CN114037395A - Abnormal consignment data identification method and system, electronic equipment and storage medium - Google Patents
Abnormal consignment data identification method and system, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114037395A CN114037395A CN202210011893.4A CN202210011893A CN114037395A CN 114037395 A CN114037395 A CN 114037395A CN 202210011893 A CN202210011893 A CN 202210011893A CN 114037395 A CN114037395 A CN 114037395A
- Authority
- CN
- China
- Prior art keywords
- data
- consignment
- screening
- consignment data
- preset feature
- 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
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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides an abnormal consignment data identification method and system, electronic equipment and a storage medium, and relates to the technical field of intelligent detection. The method comprises the following steps: acquiring M consignment data; establishing N preset feature categories, wherein each preset feature category corresponds to a corresponding relation between two pieces of consignment data; analyzing at least one first corresponding relation between the ith consignment data and the jth consignment data; matching the first corresponding relation with a preset feature class, and classifying the ith consignment data and the jth consignment data into the matched preset feature class; and respectively screening all the consignment data in each preset characteristic category through corresponding screening rules, wherein the consignment data screened in each preset characteristic category are abnormal consignment data. The technical scheme of the invention can automatically identify the abnormal consignment data, and has strong operability, high accuracy and high identification efficiency.
Description
Technical Field
The invention relates to the technical field of intelligent detection, in particular to an abnormal consignment data identification method and system, electronic equipment and a storage medium.
Background
With the vigorous development of the postal express industry, cases of selling illegal transaction products in a mailing mode occur repeatedly, for example, counterfeit and shoddy products, false certificates or dangerous chemical products are sold through an e-commerce channel, and the damage is caused to the daily life and the life health of people. Related illegal persons sell the products to large-scale regions in an online transaction mode, and the selling range of the products usually has the conditions of cross-region, cross-province and the like.
In the existing abnormal delivery data identification process, manual analysis has a large proportion, for example, a delivery blacklist is locked according to receiving, sending and checking conditions, and the like, the identification method relying on manual analysis experience is poor in operability, low in accuracy and identification efficiency, still has security holes, and cannot meet the increasing requirements of the postal express industry.
Disclosure of Invention
The invention provides an abnormal consignment data identification method and system, electronic equipment and a storage medium, which can automatically identify abnormal consignment data, and have the advantages of strong operability, high accuracy and high identification efficiency.
In a first aspect, the present invention provides a method for identifying abnormal consignment data, which adopts the following technical scheme:
the abnormal consignment data identification method comprises the following steps:
acquiring M consignment data, wherein M is a positive integer greater than 1;
establishing N preset feature categories, wherein N is a positive integer greater than 1, and each preset feature category corresponds to a corresponding relation between two pieces of consignment data;
analyzing a first corresponding relation between the ith consignment data and the jth consignment data, wherein i is more than or equal to 1 and less than or equal to M, j is more than or equal to 1 and less than or equal to M, and j is not equal to i;
matching the first corresponding relation with a preset feature class, and classifying the ith consignment data and the jth consignment data into the matched preset feature class;
and respectively screening all the consignment data in each preset characteristic category through corresponding screening rules, wherein the consignment data screened in each preset characteristic category are abnormal consignment data.
Optionally, the establishing N preset feature categories includes:
acquiring a plurality of consignment behavior data in consignment data;
presetting a plurality of second corresponding relations between any two consignment behavior data in the two consignment data;
and selecting N types from the second corresponding relations as N preset characteristic categories for forwarding the data.
Optionally, the plurality of consignment behavior data includes at least: sending name, sending mobile phone number, sending address, receiving address and delivery address; the plurality of second correspondences at least include: the mobile phone number and the address of the same sending part are the same, the mobile phone number and the address of the different sending parts are the same, and the mobile phone number and the address of the different sending parts are the same;
the selecting N types of the second corresponding relationships from the plurality of types of the second corresponding relationships, wherein the N preset feature categories used as the consignment data specifically include: the method comprises the steps of selecting the same sending name and different sending mobile phone numbers, the same sending name and different sending addresses, the same sending mobile phone number and different sending names, the same sending mobile phone number and different sending addresses and the same sending mobile phone number and different sending addresses as first to fifth preset feature categories respectively.
Optionally, the screening, according to the corresponding screening rule, all the posting data in each preset feature category respectively includes:
all the consignment data in the first and second preset characteristic categories form a first data union;
all the consignment data in the third, fourth and fifth preset feature categories form a second data union;
and screening all the consignment data in the first data union set and the second data union set respectively through corresponding screening rules.
And screening all the consignment data in the first data union set and the second data union set respectively through corresponding screening rules.
Optionally, the screening, according to the corresponding screening rule, all the consignment data in the first data union set and the second data union set respectively includes:
screening all the consignment data in the first data union by a first screening rule, wherein the first screening rule comprises: screening out the same sending names, wherein the sending addresses are more than 2 first data; screening out the same receiving names and the same receiving mobile phone numbers from the first data, wherein the receiving addresses relate to second data of more than 3 provinces; screening out the third data with the same addressee mobile phone number from the second data, wherein the addressee names are more than 2 and the addressee addresses relate to more than 2 provinces;
screening all the consignment data in the second data union by a second screening rule, wherein the second screening rule comprises: screening out the same sending mobile phone number, wherein the sending address is more than 2 fourth data; screening out the same receiving names and the same receiving mobile phone numbers from the fourth data, wherein the receiving addresses relate to the fifth data of more than 3 provinces; and screening out sixth data with the same recipient mobile phone number, more than 2 recipient names and recipient addresses related to more than 2 provinces from the fifth data.
Optionally, the analyzing the first correspondence between the ith forwarding data and the jth forwarding data specifically includes:
and analyzing any two forwarding behavior data in the ith forwarding data and the jth forwarding data to obtain at least one first corresponding relation.
Optionally, the matching the first corresponding relationship with a preset feature class, and the classifying the ith forwarding data and the jth forwarding data into the matched preset feature class specifically includes:
matching each first corresponding relation with the first to Nth preset feature categories respectively;
and if the matching is successful, classifying the ith consignment data and the jth consignment data into the matched preset feature class.
In a second aspect, the present invention provides an abnormal consignment data identification system, which adopts the following technical solutions:
the exception forwarding data identification system comprises:
the data acquisition module is used for acquiring M consignment data, wherein M is a positive integer greater than 1;
the category establishing module is used for establishing N preset feature categories, wherein N is a positive integer greater than 1, and each preset feature category corresponds to a corresponding relation between two pieces of consignment data;
the analysis module is used for analyzing a first corresponding relation between the ith consignment data and the jth consignment data, i is more than or equal to 1 and less than or equal to M, j is more than or equal to 1 and less than or equal to M, and j is not equal to i;
the classification module is used for matching the first corresponding relation with a preset feature class and classifying the ith consignment data and the jth consignment data into the matched preset feature class;
and the screening module is used for screening all the consignment data in each preset characteristic category respectively according to the corresponding screening rule, and the consignment data screened out from each preset characteristic category are abnormal consignment data.
In a third aspect, the present invention provides an electronic device comprising:
a memory storing execution instructions; and
a processor executing execution instructions stored by the memory to cause the processor to perform the method of any of the above.
In a fourth aspect, the present invention provides a readable storage medium having stored therein executable instructions, which when executed by a processor, are configured to implement the method of any one of the above.
The invention provides an abnormal consignment data identification method and system, electronic equipment and a storage medium. Therefore, the abnormal consignment data identification method can automatically identify the abnormal consignment data, and has the advantages of strong operability, high accuracy and high identification efficiency.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a flowchart of an abnormal posted data identification method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of an abnormal consignment data identification system according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the technical features in the embodiments of the present invention may be combined with each other without conflict.
An embodiment of the present invention provides an abnormal consignment data identification method, and specifically, as shown in fig. 1, fig. 1 is a flowchart of the abnormal consignment data identification method provided in the embodiment of the present invention, where the abnormal consignment data identification method includes:
and step S1, M pieces of consignment data are obtained.
Wherein M is a positive integer greater than 1. One piece of delivery data refers to one piece of express bill information. In case of a large data volume of the express delivery service, M in step S1 is also generally a large value, and may be specifically selected according to the actual situation, such as the consignment data of a part of a specific area.
And step S2, establishing N preset feature categories.
Wherein N is a positive integer greater than 1, and each preset feature type corresponds to a corresponding relationship between two posted data.
Optionally, in the embodiment of the present invention, establishing N preset feature categories includes:
and a substep S21 of obtaining a plurality of consignment behavior data in the consignment data.
Optionally, the plurality of consignment behavior data includes at least: sending name, sending mobile phone number, sending address, receiving address and delivery address.
And a substep S22 of presetting a plurality of second correspondences between any two forwarding behavior data in the two forwarding data.
Optionally, repeated training is performed according to the correlation model, it is known that the sender name and the sender mobile phone number need to be focused on the abnormal delivery data, and in order to achieve both the recognition efficiency and the accuracy, the selecting of the plurality of second corresponding relationships in the embodiment of the present invention at least includes: the mobile phone number with the same sending name and different sending addresses, the mobile phone number with the same sending name and different sending names, the mobile phone number with the same sending address and different sending addresses, and the mobile phone number with the same sending address and different sending addresses. In addition, the multiple second correspondences in the embodiment of the present invention may further include the same recipient address and different delivery addresses. The above 6 second correspondences are the 6 most typical relations obtained by generalizing based on the whole original consignment data and combining the empirical characteristics of the abnormal consignment data.
And a substep S23 of selecting N types from the plurality of second correspondences as N preset feature categories for forwarding the data.
Optionally, N types of second correspondences are selected from the multiple second correspondences, and the N preset feature categories used as the forwarding data specifically include: the method comprises the steps of selecting the same sending name and different sending mobile phone numbers, the same sending name and different sending addresses, the same sending mobile phone number and different sending names, the same sending mobile phone number and different sending addresses and the same sending mobile phone number and different sending addresses as first to fifth preset feature categories respectively. Repeated training according to the relevant model shows that the second corresponding relation of 'same receiving address and different delivery addresses' has light contribution weight to abnormal delivery data identification, so that subsequent steps can be omitted, and the identification efficiency is improved.
Step S3, analyzing at least one first corresponding relationship between the ith consignment data and the jth consignment data.
Wherein i is more than or equal to 1 and less than or equal to M, j is more than or equal to 1 and less than or equal to M, and j is not equal to i, i can be taken as any value in the range from 1 to M, and j can be taken as any value except i between 1 and M. The above "at least one" is understood to be the analysis of all first correspondences between the two, which may be one or more, rather than selecting at least one from them for analysis. At least one first corresponding relation exists between each piece of the consignment data and every other piece of the consignment data, namely, all first corresponding relations between the ith consignment data and the consignment data of which j takes any value which is not i between 1-M are analyzed.
Optionally, when the plurality of forwarding behavior data in the forwarding data are obtained in step S2, analyzing at least one first correspondence between the ith forwarding data and the jth forwarding data specifically includes:
and analyzing any two forwarding behavior data in the ith forwarding data and the jth forwarding data to obtain at least one first corresponding relation. For example, the first corresponding relationship "the same mail name and different mail mobile phone number" is obtained by analyzing the mail name and the mail mobile phone number in the ith mail data and the jth mail data, the second corresponding relationship "the same mail name and different mail address" is obtained by analyzing the mail name and the mail address in the ith mail data and the jth mail data, and the third corresponding relationship "the different mail mobile phone number and different mail address" is obtained by analyzing the mail mobile phone number and the mail address in the ith mail data and the jth mail data.
And step S4, matching the first corresponding relation with a preset feature class, and classifying the ith consignment data and the jth consignment data into the matched preset feature class.
Optionally, in the embodiment of the present invention, matching the first corresponding relationship with a preset feature class, and classifying the ith forwarding data and the jth forwarding data into the matched preset feature class specifically includes:
and step S41, matching each first corresponding relation with the first to Nth preset feature categories respectively.
Taking the 5 predetermined feature classes described in step S2 and the three first corresponding relationships described in step S3 as examples, the first corresponding relationship is respectively matched with the first to fifth predetermined feature classes, the second first corresponding relationship is respectively matched with the first to fifth predetermined feature classes, and the third first corresponding relationship is respectively matched with the first to fifth predetermined feature classes. If any of the above matches is successful, then sub-step S42 is performed.
If the first corresponding relationship is successfully matched with the first preset feature class, performing substep S42; if the second first corresponding relationship is successfully matched with the second preset feature type, performing the substep S42 again; and if the third first corresponding relation is unsuccessfully matched with each preset characteristic category, subsequent operation is not needed.
And step S42, classifying the ith consignment data and the jth consignment data into the matched preset feature categories.
For example, if the first correspondence is successfully matched with the first preset feature class, classifying the ith forwarding data and the jth forwarding data into the first preset feature class; and if the second first corresponding relation is successfully matched with the second preset feature class, classifying the ith consignment data and the jth consignment data into the second preset feature class.
It should be noted that there may not be a first correspondence between each piece of forwarding data and any other piece of forwarding data that can be successfully matched with the preset feature class, and there may also be one or more first correspondences that can be successfully matched with the preset feature class, so that a piece of forwarding data may not be classified, may also be classified into one preset feature class, or may be classified into multiple preset feature classes. For the forwarded data that cannot be classified, it can be directly filtered out in step S4.
One piece of consignment data can be matched with a plurality of characteristic categories at the same time, and the consignment data matched with one category has the correlation which is consistent with the characteristics of the category with at least one piece of consignment data under the category. Posted data that failed to match all six feature classes are filtered out.
And step S5, respectively screening all the consignment data in each preset characteristic category through corresponding screening rules, wherein the consignment data screened in each preset characteristic category are abnormal consignment data.
In step S5, all the forwarding data in each preset feature class may be sequentially screened according to the corresponding screening rule, or the forwarding data in at least two adjacent preset feature classes may be merged and then screened according to the corresponding screening rule, which may appropriately simplify and improve the screening efficiency.
Optionally, taking the 5 preset feature categories described in step S2 as an example, where the first and second preset feature categories are similar, and the third, fourth, and fifth preset feature categories are similar, then the screening of all the posting data in each preset feature category by the corresponding screening rule in the embodiment of the present invention specifically includes:
substep S51 forms all the posted data in the first and second predetermined characteristic categories into a first data union.
And a substep S52 of forming a second union of data from all the posted data in the third, fourth and fifth predetermined characteristic categories.
And screening all the consignment data in the first data union set and the second data union set respectively through corresponding screening rules.
And a substep S53 of screening all the forwarded data in the first data union and the second data union respectively according to the corresponding screening rules.
Optionally, the screening, by using the corresponding screening rule, all the consignment data in the first data union set and the second data union set respectively includes:
screening all the consignment data in the first data union through a first screening rule, wherein the first screening rule comprises the following steps: screening out the same sending names, wherein the sending addresses are more than 2 first data; screening out the same receiving names and the same receiving mobile phone numbers from the first data, wherein the receiving addresses relate to second data of more than 3 provinces; screening out the third data with the same addressee mobile phone number from the second data, wherein the addressee names are more than 2 and the addressee addresses relate to more than 2 provinces;
screening all the consignment data in the second data union through a second screening rule, wherein the second screening rule comprises the following steps: screening out the same sending mobile phone number, wherein the sending address is more than 2 fourth data; screening out the same receiving names and the same receiving mobile phone numbers from the fourth data, wherein the receiving addresses relate to the fifth data of more than 3 provinces; and screening out sixth data with the same recipient mobile phone number, more than 2 recipient names and recipient addresses related to more than 2 provinces from the fifth data.
Through the first screening rule or the second screening rule, abnormal consignment data can be located step by step, the fact that the selected first screening rule and the second screening rule can achieve high hit probability through fewer screening steps is found in the training process of the relevant model, each screening step ensures that normal consignment data are filtered as much as possible, and therefore the purpose of efficient screening is achieved.
After all the posting data in the first data union set and the second data union set are screened, corresponding abnormal posting data lists can be respectively generated, each abnormal posting data list has corresponding characteristics, so that subsequent analysis is facilitated, and if the two posting data lists are combined, the characteristics of the abnormal posting data lists can be covered to a certain extent.
It should be noted that, if the latter step in the above steps is not based on the result of the former step, the sequence of the former step and the latter step may be determined according to actual needs, for example, the specific execution sequence of step S1 and step S2 may be determined according to actual needs, a preset feature type may be established in advance, and then the forwarding data is collected, or the forwarding data may be collected first and then the preset feature type is established.
In the method for identifying the abnormal consignment data, M consignment data are obtained firstly, N preset feature classes are established, each preset feature class corresponds to one corresponding relation between two consignment data, the first corresponding relation between the ith consignment data and the jth consignment data is analyzed, the first corresponding relation is matched with the preset feature classes, the ith consignment data and the jth consignment data are classified into the matched preset feature classes, all the consignment data in each preset feature class are screened respectively according to corresponding screening rules, and the consignment data screened from each preset feature class are the abnormal consignment data. Therefore, the abnormal consignment data identification method can automatically identify the abnormal consignment data (without manual intervention), and has strong operability, high accuracy and high identification efficiency.
In addition, an embodiment of the present invention further provides an abnormal consignment data identification system, and specifically, as shown in fig. 2, fig. 2 is a schematic diagram of the abnormal consignment data identification system provided in the embodiment of the present invention, where the abnormal consignment data identification system includes:
the data acquisition module 10 is configured to acquire M posted data, where M is a positive integer greater than 1;
the category establishing module 20 is configured to establish N preset feature categories, where N is a positive integer greater than 1, and each preset feature category corresponds to a corresponding relationship between two pieces of forwarding data;
an analysis module 30, configured to analyze at least one first correspondence between the ith forwarding data and the jth forwarding data, where i is greater than or equal to 1 and less than or equal to M, j is greater than or equal to 1 and less than or equal to M, and j is not equal to i;
the classification module 40 is configured to match the first correspondence with a preset feature class, and classify the ith forwarding data and the jth forwarding data into the matched preset feature class;
the screening module 50 is configured to screen all the posting data in each preset feature category according to the corresponding screening rule, where the posting data screened in each preset feature category are all abnormal posting data.
The classification module 40 may set corresponding classification sub-modules according to the number of the preset feature classes, where each classification sub-module is configured to match the first corresponding relationship with the corresponding preset feature class, and when the first corresponding relationship is matched with the corresponding preset feature class, classify the ith posting data and the jth posting data into the preset feature class.
The screening module 50 may also be provided with a plurality of screening sub-modules, each screening sub-module corresponds to a specific screening rule, and all the posting data in the corresponding preset feature categories are screened according to the screening rule, and the screened posting data are all abnormal posting data.
It should be noted that details of each step of the method for identifying exception forwarding data in the embodiment of the present invention are all applicable to the corresponding module, and are not described herein again.
In addition, an embodiment of the present invention further provides an electronic device, where the electronic device includes:
a memory storing execution instructions; and
a processor executing execution instructions stored by the memory to cause the processor to perform the method of any of the above.
The embodiment of the invention also provides a readable storage medium, wherein the readable storage medium stores an execution instruction, and the execution instruction is used for realizing the method of any one of the above when being executed by a processor.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. An abnormal consignment data identification method, comprising:
acquiring M consignment data, wherein M is a positive integer greater than 1;
establishing N preset feature categories, wherein N is a positive integer greater than 1, and each preset feature category corresponds to a corresponding relation between two pieces of consignment data;
analyzing at least one first corresponding relation between the ith consignment data and the jth consignment data, wherein i is more than or equal to 1 and less than or equal to M, j is more than or equal to 1 and less than or equal to M, and j is not equal to i;
matching the first corresponding relation with a preset feature class, and classifying the ith consignment data and the jth consignment data into the matched preset feature class;
and respectively screening all the consignment data in each preset characteristic category through corresponding screening rules, wherein the consignment data screened in each preset characteristic category are abnormal consignment data.
2. The method of claim 1, wherein the establishing N predetermined characteristic classes comprises:
acquiring a plurality of consignment behavior data in consignment data;
presetting a plurality of second corresponding relations between any two consignment behavior data in the two consignment data;
and selecting N types from the second corresponding relations as N preset characteristic categories for forwarding the data.
3. The abnormal consignment data identification method according to claim 2, wherein said plurality of consignment behavior data includes at least: sending name, sending mobile phone number, sending address, receiving address and delivery address; the plurality of second correspondences at least include: the mobile phone number and the address of the same sending part are the same, the mobile phone number and the address of the different sending parts are the same, and the mobile phone number and the address of the different sending parts are the same;
the selecting N types of the second corresponding relationships from the plurality of types of the second corresponding relationships, wherein the N preset feature categories used as the consignment data specifically include: the method comprises the steps of selecting the same sending name and different sending mobile phone numbers, the same sending name and different sending addresses, the same sending mobile phone number and different sending names, the same sending mobile phone number and different sending addresses and the same sending mobile phone number and different sending addresses as first to fifth preset feature categories respectively.
4. The abnormal consignment data identification method according to claim 3, wherein the step of screening all the consignment data in each preset feature category according to the corresponding screening rule specifically comprises:
all the consignment data in the first and second preset characteristic categories form a first data union;
all the consignment data in the third, fourth and fifth preset feature categories form a second data union;
and screening all the consignment data in the first data union set and the second data union set respectively through corresponding screening rules.
5. The abnormal consignment data identification method according to claim 4, wherein the screening all the consignment data in the first data union set and the second data union set respectively by the corresponding screening rules specifically comprises:
screening all the consignment data in the first data union by a first screening rule, wherein the first screening rule comprises: screening out the same sending names, wherein the sending addresses are more than 2 first data; screening out the same receiving names and the same receiving mobile phone numbers from the first data, wherein the receiving addresses relate to second data of more than 3 provinces; screening out the third data with the same addressee mobile phone number from the second data, wherein the addressee names are more than 2 and the addressee addresses relate to more than 2 provinces;
screening all the consignment data in the second data union by a second screening rule, wherein the second screening rule comprises: screening out the same sending mobile phone number, wherein the sending address is more than 2 fourth data; screening out the same receiving names and the same receiving mobile phone numbers from the fourth data, wherein the receiving addresses relate to the fifth data of more than 3 provinces; and screening out sixth data with the same recipient mobile phone number, more than 2 recipient names and recipient addresses related to more than 2 provinces from the fifth data.
6. The method of claim 2, wherein analyzing at least one first correspondence between the ith forwarding data and the jth forwarding data specifically comprises:
and analyzing any two forwarding behavior data in the ith forwarding data and the jth forwarding data to obtain at least one first corresponding relation.
7. The abnormal consignment data identification method according to claim 6, wherein said matching the first correspondence with a predetermined feature class, and said classifying the ith consignment data and the jth consignment data into the matched predetermined feature class specifically comprises:
matching each first corresponding relation with the first to Nth preset feature categories respectively;
and if the matching is successful, classifying the ith consignment data and the jth consignment data into the matched preset feature class.
8. An exception forwarding data identification system, comprising:
the data acquisition module is used for acquiring M consignment data, wherein M is a positive integer greater than 1;
the category establishing module is used for establishing N preset feature categories, wherein N is a positive integer greater than 1, and each preset feature category corresponds to a corresponding relation between two pieces of consignment data;
the analysis module is used for analyzing at least one first corresponding relation between the ith consignment data and the jth consignment data, i is more than or equal to 1 and less than or equal to M, j is more than or equal to 1 and less than or equal to M, and j is not equal to i;
the classification module is used for matching the first corresponding relation with a preset feature class and classifying the ith consignment data and the jth consignment data into the matched preset feature class;
and the screening module is used for screening all the consignment data in each preset characteristic category respectively according to the corresponding screening rules, and the consignment data screened out in each preset characteristic category are abnormal consignment data.
9. An electronic device, comprising:
a memory storing execution instructions; and
a processor executing execution instructions stored by the memory to cause the processor to perform the method of any of claims 1 to 7.
10. A readable storage medium having stored therein execution instructions, which when executed by a processor, are configured to implement the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210011893.4A CN114037395A (en) | 2022-01-07 | 2022-01-07 | Abnormal consignment data identification method and system, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210011893.4A CN114037395A (en) | 2022-01-07 | 2022-01-07 | Abnormal consignment data identification method and system, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114037395A true CN114037395A (en) | 2022-02-11 |
Family
ID=80147311
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210011893.4A Pending CN114037395A (en) | 2022-01-07 | 2022-01-07 | Abnormal consignment data identification method and system, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114037395A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115544247A (en) * | 2022-08-17 | 2022-12-30 | 国家邮政局邮政业安全中心 | Information processing method, information processing device, computer equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105868952A (en) * | 2016-05-24 | 2016-08-17 | 南通睿科信息技术有限公司 | Consignment logistics management system |
| CN111325495A (en) * | 2018-12-17 | 2020-06-23 | 顺丰科技有限公司 | Abnormal part classification method and system |
| CN113449112A (en) * | 2020-03-24 | 2021-09-28 | 顺丰科技有限公司 | Abnormal consignment behavior identification method and device, computer equipment and storage medium |
| US20210349862A1 (en) * | 2020-05-08 | 2021-11-11 | Delta Electronics, Inc. | Data analysis system and data analysis method |
-
2022
- 2022-01-07 CN CN202210011893.4A patent/CN114037395A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105868952A (en) * | 2016-05-24 | 2016-08-17 | 南通睿科信息技术有限公司 | Consignment logistics management system |
| CN111325495A (en) * | 2018-12-17 | 2020-06-23 | 顺丰科技有限公司 | Abnormal part classification method and system |
| CN113449112A (en) * | 2020-03-24 | 2021-09-28 | 顺丰科技有限公司 | Abnormal consignment behavior identification method and device, computer equipment and storage medium |
| US20210349862A1 (en) * | 2020-05-08 | 2021-11-11 | Delta Electronics, Inc. | Data analysis system and data analysis method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115544247A (en) * | 2022-08-17 | 2022-12-30 | 国家邮政局邮政业安全中心 | Information processing method, information processing device, computer equipment and storage medium |
| CN115544247B (en) * | 2022-08-17 | 2023-08-04 | 国家邮政局邮政业安全中心 | Information processing method, apparatus, computer device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109255499B (en) | Complaint and complaint case processing method, device and equipment | |
| CN108667854A (en) | Network hole detection method and device, network hole automated pubilication system | |
| CN108833186A (en) | A kind of network attack prediction technique and device | |
| CN102420723A (en) | Anomaly detection method for various kinds of intrusion | |
| US20200210459A1 (en) | Method and apparatus for classifying samples | |
| CN112733146B (en) | Penetration testing method, device and equipment based on machine learning and storage medium | |
| CN116383742B (en) | Rule chain setting processing method, system and medium based on feature classification | |
| CN108197474A (en) | The classification of mobile terminal application and detection method | |
| US7236612B2 (en) | Method of video coding images comprising address information | |
| CN110995745A (en) | Method and device for separating and identifying illegal machine card of Internet of things | |
| CN113487241A (en) | Method, device, equipment and storage medium for classifying enterprise environment-friendly credit grades | |
| CN114037395A (en) | Abnormal consignment data identification method and system, electronic equipment and storage medium | |
| CN113612645A (en) | Internet of things data processing method and system | |
| CN113313095A (en) | User information matching method and device, computer equipment and storage medium | |
| CN116206093B (en) | Electric meter data acquisition method and system based on bitmap and readable storage medium | |
| CN108921433B (en) | Risk quantitative analysis system based on business continuity | |
| CN115688107A (en) | Fraud-related APP detection system and method | |
| CN114511403A (en) | Method and device for generating supervision report, electronic equipment and storage medium | |
| CN114189585A (en) | Crank call abnormity detection method and device and computing equipment | |
| CN111784182A (en) | Asset information processing method and device | |
| CN113239126A (en) | Business activity information standardization scheme based on BOR method | |
| CN113435842A (en) | Business process processing method and computer equipment | |
| CN108055661B (en) | Telephone number blacklist establishing method and device based on communication network | |
| CN108235324B (en) | Short message template testing method and server | |
| Piancó et al. | Code change history and software vulnerabilities |
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 |