A logistics problem influence factor analysis method and online analysis system

Abstract

The application discloses a logistics problem influence factor analysis method and an online analysis system, and relates to the technical field of logistics problem analysis.

Description

A method and online analysis system for analyzing the influencing factors of logistics problems Technical Field

[0001] This invention relates to the field of logistics big data technology, specifically to a method and online analysis system for analyzing the influencing factors of logistics problems. Background Technology

[0002] In the fiercely competitive logistics industry, express delivery companies are constantly striving to improve the logistics experience in order to win market share and users. The logistics experience encompasses many aspects, which can be broadly categorized into two types: timeliness and quality. Timeliness focuses on the punctuality and certainty of package delivery, while quality focuses on whether packages are damaged or lost during transit.

[0003] Logistics operations are affected by multiple links and factors, and the correlation and collaborative interaction between business nodes in the supply chain and data from various information systems are unclear. How to determine the factors affecting logistics efficiency and their importance is a technical problem that urgently needs to be solved.

[0004] In traditional operations, problem governance typically requires business-side operations experts or frontline managers to rely on their extensive experience to identify potential areas of concern and define the necessary data definitions. Technical personnel then schedule data development based on the business's requirements. Once the business receives the analyzed data, they can decide whether to address a specific area and what concrete implementation measures to take. This problem analysis and decision-making process has significant limitations: high technical development costs, a lack of ability to compare different analytical approaches, and insufficient data dimensions to support business decisions. Due to these shortcomings, problem analysis becomes a high-barrier, high-cost, and low-return endeavor.

[0005] With the widespread application of big data technology, comprehensive big data analysis of express delivery can be achieved through intelligent collection, integration, and processing of information from various stages such as express procurement, transportation, packaging, loading and unloading, distribution, and information services. Existing technology, Chinese patent application publication number CN115564216A, discloses a method for determining key nodes in the tobacco industry logistics supply chain, including: acquiring and analyzing the business flow and data flow of the tobacco industry logistics supply chain; identifying key business nodes and related factors; determining key nodes and influencing factors in the supply chain, and determining the weights of the corresponding influencing factors. This solution provides a reasonable direction and method for improving the efficiency of the logistics supply chain; however, it cannot guarantee the comprehensiveness and real-time nature of the analysis of relevant influencing factors, lacks flexibility in the analysis path, and cannot provide visualized data drill-down functionality. Summary of the Invention

[0006] In view of the above problems, this invention proposes a logistics problem influencing factor analysis method to overcome or at least partially solve the above problems. Using parcels as the analysis granularity, obtaining detailed parcel information enables the establishment of relationships between various entities in the logistics network. It also obtains a large amount of information reflecting various aspects involved in the parcel circulation process, such as order information and customer complaint data, thereby improving the comprehensiveness and universality of the influencing factor library and problem label library. During factor correlation analysis, it can statistically analyze the positive and negative sample data of labels corresponding to different factor values ​​in real time, and calculate the analysis results in real time by customizing the analysis path, thus improving the efficiency and flexibility of factor correlation analysis.

[0007] According to a first aspect of the present invention, a method for analyzing the influencing factors of logistics problems is provided, comprising: obtaining detailed information of parcels in a logistics network, the detailed information including at least operation records, order information and customer complaint data; constructing an influencing factor library based on the operation records of the parcels; constructing a problem label library based on the order information and customer complaint data of the parcels; calculating the correlation between factors in the influencing factor library and the problem label library and the target problem based on the IV value evaluation method, and obtaining the factor analysis results.

[0008] Optionally, in the logistics problem influencing factor analysis method provided by the present invention, the operation records, order information and customer complaint data of the package in the logistics network are obtained. The logistics network includes operation entities and circulation entities. The operation entities include contracted areas, transfer centers and independent outlets. The circulation entities include operation equipment, operators, vehicles and packaging. The order information includes merchant ID, customer ID, delivery address, delivery address, delivery time and delivery time. The customer complaint data includes customer complaint information, package problem records and claim work orders.

[0009] Optionally, in the logistics problem influencing factor analysis method provided by the present invention, the relationship between different entities in the logistics network is constructed based on the operation records of packages in the logistics network; factors with business meaning are obtained based on business knowledge; and an influencing factor library is constructed based on the relationship between different entities and factors with business meaning.

[0010] Optionally, in the logistics problem influencing factor analysis method provided by the present invention, it is determined whether there is a delay problem in the package based on the receipt time and delivery time in the package order information; it is determined whether there are problems such as loss, damage, problem items, and complaints in the package based on the customer complaint data of the package; if a certain problem item exists in the package, it is labeled as 1, and if a certain problem item does not exist, it is labeled as 0, thus obtaining a problem label library for each package.

[0011] Optionally, in the logistics problem influencing factor analysis method provided by the present invention, the number of packages with a corresponding problem item label of 1 in the influencing factor library under different factor values ​​is counted as the number of bad samples; the number of packages with a corresponding problem item label of 0 in the influencing factor library under different factor values ​​is counted as the number of good samples; the correlation between the factors and the target problem is calculated based on the following formula:

[0012] ;

[0013] bad j Let be the number of bad samples in the j-th impact factor. T This indicates the total number of bad samples;

[0014] good j Let good be the number of good samples in the j-th impact factor. T This represents the total number of good samples; factor analysis results for each target question are obtained by ranking based on IV values.

[0015] Optionally, in the logistics problem influencing factor analysis method provided by the present invention, the target problem, the range of analysis data in the influencing factor library and the analysis path are preset; the constructed influencing factor library is synchronized to the ClickHouse database engine according to the preset analysis data range to form a materialized view; and the correlation between the preset target problem and the factors in the materialized view is calculated layer by layer along the analysis path based on SQL statements.

[0016] According to a second aspect of the present invention, an online analysis system for logistics problem influencing factors is provided, comprising a client, a ClickHouse database management system, and an ODPS offline database. The ODPS offline database is used to process and analyze the detailed information of packages to generate an influencing factor library and a problem tag library, and synchronizes the generated influencing factor library and problem tag library to the ClickHouse database management system. The ClickHouse database management system is used to construct materialized views of the factors in the influencing factor library according to the inclusion and association relationships, and calculate the IV values ​​between the preset target problem and the factors in the materialized views layer by layer along a preset analysis path. The client is used to display the IV value sorting results along the drill-down path in real time.

[0017] Optionally, in the above-mentioned online analysis system for logistics problem impact factors, the ClickHouse database engine is used to pre-calculate IV values ​​for factors in the impact factor library and problems in the problem tag library in the ODPS offline database, and store the pre-calculated IV values ​​in the cache.

[0018] According to a third aspect of the present invention, a computing device is provided, comprising: at least one processor; and a memory storing program instructions, wherein the program instructions are configured to be executed by the at least one processor, the program instructions including instructions for performing the above-described method for analyzing the influencing factors of logistics problems.

[0019] According to a fourth aspect of the present invention, a readable storage medium storing program instructions is provided, which, when read and executed by a computing device, causes the computing device to perform the above-described method for analyzing the influencing factors of logistics problems.

[0020] According to the logistics problem influencing factor analysis method provided by the present invention, taking packages as the analysis granularity, obtaining detailed information about packages can establish the relationship between various entities in the logistics network, and obtain a large amount of information reflecting various fields involved in the package circulation process, such as order information and customer complaint data, which can improve the comprehensiveness and universality of the construction of the influencing factor library and problem tag library.

[0021] The online analysis system for logistics problem influencing factors provided by this invention can, in the process of factor correlation analysis, statistically analyze the positive and negative sample data of labels corresponding to different factor values ​​in real time based on the ClickHouse database engine. The analysis results can be obtained in real time by customizing and adjusting the analysis path, which can improve the efficiency and flexibility of factor correlation analysis.

[0022] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it in accordance with the contents of the specification, and in order to make the above and other objects, features and advantages of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0023] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0024] Figure 1 shows a structural block diagram of a computing device 100 according to an embodiment of the present invention;

[0025] Figure 2 shows a flowchart of a logistics problem influencing factor analysis method 200 according to an embodiment of the present invention;

[0026] Figure 3 shows a schematic diagram of the system architecture of an online analysis system for logistics problem influencing factors according to an embodiment of the present invention;

[0027] Figure 4 shows a schematic diagram of the drilling path according to an embodiment of the present invention. Detailed Implementation

[0028] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0029] Driven by the internet, the logistics industry has developed rapidly. However, the efficiency of traditional logistics is increasingly difficult to maintain in the market, making the digitalization and intelligentization of the logistics industry an inevitable trend.

[0030] Big data analytics in logistics can improve transportation and delivery efficiency, reduce logistics costs, and more effectively meet customer service requirements. Logistics big data effectively combines cargo flow data, express delivery companies, and supply and demand sides to form a massive, real-time information platform.

[0031] To enable real-time analysis of factors affecting logistics timeliness and quality, this solution provides a method for analyzing the influencing factors of logistics problems. It constructs an influencing factor library and a problem tag library covering the entire logistics network, using packages as the analysis granularity. Based on the Clickhouse data engine, it realizes online factor correlation analysis, which can improve the efficiency and flexibility of factor correlation analysis.

[0032] Figure 1 shows a structural diagram of a computing device 100 according to an embodiment of the present invention. As shown in Figure 1, in a basic configuration 102, the computing device 100 typically includes a system memory 106 and one or more processors 104. A memory bus 108 can be used for communication between the processors 104 and the system memory 106.

[0033] Depending on the desired configuration, processor 104 can be any type of processor, including but not limited to: microprocessors (µP), microcontrollers (µC), digital information processors (DSPs), or any combination thereof. Processor 104 may include one or more levels of cache such as L1 cache 110 and L2 cache 112, processor core 114, and registers 116. Example processor core 114 may include an arithmetic logic unit (ALU), a floating-point unit (FPU), a digital signal processing core (DSP core), or any combination thereof. Example memory controller 118 may be used with processor 104, or in some implementations, memory controller 118 may be an internal part of processor 104.

[0034] Depending on the desired configuration, system memory 106 can be any type of memory, including but not limited to: volatile memory (such as RAM), non-volatile memory (such as ROM, flash memory, etc.), or any combination thereof. Physical memory in a computing device typically refers to volatile RAM, and data on a disk needs to be loaded into physical memory before it can be read by processor 104. System memory 106 may include operating system 120, one or more applications 122, and program data 124.

[0035] In some implementations, application 122 may be configured to execute instructions on an operating system using program data 124 by one or more processors 104. The operating system 120 may be, for example, Linux, Windows, etc., and includes program instructions for handling basic system services and performing hardware-dependent tasks. Application 122 includes program instructions for implementing various user-desired functions; application 122 may be, for example, a browser, instant messaging software, software development tools (e.g., integrated development environment IDE, compiler, etc.), but is not limited thereto. When application 122 is installed in computing device 100, driver modules may be added to operating system 120.

[0036] When computing device 100 starts up, processor 104 reads and executes program instructions from memory 106 of operating system 120. Application 122 runs on operating system 120, utilizing interfaces provided by operating system 120 and underlying hardware to implement various user-expected functions. When user starts application 122, application 122 is loaded into memory 106, and processor 104 reads and executes program instructions from memory 106 of application 122.

[0037] The computing device 100 also includes a storage device 132, which includes a removable storage device 136 and a non-removable storage device 138, both of which are connected to a storage interface bus 134.

[0038] The computing device 100 may also include an interface bus 140 that facilitates communication from various interface devices (e.g., output devices 142, peripheral interfaces 144, and communication devices 146) to the basic configuration 102 via a bus / interface controller 130. Example output devices 142 include a graphics processing unit 148 and an audio processing unit 150. They may be configured to facilitate communication with various external devices such as displays or speakers via one or more A / V ports 152. Example peripheral interfaces 144 may include a serial interface controller 154 and a parallel interface controller 156, which may be configured to facilitate communication with external devices such as input devices (e.g., keyboards, mice, pens, voice input devices, touch input devices) or other peripherals (e.g., printers, scanners, etc.) via one or more I / O ports 158. Example communication devices 146 may include a network controller 160, which may be arranged to facilitate communication with one or more other computing devices 162 via a network communication link through one or more communication ports 164.

[0039] A network communication link can be an example of a communication medium. A communication medium can typically be embodied in computer-readable instructions, data structures, or program modules within a modulated data signal, such as a carrier wave or other transmission mechanism, and can include any information delivery medium. A “modulated data signal” can be a signal whose data set, or whose modifications, can be encoded with information within the signal. As a non-limiting example, a communication medium can include wired media such as wired networks or leased lines, and various wireless media including sound, radio frequency (RF), microwave, infrared (IR), or other wireless media. The term “computer-readable medium” as used herein can include both storage media and communication media. In the computing device 100 according to the invention, application 122 includes instructions for performing the logistics problem impact factor analysis method 200 of the invention.

[0040] Factor analysis is a method that summarizes a few comprehensive factors that highlight data information by studying the internal dependencies of multiple related original variables. For the governance of logistics timeliness and quality issues, it is necessary to conduct correlation analysis between the target problem and the influencing factors.

[0041] To determine the correlation between the target problem and its influencing factors, this solution provides a method for analyzing the influencing factors of logistics problems. Figure 2 shows a flowchart of a logistics problem influencing factor analysis method 200 according to an embodiment of the present invention. As shown in Figure 2, the method 200 begins at step S210, obtaining detailed information about the package in the logistics network. The detailed information includes at least operation records, order information, and customer complaint data.

[0042] The logistics network comprises routes and nodes, and can be hierarchically divided. This includes operational entities such as distribution centers or transit centers, independent outlets, and contracted areas, as well as circulation entities such as equipment, employees, vehicles, packaging, and parts. Package order information includes merchant ID, customer ID, delivery address, sender address, delivery time, and dispatch time. Corresponding customer complaint data includes customer complaint information, package issue records, and claim work orders.

[0043] Each entity has one or more attributes. For example, equipment has a type attribute, vehicles have attributes such as shift number and license plate number, and packages have attributes such as weight and volume. Entities can be linked through information such as package operation records. For instance, if a package is loaded onto a vehicle at a cross-belt machine in a transfer center, a relationship can be established between the transfer center, the cross-belt machine, and the vehicle.

[0044] Using parcels as the analytical granularity for influencing logistics issues can effectively integrate various information across the entire logistics network, and most timeliness and quality issues can be broken down into the information carried by a single parcel.

[0045] Then, step S220 is executed to construct an influencing factor library based on the package's operation records.

[0046] Based on the information of each link in the operation record of a package, such as the route, nodes, equipment, operators, vehicles, and packaging, the relationship between different entities in the logistics network is constructed.

[0047] In addition to the data factors obtained directly, a batch of factors with rich business meanings were also processed based on business knowledge on the basis of the original data. For example, the parcel collection status factor can be obtained by using whether the parcel is in the form of loose pieces or packaged contents when it passes through each transfer center along the way.

[0048] An impact factor library is constructed based on the relationships between different entities and factors with business implications. These factors reflect information from various fields involved throughout the entire lifecycle, and may not necessarily be strongly correlated with a specific problem scenario, but they can all participate in subsequent analysis. According to one embodiment of the present invention, the impact factor library constructed at the encapsulation level constitutes a general factor library containing more than 400 impact factors that is not targeted at a specific scenario.

[0049] Next, proceed to step S230 to build a problem tag library based on the package order information and customer complaint data.

[0050] Among these, delivery timeliness and quality issues can be broken down to whether there are problems with each individual package. For example, if the delivery time is not up to standard, it can be specified whether the time between pickup and signing for each package meets the standard. If a package is lost, it can be specified whether it has been lost. The system can determine whether there are delays based on the delivery and shipping times in the package order information; and it can determine whether there are more than 100 specific issues, including lost, damaged, defective, and complained items, based on customer complaint data.

[0051] Then, the packages are tagged with various specific issues such as lost, damaged, delayed, complained, and problematic. If a certain issue exists in a package, it is tagged as 1; if a certain issue does not exist, it is tagged as 0, thus obtaining a problem tag library for each package.

[0052] Finally, step S240 is executed to calculate the correlation between factors in the influence factor library and the problem label library and the target problem based on the IV value evaluation method, and to obtain the factor analysis results.

[0053] The IV (information value) indicates the strength of a factor's ability to predict a problem label, and the magnitude of the IV determines the degree of influence of the independent variable factor on the target problem.

[0054] For example, given an attribute Y= of a certain feature category Y The formula for calculating the IV value corresponding to this attribute is as follows:

[0055] ;

[0056] bad j Let be the number of bad samples in the j-th impact factor. T This indicates the total number of bad samples;

[0057] good j Let good be the number of good samples in the j-th impact factor. T This represents the total number of good samples.

[0058] According to one embodiment of the present invention, the number of packages with a corresponding issue item label of 1 in the impact factor library under different factor values ​​can be counted and used as the number of good samples in the above formula. The number of packages with a corresponding issue item label of 0 in the impact factor library under different factor values ​​can also be counted and used as the number of good samples in the above formula.

[0059] For large-scale datasets, the quantile or sorting functions built into the ClickHouse real-time big data analytics engine can be used to bin factor variables and then calculate IV values. The SQL code for calculating IV values ​​is as follows:

[0060] CREATE TABLE IF NOT EXISTS output_table_basic_0_level1

[0061] (

[0062] feature_name STRING COMMENT 'Factor Name'

[0063] ,category_name STRING COMMENT 'Factor Value'

[0064] ,cat_cntbigint COMMENT 'Total sample size for this value'

[0065] ,cat_p_cntbigint COMMENT 'This value represents the positive sample size'

[0066] ,cat_n_cntbigint COMMENT 'This value represents the negative sample size'

[0067] ,total_cntbigint COMMENT 'Total Sample Size of the Market'

[0068] ,total_p_cntbigint COMMENT 'Positive Sample Size of the Market'

[0069] ,total_n_cntbigint COMMENT 'Negative Sample Size of the Market'

[0070] )

[0071] PARTITIONED by

[0072] (

[0073] label string comment 'label name'

[0074] )

[0075] LIFECYCLE 365;

[0076] insert overwrite table output_table_basic_0_level1 partition (label ='label_name')

[0077] select feature_name,

[0078] if(category_name = 'none', null, category_name) as category_name,

[0079] cat_cnt, cat_p_cnt, cat_n_cnt,

[0080] total_cnt, total_p_cnt, total_n_cnt

[0081] from

[0082] (

[0083] select / *+mapjoin(t3)* /

[0084] case

[0085] when factor is not null then 'factor'

[0086] else null

[0087] end as feature_name,

[0088] case

[0089] when factor is not null then factor

[0090] else null

[0091] end as category_name,

[0092] cat_cnt, cat_p_cnt, cat_n_cnt,

[0093] total_cnt, total_p_cnt, total_n_cnt

[0094] from

[0095] (

[0096] select 1 as join_key,

[0097] factor,

[0098] sum(cnt) as cat_cnt,

[0099] sum(if(label_name = 1, cnt, 0)) as cat_p_cnt,

[0100] sum(if(label_name = 0, cnt, 0)) as cat_n_cnt

[0101] from

[0102] (

[0103] select factor,

[0104] label_name, count(*) as cnt

[0105] from

[0106] (

[0107] select label_name

[0108] ,coalesce(factor, 'None') as factor

[0109] from

[0110] (

[0111] select label_name

[0112] ,factor

[0113] from input_table

[0114] where label_name is not null

[0115] ) t0

[0116] ) t1

[0117] group by label_name,factor

[0118] GROUPING SETS(

[0119] (factor,label_name)

[0120] )

[0121] ) t2

[0122] group by factor

[0123] ) t3

[0124] join

[0125] ( Note: In the translation of line , "无" is translated as "None" for better understanding in English context. You can adjust it according to the actual situation.

[0126] select 1 as join_key,

[0127] sum(cnt) as total_cnt,

[0128] sum(if(label_name=1, cnt, 0)) as total_p_cnt,

[0129] sum(if(label_name=0, cnt, 0)) as total_n_cnt

[0130] from

[0131] (

[0132] select label_name, count(*) as cnt

[0133] from input_table

[0134] where label_name is not null

[0135] group by label_name

[0136] ) t4

[0137] ) t5

[0138] on t3.join_key = t5.join_key

[0139] ) t4;

[0140] In the SQL code above, `input_table` is the table containing the influencing factor database, `label_name` is the label field corresponding to the issue, and `factor` is the factor. Using the `grouping set` in this SQL, factors can be expanded to calculate the relationship between multiple factors and issue labels simultaneously.

[0141] In one embodiment of the present invention, the target problem, the range of analytical data in the influence factor library, and the analysis path can be preset; the constructed influence factor library is synchronized to the ClickHouse database engine according to the preset range of analytical data to form a materialized view; and the correlation between the preset target problem and the factors in the materialized view is calculated layer by layer along the analysis path based on SQL statements.

[0142] Figure 3 illustrates a schematic diagram of the system architecture of an online analysis system for logistics problem influencing factors according to an embodiment of the present invention. As shown in Figure 3, the system architecture includes a client, a ClickHouse database management system, and an ODPS offline database.

[0143] The ODPS offline database is used to process and analyze the detailed information of packages to generate an impact factor database and a problem tag database, and then synchronizes the generated impact factor database and problem tag database to the ClickHouse database management system.

[0144] ClickHouse database management system is used to construct materialized views of factors in the influence factor library according to their inclusion and association relationships, and calculate the IV values ​​between the preset target question and the factors in the materialized views layer by layer along the preset analysis path.

[0145] The client is used to display the sorted IV values ​​along the drilling path in real time.

[0146] The online analysis system provided by this invention allows users to independently select the target problem scenario, the range of analysis data in the influencing factor library, and the analysis path, and obtain analysis results in real time.

[0147] First, the offline factor tag library data is synchronized into the ClickHouse data engine using Alibaba Cloud's ODPS (Develop Data Services). Then, leveraging ClickHouse's materialized view functionality and business knowledge, related factors are grouped and materialized views are constructed according to inclusion and association relationships. The most basic set of factors is used as the root node.

[0148] The ClickHouse database engine can pre-calculate IV values ​​for factors in the Influence Factors library and issues in the Issue Tag library of the ODPS offline database, and store the pre-calculated IV values ​​in a cache. By pre-calculating and caching, IV values ​​can be retrieved directly from the cache, reducing the computational load during online calculations.

[0149] According to one embodiment of the present invention, the ClickHouse database engine can achieve a response time within seconds for any query on approximately 3-4 billion data points over two months. Furthermore, it enables data drill-down functionality by evaluating factor correlations layer by layer along the analysis path.

[0150] Figure 4 shows a schematic diagram of the drilling path according to an embodiment of the present invention. As shown in Figure 4, data drilling is performed with the dispatch point, first center, last center, weight segment, and package status as root nodes, respectively.

[0151] Taking the correlation calculation between delivery outlets and lost parcel issues as an example, the first layer can analyze the relationship between lost parcels and delivery outlets, and select the batch of delivery outlets with the most serious lost parcel issues; the second layer can select a delivery outlet with serious issues, and then analyze the relationship between lost parcels and receiving areas under that outlet, and select the batch of receiving areas with the most serious lost parcel issues under that outlet; the third layer can select the receiving area, and then analyze the relationship between lost parcels and collection stations under that area, and select the collection stations with the most serious lost parcel issues under that area; the fourth layer can select the collection station, and then analyze the relationship between lost parcels and signature types at that collection station, and so on.

[0152] The logistics problem influencing factor analysis method and online analysis system provided by this invention, with parcels as the analysis granularity, can obtain detailed information about parcels, establish relationships between various entities in the logistics network, and obtain a large amount of information reflecting various fields involved in the parcel circulation process, such as order information and customer complaint data, which can improve the comprehensiveness and universality of the construction of the influencing factor library and problem tag library.

[0153] During factor correlation analysis, the system can statistically analyze the positive and negative sample data of labels corresponding to different factor values ​​in real time. By customizing and adjusting the analysis path, the system can calculate the analysis results in real time, which can improve the efficiency and flexibility of factor correlation analysis, provide rich data dimensions for business decision-making, and reduce development costs.

[0154] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0155] Similarly, it should be understood that, in order to streamline this disclosure and aid in understanding one or more of the various aspects of the invention, in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof. However, this method of disclosure should not be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into this detailed description, wherein each claim itself is a separate embodiment of the invention.

[0156] Those skilled in the art will understand that modules, units, or components of the devices disclosed in the examples herein can be arranged in the devices described in this embodiment, or alternatively, can be located in one or more devices different from the devices in this example. The modules in the foregoing examples can be combined into a single module or, in addition, can be divided into multiple sub-modules.

[0157] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0158] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features but not others included in other embodiments, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

[0159] Furthermore, some of the embodiments described herein are methods or combinations of method elements that can be implemented by a processor of a computer system or by other means of performing the functions. Therefore, a processor having the necessary instructions for implementing the methods or method elements forms means for implementing the methods or method elements. Furthermore, the elements described herein in the apparatus embodiments are examples of means for implementing the functions performed by elements for the purposes of carrying out the invention.

[0160] As used herein, unless otherwise specified, the use of ordinal numbers such as “first,” “second,” “third,” etc., to describe ordinary objects merely indicates different instances of similar objects and is not intended to imply that the objects being described must have a given order in time, space, ordering, or any other manner.

[0161] Although the invention has been described with respect to a limited number of embodiments, those skilled in the art will understand from the foregoing description that other embodiments are conceivable within the scope of the invention described herein. Furthermore, it should be noted that the language used in this specification has been chosen primarily for readability and edibility purposes, and not for the purpose of interpreting or limiting the subject matter of the invention. Therefore, many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the appended claims. The disclosure of the invention is illustrative rather than restrictive, and the scope of the invention is defined by the appended claims.

Claims

1. A method for analyzing the influencing factors of logistics problems, characterized in that, include: Obtain detailed information about the package in the logistics network, including at least operation records, order information, and customer complaint data; Based on the package operation records, construct an influencing factor library; Based on package order information and customer complaint data, a problem tag library is constructed; the correlation between factors in the impact factor library and the problem tag library and the target problem is calculated using the IV value evaluation method to obtain factor analysis results; wherein, the step of calculating the correlation between factors in the impact factor library and the problem tag library and the target problem and obtaining factor analysis results using the IV value evaluation method includes: counting the number of packages with a corresponding problem item tag of 1 in the impact factor library under different factor values, as the number of bad samples; counting the number of packages with a corresponding problem item tag of 0 in the impact factor library under different factor values, as the number of good samples; calculating the IV value between factors and the target problem based on the following formula: bad j Let be the number of bad samples in the j-th impact factor. T Indicates the total number of bad samples; good j Let good be the number of good samples in the j-th impact factor. T This represents the total number of good samples; factor analysis results for each target question are obtained by ranking based on IV values.

2. The method for analyzing the influencing factors of logistics problems according to claim 1, characterized in that, The steps for obtaining detailed information about packages in the logistics network include: obtaining operation records, order information, and customer complaint data of packages in the logistics network. The logistics network includes operation entities and circulation entities. The operation entities include contracted areas, transfer centers, and independent outlets. The circulation entities include operation equipment, operators, vehicles, and packaging. The order information includes merchant ID, customer ID, delivery address, delivery address, delivery time, and delivery time. The customer complaint data includes customer complaint information, package problem records, and claim work orders.

3. The method for analyzing the influencing factors of logistics problems according to claim 2, characterized in that, The step of constructing an influencing factor library based on the operation records of packages includes: constructing the relationship between different entities in the logistics network based on the operation records of packages in the logistics network; obtaining factors with business meaning based on business knowledge; and constructing an influencing factor library based on the relationship between the different entities and the factors with business meaning.

4. The method for analyzing the influencing factors of logistics problems according to claim 2, characterized in that, The steps of constructing a problem tag library based on package order information and customer complaint data include: determining whether there is a delay problem in the package based on the delivery time and shipping time in the package order information; determining whether the package has problems including loss, damage, defective items, and complaints based on the customer complaint data; if a certain problem item exists in the package, it is tagged as 1, and if a certain problem item does not exist, it is tagged as 0, thus obtaining the problem tag library for each package.

5. The method for analyzing the influencing factors of logistics problems according to claim 4, characterized in that, The steps for calculating the correlation between factors in the impact factor library and the issue label library and the target issue based on the IV value evaluation method to obtain factor analysis results include: pre-setting the target issue, the analysis data range in the impact factor library, and the analysis path; synchronizing the constructed impact factor library to the ClickHouse database engine according to the preset analysis data range to form a materialized view; and calculating the correlation between the preset target issue and the factors in the materialized view layer by layer along the analysis path based on SQL statements.

6. An online analysis system for influencing factors of logistics problems, characterized in that, The system includes a client application, a ClickHouse database management system, and an ODPS offline database. The ODPS offline database is used to process and analyze package details to generate an impact factor library and a problem tag library, and then synchronizes the generated impact factor library and problem tag library to the ClickHouse database management system. The process of processing and analyzing package details to generate the impact factor library and problem tag library includes: establishing relationships between different entities in the logistics network based on the package's operation records in the logistics network to construct the impact factor library; determining whether the package has a preset target problem based on the package's order information and customer complaint data; and determining whether the package has a pre-defined target problem based on whether the package has a target problem. The packages are binarized for a preset target problem to construct the problem label library. The ClickHouse database management system is used to construct materialized views of the factors in the impact factor library according to their inclusion and association relationships, and calculate the IV value between the preset target problem and the factors in the materialized views layer by layer along a preset analysis path. The calculation of the IV value between the preset target problem and the factors in the materialized views includes: counting the number of packages with a corresponding problem item label of 1 in the impact factor library under different factor values, as the number of bad samples; counting the number of packages with a corresponding problem item label of 0 in the impact factor library under different factor values, as the number of good samples; and calculating the IV value between the factors and the target problem based on the following formula: bad j Let be the number of bad samples in the j-th impact factor. T Indicates the total number of bad samples; good j Let good be the number of good samples in the j-th impact factor. T This represents the total number of good samples; the client is used to display the IV value ranking results along the drilling path in real time, so as to obtain the factor analysis results for each target question based on the IV value ranking.

7. The online analysis system for logistics problem influencing factors according to claim 6, characterized in that, The ClickHouse database engine is used to pre-calculate IV values ​​for factors in the Influence Factors Library and issues in the Issue Labels Library of the ODPS offline database, and stores the pre-calculated IV values ​​in the cache.

8. A computing device, comprising: At least one processor; and a memory storing program instructions, wherein the program instructions are configured to be executed by the at least one processor, the program instructions including instructions for performing the logistics problem impact factor analysis method as described in any one of claims 1-5.

9. A readable storage medium storing program instructions, which, when read and executed by a computing device, cause the computing device to perform the logistics problem influencing factor analysis method as described in any one of claims 1-5.

Images