CN114862298A - Express package rollback monitoring method, device, equipment and storage medium - Google Patents

Express package rollback monitoring method, device, equipment and storage medium Download PDF

Info

Publication number
CN114862298A
CN114862298A CN202210292604.2A CN202210292604A CN114862298A CN 114862298 A CN114862298 A CN 114862298A CN 202210292604 A CN202210292604 A CN 202210292604A CN 114862298 A CN114862298 A CN 114862298A
Authority
CN
China
Prior art keywords
abnormal
return
package
monitoring
information
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210292604.2A
Other languages
Chinese (zh)
Inventor
陈龙
杨周龙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Dongpu Software Co Ltd
Original Assignee
Dongpu Software Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Dongpu Software Co Ltd filed Critical Dongpu Software Co Ltd
Priority to CN202210292604.2A priority Critical patent/CN114862298A/en
Publication of CN114862298A publication Critical patent/CN114862298A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083—Shipping
    • G06Q10/0837—Return transactions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/242—Query formulation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2462—Approximate or statistical queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06395—Quality analysis or management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083—Shipping
    • G06Q10/0833—Tracking
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083—Shipping
    • G06Q10/0835—Relationships between shipper or supplier and carriers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
    • G06Q30/0208—Trade or exchange of goods or services in exchange for incentives or rewards

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Data Mining & Analysis (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Accounting & Taxation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Finance (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Educational Administration (AREA)
  • Evolutionary Biology (AREA)
  • Game Theory and Decision Science (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Fuzzy Systems (AREA)
  • Health & Medical Sciences (AREA)

Abstract

The invention relates to the field of big data and discloses a method, a device, equipment and a storage medium for monitoring the rollback of an express package. The method comprises the following steps: receiving return package information to be processed; constructing a quit monitoring list according to the quit package information; monitoring logistics information of each returned package in the returned package monitoring list in real time, wherein each returned package information corresponds to one returned package; receiving abnormal piece returning information fed back by a user, determining abnormal piece returning packages according to the abnormal piece returning information, and searching logistics information of the abnormal piece returning packages; and determining a responsibility network point of the abnormal return parcel based on a preset algorithm and the logistics information of the abnormal return parcel. According to the invention, the corresponding responsibility network points are quickly positioned through the logistics information of the abnormal quit information, and corresponding reward and punishment measures are executed on the responsibility network points, so that the service quality of the network points is improved, and the capital loss and customer complaints of logistics enterprises are reduced.

Description

Express package rollback monitoring method, device, equipment and storage medium
Technical Field
The invention relates to the field of big data, in particular to a method, a device, equipment and a storage medium for monitoring the rollback of an express package.
Background
Before the addressee signs the express, the condition of unprovoked rollback of the express package often occurs, namely, the network site/distribution is used for obtaining the refund amount of the express refund, and the refund is falsely operated under the condition that objective reasons exist, so that the refund of the service charge of the intercepted piece system is obtained.
Related monitoring is not carried out aiming at the returning condition of the express package in the prior art, namely the condition of abnormal returning exists in the prior logistics transportation field, so that capital loss and customer complaints are brought to logistics enterprises, and the service quality is influenced.
Disclosure of Invention
The invention mainly aims to solve the problem of low accuracy of the conventional express parcel rollback monitoring method.
The invention provides a method for monitoring the rollback of an express package, which comprises the following steps:
receiving return package information to be processed;
constructing a quit monitoring list according to the quit package information;
monitoring logistics information of each returned package in the returned package monitoring list in real time, wherein each returned package information corresponds to one returned package;
receiving abnormal piece returning information fed back by a user, determining abnormal piece returning packages according to the abnormal piece returning information, and searching logistics information of the abnormal piece returning packages;
and determining a responsibility network point of the abnormal return parcel based on a preset algorithm and the logistics information of the abnormal return parcel.
Optionally, in a first implementation manner of the first aspect of the present invention, the constructing a drop-out monitoring list according to the drop-out package information includes:
creating an empty list object based on a preset list construction function;
generating a list element according to each piece of return package information;
and respectively adding the list elements to the empty list objects to obtain a returned monitoring list.
Optionally, in a second implementation manner of the first aspect of the present invention, a data structure of the drop monitoring list is in a form of a linked list, and after the list elements are respectively added to the empty list objects and the drop monitoring list is obtained, the method further includes:
when newly-added piece returning package information is received, performing dynamic memory allocation on the newly-added piece returning package information, wherein the performing dynamic memory allocation on the newly-added piece returning package information comprises:
applying for a continuous memory block in a dynamic memory area of a memory, and storing the newly-added piece returning and wrapping information to a data field of the memory block;
and storing the memory area address of the memory block to a pointer field of a table tail node in the linked list type return monitoring list so as to point the pointer of the table tail node to the memory block.
Optionally, in a third implementation manner of the first aspect of the present invention, the determining, based on a preset algorithm and the logistics information of the abnormal return package, a responsibility network point of the abnormal return package includes:
performing address collection calculation based on the logistics information of the abnormal return parcel to obtain a predicted value of a next return station of the abnormal return parcel;
and determining a responsibility network point of the abnormal quit package according to a preset algorithm and a predicted value of the next quit station of the abnormal quit package.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the logistics information of the abnormal package returning includes a return scanning site, a transfer subordinate site, and an origination site, and the determining, according to a preset algorithm and a predicted value of a next return site of the abnormal package returning, a responsibility network point of the abnormal package returning includes:
if the predicted value of the next returning station of the abnormal returning parcel is empty, determining the returning scanning station as a responsibility network point of the abnormal returning parcel, otherwise, judging whether a transfer subordinate station is the predicted value;
if the transfer subordinate station is the predicted value, determining the predicted value as a responsibility network point of the abnormal quit package, otherwise, judging whether the originating station is the transfer subordinate station;
and if the starting station is the transfer subordinate station, determining the return scanning station as the responsibility network point of the abnormal return package, otherwise, determining the predicted value as the responsibility network point of the abnormal return package.
Optionally, in a fifth implementation manner of the first aspect of the present invention, the method further includes:
generating a returned statistical report based on the logistics information of each returned package obtained by real-time monitoring;
according to the abnormal quit information fed back by the user, marking abnormal quit on the quit statistical report;
carrying out data splitting on a returned statistical report containing the abnormal returned piece mark to form a returned piece data set;
and executing a training task including abnormal piece returning identification on a preset neural network model based on the piece returning data set to obtain an identification model for identifying abnormal piece returning.
Optionally, in a sixth implementation manner of the first aspect of the present invention, the method further includes:
and obtaining and determining a strategy for performing reward and punishment on the responsibility network points according to the number of abnormal piece returning packages of the responsibility network points in a preset time period.
The second aspect of the present invention provides a device for monitoring the return of an express package, including:
the information receiving module is used for receiving the return parcel information to be processed;
the list construction module is used for constructing a return monitoring list according to the return package information;
the logistics information monitoring module is used for monitoring logistics information of each piece of return package in the return monitoring list in real time, wherein each piece of return package information corresponds to one piece of return package;
the abnormal piece determining module is used for receiving abnormal piece returning information fed back by a user, determining abnormal piece returning packages according to the abnormal piece returning information and searching logistics information of the abnormal piece returning packages;
and the responsibility network point determining module is used for determining the responsibility network points of the abnormal return packages based on a preset algorithm and the logistics information of the abnormal return packages.
Optionally, in a first implementation manner of the second aspect of the present invention, the list building module specifically includes:
the object creating unit is used for creating an empty list object based on a preset list construction function;
the element generating unit is used for generating a list element according to each piece of return package information;
and the element adding unit is used for respectively adding the list elements to the empty list object to obtain a quit monitoring list.
Optionally, in a second implementation manner of the second aspect of the present invention, the list building module specifically includes:
the object creating unit is used for creating an empty list object based on a preset list construction function;
the element generating unit is used for generating a list element according to each piece of return package information;
the element adding unit is used for respectively adding the list elements to the empty list object to obtain a quit monitoring list;
the dynamic application unit is used for applying for a continuous memory block in a dynamic storage area of the memory;
the information storage unit is used for storing the newly added piece returning package information to a data field of the memory block;
and a pointer setting unit, configured to store the memory area address of the memory block to a pointer field of a table tail node in the linked list type return monitoring list, so as to point the pointer of the table tail node to the memory block.
Optionally, in a third implementation manner of the second aspect of the present invention, the responsibility network point determining module specifically includes:
the predicted value calculating unit is used for performing address collection calculation based on the logistics information of the abnormal return parcel to obtain a predicted value of a next return station of the abnormal return parcel;
and the network point determining unit is used for determining a responsibility network point of the abnormal return parcel according to a preset algorithm and a predicted value of a next return station of the abnormal return parcel.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the mesh point determining unit is specifically configured to:
if the predicted value of the next returning station of the abnormal returning parcel is empty, determining the returning scanning station as a responsibility network point of the abnormal returning parcel, otherwise, judging whether a transfer subordinate station is the predicted value;
if the transfer subordinate station is the predicted value, determining the predicted value as a responsibility network point of the abnormal quit package, otherwise, judging whether the originating station is the transfer subordinate station;
and if the starting station is the transfer subordinate station, determining the return scanning station as the responsibility network point of the abnormal return package, otherwise, determining the predicted value as the responsibility network point of the abnormal return package.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the apparatus further includes an anomaly recognition model training module, where the anomaly recognition model training module is specifically configured to:
generating a returned statistical report based on the logistics information of each returned package obtained by real-time monitoring;
according to the abnormal quit information fed back by the user, marking abnormal quit on the quit statistical report;
carrying out data splitting on a returned statistical report containing the abnormal returned piece mark to form a returned piece data set;
and executing a training task including abnormal piece returning identification on a preset neural network model based on the piece returning data set to obtain an identification model for identifying abnormal piece returning.
Optionally, in a sixth implementation manner of the second aspect of the present invention, the apparatus further includes a reward and penalty determination module, where the reward and penalty determination module is specifically configured to:
and obtaining and determining a strategy for performing reward and punishment on the responsibility network points according to the number of abnormal piece returning packages of the responsibility network points in a preset time period.
The third aspect of the present invention provides a device for monitoring the rollback of an express package, including: a memory and at least one processor, the memory having instructions stored therein; the at least one processor calls the instructions in the memory to enable the express package return monitoring device to execute the express package return monitoring method.
A fourth aspect of the present invention provides a computer-readable storage medium, which stores instructions that, when executed on a computer, cause the computer to execute the above-mentioned method for monitoring the rollback of an express package.
According to the technical scheme provided by the invention, the corresponding responsibility network points are quickly positioned through the logistics information of the abnormal quit information, and corresponding reward and punishment measures are executed on the responsibility network points, so that the service quality of the network points is improved, the capital loss and customer complaints of logistics enterprises are reduced.
Drawings
Fig. 1 is a schematic diagram of a first embodiment of a method for monitoring the return of an express package according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a second embodiment of a method for monitoring the return of an express package according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a third embodiment of a method for monitoring the return of an express package in an embodiment of the present invention;
fig. 4 is a schematic diagram of an embodiment of a device for monitoring the return of an express package according to an embodiment of the present invention;
fig. 5 is a schematic diagram of another embodiment of a device for monitoring the return of a parcel by express delivery in an embodiment of the present invention;
fig. 6 is a schematic diagram of an embodiment of a device for monitoring the return of an express package in an embodiment of the present invention.
Detailed Description
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The invention can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
The server in the invention can be an independent server, and can also be a cloud server for providing basic cloud computing services such as cloud service, a cloud database, cloud computing, cloud functions, cloud storage, Network service, cloud communication, middleware service, domain name service, security service, Content Delivery Network (CDN), big data, artificial intelligence platform and the like.
For convenience of understanding, a specific flow of the embodiment of the present invention is described below, and referring to fig. 1, an embodiment of a method for monitoring a return of an express package in an embodiment of the present invention includes:
101. receiving return package information to be processed;
it can be understood that in the transportation process of the express logistics, the sender needs to cancel the delivery temporarily, and when the express logistics arrives at the recipient, the recipient refuses to sign, at this time, the express package will be returned to the sender, the server will initiate a package returning confirmation flow to the sender after receiving a request instruction for canceling the delivery initiated by the sender and when receiving an instruction for rejecting the receipt by the recipient, and after the confirmation of the sender, the server receives returning package information to be returned, and sends the returning package information to be returned to the data storage area of the returning system to wait for further processing.
102. Constructing a piece returning monitoring list according to the piece returning package information;
it can be understood that the server monitors each returned package by constructing a returned package monitoring list, that is, only the express packages recorded in the returned package monitoring list are monitored. Specifically, the server creates an empty list object based on a preset list construction function; generating a list element according to each piece of quit package information; and respectively adding the list elements to the empty list object to obtain a quit monitoring list.
In this embodiment, the data structure of the ejection monitoring list is not limited.
In one embodiment, there is a fast random access service requirement, the dispatch monitoring list may adopt a sequence table structure, the time complexity of the recommended monitoring list of the sequence table structure is O (1) (constant order), and the efficiency is higher when a certain piece of dispatch package information is searched;
in another embodiment, there is a service requirement for frequently modifying and updating the backlog monitoring list, the backlog monitoring list may adopt a linked list structure, when new backlog package information needs to be added or inserted, a continuous memory block is applied in a dynamic storage area of a memory and then the backlog package information is stored in a data field, then a pointer field of a previous node points to the memory block, and a pointer field in the memory block points to a subsequent node, so that the memory utilization rate is higher and the modification is more convenient. Optionally, in view that the linked list structure can only traverse from the head node to the back in sequence, and the corresponding time complexity is o (n) (linear order), the efficiency is low when a certain specific piece removing package information is searched compared with the sequence table structure, and the server can implement bidirectional traversal of the nodes by using the bidirectional circular linked list structure, thereby improving the data search efficiency of the piece removing monitoring list.
103. Monitoring logistics information of each returned package in a returned monitoring list in real time, wherein each returned package information corresponds to one returned package;
it can be understood that the server generally performs GPS position monitoring on the transportation truck where each returned package is located and obtains logistics information of each returned package by the electronic check-in device of each network point, and stores the logistics information in the database in a persistent manner. Optionally, the logistics information includes an outgoing and intermediate transfer name (code), an outgoing and intermediate time, a loading station name (code), loading time, return scanning time, whether there is a return operation, an originating transfer center name (code), an originating network name (code), a delivery network name (code), a return scanning station name (code), an outgoing and intermediate lower station name (code), and the like.
104. Receiving abnormal piece returning information fed back by a user, determining abnormal piece returning packages according to the abnormal piece returning information, and searching logistics information of the abnormal piece returning packages;
it can be understood that in order to obtain the refund amount of the express backspacing piece, part of the network nodes falsely operate the backspacing piece under the condition that objective reasons exist, so that the refund of the service fee of the interceptor system is obtained. And the sender or the receiver can inquire corresponding logistics tracking conditions according to the express bill number, and once finding that the express package is returned due to no reason or the logistics transportation time of the express package is abnormal (for example, 2 days of delivery are predicted and actual 4 is not delivered), the abnormal return information is fed back to the server through the logistics guarantee service interface, and then the server determines the abnormal return package and the logistics information thereof according to the abnormal return information.
105. And determining a responsibility network point of the abnormal return parcel based on a preset algorithm and the logistics information of the abnormal return parcel.
It can be understood that the server performs calculation processing on the logistics information of the abnormal return package based on a preset algorithm, so as to determine the responsibility network point of the abnormal return package. The responsibility network is the logistics network suspected of having false operation backspacing parts.
Optionally, the server acquires and determines a policy for reward punishment on the responsibility network point according to the number of abnormal piece returning packages of the responsibility network point in a preset time period. When the number of abnormal backout packages in the preset time period of the responsibility network point is larger, the possibility that the responsibility network point falsely operates the backout is higher. Furthermore, by executing corresponding reward and punishment strategies, behaviors such as nonstandard site operation and the like are avoided, and the service quality is improved.
In the embodiment, the corresponding responsibility network is quickly positioned through the logistics information of the abnormal piece returning information, and corresponding reward and punishment measures are executed on the responsibility network, so that the service quality of the network is improved, and the capital loss and customer complaints of logistics enterprises are reduced.
Referring to fig. 2, a second embodiment of the method for monitoring the return of the express package in the embodiment of the present invention includes:
201. receiving return package information to be processed;
202. constructing a piece returning monitoring list according to the piece returning package information;
203. monitoring logistics information of each returned package in a returned monitoring list in real time, wherein each returned package information corresponds to one returned package;
204. receiving abnormal piece returning information fed back by a user, determining abnormal piece returning packages according to the abnormal piece returning information, and searching logistics information of the abnormal piece returning packages;
wherein, the steps 201-204 are similar to the steps 101-104 described above, and detailed description thereof is omitted here.
205. Performing address collection calculation based on logistics information of the abnormal returned packages to obtain a predicted value of a next returning station of the abnormal returned packages;
it can be understood that a plurality of address sets are preset in the address collection calculation, each address set includes corresponding logistics information, the server matches the logistics information of the abnormal return package with the logistics information included in each set, so as to determine the address set most consistent with the abnormal return package, specifically, a similarity algorithm including, but not limited to, euclidean distance and the like may be used to determine a matching degree between the logistics information of the abnormal return package and each set, and then a next return site is determined according to an address pointed by the address set. Optionally, the address pointed by each address set is a site address, and the server determines the predicted value of the next fallback site directly according to the address set. Optionally, the address pointed by each address set is not a site address, and the server uses the site closest to the address pointed by the address set as a predicted value of the next fallback site.
206. And determining a responsibility network point of the abnormal return parcel according to a preset algorithm and a predicted value of a next return station of the abnormal return parcel.
It can be understood that the logistics information of the abnormal quit package further includes a quit scanning site, a transfer subordinate site and an originating site, if the predicted value of the quit site of the abnormal quit package is empty, the quit scanning site is determined as a responsibility network of the abnormal quit package, otherwise, the transfer subordinate site is determined whether the predicted value is the predicted value; if the transfer subordinate station is the predicted value, determining the predicted value as a responsibility network point of the abnormal quit package, otherwise, judging whether the originating station is the transfer subordinate station; and if the starting site is a transfer subordinate site, determining the return scanning site as a responsibility network point of the abnormal return package, otherwise, determining the predicted value as the responsibility network point of the abnormal return package.
In this embodiment, the process of determining the responsibility network point of the abnormal parcel return package is described in detail, and the responsibility network point of the abnormal parcel return package is accurately judged through a predicted value and an algorithm.
Referring to fig. 3, a third embodiment of the method for monitoring the return of the express package in the embodiment of the present invention includes:
301. receiving return package information to be processed;
302. constructing a piece returning monitoring list according to the piece returning package information;
303. monitoring logistics information of each returned package in a returned monitoring list in real time, wherein each returned package information corresponds to one returned package;
304. receiving abnormal piece returning information fed back by a user, determining abnormal piece returning packages according to the abnormal piece returning information, and searching logistics information of the abnormal piece returning packages;
305. determining a responsibility network point of the abnormal return parcel based on a preset algorithm and logistics information of the abnormal return parcel;
wherein, the steps 301-305 are similar to the execution steps of the steps 101-105, and detailed description thereof is omitted here.
306. Generating a returned statistical report based on the logistics information of each returned package obtained by real-time monitoring, and marking abnormal returned packages in the returned statistical report according to the abnormal returned packages information fed back by the user;
it can be understood that monitored logistics information of each returned package is stored in the database in a persistent mode, the server further generates a returned statistical report according to a preset report template and the logistics information, and the returned statistical report can be counted according to time (day, month and year), each website, each distribution, each large area and the like, so that express package information is transparent.
Optionally, the server marks abnormal quit data on the quit statistical report based on a data marking tool, such as doccano, for example, the letter "a" represents the abnormal quit data, and the letter "B" represents the non-abnormal quit data, so as to generate a type tag corresponding to each quit data. In the fine tuning stage of the model, the training result can be compared by depending on the label, so that the network parameters of the model are adjusted to reduce errors and improve the accuracy of model identification.
307. Carrying out data splitting on a returned statistical report containing the abnormal returned piece mark to form a returned piece data set;
it can be understood that the returned statistical report form is a structured data text, the server can divide the returned data into a plurality of returned data according to the structural characteristics of the server, each returned data corresponds to logistics information of one returned package, the returned data corresponding to the abnormal returned package further comprises an abnormal identifier, and finally the divided returned data are constructed into returned data sets for model training.
308. And executing a training task including abnormal piece returning identification on a preset neural network model based on the piece returning data set to obtain an identification model for identifying the abnormal piece returning.
It can be understood that, after the preset initialization parameters of the neural network model, the server inputs the quit data set into the neural network model, maps the target quit data text in the quit data set to word vector representation based on the word embedding layer of the network model, each word is n-dimensional, and splices m words in the target quit data text to obtain an m-n-dimensional feature matrix, where the feature matrix is used for representing a piece of quit data. The Neural network model may be a Convolutional Neural Network (CNN) model, such as LeNet, AlexNet, VGG, and the like, which is not limited in this embodiment.
Performing feature weight and bias learning on the feature matrix of the target piece returning data based on the convolution layer of the network model, and extracting deep semantics in the feature matrix of the target piece returning data; and performing maximum pooling on the new feature matrix obtained after convolution, thereby reducing the feature matrix into a one-dimensional feature matrix.
Optionally, in order to prevent the model from being over-fitted, the server further performs random loss on part of the features based on the Dropout layer, so as to enable the Dropout layer to learn valid features, and the probability of random loss of the Dropout layer can be adjusted according to actual requirements, and is preferably set to 0.5 in the training stage of the model and set to 0.1 in the testing stage of the model.
And finally, inputting the pooled or randomly lost feature matrix into a full-connection layer network of the model, and generating a probability value that the target piece returning data is abnormal piece returning data based on a two-classifier of the network. The identification of abnormal condition-quitting data can be regarded as a two-classification task, namely the sum of probability values of abnormal condition-quitting data and non-abnormal condition-quitting data of one condition-quitting data is 1.
The classifier performs nonlinear transformation of semantic vectors through an activation function, such as Sigmoid, so as to map an output result into a (0, 1) interval and obtain a probability value. Specifically, the server calls the classifier to calculate an initial classification score of the input feature matrix under 2 classification labels (abnormal exit data "a" and non-abnormal exit data "B"), for example, T ═ a:3.2, B:5.1, according to a score function preset in the classifier.
Secondly, the server performs value diffusion on each initial classification score based on a preset diffusion function to obtain two target classification scores; it is understood that the data dispersion between the initial classification scores is small, the server value-diffuses (expands the numerical value) the initial classification scores by a preset diffusion function, such as an exp function (X-exponentiation of e of the initial classification scores, e is an euler number, i.e., an infinite acyclic decimal number, and X is the initial classification score), and the result is more obvious when the score is larger, for example, the distribution T is value-diffused, so that the distribution X is [ a: exp (3.2), B: exp (5.1) ], i.e., X is [ a:24.5, B:164.0 ].
Then, the server performs normalization processing on each target classification score to obtain a two-classification probability distribution, wherein the two-classification probability distribution is used for representing the probability distribution that the target quitting data is abnormal quitting data and non-abnormal quitting data.
It is understood that the normalization process (normalization) aims at mapping the data to a decimal number (i.e. a probability) between 0 and 1, for example, the normalization process is performed on the distribution X, the total score is obtained by summing up each target classification score in the distribution X, and then the ratio between each classification score and the total score is calculated, so as to obtain a binary probability distribution Z ═ a:0.13, B: 0.87.
Further, the server calculates a loss value of a binary probability distribution based on a preset loss function, wherein the loss value of the binary probability distribution is used for representing the error between the current model identification result and the actual result, and the smaller the loss value is, the more accurate the identification result is. And the server iteratively adjusts the network parameters of the neural network model according to the loss value, then trains and calculates the corresponding loss value again until the model converges, and determines the network parameters with the optimal effect, so that the identification model for identifying the abnormal returned piece is obtained.
Optionally, the server may iteratively update the network parameters of the neural network model based on random gradient descent, and first input a loss value corresponding to the two-class probability distribution into the neural network model, and reversely propagate the loss value from the output layer of the neural network model to the hidden layer until the loss value is propagated to the input layer of the model. In the process of back propagation, a point direction is randomly selected for gradient descent according to a loss value, iterative updating is carried out on the weights of the feature vectors in the input layer and the hidden layer of the model according to the result of the gradient descent, the corresponding binary probability distribution and the loss value thereof are recalculated after each weight updating, and when the model converges, the current network parameter is determined as a target parameter, so that the identification model for identifying the abnormal retreating piece is obtained.
Optionally, the server may further divide the quit data set into a training data set and a verification data set based on a preset division ratio, where the preset division ratio is determined based on a business requirement, for example, 80% of sample data in the business requirement is required to be used as a training sample to construct the training data set for training the model, and the remaining 20% of sample data is used as a verification sample to construct the verification data set for verifying the model.
In this embodiment, a process of training a recognition model for recognizing an abnormal article return is described in detail, and an abnormal article return recognition mode based on a deep learning model is provided on the basis of the user feedback of abnormal article return information in embodiment 1, so that logistics enterprises can autonomously screen and recognize abnormal article return.
With reference to fig. 4, the method for monitoring the rollback of an express package according to an embodiment of the present invention is described above, and a device for monitoring the rollback of an express package according to an embodiment of the present invention is described below, where an embodiment of the device for monitoring the rollback of an express package according to an embodiment of the present invention includes:
the information receiving module 401 is configured to receive return package information to be processed;
a list construction module 402, configured to construct a return package monitoring list according to the return package information;
a logistics information monitoring module 403, configured to monitor logistics information of each returned package in the returned package monitoring list in real time, where each returned package information corresponds to one returned package;
an abnormal component determining module 404, configured to receive abnormal component returning information fed back by a user, determine an abnormal component returning package according to the abnormal component returning information, and search logistics information of the abnormal component returning package;
and a responsibility network point determining module 405, configured to determine a responsibility network point of the abnormal return package based on a preset algorithm and the logistics information of the abnormal return package.
In the embodiment, the corresponding responsibility network is quickly positioned through the logistics information of the abnormal quit information, and corresponding reward and punishment measures are executed on the responsibility network, so that the service quality of the network is improved, and the capital loss and customer complaints of logistics enterprises are reduced.
Referring to fig. 5, another embodiment of the device for monitoring the return of the express package in the embodiment of the present invention includes:
the information receiving module 401 is configured to receive return package information to be processed;
a list construction module 402, configured to construct a quit monitoring list according to the quit package information;
a logistics information monitoring module 403, configured to monitor logistics information of each returned package in the returned package monitoring list in real time, where each returned package information corresponds to one returned package;
an abnormal component determining module 404, configured to receive abnormal component returning information fed back by a user, determine an abnormal component returning package according to the abnormal component returning information, and search logistics information of the abnormal component returning package;
and a responsibility network point determining module 405, configured to determine a responsibility network point of the abnormal return package based on a preset algorithm and the logistics information of the abnormal return package.
The list building module 402 specifically includes:
an object creating unit 4021, configured to create an empty list object based on a preset list construction function;
the element generating unit 4022 is configured to generate a list element according to each piece of return package information;
an element adding unit 4023, configured to add the list elements to the empty list object, respectively, to obtain a quit monitoring list;
a dynamic application unit 4024, configured to apply for a continuous memory block in a dynamic storage area of a memory;
an information storage unit 4025, configured to store the newly added return package information to the data field of the memory block;
a pointer setting unit 4026, configured to store the memory area address of the memory block to the pointer field of the table tail node in the retired monitoring list in the linked list format, so as to point the pointer of the table tail node to the memory block.
The responsible site determining module 405 specifically includes:
the predicted value calculating unit 4051 is configured to perform address collection calculation based on the logistics information of the abnormal return package to obtain a predicted value of a next return station of the abnormal return package;
the node determining unit 4052 is configured to determine a responsibility node of the abnormal return package according to a preset algorithm and a predicted value of a next return station of the abnormal return package.
The mesh point determining unit 4052 is specifically configured to:
if the predicted value of the next returning station of the abnormal returning parcel is empty, determining the returning scanning station as a responsibility network point of the abnormal returning parcel, otherwise, judging whether a transfer subordinate station is the predicted value;
if the transfer subordinate station is the predicted value, determining the predicted value as a responsibility network point of the abnormal quit package, otherwise, judging whether the originating station is the transfer subordinate station;
and if the starting station is the transfer subordinate station, determining the return scanning station as the responsibility network point of the abnormal return package, otherwise, determining the predicted value as the responsibility network point of the abnormal return package.
In the embodiment of the invention, the modularized design ensures that hardware of each part of the express package rollback monitoring device is concentrated on realizing a certain function, the performance of the hardware is realized to the maximum extent, and meanwhile, the modularized design also reduces the coupling between modules of the device, so that the maintenance is more convenient.
Fig. 4 and 5 describe the express package return monitoring apparatus in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the express package return monitoring apparatus in the embodiment of the present invention is described in detail from the perspective of hardware processing.
Fig. 6 is a schematic structural diagram of an express package rollback monitoring device according to an embodiment of the present invention, where the express package rollback monitoring device 600 may generate a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 610 (e.g., one or more processors) and a memory 620, and one or more storage media 630 (e.g., one or more mass storage devices) storing applications 633 or data 632. Memory 620 and storage medium 630 may be, among other things, transient or persistent storage. The program stored on the storage medium 630 may include one or more modules (not shown), each of which may include a series of instructional operations in the return monitoring device 600 for an express package. Still further, the processor 610 may be configured to communicate with the storage medium 630 to execute a series of instruction operations in the storage medium 630 on the courier package return monitoring device 600.
The courier package rollback monitoring device 600 may also include one or more power supplies 640, one or more wired or wireless network interfaces 650, one or more input-output interfaces 660, and/or one or more operating systems 631, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, and the like. Those skilled in the art will appreciate that the courier package return monitoring device configuration shown in fig. 6 does not constitute a limitation of a courier package return monitoring device, and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.
The invention further provides a device for monitoring the rollback of the express package, which comprises a memory and a processor, wherein computer readable instructions are stored in the memory, and when being executed by the processor, the computer readable instructions cause the processor to execute the steps of monitoring the rollback of the express package in the embodiments.
The present invention also provides a computer readable storage medium, which may be a non-volatile computer readable storage medium, or a volatile computer readable storage medium, having stored therein instructions, which when executed on a computer, cause the computer to perform the steps of monitoring for the return of the express package.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (10)

1. A method for monitoring the return of an express package is characterized by comprising the following steps:
receiving return package information to be processed;
constructing a quit monitoring list according to the quit package information;
monitoring logistics information of each piece of piece-returning package in the piece-returning monitoring list in real time, wherein each piece of piece-returning package information corresponds to one piece of piece-returning package;
receiving abnormal piece returning information fed back by a user, determining abnormal piece returning packages according to the abnormal piece returning information, and searching logistics information of the abnormal piece returning packages;
and determining a responsibility network point of the abnormal return parcel based on a preset algorithm and the logistics information of the abnormal return parcel.
2. The method for monitoring the return of express delivery packages according to claim 1, wherein the constructing a return monitoring list according to the return package information comprises:
creating an empty list object based on a preset list construction function;
generating a list element according to each piece of return package information;
and respectively adding the list elements to the empty list objects to obtain a returned monitoring list.
3. The method for monitoring rollback of an express package according to claim 2, wherein a data structure of the return monitoring list is in a linked list form, and after the list elements are respectively added to the empty list objects and the return monitoring list is obtained, the method further comprises:
when newly-added piece returning package information is received, applying for a continuous memory block in a dynamic storage area of a memory, and storing the newly-added piece returning package information to a data field of the memory block;
and storing the memory area address of the memory block to a pointer field of a table tail node in the linked list type return monitoring list so as to point the pointer of the table tail node to the memory block.
4. The express parcel return monitoring method of claim 1, wherein the determining the responsibility network of the abnormal return parcel based on a preset algorithm and the logistics information of the abnormal return parcel comprises:
performing address collection calculation based on the logistics information of the abnormal return parcel to obtain a predicted value of a next return station of the abnormal return parcel;
and determining a responsibility network point of the abnormal quit package according to a preset algorithm and a predicted value of the next quit station of the abnormal quit package.
5. The express parcel return monitoring method according to claim 4, wherein the logistics information of the abnormal return parcel comprises a return scanning site, a transit subordinate site and an originating site, and the determining the responsibility network point of the abnormal return parcel according to the preset algorithm and the predicted value of the next return site of the abnormal return parcel comprises:
if the predicted value of the next returning station of the abnormal returning parcel is empty, determining the returning scanning station as a responsibility network point of the abnormal returning parcel, otherwise, judging whether a transfer subordinate station is the predicted value;
if the transfer subordinate station is the predicted value, determining the predicted value as a responsibility network point of the abnormal quit package, otherwise, judging whether the originating station is the transfer subordinate station;
and if the starting station is the transfer subordinate station, determining the return scanning station as the responsibility network point of the abnormal return package, otherwise, determining the predicted value as the responsibility network point of the abnormal return package.
6. The method for monitoring the return of express parcels according to claim 1, further comprising:
generating a returned statistical report based on the logistics information of each returned package obtained by real-time monitoring;
according to the abnormal quit information fed back by the user, marking abnormal quit on the quit statistical report;
carrying out data splitting on a returned statistical report containing the abnormal returned piece mark to form a returned piece data set;
and executing a training task including abnormal piece returning identification on a preset neural network model based on the piece returning data set to obtain an identification model for identifying abnormal piece returning.
7. The method for monitoring the return of express parcels according to any of claims 1-6, further comprising:
and obtaining and determining a strategy for performing reward and punishment on the responsibility network points according to the number of abnormal piece returning packages of the responsibility network points in a preset time period.
8. The utility model provides an express delivery parcel's monitoring device that rolls back which characterized in that, express delivery parcel's monitoring device that rolls back includes:
the information receiving module is used for receiving the return parcel information to be processed;
the list construction module is used for constructing a return monitoring list according to the return package information;
the logistics information monitoring module is used for monitoring logistics information of each returned package in the returned package monitoring list in real time, wherein each piece of returned package information corresponds to one returned package;
the abnormal piece determining module is used for receiving abnormal piece returning information fed back by a user, determining abnormal piece returning packages according to the abnormal piece returning information and searching logistics information of the abnormal piece returning packages;
and the responsibility network point determining module is used for determining the responsibility network points of the abnormal return packages based on a preset algorithm and the logistics information of the abnormal return packages.
9. The utility model provides an express delivery parcel's monitoring equipment that rolls back which characterized in that, express delivery parcel's monitoring equipment that rolls back includes: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invokes the instructions in the memory to cause the express package return monitoring device to perform the express package return monitoring method of any of claims 1-7.
10. A computer-readable storage medium having instructions stored thereon, wherein the instructions, when executed by a processor, implement a method for monitoring the return of a courier package according to any of claims 1-7.
CN202210292604.2A 2022-03-24 2022-03-24 Express package rollback monitoring method, device, equipment and storage medium Pending CN114862298A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210292604.2A CN114862298A (en) 2022-03-24 2022-03-24 Express package rollback monitoring method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210292604.2A CN114862298A (en) 2022-03-24 2022-03-24 Express package rollback monitoring method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN114862298A true CN114862298A (en) 2022-08-05

Family

ID=82627743

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210292604.2A Pending CN114862298A (en) 2022-03-24 2022-03-24 Express package rollback monitoring method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114862298A (en)

Similar Documents

Publication Publication Date Title
CN109255564B (en) Pick-up point address recommendation method and device
US10977290B2 (en) Transaction categorization system
CN116401464B (en) Professional user portrait construction method, device, equipment and storage medium
CN111078835A (en) Resume evaluation method and device, computer equipment and storage medium
CN110717333B (en) Automatic generation method and device for article abstract and computer readable storage medium
CN113868419A (en) Text classification method, device, equipment and medium based on artificial intelligence
CN113537878A (en) Package delivery method, device, equipment and storage medium
CN111222923B (en) Method and device for judging potential clients, electronic equipment and storage medium
CN110765778B (en) Label entity processing method, device, computer equipment and storage medium
CN114862298A (en) Express package rollback monitoring method, device, equipment and storage medium
CN111382254A (en) Electronic business card recommendation method, device, equipment and computer readable storage medium
CN115865777A (en) RPA technology-based recruitment order intelligent distribution routing method
CN116226747A (en) Training method of data classification model, data classification method and electronic equipment
CN115712684A (en) Storage method and system for dynamic information of articles in Internet of things
US20220292393A1 (en) Utilizing machine learning models to generate initiative plans
CN114092057A (en) Project model construction method and device, terminal equipment and storage medium
CN113822477A (en) Express item interception processing method, device, equipment and storage medium
CN114154480A (en) Information extraction method, device, equipment and storage medium
US20220038671A1 (en) Digital evidence management method and digital evidence management system
CN115577867B (en) Method and system for creating spot check task, computer equipment and storage medium
CN117726266A (en) Method and device for determining returning responsibility network point, electronic equipment and storage medium
CN118036606B (en) Data processing method based on intelligent decision framework
CN116304230A (en) Work order creation method, device, equipment and storage medium
CN115456514A (en) Logistics abnormity early warning method, device, equipment and storage medium
CN117056372A (en) Logistics data aggregation method, device, equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination