An intelligent tracing logistics order exception processing system and method

Abstract

The present invention relates to the field of intelligent tracing technology, and in particular to an intelligent tracing logistics order exception processing system and method, comprising: processing and analyzing order data of orders in the same batch to obtain order time, judging whether orders in the same batch are abnormal, analyzing and obtaining batch fluctuation values ​​based on abnormal orders in the same batch, judging whether the batch order is a fluctuation batch based on the batch fluctuation value, and if so, determining a first tracing table according to the fluctuation batch, extracting all abnormal orders in the fluctuation batch, classifying the abnormal orders in the fluctuation batch according to transportation nodes and transportation package quality to obtain a second tracing table, and determining a reorganized tracing table based on the first tracing table and the second tracing table. The present invention selects a cluster center and calculates the distance from other points to the cluster center, which is helpful to classify abnormal orders, determine the reorganized tracing table, and is conducive to improving the tracing efficiency of abnormal orders and optimizing the tracing process.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent tracing, and in particular to a system and method for handling logistics order exceptions using intelligent tracing. Background Art

[0002] With the booming development of e-commerce, the scale of the logistics industry is growing, and the number of logistics orders is exploding. In the process of logistics transportation, various abnormal situations frequently occur, such as package delays, loss, damage, and wrong addresses. These problems not only bring extremely poor experience to customers, but also increase the operating costs and management difficulties of logistics companies.

[0003] The same batch of orders may have time deviations or anomalies due to various reasons (such as supply chain disruptions, weather changes, human errors, etc.), and the abnormal orders need to be traced. However, the traditional traceability process often relies on manual judgment and experience, which is inefficient and prone to errors. On the one hand, abnormal orders may involve multiple reasons and types, which need to be classified and identified; on the other hand, the processing of abnormal orders needs to be efficient and accurate to avoid interfering with the processing of normal orders.

[0004] To this end, we propose an intelligent traceability logistics order exception processing system and method. Summary of the invention

[0005] The object of the present invention is to provide a system and method for handling logistics order exceptions with intelligent tracing, so as to solve at least one of the above-mentioned problems of the prior art.

[0006] In a first aspect, the present invention provides a method for handling abnormal logistics orders with intelligent tracing, comprising: Step 1: Analyze the delivery time and arrival time of the orders in the same batch to obtain the order time. Based on the order time, determine whether the orders in the same batch are abnormal. The judgment results include normal orders and abnormal orders. Step 2: Based on the abnormal orders in the same batch of orders, the batch fluctuation value is analyzed and determined. Based on the batch fluctuation value, whether the batch order is a fluctuation batch is determined. If so, the first traceability table is determined according to the fluctuation batch. Step 3: Based on the fluctuation batch, all abnormal orders in the fluctuation batch are extracted, and the abnormal orders in the fluctuation batch are classified according to the transportation nodes and the quality of the transported packages to obtain clusters. Based on the clusters, the density center aggregation degree MD of the clusters is analyzed and obtained. Based on the density center aggregation degree MD of the clusters, the ranking is determined to obtain the second traceability table; Step 4: Based on the first traceability table and the second traceability table, determine the reorganized traceability table, and trace the abnormal orders according to the reorganized traceability table; Step 5: Based on the tracing of abnormal orders, according to the ranking of abnormal orders in the reorganized tracing table, the tracing time allocation coefficient is obtained through processing and analysis, and the tracing time of abnormal orders is allocated within the tracing cycle according to the tracing time allocation coefficient.

[0007] In a second aspect, the present invention provides a logistics order exception processing system with intelligent tracing, comprising: Order analysis module: The delivery time and arrival time of the orders in the same batch are analyzed to obtain the order time. Based on the order time, it is determined whether the orders in the same batch are abnormal. The judgment results include normal orders and abnormal orders. The first traceability table determination module: based on the abnormal orders in the same batch of orders, the batch fluctuation value is analyzed and determined, based on the batch fluctuation value, whether the batch order is a fluctuation batch, if so, the first traceability table is determined according to the fluctuation batch; Second traceability table determination module: based on the fluctuation batch, extract all abnormal orders in the fluctuation batch, classify the abnormal orders in the fluctuation batch according to the transportation node and the quality of the transport package, obtain clusters, analyze the clusters based on the clusters to obtain the density center aggregation degree MD of the clusters, and determine the sorting based on the density center aggregation degree MD of the clusters to obtain the second traceability table; Reorganization traceability table determination module: Based on the first traceability table and the second traceability table, the reorganization traceability table is determined, and abnormal orders are traced according to the reorganization traceability table; Tracing time allocation module: Based on tracing abnormal orders, according to the ranking of abnormal orders in the reorganized tracing table, the tracing time allocation coefficient is obtained through processing and analysis, and the tracing time of abnormal orders is allocated within the tracing cycle according to the tracing time allocation coefficient.

[0008] Beneficial effects of the present invention: 1. The present invention obtains the order time by processing and analyzing the delivery time and arrival time of the same batch of orders. Based on the order time, it is judged whether the orders in the same batch are abnormal. The judgment result includes normal orders and abnormal orders. Based on the abnormal orders in the same batch of orders, a batch fluctuation value is analyzed. Based on the batch fluctuation value, it is judged whether the batch order is a fluctuation batch. If so, a first tracing table is determined according to the fluctuation batch. The embodiment of the present invention quantitatively evaluates the volatility of the batch order through the identified abnormal orders, which is helpful to identify batches with large volatility. The abnormal orders in the fluctuation batch are sorted to obtain a first tracing sequence table, which is conducive to tracing the abnormal orders with large time deviations preferentially based on the time deviation.

[0009] 2. The present invention extracts all abnormal orders in the fluctuation batch based on the fluctuation batch, classifies the abnormal orders in the fluctuation batch according to the transportation nodes and the quality of the transported packages, obtains clusters, analyzes and obtains the density center aggregation degree MD of the clusters based on the clusters, determines the sorting and obtains the second traceability table based on the density center aggregation degree MD of the clusters, determines the reorganization traceability table based on the first traceability table and the second traceability table, and traces the abnormal orders according to the reorganization traceability table. This embodiment realizes an automated and unsupervised clustering process by selecting the cluster center and calculating the distance from other points to the cluster center, which is helpful for classifying the abnormal orders. By calculating the radius of the cluster cluster, the number of abnormal orders and the density center aggregation degree, the credibility of the clustering results can be quantitatively evaluated. By performing overlap analysis on the first traceability sequence table and the second traceability sequence table, the reorganization traceability table is determined, which is conducive to improving the traceability efficiency of the abnormal orders and optimizing the traceability process.

[0010] 3. The present invention is based on tracing abnormal orders. According to the ranking of abnormal orders in the reorganized tracing table, the tracing time allocation coefficient is processed and analyzed. The tracing time of abnormal orders is allocated within the tracing period according to the tracing time allocation coefficient. The present invention determines each abnormal order by obtaining the reorganized tracing table, and determines the tracing time allocation coefficient of the abnormal order. The coefficient reflects the importance of the abnormal order in the ranking, and then multiplies it with the length of the tracing period to obtain the tracing time. Tracing each abnormal order within the tracing period according to this time can ensure that the tracing time allocation is reasonable and the tracing is completed normally. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 It is a flow chart of a method for handling abnormal logistics orders with intelligent tracing according to an embodiment of the present invention; Figure 2 It is a block diagram of a logistics order exception processing system for intelligent tracing according to an embodiment of the present invention; Figure 3 It is a schematic diagram of the structure of a logistics order exception processing device for intelligent tracing according to an embodiment of the present invention; Figure numbers: 3, computer device; 301, processor; 302, memory; 303, computer program. DETAILED DESCRIPTION

[0013] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0014] Embodiment 1

[0015] Figure 1 A flowchart of a method for handling logistics order exceptions with intelligent tracing is provided in Embodiment 1 of the present invention. A method for handling logistics order exceptions with intelligent tracing can be performed by a system for handling logistics order exceptions with intelligent tracing. A system for handling logistics order exceptions with intelligent tracing can be implemented by software and / or hardware. A system for handling logistics order exceptions with intelligent tracing can be configured in a device for handling logistics order exceptions with intelligent tracing. Optionally, a device for handling logistics order exceptions with intelligent tracing can be an electronic device, which can be a notebook, a desktop computer, a smart tablet, etc., and this embodiment of the present invention does not limit this.

[0016] like Figure 1 As shown, an intelligent tracing logistics order exception processing method provided by an embodiment of the present invention specifically includes: Step 1: Obtain order data and transportation data of orders in the same batch, process and analyze the order data of orders in the same batch to obtain the order time, and determine whether the orders in the same batch are abnormal based on the order time. The determination results include normal orders and abnormal orders. Among them, order data includes delivery time and arrival time, and transportation data includes transportation nodes and transportation package quality; It should be noted that during the logistics order processing, the parcels transported by the logistics are usually equipped with RFID tags, and the order data and transportation data of the logistics order during the transportation process are recorded through the RFID tags; In some embodiments, the arrival time and the delivery time of the orders in the same batch of orders are subtracted to obtain the order time; It should be noted that the same batch of orders refers to a batch of orders with the same shipping address and delivery address; Compare the order time with the standard value for order time: If the order time is greater than the standard value of the order time, the corresponding order will be marked as an abnormal order; If the order time is less than or equal to the standard value of the order time, the corresponding order will be marked as a normal order; It should be noted that the standard value of order time is set by those skilled in the art based on past experience; Step 2: Based on the abnormal orders in the same batch of orders, the batch fluctuation value is analyzed and determined. Based on the batch fluctuation value, whether the batch order is a fluctuation batch is determined. If so, the first traceability table is determined according to the fluctuation batch. Get the order time of all abnormal orders in the same batch of orders, sum and average them, and get the average time of abnormal orders; Combine the order times of all abnormal orders in the same batch of orders into an abnormal order time data group, and calculate the variance value of the abnormal order time data group; Ratio the mean value of abnormal order time to the variance value of the abnormal order time data group to obtain the coefficient of variation BY; Count the number of abnormal orders, and perform ratio processing on the number of abnormal orders and the total number of orders to obtain the abnormal order number ratio DS; Subtract the order time corresponding to the abnormal order from the standard value of the order time to obtain the order time deviation value, sum and average the order time deviation values ​​of all abnormal orders to obtain the order time deviation mean, and compare the order time deviation mean with the standard value of the order time to obtain the abnormal order time deviation ratio DC; The coefficient of variation BY, abnormal order quantity ratio DS and abnormal order deviation ratio DC are processed by the formula: The batch fluctuation value DY is calculated, where s1, s2, and s3 are all preset proportional coefficients, s1 is 1.633, s2 is 1.528, and s3 is 1.661; Compare the batch fluctuation value to the batch fluctuation threshold: If the batch fluctuation value is greater than the batch fluctuation threshold, the corresponding batch will be marked as a fluctuation batch; If the batch fluctuation value is less than or equal to the batch fluctuation threshold, the corresponding batch is marked as a normal batch; Based on the fluctuation batch, all abnormal orders in the fluctuation batch are sorted from large to small according to the order time deviation value to obtain the first traceability table; The technical solution of this embodiment is: obtaining order data and transportation data of orders in the same batch, processing and analyzing the order data of orders in the same batch to obtain order time, judging whether orders in the same batch are abnormal based on order time, and the judgment results include normal orders and abnormal orders, analyzing and obtaining batch fluctuation values ​​based on abnormal orders in the same batch, judging whether the batch order is a fluctuation batch based on the batch fluctuation value, and if so, determining a first traceability table based on the fluctuation batch. The embodiment of the present invention quantitatively evaluates the volatility of the batch order through the identified abnormal orders, which helps to identify batches with larger volatility, and sorts the abnormal orders in the fluctuation batch to obtain a first traceability sequence table, which is conducive to tracing abnormal orders with large time deviations preferentially based on time deviations.

[0017] Embodiment 2

[0018] like Figure 1 As shown, an intelligent tracing logistics order exception processing method provided by an embodiment of the present invention specifically includes: Step 3: Based on the fluctuation batch, all abnormal orders in the fluctuation batch are extracted, and the abnormal orders in the fluctuation batch are classified according to the transportation nodes and the quality of the transported packages to obtain clusters. Based on the clusters, the density center aggregation degree MD of the clusters is analyzed and obtained. Based on the density center aggregation degree MD of the clusters, the ranking is determined to obtain the second traceability table; In some embodiments, the delivery time and receipt time of all abnormal orders in the fluctuation batch are combined into a group of abnormal order feature vectors, and marked as an abnormal order feature vector group; Convert the abnormal order feature vector group into N-dimensional discrete points, where N represents the number of elements in the abnormal order feature vector group; S11, select any N-dimensional discrete point as the cluster center Z1, and integrate the other N-dimensional discrete points into Where n represents the number of other N-dimensional discrete points; S12, by formula: Calculate the distances from other N-dimensional discrete points to the cluster center Z1, where i=1, 2, …, n, sort the distances from other N-dimensional discrete points to the cluster center Z1 from large to small, and take the maximum distance from other N-dimensional discrete points to the cluster center Z1 as the cluster center Z2; S13, by formula: Calculate the distance D between two cluster centers; S14, by formula: Calculate the distance from other N-dimensional discrete points to the cluster center Z1 , through the formula Calculate the distance from other N-dimensional discrete points to the cluster center Z2 , select the minimum of the two distances ,like , then the current N-dimensional discrete point is used as the cluster center Z3; S15, and so on, until the number of cluster centers no longer increases; S16, recalculating the Euclidean distances from other N-dimensional discrete points to each cluster center; The Euclidean distances from all abnormal orders in the cluster to the cluster center are summed and averaged to obtain the radius BJ of the cluster; Count the number of abnormal orders in the cluster and mark them as BS; The radius BJ of the cluster and the number BS of abnormal orders in the cluster are processed by the formula: Calculate the density center aggregation degree MD of the cluster; It should be noted that when the number of abnormal orders contained in the cluster is greater and the radius of the cluster is smaller, the cluster where the abnormal orders are located is denser, the greater the degree of concentration of the density center of the cluster, and the higher the credibility of the clustering result of the cluster. One cluster center corresponds to one cluster. The greater the degree of concentration of the density center of the cluster, the higher the degree of concentration of the data points in the cluster. Based on the density center aggregation degree MD of the clusters, the density center aggregation degrees of all clusters are sorted from large to small to obtain a cluster sorting table; Based on the cluster sorting table, all abnormal orders in the cluster are sorted from large to small according to the order time deviation value to obtain the second traceability table; It should be noted that the cluster sorting table helps to analyze the characteristics of orders under different logistics business links or transportation conditions, and provides clues for further exploring the causes of abnormalities. The abnormal orders in each cluster are sorted from large to small according to the order time deviation value in order to further focus on the performance of abnormal orders in the time dimension; Step 4: Based on the first traceability table and the second traceability table, determine the reorganized traceability table, and trace the abnormal orders according to the reorganized traceability table; The first tracing table and the second tracing table are overlapped and analyzed, specifically: Mark the abnormal orders in the first traceability table as the first time order, the second time order, ..., the kth time order, where k represents the number of the abnormal order in the first traceability table; Mark the abnormal orders in the second traceability table as the first classification order, the second classification order, ..., the jth classification order, where j represents the number of the traceable order in the second traceability table; Combine the first time order with the first category order, the second time order with the second category order, ..., the kth time order with the jth category order into a comparison data group; If the time order in the comparison data group is the same as the classification order in the current comparison data group, the corresponding comparison data group is marked as a matching data group; If the time order in the comparison data group is not the same as the classification order in the current comparison data group, the corresponding comparison data group is marked as an unmatched data group; Count the number of matching data groups, and compare it with the total number of comparison data groups to obtain the proportion of matching data groups; If 0≤the proportion of matching data groups<1, a recombination signal is generated; If the matching data group ratio = 1, the abnormal order is traced according to the first traceability table; Based on the recombination signal, the elements in the unmatched data group are analyzed to obtain the recombination number, and based on the recombination number, a recombination traceability table is obtained; It should be noted that the elements of the unmatched data set include time orders and classification orders; Obtain the unmatched data group when the reorganization signal is generated, sum and average the numbers corresponding to the time orders in the unmatched data group and the numbers corresponding to the classified orders in the unmatched data group to obtain the reorganization number, sort the reorganization numbers from large to small, obtain the reorganization traceability table, and trace the abnormal orders according to the reorganization traceability table; It should be noted that if the reorganization numbers are the same, the abnormal orders corresponding to the reorganization numbers will be sorted in the first traceability table according to their numbering sequence; The technical solution of this embodiment is as follows: based on the fluctuation batch, all abnormal orders in the fluctuation batch are extracted, and the abnormal orders in the fluctuation batch are classified according to the transportation nodes and the quality of the transported packages to obtain clusters. Based on the clusters, the density center aggregation degree MD of the clusters is analyzed, and the second traceability table is determined based on the density center aggregation degree MD of the clusters. Based on the first traceability table and the second traceability table, a reorganized traceability table is determined, and the abnormal orders are traced according to the reorganized traceability table. The present invention realizes an automated and unsupervised clustering process by selecting a cluster center and calculating the distance from other points to the cluster center, which is helpful for classifying abnormal orders. By calculating the radius of the cluster, the number of abnormal orders and the density center aggregation degree of the cluster, the credibility of the clustering results can be quantitatively evaluated. By performing overlap analysis on the first traceability sequence table and the second traceability sequence table, the reorganized traceability table is determined, which is conducive to improving the traceability efficiency of abnormal orders and optimizing the traceability process.

[0019] Embodiment 3

[0020] Based on the first and second embodiments, a method for handling abnormalities in logistics orders with intelligent tracing according to an embodiment of the present invention includes: Step 5: Based on the tracing of abnormal orders, according to the ranking of abnormal orders in the reorganized tracing table, the tracing time allocation coefficient is obtained through processing and analysis, and the tracing time of abnormal orders is allocated within the tracing cycle according to the tracing time allocation coefficient; Specifically, a reorganization traceability table (Dd1, Dd2, Dd3, ..., Ddm) is obtained, where Ddm represents the abnormal order ranked m, and m represents the ranking number; Based on any abnormal order, determine the traceability time allocation coefficient of the abnormal order. Specifically, use the formula: Get the traceability time allocation coefficient ZF of abnormal orders, where m max represents the maximum ranking of abnormal orders, m 总 Indicates the sum of ranking numbers; It should be noted that the formula: The meaning is: the ranking of the abnormal order is compared with the maximum ranking and the inverse is taken. The purpose is to judge the importance of the abnormal order in the ranking. For example, if the ranking is 1-30, the abnormal order ranked first should be traced first and needs to be traced in detail. , then the importance of the first-ranked abnormal order is 30; at the same time, the rankings of all abnormal orders are summed up to get the total ranking m 总 , the importance of abnormal orders is processed by ratio with the total ranking, and the importance ratio of abnormal orders among all abnormal orders is obtained, which is the traceability time allocation coefficient ZF of abnormal orders; The tracing time allocation coefficient ZF of the abnormal order is multiplied by the time length corresponding to the tracing cycle to obtain the tracing time of the abnormal order; During the tracing cycle, each abnormal order is traced according to the corresponding tracing time, which is conducive to ensuring the rationality of the time allocation of tracing and ensuring the normal completion of tracing.

[0021] The technical solution of the embodiment of the present invention is: based on tracing abnormal orders, according to the ranking of abnormal orders in the reorganized tracing table, the tracing time allocation coefficient is processed and analyzed, and the tracing time of abnormal orders is allocated within the tracing period according to the tracing time allocation coefficient. The present invention determines each abnormal order by obtaining the reorganized tracing table, determines the tracing time allocation coefficient of the abnormal order, and the coefficient reflects the importance of the abnormal order in the ranking, and then multiplies the coefficient with the length of the tracing period to obtain the tracing time. According to this time, each abnormal order is traced within the tracing period, which can ensure that the tracing time allocation is reasonable and the tracing is completed normally.

[0022] Embodiment 4

[0023] like Figure 2 As shown, an intelligent tracing logistics order exception processing system provided by an embodiment of the present invention specifically includes: Order analysis module: The delivery time and arrival time of the orders in the same batch are analyzed to obtain the order time. Based on the order time, it is determined whether the orders in the same batch are abnormal. The judgment results include normal orders and abnormal orders. The first traceability table determination module: based on the abnormal orders in the same batch of orders, the batch fluctuation value is analyzed and determined, based on the batch fluctuation value, whether the batch order is a fluctuation batch, if so, the first traceability table is determined according to the fluctuation batch; Second traceability table determination module: based on the fluctuation batch, extract all abnormal orders in the fluctuation batch, classify the abnormal orders in the fluctuation batch according to the transportation node and the quality of the transport package, obtain clusters, analyze the clusters based on the clusters to obtain the density center aggregation degree MD of the clusters, and determine the sorting based on the density center aggregation degree MD of the clusters to obtain the second traceability table; Reorganization traceability table determination module: Based on the first traceability table and the second traceability table, the reorganization traceability table is determined, and abnormal orders are traced according to the reorganization traceability table; Tracing time allocation module: Based on tracing abnormal orders, according to the ranking of abnormal orders in the reorganized tracing table, the tracing time allocation coefficient is obtained through processing and analysis, and the tracing time of abnormal orders is allocated within the tracing cycle according to the tracing time allocation coefficient.

[0024] Embodiment 5

[0025] Reference Figure 3 The embodiment of the present invention further provides a computer device 3, comprising: a memory 302 and a processor 301 and a computer program 303 stored in the memory 302. When the computer program 303 is executed on the processor 301, an intelligent traceability logistics order exception processing method as described in any one of the above methods is implemented.

[0026] The computer device 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will appreciate that Figure 3 It is only an example of computer device 3 and does not constitute a limitation on computer device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0027] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0028] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as a hard disk or memory of the computer device 3. In other embodiments, the memory 302 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device 3. Further, the memory 302 may also include both an internal storage unit of the computer device 3 and an external storage device. The memory 302 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory 302 may also be used to temporarily store data that has been output or is to be output.

[0029] Embodiment 6

[0030] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for handling logistics order exceptions with intelligent tracing as described in any one of the above methods is implemented.

[0031] In this embodiment, 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 present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, USB flash drive, mobile hard disk, disk or optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0032] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0033] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0034] In the embodiments disclosed in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0035] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0036] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0037] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A method for handling abnormal logistics orders with intelligent tracing, characterized in that: include: Step 1: Analyze the delivery time and arrival time of the orders in the same batch to obtain the order time. Based on the order time, determine whether the orders in the same batch are abnormal. The judgment results include normal orders and abnormal orders. Step 2: Based on the abnormal orders in the same batch of orders, the batch fluctuation value is analyzed and determined. Based on the batch fluctuation value, whether the batch order is a fluctuation batch is determined. If so, the first traceability table is determined according to the fluctuation batch. Step 3: Based on the fluctuation batch, all abnormal orders in the fluctuation batch are extracted, and the abnormal orders in the fluctuation batch are classified according to the transportation nodes and the quality of the transported packages to obtain clusters. Based on the clusters, the density center aggregation degree MD of the clusters is analyzed and obtained. Based on the density center aggregation degree MD of the clusters, the ranking is determined to obtain the second traceability table; Step 4: Based on the first traceability table and the second traceability table, determine the reorganized traceability table, and trace the abnormal orders according to the reorganized traceability table; Step 5: Based on the tracing of abnormal orders, according to the ranking of abnormal orders in the reorganized tracing table, the tracing time allocation coefficient is obtained through processing and analysis, and the tracing time of abnormal orders is allocated within the tracing cycle according to the tracing time allocation coefficient.

2. According to claim 1, a method for handling abnormal logistics orders with intelligent tracing is characterized in that: The batch fluctuation value is obtained as follows: Extract all abnormal orders in the same batch of orders, analyze and obtain the coefficient of variation BY, abnormal order quantity ratio DS, and abnormal order time deviation ratio DC; The coefficient of variation BY, abnormal order quantity ratio DS and abnormal order deviation ratio DC are processed by the formula: The batch fluctuation value DY is calculated, where s1, s2, and s3 are all preset proportional coefficients.

3. According to claim 2, a method for handling abnormal logistics orders with intelligent tracing is characterized in that: The coefficient of variation BY, the abnormal order quantity ratio DS, and the abnormal order time deviation ratio DC are obtained as follows: Subtract the arrival time from the delivery time of the orders in the same batch to get the order time; Get the order time of all abnormal orders in the same batch of orders, sum and average them, and get the average time of abnormal orders; Combine the order times of all abnormal orders in the same batch of orders into an abnormal order time data group, and calculate the variance value of the abnormal order time data group; Ratio the mean value of abnormal order time to the variance value of the abnormal order time data group to obtain the coefficient of variation BY; Count the number of abnormal orders, and perform ratio processing on the number of abnormal orders and the total number of orders to obtain the abnormal order number ratio DS; The order time corresponding to the abnormal order is subtracted from the standard value of the order time to obtain the order time deviation value. The order time deviation values ​​of all abnormal orders are summed and averaged to obtain the order time deviation mean. The order time deviation mean is compared with the standard value of the order time to obtain the abnormal order time deviation ratio DC.

4. According to claim 1, a method for handling abnormal logistics orders with intelligent tracing is characterized in that: The density center aggregation degree MD of the cluster is obtained as follows: Extract abnormal orders from the fluctuation batches, analyze and obtain clusters, and determine the radius BJ of the cluster and the number BS of abnormal orders in the cluster based on the clusters; The radius BJ of the cluster and the number BS of abnormal orders in the cluster are processed by the formula: The density center aggregation degree MD of the clusters is calculated.

5. According to claim 4, a method for handling abnormal logistics orders with intelligent tracing is characterized in that: The clustering process is as follows: Combine the delivery time and receipt time of all abnormal orders in the fluctuation batch into a set of abnormal order feature vectors and mark them as abnormal order feature vector group; Convert the abnormal order feature vector group into N-dimensional discrete points, where N represents the number of elements in the abnormal order feature vector group; Select any N-dimensional discrete point as the cluster center Z1, and integrate the other N-dimensional discrete points into , where n represents the number of other N-dimensional discrete points; By formula: Calculate the distances from other N-dimensional discrete points to the cluster center Z1, where i=1, 2, …, n, sort the distances from other N-dimensional discrete points to the cluster center Z1 from large to small, and take the maximum distance from other N-dimensional discrete points to the cluster center Z1 as the cluster center Z2; By formula: Calculate the distance D between two cluster centers; By formula: Calculate the distance from other N-dimensional discrete points to the cluster center Z1 , through the formula: Calculate the distance from other N-dimensional discrete points to the cluster center Z2 , select the minimum of the two distances ,like , then the current N-dimensional discrete point is used as the cluster center Z3; And so on, until the number of cluster centers no longer increases; Recalculate the Euclidean distances from other N-dimensional discrete points to each cluster center.

6. According to claim 4, a method for handling abnormal logistics orders with intelligent tracing is characterized in that: The process of obtaining the radius BJ of the cluster and the number BS of abnormal orders in the cluster is as follows: The Euclidean distances from all abnormal orders in the cluster to the cluster center are summed and averaged to obtain the radius BJ of the cluster; Count the number of abnormal orders in the cluster and mark them as BS.

7. The method for handling abnormal logistics orders with intelligent tracing according to claim 1 is characterized in that: The first tracing table and the second tracing table are obtained in the following manner: Based on the fluctuation batch, all abnormal orders in the fluctuation batch are sorted from large to small according to the order time deviation value to obtain the first traceability table; Based on the density center aggregation degree MD of the clusters, the density center aggregation degrees of all clusters are sorted from large to small to obtain a cluster sorting table; Based on the cluster sorting table, all abnormal orders in the cluster are sorted from large to small according to the order time deviation value to obtain the second traceability table.

8. The method for handling abnormal logistics orders with intelligent tracing according to claim 7 is characterized in that: The method for obtaining the reorganization traceability table is as follows: Mark the abnormal orders in the first traceability table as the first time order, the second time order, ..., the kth time order, where k represents the number of the abnormal order in the first traceability table; Mark the abnormal orders in the second traceability table as the first classification order, the second classification order, ..., the jth classification order, where j represents the number of the traceable order in the second traceability table; Combine the first time order with the first category order, the second time order with the second category order, ..., the kth time order with the jth category order into a comparison data group; If the time order in the comparison data group is the same as the classification order in the current comparison data group, the corresponding comparison data group is marked as a matching data group; If the time order in the comparison data group is not the same as the classification order in the current comparison data group, the corresponding comparison data group is marked as an unmatched data group; Count the number of matching data groups, and compare it with the total number of comparison data groups to obtain the proportion of matching data groups; If 0≤the proportion of matching data groups<1, a recombination signal is generated; If the matching data group ratio = 1, the abnormal order is traced according to the first traceability table; Based on the recombination signal, the elements in the unmatched data group are analyzed to obtain the recombination number, and based on the recombination number, a recombination traceability table is obtained; Obtain the mismatched data group when generating the reorganization signal, sum and average the numbers corresponding to the time orders in the mismatched data group and the numbers corresponding to the classified orders in the mismatched data group to obtain the reorganization number, sort the reorganization numbers from large to small, obtain the reorganization traceability table, and trace the abnormal orders according to the reorganization traceability table.

9. The method for handling abnormal logistics orders with intelligent tracing according to claim 8 is characterized in that: The method for obtaining the traceability time allocation coefficient is as follows: Get the reorganization traceability table (Dd1, Dd2, Dd3...Ddm), where Ddm represents the abnormal order ranked m, and m represents the ranking number; Based on any abnormal order, determine the traceability time allocation coefficient of the abnormal order. Specifically, use the formula: Get the traceability time allocation coefficient ZF of abnormal orders, where m max represents the maximum ranking of abnormal orders, m 总 Indicates the sum of ranking numbers; The tracing time allocation coefficient ZF of the abnormal order is multiplied by the time length corresponding to the tracing cycle to obtain the tracing time of the abnormal order; During the tracing cycle, each abnormal order is traced according to the corresponding tracing time, which is conducive to ensuring the rationality of the time allocation of tracing and ensuring the normal completion of tracing.

10. An intelligent tracing logistics order exception processing system, the system implements an intelligent tracing logistics order exception processing method as claimed in any one of claims 1 to 9, characterized in that: include: Order analysis module: The delivery time and arrival time of the orders in the same batch are analyzed to obtain the order time. Based on the order time, it is determined whether the orders in the same batch are abnormal. The judgment results include normal orders and abnormal orders. The first traceability table determination module: based on the abnormal orders in the same batch of orders, the batch fluctuation value is analyzed and determined, based on the batch fluctuation value, whether the batch order is a fluctuation batch, if so, the first traceability table is determined according to the fluctuation batch; Second traceability table determination module: based on the fluctuation batch, extract all abnormal orders in the fluctuation batch, classify the abnormal orders in the fluctuation batch according to the transportation node and the quality of the transport package, obtain clusters, analyze the clusters based on the clusters to obtain the density center aggregation degree MD of the clusters, and determine the sorting based on the density center aggregation degree MD of the clusters to obtain the second traceability table; Reorganization traceability table determination module: Based on the first traceability table and the second traceability table, the reorganization traceability table is determined, and abnormal orders are traced according to the reorganization traceability table; Tracing time allocation module: Based on tracing abnormal orders, according to the ranking of abnormal orders in the reorganized tracing table, the tracing time allocation coefficient is obtained through processing and analysis, and the tracing time of abnormal orders is allocated within the tracing cycle according to the tracing time allocation coefficient.

Images