Express false weighing identification method, device and equipment and medium

Abstract

The invention provides an express false weighing identification method, apparatus and device, and a medium. The method comprises the steps of obtaining the volume and corresponding weight data of a package in each logistics link; preprocessing the obtained volume and the corresponding weight data to obtain the preprocessed volume and the corresponding weight data; and performing anomaly analysis on the plurality of pairs of preprocessed volume and corresponding weight data to identify abnormal data, and marking the abnormal data as false and heavy data. According to the invention, by reducing weighing errors and false weighing behaviors, the satisfaction degree of customers to the express service quality is improved.

Description

Technical Field

[0001] The present invention relates to the field of logistics optimization technology, and in particular to a method, device, equipment and medium for identifying false weighing of express delivery. Background Art

[0002] False weighing of express delivery harms the interests of many parties during the operation process, including consumers, express delivery companies, outlets, couriers, and transfer stations. Consumers may pay extra fees, the company's image is damaged, the operation of outlets is affected, the settlement of transfer stations is wrong, the industry's trust is reduced, and the people involved face legal consequences. This behavior violates the Consumer Rights Protection Law, increases the difficulty of industry supervision, may conceal the true situation of express delivery, and trigger legal proceedings. In addition, the supervision and regulations are not enforced effectively, and the safety awareness of practitioners is insufficient. Summary of the invention

[0003] The main purpose of the present invention is to solve the technical problem that false weighing of express delivery is difficult to supervise in the prior art.

[0004] The first aspect of the present invention provides a method for identifying false weighing of express delivery, comprising: Obtain the volume and corresponding weight data of the package in each logistics link; Preprocessing the acquired volume and corresponding weight data to obtain preprocessed volume and corresponding weight data; Anomaly analysis is performed on multiple pairs of preprocessed volume and corresponding weight data to identify abnormal data, and the abnormal data are marked as false weight.

[0005] Optionally, in a first implementation of the first aspect of the present invention, obtaining the volume and corresponding weight data of the package in each logistics link includes: Obtaining volume data of packages in various logistics links based on at least one of 3D vision technology, light curtain measurement technology, ultrasonic measurement technology and laser measurement technology; The weight data of the package in each logistics link is obtained based on at least one of the intelligent weighing sensor and the weighing instrument.

[0006] Optionally, in a second implementation of the first aspect of the present invention, the preprocessing of the acquired volume and corresponding weight data includes: The acquired volume and corresponding weight data are processed including removing noise and outliers to obtain denoised volume and corresponding weight data; The denoised volume and the corresponding weight data are standardized or normalized to obtain processed volume and the corresponding weight data.

[0007] Optionally, in a third implementation of the first aspect of the present invention, performing abnormal analysis on the plurality of pairs of preprocessed volume and corresponding weight data to identify abnormal data, and marking the abnormal data as false weight, comprises: Obtain multiple pairs of preprocessed volume and corresponding weight data; For multiple pairs of preprocessed volume and corresponding weight data, cluster analysis is performed using a clustering algorithm to divide the preprocessed volume and corresponding weight data into multiple clusters, analyze the data characteristics of each cluster, identify abnormal clusters that are different from other clusters, and mark the abnormal clusters as false weighing; The clustering algorithms include K-Means clustering, hierarchical clustering and DBSCAN clustering.

[0008] Optionally, in a fourth implementation of the first aspect of the present invention, performing abnormal analysis on the plurality of pairs of preprocessed volume and corresponding weight data to identify abnormal data, and marking the abnormal data as false weight, includes: Based on the statistical analysis of historical data, the threshold range is determined, and the upper and lower limits of the package weight are set according to the determined threshold range. When the obtained package weight exceeds the upper and lower limits, it is considered to be abnormal data; The identified abnormal data is analyzed and verified based on the corresponding volume data and the courier's operation records, and a comprehensive judgment is made as to whether the current abnormal data is false weighing.

[0009] Optionally, in a fifth implementation of the first aspect of the present invention, performing abnormal analysis on the plurality of pairs of preprocessed volume and corresponding weight data to identify abnormal data, and marking the abnormal data as false weight, comprises: Detect abnormal fluctuations in weight data through statistical analysis methods, calculate the average, standard deviation and variance of the data, and when the fluctuation of the data exceeds the preset range, it is considered abnormal data; The identified abnormal data is analyzed and verified based on the corresponding volume data and the courier's operation records, and a comprehensive judgment is made as to whether the current abnormal data is false weighing.

[0010] Optionally, in a sixth implementation of the first aspect of the present invention, the method further includes: Obtaining the weight data, volume data, courier's operation records and outlets' historical data of the parcel, and quantifying and standardizing the obtained weight data, volume data, courier's operation records and outlets' historical data; Based on the quantified and standardized weight and volume of the parcel, the courier's operation and outlets, the constructed risk assessment model is used to score the risk of false weighing. When the score value is higher than the threshold, an early warning is triggered. The risk assessment model is to score the risk by using one of the following methods: analytic hierarchy process, fuzzy comprehensive evaluation method, and neural network.

[0011] A second aspect of the present invention provides a device for identifying false weighing of express delivery, comprising: The data acquisition module is used to obtain the volume and corresponding weight data of the package in each logistics link; A data preprocessing module, used to preprocess the acquired volume and corresponding weight data to obtain preprocessed volume and corresponding weight data; The false weighing identification module is used to perform abnormal analysis on multiple pairs of pre-processed volume and corresponding weight data to identify abnormal data and mark the abnormal data as false weight.

[0012] Optionally, in a first implementation of the second aspect of the present invention, the data acquisition module includes: Obtaining volume data of packages in various logistics links based on at least one of 3D vision technology, light curtain measurement technology, ultrasonic measurement technology and laser measurement technology; The weight data of the package in each logistics link is obtained based on at least one of the intelligent weighing sensor and the weighing instrument.

[0013] Optionally, in a second implementation of the second aspect of the present invention, the data preprocessing module includes: The acquired volume and corresponding weight data are processed including removing noise and outliers to obtain denoised volume and corresponding weight data; The denoised volume and the corresponding weight data are standardized or normalized to obtain processed volume and the corresponding weight data.

[0014] Optionally, in a third implementation of the second aspect of the present invention, the false weighing identification module includes: Obtain multiple pairs of preprocessed volume and corresponding weight data; For multiple pairs of preprocessed volume and corresponding weight data, cluster analysis is performed using a clustering algorithm to divide the preprocessed volume and corresponding weight data into multiple clusters, analyze the data characteristics of each cluster, identify abnormal clusters that are different from other clusters, and mark the abnormal clusters as false weighing; The clustering algorithms include K-Means clustering, hierarchical clustering and DBSCAN clustering.

[0015] Optionally, in a fourth implementation of the second aspect of the present invention, the false weighing identification module includes: Based on the statistical analysis of historical data, the threshold range is determined, and the upper and lower limits of the package weight are set according to the determined threshold range. When the obtained package weight exceeds the upper and lower limits, it is considered to be abnormal data; The identified abnormal data is analyzed and verified based on the corresponding volume data and the courier's operation records, and a comprehensive judgment is made as to whether the current abnormal data is false weighing.

[0016] Optionally, in a fifth implementation of the second aspect of the present invention, the false weighing identification module includes: Detect abnormal fluctuations in weight data through statistical analysis methods, calculate the average, standard deviation and variance of the data, and when the fluctuation of the data exceeds the preset range, it is considered abnormal data; The identified abnormal data is analyzed and verified based on the corresponding volume data and the courier's operation records, and a comprehensive judgment is made as to whether the current abnormal data is false weighing.

[0017] Optionally, in a sixth implementation of the second aspect of the present invention, the device further includes: a risk assessment module; A quantification submodule is used to obtain the weight data, volume data, courier operation records and historical data of the outlets of the package, and quantify and standardize the obtained weight data, volume data, courier operation records and historical data of the outlets; The scoring submodule is used to score the risk of false weighing based on the quantified and standardized weight and volume of the package, the courier's operation and the outlets, using the constructed risk assessment model. When the score value is higher than the threshold, an early warning is triggered; The risk assessment model is to score the risk by using one of the following methods: analytic hierarchy process, fuzzy comprehensive evaluation method, and neural network.

[0018] A third aspect of the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for identifying false weighing of express delivery. A fourth aspect of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the above-mentioned method for identifying false weighing of express delivery.

[0019] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention uses a variety of data acquisition technologies, such as 3D vision, light curtain, ultrasound, laser, etc., to achieve high-precision acquisition of package weight and volume; this precise measurement can effectively reduce the false weighing phenomenon caused by errors and improve the accuracy and credibility of identification; 2. The present invention provides a variety of abnormal analysis methods, such as cluster analysis, threshold judgment, statistical analysis, etc., and can select appropriate technical means to detect and identify abnormal data in different situations; a strategy combining multiple algorithms is adopted, so that the system can still maintain a high recognition rate and robustness when facing complex and changeable data.

[0020] 3. The present invention constructs a risk assessment model based on quantified and standardized data, dynamically scores false express weighing and triggers early warnings; this real-time monitoring and feedback mechanism can improve the security of overall logistics management, detect potential risks in a timely manner, and thus prevent losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings: Figure 1 A first flow chart of the express false weighing identification method provided in an embodiment of the present invention.

[0022] Figure 2 A second flow chart of the express false weighing identification method provided in an embodiment of the present invention.

[0023] Figure 3 A third flow chart of the express false weighing identification method provided in an embodiment of the present invention.

[0024] Figure 4 A fourth flow chart of the express false weighing identification method provided in an embodiment of the present invention.

[0025] Figure 5 A fifth flow chart of the express false weighing identification method provided in an embodiment of the present invention.

[0026] Figure 6 A schematic diagram of the structure of a false weighing identification device for express delivery provided in an embodiment of the present invention.

[0027] Figure 7 Another structural schematic diagram of the express false weighing identification device provided in an embodiment of the present invention.

[0028] Figure 8 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The embodiment of the present invention provides a method, device, equipment and medium for identifying false weighing of express delivery, which obtains the volume and corresponding weight data of the package in each logistics link; pre-processes the obtained volume and corresponding weight data to obtain the pre-processed volume and corresponding weight data; performs abnormal analysis on multiple pairs of pre-processed volume and corresponding weight data to identify abnormal data, and marks the abnormal data as false weight. The present invention solves the technical problem that false weighing of express delivery is difficult to supervise in the prior art.

[0030] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 The first embodiment of the express delivery false weighing identification method in the embodiment of the present invention includes: 101. Obtain the volume and corresponding weight data of the package in each logistics link; In this embodiment, in the process of express delivery, such as pickup, transfer, sorting, and delivery, 3D vision technology, light curtain measurement technology, ultrasonic measurement technology, or laser measurement technology is used to automatically measure the volume of the package and obtain the package volume data. Intelligent weighing sensors or weighing meters are used to measure the weight of the package in real time and accurately to obtain the package weight data.

[0032] This embodiment uses the above technology to quickly and accurately obtain the size data and weight data of the package, reducing the error and time consumption of manual measurement.

[0033] 102. Preprocessing the acquired volume and corresponding weight data to obtain preprocessed volume and corresponding weight data; In this embodiment, the acquired volume and corresponding weight data are subjected to noise and outlier removal processing to obtain denoised volume and corresponding weight data; for example, using a filtering algorithm, a statistical method or a data visualization tool to identify and remove obviously erroneous data points; The denoised volume and the corresponding weight data are standardized or normalized to obtain processed volume and the corresponding weight data; for example, using the Z-score standardization or Min-Max normalization method to convert the data into data with a mean of 0 and a standard deviation of 1 or in the interval [0,1].

[0034] This embodiment implements noise and outlier processing, as well as standardization or normalization processing on the acquired data, which can ensure the stability and comparability of subsequent analysis.

[0035] 103. Perform anomaly analysis on multiple pairs of pre-processed volume and corresponding weight data to identify abnormal data, and mark the abnormal data as false weight.

[0036] In this embodiment, multiple pairs of preprocessed volume and corresponding weight data are obtained; for the multiple pairs of preprocessed volume and corresponding weight data, cluster analysis is performed by using a clustering algorithm, the preprocessed volume and corresponding weight data are divided into multiple clusters, the data characteristics of each cluster are analyzed, abnormal clusters different from other clusters are identified, and the abnormal clusters are marked as false weighing; wherein the clustering algorithm includes K-Means clustering, hierarchical clustering and DBSCAN clustering; a suitable clustering algorithm is selected for cluster analysis according to the characteristics of the data and business requirements; More specifically, the optimal number of clusters is determined by trying different parameter values ​​or using methods such as the elbow theorem and silhouette coefficient.

[0037] This embodiment combines big data, automatic volume measurement, and intelligent weighing technology to improve the accuracy of express weighing and prevent false behavior; analyzes the collected data through a clustering algorithm to identify weighing data that does not conform to the norm; and improves customer satisfaction with the quality of express service by reducing weighing errors and false weighing behaviors.

[0038] See also Figure 2 The second embodiment of the express delivery false weighing identification method in the embodiment of the present invention includes: 201. Obtain the volume and corresponding weight data of the package in each logistics link; In this embodiment, in the process of picking up, transferring, sorting, and delivering express parcels, 3D vision technology, light curtain measurement technology, ultrasonic measurement technology, or laser measurement technology are used to automatically measure the volume of the parcel. These technologies can quickly and accurately obtain the size data of the goods, reducing the error and time consumption of manual measurement; intelligent weighing sensors and weighing instruments are used to measure the weight of the parcel in real time and accurately; Evaluate the advantages and disadvantages of different volume measurement technologies, and select appropriate technologies based on the needs and actual conditions of the express delivery business. 3D vision technology is suitable for packages with complex shapes, but the cost is relatively high; light curtain measurement technology is fast, but the accuracy is relatively low; ultrasonic measurement technology and laser measurement technology are highly accurate, but have high environmental requirements; install and debug volume measurement equipment to ensure that the equipment can accurately measure the volume of the package, adjust the position, angle and parameters of the equipment to adapt to packages of different sizes and shapes; calibrate and verify the measurement results to ensure the accuracy of the data, use standard objects for calibration, compare the measurement results of different equipment, and promptly discover and correct errors; Select appropriate intelligent weighing sensors and weighing instruments to ensure that their accuracy and stability meet business requirements. Select appropriate sensor range and resolution based on the weight range and accuracy requirements of the package; install and connect the weighing equipment to ensure that it can work properly.

[0039] 202. Preprocessing the acquired volume and corresponding weight data to obtain preprocessed volume and corresponding weight data; In this embodiment, the acquired volume and corresponding weight data are subjected to noise and outlier removal processing to obtain denoised volume and corresponding weight data; the denoised volume and corresponding weight data are subjected to standardization or normalization processing to obtain processed volume and corresponding weight data.

[0040] 203. Perform anomaly analysis on multiple pairs of pre-processed volume and corresponding weight data to identify abnormal data, and mark the abnormal data as false weight; In this embodiment, a threshold range is determined based on statistical analysis of historical data, and upper and lower limits of the package weight are set based on the determined threshold range. When the obtained package weight exceeds the upper and lower limits, it is considered to be abnormal data; Detect abnormal fluctuations in weight data through statistical analysis methods, calculate the average, standard deviation and variance of the data, and when the fluctuation of the data exceeds the preset range, it is considered abnormal data; The identified abnormal data is analyzed and verified based on the corresponding volume data and the courier's operation records, and a comprehensive judgment is made as to whether the current abnormal data is false weighing.

[0041] See also Figure 3 The third embodiment of the express false weighing identification method in the embodiment of the present invention includes: 301. Obtain the volume and corresponding weight data of the package in each logistics link; 302. Preprocess the acquired volume and corresponding weight data to obtain preprocessed volume and corresponding weight data; 303. Perform anomaly analysis on multiple pairs of pre-processed volume and corresponding weight data to identify abnormal data, and mark the abnormal data as false weight; In this embodiment, multiple pairs of preprocessed volume and corresponding weight data are obtained; for the multiple pairs of preprocessed volume and corresponding weight data, cluster analysis is performed by using a clustering algorithm, the preprocessed volume and corresponding weight data are divided into multiple clusters, the data characteristics of each cluster are analyzed, abnormal clusters different from other clusters are identified, and the abnormal clusters are marked as false weighing; At the same time, based on the statistical analysis of historical data, the threshold range is determined, and the upper and lower limits of the package weight are set according to the determined threshold range. If the weight of the package based on the non-abnormal cluster exceeds the upper and lower limits, it is considered to be abnormal data; then the abnormal fluctuation of the weight data is detected by statistical analysis methods, and the average, standard deviation and variance of the data are calculated. When the fluctuation of the data exceeds the preset range, it is considered to be abnormal data; The identified abnormal data is analyzed and verified based on the corresponding volume data and the courier's operation records, and a comprehensive judgment is made as to whether the current abnormal data is false weighing.

[0042] See also Figure 4 The fourth embodiment of the express delivery false weighing identification method in the embodiment of the present invention includes: 401. Obtain the volume and corresponding weight data of the package in each logistics link; 402. Preprocess the acquired volume and corresponding weight data to obtain preprocessed volume and corresponding weight data; 403. Perform anomaly analysis on multiple pairs of pre-processed volume and corresponding weight data to identify abnormal data, and mark the abnormal data as false weight; 404. Using the constructed risk assessment model, the risk of false weighing is scored based on the quantified and standardized weight and volume of the package, the courier's operation and the outlets. When the score value is higher than the threshold, an early warning is triggered; In this embodiment, the risk assessment model is to perform risk scoring by using one of the following methods: analytic hierarchy process, fuzzy comprehensive evaluation method, and neural network.

[0043] In this embodiment, it also includes: obtaining weight data, volume data, courier operation records and historical data of outlets of the package, and quantifying and standardizing the obtained weight data, volume data, courier operation records and historical data of outlets; For example, the weight and volume values ​​of all packages can be directly quantified as floating point numbers (in kilograms or cubic meters). If the goal is classification, divide them into specific intervals (such as less than 1kg, less than 5kg, etc.) and assign corresponding scores; Based on the courier's operational performance, it is quantified into a score.

[0044] Quantify the historical data of the outlets (such as success rate, delay rate); For example: a success rate above 90% gets 10 points, 80% to 90% gets 8 points, 70%-80% gets 6 points, and below 70% gets 0 points.

[0045] See also Figure 5 The fourth embodiment of the express delivery false weighing identification method in the embodiment of the present invention includes: 501. Obtain the volume and corresponding weight data of the package in each logistics link; 502. Preprocessing the acquired volume and corresponding weight data to obtain preprocessed volume and corresponding weight data; 503. Perform anomaly analysis on multiple pairs of pre-processed volume and corresponding weight data to identify abnormal data, and mark the abnormal data as false weight; 504. Using the constructed risk assessment model, the risk of false weighing is scored based on the quantified and standardized weight and volume of the package, the courier's operation and the outlets. When the score value is higher than the threshold, an early warning is triggered; 505. Provide managers with decision support tools, such as data visualization dashboards, to display key indicators and abnormal trends, and communicate identified false weighing behaviors to relevant personnel or departments so that appropriate corrective measures can be taken.

[0046] In this embodiment, a data visualization dashboard is designed and developed to present key indicators and abnormal trends to managers in the form of intuitive charts, graphs, etc. Business intelligence tools, data visualization software, or custom-developed dashboard systems can be used. Data analysis and query functions are provided, and managers can query data for specific time periods, couriers, outlets, etc. as needed for in-depth analysis and comparison. Combined with the risk assessment model, prediction and early warning functions are provided to help managers discover potential risk events in advance and take corresponding preventive measures.

[0047] Communicate the identified false weighing behaviors with relevant personnel or departments, such as couriers, branch managers, quality management departments, etc., and convey information in a timely manner through emails, text messages, meetings, etc., discuss solutions together, establish communication mechanisms and feedback channels, and ensure smooth information flow and timely resolution of problems. Managers can listen to the opinions and suggestions of relevant personnel and continuously improve business processes and preventive measures.

[0048] The above describes the express delivery false weighing identification method in the embodiment of the present invention. The following describes the express delivery false weighing identification device in the embodiment of the present invention. Figure 6In one embodiment of the present invention, a device for identifying false weighing of express delivery includes: The data acquisition module 601 is used to obtain the volume and corresponding weight data of the package in each logistics link; In this embodiment, the data acquisition module 601 includes: The volume data acquisition submodule 6011 is used to automatically measure the volume of the package using 3D vision technology, light curtain measurement technology, ultrasonic measurement technology or laser measurement technology in the process of express delivery, such as pickup, transfer, sorting and delivery, to obtain the volume data of the package; The weight data acquisition submodule 6012 is used to use an intelligent weighing sensor or a weighing meter to measure the weight of the package in real time and accurately to obtain the weight data of the package.

[0049] A data preprocessing module 602 is used to preprocess the acquired volume and corresponding weight data to obtain preprocessed volume and corresponding weight data; In this embodiment, the data preprocessing module 602 includes: The abnormal data processing submodule 6021 is used to perform noise and abnormal value processing on the acquired volume and corresponding weight data to obtain the denoised volume and corresponding weight data; for example, using a filtering algorithm, a statistical method or a data visualization tool to identify and remove obviously erroneous data points; The standardization processing submodule 6022 is used to standardize or normalize the denoised volume and corresponding weight data to obtain processed volume and corresponding weight data; for example: using Z-score standardization or Min-Max normalization method to convert the data into data with a mean of 0, a standard deviation of 1 or in the interval [0,1].

[0050] The false weighing identification module 603 is used to perform abnormal analysis on multiple pairs of pre-processed volume and corresponding weight data to identify abnormal data and mark the abnormal data as false weight.

[0051] In this embodiment, multiple pairs of preprocessed volume and corresponding weight data are obtained; for the multiple pairs of preprocessed volume and corresponding weight data, cluster analysis is performed by using a clustering algorithm, the preprocessed volume and corresponding weight data are divided into multiple clusters, the data characteristics of each cluster are analyzed, abnormal clusters different from other clusters are identified, and the abnormal clusters are marked as false weighing; At the same time, based on the statistical analysis of historical data, the threshold range is determined, and the upper and lower limits of the package weight are set according to the determined threshold range. If the weight of the package based on the non-abnormal cluster exceeds the upper and lower limits, it is considered to be abnormal data; then the abnormal fluctuation of the weight data is detected by statistical analysis methods, and the average, standard deviation and variance of the data are calculated. When the fluctuation of the data exceeds the preset range, it is considered to be abnormal data; The identified abnormal data is analyzed and verified based on the corresponding volume data and the courier's operation records, and a comprehensive judgment is made as to whether the current abnormal data is false weighing.

[0052] The risk assessment module 604 is used to score the risk of false weighing based on the quantified and standardized weight and volume of the package, the courier's operation and the outlets by using the constructed risk assessment model, and trigger an early warning when the score value is higher than a threshold; In this embodiment, the risk assessment model is to score the risk by using one of the following methods: analytic hierarchy process, fuzzy comprehensive evaluation method, and neural network.

[0053] In this embodiment, it also includes: obtaining weight data, volume data, courier operation records and historical data of outlets of the package, and quantifying and standardizing the obtained weight data, volume data, courier operation records and historical data of outlets; For example, the weight and volume values ​​of all packages can be directly quantified as floating point numbers (in kilograms or cubic meters). If the goal is classification, divide them into specific intervals (such as less than 1kg, less than 5kg, etc.) and assign corresponding scores; Based on the courier's operational performance, it is quantified into a score.

[0054] Quantify the historical data of the outlets (such as success rate, delay rate); For example: a success rate above 90% gets 10 points, 80% to 90% gets 8 points, 70%-80% gets 6 points, and below 70% gets 0 points.

[0055] See also Figure 7 Another embodiment of the express false weighing identification device in the embodiment of the present invention includes: Data acquisition module 701, used to obtain the volume and corresponding weight data of the package in each logistics link; A data preprocessing module 702 is used to preprocess the acquired volume and corresponding weight data to obtain preprocessed volume and corresponding weight data; In this embodiment, the collected data is cleaned and preprocessed to remove noise and outliers, and filtering algorithms, statistical methods or data visualization tools are used to identify and remove obviously erroneous data points; the data is standardized or normalized so that the data of different variables have the same scale and range, and the Z-score standardization or Min-Max normalization method is used to convert the data into data with a mean of 0 and a standard deviation of 1 or in the interval [0,1]; A false weighing identification module 703 is used to perform abnormal analysis on multiple pairs of pre-processed volume and corresponding weight data to identify abnormal data and mark the abnormal data as false weight; In this embodiment, a suitable clustering algorithm is selected, such as K-Means clustering, hierarchical clustering, DBSCAN clustering, etc. According to the characteristics of the data and business requirements, a suitable algorithm is selected for clustering analysis, the number of clusters or parameters is determined, and the optimal number of clusters is determined by trying different parameter values ​​or using methods such as the elbow rule and the silhouette coefficient. The data is clustered and analyzed to divide the data objects into different clusters. The characteristics and attributes of each cluster are analyzed to identify abnormal clusters that are significantly different from other clusters; thresholds are set to identify packages with abnormal weights. Based on the statistical analysis of historical data, a reasonable threshold range can be determined, and the upper and lower limits of the package weight can be set. Packages outside this range are considered outliers. Detect abnormal fluctuations in weighing data through statistical analysis methods, calculate the mean, standard deviation, variance and other statistical quantities of the data, and consider them to be outliers when the fluctuation of the data exceeds a certain range. Use big data analysis tools, such as association rule mining, to identify possible patterns of false weighing. By analyzing the correlation between couriers, outlets and package weights, it is found that couriers or outlets with frequent weight abnormalities may be signals of false weighing. Analyze and verify the identified abnormal data to determine whether it is really false weighing or abnormal situation. Combined with other information, such as the volume of the package, the courier's operation records, etc., a comprehensive judgment can be made; abnormal data can be marked and recorded for subsequent investigation and processing. At the same time, summarize and analyze abnormal situations to provide a basis for improving business processes and preventing false weighing.

[0056] The risk assessment module 704 is used to score the risk of false weighing based on the quantified and standardized weight and volume of the package, the courier's operation and the outlets by using the constructed risk assessment model, and trigger an early warning when the score value is higher than a threshold; In this embodiment, a risk assessment model is established to score the risk of each package, courier or outlet. This model can be dynamically adjusted according to historical data and real-time data to reflect the latest risk status; a real-time monitoring system is developed to monitor the weighing data in the express delivery process in real time. Once an abnormality is detected, the system can automatically issue an early warning to remind the management personnel to conduct further investigation; determine the factors that affect the risk of express weighing data, such as the weight, volume, value of the package, the courier's operation record, the historical data of the outlet, etc.; quantify and standardize each factor so that the data of different factors have the same scale and range, and use numerical scoring, grade division or standardized formula to convert the factors into comparable values; select a suitable risk assessment method, such as hierarchical analysis method, fuzzy comprehensive evaluation method, neural network, etc., and select a suitable method to establish a risk assessment model according to the characteristics of the data and business needs; determine the parameters and weights of the model, and adjust the parameters and weights of the model through training and verification of historical data so that the model can accurately assess the degree of risk; test and optimize the model, and use an independent test data set to test the model to evaluate the accuracy and reliability of the model. According to the test results, the model is optimized and improved to improve the performance of the model.

[0057] Using the established risk assessment model, we calculate the risk score for each package, courier or outlet. We input the data of relevant factors into the model to obtain the numerical result of the risk score; we interpret and analyze the risk score, determine the risk level and meaning of different score intervals, and divide the risk score into three levels: high, medium and low, corresponding to different risk levels and treatment measures.

[0058] Use data acquisition equipment, sensor networks or software systems to obtain weighing data and related information in real time, set monitoring indicators and thresholds, and determine the indicators and corresponding thresholds that need to be monitored based on risk assessment models and business needs. When the indicators exceed the thresholds, the system automatically issues an early warning signal; process and respond to the early warning signal. When the system issues an early warning signal, the management personnel should investigate and handle it in a timely manner. Measures such as suspending the flow of packages, checking weighing equipment, and verifying the courier's operation can be taken to ensure the accuracy and reliability of weighing data.

[0059] Visualization module 705 is used to provide decision support tools for managers, including: data visualization dashboards that display key indicators and abnormal trends; In this embodiment, a data visualization dashboard is designed and developed to present key indicators and abnormal trends to managers in the form of intuitive charts, graphs, etc. Business intelligence tools, data visualization software, or custom-developed dashboard systems can be used. Data analysis and query functions are provided, and managers can query data for specific time periods, couriers, outlets, etc. as needed for in-depth analysis and comparison. Combined with the risk assessment model, prediction and early warning functions are provided to help managers discover potential risk events in advance and take corresponding preventive measures.

[0060] Communicate the identified false weighing behaviors with relevant personnel or departments, such as couriers, branch managers, quality management departments, etc., and convey information in a timely manner through emails, text messages, meetings, etc., discuss solutions together, establish communication mechanisms and feedback channels, and ensure smooth information flow and timely resolution of problems. Managers can listen to the opinions and suggestions of relevant personnel and continuously improve business processes and preventive measures.

[0061] above Figure 6 and Figure 7 The express false weighing identification device in the embodiment of the present invention is described in detail from the perspective of modular functional entities, and the electronic device in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0062] Figure 8 7 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device 700 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 710 (for example, one or more processors) and a memory 720, and one or more storage media 730 (for example, one or more mass storage devices) storing application programs 733 or data 732. Among them, the memory 720 and the storage medium 730 can be temporary storage or permanent storage. The program stored in the storage medium 730 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the electronic device 700. Furthermore, the processor 710 may be configured to communicate with the storage medium 730 to execute a series of instruction operations in the storage medium 730 on the electronic device 700.

[0063] The electronic device 700 may also include one or more power supplies 740, one or more wired or wireless network interfaces 750, one or more input and output interfaces 750, and / or one or more operating systems 731, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, etc. It will be appreciated by those skilled in the art that Figure 8The structure of the electronic device shown does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine some components, or arrange the components differently.

[0064] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the express false weighing identification method.

[0065] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device or unit described above can refer to the corresponding process in the aforementioned method embodiment and will not be repeated here.

[0066] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the whole or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0067] As described above, the above embodiments 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 the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, 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 embodiments of the present invention.

Claims

1. A method for identifying false weighing of express delivery, characterized in that: include: Obtain the volume and corresponding weight data of the package in each logistics link; Preprocessing the acquired volume and corresponding weight data to obtain preprocessed volume and corresponding weight data; Anomaly analysis is performed on multiple pairs of preprocessed volume and corresponding weight data to identify abnormal data, and the abnormal data are marked as false weight.

2. The express delivery false weighing identification method according to claim 1 is characterized in that: The obtaining of the volume and corresponding weight data of the package in each logistics link includes: Obtaining volume data of packages in various logistics links based on at least one of 3D vision technology, light curtain measurement technology, ultrasonic measurement technology and laser measurement technology; The weight data of the package in each logistics link is obtained based on at least one of the intelligent weighing sensor and the weighing instrument.

3. The express delivery false weighing identification method according to claim 1 is characterized in that: The preprocessing of the acquired volume and corresponding weight data includes: The acquired volume and corresponding weight data are processed including removing noise and outliers to obtain denoised volume and corresponding weight data; The denoised volume and the corresponding weight data are standardized or normalized to obtain processed volume and the corresponding weight data.

4. The express delivery false weighing identification method according to claim 1 is characterized in that: The method of performing abnormal analysis on the plurality of pairs of pre-processed volume and corresponding weight data to identify abnormal data and marking the abnormal data as false weight includes: Obtain multiple pairs of preprocessed volume and corresponding weight data; For multiple pairs of preprocessed volume and corresponding weight data, cluster analysis is performed using a clustering algorithm to divide the preprocessed volume and corresponding weight data into multiple clusters, analyze the data characteristics of each cluster, identify abnormal clusters that are different from other clusters, and mark the abnormal clusters as false weighing; The clustering algorithms include K-Means clustering, hierarchical clustering and DBSCAN clustering.

5. The express delivery false weighing identification method according to claim 1 is characterized in that: The method of performing abnormal analysis on the plurality of pairs of pre-processed volume and corresponding weight data to identify abnormal data and marking the abnormal data as false weight includes: Based on the statistical analysis of historical data, the threshold range is determined, and the upper and lower limits of the package weight are set according to the determined threshold range. When the obtained package weight exceeds the upper and lower limits, it is considered to be abnormal data; The identified abnormal data is analyzed and verified based on the corresponding volume data and the courier's operation records, and a comprehensive judgment is made as to whether the current abnormal data is false weighing.

6. The express delivery false weighing identification method according to claim 1 is characterized in that: The method of performing abnormal analysis on the plurality of pairs of pre-processed volume and corresponding weight data to identify abnormal data and marking the abnormal data as false weight includes: Detect abnormal fluctuations in weight data through statistical analysis methods, calculate the average, standard deviation and variance of the data, and when the fluctuation of the data exceeds the preset range, it is considered abnormal data; The identified abnormal data is analyzed and verified based on the corresponding volume data and the courier's operation records, and a comprehensive judgment is made as to whether the current abnormal data is false weighing.

7. The method for identifying false weighing of express delivery according to claim 1, characterized in that: The method further comprises: Obtaining the weight data, volume data, courier's operation records and outlets' historical data of the parcel, and quantifying and standardizing the obtained weight data, volume data, courier's operation records and outlets' historical data; Based on the quantified and standardized weight and volume of the parcel, the courier's operation and outlets, the constructed risk assessment model is used to score the risk of false weighing. When the score value is higher than the threshold, an early warning is triggered. The risk assessment model is to score the risk by using one of the following methods: analytic hierarchy process, fuzzy comprehensive evaluation method, and neural network.

8. A device for identifying false weighing of express delivery, characterized in that: include: The data acquisition module is used to obtain the volume and corresponding weight data of the package in each logistics link; A data preprocessing module, used to preprocess the acquired volume and corresponding weight data to obtain preprocessed volume and corresponding weight data; The false weighing identification module is used to perform abnormal analysis on multiple pairs of pre-processed volume and corresponding weight data to identify abnormal data and mark the abnormal data as false weight.

9. 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 express false weighing identification method described in any one of claims 1 to 7 are implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the computer program is executed by a processor, the steps of the express false weighing identification method described in any one of claims 1 to 7 are implemented.

Images