Artificial Intelligence-based Monitoring Method, System and Equipment for Automobile Financial Asset Data

Abstract

The present invention discloses an artificial intelligence-based method for monitoring automotive financial asset data, which relates to the technical field of data processing. The method includes: obtaining the automotive financial asset data to be uploaded based on an artificial intelligence terminal, and obtaining the importance degree of the automotive financial asset data; obtaining the upload path; uploading the automotive financial asset data according to the upload path, and monitoring the real-time data transfer time of each adjacent data transfer node; obtaining the monitoring degree based on the monitoring model, the importance degree, and the number of data transfer nodes, and obtaining the target number according to the monitoring degree; extracting the target number of real-time data transfer times from multiple real-time data transfer times, and determining whether the extracted real-time data transfer times exceed the corresponding time thresholds; if not, processing the automotive financial asset data; if so, re-uploading the automotive financial asset data. The present invention has the advantages of ensuring timely data upload, good monitoring effect, and resource saving.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a method, system and device for monitoring automotive financial asset data based on artificial intelligence. Background Art

[0002] Automotive financial assets not only involve traditional auto loans, but also include various financial services such as auto finance leases, auto insurance, and related derivatives. A large amount of data is generated during the operation of these services, including but not limited to borrower information, vehicle information, loan or lease status, repayment records, insurance claim records, etc. These data are crucial for financial institutions in aspects such as risk control, business decision-making, customer service, and compliance management. Therefore, it is necessary to monitor the transmission of automotive financial asset data to ensure data integrity and confidentiality. Once the data is leaked or tampered with, it will cause serious losses to financial institutions and customers.

[0003] Currently, in order to ensure the integrity and security of automotive financial asset data during upload, existing data monitoring methods perform data verification at each data transfer node during the transmission process, conduct encryption and decryption verification during data transmission, and also widely use data caching and preprocessing technologies.

[0004] However, checking data at each data transfer node not only increases the processing time, but may also cause congestion when data flows between nodes, thereby prolonging the data transfer time and seriously affecting data real-time performance. At the same time, the encryption and decryption processes themselves consume a large amount of computing resources, further increasing the complexity and latency of data monitoring. In the field of automotive financial assets with a large amount of data, this encryption and decryption verification mechanism may become a bottleneck for data transmission, resulting in a significant extension of the data transfer time. Finally, data caching may lead to a decrease in data accuracy due to the timeliness of cached data, while preprocessing technologies introduce additional errors due to imperfect preprocessing logic. These problems may have an adverse impact on data real-time performance and accuracy. In summary, existing data monitoring methods lead to a reduction in the upload efficiency of automotive financial asset data and an increase in further processing latency, making it difficult to meet the requirements of real-time decision-making. Summary of the Invention

[0005] Aiming at the deficiencies in the prior art, the present invention provides a method, system and device for monitoring automotive financial asset data based on artificial intelligence, effectively solving the problems of low efficiency, large latency, and poor security existing in the upload process of existing automotive financial asset data, and providing more efficient, accurate and reliable data support for financial business decision-making.

[0006] An artificial intelligence-based method for monitoring automotive financial asset data, comprising: obtaining automotive financial asset data to be uploaded based on an artificial intelligence terminal, and obtaining the importance level of the automotive financial asset data; obtaining an upload path, where the upload path includes multiple data transfer nodes; uploading the automotive financial asset data according to the upload path, and monitoring the real-time data transfer time of each adjacent data transfer node; obtaining a monitoring degree based on a monitoring model, the importance level, and the number of data transfer nodes, and obtaining a target number according to the monitoring degree; randomly extracting a target number of real-time data transfer times from multiple real-time data transfer times, and determining whether each extracted real-time data transfer time exceeds the corresponding time threshold; if not, processing the automotive financial asset data; if so, re-uploading the automotive financial asset data.

[0007] Preferably, the monitoring model in obtaining the monitoring degree based on the monitoring model, the importance level, and the number of data transfer nodes is expressed as: where M is the monitoring degree, α and β are adjustment parameters, I is the importance level of the automotive financial asset data, and N tr is the number of data transfer nodes.

[0008] Preferably, obtaining the target number according to the monitoring degree includes: obtaining a monitoring threshold; if the monitoring degree does not exceed the monitoring threshold, the target number is 1; if the monitoring degree exceeds the monitoring threshold, obtaining a proportionality coefficient according to the monitoring degree and the monitoring threshold, and obtaining the target number based on a target model, the proportionality coefficient, and the number of data transfer nodes.

[0009] Preferably, obtaining the proportionality coefficient according to the monitoring degree and the monitoring threshold is expressed as: where P is the proportionality coefficient, MI is the monitoring degree, and MT is the monitoring threshold.

[0010] Preferably, the target model in obtaining the target number based on the target model, the proportionality coefficient, and the number of data transfer nodes is expressed as: N ta = N tr ·P; where N ta is the target number, and N tr is the number of data transfer nodes.

[0011] Preferably, determining whether each extracted real-time data transfer time exceeds the corresponding time threshold includes: obtaining the upstream node and the downstream node corresponding to the extracted real-time data transfer time; obtaining the theoretical data transfer time according to the upstream node and the downstream node; obtaining the time threshold according to the theoretical data transfer time, and determining whether the real-time data transfer time exceeds the time threshold.

[0012] Preferably, the importance of obtaining automotive financial asset data includes: the data source and data size of the automotive financial asset data; obtaining a comprehensive score based on the data source and data size; and obtaining the importance of the automotive financial asset data based on the comprehensive score.

[0013] There is also provided an automotive financial asset data monitoring system based on artificial intelligence. The system includes: a first acquisition module for acquiring the automotive financial asset data to be uploaded based on an artificial intelligence terminal and obtaining the importance of the automotive financial asset data; a second acquisition module for obtaining an upload path, where the upload path includes multiple data transfer nodes; a data monitoring module for uploading the automotive financial asset data according to the upload path and monitoring the real-time data transfer time of each adjacent data transfer node; a model calculation module for obtaining a monitoring degree based on a monitoring model, the importance, and the number of data transfer nodes, and obtaining a target number based on the monitoring degree; an extraction and judgment module for randomly extracting the target number of real-time data transfer times from multiple real-time data transfer times and judging whether each extracted real-time data transfer time exceeds the corresponding time threshold; a first control module for processing the automotive financial asset data when the extracted real-time data transfer time does not exceed the corresponding time threshold; and a second control module for re-uploading the automotive financial asset data when the extracted real-time data transfer time exceeds the corresponding time threshold.

[0014] There is also provided an electronic device, including: a memory storing a computer program thereon; a processor for executing the computer program in the memory to implement the above-mentioned automotive financial asset data monitoring method based on artificial intelligence.

[0015] There is also provided a non-transitory computer-readable storage medium storing a computer program thereon, and the program, when executed by a processor, implements the above-mentioned automotive financial asset data monitoring method based on artificial intelligence.

[0016] The beneficial effects of the present invention are reflected in:

[0017] In the entire artificial intelligence-based automotive financial asset data monitoring method, an artificial intelligence terminal is introduced to obtain the automotive financial asset data to be uploaded, and the importance of the data is evaluated, providing strong support for subsequent monitoring and processing. At the same time, in coordination with subsequent monitoring and processing, the monitoring strategy is dynamically adjusted, thereby more reasonably allocating resources to ensure that important data can be more strictly monitored and protected. Further, by dynamically adjusting the monitoring degree and randomly sampling to check the real-time transfer time of the data, efficient monitoring of the data transmission process is achieved. Compared with the traditional method of performing data verification and encryption / decryption verification at each transit node, this monitoring method not only reduces the consumption of processing time and computing resources, but also can more accurately detect abnormalities and bottlenecks in the data transmission process. More importantly, it will not affect the real-time nature of the data, ensuring the timely upload and processing of the data. Further, when an abnormality is found in the data transmission process, the system will trigger a mechanism to re-upload the data and attempt to analyze the possible reasons and take corresponding measures to solve the problem. This mechanism can not only ensure the integrity and accuracy of the data, but also improve the fault tolerance and stability of the system, providing more reliable data support for the business decisions of financial institutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0019] Figure 1 It is a schematic diagram of the steps of the artificial intelligence-based automotive financial asset data monitoring method of the present invention;

[0020] Figure 2 It is a partial schematic diagram of step S4 in the artificial intelligence-based automotive financial asset data monitoring method of the present invention;

[0021] Figure 3 It is a partial schematic diagram of step S5 in the artificial intelligence-based automotive financial asset data monitoring method of the present invention;

[0022] Figure 4 It is a partial schematic diagram of step S1 in the artificial intelligence-based automotive financial asset data monitoring method of the present invention;

[0023] Figure 5 It is a block diagram of an electronic device shown in an embodiment of the present invention.

[0024] Reference Numerals:

[0025] 700 - Electronic device, 701 - Processor, 702 - Memory, 703 - Multimedia component, 704 - Input / Output (I / O) interface, 705 - Communication component. Detailed implementation

[0026] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and illustrated herein can be arranged and designed in various different configurations.

[0027] Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0028] It should be noted that: similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. In addition, the terms "first", "second", etc. are only used for descriptive distinction and cannot be understood as indicating or implying relative importance.

[0029] As Figure 1 shown, a method for monitoring automotive financial asset data based on artificial intelligence is provided, including:

[0030] S1. Obtain the automotive financial asset data to be uploaded based on an artificial intelligence terminal, and obtain the importance of the automotive financial asset data;

[0031] S2. Obtain an upload path, where the upload path includes multiple data transfer nodes;

[0032] S3. Upload the automotive financial asset data according to the upload path, and monitor the real-time data transfer time of each adjacent data transfer node;

[0033] S4. Obtain a monitoring degree based on the monitoring model, importance, and the number of data transfer nodes, and obtain a target number according to the monitoring degree;

[0034] S5. Randomly extract the target number of real-time data transfer times from multiple real-time data transfer times, and determine whether each extracted real-time data transfer time exceeds the corresponding time threshold;

[0035] S6. If not, process the automotive financial asset data;

[0036] S7. If it exceeds, re-upload the automotive financial asset data.

[0037] In this embodiment, it should be noted that in S1, an artificial intelligence terminal is used to obtain the automotive financial asset data to be uploaded. These intelligent terminals can be servers or dedicated devices equipped with high-performance computing capabilities and artificial intelligence algorithms, capable of efficiently obtaining a large amount of data. Then, while obtaining the data, the importance of each piece of automotive financial asset data is obtained according to preset rules and algorithms. The importance is an indicator that measures the value and priority of the data, and it can be comprehensively evaluated based on multiple dimensions such as the type, source, content, and business requirements of the data; for example, for automotive loan business, data such as the borrower's credit record, repayment history, and vehicle information has a relatively high importance because these data are directly related to the risk control and business decisions of financial institutions; the importance of customer consultation records, market analysis reports, etc. may be relatively low; each piece of automotive financial asset data has an importance, providing strong support for subsequent data monitoring.

[0038] In S2, first analyze the current network environment, including key parameters such as the locations, connection status, bandwidth, and latency of each data transfer node, and select a path with low latency and high bandwidth to ensure that this data can reach the destination faster and more stably; at the same time, the redundancy and fault tolerance capabilities of the network are also considered to avoid the failure of the entire data transmission process due to the failure of a single node.

[0039] In S3, according to the upload path determined in step S2, start uploading the automotive financial asset data and real-time monitor the real-time data transfer time between each adjacent data transfer node. Specifically, by precisely measuring the data transfer time for each data transfer node, including the arrival time and sending time of the data at each node, the monitoring results of these data transfer times are recorded, providing an important basis for subsequent monitoring and processing.

[0040] Suppose the automotive financial data needs to be uploaded from location A to the server at location E through three data transfer nodes B, C, and D. During the upload process, the data transfer times between the four adjacent nodes A to B, B to C, C to D, and D to E are monitored respectively.

[0041] In S4, by introducing a monitoring model, following certain rules or algorithms, and dynamically adjusting the monitoring degree according to the importance and the number of data transfer nodes, the setting of the monitoring degree is directly related to the monitoring requirements during the data transmission process. Finally, the target quantity is obtained based on the monitoring degree, that is, the number of real-time data transfer time samples that need to be extracted. First of all, the importance of data has a direct impact on the monitoring degree. The greater the importance, the higher the value of these data for business decision-making and risk control. Therefore, the requirements for the data transmission process are more stringent. To ensure that these data can reach the destination safely and accurately, the obtained monitoring degree is greater, and the target quantity obtained according to the monitoring degree is also greater. Secondly, the number of data transfer nodes is also an important factor affecting the monitoring degree. During the data transmission process, every time the data passes through a data transfer node, the risk of data error or loss will increase. Therefore, when the number of data transfer nodes is larger, the probability of problems occurring during the data transmission process is greater. To reduce this risk, the obtained monitoring degree is greater, and the target quantity obtained according to the monitoring degree is also greater.

[0042] Suppose there is a batch of auto finance asset data that needs to be uploaded to a remote server. The importance of this batch of data is very high because they are directly related to the risk control and business decision-making of financial institutions. At the same time, due to the complex network environment, the data needs to pass through multiple data transfer nodes to reach the destination. In this case, according to the importance of the data and the number of data transfer nodes, a relatively large monitoring degree is obtained, and then the target quantity that needs to be extracted from multiple data transfer nodes is obtained based on this monitoring degree.

[0043] In S5, according to the determined target quantity, the corresponding number of samples is randomly selected from the multiple real-time data transfer times that have been monitored and recorded. This is a retrospective detection and analysis of the upload process after the data has been uploaded to the destination to ensure that the monitoring process does not affect the real-time nature of the data. The purpose of this step is to infer the efficiency and stability of the overall data transmission process by checking the transfer times of some data, and then to evaluate whether there is a risk of data being tampered with. Specifically, the method of random sampling is used to ensure that the probability of each real-time data transfer time being selected is equal, so as to avoid biases or misguidance caused by improper sample selection. After extracting the target quantity of real-time data transfer times, each of these samples is checked to see if it exceeds the corresponding time threshold. The time threshold is a preset standard value considering the actual network environment of the data transfer nodes and other influences, and it reflects the maximum time allowed for the data to transfer between each adjacent transfer node.

[0044] Suppose the determined number of targets is 4, and the total real-time transfer time of the monitored and recorded data is 20. In S5, 4 samples will be randomly selected from these 20 real-time data transfer times for inspection. If the transfer time of a certain sample exceeds the preset time threshold of 500 milliseconds, it is considered that there may be problems during the data transfer process, such as network congestion, node failure, etc. In summary, by uploading the analysis of the data transfer time record, the bottlenecks and anomalies in the data transmission process can be identified more efficiently, without the need for multiple verifications during the transmission process, thus reducing the burden and ensuring the real-time nature of the data. Further, by randomly sampling and inspecting the real-time data transfer time, the possible problems and risk points in the data transmission process can be efficiently discovered, without the need to check each data transfer time, thus greatly improving the efficiency of monitoring.

[0045] In S6, if it is determined that the real-time transfer times of the randomly selected data do not exceed the corresponding time thresholds, it is considered that the entire data transmission process has met the expected standards in terms of efficiency and stability, and there is no abnormal transmission process. At this time, continue with the subsequent processing process for the automotive financial asset data that has been uploaded to the destination. The subsequent data processing includes, but is not limited to, data cleaning, data verification, data integration, and data warehousing, etc., for subsequent business analysis and decision-making.

[0046] In S7, if there is a situation where the real-time transfer time of the randomly selected data exceeds the corresponding time threshold, it is determined that there may be an abnormality in the data transmission process. At this time, trigger the mechanism to re-upload the automotive financial asset data to ensure the integrity of the data.

[0047] At the same time, when it is found that the real-time transfer time of a certain data exceeds the time threshold, this abnormal event will be recorded, and an attempt will be made to analyze the possible reasons, such as network congestion, node failure, unreasonable data transmission path, etc. Then, corresponding measures will be taken according to the analysis results to solve the problem. If the problem is caused by network congestion or node failure, wait for a period of time and then re-upload the data, or try to change to other available data transmission paths. If the problem is caused by an unreasonable data transmission path, recalculate and select a better path to upload the data.

[0048] In summary, in the entire AI-based automotive finance asset data monitoring method, an AI terminal is introduced to obtain the automotive finance asset data to be uploaded and evaluate the importance of the data, providing strong support for subsequent monitoring and processing. At the same time, it cooperates with subsequent monitoring and processing to dynamically adjust the monitoring strategy, thereby more reasonably allocating resources to ensure that important data can be more strictly monitored and protected. Further, by dynamically adjusting the monitoring degree and randomly sampling to check the real-time transfer time of the data, efficient monitoring of the data transmission process is achieved. Compared with the traditional method of performing data verification and encryption / decryption verification at each transfer node, this monitoring method not only reduces the consumption of processing time and computing resources, but also can more accurately detect anomalies and bottlenecks in the data transmission process. More importantly, it will not affect the real-time nature of the data, ensuring the timely upload and processing of the data. Further, when an anomaly is found in the data transmission process, a mechanism to re-upload the data is triggered, and an attempt is made to analyze the possible causes and take corresponding measures to solve the problem. This mechanism can not only ensure the integrity and accuracy of the data, but also improve the fault tolerance and stability, providing more reliable data support for the business decisions of financial institutions.

[0049] In one embodiment, the monitoring model in the monitoring degree obtained based on the monitoring model, importance, and the number of data transfer nodes is expressed as:

[0050] Where,

[0051] M is the monitoring degree, α and β are adjustment parameters, I is the importance of the automotive finance asset data, and N tr is the number of data transfer nodes.

[0052] In this embodiment, it should be noted that the design of this monitoring model aims to dynamically adjust the monitoring degree according to the importance of the data and the number of data transfer nodes to achieve more accurate and stable data monitoring. In ln(αxN tr +β), when the importance I or the number of data transfer nodes N tr is small, the change of the monitoring degree M is very sensitive, and the monitoring degree can be adjusted quickly to adapt to different situations. When I or N tr increases to a certain extent, the increase of the monitoring degree will gradually slow down to avoid waste of resources caused by over-monitoring. By adjusting the two parameters α and β, the shape and position of ln(αxN tr +β) can be flexibly controlled, so as to achieve fine adjustment of the monitoring degree. The requirements and demands for data monitoring in different business scenarios are different. Therefore, when obtaining the values of α and β, it is necessary to fully consider the characteristics and requirements of the business scenario, and the initial values of α and β can also be set based on historical record information or other professional knowledge according to the monitoring effect of historical projects. Among them, considering the cumulative impact of the data importance on the calculated monitoring degree within the entire range of x from 0 to I, this means that when calculating the monitoring degree, not only the current data importance is considered, but also the cumulative effect of all previous importances is considered. At the same time, by comprehensively considering various factors such as I, N tr , α and β and calculating their cumulative effects, the model can more accurately reflect the actual situation, and the smoothness of the monitoring model enables the monitoring degree to smoothly transition with the change of data importance, improving the continuity and stability of the monitoring degree.

[0053] As Figure 2 shown, in one embodiment, obtaining the target quantity according to the monitoring degree in S4 includes:

[0054] S41. Obtain a monitoring threshold;

[0055] S42. If the monitoring degree does not exceed the monitoring threshold, the target quantity is 1;

[0056] S43. If the monitoring degree exceeds the monitoring threshold, obtain a proportionality coefficient according to the monitoring degree and the monitoring threshold, and obtain the target quantity based on the target model, the proportionality coefficient, and the number of data transfer nodes.

[0057] In this embodiment, it should be noted that in S41, first, a monitoring threshold needs to be determined. This monitoring threshold is a preset boundary used to judge which range the current data monitoring degree is in, and then determine subsequent processing measures. The setting of the monitoring threshold is usually based on a comprehensive consideration of multiple factors such as historical data, business requirements, security standards, and system performance. For example, based on past experience, when the number of data transfer nodes reaches a certain level, the probability of data loss and tampering is relatively high, and when the importance reaches a certain level, data loss and tampering will have a significant impact on the business. At this time, a corresponding monitoring threshold needs to be set to trigger additional monitoring measures. Finally, this monitoring threshold can be obtained through a configuration file, a database, or real-time monitoring data and used as the basis for subsequent judgments.

[0058] S42. If the monitoring degree does not exceed this threshold, it means that the current data transmission state is stable and has not reached the level that requires special attention or additional measures. Therefore, in this case, the target quantity is set to 1, which means that only the simplest monitoring measures need to be maintained without adding additional monitoring resources. This setting helps to reduce unnecessary resource waste and ensure that the normal operation of the business will not be overly interfered with when the data status is good.

[0059] S43. If the monitoring degree exceeds the preset monitoring threshold, it indicates that there may be problems with the current data transmission status, and more stringent monitoring measures need to be taken to ensure the security and stability of the data. In this case, first calculate a proportionality coefficient based on the difference between the monitoring degree and the monitoring threshold. This proportionality coefficient reflects the degree to which the monitoring degree exceeds the threshold and the urgency of increasing monitoring resources. Then, using a pre-established target model, combine this proportionality coefficient and the number of data transfer nodes to calculate a reasonable target number. This target number represents the amount of monitoring resources that need to be invested in order to ensure the secure and stable transmission of data under the current circumstances. In this way, the monitoring strategy can be dynamically adjusted to cope with different data transmission statuses and risk levels.

[0060] In one implementation, the obtaining of the proportionality coefficient according to the monitoring degree and the monitoring threshold in S43 is expressed as:

[0061] Among them,

[0062] P is the proportionality coefficient, MI is the monitoring degree, and MT is the monitoring threshold.

[0063] In this implementation, it should be noted that P is a value between 0 and 1, which is used to represent the relative degree to which the monitoring degree exceeds the monitoring threshold. When MI approaches MT, P is smaller, indicating that no additional monitoring resources are required for the monitoring degree; when MI is much larger than MT, P approaches 1, indicating that the monitoring degree far exceeds the threshold and a large amount of monitoring resources need to be increased. By calculating the proportionality coefficient P, the allocation of monitoring resources can be dynamically adjusted according to the real-time relationship between the monitoring degree and the monitoring threshold. This helps to prioritize the data transmission processes with higher monitoring degrees and greater risks under limited resources; further, it can avoid wasting monitoring resources when the monitoring degree is low or insufficient monitoring resources are invested when the monitoring degree is high, thereby improving the efficiency and accuracy of monitoring.

[0064] In one implementation, the target model in obtaining the target number based on the target model, the proportionality coefficient, and the number of data transfer nodes in S43 is expressed as:

[0065] N ta = N tr ·P; among them,

[0066] N ta is the target number, and N tt is the number of data transfer nodes.

[0067] In this implementation, it should be noted that N tris the total number of intermediate nodes involved in the data transmission process. The more intermediate nodes there are, the higher the complexity and risk of data transmission, and thus more monitoring resources may be required; P is a coefficient calculated based on the monitoring degree and the monitoring threshold, used to quantify the degree to which the monitoring degree exceeds the monitoring threshold. The larger the value of P, the higher the degree to which the monitoring degree exceeds the threshold, and thus more monitoring resources need to be invested. By combining the number of data intermediate nodes and the proportional coefficient, the target model can dynamically calculate the amount of monitoring resources to be invested, which ensures that the monitoring resources can be reasonably allocated according to the actual situation and risk level of data transmission; further, by accurately calculating the target quantity, waste of monitoring resources can be avoided. In the case of a lower monitoring degree or fewer data intermediate nodes, the investment in monitoring resources can be correspondingly reduced, thereby optimizing the utilization efficiency of resources.

[0068] As Figure 3 shown, in one embodiment, in S5, determining whether the real-time transfer time of each extracted data exceeds the corresponding time threshold includes:

[0069] S51. Obtain the upstream node and downstream node corresponding to the real-time transfer time of the extracted data;

[0070] S52. Obtain the theoretical transfer time of the data according to the upstream node and downstream node;

[0071] S53. Obtain the time threshold according to the theoretical transfer time of the data, and determine whether the real-time transfer time of the data exceeds the time threshold.

[0072] In this embodiment, it should be noted that in S51, first identify and obtain the upstream node and downstream node related to the real-time transfer time of the extracted data. The upstream node refers to the previous node in the data transfer process, which is responsible for sending the data to the downstream node; while the downstream node refers to the next node in the data transfer process, which is responsible for receiving the data from the upstream node. By tracing the data transfer path, the upstream and downstream nodes corresponding to each real-time transfer time of the data can be determined.

[0073] In S52, after determining the upstream node and downstream node corresponding to the real-time transfer time of the data, next, the theoretical transfer time of the data will be calculated based on the information of these nodes. The theoretical transfer time of the data refers to the time required for the data to be transferred from the upstream node to the downstream node under ideal conditions. The calculation of this time may consider multiple factors, such as network bandwidth, node processing capacity, data transfer protocol, etc. The parameters of these factors may be obtained through historical data, performance testing or real-time monitoring, and combined with the configuration and status of the nodes to calculate the theoretical transfer time of the data. This time serves as the benchmark for subsequent judgment of whether the real-time transfer time of the data is reasonable.

[0074] In S53, after obtaining the theoretical transfer time of the data, a time threshold is determined based on this time. The time threshold is a tolerance range used to allow for minor delays in the actual transmission of data due to various reasons (such as network congestion, node load, etc.). This time threshold can be set according to business requirements, service quality requirements, or historical experience. After setting the time threshold, the real-time transfer time of the data is compared with this time threshold to determine whether the data has been transmitted within a reasonable time. If the real-time transfer time of the data exceeds the time threshold, an alarm will be triggered or other measures will be taken to diagnose and solve the problem to ensure the timely transmission and processing of the data.

[0075] As Figure 4 shown, in one embodiment, the importance of obtaining automotive finance asset data in S1 includes:

[0076] S11. Obtain the data source and data size of the automotive finance asset data;

[0077] S12. Obtain a comprehensive score based on the data source and data size;

[0078] S13. Obtain the importance of the automotive finance asset data based on the comprehensive score.

[0079] In this embodiment, it should be noted that in S11, first, it is necessary to identify and collect the data source and data size of the automotive finance asset data. The data source may include multiple channels, such as automobile manufacturers, financial institutions, third-party data providers, etc. The data from each source may have different reliability and importance. The data size reflects the amount of data, including the number of records, the number of fields, and the data volume of each field, etc. Information on these data sources and data sizes can be obtained based on an artificial intelligence terminal accessing storage and transmission data facilities such as databases, data warehouses, or real-time data streams. These information are the basis for subsequent evaluation of data importance.

[0080] In S12, a comprehensive score is calculated based on the information of the data source and data size. This comprehensive score is a quantitative indicator. Both the data source and the data size correspond to an indicator, reflecting their contribution degrees in the overall evaluation. By multiplying these indicators, the comprehensive score is calculated. Suppose there are two sources of automotive finance asset data, which are an automobile manufacturer and a financial institution respectively. The indicator corresponding to the automobile manufacturer is 0.6, the indicator corresponding to the financial institution is 0.7, and at the same time, the data size is a medium-sized data set (100MB - 1GB), and its corresponding indicator is 1.2. Then the comprehensive score = 0.7 * 1.2 + 0.6 * 1.2 = 1.56. This comprehensive score will be used as the main basis for judging the importance of the data.

[0081] S13. After calculating the comprehensive score, determine the importance of the auto finance asset data based on this score. By determining the importance of the data, different strategies and measures can be adopted according to the importance level of the data during subsequent data monitoring, storage, and transmission processes to ensure the secure, efficient, and reasonable utilization of the data. Among them, the comprehensive score can be directly recognized as the importance, or a series of amplification or reduction calculations can be performed.

[0082] There is also provided an auto finance asset data monitoring system based on artificial intelligence. The system is used to implement the auto finance asset data monitoring method based on artificial intelligence in any of the above embodiments. The system includes:

[0083] A first acquisition module, configured to acquire the auto finance asset data to be uploaded based on an artificial intelligence terminal and acquire the importance of the auto finance asset data;

[0084] A second acquisition module, configured to acquire an upload path, where the upload path includes multiple data transfer nodes;

[0085] A data monitoring module, configured to upload the auto finance asset data according to the upload path and monitor the real-time data transfer time of each adjacent data transfer node;

[0086] A model calculation module, configured to obtain a monitoring degree based on a monitoring model, the importance, and the number of data transfer nodes, and obtain a target number according to the monitoring degree;

[0087] An extraction and judgment module, configured to randomly extract the real-time data transfer time of the target number from multiple real-time data transfer times and judge whether each extracted real-time data transfer time exceeds the corresponding time threshold;

[0088] A first control module, configured to process the auto finance asset data when the extracted real-time data transfer time does not exceed the corresponding time threshold;

[0089] A second control module, configured to re-upload the auto finance asset data when the extracted real-time data transfer time exceeds the corresponding time threshold.

[0090] In this embodiment, it should be noted that regarding the above auto finance asset data monitoring system based on artificial intelligence, the specific manner of performing operations has been described in detail in the embodiments of the auto finance asset data monitoring method based on artificial intelligence, and will not be elaborated here.

[0091] Figure 5 It is a block diagram of an electronic device for an auto finance asset data monitoring method based on an exemplary embodiment. As Figure 5As shown, the electronic device 700 may include: a processor 701 and a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input / output (I / O) interface 704, and a communication component 705.

[0092] Among them, the processor 701 is used to control the overall operation of the electronic device 700 to complete all or part of the steps in the above-mentioned method for monitoring automotive financial asset data based on artificial intelligence. The memory 702 is used to store various types of data to support the operation of the electronic device 700. These data may include, for example, instructions for any application or method operating on the electronic device 700, as well as application-related data, such as contact data, sent and received messages, pictures, audio, video, and so on. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disc. The multimedia component 703 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 702 or sent through the communication component 705. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 704 provides an interface between the processor 701 and other interface modules, and the above-mentioned other interface modules may be a keyboard, a mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IoT, eMTC, or other 5G, etc., or a combination of one or several of them, is not limited herein. Accordingly, the communication component 705 may include: a Wi-Fi module, a Bluetooth module, an NFC module, and so on.

[0093] In one exemplary embodiment, the electronic device 700 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components, and is used to execute the above-mentioned artificial intelligence-based automotive finance asset data monitoring method.

[0094] In another exemplary embodiment, a computer-readable storage medium including program instructions is further provided. When the program instructions are executed by a processor, the steps of the above-mentioned artificial intelligence-based automotive finance asset data monitoring method are implemented. For example, the computer-readable storage medium may be the above-mentioned memory 702 including program instructions, and the above-mentioned program instructions may be executed by the processor 701 of the electronic device 700 to complete the above-mentioned artificial intelligence-based automotive finance asset data monitoring method.

[0095] In another exemplary embodiment, a computer program product is further provided. The computer program product includes a computer program executable by a programmable device, and the computer program has a code portion for executing the above-mentioned artificial intelligence-based automotive finance asset data monitoring method when executed by the programmable device.

[0096] The preferred embodiments of the present disclosure have been described in detail above with reference to the accompanying drawings. However, the present disclosure is not limited to the specific details in the above embodiments. Within the scope of the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0097] In addition, it should be noted that, in the above specific embodiments, the various specific technical features described can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the present disclosure does not separately describe various possible combination manners.

[0098] Furthermore, any combination can be made between various different embodiments of the present disclosure as long as it does not violate the idea of the present disclosure, and it should also be regarded as the content disclosed by the present disclosure.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered by the scope of the claims and the specification of the present invention.

Claims

1. An artificial intelligence-based method for monitoring automotive financial asset data, characterized in that, Including: Obtaining the automotive financial asset data to be uploaded based on an artificial intelligence terminal, and obtaining the importance degree of the automotive financial asset data; Obtaining an upload path, where the upload path includes multiple data transfer nodes; Uploading the automotive financial asset data according to the upload path, and monitoring the real-time data transfer time of each adjacent data transfer node; Obtaining a monitoring degree based on a monitoring model, the importance degree, and the number of data transfer nodes, and obtaining a target number according to the monitoring degree; Randomly extracting the real-time data transfer time of the target number from multiple real-time data transfer times, and determining whether each extracted real-time data transfer time exceeds the corresponding time threshold; If not, processing the automotive financial asset data; If it exceeds, re-uploading the automotive financial asset data.

2. The method for monitoring automotive financial asset data based on artificial intelligence according to claim 1, wherein, The monitoring model in the obtaining the monitoring degree based on the monitoring model, the importance degree, and the number of data transfer nodes is expressed as: Among them, Let M be the monitoring degree, α and β be the adjustment parameters, I be the importance of automotive financial asset data, and N tr be the number of data transfer nodes.

3. The method for monitoring automotive financial asset data based on artificial intelligence according to claim 1, wherein, The obtaining the target number according to the monitoring degree includes: Obtaining a monitoring threshold; If the monitoring degree does not exceed the monitoring threshold, the target number is 1; If the monitoring degree exceeds the monitoring threshold, obtaining a proportionality coefficient according to the monitoring degree and the monitoring threshold, and obtaining the target number based on the target model, the proportionality coefficient, and the number of data transfer nodes.

4. The method for monitoring automotive financial asset data based on artificial intelligence according to claim 3, characterized in that The obtaining the proportionality coefficient according to the monitoring degree and the monitoring threshold is expressed as: Among them, P is the proportionality coefficient, MI is the monitoring degree, and MT is the monitoring threshold.

5. The method for monitoring automotive financial asset data based on artificial intelligence according to claim 4, wherein The target model in the obtaining the target number based on the target model, the proportionality coefficient, and the number of data transfer nodes is expressed as: N ta = N tr ·P; wherein, N ta is the target quantity, N tr is the quantity of data transfer nodes.

6. The method for monitoring automotive financial asset data based on artificial intelligence according to claim 1, characterized in that The determining whether each extracted real-time data transfer time exceeds the corresponding time threshold includes: Obtaining the upstream node and the downstream node corresponding to the extracted real-time data transfer time; Obtaining the theoretical data transfer time according to the upstream node and the downstream node; Obtaining the time threshold according to the theoretical data transfer time, and determining whether the real-time data transfer time exceeds the time threshold.

7. The method for monitoring automotive financial asset data based on artificial intelligence according to claim 1, wherein The obtaining the importance degree of the automotive financial asset data includes: Obtaining the data source and the data size of the automotive financial asset data; Obtaining a comprehensive score according to the data source and the data size; Obtaining the importance degree of the automotive financial asset data according to the comprehensive score.

8. An artificial intelligence-based vehicle finance asset data monitoring system, characterized in that, The system is used to implement the monitoring method for automotive financial asset data based on artificial intelligence described in any one of claims 1 to 7. The system includes: A first obtaining module, which is used to obtain the automotive financial asset data to be uploaded based on an artificial intelligence terminal, and obtain the importance degree of the automotive financial asset data; A second obtaining module, which is used to obtain an upload path, where the upload path includes multiple data transfer nodes; A data monitoring module, which is used to upload the automotive financial asset data according to the upload path, and monitor the real-time data transfer time of each adjacent data transfer node; A model calculation module, which is used to obtain a monitoring degree based on a monitoring model, the importance degree, and the number of data transfer nodes, and obtain a target number according to the monitoring degree; An extraction and judgment module, which is used to randomly extract the real-time data transfer time of the target number from multiple real-time data transfer times, and determine whether each extracted real-time data transfer time exceeds the corresponding time threshold; The first control module is used to process the automotive financial asset data when the real-time transfer time of the extracted data does not exceed the corresponding time threshold; The second control module is used to re-upload the automotive financial asset data when the real-time transfer time of the extracted data exceeds the corresponding time threshold.

9. An electronic device, characterized in that, Comprising: A memory on which a computer program is stored; A processor for executing the computer program in the memory to implement the method for monitoring automotive financial asset data based on artificial intelligence according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method for monitoring automotive financial asset data based on artificial intelligence according to any one of claims 1 to 7.

Images