Pre-warning method and device for primortgage risk and automatic pre-warning system for primortgage

Abstract

The invention provides a prison product risk early warning method and device and a prison product automatic early warning system, and the method comprises the steps: obtaining prison product information of a target prison product, the prison product information comprising a prison product type and multiple pieces of price influence factor information; inputting a plurality of pieces of price influence factor information in the prison product information of the target prison product into a downlink estimation model corresponding to the prison product type to obtain a minimum estimation value of the target prison product within a predetermined duration, the downlink estimation model being obtained by training a plurality of downlink samples of historical prison products of the prison product type, the downlink sample comprises the prisoned product information of the historical prisoned product and the maximum drop of the historical prisoned product in a preset time period; under the condition that the minimum estimated value of the target prisoned product meets the early warning condition, early warning information and prisoned product disposal measures of the target prisoned product are sent out, and the prisoned product disposal measures comprise the steps of giving up signing of a prisoned product contract, adjusting the prisoned product contract estimated value of the target prisoned product and requiring a quality producer of the target prisoned product to provide guarantee. The problem that the risk of deficit of the detained products cannot be avoided in time is solved.

Description

Technical Field

[0001] This invention relates to the field of image recognition technology, and more specifically, to a method, apparatus, computer program product, and automatic collateral risk warning system. Background Technology

[0002] In terms of technology, the development of collateral early warning systems has already established a certain technological foundation. For example, big data technology can analyze and process massive amounts of data, providing a technological basis for the device to collect, analyze, and process large amounts of collateral data; OCR recognition technology has been commercialized, providing automatic image information recognition functions and improving the accuracy of collateral data sources; and artificial intelligence technology provides intelligent analysis and prediction capabilities, which can help the system predict collateral value fluctuations in advance and identify potential risks ahead of time.

[0003] Existing technical solutions mainly consist of existing collateral management devices and risk assessment models. These systems or models typically have the function of collecting, analyzing, and issuing early warnings for collateral information. However, they may have certain limitations, delays, inflexibility, and inaccuracies in terms of risk identification, early warning mechanisms, and real-time performance. Furthermore, these devices and methods lack the function of real-time risk notification, which further prolongs the processing time on top of the already delayed early warning signals, making it extremely detrimental to the identification and early warning of collateral risks.

[0004] Collateral risk identification and early warning play a crucial role in risk management; however, existing technologies have some shortcomings, which are mainly analyzed below:

[0005] I. Limitations of Data Collection and Processing:

[0006] Collateral risk warnings rely heavily on data, but the limitations of data collection and processing are a significant drawback. First, data sources are insufficient; existing collateral risk identification and warning technologies are based on existing data without expanding data sources, thus limiting the scope of data-driven warnings. Second, the data collection process heavily relies on manual entry, resulting in insufficient accuracy of basic data and inaccurate risk identification, which affects the accuracy and reliability of warnings.

[0007] II. The Delay in Risk Discovery:

[0008] Under current technology, risk warning devices can only provide risk alerts when risks occur, but cannot capture potential risk information in advance. Forward-looking risk prediction is an urgent problem to be solved.

[0009] III. Inflexibility in configuring early warning thresholds:

[0010] In the context of a rapidly changing economic environment, the configuration of early warning parameters needs to adapt to market changes and business development. Therefore, the flexibility of parameter configuration and the timeliness of parameter activation are particularly important. However, existing technologies have not conducted detailed research on early warning parameter configuration, and this issue needs to be addressed as soon as possible in the current economic context.

[0011] IV. The Delay in the Dissemination of Early Warning Information:

[0012] Existing technologies for collateral risk identification and early warning tend to focus on optimizing the accuracy and comprehensiveness of early warning information, while neglecting how to quickly deactivate early warnings after they are generated. It is necessary to incorporate both notification and deactivation of early warnings into the risk identification and early warning device to achieve a closed-loop process from warning detection to deactivation.

[0013] V. Accuracy of Early Warning Information:

[0014] Existing collateral risk identification technologies often require identifying similar collateral to make the warning parameters more closely matched and the warnings more accurate. However, such solutions can only approximate the target collateral and cannot guarantee the complete accuracy of the warning information. Therefore, further improvements in accuracy are needed. Summary of the Invention

[0015] The main objective of this application is to provide a method, device, computer program product, and automatic collateral risk warning system to at least solve the problem that the prior art cannot avoid the risk of collateral loss in a timely manner.

[0016] To achieve the above objectives, according to one aspect of this application, a method for early warning of collateral risk is provided, comprising: obtaining collateral information of a target collateral, the collateral information including collateral type and multiple price influencing factor information; inputting the multiple price influencing factor information from the collateral information of the target collateral into a downtrend valuation model corresponding to the collateral type to obtain the lowest valuation of the target collateral within a predetermined period, the downtrend valuation model being trained using multiple downtrend samples of historical collateral of the collateral type, the downtrend samples including multiple price influencing factor information of the historical collateral and the maximum decline of the historical collateral within the predetermined period; and, when the lowest valuation of the target collateral meets the early warning conditions, issuing early warning information and collateral disposal measures for the target collateral, the collateral disposal measures including abandoning the signing of a collateral contract, adjusting the collateral contract valuation of the target collateral, and requiring the pledgor of the target collateral to provide a guarantee.

[0017] Optionally, after obtaining the collateral information of the target collateral, the method further includes: in response to selecting an operation with a favorable economic situation, inputting multiple price influencing factor information from the collateral information of the target collateral into an upward valuation model corresponding to the collateral type to obtain the lowest valuation of the target collateral within a predetermined period, wherein the upward valuation model is trained using multiple upward samples of the historical collateral of the collateral type, and the upward samples include multiple price influencing factor information of the historical collateral and the lowest increase of the historical collateral within the predetermined period; in response to selecting an operation with a poor economic situation, inputting multiple price influencing factor information from the collateral information of the target collateral into a downward valuation model corresponding to the collateral type to obtain the lowest valuation of the target collateral within the predetermined period.

[0018] Optionally, after obtaining the collateral information of the target collateral, the method further includes: using the XGBoost algorithm to perform binary classification on the samples of the historical collateral of the collateral type to obtain multiple uplink samples and multiple downlink samples of the historical collateral, wherein the samples include multiple price influencing factor information of the historical collateral and multiple prices of the historical collateral within the predetermined time period.

[0019] Optionally, before using the XGBoost algorithm to perform binary classification on the samples of the historical collateral of the collateral type to obtain multiple uplink samples and multiple downlink samples of the historical collateral, the method further includes: filtering the preliminary samples of the historical collateral based on the Shapley value to obtain the samples of the historical collateral, wherein the filtering process includes irrelevant feature removal, feature derivation, missing item processing, and abnormal sample deletion.

[0020] Optionally, obtaining the collateral information of the target collateral includes: obtaining first collateral information of the target collateral collected from multiple channels; using OCR recognition technology to identify the target collateral to obtain second collateral information; and, if the first collateral information and the second collateral information are consistent, combining the first collateral information and the second collateral information to form the collateral information of the target collateral.

[0021] Optionally, before issuing an early warning message and collateral disposal measures for the target collateral when the minimum valuation of the target collateral meets the early warning conditions, the method further includes: setting the early warning conditions, the early warning conditions including the price fluctuation of the collateral being greater than a predetermined percentage and the price drop of the target collateral being greater than a predetermined threshold; and updating the predetermined percentage or the predetermined threshold of the early warning conditions in response to the operation of adjusting the predetermined percentage or the predetermined threshold.

[0022] Optionally, if the minimum valuation of the target collateral meets the warning conditions, a warning message and collateral disposal measures are issued for the target collateral, including: pushing the warning message and collateral disposal measures to the target terminal in real time according to the target push method, wherein the target push method includes warning SMS push and warning details interface push.

[0023] According to another aspect of this application, a collateral risk early warning device is provided, comprising: an acquisition unit for acquiring collateral information of a target collateral, the collateral information including collateral type and multiple price influencing factor information; an analysis unit for inputting the multiple price influencing factor information from the collateral information of the target collateral into a downtrend valuation model corresponding to the collateral type to obtain the lowest valuation of the target collateral within a predetermined period, the downtrend valuation model being trained using multiple downtrend samples of historical collateral of the collateral type, the downtrend samples including multiple price influencing factor information of the historical collateral and the maximum decline of the historical collateral within the predetermined period; and a sending unit for issuing early warning information and collateral disposal measures for the target collateral when the lowest valuation of the target collateral meets the early warning conditions, the collateral disposal measures including abandoning the signing of a collateral contract, adjusting the collateral contract valuation of the target collateral, and requiring the pledgor of the target collateral to provide collateral.

[0024] According to another aspect of this application, a computer program product is provided, comprising a computer program that, when executed by a processor, implements any of the methods described.

[0025] According to another aspect of this application, an automatic collateral warning system is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including methods for performing any one of the methods described.

[0026] By applying the technical solution of this application, the above-mentioned collateral risk early warning method uses a downside valuation model trained with multiple downside samples of historical collateral of the collateral type to analyze the lowest valuation of the target collateral within a predetermined period. If the lowest valuation meets the early warning conditions, it indicates that there is a risk of loss, and early warning information and collateral disposal measures are issued for the target collateral to remind relevant personnel of the risk of collateral loss in advance, and to provide collateral disposal measures to reduce the risk of collateral loss. This solves the technical problem in the prior art that it is impossible to avoid the risk of collateral loss in a timely manner. Attached Figure Description

[0027] Figure 1A hardware structure block diagram of a mobile terminal for implementing a collateral risk early warning method according to an embodiment of this application is shown.

[0028] Figure 2 A flowchart illustrating a method for early warning of collateral risk according to an embodiment of this application is shown.

[0029] Figure 3 A flowchart illustrating a pre-sample screening method according to an embodiment of this application is shown.

[0030] Figure 4 A schematic diagram of a collateral information collection process according to an embodiment of this application is shown;

[0031] Figure 5 A schematic flowchart illustrating a warning parameter configuration according to an embodiment of this application is shown;

[0032] Figure 6 A schematic diagram of a monitoring process for early warning information according to an embodiment of this application is shown;

[0033] Figure 7 A structural block diagram of a collateral risk warning device provided according to an embodiment of this application is shown.

[0034] The above figures include the following reference numerals:

[0035] 102. Processor; 104. Memory; 106. Transmission device; 108. Input / output device. Detailed Implementation

[0036] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0037] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0038] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be used interchangeably where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0039] For ease of description, the following explains some of the nouns or terms used in the embodiments of this application:

[0040] Collateral: Collateral refers to property or rights that a debtor or a third party pledges or mortgages to a commercial bank to secure the realization of the commercial bank's related claims, in order to mitigate credit risk.

[0041] Collateral early warning: Collateral early warning refers to the real-time monitoring and assessment of factors such as the status, value, and risks of collateral through technical means. When the status or value of collateral changes and reaches or exceeds a preset risk threshold, the system automatically triggers an alarm so that relevant institutions can take timely risk control measures to ensure the safety of credit assets.

[0042] As described in the background section, the prior art cannot avoid the risk of collateral loss in a timely manner. To solve this technical problem, the embodiments of this application provide a collateral risk early warning method, device, computer program product, and collateral automatic early warning system.

[0043] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0044] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a collateral risk early warning method according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0045] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the collateral risk warning method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one instance, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0046] This embodiment provides a method for early warning of collateral risk that runs on a mobile terminal, computer terminal or similar computing device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although the logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0047] Figure 2 This is a flowchart of a collateral risk warning method according to an embodiment of this application. Figure 2 As shown, the method includes the following steps:

[0048] Step S201: Obtain collateral information for the target collateral, including collateral type and multiple price influencing factors.

[0049] Step S202: Input the multiple price influencing factors information from the collateral information of the target collateral into the downside valuation model corresponding to the collateral type to obtain the lowest valuation of the target collateral within a predetermined period. The downside valuation model is trained using multiple downside samples of historical collateral of the collateral type. The downside samples include multiple price influencing factors information of the historical collateral and the maximum decline of the historical collateral within the predetermined period.

[0050] Step S203: If the minimum valuation of the target collateral meets the warning conditions, issue a warning message and collateral disposal measures for the target collateral. The collateral disposal measures include abandoning the signing of the collateral contract, adjusting the collateral contract valuation of the target collateral, and requiring the pledgor of the target collateral to provide a guarantee.

[0051] The aforementioned collateral risk early warning method uses a downside valuation model trained with multiple downside samples of historical collateral of the collateral type to analyze the lowest valuation of the target collateral within a predetermined period. If the lowest valuation meets the early warning conditions, it indicates a risk of loss, and an early warning message and collateral disposal measures are issued for the target collateral. This serves to remind relevant personnel of the risk of collateral loss in advance and provides collateral disposal measures to reduce the risk of collateral loss, thus solving the technical problem in existing technologies that cannot avoid the risk of collateral loss in a timely manner.

[0052] To improve the accuracy of valuation, in one optional implementation, after obtaining the collateral information of the target collateral, the method further includes:

[0053] Step S301: In response to selecting an operation with a favorable economic situation, input the multiple price influencing factors information from the collateral information of the target collateral into the upward valuation model corresponding to the collateral type to obtain the lowest valuation of the target collateral within the predetermined period. The upward valuation model is trained using multiple upward samples of the historical collateral of the collateral type. The upward samples include multiple price influencing factors information of the historical collateral and the lowest increase of the historical collateral within the predetermined period.

[0054] In step S302, in response to the operation of selecting a poor economic situation, the information on multiple price influencing factors in the collateral information of the target collateral is input into the downside valuation model corresponding to the collateral type to obtain the lowest valuation of the target collateral within the predetermined time period.

[0055] In the above implementation, the price of collateral typically fluctuates with market conditions, rising during upward cycles and falling during downward cycles. The judgment of relevant personnel regarding market conditions can be used as a reference factor. If relevant personnel believe the market is favorable and the collateral price is trending upward, they can execute an operation targeting a favorable economic situation. Multiple price-influencing factors from the collateral information of the target collateral are input into the upward valuation model corresponding to the collateral type to obtain the lowest valuation of the target collateral within a predetermined period. The upward valuation model trained with upward samples can then predict the minimum increase in the price of the target collateral within the predetermined period, obtaining the lowest valuation as a reference for collateral contract valuation. Conversely, if relevant personnel believe the market is unfavorable and the collateral price is trending downward, they can execute an operation targeting a unfavorable economic situation. Multiple price-influencing factors from the collateral information of the target collateral are input into the downward valuation model corresponding to the collateral type. The downward valuation model trained with downward samples can then predict the maximum decrease in the price of the target collateral within the predetermined period, obtaining the lowest valuation to assess the risk of loss when signing the mortgage contract.

[0056] To achieve targeted training, in one optional implementation, after obtaining the collateral information of the target collateral, the method further includes:

[0057] Step S401: The XGBoost algorithm is used to perform binary classification on the samples of the historical collateral of the above collateral type to obtain multiple uplink samples and multiple downlink samples of the above historical collateral. The samples include multiple price influencing factors of the above historical collateral and multiple prices of the above historical collateral within the above predetermined time period.

[0058] In the above implementation, XGBoost is used to perform binary classification on the historical collateral samples of each collateral type, and to filter out samples with upward and downward valuations, so as to facilitate targeted training under the corresponding economic conditions. A sufficient number of samples of the above historical collateral samples for each collateral type need to be collected.

[0059] To improve data quality, in one optional implementation, before using the XGBoost algorithm to perform binary classification on the samples of the historical collateral of the aforementioned collateral type to obtain multiple uplink samples and multiple downlink samples of the aforementioned historical collateral, the method further includes:

[0060] Step S501: Based on the Shapley value, the preliminary sample of the above-mentioned historical collateral is screened to obtain the above-mentioned sample of the above-mentioned historical collateral. The above-mentioned screening process includes irrelevant feature removal, feature derivation, missing item processing and abnormal sample deletion.

[0061] In the above embodiments, such as Figure 3As shown, through data preprocessing, massive amounts of collateral information are transformed into suitable data structures for storage, providing a foundation for the generation of subsequent early warning information. The data source after data processing first undergoes feature engineering for feature screening and other processing. The screening principle is based on Shapley values. The screening process involves four aspects: irrelevant feature removal, feature derivation, missing item handling, and abnormal sample deletion. Then, the samples are sent to the model training module for training. Machine learning technology is used in the process to enhance the intelligence level of the model.

[0062] To improve the accuracy of collateral information, in one optional implementation, step S201 includes:

[0063] Step S2011: Obtain the first collateral information of the above-mentioned target collateral collected from multiple channels;

[0064] Step S2012: Use OCR recognition technology to identify the target collateral and obtain the second collateral information;

[0065] Step S2013: If the first collateral information and the second collateral information are identical, the first collateral information and the second collateral information are combined to form the collateral information of the target collateral.

[0066] In the above embodiments, such as Figure 4 As shown, the collateral information collection module primarily implements two functions: comprehensive collection of collateral information and preparation for collection of collateral information. Collateral information includes, but is not limited to, basic information such as the type, quantity, quality, value, and storage location of the collateral. Information collected from various channels is transmitted to the collateral information collection module, ensuring a broad and comprehensive data source. An embedded OCR recognition module supports automatic recognition of information after image upload, ensuring the data source is not affected by human error and improving accuracy. Similar information in both the first and second collateral information sets is consistent, and the first and second collateral information sets are combined to form the collateral information for the target collateral, ensuring the accuracy of the collateral information.

[0067] To improve the accuracy of collateral information, in one optional implementation, after using OCR recognition technology to identify the target collateral and obtain the second collateral information, the method further includes:

[0068] Step S601: If the information of the same type between the first collateral information and the second collateral information is inconsistent, the first collateral information is re-entered to obtain the third collateral information, and the target collateral is re-identified to obtain the fourth collateral information.

[0069] Step S602: If the information of the same type of the third collateral information and the fourth collateral information are consistent, the third collateral information and the fourth collateral information are combined to form the collateral information of the target collateral.

[0070] Step S603: If the information of the same type of collateral as the third collateral information and the fourth collateral information are inconsistent, the task of identifying the target collateral is issued to the professionals of the collateral type.

[0071] In the above implementation, if the information of the first collateral and the information of the second collateral are inconsistent, it may be due to an error in information entry or OCR recognition. Therefore, the information of the first collateral is re-entered to obtain the information of the third collateral, and the target collateral is re-identified to obtain the information of the fourth collateral. If the information of the third collateral and the information of the fourth collateral are consistent, the accuracy of the collateral information can be guaranteed. If the information of the third collateral and the information of the fourth collateral are still inconsistent, manual verification is required to ensure the accuracy of the collateral information.

[0072] To achieve flexible threshold configuration, in one optional implementation, before issuing the warning information and collateral disposal measures for the target collateral when the minimum valuation of the target collateral meets the warning conditions, the method further includes:

[0073] Step S701: Set the above-mentioned early warning conditions, including the price fluctuation of the collateral being greater than a predetermined percentage and the price drop of the target collateral being greater than a predetermined threshold.

[0074] Step S702: In response to the operation of adjusting the predetermined percentage or the predetermined threshold, update the predetermined percentage or the predetermined threshold of the warning condition.

[0075] In the above embodiments, such as Figure 5 As shown, based on the characteristics and requirements of the collateral early warning rules, reasonable early warning thresholds are set. These thresholds can be configured for collateral value fluctuations, insufficient collateral value, and loss or damage of collateral. When the real-time monitoring data of the collateral exceeds or falls below the set threshold, the device will automatically trigger the early warning mechanism. The early warning thresholds support flexible configuration via a user interface. After changing the threshold, the big data early warning model will capture the changes in early warning parameters in real time and update the model parameters accordingly, ensuring timely and accurate delivery of early warning information. Of course, it is also possible to add or remove the aforementioned early warning conditions.

[0076] In order to conduct timely risk management, in one optional implementation, step S203 above includes:

[0077] Step S2031: The aforementioned warning information and the aforementioned collateral disposal measures are pushed to the target terminal in real time according to the target push method, which includes warning SMS push and warning details interface push.

[0078] In the above embodiments, such as Figure 6 As shown, once the early warning information generation module generates the early warning information that needs attention in real time, the early warning information platform will automatically receive the signal and take measures in a timely manner. The platform stores the basic information of the early warning handling personnel and can send the received early warning information to the official WeChat account of the person to be dealt with in real time, reminding them to pay attention to the early warning information in a timely manner and complete the subsequent collateral disposal measures. At the same time, it will also output a detailed early warning report to help users quickly locate and deal with the problem.

[0079] In an optional implementation of appropriate collateral disposal measures, step S203 further includes:

[0080] Step S2032: Calculate the price fluctuation range and price decline based on the aforementioned minimum valuation and current valuation of the target collateral.

[0081] Step S2033: If the price fluctuation exceeds a predetermined percentage, issue the warning message that the price fluctuation of the target collateral is too large and provide the collateral disposal measures that require the pledgor of the target collateral to provide a guarantee.

[0082] Step S2034: If the price drop exceeds the predetermined threshold, issue the warning message that the target collateral is insufficient and provide the collateral disposal measures such as abandoning the signing of the collateral contract or adjusting the valuation of the collateral contract for the target collateral.

[0083] In the above implementation, the situations that have a significant impact on the price of collateral are collateral value fluctuations, collateral undervaluation, and collateral loss or damage. There are fixed disposal measures for collateral loss or damage. For collateral value fluctuations and collateral undervaluation, there are currently only clear disposal measures. Therefore, when the price fluctuation exceeds a predetermined percentage, a warning message is issued that the target collateral price fluctuation is too large, and collateral disposal measures are given that the pledgor of the target collateral must provide a guarantee. When the price drop exceeds a predetermined threshold, a warning message is issued that the target collateral is undervalued, and collateral disposal measures are given that the signing of the collateral contract is abandoned or the valuation of the collateral contract of the target collateral is adjusted. This realizes the provision of corresponding reasonable disposal measures for different situations, so as to facilitate relevant personnel to avoid risks or reduce losses.

[0084] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0085] This application also provides a collateral risk early warning device. It should be noted that the collateral risk early warning device of this application can be used to execute the collateral risk early warning method provided in this application. This device is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0086] The following describes the collateral risk warning device provided in the embodiments of this application.

[0087] Figure 7 This is a structural block diagram of a collateral risk early warning device according to an embodiment of this application. Figure 7 As shown, the device includes:

[0088] The acquisition unit 10 is used to acquire collateral information of the target collateral, including collateral type and multiple price influencing factors.

[0089] Analysis unit 20 is used to input multiple price influencing factor information from the collateral information of the target collateral into the downside valuation model corresponding to the collateral type to obtain the lowest valuation of the target collateral within a predetermined period. The downside valuation model is trained using multiple downside samples of historical collateral of the collateral type. The downside samples include multiple price influencing factor information of the historical collateral and the maximum decline of the historical collateral within the predetermined period.

[0090] The sending unit 30 is used to issue a warning message and collateral disposal measures for the target collateral when the minimum valuation of the target collateral meets the warning conditions. The collateral disposal measures include abandoning the signing of the collateral contract, adjusting the collateral contract valuation of the target collateral, and requiring the pledgor of the target collateral to provide a guarantee.

[0091] The aforementioned collateral risk early warning device uses a downside valuation model trained with multiple downside samples of historical collateral of the collateral type to analyze the lowest valuation of the target collateral within a predetermined period. If the lowest valuation meets the early warning conditions, it indicates a risk of loss and issues early warning information and collateral disposal measures for the target collateral. This serves to remind relevant personnel of the risk of collateral loss in advance and provides collateral disposal measures to reduce the risk of collateral loss, thus solving the technical problem in the prior art that it is impossible to avoid the risk of collateral loss in a timely manner.

[0092] To improve the accuracy of the valuation, in one optional embodiment, the above-mentioned apparatus further includes:

[0093] The first response unit, after obtaining the collateral information of the target collateral, responds to the operation of selecting a favorable economic situation by inputting multiple price influencing factors from the collateral information of the target collateral into the upward valuation model corresponding to the collateral type, and obtains the lowest valuation of the target collateral within the predetermined period. The upward valuation model is trained using multiple upward samples of the historical collateral of the collateral type. The upward samples include multiple price influencing factors of the historical collateral and the lowest increase of the historical collateral within the predetermined period.

[0094] The second response unit is used to respond to the operation of selecting a poor economic situation by inputting multiple price influencing factors from the collateral information of the target collateral into the downside valuation model corresponding to the collateral type, so as to obtain the lowest valuation of the target collateral within the predetermined time period.

[0095] In the above implementation, the price of collateral typically fluctuates with market conditions, rising during upward cycles and falling during downward cycles. The judgment of relevant personnel regarding market conditions can be used as a reference factor. If relevant personnel believe the market is favorable and the collateral price is trending upward, they can execute an operation targeting a favorable economic situation. Multiple price-influencing factors from the collateral information of the target collateral are input into the upward valuation model corresponding to the collateral type to obtain the lowest valuation of the target collateral within a predetermined period. The upward valuation model trained with upward samples can then predict the minimum increase in the price of the target collateral within the predetermined period, obtaining the lowest valuation as a reference for collateral contract valuation. Conversely, if relevant personnel believe the market is unfavorable and the collateral price is trending downward, they can execute an operation targeting a unfavorable economic situation. Multiple price-influencing factors from the collateral information of the target collateral are input into the downward valuation model corresponding to the collateral type. The downward valuation model trained with downward samples can then predict the maximum decrease in the price of the target collateral within the predetermined period, obtaining the lowest valuation to assess the risk of loss when signing the mortgage contract.

[0096] To achieve targeted training, in one optional implementation, the above-mentioned device further includes:

[0097] The classification unit is used to perform binary classification on the samples of the historical collateral of the above-mentioned collateral type using the XGBoost algorithm after obtaining the collateral information of the target collateral, so as to obtain multiple up-line samples and multiple down-line samples of the above-mentioned historical collateral. The samples include multiple price influencing factors of the above-mentioned historical collateral and multiple prices of the above-mentioned historical collateral within the above-mentioned predetermined time period.

[0098] In the above implementation, XGBoost is used to perform binary classification on the historical collateral samples of each collateral type, and to filter out samples with upward and downward valuations, so as to facilitate targeted training under the corresponding economic conditions. A sufficient number of samples of the above historical collateral samples for each collateral type need to be collected.

[0099] To improve data quality, in one optional embodiment, the above-mentioned apparatus further includes:

[0100] The filtering unit is used to perform filtering processing on the preparatory samples of the historical collateral based on the Shapley value before performing binary classification on the samples of the historical collateral of the above-mentioned collateral type using the XGBoost algorithm to obtain multiple uplink samples and multiple downlink samples of the above-mentioned historical collateral, so as to obtain the samples of the above-mentioned historical collateral. The filtering processing includes irrelevant feature removal, feature derivation, missing item processing and abnormal sample deletion.

[0101] In the above embodiments, such as Figure 3 As shown, through data preprocessing, massive amounts of collateral information are transformed into suitable data structures for storage, providing a foundation for the generation of subsequent early warning information. The data source after data processing first undergoes feature engineering for feature screening and other processing. The screening principle is based on Shapley values. The screening process involves four aspects: irrelevant feature removal, feature derivation, missing item handling, and abnormal sample deletion. Then, the samples are sent to the model training module for training. Machine learning technology is used in the process to enhance the intelligence level of the model.

[0102] To improve the accuracy of collateral information, in one optional implementation, the acquisition unit includes:

[0103] The acquisition module is used to acquire the first collateral information of the aforementioned target collateral collected from multiple channels;

[0104] The identification module is used to identify the target collateral using OCR recognition technology to obtain information about the second collateral.

[0105] The combination module is used to combine the first collateral information and the second collateral information to form the collateral information of the target collateral when the first collateral information and the second collateral information are identical.

[0106] In the above embodiments, such as Figure 4 As shown, the collateral information collection module primarily implements two functions: comprehensive collection of collateral information and preparation for collection of collateral information. Collateral information includes, but is not limited to, basic information such as the type, quantity, quality, value, and storage location of the collateral. Information collected from various channels is transmitted to the collateral information collection module, ensuring a broad and comprehensive data source. An embedded OCR recognition module supports automatic recognition of information after image upload, ensuring the data source is not affected by human error and improving accuracy. Similar information in both the first and second collateral information sets is consistent, and the first and second collateral information sets are combined to form the collateral information for the target collateral, ensuring the accuracy of the collateral information.

[0107] To improve the accuracy of collateral information, in one optional embodiment, the above-mentioned device further includes:

[0108] The repeating unit is used to, after identifying the target collateral using OCR recognition technology and obtaining the second collateral information, re-enter the first collateral information to obtain the third collateral information and re-identify the target collateral to obtain the fourth collateral information when the first collateral information and the second collateral information are inconsistent.

[0109] A combination unit is used to combine the third collateral information and the fourth collateral information into the collateral information of the target collateral when the third collateral information and the fourth collateral information are identical.

[0110] The issuing unit is used to issue the identification task of the target collateral to professionals of the collateral type when there is inconsistency between the third collateral information and the fourth collateral information.

[0111] In the above implementation, if the information of the first collateral and the information of the second collateral are inconsistent, it may be due to an error in information entry or OCR recognition. Therefore, the information of the first collateral is re-entered to obtain the information of the third collateral, and the information of the target collateral is re-identified to obtain the information of the fourth collateral. If the information of the third collateral and the information of the fourth collateral are consistent, the accuracy of the collateral information can be guaranteed. If the information of the third collateral and the information of the fourth collateral are still inconsistent, the identification task of the target collateral is issued, and manual verification is required to ensure the accuracy of the collateral information.

[0112] To achieve flexible threshold configuration, in one optional implementation, the above-mentioned device further includes:

[0113] The setting unit is used to set the warning conditions before issuing the warning information and collateral disposal measures for the target collateral when the minimum valuation of the target collateral meets the warning conditions. The warning conditions include the price fluctuation of the collateral being greater than a predetermined percentage and the price drop of the target collateral being greater than a predetermined threshold.

[0114] The updating unit is used to update the predetermined percentage or the predetermined threshold of the warning condition in response to the operation of adjusting the predetermined percentage or the predetermined threshold.

[0115] In the above embodiments, such as Figure 5 As shown, based on the characteristics and requirements of the collateral early warning rules, reasonable early warning thresholds are set. These thresholds can be configured for collateral value fluctuations, insufficient collateral value, and loss or damage of collateral. When the real-time monitoring data of the collateral exceeds or falls below the set threshold, the device will automatically trigger the early warning mechanism. The early warning thresholds support flexible configuration via a user interface. After changing the threshold, the big data early warning model will capture the changes in early warning parameters in real time and update the model parameters accordingly, ensuring timely and accurate delivery of early warning information. Of course, it is also possible to add or remove the aforementioned early warning conditions.

[0116] To facilitate timely risk management, in one optional implementation, the aforementioned sending unit includes:

[0117] The first sending module is used to push the aforementioned warning information and the aforementioned collateral disposal measures to the target terminal in real time according to the target push method, which includes warning SMS push and warning details interface push.

[0118] In the above embodiments, such as Figure 6 As shown, once the early warning information generation module generates the early warning information that needs attention in real time, the early warning information platform will automatically receive the signal and take measures in a timely manner. The platform stores the basic information of the early warning handling personnel and can send the received early warning information to the official WeChat account of the person to be dealt with in real time, reminding them to pay attention to the early warning information in a timely manner and complete the subsequent collateral disposal measures. At the same time, it will also output a detailed early warning report to help users quickly locate and deal with the problem.

[0119] In an optional implementation of appropriate collateral disposal measures, the aforementioned dispatch order further includes:

[0120] The calculation module is used to calculate the price fluctuation range and price decline based on the minimum valuation and current valuation of the target collateral.

[0121] The second sending module is used to issue the warning message that the price fluctuation of the target collateral is too large when the price fluctuation range is greater than a predetermined percentage, and to provide the collateral disposal measures that require the pledgor of the target collateral to provide a guarantee.

[0122] The third sending module is used to issue the warning information that the target collateral is insufficient when the price drop exceeds the predetermined threshold, and to provide the collateral disposal measures such as abandoning the signing of the collateral contract or adjusting the valuation of the collateral contract for the target collateral.

[0123] In the above implementation, the situations that have a significant impact on the price of collateral are collateral value fluctuations, collateral undervaluation, and collateral loss or damage. There are fixed disposal measures for collateral loss or damage. For collateral value fluctuations and collateral undervaluation, there are currently only clear disposal measures. Therefore, when the price fluctuation exceeds a predetermined percentage, a warning message is issued that the target collateral price fluctuation is too large, and collateral disposal measures are given that the pledgor of the target collateral must provide a guarantee. When the price drop exceeds a predetermined threshold, a warning message is issued that the target collateral is undervalued, and collateral disposal measures are given that the signing of the collateral contract is abandoned or the valuation of the collateral contract of the target collateral is adjusted. This realizes the provision of corresponding reasonable disposal measures for different situations, so as to facilitate relevant personnel to avoid risks or reduce losses.

[0124] The aforementioned collateral risk early warning device includes a processor and a memory. The acquisition unit, analysis unit, and transmission unit are all stored as program units in the memory, and the processor executes these program units to achieve their respective functions. All of the above modules reside in the same processor; alternatively, the modules may be located in different processors in any combination.

[0125] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and adjusting kernel parameters can address the technical problem of existing technologies' inability to promptly mitigate the risk of collateral losses.

[0126] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0127] This invention provides a computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the collateral risk warning method.

[0128] Specifically, methods for early warning of collateral risk include:

[0129] Step S201: Obtain collateral information for the target collateral, including collateral type and multiple price influencing factors.

[0130] Step S202: Input the multiple price influencing factors information from the collateral information of the target collateral into the downside valuation model corresponding to the collateral type to obtain the lowest valuation of the target collateral within a predetermined period. The downside valuation model is trained using multiple downside samples of historical collateral of the collateral type. The downside samples include multiple price influencing factors information of the historical collateral and the maximum decline of the historical collateral within the predetermined period.

[0131] Step S203: If the minimum valuation of the target collateral meets the warning conditions, issue a warning message and collateral disposal measures for the target collateral. The collateral disposal measures include abandoning the signing of the collateral contract, adjusting the collateral contract valuation of the target collateral, and requiring the pledgor of the target collateral to provide a guarantee.

[0132] This invention provides a processor for running a program, wherein the program executes the aforementioned collateral risk warning method.

[0133] Specifically, methods for early warning of collateral risk include:

[0134] Step S201: Obtain collateral information for the target collateral, including collateral type and multiple price influencing factors.

[0135] Step S202: Input the multiple price influencing factors information from the collateral information of the target collateral into the downside valuation model corresponding to the collateral type to obtain the lowest valuation of the target collateral within a predetermined period. The downside valuation model is trained using multiple downside samples of historical collateral of the collateral type. The downside samples include multiple price influencing factors information of the historical collateral and the maximum decline of the historical collateral within the predetermined period.

[0136] Step S203: If the minimum valuation of the target collateral meets the warning conditions, issue a warning message and collateral disposal measures for the target collateral. The collateral disposal measures include abandoning the signing of the collateral contract, adjusting the collateral contract valuation of the target collateral, and requiring the pledgor of the target collateral to provide a guarantee.

[0137] This invention provides an automatic collateral early warning system. The device includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps:

[0138] Step S201: Obtain collateral information for the target collateral, including collateral type and multiple price influencing factors.

[0139] Step S202: Input the multiple price influencing factors information from the collateral information of the target collateral into the downside valuation model corresponding to the collateral type to obtain the lowest valuation of the target collateral within a predetermined period. The downside valuation model is trained using multiple downside samples of historical collateral of the collateral type. The downside samples include multiple price influencing factors information of the historical collateral and the maximum decline of the historical collateral within the predetermined period.

[0140] Step S203: If the minimum valuation of the target collateral meets the warning conditions, issue a warning message and collateral disposal measures for the target collateral. The collateral disposal measures include abandoning the signing of the collateral contract, adjusting the collateral contract valuation of the target collateral, and requiring the pledgor of the target collateral to provide a guarantee.

[0141] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps:

[0142] Step S201: Obtain collateral information for the target collateral, including collateral type and multiple price influencing factors.

[0143] Step S202: Input the multiple price influencing factors information from the collateral information of the target collateral into the downside valuation model corresponding to the collateral type to obtain the lowest valuation of the target collateral within a predetermined period. The downside valuation model is trained using multiple downside samples of historical collateral of the collateral type. The downside samples include multiple price influencing factors information of the historical collateral and the maximum decline of the historical collateral within the predetermined period.

[0144] Step S203: If the minimum valuation of the target collateral meets the warning conditions, issue a warning message and collateral disposal measures for the target collateral. The collateral disposal measures include abandoning the signing of the collateral contract, adjusting the collateral contract valuation of the target collateral, and requiring the pledgor of the target collateral to provide a guarantee.

[0145] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0146] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0147] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0148] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0149] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0150] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0151] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0152] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0153] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0154] As can be seen from the above description, the embodiments of this application achieve the following technical effects:

[0155] 1) In the collateral risk early warning method of this application, a downside valuation model trained with multiple downside samples of historical collateral of the collateral type is used to analyze the minimum valuation of the target collateral within a predetermined period. If the minimum valuation meets the early warning conditions, it indicates that there is a risk of loss. Early warning information and collateral disposal measures are issued for the target collateral to remind relevant personnel of the risk of collateral loss in advance and to provide collateral disposal measures to reduce the risk of collateral loss. This solves the technical problem in the prior art that the risk of collateral loss cannot be avoided in a timely manner.

[0156] 2) In the collateral risk early warning device of this application, a downside valuation model trained with multiple downside samples of historical collateral of the collateral type is used to analyze the minimum valuation of the target collateral within a predetermined period. If the minimum valuation meets the early warning conditions, it indicates that there is a risk of loss. The device issues early warning information and collateral disposal measures for the target collateral in advance to remind relevant personnel of the risk of collateral loss and provides collateral disposal measures to reduce the risk of collateral loss. This solves the technical problem in the prior art that it is impossible to avoid the risk of collateral loss in a timely manner.

[0157] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for early warning of collateral risk, characterized in that, include: Obtain collateral information for the target collateral, including collateral type and information on multiple price influencing factors; The multiple price influencing factors information in the collateral information of the target collateral are input into the downside valuation model corresponding to the collateral type to obtain the lowest valuation of the target collateral within a predetermined period. The downside valuation model is trained using multiple downside samples of historical collateral of the collateral type. The downside samples include multiple price influencing factors information of the historical collateral and the maximum decline of the historical collateral within the predetermined period. If the minimum valuation of the target collateral meets the warning conditions, a warning message and collateral disposal measures are issued for the target collateral. The collateral disposal measures include abandoning the signing of the collateral contract, adjusting the collateral contract valuation of the target collateral, and requiring the pledgor of the target collateral to provide a guarantee.

2. The method according to claim 1, characterized in that, After obtaining the collateral information of the target collateral, the method further includes: In response to selecting an operation with a favorable economic situation, the multiple price influencing factors information from the collateral information of the target collateral are input into the upward valuation model corresponding to the collateral type to obtain the lowest valuation of the target collateral within the predetermined period. The upward valuation model is trained using multiple upward samples of the historical collateral of the collateral type. The upward samples include multiple price influencing factors information of the historical collateral and the lowest increase of the historical collateral within the predetermined period. In response to the operation of selecting a poor economic situation, multiple price influencing factors from the collateral information of the target collateral are input into the downside valuation model corresponding to the collateral type to obtain the lowest valuation of the target collateral within the predetermined time period.

3. The method according to claim 2, characterized in that, After obtaining the collateral information of the target collateral, the method further includes: The XGBoost algorithm is used to perform binary classification on the samples of the historical collateral of the collateral type to obtain multiple uplink samples and multiple downlink samples of the historical collateral. The samples include multiple price influencing factors of the historical collateral and multiple prices of the historical collateral within the predetermined time period.

4. The method according to claim 3, characterized in that, Before using the XGBoost algorithm to perform binary classification on the samples of the historical collateral of the collateral type to obtain multiple uplink samples and multiple downlink samples of the historical collateral, the method further includes: The preliminary sample of the historical collateral is screened based on the Shapley value to obtain the sample of the historical collateral. The screening process includes irrelevant feature removal, feature derivation, missing item handling, and abnormal sample deletion.

5. The method according to claim 1, characterized in that, Obtain collateral information for the target collateral, including: Obtain first collateral information of the target collateral collected from multiple channels; The target collateral is identified using OCR recognition technology to obtain information about the second collateral. If the first collateral information and the second collateral information are identical, the first collateral information and the second collateral information are combined to form the collateral information of the target collateral.

6. The method according to claim 1, characterized in that, Before issuing an early warning message and taking collateral disposal measures when the minimum valuation of the target collateral meets the early warning conditions, the method further includes: The warning conditions are set, including the price fluctuation of the collateral being greater than a predetermined percentage and the price drop of the target collateral being greater than a predetermined threshold. In response to the operation of adjusting the predetermined percentage or the predetermined threshold, the predetermined percentage or the predetermined threshold of the warning condition is updated.

7. The method according to claim 6, characterized in that, If the minimum valuation of the target collateral meets the warning conditions, a warning message and collateral disposal measures will be issued for the target collateral, including: The warning information and the collateral disposal measures are pushed to the target terminal in real time according to the target push method, which includes warning SMS push and warning details interface push.

8. A collateral risk early warning device, characterized in that, include: The acquisition unit is used to acquire collateral information of the target collateral, including collateral type and multiple price influencing factors. The analysis unit is used to input multiple price influencing factor information from the collateral information of the target collateral into the downside valuation model corresponding to the collateral type to obtain the lowest valuation of the target collateral within a predetermined period of time. The downside valuation model is trained using multiple downside samples of historical collateral of the collateral type. The downside samples include multiple price influencing factor information of the historical collateral and the maximum decline of the historical collateral within the predetermined period of time. The sending unit is configured to issue a warning message and collateral disposal measures for the target collateral when the minimum valuation of the target collateral meets the warning conditions. The collateral disposal measures include abandoning the signing of the collateral contract, adjusting the collateral contract valuation of the target collateral, and requiring the pledgor of the target collateral to provide a guarantee.

9. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method described in any one of claims 1 to 7.

10. An automatic early warning system for collateral, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising methods for performing any one of claims 1 to 7.

Images