a1, a2, and a3 are set by professionals according to the actual situation. Generally, the sum of a1, a2, and a3 is 1. For example, a1, a2, and a3 can be 0.5, 0.2, and 0.3 respectively, or other numbers; there are no specific limitations.

[0077] It should be noted that the actual amount of data about a target user stored by the operator generally includes behavioral data, consumption data, location information, etc., that the operator successfully acquires and stores within a given time period. The actual amount of data about the target user can be directly obtained through the operator's database or system logs. The amount of data recorded at each moment can be determined by querying user-related event logs, network packet statistics, etc.; other methods may also be used, which will not be limited or elaborated here.

[0078] It should be noted that the greater the extent of data loss, the more problematic the operator's data storage is. Relying on data stored by the operator for user risk assessment may lead to inaccurate results and increased financial risk. This is because data loss means that certain user behavior, transaction, or location data were not stored or transmitted to the system. This directly results in missing information, affecting the assessment of the user's complete behavior and financial situation. Missing data may include key transaction information, high-risk behavior records, etc., all of which are necessary for accurate risk assessment. Risk control systems typically rely on comprehensive and accurate data to build user risk profiles. Data loss leads to a lack of user behavior analysis, making it impossible to fully understand the user's risk characteristics. Risk assessments based on incomplete data often underestimate or overestimate actual risks, resulting in inaccurate assessment results.

[0079] In one feasible implementation, steps B11 to B14 may be included before step S10:

[0080] Step B11: Obtain the amount of tampered data, the total amount of data in the interval, the number of times data was tampered, and the total number of data detected for each sub-interval of the target time interval;

[0081] It should be noted that the amount of tampered data refers to the amount of user data originally stored that has been altered through external attacks or other means not through legitimate channels. Specifically, the amount of tampered data can be detected through data integrity checks and audit logs. The system typically records detailed information for each data tampering event, including the specific data entries or records that were tampered with. By comparing the original and modified versions of the data, the number of tampered records can be calculated. The total data volume for a given interval can be obtained from the operator's data storage system. The system usually provides the total data volume for each sub-interval, including both original and processed data. The number of data tampering incidents can be obtained from the risk control system's logs or detection reports. The system typically records the data tampering events detected in each detection, including the detection time and results. The total number of data detections can be obtained from the risk control system, including statistics on all data detections performed, including all data verification and integrity checks, regardless of whether tampering was detected.

[0082] Step B12: Obtain the tampering quantity coefficient based on the amount of tampered data and the total amount of data in the interval;

[0083] It is understandable that the tampering quantity coefficient refers to the proportion of the total amount of data that has been tampered with within a specific time period.

[0084] In practice, the number of tampered data items in the data about the target user stored by the operator within each sub-interval is obtained, and the number of tampered data items is divided by the corresponding total number of data items to obtain the tampering quantity coefficient TG. The calculation formula is: TG = ed / v, where ed and v are the number of tampered data items and the total number of data items, respectively.

[0085] It should be noted that the total number of data points refers to the total number of target users stored by the operator within each sub-interval, and is not equivalent to the actual data volume G mentioned above. 实 l Because of G mentioned above 实 l The total number of data points represents the amount of data at each time step within each sub-interval; while the total number of data points encompasses all time steps within an interval, which can be expressed as...

[0086] Step B13: Obtain the tampering frequency coefficient based on the number of data tamperings and the total number of data detections;

[0087] Understandably, the tampering frequency coefficient refers to the proportion of the number of times data was tampered with within a specific time period to the total number of operations.

[0088] In practice, the number of times data tampering is detected in the data about the target user stored by the operator in each sub-interval is obtained, and the number of data tampering is divided by the total number of detections to obtain the tampering coefficient WD. The calculation formula is: WD = qa / qz, where qa and qz are the number of data tampering detected and the total number of detections, respectively.

[0089] Step B14: Determine the data tampering coefficient based on the tampering quantity coefficient, the tampering frequency coefficient, the preset tampering impact level, and the preset importance coefficient.

[0090] In practical implementation, the data tampering coefficient is obtained based on the tampering quantity coefficient TG, the tampering frequency coefficient WD, the preset tampering impact level HN, and the preset impact level importance coefficient λ. The calculation formula is as follows:

[0091] Bak=b1×TG+b2×WD+b3×(1-e -λ×HN )

[0092] In the formula, Bak is the data tampering coefficient, and b1, b2, and b3 are preset weight coefficients, all of which are greater than 0. b1, b2, and b3 are set by professionals based on actual conditions. Generally, the sum of b1, b2, and b3 is 1. For example, b1, b2, and b3 can be 0.4, 0.3, and 0.3 respectively, or other numbers; there are no specific limitations.

[0093] It should be noted that the importance coefficient λ of the preset impact level refers to the parameter that controls the contribution of the tampering impact level to the data tampering coefficient. It determines the non-linear impact of the tampering impact level. The larger the value, the more significant the contribution of the impact level to the final coefficient. The common value range is usually between 0.1 and 1.0. The specific value is adjusted by professionals according to the actual system requirements and sensitivity, and will not be limited or elaborated. The preset tampering impact level HN is an indicator used to quantify the potential impact of data tampering. It is usually determined based on the type of tampered data, its sensitivity, and the possible consequences. The value range of the impact level is generally between 1 and 10, where 1 represents the minimum impact and 10 represents the maximum impact. Through this level, the system can more accurately reflect the severity of high-risk tampering events. The specific value is adjusted by professionals according to the actual situation, and will not be limited or elaborated. In summary, λ is used to adjust the weight of the tampering impact level, and the impact level quantifies the degree of risk of tampering. The combination of the two allows the calculation of the data tampering coefficient to better reflect the actual threat of tampering.

[0094] It should be noted that a higher data tampering coefficient indicates a problem with the operator's data storage. Relying on the operator's stored data for user risk assessment may lead to inaccurate risk assessments and increase financial risk. This is because a higher data tampering coefficient indicates a greater proportion and frequency of data tampering. This means the operator's data no longer accurately reflects the user's true behavior or status. Financial risk control systems rely on accurate data to identify risks; therefore, data tampering directly affects the accuracy of risk assessments. These systems assess user risk based on data stored by operators. If this data is tampered with, the system's assessment criteria will be biased, leading to incorrect risk judgments. For example, tampering may conceal genuine risk behavior or fabricate false risk data, making the system's risk assessment of users inaccurate. A high data tampering coefficient may cause the risk control system to misclassify normal users as high-risk users or miss actual high-risk users. Since tampered data may hide or falsify important information, this can lead financial institutions to make incorrect decisions in risk management, thereby increasing financial risk.

[0095] In one feasible implementation, steps C11 to C13 may be included before step S10:

[0096] Step C11: Obtain the number of target data updates and the total number of target data corresponding to each sub-interval of the target time interval;

[0097] It should be noted that the number of times the target data is updated refers to the actual number of times each piece of data about the target user stored by the operator in each sub-interval is updated, and the total number of target data refers to the total number of data.

[0098] Step C12: Filter the data based on the target data update count and the preset data update count to obtain the total number of filtered data.

[0099] It is understandable that the preset data update count refers to the minimum number of data updates set in advance, and is set by professionals according to the actual situation. There is no specific limitation. The total number of filtered data refers to the total number of data that is less than the preset minimum update count. The actual number of updates of each data about the target user stored by the operator can be obtained directly through the operator's system, or it can be done in other ways. There are no specific limitations or elaborations.

[0100] In practice, the number of times each piece of data about the target user stored by the operator is actually updated within each sub-interval is obtained and marked as R. 实 f f represents the exponent of the data points, f = 1, 2, 3, 4, ..., v, where v represents the total number of data points and v is a positive integer; R 实 fData that is less than the preset minimum number of updates is re-marked as Q. w w represents R 实 f The sequential numbering of data items less than the preset minimum update count, w = 1, 2, 3, 4, ..., m, where m represents R. 实 f The total number of data items less than the preset minimum number of updates, where m is a positive integer.

[0101] Step C13: Determine the data update delay coefficient based on the total number of target data and the total number of filtered data.

[0102] In practice, the data update delay coefficient BC is calculated using the formula: BC = ln(m / v + 1).

[0103] It should be noted that a higher data update delay coefficient indicates a problem with the operator's data storage. Relying on the operator's stored data for user risk assessment may lead to inaccurate final risk assessments, increasing financial risk. The reason is as follows:

[0104] Delays lead to inaccurate risk information: Failure to promptly reflect user behavior: Delayed data updates prevent financial risk control systems from obtaining the latest user behavior data in a timely manner. For example, abnormal user trading behavior may not be captured and analyzed in a timely manner, thus missing the optimal opportunity to identify potential risks.

[0105] Lagging data impacts judgment: Financial risk control systems rely on the latest data to assess a user's risk status. Delayed data updates can cause the system to make decisions based on outdated information, judgments that may no longer be applicable to current circumstances, thus increasing the risk of incorrect assessments.

[0106] Data lag effect: When data updates are delayed, the system may receive an outdated snapshot, failing to accurately reflect a user's current financial situation or behavioral patterns. This lag effect can lead to misjudgments of a user's actual risk level, impacting the effectiveness of risk control strategies.

[0107] High proportion of delayed data: A high proportion of delayed data means that a large amount of information in the system is not being updated in a timely manner, which may negatively impact risk assessment. Even if some data is not delayed, the overall assessment may be inaccurate due to the presence of some delayed data.

[0108] Delayed processing: Risk assessment relies on the real-time nature of data. If the system makes decisions based on delayed data, the response time for risk control measures may also be prolonged. For example, if there is a significant delay in data updates after a risk is detected, it may be too late to take timely action.

[0109] Delayed Early Warning: In financial risk management, a timely early warning system is crucial. If data updates are delayed, the risk control system may fail to issue alerts in a timely manner, thus missing the best opportunity to address potential risks.

[0110] Therefore, a higher data update latency coefficient indicates a more severe data update delay problem, suggesting that the risk control system may be basing risk assessments on outdated or incomplete information. This leads to inaccurate risk assessment results and increases financial risk. To effectively manage risk, it is necessary to ensure timely data updates to guarantee the accuracy and responsiveness of the risk control system.

[0111] Step S20: Establish an abnormal coefficient set based on the unavailability coefficients of each sub-interval, and determine the target standard deviation value corresponding to the abnormal coefficient set;

[0112] It is understandable that the set of outlier coefficients refers to the set of all outlier coefficients in the set of unavailable coefficients, and the target standard deviation refers to the standard deviation of several outlier coefficients in the set of outlier coefficients.

[0113] In practice, an unavailable coefficient set is established based on the unavailable coefficients in all sub-intervals, and all abnormal coefficients in the unavailable coefficient set are selected to establish an abnormal coefficient set. The standard deviation of several abnormal coefficients in the dataset is then calculated to obtain the target standard deviation value.

[0114] In one feasible implementation, step S20 may include steps A21 to A23:

[0115] Step A21: Establish a set of unavailability coefficients based on the unavailability coefficients of each sub-interval;

[0116] It is understandable that the set of unavailable coefficients refers to the set of unavailable coefficients within all sub-intervals.

[0117] In practice, unusable coefficients in all sub-intervals are summarized and a set of unusable coefficients is established.

[0118] Step A22: Filter the unusable coefficient set according to a preset unusable coefficient threshold to obtain multiple abnormal coefficients;

[0119] It is understandable that the preset unavailability coefficient threshold refers to a pre-set reference threshold used to determine whether the unavailability coefficient is abnormal data. The preset unavailability coefficient threshold is set by professionals according to the actual situation, and the details will not be elaborated further. The abnormal coefficient refers to the unavailability coefficient that is less than the preset unavailability coefficient reference threshold.

[0120] In practice, each unusable coefficient in the unusable coefficient set is compared with a pre-set reference threshold for determining whether an unusable coefficient is abnormal data. When an unusable coefficient is not less than the preset unusable coefficient reference threshold, the unusable coefficient is marked as an abnormal coefficient, thus obtaining multiple abnormal coefficients.

[0121] Step A23: Establish an abnormal coefficient set based on multiple abnormal coefficients, and determine the target standard deviation corresponding to the abnormal coefficient set.

[0122] In practice, all the obtained abnormal coefficients are summarized and an abnormal coefficient set is established. Then, the standard deviation of several abnormal coefficients in the abnormal coefficient set is calculated to obtain the target standard deviation value.

[0123] It should be noted that an unavailability coefficient set is established based on the unavailability coefficients within all sub-intervals, and all abnormal coefficients in the unavailability coefficient set are filtered out. Specifically: when the unavailability coefficient is not less than a preset unavailability coefficient reference threshold, the unavailability coefficient is marked as an abnormal coefficient; when the unavailability coefficient is less than the preset unavailability coefficient reference threshold, the unavailability coefficient is marked as a normal coefficient. A dataset of several abnormal coefficients is established and labeled F, then F = {W} e}, where e = {1,2,3…g}, g is a positive integer; and calculate the standard deviation of several outlier coefficients in the dataset, and calibrate the standard deviation of several outlier coefficients in the dataset as rftg.

[0124] Step S30: Determine the target data status based on the target standard deviation and the preset standard deviation;

[0125] It is understandable that the preset standard deviation refers to the preset standard deviation threshold of the anomaly coefficient, which is used to determine the standard deviation threshold of whether the data about the target user stored by the operator is available. The target data status includes data availability status and data unavailability status.

[0126] In practice, the standard deviation of several abnormal coefficients in the abnormal coefficient set is compared with the standard deviation threshold used to determine whether the data about the target user stored by the operator is available, thereby determining whether the target data is in a data available state or a data unavailable state.

[0127] Step S40: When the target data status is data available, perform a risk assessment on the stored user data and determine the user's risk assessment result.

[0128] In practice, the user's risk assessment result refers to the result of the user's financial risk assessment. When the target data status is data available, it means that the data about the target user stored by the operator is available. Based on the data stored by the operator, the risk assessment of the user can be performed more accurately to assess the financial risk of the target user, thus obtaining the user's risk assessment result.

[0129] This embodiment obtains the unavailability coefficient of each sub-interval based on the data loss coefficient, data tampering coefficient, and data update delay coefficient corresponding to each sub-interval of the target time interval; establishes an anomaly coefficient set based on the unavailability coefficient of each sub-interval, and determines the target standard deviation corresponding to the anomaly coefficient set; determines the target data status based on the target standard deviation and a preset standard deviation; when the target data status is data available, performs a risk assessment on the stored user data, and determines the user's risk assessment result. By determining whether the data about the target user stored by the operator is available, and then performing a risk assessment on the stored user data, the final risk assessment of the target user is more accurate, reducing the impact of data storage problems of the operator on the risk assessment.

[0130] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 The risk assessment method further includes steps S31 to S33 in step S30:

[0131] Step S31: Compare the target standard deviation with the preset standard deviation to obtain the standard deviation comparison result;

[0132] It is understandable that the standard deviation comparison result refers to the comparison result between the target standard deviation value and the preset standard deviation value.

[0133] In practice, the standard deviations of several abnormal coefficients in the abnormal coefficient set are compared with the standard deviation threshold used to determine whether the data about the target user stored by the operator is usable. The result of the standard deviation comparison is either that the standard deviations of several abnormal coefficients in the abnormal coefficient set are greater than or equal to the standard deviation threshold used to determine whether the data about the target user stored by the operator is usable, or that the standard deviations of several abnormal coefficients in the abnormal coefficient set are less than the standard deviation threshold used to determine whether the data about the target user stored by the operator is usable.

[0134] Step S32: When the standard deviation comparison result shows that the target standard deviation is greater than or equal to the preset standard deviation, the target data status is determined to be unavailable, and a data unavailable alarm message is generated.

[0135] It is understandable that the data unavailability status refers to the state in which the data about the target user stored by the operator is unavailable, and the data unavailability alarm information refers to the alarm information used to remind staff that they cannot conduct financial risk assessment of the target customer based on the operator's data.

[0136] In practice, when the standard deviation of several abnormal coefficients in the abnormal coefficient set is greater than or equal to the standard deviation threshold used to determine whether the data about the target user stored by the operator is usable, it indicates that the data about the target user stored by the operator is unusable, that is, the target data status is unusable, and thus an alarm message is generated to remind staff that they cannot conduct financial risk assessment of the target customer based on the operator's data.

[0137] Step S33: When the standard deviation comparison result shows that the target standard deviation is less than the preset standard deviation, the target data status is determined to be a data usable status.

[0138] In practical implementation, the data availability status refers to the availability of the data about the target user stored by the operator. When the standard deviation comparison result shows that the standard deviation of several outlier coefficients in the outlier coefficient set is less than the standard deviation threshold used to determine whether the data about the target user stored by the operator is available, it indicates that the data about the target user stored by the operator is available, that is, the target data status is determined to be data availability status.

[0139] It should be noted that the standard deviation of the anomaly coefficient rftg is compared with the preset standard deviation threshold rftgh: if the standard deviation of the anomaly coefficient rftg is not less than the preset standard deviation threshold rftgh, it indicates that the data about the target user stored by the operator is unavailable, and an alarm signal is issued; if the standard deviation of the anomaly coefficient rftg is less than the preset standard deviation threshold rftgh, it indicates that the data about the target user stored by the operator is available, and no alarm signal is issued.

[0140] It should be noted that when an alarm signal is issued, it indicates that the data stored by the operator regarding the target user is unavailable. Relying on this stored data for risk assessment may lead to inaccurate results and increased financial risk. In this case, an alarm should be issued immediately to remind staff that financial risk assessments of the target customer cannot be conducted based on the operator's data; even if an assessment were performed, the results would be inaccurate. Conversely, when no alarm signal is issued, it indicates that the data stored by the operator regarding the target user is available. Using this data for risk assessment allows for a more accurate assessment of the target user's financial risk, thereby improving the precision and efficiency of risk control decisions and effectively reducing financial risk.

[0141] This embodiment compares the target standard deviation with a preset standard deviation to obtain a standard deviation comparison result. When the standard deviation comparison result shows that the target standard deviation is greater than or equal to the preset standard deviation, the target data status is determined to be unavailable, and a data unavailability alarm is generated. When the standard deviation comparison result shows that the target standard deviation is less than the preset standard deviation, the target data status is determined to be available. Through this method, the availability of user data stored by the operator is accurately determined, thereby improving the accuracy and efficiency of risk control decisions and effectively reducing financial risks.

[0142] For example, to help understand the implementation process of the risk assessment method obtained by combining this embodiment with the above embodiment one, please refer to... Figure 3 , Figure 3 A simplified flowchart of a risk assessment method is provided, specifically: The time period from the target user's data stored by the operator to the current time is obtained and used as the target time interval; the target time interval is divided into several sub-intervals according to a preset window; data loss information of the target user's data stored by the operator within each sub-interval is obtained, and a data loss coefficient is calculated based on the data loss information; data tampering information of the target user's data stored by the operator within each sub-interval is obtained, and a data tampering coefficient is calculated based on the data tampering information; data update information of the target user's data stored by the operator within each sub-interval is obtained, and a data update coefficient is calculated based on the data update information. The update information yields a data update delay coefficient; based on the data loss coefficient, data tampering coefficient, and data update delay coefficient within each sub-interval, the unavailability coefficient for that sub-interval is obtained; an unavailability coefficient set is established based on the unavailability coefficients of all sub-intervals, and all abnormal coefficients in the unavailability coefficient set are filtered out, and an abnormal set is established for all abnormal coefficients. The standard deviation in the abnormal set is calculated, and the standard deviation is compared with a preset standard deviation value. Based on the comparison result, it is determined whether the data about the target user stored by the operator is available. Finally, if it is determined that the data about the target user stored by the operator is available, a risk assessment is performed on the data of the target user.

[0143] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the risk assessment method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0144] This application also provides a risk assessment device, please refer to... Figure 4 The risk assessment device includes:

[0145] The processing module 10 is used to obtain the unavailability coefficient of each sub-interval based on the data loss coefficient, data tampering coefficient and data update delay coefficient corresponding to each sub-interval of the target time interval;

[0146] Module 20 is used to establish an abnormal coefficient set based on the unavailability coefficients of each sub-interval, and to determine the target standard deviation value corresponding to the abnormal coefficient set.

[0147] The processing module 10 is further configured to determine the target data status based on the target standard deviation and the preset standard deviation;

[0148] The assessment module 30 is used to perform a risk assessment on the stored user data when the target data status is a data available status, and to determine the user's risk assessment result.

[0149] Optionally, the processing module 10 is further configured to:

[0150] Obtain the current amount of stored data, the time period of data loss, and the amount of critical data loss for each sub-interval of the target time interval;

[0151] The data loss coefficient is obtained based on the current amount of stored data and the preset amount of stored data.

[0152] The data loss time coefficient is obtained based on the data loss time period and the preset loss time period.

[0153] The key data loss coefficient is obtained based on the key data loss amount and the total data loss amount.

[0154] The data loss coefficient is determined based on the data loss quantity coefficient, the data loss time coefficient, and the data key quantity loss coefficient.

[0155] Optionally, the processing module 10 is further configured to:

[0156] Obtain the amount of tampered data, the total amount of data in the interval, the number of times data was tampered, and the total number of data detected for each sub-interval of the target time interval;

[0157] The tampering quantity coefficient is obtained based on the amount of tampered data and the total amount of data in the interval.

[0158] The tampering frequency coefficient is obtained based on the number of data tamperings and the total number of data detections.

[0159] The data tampering coefficient is determined based on the tampering quantity coefficient, the tampering frequency coefficient, the preset tampering impact level, and the preset importance coefficient.

[0160] Optionally, the processing module 10 is further configured to:

[0161] Obtain the number of times the target data is updated and the total number of target data corresponding to each sub-interval of the target time interval;

[0162] Data is filtered based on the target data update count and the preset data update count to obtain the total number of filtered data.

[0163] The data update delay coefficient is determined based on the total number of target data and the total number of filtered data.

[0164] Optionally, the establishment module 20 is further configured to:

[0165] Establish a set of unavailability coefficients based on the unavailability coefficients of each sub-interval;

[0166] The unusable coefficient set is filtered according to a preset unusable coefficient threshold to obtain multiple abnormal coefficients;

[0167] An abnormal coefficient set is established based on multiple abnormal coefficients, and the target standard deviation corresponding to the abnormal coefficient set is determined.

[0168] Optionally, the processing module 10 is further configured to:

[0169] The target standard deviation is compared with the preset standard deviation to obtain the standard deviation comparison result;

[0170] When the standard deviation comparison result shows that the target standard deviation is greater than or equal to the preset standard deviation, the target data status is determined to be unavailable, and a data unavailable alarm message is generated.

[0171] When the standard deviation comparison result shows that the target standard deviation is less than the preset standard deviation, the target data status is determined to be a data usable status.

[0172] The risk assessment device provided in this application, employing the risk assessment method described in the above embodiments, can solve the technical problem of ensuring the accuracy of financial risk assessment when data storage problems occur in operators. Compared with the prior art, the beneficial effects of the risk assessment device provided in this application are the same as those of the risk assessment method provided in the above embodiments, and other technical features in the risk assessment device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0173] This application provides a risk assessment device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the risk assessment method in Embodiment 1 above.

[0174] The following is for reference. Figure 5The diagram illustrates a structural schematic of a risk assessment device suitable for implementing embodiments of this application. The risk assessment device in this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The risk assessment device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0175] like Figure 5 As shown, the risk assessment device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the risk assessment device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the risk assessment device to communicate wirelessly or wiredly with other devices to exchange data. While the figure shows a risk assessment device with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0176] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0177] The risk assessment device provided in this application, employing the risk assessment method described in the above embodiments, can solve the technical problem of ensuring the accuracy of financial risk assessment when data storage issues arise in operators. Compared with the prior art, the beneficial effects of the risk assessment device provided in this application are the same as those of the risk assessment method provided in the above embodiments, and other technical features of this risk assessment device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0178] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0179] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0180] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to perform the risk assessment method described in the above embodiments.

[0181] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0182] The aforementioned computer-readable storage medium may be included in the risk assessment device; or it may exist independently and not be assembled into the risk assessment device.

[0183] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by a risk assessment device, the risk assessment device: obtains the unavailability coefficient of each sub-interval based on the data loss coefficient, data tampering coefficient, and data update delay coefficient corresponding to each sub-interval of the target time interval; establishes an anomaly coefficient set based on the unavailability coefficient of each sub-interval, and determines the target standard deviation corresponding to the anomaly coefficient set; determines the target data status based on the target standard deviation and a preset standard deviation; and when the target data status is a data availability status, performs a risk assessment on the stored user data and determines the user's risk assessment result.

[0184] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0185] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0186] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0187] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described risk assessment method. This addresses the technical problem of ensuring the accuracy of financial risk assessment when data storage by operators encounters problems. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the risk assessment method provided in the above embodiments, and will not be elaborated upon here.

[0188] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the risk assessment method described above.

[0189] The computer program product provided in this application can solve the technical problem of ensuring the accuracy of financial risk assessment when data storage problems occur in operators. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the risk assessment method provided in the above embodiments, and will not be repeated here.

[0190] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A risk assessment method, characterized in that, The risk assessment methods include: The unavailability coefficient of each sub-interval is obtained based on the data loss coefficient, data tampering coefficient, and data update delay coefficient corresponding to each sub-interval of the target time interval; An abnormal coefficient set is established based on the unavailability coefficients of each sub-interval, and the target standard deviation corresponding to the abnormal coefficient set is determined. The target data status is determined based on the target standard deviation and the preset standard deviation; When the target data is in a data-available state, a risk assessment is performed on the stored user data to determine the user's risk assessment result.

2. The method as described in claim 1, characterized in that, Before the step of obtaining the unavailability coefficient of each sub-interval based on the data loss coefficient, data tampering coefficient, and data update delay coefficient corresponding to each sub-interval of the target time interval, the method further includes: Obtain the current amount of stored data, the time period of data loss, and the amount of critical data loss for each sub-interval of the target time interval; The data loss coefficient is obtained based on the current amount of stored data and the preset amount of stored data. The data loss time coefficient is obtained based on the data loss time period and the preset loss time period. The key data loss coefficient is obtained based on the key data loss amount and the total data loss amount. The data loss coefficient is determined based on the data loss quantity coefficient, the data loss time coefficient, and the data key quantity loss coefficient.

3. The method as described in claim 1, characterized in that, Before the step of obtaining the unavailability coefficient of each sub-interval based on the data loss coefficient, data tampering coefficient, and data update delay coefficient corresponding to each sub-interval of the target time interval, the method further includes: Obtain the amount of tampered data, the total amount of data in the interval, the number of times data was tampered, and the total number of data detected for each sub-interval of the target time interval; The tampering quantity coefficient is obtained based on the amount of tampered data and the total amount of data in the interval. The tampering frequency coefficient is obtained based on the number of data tamperings and the total number of data detections. The data tampering coefficient is determined based on the tampering quantity coefficient, the tampering frequency coefficient, the preset tampering impact level, and the preset importance coefficient.

4. The method as described in claim 1, characterized in that, Before the step of obtaining the unavailability coefficient of each sub-interval based on the data loss coefficient, data tampering coefficient, and data update delay coefficient corresponding to each sub-interval of the target time interval, the method further includes: Obtain the number of times the target data is updated and the total number of target data corresponding to each sub-interval of the target time interval; Data is filtered based on the target data update count and the preset data update count to obtain the total number of filtered data. The data update delay coefficient is determined based on the total number of target data and the total number of filtered data.

5. The method as described in claim 1, characterized in that, The step of establishing an anomaly coefficient set based on the unavailability coefficients of each sub-interval and determining the target standard deviation corresponding to the anomaly coefficient set includes: Establish a set of unavailability coefficients based on the unavailability coefficients of each sub-interval; The unusable coefficient set is filtered according to a preset unusable coefficient threshold to obtain multiple abnormal coefficients; An abnormal coefficient set is established based on multiple abnormal coefficients, and the target standard deviation corresponding to the abnormal coefficient set is determined.

6. The method according to any one of claims 1-5, characterized in that, The step of determining the target data state based on the target standard deviation and the preset standard deviation includes: The target standard deviation is compared with the preset standard deviation to obtain the standard deviation comparison result; When the standard deviation comparison result shows that the target standard deviation is greater than or equal to the preset standard deviation, the target data status is determined to be unavailable, and a data unavailable alarm message is generated. When the standard deviation comparison result shows that the target standard deviation is less than the preset standard deviation, the target data status is determined to be a data usable status.

7. A risk assessment device, characterized in that, The device includes: The processing module is used to obtain the unavailability coefficient of each sub-interval based on the data loss coefficient, data tampering coefficient, and data update delay coefficient corresponding to each sub-interval of the target time interval; A module is established to build an abnormal coefficient set based on the unavailability coefficients of each sub-interval, and to determine the target standard deviation value corresponding to the abnormal coefficient set; The processing module is also used to determine the target data status based on the target standard deviation and the preset standard deviation; The assessment module is used to perform a risk assessment on the stored user data when the target data status is data available, and to determine the user's risk assessment result.

8. A risk assessment device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the risk assessment method as described in any one of claims 1 to 6.

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

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

Images