Delivery service quality intelligent analysis system based on big data

Through the intelligent analysis system of delivery service quality based on big data, the problem of third-party carriers in e-commerce logistics lacks monitoring of timeliness and quality, real-time monitoring and data analysis of the transportation process are realized, and abnormalities are quickly identified and handled, which has improved Customer satisfaction and market competitiveness.

CN119005463APending Publication Date: 2024-11-22SICHUAN WENXUAN ONLINE E-COMMERCE CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411011220.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-26
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

E-commerce logistics relies on third-party carriers to ensure timeliness and quality, and lack of monitoring, resulting in the inability to detect and intervene in handling abnormal parts in a timely manner.

Method used

Design an intelligent analysis system for delivery service quality based on big data, including big data module, tracking module, management module and visual module, standardize the carrier's delivery trajectory data, monitor alarms and work order management, analyze transportation abnormalities in real time, and quickly Identify potential problems and intervene in dealing with them.

Benefits of technology

Real-time monitoring and data analysis of the transportation process are realized, quickly identifying transportation problems, shortening the delivery cycle, improving customer satisfaction, and enhancing market competitiveness.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119005463A_ABST
    Figure CN119005463A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of big data, in particular to a big data-based distribution service quality intelligent analysis system, which comprises a big data module, the tracking module is connected with the big data module and comprises a common line sub-model and a tracking sub-model; the management module is connected with the big data module and the tracking module and comprises a monitoring alarm sub-module and a work order management sub-module; and the visualization module is connected with the tracking module and comprises a problem analysis sub-module and an arrival rate analysis sub-module, and the arrival rate analysis sub-module is used for calculating the arrival condition of each carrier in each region. The distribution service quality intelligent analysis system based on big data provided by the invention can realize real-time monitoring and data analysis in a transportation process, quickly identify potential transportation problems, take corresponding measures for processing, enhance customer service and support channel operation, effectively shorten a distribution period, improve customer satisfaction, and improve the transportation efficiency. And the competitiveness of enterprises in the market with intense competition is enhanced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to a distribution service quality intelligent analysis system based on big data. Background Art

[0002] Online merchants entrust third-party carriers to deliver goods to users. From the time an order is shipped out to the time it is signed for by the user, they rely on third-party carriers to ensure timeliness and quality. This lack of monitoring results in the inability to promptly detect and intervene in the handling of some abnormal items. Summary of the invention

[0003] The purpose of the present invention is to provide a distribution service quality intelligent analysis system based on big data, which is used to solve the problem that the current e-commerce logistics mainly relies on third-party carriers to ensure timeliness and quality, lacks monitoring, and thus cannot promptly discover and intervene in the processing of some abnormal items.

[0004] The technical solution of the present invention is achieved in this way:

[0005] A distribution service quality intelligent analysis system based on big data, comprising: a big data module, used to regularly standardize the carrier's distribution trajectory data according to the standardized data processing rules preset in the trajectory rule submodule, so as to obtain standardized carrier distribution trajectory data; a tracking module, connected to the big data module, comprising a common route submodel and a tracking submodel, wherein the common route submodel is used to measure the timeliness standard of the historical transportation route, and the tracking submodel is used to predict whether the waybill in transportation will time out according to the common route; a management module, connected to the big data module and the tracking module, comprising a monitoring alarm submodule and a work The order management submodule includes a monitoring and alarm submodule for querying overtime waybills predicted by the tracking submodel, and a work order management submodule for transferring seriously overtime waybills to carriers and customer service; a visualization module connected to the tracking module includes a problem analysis submodule and an on-time delivery rate analysis submodule, wherein the problem analysis submodule is used to visualize the concentration of overtime waybills, and analyze the causes of logistics anomalies in multiple dimensions based on transportation links, regions, carriers, warehouses and outlets through multiple analysis modules, and the on-time delivery rate analysis submodule is used to calculate the on-time delivery status of each carrier in each region, and then analyze the timeliness of each carrier in each region.

[0006] Optionally, the system further comprises a configuration module, which is connected to the tracking module and the big data module respectively, and comprises a trajectory rule submodule and a tracking parameter submodule;

[0007] Among them, the trajectory rule submodule is used to manually set multiple data processing rules, and the data processing rules include transportation link rules, site rules and exception rules;

[0008] The tracking parameter submodule is used to manually set the calculation parameters of multiple commonly used line submodels and tracking submodels.

[0009] Optionally, the data processing rules include transportation link rules, site rules and exception rules;

[0010] The transport link rules include outbound delivery, collection, transit, dispatch and receipt. Outbound delivery corresponds to the completion of order package packaging, collection corresponds to the first-level distribution center of the waybill collecting and warehousing, transit corresponds to the transportation of the second-level distribution center of the waybill, dispatch corresponds to the outlets in the destination city, and receipt corresponds to the receipt status of the waybill;

[0011] The site rules include collection points, distribution centers and outlets. The collection point is the first-level distribution center, which is the designated collection point of the warehouse. The distribution center is defined in two types, one is marked by the track, and the other is cleaned by keywords in the track path. The first-level distribution center, the second-level distribution center and the receipt point are excluded, and the remaining sites are outlets;

[0012] The abnormal rules include returned items, lost items and branch closures, and the abnormal sources include abnormal status, site failures and transportation abnormalities.

[0013] Optionally, the commonly used route sub-model parameters include timeliness update standard deviation and maximum number of route sites;

[0014] The standard deviation of time efficiency update is used to determine whether the time efficiency in the region is normal. The maximum number of route stations is the maximum number of stations allowed when selecting a route. The route selection is determined by calculating the distribution and outlets of the optimal path for the entire route through the proportion of route segments in the same district / county.

[0015] Optionally, the carrier delivery trajectory data is regularly standardized according to the standardized data processing rules preset in the trajectory rule submodule to obtain standardized carrier delivery trajectory data, including:

[0016] Clean and transform the delivery trajectory data of multiple carriers to make them standardized carrier delivery trajectory data;

[0017] Summarize the waybill track of the standardized carrier delivery track data;

[0018] Wherein, the cleaning and conversion operations include:

[0019] The ODS layer data remains in the original data format without being processed, providing the DW layer with basic original data, thereby reducing the impact on the business system;

[0020] The DIM layer is composed of dimension tables. Based on the concept of dimensional modeling, it establishes the consistent dimension site dimension processing process of the entire enterprise: obtain incremental track data from the ODS layer, clean invalid tracks, determine the site type according to the rules, deduplicate the site ID to obtain the latest site name, site type and other information, and update the changed site information by comparing the site ID with the original dimension table data. Specifically, the DIM layer cleans and processes invalid outlets for different carriers' hubs, shipping centers, service departments, consolidation centers and other differentiated transportation network points, and uniformly identifies them as valid primary distribution, secondary distribution, and outlet dimensions;

[0021] The structure and granularity of the DW layer are consistent with those of the ODS layer. The DW layer summarizes the dimensional data of the DIM layer, cleans and associates the dimension table with the ODS layer data to obtain standard data that removes null values ​​and invalid data, and obtains incremental track\waybill data from the ODS. The DW layer cleans and processes invalid states based on the status information in the incremental track\waybill data: inbound status information, outbound status information, transshipment status information, lost item status information, package abnormal status information, and delivery status information. The incremental track\waybill data in the transportation state is uniformly identified and summarized into five standard links: effective outbound, collection, transit, delivery, and receipt, and associated with the dimension table to obtain the dimension table proxy key in order to obtain the dimension table data information at that time, and write it into the original DW table according to the partition increment;

[0022] The structure of the DWD layer is consistent with that of DW, and only the latest records are saved: The detailed processing logic of the logistics track of the DWD layer: Get data from DW to remove duplicates, retain the latest data, generate track sorting fields in chronological order, and write them into the original DWD table;

[0023] Among them, the waybill trajectory summary operation is to realize the detailed summary of indicators through statistical calculation of basic data, obtain data from dw by site + link, deduplicate the entire trajectory status in the order of trajectory, obtain the current last trajectory, clean up useless trajectories, and splice and record the time and timeliness of the main links of the trajectory in sequence, and associate the deactivated area.

[0024] Optionally, the monitoring and alarm submodule provides abnormal data monitoring of each link based on the commonly used routes and standard time efficiency, wherein the sub-links include the collection link, the transit link and the delivery link, wherein the abnormal data of the collection link includes the collection timeout abnormal data, the abnormal data of the transit link includes the transit interruption abnormal data, the problem piece transportation data and the returned piece transportation data, and the abnormal data of the delivery link includes the delivery timeout and the receipt failure;

[0025] The work order management submodule intervenes in advance to handle abnormal waybills that are prone to complaints. Abnormal waybills include:

[0026] a. Every other day + collect overdue waybills;

[0027] b. The next day + order placement >= 3 days + transit interruption;

[0028] At the same time, abnormal waybills within the range will be automatically created as delivery problem work orders at a frequency of 2 hours / time, and transferred to various carriers for track confirmation, so that customer service can choose a reasonable way to handle the delivery problem based on the carrier's confirmation results.

[0029] Optionally, the problem analysis submodule obtains in real time the relevant data of the overall transportation volume and transportation results as of the day in each link from warehouse-out-collection-transit-delivery-signature, and provides detailed documents of transportation anomalies in each link from warehouse-out-collection-transit-delivery-signature based on the relevant data set;

[0030] The relevant data include the number of parcels collected on the day, the number of parcels transferred on the day, the number of parcels delivered on the day, and the number of parcels signed for on the day. The transportation anomalies include:

[0031] Collection timeout and abnormal collection time in the collection process;

[0032] Transfer timeout, transfer interruption, problem items and returned items during the transfer process;

[0033] Delivery timeout and receipt failure during the delivery process.

[0034] Optionally, the on-time delivery rate analysis submodule provides next-day package delivery time data at the warehouse + province, city, district and county granularity based on the differentiated transportation time requirements of each carrier, and continuously pays attention to the changing trend of the carrier's transportation results, identifies existing transportation anomalies and risks, and at the same time horizontally compares the time achievement of each carrier, explores the advantageous and disadvantageous areas of each carrier, and provides reference data for the carrier allocation strategy for transportation capacity selection.

[0035] The beneficial effects of the present invention are:

[0036] The distribution service quality intelligent analysis system based on big data provided by the present invention can realize real-time monitoring and data analysis during the transportation process, quickly identify potential transportation problems, and take corresponding measures to deal with them, strengthen customer service and support channel operations, effectively shorten the delivery cycle, improve customer satisfaction, and enhance the competitiveness of enterprises in the fiercely competitive market. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0038] Figure 1 This is a structural diagram of the intelligent analysis system for delivery service quality based on big data. DETAILED DESCRIPTION

[0039] The technical solutions in the embodiments of the present invention will be described clearly and completely 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, rather than all the embodiments.

[0040] In the description of the present invention, it is necessary to understand that the terms "upper", "lower", "front", "back", "left", "right", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship are based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0041] Example 1

[0042] like Figure 1 As shown, this embodiment is used to provide a delivery service quality intelligent analysis system based on big data, which is characterized by including:

[0043] The big data module is used to regularly standardize the carrier delivery trajectory data according to the standardized data processing rules preset in the trajectory rule submodule, thereby obtaining standardized carrier delivery trajectory data;

[0044] A tracking module, connected to the big data module, includes a common route sub-model and a tracking sub-model, wherein the common route sub-model is used to measure the timeliness standard of historical transportation routes, and the tracking sub-model is used to predict whether the waybill in transportation will be overdue according to the common routes;

[0045] Commonly used line sub-models can be:

[0046] enter:

[0047] H = {h1, h2, h3, ..., hm}: a set of historical waybill data.

[0048] E = {e1, e2, e3, ..., en}: a collection of transport links, such as outbound delivery, collection, transit, dispatch, and receipt;

[0049] Teh=teh+1-teh:For each waybill h∈H, teh is the time consumption of link eh;C={Teh1,Teh2,Teh3,...Tehm}:The time consumption set of each waybill in each link;X={C1,C2,C3…,Cn}:The link efficiency data set of all waybills on the same route;

[0050] s: parameter

[0051] Algorithm model:

[0052] Common route calculations:

[0053] Rcommon=arg maxR QR

[0054] condition:

[0055] Where R is the set of routes, Qr is the order quantity on route r;

[0056] R needs to include a shipping order with the same carrier, warehouse, and destination.

[0057] Common route time calculation:

[0058] Tstandardi=max{Xi|Xi∈[Li,Ui]}

[0059] condition:

[0060] For each link i:

[0061] Define upper and lower bounds on the timeliness of removing outliers:

[0062] Lower bound Li = Q1i-3×IQRi.

[0063] Upper bound Ui=Q3i+3×IQRi.

[0064] Select the waybill ti whose validity period is within the range [Li,Ui].

[0065] Output:

[0066] Rcommon: Commonly used routes.

[0067] Tstandardi: Standard link time on commonly used routes.

[0068] The tracking sub-models can be:

[0069] enter:

[0070] H = {ri, ti}: the waybill in progress, the current link ri, and the current time ti;

[0071] Rcommon={r1,r2,r3,…,rm}:common route;

[0072] Tstandard = {t1, t2, t3, …, tm}: time efficiency standard for each link of the commonly used route;

[0073] n and x: timeout and interrupt rule parameters;

[0074] Algorithm model:

[0075]

[0076] condition:

[0077] If the timeliness standard of the current link cannot be found, the greedy algorithm is used to calculate the maximum timeliness standard of the previous point.

[0078] Great timeliness standard.

[0079] Output:

[0080] Status: indicates the status of the current waybill. Possible values ​​are Normal, Timeout, or Interrupted.

[0081] A management module connected to the big data module and the tracking module, including a monitoring and alarm submodule and a work order management submodule, wherein the monitoring and alarm submodule is used to query the overdue waybills predicted by the tracking submodel, and the work order management submodule is used to transfer seriously overdue waybills to the carrier and customer service;

[0082] Among them, the monitoring and alarm submodule provides abnormal data monitoring of each link based on the commonly used routes and standard timeliness. The sub-links include the collection link, the transit link and the delivery link. The abnormal data of the collection link includes the abnormal data of the collection timeout, the abnormal data of the transit link includes the abnormal data of the transit interruption, the transportation data of the problem pieces and the transportation data of the returned pieces, and the abnormal data of the delivery link includes the delivery timeout and the receipt failure.

[0083] The work order management submodule intervenes in advance to handle abnormal waybills that are prone to complaints. Abnormal waybills include:

[0084] a. Every other day + collect overdue waybills;

[0085] b. The next day + order placement >= 3 days + transit interruption;

[0086] At the same time, abnormal waybills within the range will be automatically created as delivery problem work orders at a frequency of 2 hours / time, and transferred to various carriers for track confirmation, so that customer service can choose a reasonable way to handle the delivery problem based on the carrier's confirmation results.

[0087] A visualization module is connected to the tracking module, and includes a problem analysis submodule and an on-time delivery rate analysis submodule. The problem analysis submodule is used to display the concentration of overdue waybills, and analyze the causes of logistics anomalies in multiple dimensions based on transportation links, regions, carriers, warehouses and outlets through multiple analysis modules. The on-time delivery rate analysis submodule is used to calculate the on-time delivery status of each carrier in each region, and then analyze the timeliness of each carrier in each region. Specifically, the problem analysis submodule obtains relevant data on the overall transport volume and transport results as of the day in each link from warehouse-out-collection-transit-delivery-signature in real time, and provides detailed documents of transport anomalies in each link from warehouse-out-collection-transit-delivery-signature based on relevant data;

[0088] The relevant data include the number of parcels collected on the day, the number of parcels transferred on the day, the number of parcels delivered on the day, and the number of parcels signed for on the day. The transportation anomalies include:

[0089] Collection timeout and abnormal collection time in the collection process;

[0090] Transfer timeout, transfer interruption, problem items and returned items during the transfer process;

[0091] Delivery timeout and receipt failure during the delivery process.

[0092] Secondly, the accuracy rate analysis submodule provides next-day package delivery time data at the warehouse + province, city, district and county granularity based on the differentiated transportation time requirements of each carrier, and continuously monitors the changing trend of the carrier's transportation results, identifies existing transportation anomalies and risks, and at the same time compares the time efficiency of each carrier horizontally, explores the advantageous and disadvantageous areas of each carrier, and provides reference data for the carrier's allocation strategy to select transportation capacity.

[0093] Secondly, in this embodiment, the system further includes a configuration module, which is connected to the tracking module and the big data module respectively, and includes a trajectory rule submodule and a tracking parameter submodule;

[0094] Among them, the trajectory rule submodule is used to manually set multiple data processing rules, and the data processing rules include transportation link rules, site rules and exception rules;

[0095] The transport link rules include outbound delivery, collection, transit, dispatch and receipt. Outbound delivery corresponds to the completion of order package packaging, collection corresponds to the first-level distribution center of the waybill collecting and warehousing, transit corresponds to the transportation of the second-level distribution center of the waybill, dispatch corresponds to the outlets in the destination city, and receipt corresponds to the receipt status of the waybill;

[0096] The site rules include collection points, distribution centers and outlets. The collection point is the first-level distribution center, which is the designated collection point of the warehouse. The distribution center is defined in two types, one is marked by the track, and the other is cleaned by keywords in the track path. The first-level distribution center, the second-level distribution center and the receipt point are excluded, and the remaining sites are outlets;

[0097] The abnormal rules include returned items, lost items and branch closures, and the abnormal sources include abnormal status, site failures and transportation abnormalities.

[0098] The tracking parameter submodule is used to manually set the calculation parameters of multiple commonly used line submodels and tracking submodels.

[0099] The commonly used route sub-model parameters include the standard deviation of timeliness update and the maximum number of route sites, where route selection is determined by calculating the distribution and network points of the optimal path of the entire route through the proportion of route segments in the same district / county. The above principle is the logical processing principle of the adaptive route model;

[0100] The timeliness update standard deviation is used to determine whether the timeliness in the area is a normal value, and the maximum number of route stations is the maximum number of stations allowed when selecting a route.

[0101] Secondly, in this embodiment, the carrier delivery trajectory data is regularly standardized according to the standardized data processing rules preset in the trajectory rule submodule, and the implementation method of obtaining the standardized carrier delivery trajectory data is as follows:

[0102] Clean and transform the delivery trajectory data of multiple carriers to make them standardized carrier delivery trajectory data;

[0103] Summarize the waybill track of the standardized carrier delivery track data;

[0104] Wherein, the cleaning and conversion operations include:

[0105] The ODS layer data remains in the original data format without being processed, providing the DW layer with basic original data, thereby reducing the impact on the business system;

[0106] The DIM layer is composed of dimension tables. Based on the concept of dimensional modeling, it establishes the consistent dimension site dimension processing process of the entire enterprise: obtain incremental track data from the ODS layer, clean invalid tracks, determine the site type according to the rules, deduplicate by site ID to obtain the latest site name, site type and other information, and update the changed site information by comparing the site ID with the original dimension table data. The specific implementation method can be: the DIM layer cleans and processes invalid outlets for different carriers' hubs, shipping centers, service departments, consolidation centers and other differentiated transportation network points, and uniformly identifies them as valid primary distribution, secondary distribution, and outlet dimensions;

[0107] The structure and granularity of the DW layer are consistent with those of the ODS layer. The DW layer summarizes the dimensional data of the DIM layer, cleans and associates the dimension table with the ODS layer data to obtain standard data that removes null values ​​and invalid data, and obtains incremental track\waybill data from the ODS. The DW layer cleans and processes invalid states based on the status information in the incremental track\waybill data: inbound status information, outbound status information, transshipment status information, lost item status information, package abnormal status information, and delivery status information. The incremental track\waybill data in the transportation state is uniformly identified and summarized into five standard links: effective outbound, collection, transit, delivery, and receipt, and associated with the dimension table to obtain the dimension table proxy key in order to obtain the dimension table data information at that time, and write it into the original DW table according to the partition increment;

[0108] The structure of the DWD layer is consistent with that of DW, and only the latest records are saved: The detailed processing logic of the logistics track of the DWD layer: Get data from DW to remove duplicates, retain the latest data, generate track sorting fields in chronological order, and write them into the original DWD table;

[0109] Among them, the waybill trajectory summary operation is to realize the detailed summary of indicators through statistical calculation of basic data, obtain data from dw by site + link, deduplicate the entire trajectory status in the order of trajectory, obtain the current last trajectory, clean up useless trajectories, and splice and record the time and timeliness of the main links of the trajectory in sequence, and associate the deactivated area.

[0110] The distribution service quality intelligent analysis system based on big data provided in this embodiment can realize real-time monitoring and data analysis during the transportation process, quickly identify potential transportation problems, and take corresponding measures to deal with them, strengthen customer service and support channel operations, effectively shorten the delivery cycle, improve customer satisfaction, and enhance the competitiveness of enterprises in the fiercely competitive market.

[0111] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A distribution service quality intelligent analysis system based on big data, characterized in that: include: The big data module is used to regularly standardize the carrier delivery trajectory data according to the standardized data processing rules preset in the trajectory rule submodule, thereby obtaining standardized carrier delivery trajectory data; A tracking module, connected to the big data module, includes a common route sub-model and a tracking sub-model, wherein the common route sub-model is used to measure the timeliness standard of historical transportation routes, and the tracking sub-model is used to predict whether the waybill in transportation will be overdue according to the common routes; A management module connected to the big data module and the tracking module, including a monitoring and alarm submodule and a work order management submodule, wherein the monitoring and alarm submodule is used to query the overdue waybills predicted by the tracking submodel, and the work order management submodule is used to transfer seriously overdue waybills to the carrier and customer service; The visualization module is connected to the tracking module and includes a problem analysis submodule and an on-time delivery rate analysis submodule. The problem analysis submodule is used to display the concentration of overdue waybills and analyze the causes of logistics anomalies in multiple dimensions based on transportation links, regions, carriers, warehouses and outlets through multiple analysis modules. The on-time delivery rate analysis submodule is used to calculate the on-time delivery status of each carrier in each region, and then analyze the timeliness of each carrier in each region.

2. According to the big data-based intelligent analysis system for distribution service quality according to claim 1, it is characterized in that: The system further comprises a configuration module, which is connected to the tracking module and the big data module respectively, and comprises a trajectory rule submodule and a tracking parameter submodule; Among them, the trajectory rule submodule is used to manually set multiple data processing rules, and the data processing rules include transportation link rules, site rules and exception rules; The tracking parameter submodule is used to manually set the calculation parameters of multiple commonly used line submodels and tracking submodels.

3. According to claim 2, a distribution service quality intelligent analysis system based on big data is characterized in that: The data processing rules include transportation link rules, site rules and exception rules; The transport link rules include outbound delivery, collection, transit, dispatch and receipt. Outbound delivery corresponds to the completion of order package packaging, collection corresponds to the first-level distribution center of the waybill collecting and warehousing, transit corresponds to the transportation of the second-level distribution center of the waybill, dispatch corresponds to the outlets in the destination city, and receipt corresponds to the receipt status of the waybill; The site rules include collection points, distribution centers and outlets. The collection point is the first-level distribution center, which is the designated collection point of the warehouse. The distribution center is defined in two types, one is marked by the track, and the other is cleaned by keywords in the track path. The first-level distribution center, the second-level distribution center and the receipt point are excluded, and the remaining sites are outlets; The abnormal rules include returned items, lost items and branch closures, and the abnormal sources include abnormal status, site failures and transportation abnormalities.

4. According to claim 2, a distribution service quality intelligent analysis system based on big data is characterized in that: The commonly used route sub-model parameters include the timeliness update standard deviation and the maximum number of route stations; The standard deviation of time efficiency update is used to determine whether the time efficiency in the region is normal. The maximum number of route stations is the maximum number of stations allowed when selecting a route. The route selection is determined by calculating the distribution and outlets of the optimal path for the entire route through the proportion of route segments in the same district / county.

5. The big data-based intelligent analysis system for distribution service quality according to claim 2 is characterized in that: The carrier delivery trajectory data is regularly standardized according to the standardized data processing rules preset in the trajectory rule submodule, thereby obtaining standardized carrier delivery trajectory data, including: Clean and transform the delivery trajectory data of multiple carriers to make them standardized carrier delivery trajectory data; Summarize the waybill track of the standardized carrier delivery track data; Wherein, the cleaning and conversion operations include: The ODS layer data remains in the original data format without being processed, providing the DW layer with basic original data, thereby reducing the impact on the business system; The DIM layer is composed of dimension tables. Based on the concept of dimensional modeling, the consistent dimension of the entire enterprise is established. The site dimension processing process: obtain incremental trajectory data from the ODS layer, clean invalid trajectories, determine the site type according to the rules, deduplicate by site ID to obtain the latest site name, site type and other information, compare the site ID with the original dimension table data, and update the changed site information; The structure and granularity of the DW layer are consistent with those of the ODS layer. The DW layer summarizes the dimensional data of the DIM layer, and cleans and associates the ODS layer data currently in the transportation stage through the dimension table to obtain standard data that removes null values ​​and invalid data, and obtains incremental track\waybill data from the ODS. The DW layer cleans and processes invalid states based on the status information in the incremental track\waybill data: inbound status information, outbound status information, transshipment status information, lost item status information, package abnormal status information, and delivery status information. The incremental track\waybill data in the transportation state is uniformly identified and summarized into five standard links: effective outbound, collection, transit, delivery, and receipt, and associated with the dimension table to obtain the dimension table proxy key in order to obtain the dimension table data information at that time, and write it into the original DW table according to the partition increment; The structure of the DWD layer is consistent with that of DW, and only the latest records are saved: The detailed processing logic of the logistics track of the DWD layer: Get data from DW to remove duplicates, retain the latest data, generate track sorting fields in chronological order, and write them into the original DWD table; Among them, the waybill trajectory summary operation is to realize the detailed summary of indicators through statistical calculation of basic data, obtain data from dw by site + link, deduplicate the entire trajectory status in the order of trajectory, obtain the current last trajectory, clean up useless trajectories, and splice and record the time and timeliness of the main links of the trajectory in sequence, and associate the deactivated area.

6. The big data-based intelligent analysis system for distribution service quality according to claim 2, characterized in that: The monitoring and alarm submodule provides abnormal data monitoring of each link based on the commonly used routes and standard time efficiency. The sub-links include the collection link, the transit link and the delivery link. The abnormal data of the collection link includes the abnormal data of the collection timeout, the abnormal data of the transit link includes the abnormal data of the transit interruption, the transportation data of the problem pieces and the transportation data of the returned pieces, and the abnormal data of the delivery link includes the delivery timeout and the receipt failure. The work order management submodule intervenes in advance to handle abnormal waybills that are prone to complaints. Abnormal waybills include: a. Every other day + collect overdue waybills; b. The next day + order placement >= 3 days + transit interruption; At the same time, abnormal waybills within the range will be automatically created as delivery problem work orders at a frequency of 2 hours / time, and transferred to various carriers for track confirmation, so that customer service can choose a reasonable way to handle the delivery problem based on the carrier's confirmation results.

7. The big data-based intelligent analysis system for distribution service quality according to claim 2, characterized in that: The problem analysis submodule obtains relevant data on the overall transportation volume and transportation results of the day in real time from the outbound delivery, collection, transit, delivery, and receipt, and provides detailed documents of transportation anomalies in the outbound delivery, collection, transit, delivery, and receipt based on the relevant data; The relevant data include the number of parcels collected on the day, the number of parcels transferred on the day, the number of parcels delivered on the day, and the number of parcels signed for on the day. The transportation anomalies include: Collection timeout and abnormal collection time in the collection process; Transfer timeout, transfer interruption, problem items and returned items during the transfer process; Delivery timeout and receipt failure during the delivery process.

8. The big data-based intelligent analysis system for distribution service quality according to claim 2, characterized in that: The on-time delivery rate analysis submodule provides next-day package delivery time data at the warehouse + province, city, district and county granularity based on the differentiated transportation time requirements of each carrier, and continuously monitors the changing trend of the carrier's transportation results, identifies existing transportation anomalies and risks, and at the same time compares the time efficiency achievement of each carrier horizontally, explores the advantageous and disadvantageous areas of each carrier, and provides reference data for the carrier's allocation strategy for transportation capacity selection.