CN120543046A

CN120543046A - Package loss warning processing method and device, electronic equipment, and medium

Info

Publication number: CN120543046A
Application number: CN202410210974.6A
Authority: CN
Inventors: 曾浩
Original assignee: Beijing Jd Yuansheng Technology Co ltd
Current assignee: Beijing Jd Yuansheng Technology Co ltd
Priority date: 2024-02-26
Filing date: 2024-02-26
Publication date: 2025-08-26

Abstract

The invention provides a package loss early warning processing method which can be applied to the technical field of intelligent logistics and the technical field of big data computers, and comprises the steps of reading target loss discrimination rules pre-constructed for a target station from a rule base, wherein the target loss discrimination rules are constructed based on N pieces of historical loss discrimination data, the N pieces of historical loss discrimination data correspond to N pieces of historical packages passing through the target station, and the historical loss discrimination data are used for representing the reason of package loss; and carrying out loss early warning processing on the target package which is transferred to the target station by utilizing a target loss discrimination rule.

Description

Package loss early warning processing method and device, electronic equipment and medium

Technical Field

The disclosure relates to the technical field of intelligent logistics and the technical field of big data computers, in particular to a package loss early warning processing method, a package loss early warning processing device, package loss early warning processing equipment, package loss early warning processing medium and a package loss early warning processing program product.

Background

In the package logistics transportation, package loss and breakage abnormal events frequently occur, and losses are caused to clients and logistics enterprises.

In the process of realizing the disclosed concept, the inventor finds that at least the following problems exist in the related art, namely, the conventional method is mainly a post-processing mechanism for package loss, such as post-responsibility judgment and inventory analysis of the cause of abnormality. Because the processing mode is a post-hoc mechanism, the package loss cannot be pre-warned in advance, and the effect of effectively improving the package loss condition of the current field station is not achieved.

Disclosure of Invention

In view of the foregoing, the present disclosure provides a method, apparatus, device, medium, and program product for processing package loss data.

In one aspect of the present disclosure, a method for pre-warning package loss is provided, including:

reading a target loss discrimination rule pre-constructed for a target station from a rule base, wherein the target loss discrimination rule is constructed based on N pieces of historical loss discrimination data, the N pieces of historical loss discrimination data correspond to N historical packages passing through the target station, and the historical loss discrimination data are used for representing loss attribution of the packages;

And carrying out loss early warning processing on the target package which is transferred to the target station by utilizing a target loss discrimination rule.

According to an embodiment of the present disclosure, the above method further includes:

acquiring N pieces of historical loss judgment data corresponding to the N historical packages;

generating M initial loss judgment rules based on N pieces of historical loss judgment rule data;

and screening the M initial loss discrimination rules to generate target loss discrimination rules for the target field station.

According to an embodiment of the present disclosure, each piece of historical loss determination data includes a package identifier and at least one attribution, and generating M pieces of initial loss determination rules based on the N pieces of historical loss determination data includes:

Determining the frequency of each of L attribution items contained in N pieces of historical loss judgment data;

Determining S reference attribution items from the L attribution items based on a preset frequency threshold value and the frequency of each attribution item;

And generating M initial loss judgment rules by utilizing the N historical loss judgment data and the S reference attribution items.

According to an embodiment of the present disclosure, generating M initial loss discrimination rules using N pieces of historical loss discrimination data and S pieces of reference attribution items includes:

determining at least one target attribution item matched with the historical loss judgment data from S reference attribution items according to each piece of the historical loss judgment data;

M initial loss discrimination rules are generated based on at least one target attribution item matched with each historical loss discrimination data.

Based on S reference attribution items, attribution item screening is carried out on N pieces of historical loss judgment data respectively, and N pieces of basic construction data are generated;

constructing a frequent pattern tree based on the N pieces of basic construction data, wherein the sub-nodes or leaf nodes of the frequent pattern tree correspond to reference attribution items, and the subtrees of the frequent pattern tree correspond to the basic construction data;

Obtaining at least one target attribution item matched with each piece of historical loss judgment data based on the frequent pattern tree;

According to an embodiment of the present disclosure, wherein:

The at least one attribution item comprises a first attribution item, a second attribution item and a third attribution item, wherein the first attribution item is used for representing basic reference information of a target parcel flowing to the target station, the second attribution item is used for representing logistics operation information of the target parcel at the target station, and the third attribution item is used for representing environment information of the target station.

According to an embodiment of the present disclosure, wherein:

Each attribution item is one of a plurality of predefined factors, and the plurality of predefined factors at least comprise seasons, operation links, weather conditions, ambient temperature, ambient humidity, article types, responsible person labels and shipping merchant labels.

According to an embodiment of the present disclosure, the filtering processing is performed on M pieces of initial loss discrimination rules, and generating a target loss discrimination rule for a target field station includes:

calculating the support, confidence and lifting degree of each initial loss judgment rule;

And screening the M initial loss discrimination rules by using preset screening rules based on the support, the confidence and the lifting degree of each initial loss discrimination rule to generate target loss discrimination rules for the target field station.

According to an embodiment of the present disclosure, the target loss discrimination rule is used to characterize at least one target attribution item that is likely to cause a loss of a package at a target station, and the performing, with the target loss discrimination rule, a loss early warning process on a target package that is transferred to the target station includes:

Basic reference information of the target package, logistics operation information of the target package at the target station and environment information of the target station are acquired;

And under the condition that the basic reference information, the logistics operation information and the environment information hit the target loss judgment rule, carrying out loss early warning processing on the target package.

According to an embodiment of the present disclosure, wherein:

The basic reference information comprises at least one of an article type and a delivery merchant label, wherein the delivery merchant label is obtained by inquiring a label database based on a delivery merchant identification;

The logistics operation information comprises at least one operation link and a responsible person label, wherein the responsible person label is obtained by inquiring a label database based on a responsible person identifier;

the environmental information includes at least one of season, weather condition, ambient temperature, ambient humidity.

Another aspect of the disclosure provides a package damage early-warning processing device, which includes a reading module and an early-warning module.

The device comprises a rule base, a reading module, an early warning module and a target loss judgment module, wherein the rule base is used for reading target loss judgment rules pre-constructed for a target station, the target loss judgment rules are constructed based on N pieces of historical loss judgment data, the N pieces of historical loss judgment data correspond to N historical packages passing through the target station, the historical loss judgment data are used for representing loss attribution of the packages, and the early warning module is used for carrying out early warning treatment on the target packages which are transferred to the target station in a streaming manner by utilizing the target loss judgment rules.

According to the embodiment of the disclosure, the device further comprises an acquisition module, a generation module and a screening module.

The device comprises an acquisition module for acquiring N pieces of historical loss judgment data corresponding to N historical packages, a generation module for generating M pieces of initial loss judgment rules based on the N pieces of historical loss judgment data, and a screening module for screening the M pieces of initial loss judgment rules to generate target loss judgment rules for target stations.

According to the embodiment of the disclosure, each piece of historical loss judgment data comprises a package identifier and at least one attribution item, and the generating module comprises a first determining unit, a second determining unit and a generating unit.

The device comprises a first determining unit, a second determining unit and a generating unit, wherein the first determining unit is used for determining the frequency of each attribution item in L attribution items contained in N historical loss judgment data, the second determining unit is used for determining S reference attribution items from the L attribution items based on a preset frequency threshold value and the frequency of each attribution item, and the generating unit is used for generating M initial loss judgment rules by utilizing the N historical loss judgment data and the S reference attribution items.

According to an embodiment of the disclosure, the generating unit comprises a first determining subunit, a first generating subunit.

The device comprises a first determining subunit, a first generating subunit and a second generating subunit, wherein the first determining subunit is used for determining at least one target attribution item matched with the historical loss judgment data from S reference attribution items aiming at each piece of historical loss judgment data, and the first generating subunit is used for generating M initial loss judgment rules based on the at least one target attribution item matched with each piece of historical loss judgment data.

According to an embodiment of the disclosure, the generating unit includes a second generating subunit, a building subunit, a third generating subunit, and a fourth generating subunit.

The device comprises a first generation subunit, a construction subunit, a third generation subunit and a fourth generation subunit, wherein the first generation subunit is used for respectively carrying out attribution item screening on N pieces of historical loss judgment data based on S reference attribution items to generate N pieces of basic construction data, the construction subunit is used for constructing a frequent pattern tree based on the N pieces of basic construction data, the child nodes or leaf nodes of the frequent pattern tree correspond to the reference attribution items, the subtree of the frequent pattern tree corresponds to the basic construction data, the third generation subunit is used for obtaining at least one target attribution item matched with each piece of historical loss judgment data based on the frequent pattern tree, and the fourth generation subunit is used for generating M pieces of initial loss judgment rules based on at least one target attribution item matched with each piece of historical loss judgment data.

According to an embodiment of the present disclosure, the at least one attribution comprises a first type attribution, a second type attribution, and a third type attribution, wherein the first type attribution is used for characterizing basic reference information of a target parcel flowing to a target venue, the second type attribution is used for characterizing logistics operation information of the target parcel at the target venue, and the third type attribution is used for characterizing environmental information of the target venue.

According to an embodiment of the present disclosure, each of the attribution items is one of a plurality of predefined factors including at least season, operation link, weather condition, ambient temperature, ambient humidity, item category, responsible person tag, shipping merchant tag.

According to an embodiment of the disclosure, the screening module comprises a computing unit and a screening unit.

The device comprises a calculation unit, a screening unit and a screening unit, wherein the calculation unit is used for calculating the support degree, the confidence degree and the lifting degree of each initial loss judgment rule, and the screening unit is used for screening M initial loss judgment rules by using preset screening rules based on the support degree, the confidence degree and the lifting degree of each initial loss judgment rule to generate target loss judgment rules aiming at target stations.

According to the embodiment of the disclosure, the target loss discrimination rule is used for representing at least one target attribution item which is easy to cause package loss at the target field station, and the early warning module comprises an acquisition unit and an early warning unit.

The system comprises an acquisition unit, an early warning unit and a warning unit, wherein the acquisition unit is used for acquiring basic reference information of a target package, logistics operation information of the target package at a target station and environment information of the target station, and the early warning unit is used for carrying out loss-warning processing on the target package under the condition that the basic reference information, the logistics operation information and the environment information hit a target loss judgment rule.

According to an embodiment of the present disclosure, wherein:

Another aspect of the disclosure provides an electronic device comprising one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the wraparound data processing method described above.

Another aspect of the disclosure also provides a computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the above-described method of processing wrapping data.

Another aspect of the disclosure also provides a computer program product comprising a computer program which, when executed by a processor, implements the above-described method of processing wrapping data.

According to the embodiment of the disclosure, the historical loss judging responsibility data of the station packages are processed, and the loss judging rule for each station is pre-established, so that when the packages flow to each station, the packages hitting the judging rules are pre-warned by calling the judging rules for each station, a new solution is provided for the loss management improvement of the logistics industry, intelligent analysis and pre-warning are realized, the technical problem of high package loss rate caused by incapability of pre-warning is solved, the loss rate in the logistics transportation is reduced, and measures such as optimizing operation links, reinforcing training of responsible persons, improving weather and environment are facilitated, so that the package loss and breakage rate are reduced.

Drawings

The foregoing and other objects, features and advantages of the disclosure will be more apparent from the following description of embodiments of the disclosure with reference to the accompanying drawings, in which:

FIG. 1 schematically illustrates an application scenario diagram of a method, apparatus, device, medium and program product for package loss pre-alarm processing according to an embodiment of the disclosure;

FIG. 2 schematically illustrates a flow chart of a method of package loss pre-alarm processing according to an embodiment of the disclosure;

FIG. 3 schematically illustrates a flow chart of a method of generating a target loss discrimination rule in accordance with an embodiment of the disclosure;

FIG. 4 schematically illustrates a flow chart of a method of generating an initial loss discrimination rule in accordance with an embodiment of the disclosure;

FIG. 5 schematically illustrates a flow chart of a method of processing a loss of a package in accordance with another embodiment of the disclosure;

FIG. 6 schematically illustrates a structural schematic of a constructed frequent item tree, in accordance with an embodiment of the present disclosure;

FIG. 7 schematically shows a block diagram of a device for processing a loss-in-package according to an embodiment of the present disclosure, and

Fig. 8 schematically illustrates a block diagram of an electronic device suitable for implementing a method for processing a loss of a package according to an embodiment of the disclosure.

Detailed Description

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is only exemplary and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. In addition, in the following description, descriptions of well-known structures and techniques are omitted so as not to unnecessarily obscure the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and/or the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It should be noted that the terms used herein should be construed to have meanings consistent with the context of the present specification and should not be construed in an idealized or overly formal manner.

Where a convention analogous to "at least one of A, B and C, etc." is used, in general such a convention should be interpreted in accordance with the meaning of one of skill in the art having generally understood the convention (e.g., "a system having at least one of A, B and C" would include, but not be limited to, systems having a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).

In embodiments of the present disclosure, the collection, updating, analysis, processing, use, transmission, provision, disclosure, storage, etc., of the data involved (including, but not limited to, user personal information) all comply with relevant legal regulations, are used for legal purposes, and do not violate well-known. In particular, necessary measures are taken for personal information of the user, illegal access to personal information data of the user is prevented, and personal information security, network security and national security of the user are maintained.

In embodiments of the present disclosure, the user's authorization or consent is obtained before the user's personal information is obtained or collected.

The embodiment of the disclosure provides a method for processing package loss early warning, which comprises the following steps:

The method comprises the steps of reading target loss judging rules pre-constructed for a target station from a rule base, wherein the target loss judging rules are constructed based on N pieces of historical loss judging data, the N pieces of historical loss judging data correspond to N historical packages passing through the target station, the historical loss judging data are used for representing loss attribution of the packages, and performing loss early warning processing on the target packages transferred to the target station by streaming by utilizing the target loss judging rules.

Fig. 1 schematically illustrates an application scenario diagram of a method, an apparatus, a device, a medium and a program product for processing a loss pre-alarm of a package according to an embodiment of the disclosure.

As shown in fig. 1, an application scenario 100 according to this embodiment may include a terminal device 101, a server 102, and a database 103. The terminal device 101, the server 102, and the database 103 may communicate via a network, which may include various connection types, such as a wired, wireless communication link, or a fiber optic cable, etc.

A user may interact with the server 102 through a network using the terminal device 101 to receive or send messages or the like. Various communication client applications, such as shopping class applications, web browser applications, search class applications, instant messaging tools, mailbox clients, social platform software, etc., may be installed on the terminal device 101 (by way of example only).

The terminal device 101 may be a variety of electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.

The server 102 may be a server providing various services, such as a background management server (for example only) providing support for websites browsed by the user using the terminal device 101. The background management server may analyze and process the received data such as the user request, and feed back the processing result (e.g., the web page, information, or data obtained or generated according to the user request) to the terminal device.

Database 103 may also be various types of data storage structures such as relational databases, or non-relational databases, and the like.

In the application scenario of the present disclosure, a user may interact with the server 102 through the terminal device 101 to initiate processing of a target package that flows to a target station to determine whether to initiate loss early warning. In response to a user request, the server 102 may be configured to perform the method according to the embodiments of the present disclosure, for example, read, from the database 103, the history loss determination rule data of the history packages passing through the target station, and establish the loss determination rule based on the history loss determination rule data and store the loss determination rule in the database 103, and in the case that the packages flow to the target station, determine whether to initiate loss warning based on the previously constructed determination rule, and return the processing result to the user through the terminal device 101.

It should be noted that, the method for processing the package loss alarm provided in the embodiments of the disclosure may be generally executed by the server 102. Accordingly, the package loss warning processing device provided in the embodiments of the present disclosure may be generally disposed in the server 102. The method for processing the loss of packages provided in the embodiments of the present disclosure may also be performed by a server or a server cluster that is different from the server 102 and is capable of communicating with the terminal device 101 and/or the server 102. Accordingly, the package loss pre-alarm processing apparatus provided by the embodiments of the present disclosure may also be disposed in a server or a server cluster different from the server 102 and capable of communicating with the terminal device 101 and/or the server 102.

It should be understood that the number of terminal devices, servers, databases in fig. 1 is merely illustrative. There may be any number of terminal devices, servers, databases, as desired for implementation.

The method for processing the package loss early warning according to the disclosed embodiment will be described in detail with reference to fig. 2 to 8 based on the scenario described in fig. 1.

Fig. 2 schematically shows a flowchart of a method of package loss pre-alarm processing according to an embodiment of the disclosure.

As shown in FIG. 2, the method for processing the loss-in-package alarm includes operations S201 to S202.

In operation S201, a target loss discrimination rule pre-constructed for a target station is read from a rule base, where the target loss discrimination rule is constructed based on N pieces of history loss discrimination data, the N pieces of history loss discrimination data correspond to N pieces of history packages passing through the target station, and the history loss discrimination data is used to characterize loss attribution of the packages;

In operation S202, the target packages flowing to the target station are subjected to the loss early warning process using the target loss discrimination rule.

According to embodiments of the present disclosure, a parcel may be routed through multiple stations throughout a stream link to a destination, with a target station referring to any station in transit, such as a station to which the parcel is currently being streamed. The loss discrimination rule for each station may be constructed in advance, and stored in a rule base, and when the package flow goes to the current target station, the loss discrimination rule adapted to the station is read from the rule base through operation S201, and the loss discrimination processing is performed on the package through operation S202.

The loss determination rule may be constructed for each station (e.g., target station) by using the historical loss determination rule data of the station. For example, the target loss judgment rule for the target station is constructed based on N pieces of historical loss judgment data corresponding to N historical packages (packages where loss happens in the past in the history) passing through the target station, each package corresponds to one piece of loss judgment data, and the loss judgment data is obtained by carrying out responsibility judgment analysis processing on the lost packages and used for representing loss attribution of each historical loss package, including related data of package loss and breakage, such as information including time, operation links, responsible persons, weather, temperature, humidity, commodity class, merchant and the like.

The target loss discrimination rule is used to characterize at least one target attribution term (loss factor) that is likely to cause a loss of a wrapping at the target station, and the attribution term may include a plurality of, and may generally include an objective attribution term and a subjective attribution term. For example, objective factors such as commodity class (fragile), temperature (high temperature), and subjective factors such as operation links, operation actions, and the like.

According to the embodiments of the present disclosure, for a single station, which links, which categories, which flows, when, and which scenes are easy to lose are often analyzed and prevented empirically, so that early warning of lost damage and advice of empirical improvement cannot be provided for the station. Therefore, most of the package loss is currently a post-processing mechanism, such as post-processing of responsibility determination and inventory analysis of the cause of the abnormality. Because the processing mode is a post-hoc mechanism, the package loss cannot be pre-warned in advance, and the effect of effectively improving the package loss condition of the current field station is not achieved.

According to the embodiment of the disclosure, after the loss discrimination rule for each station is established, an operator can be trained by utilizing the loss discrimination rule, for example, improper operation of certain links is found to be easy to cause package damage according to the association rule, corresponding SOP operation can be formulated and improved, and popularization and propaganda work of standard operation are enhanced.

According to the embodiment of the disclosure, after the loss judgment rule for each station is established, the loss judgment rule can be used for early warning of the station, for example, if some merchants and goods of the goods are easy to damage on site according to the association rule, early warning reminding can be added, for example, when the goods of the merchants and the goods arrive at the station, site broadcasting early warning is added, and the like.

According to the embodiment of the disclosure, the historical loss judging responsibility data of the station packages are processed, and the loss judging rule for each station is established in advance, so that when the packages flow to each station, the packages hitting the judging rules are pre-warned by calling the judging rules for each station, a new solution is provided for the loss management improvement of the logistics industry, the mode of loss links possibly caused by intelligent analysis and early warning is realized, the great improvement and guidance effect on the loss rate of the tens of thousands of units in the express industry is realized, and the method is convenient for optimizing operation links, strengthening the training of responsible persons, improving measures such as weather and environment and the like, so that the loss and the breakage rate of the packages are reduced.

According to embodiments of the present disclosure, the target loss discrimination rule is used to characterize at least one target attribution term (loss factor) that is likely to cause a wrap-loss at the target field station, which may include at least one.

According to the first classification method, at least one attribution may be classified into an objective attribution and a subjective attribution. For example, objective factors such as commodity class (fragile), temperature (high temperature), and subjective factors such as operation links, operation actions, and the like.

According to a second classification method, at least one attribution item is classified into three categories, including a first category attribution item, a second category attribution item and a third category attribution item, wherein the first category attribution item is used for representing basic reference information of a target parcel flowing to a target station, the second category attribution item is used for representing logistics operation information of the target parcel at the target station, and the third category attribution item is used for representing environment information of the target station.

Further, each of the attribution items is one of a plurality of predefined factors including at least season, operation link, operation action, weather condition, ambient temperature, ambient humidity, article type, responsible person tag, shipping merchant tag. These items are key factors that are liable to cause loss of packages, such as seasonal factors that are liable to cause damage to fresh food in summer, handling links that are liable to cause damage to packages in the unloading link, ambient temperature that is liable to cause damage to fresh food in high temperature, kinds of articles that are fragile, responsible person labels that are fragile for packages executed by operators who complain about more customers, shipping merchant labels that are fragile for packages sent by merchants who are not in standardization in packaging, and so on.

According to the first classification method, seasons, weather conditions, ambient temperature, ambient humidity, article types and the like belong to objective attribution items, and operation links, operation actions, responsible person labels, shipping merchant labels and the like belong to subjective attribution items.

According to the second classification method, the object types and the labels of shipping merchants belong to basic reference information of packages, the labels of responsible persons, operation links and operation actions belong to logistics operation information, and seasons, weather conditions, environment temperature and environment humidity belong to environment information.

According to an embodiment of the present disclosure, based on an established target loss discrimination rule, performing loss early warning processing on a target package flowing to a target station by using the target loss discrimination rule includes the following operations:

and 11, acquiring basic reference information of the target package, logistics operation information of the target package at the target station and environment information of the target station.

The basic reference information comprises at least one of the types of articles (fragile articles, fresh articles, clothes and pets, etc.), and a delivery merchant label (whether packaging is not standard and whether the delivery merchant label is easy to miss, etc.), wherein the delivery merchant label is obtained by inquiring a label database based on the identification of the delivery merchant. Marking is carried out on a plurality of merchants through order logistics data, and labels such as whether packaging is not standard, whether goods are frequently missed or not are added.

The logistics operation information comprises at least one of operation links (unloading and sorting, and the like), responsibility person labels (whether the responsibility person is seriously responsible, whether complaint records exist, and the like), wherein the responsibility person labels are obtained by inquiring a label database based on responsibility person identification, and labels such as whether the responsibility person is seriously responsible, whether the complaint records exist, and the like can be added by marking a plurality of responsibility persons through order logistics data.

The environmental information includes at least one of a season (spring, summer, autumn, winter), a weather condition (strong wind, cold, hot, etc.), an environmental temperature (high temperature, low temperature, etc.), an environmental humidity (high humidity, low humidity, etc.).

And an operation 12, wherein when the basic reference information, the logistics operation information and the environment information hit the target loss judgment rule (hit all the attribution items contained in the rule), the target package is subjected to loss early warning processing.

For example, for the current station, one of the loss discrimination rules is "if the operation link is unloading and the ambient temperature is high temperature, the loss of the package is easy to cause". The obtained basic reference information comprises the types of the articles (fragile articles), the labels of shipping merchants (non-packaging non-standard merchants), logistics operation information comprises operation links (unloading), and environment information comprises seasons (summer), weather conditions (hot), environment temperature (high temperature) and environment humidity (high humidity). By matching the information with the loss discrimination rule, the operation link (unloading) and the environment temperature (high temperature), all the items contained in the hit rule are easy to cause loss of the package, and the package is subjected to loss early warning treatment.

Fig. 3 schematically shows a flow chart of a method of generating a target loss discrimination rule according to an embodiment of the disclosure.

As shown in FIG. 3, the method of this embodiment includes operations S301-S303.

In operation S301, N pieces of history loss judgment data corresponding to the N history packages are obtained;

in operation S302, M initial loss determination rules are generated based on the N pieces of historical loss determination data, for example, the M initial loss determination rules may be generated by combining the attribution items with higher frequency (greater than a preset threshold value) based on the frequency of each attribution item in all attribution items included in the N pieces of historical loss determination data.

In operation S303, a screening process is performed on the M pieces of initial loss discrimination rules, and a target loss discrimination rule for the target station is generated.

As is clear from the above operation, the loss determination rule may be constructed for each station (for example, target station) by using the historic loss determination data of the station. Each package corresponds to a piece of loss judgment data, and the loss judgment data is obtained by carrying out responsibility judgment analysis processing on the package of the loss and is used for representing the loss attribution of each historical loss package.

Based on N pieces of historical loss judgment rule data, M pieces of initial loss judgment rules are firstly generated, and rules which are most suitable for the station are further obtained through rule screening to serve as target rules.

According to the embodiment of the disclosure, the root cause establishment rule generated by the loss and the break is mined by analyzing and utilizing the responsibility judging data, so that the responsibility station can be guided to make specific and effective loss and loss improvement measures.

Fig. 4 schematically shows a flow chart of a method of generating an initial loss discrimination rule in accordance with an embodiment of the disclosure.

As shown in fig. 4, the method of this embodiment includes operations S401 to S403.

In operation S401, the frequency of each attribution item in L attribution items contained in the N pieces of historical loss judgment data is determined, wherein each piece of historical loss judgment data comprises at least one attribution item used for representing the loss attribution of each historical loss package, and the historical loss judgment data comprises time, operation links, responsible persons, weather, temperature, humidity, commodity class, merchant and the like. The N pieces of historical loss judgment data obtained through statistics can be the occurrence frequency of each attribution item in all attribution items included in the N pieces of historical loss judgment data.

In operation S402, S reference attribution items are determined from L attribution items based on a preset frequency threshold and the frequency of each attribution item, for example, 100 pieces of historical loss judgment data including 5 attribution items (A\B\C\D\E) with frequencies of 50, 24, 20, 10 and 2 respectively, the frequency threshold is set to be 20, and attribution items (A\B\C) with frequencies greater than or equal to the frequency threshold of 20 are used as reference attribution items.

In operation S403, M initial loss discrimination rules are generated using the N pieces of history loss discrimination data and the S pieces of reference attribution items. And according to the combination mode of attribution items included in each piece of historical loss judgment data, part or all of the S reference attribution items can be combined to generate M pieces of initial loss judgment rules.

Further, the method for generating M initial loss judging rules by using the N pieces of historical loss judging data and the S pieces of reference attribution items comprises various methods, for example, the initial loss judging rules can be generated by a data matching processing mode, or the initial loss judging rules can be generated by constructing a frequent item tree (Frequent PATTERN TREE) and mining frequent items in the frequent item tree.

Fig. 5 schematically shows a flowchart of a package loss warning processing method according to this embodiment.

In the method of this embodiment, as shown in fig. 5, data collection is first performed. And (3) in each station, judging and analyzing the lost packages, carding out factors influencing the loss of the packages, and establishing a piece of loss judgment data for each package. Related data of package loss and breakage, such as time, operation links, responsible person, weather, temperature, humidity, commodity class, merchant and other information

After that, data preprocessing is performed. The data is arranged into a format suitable for processing, such as forming a data set containing package loss, breakage labels, and cleaning and missing value filling of the data, such as removing duplicate data, processing outliers, etc. The tag is converted to a binary feature for more convenient processing of the data.

Then, a frequent item tree is constructed, and an initial loss discrimination rule is generated by mining frequent items in the frequent item tree. And the generated rule is used for the loss early warning of the station, so that evading measures possibly causing the loss of the package are executed in advance, and the occurrence of the loss of the package is reduced.

Further, the method for generating the M initial loss discrimination rules by using the N historical loss discrimination data and the S reference attribution items may be to generate the initial loss discrimination rules by means of data matching processing, or may also be to construct a frequent item tree, and generate the initial loss discrimination rules by mining frequent items in the frequent item tree. Hereinafter, the two methods are described separately.

Specifically, the method for generating the initial loss discrimination rule by means of data matching processing includes an operation 21 and an operation 22.

At operation 21, at least one target attribution item matching the history loss judgment result data is determined from among the S reference attribution items for each of the history loss judgment result data. That is, the intersection of the S reference attribution items with attribution items included in the history loss judgment data is calculated.

For example, one piece of historical loss judgment data comprises attribution items including an A season, a B operation link, a C weather condition and a D environment temperature, the reference attribution items comprise the B operation link, the D environment temperature, the E object type and the F shipping merchant label, and the attribution items matched with the data attribution items are determined to be the B operation link and the D environment temperature from the S reference attribution items.

In operation 22, M initial loss discrimination rules are generated based on at least one target attribution item matching each of the historical loss discrimination data. For example, an initial loss judgment rule is established based on the obtained target attribution item B operation link and the obtained target attribution item D environmental temperature, wherein the loss of the package is easy to cause if the operation link is unloading and the environmental temperature is high.

Specifically, a method of generating an initial loss discrimination rule by constructing a frequent item tree, by mining frequent items in the frequent item tree, is described below. The method comprises the following operations:

and (31) based on the S reference attribution items, attribution item screening is carried out on the N pieces of historical loss judgment data respectively to generate N pieces of basic construction data, and the reference attribution items contained in each piece of historical loss judgment data are screened out, and non-reference attribution items are filtered out to obtain the basic construction data.

For example, the reference attribution items comprise a B operation link, a D environment temperature, an E object type and an F shipping merchant label, wherein one piece of historical loss judgment data comprises attribution items comprising a season A, a B operation link, a weather condition C and an environment temperature D, and the basic construction data are obtained by filtering non-reference attribution items.

And an operation 32 of constructing a frequent pattern tree based on the N pieces of basic construction data, wherein the sub-nodes or leaf nodes of the frequent pattern tree correspond to the reference attribution items, and the subtrees of the frequent pattern tree correspond to the basic construction data.

For example, the N pieces of basic construction data are inserted into the frequent item tree one by one, each responsibility judging record is constructed as an independent subtree, when the frequent item tree is constructed, the frequency of each item set needs to be counted, the insertion sequence can be the ancestor node in the front of the sequence according to the sequence from high frequency to low frequency of the attribution items, the offspring node is the latter, if common ancestors exist, the frequency of the corresponding common ancestor nodes is increased by 1, all the data are guided to be inserted into the frequent item tree, and the construction of the frequent item tree is completed.

Fig. 6 schematically illustrates a structural schematic of a constructed frequent item tree, according to an embodiment of the disclosure.

As shown in fig. 6, the root node identifies the station, each sub-tree corresponds to one piece of basic construction data, one piece of data is a season a, an operation link B, an item type E and an F shipping merchant label, and the other piece of data is a season a, a weather condition C and an item type E.

At least one target attribution item matching each of the historical loss judgment data is obtained based on the frequent pattern tree, operation 33.

And performing frequent item mining on the constructed frequent pattern tree. For example, starting from the root node of the frequent item tree, each node is recursively traversed and the frequent item set for that node is mined. For each node, a set of frequent items is mined. Specifically, for each subset of the infrequent item sets, a new subset is generated by recursively deleting the elements therein, and the support thereof is calculated. And storing all the frequent item sets meeting the minimum support threshold as candidate frequent item sets causing the cause of loss.

An operation 34 generates M initial loss discrimination rules based on at least one target attribution item matching each of the historical loss discrimination data. For each frequent item set, all possible association rules are generated. The association rules may be expressed in terms of conditional statements, such as "if the link of operation is a drop, then package breakage is likely to result".

According to embodiments of the present disclosure, frequent item trees are constructed based on the preprocessed data for storing frequent items and association rules in package lost, corrupted data.

Compared to methods for traditional manual analysis of responsibility-judging data, or based on other algorithms, such as the defect that the data mining technology based on Apriori algorithm needs to scan the database multiple times, the algorithm of the embodiment of the disclosure only needs to scan the database twice, does not need to generate a candidate set, but directly mines frequent item sets in the process of constructing a frequent item tree, has high speed and can reduce unnecessary calculation and storage cost.

Aiming at the problem that the traditional loss improvement is finished by manual work and experience effect is poor, the method of the embodiment of the invention uses the loss root factor obtained by the association rule analysis algorithm for actual loss early warning improvement, and can feed back data input in the process to update the frequent item tree model.

According to the embodiment of the disclosure, after the initial loss discrimination rule is generated, screening processing is performed on the M initial loss discrimination rules to generate the target loss discrimination rule for the target station, for example, for the generated association rule, indexes such as a support degree, a confidence degree, a lifting degree and the like may be used for evaluation and screening. The threshold values of the support degree, the confidence degree and the lifting degree can be set to screen out the association rules which have important influences on package loss and breakage. The method specifically comprises the following steps:

first, the support, confidence and improvement of each initial loss discrimination rule are calculated.

The support is used for representing and calculating the frequency of each initial loss judgment rule in the rule set (including all initial loss judgment rules). Confidence, which characterizes how frequently (proportion of) each initial loss discrimination rule appears in the rule containing all its terms. The degree of promotion is used for representing the influence degree of each association rule on the occurrence probability of other association rules, and the degree of promotion refers to the comparison between one rule and the corresponding independent hypothesis thereof, and reflects the prediction capability of one rule.

And then, based on the support, confidence and lifting degree of each initial loss discrimination rule, screening M initial loss discrimination rules by using preset screening rules to generate target loss discrimination rules for target stations. For example, the rules with the support degree larger than the preset support degree threshold, the confidence degree larger than the preset confidence degree threshold and the lifting degree larger than the preset lifting degree threshold are screened out and used as final target loss judging rules.

According to the embodiment of the disclosure, the applicability of the rule in the field station can be improved and the accuracy of loss prediction can be improved by screening the initial loss discrimination rule based on the support, the confidence and the promotion.

Based on the package loss early warning processing method, the disclosure also provides a package loss early warning processing device. The device will be described in detail below in connection with fig. 7.

Fig. 7 schematically shows a block diagram of a package loss early-warning processing apparatus according to an embodiment of the present disclosure.

As shown in fig. 7, the apparatus 700 for processing the loss of packages according to this embodiment includes a reading module 701 and an early warning module 702.

The reading module 701 is configured to read, from a rule base, a target loss discrimination rule pre-constructed for a target station, where the target loss discrimination rule is constructed based on N pieces of historical loss discrimination data, the N pieces of historical loss discrimination data correspond to N historical packages passing through the target station, and the historical loss discrimination data is used to characterize loss attribution of the packages;

And the early warning module 702 is used for carrying out loss early warning processing on the target packages which flow to the target station by utilizing the target loss discrimination rule.

According to an embodiment of the disclosure, the target loss discrimination rule is used for characterizing at least one target attribution item that is easy to cause the package loss at the target field station, and the early warning module 702 includes an acquisition unit and an early warning unit.

According to an embodiment of the present disclosure, wherein:

Any of the plurality of modules of the reading module 701, the pre-warning module 702 may be combined in one module to be implemented, or any of the plurality of modules may be split into a plurality of modules, according to embodiments of the present disclosure. Or at least some of the functionality of one or more of the modules may be combined with, and implemented in, at least some of the functionality of other modules. According to embodiments of the present disclosure, at least one of the read module 701, the pre-alarm module 702 may be implemented at least in part as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or in hardware or firmware, such as any other reasonable way of integrating or packaging the circuit, or in any one of or a suitable combination of three of software, hardware, and firmware. Or at least one of the reading module 701, the pre-warning module 702 may be at least partly implemented as a computer program module which, when run, may perform the corresponding function.

As shown in fig. 8, an electronic device 800 according to an embodiment of the present disclosure includes a processor 801 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 802 or a program loaded from a storage section 808 into a Random Access Memory (RAM) 803. The processor 801 may include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or an associated chipset and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), or the like. The processor 801 may also include on-board memory for caching purposes. The processor 801 may include a single processing unit or multiple processing units for performing the different actions of the method flows according to embodiments of the disclosure.

In the RAM 803, various programs and data required for the operation of the electronic device 800 are stored. The processor 801, the ROM 802, and the RAM 803 are connected to each other by a bus 804. The processor 801 performs various operations of the method flow according to the embodiments of the present disclosure by executing programs in the ROM 802 and/or the RAM 803. Note that the program may be stored in one or more memories other than the ROM 802 and the RAM 803. The processor 801 may also perform various operations of the method flows according to embodiments of the present disclosure by executing programs stored in the one or more memories.

According to an embodiment of the present disclosure, the electronic device 800 may also include an input/output (I/O) interface 805, the input/output (I/O) interface 805 also being connected to the bus 804. The electronic device 800 may also include one or more of an input portion 806 including a keyboard, a mouse, etc., an output portion 807 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), etc., and a speaker, etc., a storage portion 808 including a hard disk, etc., and a communication portion 809 including a network interface card such as a LAN card, a modem, etc., connected to an input/output (I/O) interface 805. The communication section 809 performs communication processing via a network such as the internet. The drive 810 is also connected to an input/output (I/O) interface 805 as needed. A removable medium 811 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 810 as needed so that a computer program read out therefrom is mounted into the storage section 808 as needed.

The present disclosure also provides a computer-readable storage medium that may be included in the apparatus/device/system described in the above embodiments, or may exist alone without being assembled into the apparatus/device/system. The computer-readable storage medium carries one or more programs which, when executed, implement methods in accordance with embodiments of the present disclosure.

According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example, but is not limited to, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, the computer-readable storage medium may include ROM 802 and/or RAM 803 and/or one or more memories other than ROM 802 and RAM 803 described above.

Embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowcharts. When the computer program product runs in a computer system, the program code is used for enabling the computer system to realize the package loss pre-warning processing method provided by the embodiment of the disclosure.

The above-described functions defined in the system/apparatus of the embodiments of the present disclosure are performed when the computer program is executed by the processor 801. The systems, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.

In one embodiment, the computer program may be based on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted, distributed, and downloaded and installed in the form of a signal on a network medium, and/or from a removable medium 811 via a communication portion 809. The computer program may comprise program code that is transmitted using any appropriate network medium, including but not limited to wireless, wireline, etc., or any suitable combination of the preceding.

In such an embodiment, the computer program may be downloaded and installed from a network via the communication section 809, and/or installed from the removable media 811. The above-described functions defined in the system of the embodiments of the present disclosure are performed when the computer program is executed by the processor 801. The systems, devices, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.

According to embodiments of the present disclosure, program code for performing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, such computer programs may be implemented in high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. Programming languages include, but are not limited to, such as Java, c++, python, "C" or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Those skilled in the art will appreciate that the features recited in the various embodiments of the disclosure and/or in the claims may be provided in a variety of combinations and/or combinations, even if such combinations or combinations are not explicitly recited in the disclosure. In particular, the features recited in the various embodiments of the present disclosure and/or the claims may be variously combined and/or combined without departing from the spirit and teachings of the present disclosure. All such combinations and/or combinations fall within the scope of the present disclosure.

The embodiments of the present disclosure are described above. These examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the embodiments cannot be used advantageously in combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be made by those skilled in the art without departing from the scope of the disclosure, and such alternatives and modifications are intended to fall within the scope of the disclosure.

Claims

1. A package loss early warning processing method comprises the following steps:

and carrying out loss early warning processing on the target package flowing to the target station by utilizing the target loss discrimination rule.

2. The method of claim 1, further comprising:

Generating M initial loss judgment rules based on the N pieces of historical loss judgment data;

And screening the M initial loss discrimination rules to generate the target loss discrimination rules for the target field station.

3. The method of claim 2, wherein each of the historical loss tangent data includes a package identification and at least one attribution, generating M initial loss tangent rules based on the N historical loss tangent data includes:

Determining the frequency of each attribution item in L attribution items contained in the N pieces of historical loss judgment data;

determining S reference attribution items from the L attribution items based on a preset frequency threshold and the frequency of each attribution item;

And generating M initial loss judgment rules by using the N pieces of historical loss judgment data and the S pieces of reference attribution items.

4. A method according to claim 3, wherein generating M initial loss discrimination rules using the N pieces of historical loss discrimination data and the S reference attribution items comprises:

Determining at least one target attribution item matched with the historical loss judgment data from the S reference attribution items according to each piece of the historical loss judgment data;

and generating M initial loss judgment rules based on at least one target attribution item matched with each piece of historical loss judgment data.

5. A method according to claim 3, wherein generating M initial loss discrimination rules using the N pieces of historical loss discrimination data and the S reference attribution items comprises:

Based on the S reference attribution items, attribution item screening is carried out on the N pieces of historical loss judgment data respectively, and N pieces of basic construction data are generated;

Constructing a frequent pattern tree based on the N pieces of basic construction data, wherein child nodes or leaf nodes of the frequent pattern tree correspond to the reference attribution items, and subtrees of the frequent pattern tree correspond to the basic construction data;

6.A method according to claim 3, wherein:

The at least one attribution item comprises a first type attribution item, a second type attribution item and a third type attribution item, wherein the first type attribution item is used for representing basic reference information of a target parcel flowing to the target station, the second type attribution item is used for representing logistics operation information of the target parcel at the target station, and the third type attribution item is used for representing environment information of the target station.

7. A method according to claim 3, wherein:

each attribution item is one of a plurality of predefined factors, wherein the predefined factors at least comprise seasons, operation links, weather conditions, ambient temperature, ambient humidity, article types, responsible person labels and shipping merchant labels.

8. The method of claim 2, wherein filtering the M initial loss discrimination rules to generate a target loss discrimination rule for the target station comprises:

9. The method of claim 1, wherein the target loss discrimination rule is used to characterize at least one target attribution item that is likely to cause a package loss at the target station, and performing a loss early warning process on a target package flowing to the target station using the target loss discrimination rule comprises:

Acquiring basic reference information of the target package, logistics operation information of the target package at the target station and environment information of the target station;

10. The method according to claim 9, wherein:

the logistics operation information comprises at least one of an operation link and a responsible person tag, wherein the responsible person tag is obtained by inquiring a tag database based on a responsible person identifier;

11. A package loss early warning processing device, comprising:

the reading module is used for reading target loss judging rules pre-constructed for the target station from a rule base, wherein the target loss judging rules are constructed based on N pieces of historical loss judging data, the N pieces of historical loss judging data correspond to N historical packages passing through the target station, and the historical loss judging data are used for representing loss attribution of the packages;

and the early warning module is used for carrying out loss early warning processing on the target packages flowing to the target station by utilizing the target loss discrimination rule.

12. An electronic device, comprising:

One or more processors;

Storage means for storing one or more programs,

Wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method of any of claims 1-10.

13. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method according to any of claims 1-10.

14. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-10.