Risk identification method and device for report information, equipment and medium

Abstract

The invention relates to the technical field of risk identification, and discloses a risk identification method and device for report information, equipment and a medium, and the method comprises the steps: receiving report information about vehicle renting, which is transmitted by a user in a manner of scanning a target near field communication tag through terminal equipment; target vehicle business information corresponding to the target near field communication tag is determined according to a preset corresponding relation, positioning information corresponding to the terminal equipment is determined, and the preset corresponding relation is used for representing the vehicle business information corresponding to each near field communication tag; determining vehicle merchant address information corresponding to the target vehicle merchant information, and calculating a positioning distance between the vehicle merchant address information and the positioning information; and if the positioning distance is greater than a preset distance threshold, determining that the report information is a risk report. The method can be applied to business management program systems such as financial science and technology, and aims to improve the identification accuracy of the report information.

Description

Technical Field

[0001] The present invention relates to the field of risk identification technology, and in particular to a method, device, equipment and medium for risk identification of order information. Background Art

[0002] In the financial sector, auto financing leasing, as a key asset financing method, has experienced rapid growth in recent years. In the leasing industry, customer leads typically originate from various car dealerships, including dealers in the used car market and 4S dealerships. These dealers then recommend potential customers with financing needs to leasing companies, initiating the subsequent financing review and vehicle delivery process. However, leasing companies currently struggle to maintain sufficient sales personnel at every dealership, resulting in a lack of verification of the authenticity of order information. This situation increases the risk of fraudulent orders being submitted through dealers they don't actually work with. Customers may impersonate dealer channel information to obtain higher rebates or lower interest rates, creating the risk of order placement.

[0003] Currently, the most common technology uses QR codes, assigning dealers a unique QR code. Customers scan the code at the dealership to complete their order placement. However, QR codes are easily copied and misused. Customers can copy the code by taking screenshots, forwarding it, and other means, leading to fraudulent order placements. This further impacts the effectiveness of order management and may even lead to fraudulent orders. Therefore, a risk identification method for order information is urgently needed to verify its authenticity and improve its accuracy. Summary of the Invention

[0004] The present invention provides a method, device, computer equipment and medium for risk identification of order information to solve the technical problem in related technologies that order information cannot be accurately and quickly identified.

[0005] In the first aspect, a risk identification method based on order information is provided, comprising:

[0006] Receiving order information about vehicle leasing sent by a user by scanning a target near-field communication tag with a terminal device;

[0007] Determining target dealer information corresponding to the target near-field communication tag according to a preset correspondence relationship, and determining positioning information corresponding to the terminal device, wherein the preset correspondence relationship is used to characterize the dealer information corresponding to each near-field communication tag;

[0008] Determine the dealer address information corresponding to the target dealer information, and calculate the positioning distance between the dealer address information and the positioning information;

[0009] If the positioning distance is greater than a preset distance threshold, the order information is determined to be a risk order.

[0010] In a second aspect, a risk identification device for order information is provided, comprising:

[0011] A receiving module, configured to receive information about a vehicle rental order sent by a user by scanning a target near-field communication tag with a terminal device;

[0012] a determination module, configured to determine target dealer information corresponding to the target near-field communication tag according to a preset correspondence relationship, and to determine positioning information corresponding to the terminal device, wherein the preset correspondence relationship is used to characterize the dealer information corresponding to each near-field communication tag;

[0013] The determination module is further configured to determine the dealer address information corresponding to the target dealer information, and calculate the positioning distance between the dealer address information and the positioning information;

[0014] The risk assessment module is configured to determine that the order information is a risk order if the positioning distance is greater than a preset distance threshold.

[0015] In a third aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the above-mentioned method for identifying risk of order information are implemented.

[0016] In a fourth aspect, a computer-readable storage medium is provided, which stores a computer program, and when the computer program is executed by a processor, the steps of the risk identification method for the above-mentioned order information are implemented.

[0017] The above-described method, apparatus, computer device, and storage medium for risk identification based on order information implement a solution that receives a vehicle rental order from a user by scanning a target near-field communication (NFC) tag via a terminal device. The solution then determines the target dealer information corresponding to the target NFC tag based on a preset correspondence, and also determines the corresponding positioning information of the terminal device. The preset correspondence characterizes the dealer information corresponding to each NFC tag. Furthermore, the method determines the dealer address information corresponding to the target dealer information and calculates the location distance between the dealer address information and the location information. If the location distance exceeds a preset distance threshold, the order information is determined to be risky. The present invention aims to improve the accuracy of risk identification of order information by combining NFC tags with location information. By scanning the target NFC tag, the corresponding target dealer information can be accurately identified. The distance between the terminal device's location and the dealer address can be determined based on the preset correspondence, thereby determining the authenticity and risk of the order information. If the location distance exceeds a preset threshold, the order information can be automatically marked as risky, thereby reducing the incidence of fraud and improving the security of financial services. This method can effectively prevent malicious users from obtaining improper benefits through false orders and reduce financial losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments of the present invention. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0019] Figure 1 This is a schematic diagram of an application environment of a method for identifying risks in order information according to an embodiment of the present invention;

[0020] Figure 2 This is a flow chart of a method for identifying risks in order information according to an embodiment of the present invention;

[0021] Figure 3 yes Figure 1 A schematic flow chart of a specific implementation of step S40;

[0022] Figure 4 This is a schematic structural diagram of a risk identification device for order information according to an embodiment of the present invention;

[0023] Figure 5 is a structural diagram of a computer device in one embodiment of the present invention;

[0024] Figure 6 FIG. 2 is another structural diagram of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0026] The risk identification method based on order information provided by the embodiment of the present invention can be applied in the following situations: Figure 1 In an application environment, a client communicates with a server via a network. The server can receive, via the client, a vehicle rental order sent by a user via a terminal device by scanning a target near-field communication (NFC) tag; determine target dealer information corresponding to the target NFC tag based on a preset correspondence, and determine the location information corresponding to the terminal device, wherein the preset correspondence is used to characterize the dealer information corresponding to each NFC tag; determine the dealer address information corresponding to the target dealer information, and calculate the location distance between the dealer address information and the location information; if the location distance is greater than a preset distance threshold, determine the order information as a risky order. In the present invention, by combining NFC tags with location information, the accuracy of risk identification of order information is improved. By scanning the target NFC tag, the corresponding target dealer information can be accurately identified, and the distance between the terminal device's location and the dealer address can be determined based on the preset correspondence, thereby determining the authenticity and risk of the order information. If the location distance is greater than a preset threshold, the order information can be automatically marked as a risky order, thereby reducing the occurrence of fraud and improving the security of financial services. This method can effectively prevent malicious users from obtaining improper benefits through fraudulent orders, thereby reducing financial losses. The client can include, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices. The server can be implemented as a standalone server or a server cluster consisting of multiple servers. The present invention is described in detail below using specific embodiments.

[0027] See also Figure 2 As shown, Figure 2 A flow chart of a risk identification method based on order information provided by an embodiment of the present invention includes the following steps:

[0028] S10: receiving order information about vehicle leasing sent by the user by scanning the target near-field communication tag with a terminal device.

[0029] For example, in step S10, the user first receives order information by scanning a target Near-Field Communication (NFC) tag with a terminal device. The target NFC tag is typically pre-assigned to a specific vehicle or dealer, and the user can scan it using a mobile phone or other NFC-enabled device. After scanning, the terminal device automatically retrieves the policy information associated with the target NFC tag, completes the form, and sends it as part of the rental application to the controller for subsequent processing. This process ensures the authenticity of the order information source and avoids errors or tampering that may result from manual input.

[0030] This step also ensures the real-time and convenient delivery of order information. Compared to traditional manual data entry, the Target Near Field Communication (NFC) tag method allows for faster data collection, improving the user experience while reducing the safety risks associated with manual operation. Because Target Near Field Communication (NFC) tag technology relies on short-range wireless communication, users must scan the tags near the vehicle or at a designated location designated by the dealer. This ensures the authenticity of the rental transaction to a certain extent and provides a reliable data foundation for subsequent risk identification.

[0031] S20: Determine the target car dealer information corresponding to the target near-field communication tag according to a preset corresponding relationship, and determine the positioning information corresponding to the terminal device.

[0032] The preset corresponding relationship is used to represent the car dealer information corresponding to each near-field communication tag.

[0033] For example, in step S20, the target dealer information corresponding to the target NFC tag scanned by the user is first determined based on a preset mapping relationship. This preset mapping relationship is a pre-established database in which each target NFC tag is associated with specific dealer information, such as the dealer's name, business address, and vehicle inventory. Therefore, when a user scans a target NFC tag through a terminal device and submits an order, the system can quickly match the target dealer to the target NFC tag, thereby ensuring the correspondence between the order information and the actual dealer, providing data support for subsequent risk identification.

[0034] At the same time, the real-time positioning information of the terminal device will be obtained to determine the geographical location of the user when submitting the order. This positioning information can be obtained through GPS (Global Positioning System), Wi-Fi or base station signals, which is not limited in this application, and is used to compare the distance between the user's current location and the dealer's address. In this way, it is possible to determine whether the order information is submitted within a reasonable geographical range, providing a key basis for subsequent risk assessment.

[0035] In some embodiments, determining the positioning information corresponding to the terminal device includes: obtaining geographic location information provided by a built-in positioning device of the terminal device; and determining the geographic location information as the positioning information corresponding to the terminal device.

[0036] For example, the real-time geographic location information of the user when submitting the order can be obtained through the built-in positioning function of the terminal device. Specifically, the terminal device can use GPS (Global Positioning System), Wi-Fi positioning, base station signals or other available positioning technologies to obtain the current latitude and longitude data and upload it to the background. After receiving the geographic location information, it will be directly identified as the positioning information of the terminal device and compared with the address information of the target car dealer. In this way, it can be ensured that the collected location information is generated by the device in real time, reducing the possibility of human intervention or falsification of positioning data, and providing accurate data support for subsequent risk identification.

[0037] S30: Determine the dealer address information corresponding to the target dealer information, and calculate the positioning distance between the dealer address information and the positioning information.

[0038] For example, the target dealer's information can be used to determine the dealer's address. This address is typically a pre-stored dealer's business location or vehicle storage location. Mathematical calculations (such as the Haversine formula or other geographic calculation algorithms) can then be used to calculate the distance between the dealer's address and the user's terminal device's location. This calculation result is used to measure the physical distance between the user's actual location at the time of order submission and the dealer's location, providing key data support for subsequent risk assessment.

[0039] S40: If the positioning distance is greater than a preset distance threshold, the order information is determined to be a risk order.

[0040] For example, the calculated location distance can be compared with a preset distance threshold. If the location distance exceeds the preset distance threshold, it indicates that the user's actual location when submitting the order information deviates significantly from the target dealer's address, indicating a possible anomaly. Therefore, the order information can be marked as risky, potentially triggering further risk control measures such as manual review, transaction restrictions, or early warning notifications to relevant parties. The core goal of this step is to prevent malicious users from forging rental orders through geolocation matching, thereby improving the security and credibility of the transaction.

[0041] In some embodiments, in step S40, the order information includes order frequency, user credibility, and user return rate. If the positioning distance is greater than a preset distance threshold, determining that the order information is a risky order includes the following steps:

[0042] S41: If the positioning distance is greater than a preset distance threshold, the order frequency, the user credibility and the user order cancellation rate are analyzed through a deep learning model to obtain an analysis result.

[0043] S42: If the analysis result shows that the order information is the risk order, a prompt message is generated to trigger a manual secondary review of the risk order.

[0044] In steps S41-S42, risk identification relies not only on determining the location distance threshold but also incorporates a deep learning model to comprehensively analyze user behavior data to improve the accuracy of risk assessment. Specifically, when the location distance is detected to exceed the preset distance threshold, the deep learning model is further used to analyze key characteristics of the user, such as order frequency, credibility, and return rate. Order frequency reflects the user's normal trading habits, user credibility is scored based on historical trading behavior and reviews, and return rate measures the user's default risk. Based on this data, the deep learning model combines historical patterns to perform intelligent analysis and output a risk assessment result.

[0045] Furthermore, the deep learning model's analysis results can be used to further determine whether the order is a risky one. If the analysis indicates a high risk of fraud or non-compliance, a prompt message will be automatically generated, notifying the relevant reviewer for manual review. The reviewer can then make a final judgment based on more comprehensive context, such as the user's identity authentication and historical transaction records. This approach not only reduces misjudgments due to a single factor but also improves the accuracy of risk identification while minimizing disruption to legitimate users, ensuring the security and fairness of transactions.

[0046] In some embodiments, after determining that the order information is a risk order, it also includes: generating and storing a risk order log based on the order information, the risk order log includes the order information, the positioning information, and the target car dealer information; performing a risk assessment on the risk order log through a risk prediction model to obtain the risk occurrence frequency of the order information.

[0047] For example, once a report is determined to be a risk report, a risk report log is generated and stored for subsequent analysis and management. The risk report log details the core data related to the report, including the report time, user ID, rental vehicle details, the user's terminal device location information (latitude and longitude, geographic location at the time of submission), and the target dealer information (dealer name, address, etc.). By storing this information, a historical risk database can be established, providing a basis for subsequent risk control, audit tracking, and user behavior analysis, further improving the effectiveness of risk management.

[0048] The system also uses risk prediction models to conduct in-depth analysis of risk report logs and calculate the frequency of risky reports. Based on historical data and machine learning algorithms, the risk prediction model can identify patterns and trends in risky reports. For example, the system can assess whether the frequency of risk reports from a specific user, dealer, or geographic region is abnormally high, providing early warning of potential fraud. This approach not only helps accurately identify high-risk users but also optimizes risk control strategies, reducing financial losses and operational risks in the leasing business.

[0049] In some embodiments, the above method also includes: obtaining a training data set and a pre-trained model, wherein the training data set includes historical order frequencies, historical user credibility, and historical user return rates corresponding to several historical order information; labeling the training data set to obtain labeling results, wherein the labeling results include analysis results corresponding to the historical order information; training the pre-trained model through the training data set and the labeling results to obtain the deep learning model.

[0050] Specifically, the annotation results corresponding to the training data set can be used as the label of the group of input data, and then each group of labeled training sets can be input into the pre-training model for supervised learning. When the training end conditions are met, such as the number of training times reaches the number threshold or the output accuracy of the model reaches the accuracy threshold, the training is terminated to obtain a trained deep learning model.

[0051] On the basis of the above embodiment, after obtaining the deep learning model, it also includes: iteratively training the natural language processing model based on the training data set and the annotation results to extract data features, and calculate the loss function; using a preset method to iteratively train the loss function for the purpose of reducing the value of the loss function until the expected threshold requirement is met; based on the loss function after iterative training, obtaining the iterative deep learning model.

[0052] It is understandable that in order to train a deep learning model with higher accuracy, the deep learning model can be repeatedly trained iteratively to continuously reduce the loss function until the loss function meets the expected threshold requirement.

[0053] It should be noted that this application does not limit the above-mentioned preset method and expected threshold. For example, the preset method can be a gradient descent algorithm, a batch gradient descent algorithm, a stochastic gradient descent algorithm, etc. This application takes the gradient descent algorithm as an example for illustration.

[0054] The purpose of the gradient descent algorithm is to find the minimum value of the loss function or converge to the minimum value through iteration. In a geometric sense, the gradient descent algorithm is that the gradient decreases fastest in the direction opposite to the vector where the function changes the fastest, making it easier to find the minimum value of the function. Based on this, in an embodiment of the present application, the gradient descent algorithm can be used to repeatedly iteratively train the deep learning model so that the loss function is continuously reduced, thereby reducing the error of the calculation result.

[0055] As can be seen, the above solution, by combining NFC tags with positioning information, improves the accuracy of risk identification in order information. By scanning the target NFC tag, the corresponding dealer information can be accurately identified. Based on a pre-set correspondence, the distance between the terminal device and the dealer's address can be determined, thereby assessing the authenticity and risk of the order information. If the positioning distance exceeds a preset threshold, the order is automatically marked as risky, thereby reducing the risk of fraud and enhancing the security of financial services. This method effectively prevents malicious users from obtaining improper benefits through false orders, thereby reducing financial losses.

[0056] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0057] In one embodiment, a risk identification device for order information is provided, which corresponds one-to-one to the risk identification method based on order information in the above embodiment. Figure 4 As shown, the risk identification device for order information includes a receiving module 101, a determining module 102 and a risk assessment module 103. The functional modules are described in detail as follows:

[0058] The receiving module 101 is configured to receive a vehicle rental order information sent by a user by scanning a target near-field communication tag with a terminal device;

[0059] A determination module 102 is configured to determine target dealer information corresponding to the target NFC tag based on a preset correspondence relationship, and to determine positioning information corresponding to the terminal device, wherein the preset correspondence relationship is used to represent the dealer information corresponding to each NFC tag;

[0060] The determining module 102 is further configured to determine the dealer address information corresponding to the target dealer information, and calculate the location distance between the dealer address information and the location information;

[0061] The risk assessment module 103 is configured to determine that the order information is a risk order if the positioning distance is greater than a preset distance threshold.

[0062] In one embodiment, the risk assessment module 103 is further configured to:

[0063] If the positioning distance is greater than a preset distance threshold, the order frequency, the user credibility, and the user order cancellation rate are analyzed using a deep learning model to obtain an analysis result;

[0064] If the analysis result shows that the order information is the risk order, a prompt message is generated to trigger manual secondary review of the risk order.

[0065] In one embodiment, the determination module 102 is further configured to:

[0066] Obtaining business area ranges corresponding to information of several car dealers, and calculating an average order distance based on each of the business area ranges;

[0067] Determine a position deviation based on historical order information, and adjust the average order distance by the position deviation to obtain an adjusted order distance;

[0068] The adjusted order distance is determined as the preset distance threshold.

[0069] In one embodiment, the determination module 102 is further configured to:

[0070] Obtaining geographic location information provided by a built-in positioning device of the terminal device;

[0071] The geographical location information is determined as the positioning information corresponding to the terminal device.

[0072] In one embodiment, the determination module 102 is further configured to:

[0073] Generate and store a risk order log according to the order information, wherein the risk order log includes the order information, the positioning information, and the target car dealer information;

[0074] The risk prediction model is used to perform risk assessment on the risk order log to obtain the risk occurrence frequency of the order information.

[0075] In one embodiment, the receiving module 101 is further configured to:

[0076] Obtaining a training data set and a pre-trained model, wherein the training data set includes historical order frequencies, historical user credibility, and historical user order cancellation rates corresponding to a number of historical order information;

[0077] Labeling the training data set to obtain labeling results, wherein the labeling results include corresponding analysis results of the historical order information;

[0078] The pre-training model is trained using the training data set and the annotation results to obtain the deep learning model.

[0079] In one embodiment, the receiving module 101 is further configured to:

[0080] Iteratively training the natural language processing model based on the training data set and the annotation results to extract data features, and calculate a loss function;

[0081] Iteratively training the loss function using a preset method with the purpose of reducing the value of the loss function until the expected threshold requirement is met;

[0082] Based on the loss function after iterative training, an iterative deep learning model is obtained.

[0083] The present invention provides a device for identifying risk in order information. By combining near-field communication (NFC) tags with positioning information, the device improves the accuracy of risk identification in order information. By scanning the target NFC tag, the corresponding dealer information can be accurately identified. Based on a preset correspondence, the distance between the terminal device and the dealer's address can be determined, thereby assessing the authenticity and risk of the order information. If the positioning distance exceeds a preset threshold, the order is automatically marked as risky, thereby reducing the incidence of fraud and enhancing the security of financial services. This method can effectively prevent malicious users from obtaining improper benefits through false orders, thereby reducing financial losses.

[0084] The specific definition of the order information risk identification device can be found in the definition of the order information risk identification method described above and will not be repeated here. The various modules in the above-mentioned order information risk identification device can be implemented in whole or in part through software, hardware, or a combination thereof. The above-mentioned modules can be embedded in or independent of the processor of the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each of the above modules.

[0085] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor, memory, network interface and database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client via a network connection. When the computer program is executed by the processor, it implements the functions or steps on the service side of a risk identification method based on order information.

[0086] In one embodiment, a computer device is provided. The computer device may be a client, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor, memory, network interface, display screen and input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server via a network connection. When the computer program is executed by the processor, it realizes the functions or steps on the client side of a risk identification method based on order information.

[0087] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are performed:

[0088] Receiving order information about vehicle leasing sent by a user by scanning a target near-field communication tag with a terminal device;

[0089] Determining target dealer information corresponding to the target near-field communication tag according to a preset correspondence relationship, and determining positioning information corresponding to the terminal device, wherein the preset correspondence relationship is used to characterize the dealer information corresponding to each near-field communication tag;

[0090] Determine the dealer address information corresponding to the target dealer information, and calculate the positioning distance between the dealer address information and the positioning information;

[0091] If the positioning distance is greater than a preset distance threshold, the order information is determined to be a risk order.

[0092] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0093] Receiving order information about vehicle leasing sent by a user by scanning a target near-field communication tag with a terminal device;

[0094] Determining target dealer information corresponding to the target near-field communication tag according to a preset correspondence relationship, and determining positioning information corresponding to the terminal device, wherein the preset correspondence relationship is used to characterize the dealer information corresponding to each near-field communication tag;

[0095] Determine the dealer address information corresponding to the target dealer information, and calculate the positioning distance between the dealer address information and the positioning information;

[0096] If the positioning distance is greater than a preset distance threshold, the order information is determined to be a risk order.

[0097] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can be found in the relevant descriptions of the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0098] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchl ink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0099] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0100] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A method for identifying risks in order information, characterized in that: The method comprises: Receiving order information about vehicle leasing sent by a user by scanning a target near-field communication tag with a terminal device; Determining target dealer information corresponding to the target near-field communication tag according to a preset correspondence relationship, and determining positioning information corresponding to the terminal device, wherein the preset correspondence relationship is used to characterize the dealer information corresponding to each near-field communication tag; Determine the dealer address information corresponding to the target dealer information, and calculate the positioning distance between the dealer address information and the positioning information; If the positioning distance is greater than a preset distance threshold, the order information is determined to be a risk order.

2. The method according to claim 1, characterized in that The order information includes order frequency, user credibility, and user cancellation rate. If the positioning distance is greater than a preset distance threshold, determining that the order information is a risky order includes: If the positioning distance is greater than a preset distance threshold, the order frequency, the user credibility, and the user order cancellation rate are analyzed using a deep learning model to obtain an analysis result; If the analysis result shows that the order information is the risk order, a prompt message is generated to trigger manual secondary review of the risk order.

3. The method according to claim 1, characterized in that The preset distance threshold is obtained by: Obtaining business area ranges corresponding to information of several car dealers, and calculating an average order distance based on each of the business area ranges; Determine a position deviation based on historical order information, and adjust the average order distance by the position deviation to obtain an adjusted order distance; The adjusted order distance is determined as the preset distance threshold.

4. The method according to claim 1, wherein The determining the positioning information corresponding to the terminal device includes: Obtaining geographic location information provided by a built-in positioning device of the terminal device; The geographical location information is determined as the positioning information corresponding to the terminal device.

5. The method according to claim 1, wherein After determining that the order information is a risk order, the method further includes: Generate and store a risk order log according to the order information, wherein the risk order log includes the order information, the positioning information, and the target car dealer information; The risk prediction model is used to perform risk assessment on the risk order log to obtain the risk occurrence frequency of the order information.

6. The method according to claim 1, characterized in that The method further comprises: Obtaining a training data set and a pre-trained model, wherein the training data set includes historical order frequencies, historical user credibility, and historical user order cancellation rates corresponding to a number of historical order information; Labeling the training data set to obtain labeling results, wherein the labeling results include corresponding analysis results of the historical order information; The pre-training model is trained using the training data set and the annotation results to obtain the deep learning model.

7. The method according to claim 6, characterized in that After obtaining the deep learning model, the method further includes: Iteratively train the deep learning model based on the training data set and the annotation results to extract data features, and calculate the loss function; Iteratively training the loss function using a preset method with the purpose of reducing the value of the loss function until the expected threshold requirement is met; Based on the loss function after iterative training, an iterative deep learning model is obtained.

8. A risk identification device for order information, characterized in that: include: A receiving module, configured to receive information about a vehicle rental order sent by a user by scanning a target near-field communication tag with a terminal device; a determination module, configured to determine target dealer information corresponding to the target near-field communication tag according to a preset correspondence relationship, and to determine positioning information corresponding to the terminal device, wherein the preset correspondence relationship is used to characterize the dealer information corresponding to each near-field communication tag; The determination module is further configured to determine the dealer address information corresponding to the target dealer information, and calculate the positioning distance between the dealer address information and the positioning information; The risk assessment module is configured to determine that the order information is a risk order if the positioning distance is greater than a preset distance threshold.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the risk identification method for order information as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the risk identification method for order information as claimed in any one of claims 1 to 7 are implemented.

Images