Method and device for searching and controlling high-risk customers of throwing goods and computer equipment

Abstract

The embodiment of the application discloses a kind of methods, devices and computer equipment for searching and controlling high-risk customers, which comprises the following steps: obtaining order data; obtaining real-time monitoring data of transport vehicle passing timestamp authentication; according to the order data and the real-time monitoring data of transport vehicle passing timestamp authentication, and according to the preset risk threshold of throwing goods, it is judged whether the customer is throwing goods; obtain the details and the rate of throwing goods of each customer within a certain time range, output the risk customer of throwing goods and the risk comprehensive score of the risk customer of throwing goods according to the rate of throwing goods, and generate the risk customer portrait of throwing goods; compare the risk comprehensive score of the risk customer of throwing goods with the risk level threshold of throwing goods, and obtain the risk level of the customer of throwing goods; according to the comprehensive score, generate the inspection task related to the inspection amount and the inspection frequency, and push the inspection task to the supervision background.The application reduces the rate of missing collection of throwing goods, and reduces the loss of enterprise.

Description

Technical Field

[0001] This application relates to the field of cargo handling risk investigation and control in the logistics industry, and in particular to a method, device and computer equipment for investigating and controlling customers with high risk of cargo handling. Background Technology

[0002] In the logistics and transportation industry's billing system, freight charges are typically calculated based on the greater of the "actual weight" and the "volume weight." Lightweight cargo (thin goods with a volume weight greater than their actual weight) is a special category, and its freight calculation heavily relies on the accuracy of on-site volumetric measurement data during loading. However, there are significant loopholes in the current customer cargo information collection process: frontline operators (drivers / on-site workers) lack standardized procedures for volumetric measurement, leading to some lightweight cargo that should be billed by volume being incorrectly classified as ordinary heavy cargo, directly resulting in uncollected freight charges.

[0003] Ultimately, the root of the problem lies in the lack of an effective oversight mechanism in the existing processes: customers may intentionally conceal the characteristics of their goods when reporting them, while drivers, under pressure to meet performance targets (piece-rate commission system) and lacking professional measurement tools, generally prioritize speed over measurement during the pickup process. More seriously, some customers with a high proportion of low-volume goods have developed a systemic practice of omitting charges, deliberately obscuring the attributes of their goods to profit from freight arbitrage. This not only causes direct economic losses to transportation companies but also disrupts the market price system and hinders industry development. Summary of the Invention

[0004] This application provides a method, apparatus, and computer equipment for investigating and controlling customers with a high risk of cargo dumping. The aim is to identify customers with a high probability of cargo dumping through big data analysis, and to conduct different spot checks and monitoring on customers with different cargo dumping rates and risk levels, thereby reducing the rate of missed freight charges for cargo dumping and reducing corporate losses.

[0005] The technical solution is as follows:

[0006] In a first aspect, embodiments of this application provide a method for risk assessment and control of cargo volume, including:

[0007] Obtain order data, including order number, customer ID, goods type, declared weight and / or volume, and billing;

[0008] Acquire real-time monitoring data of transport vehicles that have been timestamped and certified, including vehicle location data obtained through vehicle GPS, weight data obtained by sensors, cargo volume data obtained through laser rangefinders, cargo placement status images, loading and unloading videos, as well as driver operation log data including loading start / end time and operator ID;

[0009] Based on the acquired order data and real-time monitoring data of the transport vehicle after timestamp authentication, and according to the preset cargo dumping risk threshold, it is determined whether the customer has dumped cargo. If so, the cargo dumping is marked and the verification information is output to the driver.

[0010] Obtain the details and rate of each customer's dumping within a certain time range, output the dumping risk customers and the comprehensive dumping risk score of the dumping risk customers based on the dumping rate, and generate a dumping risk customer profile;

[0011] The risk level of a customer who is dumping goods is obtained by comparing the comprehensive risk score of the customer with the risk level threshold for dumping goods.

[0012] Based on a comprehensive score that includes the risk level of customers who dump goods, the historical measurement errors of drivers, and the influence of external conditions, each factor is weighted to generate inspection tasks related to the number and frequency of inspections, and these tasks are then pushed to the regulatory backend.

[0013] Furthermore, the disposal rate includes the difference between the absolute disposal rate and the volume deviation rate and the abnormal fluctuation deviation rate. The absolute disposal rate is the percentage of customer's disposal orders within a certain time period, representing the percentage of orders with volumetric weight exceeding actual weight. The volume deviation rate is the average of all order discrepancy rates within a certain time period, specifically calculated as: Deviation Rate = |Declared Value - Verified Value| / Verified Value × 100%. The abnormal fluctuation deviation rate is the average of all order abnormal fluctuation deviation rates within a certain time period, where the abnormal fluctuation deviation rate for each order is: |Customer Shipped Volume - Industry Average| / Industry Average × 100%, reflecting the degree of deviation between the customer's shipped volume and the industry average.

[0014] Furthermore, the step of comparing the comprehensive score of a high-risk customer's dumping with the dumping risk level threshold to obtain the customer's risk level includes:

[0015] Obtain the first score related to the dumping rate over a certain period of time;

[0016] The second scoring value is obtained based on the maximum error amount per ticket;

[0017] The third-level score is obtained based on the customer's rectification timeliness.

[0018] Obtain the weight of the first, second, and third rating scores respectively. Multiply the obtained first, second, and third rating scores by their respective weights according to their rating categories, and then sum them to obtain the total score. Compare the total score with the dumping risk level threshold to obtain the dumping risk level of the dumping customer.

[0019] Further, the weights of the first, second, and third rating scores are obtained respectively. These scores are then multiplied by their respective weights according to their rating categories, and summed to obtain a total score. This total score is then compared with the dumping risk level threshold to determine the dumping risk level for all dumping customers, including:

[0020] The total score of all customers who dump goods is obtained over time. The total score is then compared with the dumping risk level threshold to determine the dumping risk level of each customer.

[0021] Furthermore, the step of obtaining the details and rate of each customer's dumping within a certain time range, outputting the dumping risk customers and the comprehensive dumping risk score of the dumping risk customers based on the dumping rate, and generating a dumping risk customer profile includes: displaying the regional distribution density of dumping customers through a dumping trend heatmap on a visualization platform.

[0022] Furthermore, the process involves obtaining the details and rate of cargo dumping for each customer within a certain time frame, outputting the cargo dumping risk customers and their comprehensive cargo dumping risk scores based on the cargo dumping rate, and generating a cargo dumping risk customer profile. This profile includes a customer risk ranking list generated on a visualization platform, ordered from highest to lowest cargo dumping rate. For each customer in the risk ranking list, a cascading data profile is generated for that customer. This cascading data profile includes changes in the customer's cargo categories over a certain period, seasonal freight order data fluctuations, and complete operation records of abnormal orders for that customer, including order number, customer ID, cargo type, declared weight and / or volume, and driver operation logs, displayed via a timeline.

[0023] Furthermore, the step of generating inspection tasks related to the inspection volume and frequency based on a comprehensive score with weights assigned to each of the following factors: the risk level of the customer who dumps goods, the driver's historical measurement error, and the influence of external conditions. This includes: pushing the inspection tasks to the regulatory backend and / or mobile terminal over time. Drivers can view their own inspection task interface through the mobile terminal, and managers are assigned different viewing content according to different management permissions.

[0024] Furthermore, based on the acquired order data and the real-time monitoring data of the transport vehicle after timestamp authentication, and according to the preset cargo dumping risk threshold, it is determined whether the customer has dumped cargo. If so, the cargo dumping is marked and verification information is output to the driver. This includes outputting alarm information after determining that the customer has dumped cargo according to the preset cargo dumping risk threshold. The alarm information includes being sent to the driver's mobile terminal through the management backend to notify the driver to verify or remeasure.

[0025] Secondly, embodiments of the present invention also provide a device for tracing and controlling high-risk customers who dump goods, comprising:

[0026] The order data acquisition unit is used to acquire order data, including order number, customer ID, goods type, declared weight and / or volume, and billing.

[0027] The real-time monitoring data acquisition unit is used to acquire real-time monitoring data of the transport vehicle that has been timestamped and certified. This includes vehicle location data acquired through the vehicle GPS, weight data acquired by sensors, cargo volume data acquired through the laser rangefinder, images of cargo placement status, loading and unloading videos, as well as driver operation log data including loading start / end time and operator ID.

[0028] The cargo dumping judgment unit is used to determine whether a customer has dumped cargo based on the acquired order data and real-time monitoring data of the transport vehicle after time stamp authentication, and according to the preset cargo dumping risk threshold. If so, it marks the cargo dumping and outputs the verification information to the driver.

[0029] The customer profile generation unit for dumping risk is used to obtain dumping details and dumping rate for each customer within a certain time range, output dumping risk customers and dumping risk comprehensive scores for dumping risk customers based on the dumping rate, and generate dumping risk customer profiles;

[0030] The risk level acquisition unit for customers who sell off goods is used to compare the comprehensive risk score of risky customers with the risk level threshold for selling off goods to obtain the risk level of customers who sell off goods.

[0031] The inspection task production unit is used to generate inspection tasks related to the inspection volume and frequency based on a comprehensive score with weights assigned to each of the following factors: the risk level of customers who dump goods, the driver's historical measurement error, and the influence of external conditions. The inspection tasks are then pushed to the regulatory backend.

[0032] Thirdly, this embodiment also provides a computer device, including: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and executed as described above.

[0033] The beneficial effects of the technical solutions provided in some embodiments of this application include at least the following:

[0034] By acquiring order data, including order number, customer ID, cargo type, declared weight and / or volume, and billing; acquiring real-time monitoring data of transport vehicles verified by timestamps, including vehicle location data obtained through onboard GPS, weight data obtained through sensors, cargo volume data obtained through laser rangefinders, images of cargo placement, loading and unloading videos, and driver operation log data including loading start / end time and operator ID; based on the acquired order data and real-time monitoring data of transport vehicles verified by timestamps, and according to a preset cargo dumping risk threshold, determining whether a customer has dumped cargo, if so, marking it as dumped and outputting verification information to the driver; acquiring cargo dumping details and dumping rate for each customer within a certain time range, outputting a comprehensive cargo dumping risk score for customers with cargo dumping risk based on the dumping rate, and generating... A customer profile for cargo dumping risk is created; the comprehensive risk score of risky customers is compared with the cargo dumping risk level threshold to obtain the customer risk level; based on the comprehensive score, which includes the customer risk level, driver historical measurement errors, and the influence of external conditions, and the weights of each factor, a sampling task related to the sampling volume and frequency is generated and pushed to the regulatory backend. This has significantly reduced the abnormal rate of cargo dumping declarations from high-risk customers, greatly improved the authenticity of customer data, increased the rectification rate of high-risk customers, and enhanced customers' awareness of compliance. At the same time, dynamic risk rating has continuously optimized the accuracy of cargo dumping customer identification, and the data audit closed loop has greatly shortened the time for abnormal response, increased the driver's proactive re-inspection rate, improved the standardization compliance rate of front-line operations, reduced the rate of missed freight charges for cargo dumping, and reduced corporate losses. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0036] Figure 1 This is a flowchart of the method provided in the embodiments of this application;

[0037] Figure 2 This is a schematic diagram of the structure of the high-risk customer tracking and control device for dumping goods provided in the embodiments of this application;

[0038] Figure 3 This is a schematic diagram of the structure of the high-risk customer tracking and control equipment provided in this application embodiment. Detailed Implementation

[0039] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0040] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0041] It should be understood that, in order to clearly describe the technical solutions of the embodiments of the present invention, the terms "first" and "second" are used in the embodiments of the present invention to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and the terms "first" and "second" are not necessarily different.

[0042] It should be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of the application. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0043] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0044] In the logistics and transportation industry, cargo billing is typically based on weight or volume (volume-sensitive cargo). However, due to inconsistent volumetric measurement practices in frontline reporting, many goods that are actually volume-sensitive are incorrectly billed based on weight, leading to revenue losses for businesses. To address this issue, this invention aims to comprehensively control and manage the situation by automating data collection, volume-sensitive cargo rate assessment, and the identification and randomization of high-risk customers, including configuring volumetric measurement tasks to check customers with a high proportion of volume-sensitive cargo. This reduces instances of drivers failing to measure or providing inaccurate volumetric measurements, thereby improving business revenue.

[0045] See Figure 1 , Figure 1This is a schematic flowchart illustrating a method for tracing and controlling high-risk customers involved in dumping goods, provided in one embodiment of this application. This method can be implemented using computer equipment, which can be deployed on a single server or a server cluster. It can also be deployed on handheld terminals, laptops, wearable devices, or robots, etc.

[0046] It should be noted that the acquisition of any information involved in the provided methods is in compliance with relevant regulations and is carried out with the client's consent, and will not infringe on the client's privacy or violate relevant laws and regulations.

[0047] Specifically, such as Figure 1 As shown, the method for tracing and controlling high-risk customers who dump goods provided in this embodiment may include the following steps:

[0048] S101. Obtain order data, including order number, customer ID, goods type, declared weight and / or volume, and billing.

[0049] The above data can be obtained by extracting key fields through the company's Transportation Management System (TMS), including order number, cargo category, declared weight / volume, billing method, etc.

[0050] S102, acquire real-time monitoring data of transport vehicles that have been timestamped and certified, including vehicle location data obtained through vehicle GPS, weight data obtained by sensors, cargo volume data obtained through laser rangefinder, cargo placement status pictures and videos, loading and unloading videos, as well as driver operation log data including loading start / end time and operator ID.

[0051] Specifically, the system collects real-time data on the actual weight of the goods (weighbridge data) using onboard sensors and volume data of the goods using a laser rangefinder, simultaneously controlling the error rate to within ±1%. The system also acquires loading completion time, photos and videos of the goods' placement, and loading / unloading videos via onboard cameras or PDA scanning. Furthermore, the acquired data is timestamped to prevent tampering.

[0052] The data obtained from the above two steps needs to be processed by removing extreme outliers, such as invalid data whose volume is greater than 150% of the carriage volume, and filling in missing values. For example, for orders where the sensors are not turned on, the historical average of the same route and vehicle model is used as a substitute. This process is intended to improve the accuracy of the processed data.

[0053] The obtained data is uploaded to the cloud system via the vehicle terminal, and then sent to the enterprise's back-end data processing equipment via the cloud system.

[0054] To handle massive data sources and processing tasks, different data processing and backup centers can be set up in different locations, and data synchronization can be achieved through dedicated lines. For example, data centers in cities A and B can be deployed to back each other up, and real-time data synchronization can be achieved through dedicated lines (RPO < 5 seconds, RTO < 2 minutes). In addition, load balancers can be used to dynamically allocate traffic, and automatically switch to the backup node when a single data center fails. At the same time, to avoid the risk of data loss, critical servers can adopt an N+1 redundancy configuration, and the storage system uses a RAID 10 array + hot spare disk. The vehicle terminal equipment can be configured with dual SIM cards (China Mobile / China Unicom) for automatic switching, and local data is cached for 24 hours in the event of network interruption.

[0055] Step S103: Based on the obtained order data and real-time monitoring data of the transport vehicle after timestamp authentication, and according to the preset cargo dumping risk threshold, determine whether the customer has dumped cargo. If so, mark the cargo dumping and output the verification information to the driver.

[0056] Due to the sheer volume of data, higher demands are placed on data processing and reception capabilities. In some implementations, backend data processing equipment leverages Apache Spark for fast and efficient processing of large-scale models. Apache Spark is a fast and general-purpose computing engine designed specifically for large-scale data processing. Spark is an open-source, Hadoop MapReduce-like general-purpose parallel framework developed by the UC Berkeley AMP lab. Spark possesses the advantages of Hadoop MapReduce; however, unlike MapReduce, intermediate job outputs can be stored in memory, eliminating the need to read and write to HDFS. Therefore, Spark is better suited for iterative MapReduce algorithms such as data mining and machine learning. Spark performs even better on certain workloads. Spark enables in-memory distributed datasets, providing interactive queries and optimizing iterative workloads.

[0057] The risk threshold for cargo dumping is not a fixed value, but includes a basic risk threshold and a dynamic correction threshold. The basic risk threshold includes the deviation between the theoretical volumetric weight automatically calculated based on the data obtained in steps S101 and S102 and the declared value. For example, if the deviation exceeds 10%, it is judged as cargo dumping. The dynamic correction threshold is a threshold that is dynamically adjusted based on the characteristics of the goods. For example, the deviation threshold for textiles cannot exceed 8%, and only 5% is allowed for metal products. The basic risk threshold plus the dynamic correction threshold constitutes the risk threshold for cargo dumping.

[0058] By acquiring order data and real-time monitoring data of transport vehicles that have been timestamped and certified, and by determining whether a customer has dumped goods based on a preset risk threshold for dumping, if so, the order is marked as dumped and the verification information is output to the driver's handheld terminal through the management backend for review.

[0059] S104: Obtain the details and rate of each customer's dumping within a certain time range, output the customers at risk of dumping based on the dumping rate, and generate a profile of the customers at risk of dumping.

[0060] The details of the cargo disposal include order number, customer ID, cargo type, declared weight and / or volume, customer-declared billing, vehicle location data obtained from vehicle GPS, weight data obtained from sensors, cargo volume data obtained from laser rangefinder, pictures and videos of cargo placement, loading and unloading videos, loading start / end time, driver operation log data including operator ID, etc.

[0061] In some embodiments, the dumping rate is the difference between the absolute dumping rate, the volumetric deviation rate, and the abnormal fluctuation deviation rate. The absolute dumping rate includes the percentage of orders with dumped goods by the customer within a certain time period, representing the percentage of orders with volumetric weight exceeding actual weight. The volumetric deviation rate is the average of the difference rates of all orders within a certain time period, specifically calculated as: Deviation Rate = |Declared Value - Verified Value| / Verified Value × 100%. The abnormal fluctuation deviation rate is the average of the abnormal fluctuation deviation rates of all orders within a certain time period, where the abnormal fluctuation deviation rate for each order is: |Customer Shipped Volume - Industry Average| / Industry Average × 100%, reflecting the degree of deviation between the customer's shipped volume and the industry average. Accurate determination of this dumping rate allows for a more objective and limited identification of customers who dump goods.

[0062] To identify customers at risk of dumping based on their dumping rate, it is necessary to first determine the dumping rate threshold. When the dumping rate reaches this threshold, it is considered dumping. For example, if a customer's absolute dumping rate is 30%, the volume deviation rate is 10%, and the abnormal fluctuation deviation rate is 5% within a month, then the customer's dumping rate for that month is 15%.

[0063] In some embodiments, the generated customer profile at risk of dumping goods is displayed on a visualization platform using a dumping trend heatmap to show the density of regional distribution of dumping customers.

[0064] In some embodiments, the generated customer profile for cargo dumping risk also includes a customer risk ranking list generated on a visualization platform in descending order of customer cargo dumping rate. For each customer in the customer risk ranking list, a cascading data profile is generated for that customer information. The cascading data profile includes changes in the customer's cargo category over a certain period of time, seasonal freight order data fluctuations, and complete operation records of abnormal orders under that customer information, including order number, customer ID, cargo type, declared weight and / or volume, and driver operation logs, displayed through a time axis.

[0065] By displaying customer profiles at risk of cargo dumping through a visualization platform, customers can more intuitively view details of these customers and gain a clearer understanding of changes in cargo categories and seasonal fluctuations. This provides valuable information for targeted recommendations of services, such as providing moisture-proof packaging packages for textile customers.

[0066] S105, compare the comprehensive risk score of the risky customer with the risk level threshold of the risky customer to obtain the risk level of the customer who is dumping goods;

[0067] In some embodiments, a method for obtaining the comprehensive risk score of the dumping includes:

[0068] Obtain the first score related to the dumping rate over a certain period of time;

[0069] The second scoring value is obtained based on the maximum error amount per ticket;

[0070] The third-level score is obtained based on the customer's rectification timeliness.

[0071] Obtain the weight of the first, second, and third rating scores respectively. Multiply the obtained first, second, and third rating scores by their respective weights according to their rating categories, and then sum them to obtain the total score. Compare the total score with the dumping risk level threshold to obtain the dumping risk level of the dumping customer.

[0072] For example, the first score related to the clearance rate is configured as follows: 50 points for a clearance rate > 30%, 30 points for a clearance rate between 15% and 30% (inclusive), and 10 points for a clearance rate < 15%. The second score related to the maximum error amount per shipment is as follows: 20 points for a maximum error amount per shipment greater than 5000 yuan, 10 points for a maximum error amount between 1000 yuan and 5000 yuan (inclusive), and 5 points for a maximum error amount per shipment < 1000 yuan. The third score related to the rectification timeliness is as follows: 15 points for a rectification timeliness > 48 hours, 8 points for a rectification timeliness between 24 and 48 hours (inclusive), and 3 points for a rectification timeliness < 24 hours. After obtaining the three scores, multiply them by their respective weights and then add them together to get the total score. Compare the total score with the risk level threshold for dumping goods. The risk level threshold can be a range of several levels. For example, the threshold range for high risk level is a total score of 30 or above, the threshold range for medium risk level is 30-10 points, and the threshold range for low risk level is below 10 points.

[0073] In some embodiments, the steps involve obtaining the weights of the first, second, and third rating scores respectively, multiplying each score by its respective weight according to its rating category, summing the results to obtain a total score, and comparing the total score with a risk level threshold to determine the risk level of all customers who are dumping goods.

[0074] The total score of all customers who dump goods is obtained over time. The total score is then compared with the dumping risk level threshold to determine the dumping risk level of each customer.

[0075] The total score depends on the three scores mentioned above. Therefore, the scores for the first, second, and third scores change over time.

[0076] By comparing the comprehensive risk score of high-risk customers with the risk level threshold for dumping goods, the risk level of dumping customers can be obtained. This allows for a fair and accurate differentiation of the risk situation of different customers, enabling more objective sampling tasks to be carried out in the future.

[0077] S106 generates inspection tasks related to the number and frequency of inspections based on a comprehensive score that includes the risk level of customers who dump goods, the historical measurement error of drivers, and the influence of external conditions, and pushes the inspection tasks to the regulatory backend.

[0078] Among these factors, the risk level of customers handling large volumes of cargo is directly proportional to the number and frequency of inspections. The greater the historical measurement error of the driver, the higher the score, and the higher the number and frequency of inspections should be. If a red alert for a typhoon or heavy rain occurs during a certain period, inspections should be suspended. Taking all these factors into account, an objective inspection task mechanism that is relevant to the actual situation is output.

[0079] For example, 100% of orders from high-risk customers are subject to random checks; 30% of orders from medium-risk customers are subject to random checks weekly; and 5% of orders from low-risk customers are subject to random checks weekly. Different sampling volumes and frequencies are set according to actual needs.

[0080] In some embodiments, generating inspection tasks related to the number and frequency of inspections based on a comprehensive score with weights assigned to each of the following factors: the risk level of the customer who dumps goods, the driver's historical measurement error, and the influence of external conditions. This includes: pushing the inspection tasks to the regulatory backend and / or mobile terminal over time. Drivers can view their own inspection task interface through the mobile terminal, and managers are assigned different viewing content according to different management permissions.

[0081] Since the risk level of customers who dump goods, the historical measurement errors of drivers, and the influence of external conditions change over time, the comprehensive score also changes over time. Therefore, it is possible to set the interval at which any random checks are pushed to the regulatory backend and / or mobile terminal, such as 12 hours or 24 hours, and push new random check tasks to the regulatory backend and / or mobile terminal.

[0082] Pushing random inspection tasks to the management backend and / or mobile terminals is not open to all customers. For example, drivers can only view the review requirements of their own randomly inspected orders, regional managers can only view all abnormal orders and processing progress within their jurisdiction, and finance personnel only have the authority to correct billing amounts. Operations are traceable and can be logged. Access control prevents the risk of data leakage.

[0083] In some embodiments, the process of determining whether a customer has dumped goods based on the acquired order data and real-time monitoring data of the transport vehicle (verified by timestamps) and a preset risk threshold for dumping goods is implemented. If so, the dumping is flagged and verification information is output to the driver. This includes outputting an alarm message after determining that the customer has dumped goods based on the preset risk threshold. The alarm message is sent to the driver's mobile terminal via the management backend to notify the driver to verify or remeasure. The alarm message can be generated using a combination of various alarm methods, such as sending it to the driver's mobile terminal via WeChat or SMS, or using an audible and visual alarm in the backend to alert maintenance and monitoring personnel.

[0084] In summary, the above methods significantly reduced the anomaly rate of cargo dumping declarations from high-risk customers, greatly improved the authenticity of customer data, and increased the rectification rate of high-risk cargo dumping customers. This also enhanced customers' awareness of contract compliance. Simultaneously, dynamic risk rating continuously optimized the accuracy of cargo dumping customer identification, and the closed-loop data audit significantly shortened the time required for anomaly response, increasing drivers' proactive re-inspection rate and improving the standardization compliance rate of frontline operations.

[0085] The following are embodiments of the apparatus of this application, which can be used to execute the embodiments of the method of this application. For details not disclosed in the embodiments of the apparatus of this application, please refer to the embodiments of the method of this application.

[0086] Please see Figure 2 This application illustrates an exemplary embodiment of a high-risk customer tracking and control device for dumping goods, comprising:

[0087] The order data acquisition unit 201 is used to acquire order data, including order number, customer ID, goods type, declared weight and / or volume, and billing.

[0088] The real-time monitoring data acquisition unit 202 is used to acquire real-time monitoring data of the transport vehicle after timestamp authentication, including vehicle location data acquired through vehicle GPS, weight data acquired by sensors, cargo volume data acquired through laser rangefinder, cargo placement status pictures, loading and unloading videos, and driver operation log data including loading start / end time and operator ID.

[0089] The cargo dumping judgment unit 203 is used to determine whether the customer has dumped cargo based on the acquired order data and the real-time monitoring data of the transport vehicle after time stamp authentication, and according to the preset cargo dumping risk threshold. If so, it marks the cargo dumping and outputs the verification information to the driver.

[0090] The customer profile generation unit 204 for dumping risk is used to obtain dumping details and dumping rate of each customer within a certain time range, output dumping risk customers and dumping risk comprehensive scores of dumping risk customers based on the dumping rate, and generate dumping risk customer profiles;

[0091] The risk level acquisition unit 205 for customers who sell off goods is used to compare the comprehensive risk score of the customers who sell off goods with the risk level threshold to obtain the risk level of the customers who sell off goods.

[0092] The sampling task production unit 206 is used to generate sampling tasks related to the sampling volume and frequency based on a comprehensive score with weights assigned to each of the following factors: the risk level of customers who dump goods, the driver's historical measurement error, and the influence of external conditions. The sampling tasks are then pushed to the regulatory backend.

[0093] Based on the above methods for investigating and controlling high-risk customers who dump goods, such as Figure 3 As shown in the diagram, this embodiment of the invention also provides a structural schematic diagram of a high-risk customer tracking and control device for dumping goods. This high-risk customer tracking and control device 3 includes a processor 31 and a memory 32 coupled to the processor 31. The memory 32 stores a computer program, which, when executed by the processor 31, causes the processor 31 to perform the high-risk customer tracking and control method for dumping goods described in the above embodiment.

[0094] For other details regarding the implementation of the above-mentioned technical solution by the processor 31 in the above-mentioned high-risk customer tracking and control equipment for dumping goods, please refer to the description in the above-mentioned invention embodiment of the high-risk customer tracking and control method for dumping goods, which will not be repeated here.

[0095] The processor 31 can also be called a CPU (Central Processing Unit). The processor 31 may be an integrated circuit chip with signal processing capabilities. The processor 31 can also be a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor, or the processor 31 can be any conventional processor.

[0096] In the several embodiments provided in this application, it should be understood that the disclosed apparatus, devices, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between devices or modules, and may be electrical, mechanical, or other forms.

[0097] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0098] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0099] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product.

[0100] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0101] The technical solutions provided in this application have been described in detail above. Specific examples have been used in this application to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

[0102] 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.

[0103] This application is described with reference to flowchart illustrations and / or block diagrams of the methods, apparatus, and computer program products according to this application. It should 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.

[0104] 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.

[0105] 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.

[0106] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for tracing and controlling high-risk customers who dump goods, characterized in that, include: Obtain order data, including order number, customer ID, goods type, declared weight and / or volume, and billing; Acquire real-time monitoring data of transport vehicles that have been timestamped and certified, including vehicle location data obtained through vehicle GPS, weight data obtained by sensors, cargo volume data obtained through laser rangefinders, cargo placement status images, loading and unloading videos, as well as driver operation log data including loading start / end time and operator ID; Based on the acquired order data and real-time monitoring data of the transport vehicle after timestamp authentication, and according to the preset cargo dumping risk threshold, it is determined whether the customer has dumped cargo. If so, the cargo dumping is marked and the verification information is output to the driver. The system obtains details and rate of goods dumped by each customer within a certain time frame. Based on the dumping rate, it outputs a comprehensive risk score for customers at risk of goods dumping and generates a profile of such customers. The dumping rate is the difference between the absolute dumping rate and the volume deviation rate and abnormal fluctuation deviation rate. The absolute dumping rate is the percentage of customer dumping orders out of the total number of shipped orders within a certain time frame. The volume deviation rate is the average of all order discrepancy rates within a certain time frame, specifically calculated as: Deviation Rate = |Declared Value - Verified Value| / Verified Value × 100%. The abnormal fluctuation deviation rate is the average of all order abnormal fluctuation deviation rates within a certain time frame, where the abnormal fluctuation deviation rate for each order is: |Customer Shipped Volume - Industry Average| / Industry Average × 100%, reflecting the degree of deviation between the customer's shipped volume and the industry average. The risk level of a customer who is dumping goods is obtained by comparing the comprehensive risk score of the customer with the risk level threshold for dumping goods. Based on a comprehensive score that includes the risk level of customers who dump goods, the historical measurement errors of drivers, and the influence of external conditions, each factor is weighted to generate inspection tasks related to the number and frequency of inspections, and these tasks are then pushed to the regulatory backend.

2. The method for investigating and controlling high-risk customers who dump goods as described in claim 1, characterized in that, The risk level of a customer who is dumping goods is determined by comparing their comprehensive risk score with the risk level threshold. This includes: Obtain the first score related to the dumping rate over a certain period of time; The second scoring value is obtained based on the maximum error amount per ticket; The third-level score is obtained based on the customer's rectification timeliness. Obtain the weight of the first, second, and third rating scores respectively. Multiply each of the obtained first, second, and third rating scores by its respective weight according to the rating type, and then sum them to obtain the total score. The total score is the comprehensive score for the risk of dumping goods. Compare the total score with the threshold for the risk level of dumping goods to obtain the level of the risk level of dumping goods for the customer.

3. The method for investigating and controlling high-risk customers who dump goods as described in claim 2, characterized in that, The process involves obtaining the weights of the first, second, and third rating scores, multiplying each score by its respective weight, summing the results to obtain a total score, and comparing this total score with the dumping risk level threshold to determine the dumping risk level for all dumping customers, including: The total score of all customers who dump goods is obtained over time. The total score is then compared with the dumping risk level threshold to determine the dumping risk level of each customer.

4. The method for investigating and controlling high-risk customers who dump goods as described in claim 3, characterized in that, The process of obtaining the details and rate of each customer's dumping within a certain time range, outputting the dumping risk customers and the comprehensive dumping risk score of the dumping risk customers based on the dumping rate, and generating a dumping risk customer profile includes: displaying the regional distribution density of dumping customers through a dumping trend heatmap on a visualization platform.

5. The method for investigating and controlling high-risk customers who dump goods according to claim 4, characterized in that, The process involves acquiring the details and rate of cargo dumping for each customer within a certain time frame, outputting the cargo dumping risk customers and their comprehensive cargo dumping risk scores based on the cargo dumping rate, and generating a cargo dumping risk customer profile. This profile includes a customer risk ranking list generated on a visualization platform, ordered from highest to lowest cargo dumping rate. For each customer in the risk ranking list, a cascading data profile is generated under the customer information. This cascading data profile includes changes in the customer's cargo category over a certain period, seasonal fluctuations in freight order data, and complete operation records of abnormal orders under the customer information, including order number, customer ID, cargo type, declared weight and / or volume, and driver operation logs, displayed via a time axis.

6. The method for investigating and controlling high-risk customers who dump goods as described in claim 5, characterized in that, The process of generating inspection tasks related to the inspection volume and frequency based on a comprehensive score with weights assigned to each of the following factors: the risk level of the customer who dumps goods, the driver's historical measurement error, and the influence of external conditions. This includes: pushing the inspection tasks to the regulatory backend and / or mobile terminals over time. Drivers can view their own inspection task interface through the mobile terminal, and managers are assigned different viewing content according to their different management permissions.

7. The method for investigating and controlling high-risk customers who dump goods as described in claim 6, characterized in that, The process involves determining whether a customer has dumped goods based on the acquired order data and real-time monitoring data of the transport vehicle that has been timestamped, and according to a preset dumping risk threshold. If so, the dumping is marked and verification information is output to the driver. This includes: after determining that the customer has dumped goods based on the preset dumping risk threshold, an alarm message is output. The alarm message is sent to the driver's mobile terminal through the management backend to notify the driver to verify or remeasure.

8. A device for tracing and controlling high-risk customers who dump goods, characterized in that, include: The order data acquisition unit is used to acquire order data, including order number, customer ID, goods type, declared weight and / or volume, and billing. The real-time monitoring data acquisition unit is used to acquire real-time monitoring data of the transport vehicle that has been timestamped and certified. This includes vehicle location data acquired through the vehicle GPS, weight data acquired by sensors, cargo volume data acquired through the laser rangefinder, images of cargo placement status, loading and unloading videos, as well as driver operation log data including loading start / end time and operator ID. The cargo dumping judgment unit is used to determine whether a customer has dumped cargo based on the acquired order data and real-time monitoring data of the transport vehicle after time stamp authentication, and according to the preset cargo dumping risk threshold. If so, it marks the cargo dumping and outputs the verification information to the driver. The customer profile generation unit for dumping risk is used to obtain dumping details and dumping rate for each customer within a certain time range. Based on the dumping rate, it outputs a dumping risk customer and a comprehensive dumping risk score for that customer, and generates a dumping risk customer profile. The dumping rate includes the difference between the absolute dumping rate and the volume deviation rate and abnormal fluctuation deviation rate. The absolute dumping rate is the percentage of dumping orders by the customer within a certain time range out of the total number of shipped orders. The volume deviation rate is the average of the difference rates of all orders within a certain time range, where the difference rate for each order is specifically: Deviation Rate = |Declared Value - Reviewed Value| / Reviewed Value × 100%. The abnormal fluctuation deviation rate is the average of the abnormal fluctuation deviation rates of all orders within a certain time range, where the abnormal fluctuation deviation rate for each order is: |Customer Shipped Volume - Industry Average| / Industry Average × 100%, reflecting the degree of deviation between the customer's shipped volume and the industry average. The risk level acquisition unit for customers who sell off goods is used to compare the comprehensive risk score of risky customers with the risk level threshold for selling off goods to obtain the risk level of customers who sell off goods. The inspection task production unit is used to generate inspection tasks related to the inspection volume and frequency based on a comprehensive score with weights assigned to each of the following factors: the risk level of customers who dump goods, the driver's historical measurement error, and the influence of external conditions. The inspection tasks are then pushed to the regulatory backend.

9. A computer device, characterized in that, include: A processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and executed as described in any one of claims 1 to 7.

Images