CN111104593A - Logistics information platform, logistics service recommendation method and logistics service coordination method - Google Patents

Logistics information platform, logistics service recommendation method and logistics service coordination method Download PDF

Info

Publication number
CN111104593A
CN111104593A CN201911271590.0A CN201911271590A CN111104593A CN 111104593 A CN111104593 A CN 111104593A CN 201911271590 A CN201911271590 A CN 201911271590A CN 111104593 A CN111104593 A CN 111104593A
Authority
CN
China
Prior art keywords
user
logistics
recommendation
information
logistics service
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.)
Withdrawn
Application number
CN201911271590.0A
Other languages
Chinese (zh)
Inventor
孙雁飞
吴永清
亓晋
许斌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing University of Posts and Telecommunications
Original Assignee
Nanjing University of Posts and Telecommunications
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nanjing University of Posts and Telecommunications filed Critical Nanjing University of Posts and Telecommunications
Priority to CN201911271590.0A priority Critical patent/CN111104593A/en
Publication of CN111104593A publication Critical patent/CN111104593A/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9536—Search customisation based on social or collaborative filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/083—Shipping
    • G06Q10/0838—Historical data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0254—Targeted advertisements based on statistics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0255—Targeted advertisements based on user history
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0261—Targeted advertisements based on user location

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Probability & Statistics with Applications (AREA)
  • Human Resources & Organizations (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention provides a logistics information platform, a logistics service recommendation method and a logistics service coordination method, wherein the logistics information platform comprises the following steps: an application layer: the system has a basic query function, a registration function and a logistics service recommendation function; core layer: according to the user state, different recommendation algorithms are adopted to recommend the logistics service to the user; and (3) a data layer: and carrying out data acquisition on the user behavior information and the user basic information. Meanwhile, a logistics service recommendation method and a logistics service coordination method are also provided. Compared with the prior art, the logistics service recommendation function is arranged on the logistics information platform, so that the recommendation efficiency is improved, the information safety is ensured, the quality of the logistics service recommendation result is improved, and the low-delay logistics service recommendation is realized.

Description

Logistics information platform, logistics service recommendation method and logistics service coordination method
Technical Field
The invention relates to a logistics information platform, a logistics service recommendation method and a logistics service coordination method, and belongs to the field of logistics.
Background
With the rapid development of domestic economy and electronic commerce, the demand of the domestic market for logistics distribution is increasing. The logistics distribution refers to logistics activities of moving articles to designated places on time through operations such as distribution, sorting and the like according to requirements of customers. At present, the domestic logistics distribution mode can be divided into four modes, including self-operation distribution, common distribution, inter-use distribution, third-party distribution and the like. The third-party distribution mode is a leading choice for the distribution of articles by the broad distribution demanders including network merchants and industrial and commercial enterprises because of its advantages of strong professional skill and low price. However, due to the large number of service schemes of the third-party logistics enterprise, customers with personalized requirements have poor understanding of the quality of the numerous delivery service schemes, and cannot quickly select a service scheme suitable for the customers. Therefore, a problem of "information overload" arises, and an effective method for solving this problem is personalized recommendation.
The personalized recommendation refers to a process of calculating an object of interest of a user according to similarity between the user and a service through relevant knowledge of data mining based on behavior data left by the user in a logistics information platform, and accurately recommending the service meeting personalized requirements of the user and having service quality guarantee to the user. However, the prior art has the following defects: firstly, the logistics service recommendation mode based on a public information platform has the problems of insufficient information authenticity and long recommendation response time; secondly, the recommendation method based on the collaborative filtering mechanism has the problems of increased calculation amount and low recommendation efficiency when the data volume is large; finally, the existing recommendation scheme only focuses on the logistics service which is already evaluated by the user, and cannot recommend services which are not evaluated by the user, so that the problem of narrow recommendation plane exists.
In view of the above, it is necessary to provide a logistics information platform, a logistics service recommendation method, and a logistics service coordination method to solve the above problems.
Disclosure of Invention
The invention aims to provide a logistics information platform based on a block chain and combined with edge computing nodes and a logistics service recommendation method based on the platform, and simultaneously provides a cloud-coordinated logistics service coordination method for realizing near recommendation so as to realize low-delay recommendation.
In order to achieve the above object, the present invention provides a logistics information platform, comprising:
an application layer: the system has a basic query function, a registration function and a logistics service recommendation function;
core layer: according to the user state, different recommendation algorithms are adopted to recommend the logistics service to the user;
and (3) a data layer: and carrying out data acquisition on the user behavior information and the user basic information.
Optionally, the logistics service recommendation function completes the logistics service screening at the core layer based on the algorithm through the user behavior information and the user basic information, and completes the display and recommendation at the application layer, so that the user can select and evaluate the recommendation result.
Optionally, after data acquisition is completed, the data layer completes preliminary processing of data through data cleaning, and encrypts the data based on distributed storage of the block chain, so as to store the cleaned data into the block chain nodes and persistently store the data.
In order to achieve the above object, the present invention further provides a method for recommending a logistics service, which mainly comprises the following steps:
a1, a user accesses a cloud server to obtain an optimal edge computing node;
step A2, establishing connection between a user and an edge computing node, and starting to access a logistics information platform;
a3, the logistics information platform judges the user identity and carries out the related information inquiry work;
a4, adopting different recommendation algorithms to recommend logistics services to a user according to the user state;
step A5, recording user browsing information and order information;
and step A6, the user quits the logistics information platform, the edge computing node releases resources, and the cloud server updates the edge computing node information.
Optionally, the recommendation algorithm mainly includes:
A. for new users, adopting a recommendation algorithm based on demographics and combining default recommendations;
B. for users with few historical orders and browsing information, a recommendation algorithm based on service similarity is adopted;
C. for users with more historical orders and browsing information, adopting a collaborative filtering recommendation algorithm based on service similarity according to preference values of the users;
D. for the unregistered user, the logistics service which is used frequently and is close to the geographical position of the user is selected as a recommendation result.
Optionally, the specific algorithm in a includes:
s1, determining occupation, address and the like of the user according to the basic information of the user;
s2, screening out users with the same occupation, address and other information as the current user, and extracting the logistics services selected by the users to form a logistics service set to be recommended;
s3, counting the logistics service topn with the most selected times as default recommendation according to all current order information;
s4, solving an intersection of the default recommendation set and the logistics service set to be recommended to obtain a recommendation set, and if the number of logistics services in the recommendation set can meet the recommendation number requirement, recommending in the mode; and if the number of the logistics services cannot meet the requirement of the recommended number, calculating a difference set between the default recommended set and the recommended set, and filling insufficient items with the logistics services in the difference set to form a final recommended set for recommendation.
Optionally, the recommendation algorithm based on the service similarity is as follows:
Figure BDA0002314353260000031
wherein S isabRepresenting the degree of similarity between the logistics services a, b after normalization, aiAnd biRespectively representing the scores of the logistics services a and b on the attribute i;
the calculation formula of the preference value of the user is as follows:
Figure BDA0002314353260000032
wherein, PijIndicating the preference value of user i for the logistics service j,
Figure BDA0002314353260000033
the value k of the credit for the user i on the feature k of the logistics service j is {1,2, …, m }, wkAnd expressing the weight corresponding to the characteristic k, wherein the scoring value is determined by the satisfaction degree of each item of information of the user on the characteristic.
Optionally, the collaborative filtering recommendation algorithm simplifies the data by using a Singular Value Decomposition (SVD) method.
In order to achieve the above object, the present invention further provides a method for coordinating logistics services, which is used for implementing low-delay logistics service recommendation, and mainly comprises the following steps:
step B1, after the user accesses the cloud server, each edge computing node registers to the cloud server, and starts a heartbeat subprocess for reporting node state information to the cloud server;
and step B2, after the request information of the user is sent to the cloud server, the cloud server selects the optimal edge computing node by adopting a proper comparison rule according to the current resources of each edge computing node and the relative positions of the user and each edge computing node.
And step B3, the cloud server sends the screened ip address of the optimal edge computing node to the user, and the user establishes connection with the edge computing node.
And step B4, after the connection between the user and the edge computing node is successfully established, the user can use the functions provided by the logistics information platform.
Optionally, the registered information includes: the geographical location of the edge compute node, the ip address of the edge compute node, the state of the edge compute node, and the resources of the edge compute node.
The invention has the beneficial effects that: according to the invention, the logistics service recommendation function is arranged on the logistics information platform, so that the recommendation efficiency is improved, the information safety is ensured, the quality of the logistics service recommendation result is improved, and the low-delay logistics service recommendation is realized.
Drawings
Fig. 1 is a structural diagram of a logistics information platform of the present invention.
Fig. 2 is a flowchart of a logistics service recommendation method of the present invention.
Fig. 3 is a coordination structure diagram of the logistics service coordination method of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
As shown in fig. 1 to 3, the present invention discloses a logistics information platform, a logistics service recommendation method, and a logistics service coordination method.
As shown in fig. 1, the structure of the logistics information platform of the invention mainly comprises: an application layer, a core layer, and a data layer. Wherein, the application layer: the system has a basic query function, a registration function and a logistics service recommendation function; core layer: according to the user state, different recommendation algorithms are adopted to recommend the logistics service to the user; and (3) a data layer: and carrying out data acquisition on the user behavior information and the user basic information.
The functions of the application layer, core layer, and data layer are described in detail below.
An application layer: the application layer mainly provides friendly user operation and display pages and has a basic query function, a registration function and a logistics service recommendation function. The basic query function can query information such as user history information, basic information and the like, including information of each logistics service used by the user, evaluation information of the user and the like. The registration function can enable a user to complete registration, modify basic information and the like through an operation interface provided by the application layer. The logistics service recommendation function completes logistics service screening in the core layer based on an algorithm through the user behavior information and the user basic information, and completes display and recommendation in the application layer, so that a user can select and evaluate recommendation results.
Core layer: the core layer has the main function of selecting the most appropriate recommendation algorithm according to the basic information, the historical order information, the browsing information and other information of the user so as to recommend high-quality logistics service to the user.
And (3) a data layer: the data layer is a basic layer for providing data support for processing and analyzing upper-layer data. After data acquisition is completed, the data layer completes primary processing of data through data cleaning, and encrypts the data based on distributed storage of the block chain so as to store the cleaned data into the block chain nodes.
The data acquisition mainly acquires information such as basic information during user registration, state information of the user using the logistics service, browsing information of the user on various logistics services and the like in real time, and provides data support for generating a user portrait. Meanwhile, the recommendation effect of the recommendation algorithm can be further improved by the diversity of data acquisition.
The data cleaning is mainly to carry out preliminary processing on data, screen acquired data according to a certain rule according to an input data format adopted by a recommendation algorithm, filter abnormal and incomplete data which do not meet the matching rule, and finally save a data formatting process before the recommendation algorithm is executed so as to accelerate the recommendation speed.
Distributed storage based on the block chain mainly saves the cleaned data into block chain nodes and stores the data persistently. The data is finally stored in the form of blocks, and the blocks need to be established based on a consensus algorithm to achieve consensus among the blockchain nodes deployed on different edge computing nodes. The consensus mechanism can realize the synchronization of data among nodes while ensuring the reliability of the data, so that each node stores complete data. The block chain adopts an asymmetric encryption algorithm to encrypt the stored data, so that the purpose of preventing user information from being leaked is achieved.
As shown in fig. 2, based on the logistics information platform provided by the invention, the invention provides a logistics service recommendation method, which mainly includes the following steps:
a1, a user accesses a cloud server to obtain an optimal edge computing node;
step A2, establishing connection between a user and an edge computing node, and starting to access a logistics information platform;
a3, the logistics information platform judges the user identity and carries out the related information inquiry work;
a4, adopting different recommendation algorithms to recommend logistics services to a user according to the user state;
step A5, recording user browsing information and order information;
and step A6, the user quits the logistics information platform, the edge computing node releases resources, and the cloud server updates the edge computing node information.
In step a4, the specific recommendation algorithm is as follows:
A. for new users, a recommendation algorithm based on demographics is adopted and combined with default recommendations, and the specific algorithm comprises the following steps:
s1, determining occupation, address and the like of the user according to the basic information of the user;
s2, screening out users with the same occupation, address and other information as the current user, and extracting the logistics services selected by the users to form a logistics service set to be recommended;
s3, counting the logistics service topn with the most selected times as default recommendation according to all current order information;
s4, solving an intersection of the default recommendation set and the logistics service set to be recommended to obtain a recommendation set, and if the number of logistics services in the recommendation set can meet the recommendation number requirement, recommending in the mode; and if the number of the logistics services cannot meet the requirement of the recommended number, calculating a difference set between the default recommended set and the recommended set, and filling insufficient items with the logistics services in the difference set to form a final recommended set for recommendation.
B. For users with few historical orders and browsing information, a recommendation algorithm based on service similarity is adopted, and the specific algorithm comprises the following steps:
s1, extracting some important attributes of the logistics service, wherein the extracting mode of the attributes can be determined according to the attention degree of the user, the important logistics service attributes are finally selected by counting the screening label options selected by the user when selecting the logistics service in the browsing records of the user, and performing descending sorting according to the selected times of the labels;
s2, the score values of the physical distribution service attributes of different physical distribution services can be determined jointly by the frequency of selecting the labels corresponding to the service attributes and extracting the user' S evaluation of the attributes through semantic analysis and other means;
s3, calculating the similarity of different logistics services on the logistics service attributes, normalizing the similarity, and selecting the top n with the highest similarity with the logistics services selected by the current user for recommendation
Figure BDA0002314353260000071
Wherein S isabRepresenting the degree of similarity between the logistics services a, b after normalization, aiAnd biRespectively representing the values of the scores of the logistics services a and b on the attribute i.
C. For a user with more historical orders and browsing information, adopting a collaborative filtering recommendation algorithm based on service similarity according to the preference value of the user, wherein the specific algorithm comprises the following steps:
s1, calculating the preference value of the user to the logistics service according to the historical order information and the browsing information of the user, distributing different weights to different features by adopting a grade grading mode, wherein each feature corresponds to different scores according to the state meeting the conditions, and the calculation formula of the preference value of the user is as follows:
Figure BDA0002314353260000072
wherein, PijIndicating the preference value of user i for the logistics service j,
Figure BDA0002314353260000073
the value k of the credit for the user i on the feature k of the logistics service j is {1,2, …, m }, wkRepresenting the weight corresponding to feature k. The scoring value is determined by the satisfaction degree of each item of information of the user on the characteristics;
s2 calculating similarity between services
Figure BDA0002314353260000081
Simjj′＝1/(1+djj′)，
Wherein d isjj′Denotes the Euclidean distance, Sim, between services j and jjj′Representing the similarity of service j and j';
s3, in order to solve the problems of too large data volume and sparse preference matrix, a Singular Value Decomposition (SVD) method can be adopted to simplify data so as to remove noise and redundancy, reduce the calculation amount and improve the recommendation speed and quality;
s4, after the data are simplified by adopting SVD, obtaining a recommendation result based on a collaborative filtering recommendation algorithm through a similarity calculation formula among the services;
s5, in order to solve the problem that the recommendation result of the single collaborative filtering recommendation algorithm is too narrow, a hybrid recommendation algorithm is adopted, and the hybrid recommendation algorithm is to perform weighted reordering on recommendation results obtained by the algorithms through the collaborative filtering recommendation algorithm based on the service similarity, the recommendation algorithm based on the service similarity and the recommendation algorithm based on the demographics to obtain a final hybrid recommendation result.
D. For the unregistered user, the logistics service which is used frequently and is close to the geographical position of the user is selected as a recommendation result.
In order to realize low-delay logistics service recommendation, the invention provides a logistics service coordination method, wherein the logistics service recommendation function is completed at an edge computing node, so that the edge node is actually accessed by a user, and the load inclination problem is caused by unreasonable allocation of user requests, so that the function of nearby computing cannot be achieved, and the efficiency of the whole logistics information platform is reduced. Therefore, the logistics service coordination method provided by the invention is based on a cloud coordination structure, realizes nearby calculation and load balancing, and achieves the effect of low-delay recommendation, and comprises the following specific steps:
and step B1, after the user accesses the cloud server, each edge computing node registers to the cloud server, and starts a heartbeat subprocess for reporting the node state information to the cloud server. The registered information includes: the geographical location of the edge compute node, the ip address of the edge compute node, the state of the edge compute node, and the resources of the edge compute node.
And step B2, after the request information of the user is sent to the cloud server, the cloud server selects the optimal edge computing node by adopting a proper comparison rule according to the current resources of each edge computing node and the relative positions of the user and each edge computing node. The cloud server stores information sent when the edge computing node is registered, and meanwhile, heartbeat information can be periodically detected to judge the survival state of the edge computing node.
And step B3, the cloud server sends the screened ip address of the optimal edge computing node to the user, and the user establishes connection with the edge computing node. If the connection is established successfully, sending connection success information to the cloud server, updating resource information of the edge computing node by the cloud server, and storing the request and the occupied resource information in a specific data structure; if the connection is over time, that is, the connection fails, the user sends connection failure information to the cloud server, the cloud server deletes the edge computing node information, and the step B2 is performed again to allocate edge computing nodes for the user.
And step B4, after the connection between the user and the edge computing node is successfully established, the user can use the functions provided by the logistics information platform. After the user request is successfully processed, the user sends information to the cloud server, the cloud server inquires resources of the edge computing nodes occupied by the request, updates resource information of the corresponding edge computing nodes, and finally deletes information which is maintained in a specific data structure and is related to the request.
As shown in fig. 3, the workflow of the logistics information platform of the present invention will be described in detail below.
After a user accesses the cloud server, the cloud server picks out the optimal edge computing node according to the current state of each edge computing node; after receiving the information returned by the cloud server, the user starts to establish connection with the edge computing node, and at the moment, the user can access the logistics information platform.
The logistics information platform judges whether the user belongs to the registered user or not and provides different services according to the user category.
If the user belongs to the unregistered user, the logistics information platform selects the logistics service which meets the user requirements and is used frequently in the logistics information platform according to the logistics service requirements filled by the user, and recommends the logistics service to the user, and meanwhile corresponding sorting and filtering are carried out by combining the geographical position information of the user, and finally a more reasonable recommendation result is formed and presented to the user;
if the user belongs to the registered user, the logistics information platform automatically queries the logistics service use condition of the user, some basic information and historical browsing information of the user in a database based on the block chain in the background, and different recommendation strategies are adopted according to the information of the user; if the user only finishes the registration and does not generate an order, the user belongs to a new user, and a final recommendation result is formed by adopting a recommendation algorithm based on demographics and combining with default recommendation; if the user generates a historical order, but the historical order and browsing information are less, a recommendation algorithm based on service similarity is adopted, and the algorithm ensures that the service which is most similar to the used service of the user is provided as a final recommendation result as far as possible on the premise that the requirement of the user is met; if the user has more historical orders and browsing information, a collaborative filtering recommendation algorithm based on service similarity is adopted, and the algorithm optimizes the traditional collaborative filtering recommendation algorithm, so that recommendation results are richer, and the recommendation speed is greatly improved.
In summary, the logistics service recommendation function is arranged on the logistics information platform, so that the recommendation efficiency is improved, the information safety is ensured, the quality of the logistics service recommendation result is improved, and the low-delay logistics service recommendation is realized.
Although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted for elements thereof without departing from the spirit and scope of the present invention.

Claims (10)

1. A logistics information platform, comprising:
an application layer: the system has a basic query function, a registration function and a logistics service recommendation function;
core layer: according to the user state, different recommendation algorithms are adopted to recommend the logistics service to the user;
and (3) a data layer: and carrying out data acquisition on the user behavior information and the user basic information.
2. The logistics information platform of claim 1, wherein the logistics service recommendation function completes logistics service screening at the core layer based on an algorithm through user behavior information and user basic information, and completes display and recommendation at the application layer, so that a user can select and evaluate recommendation results.
3. The logistics information platform of claim 1, wherein: after data acquisition is completed, the data layer completes primary processing of data through data cleaning, and encrypts the data based on distributed storage of a block chain, so that the cleaned data is stored in block chain nodes and the data is stored persistently.
4. A logistics service recommendation method is characterized by mainly comprising the following steps:
a1, a user accesses a cloud server to obtain an optimal edge computing node;
step A2, establishing connection between a user and an edge computing node, and starting to access a logistics information platform;
a3, the logistics information platform judges the user identity and carries out the related information inquiry work;
a4, adopting different recommendation algorithms to recommend logistics services to a user according to the user state;
step A5, recording user browsing information and order information;
and step A6, the user quits the logistics information platform, the edge computing node releases resources, and the cloud server updates the edge computing node information.
5. The logistics service recommendation method of claim 4, wherein: the recommendation algorithm comprises:
A. for new users, adopting a recommendation algorithm based on demographics and combining default recommendations;
B. for users with few historical orders and browsing information, a recommendation algorithm based on service similarity is adopted;
C. for users with more historical orders and browsing information, adopting a collaborative filtering recommendation algorithm based on service similarity according to preference values of the users;
D. for the unregistered user, the logistics service which is used frequently and is close to the geographical position of the user is selected as a recommendation result.
6. The logistics service recommendation method of claim 5, wherein the specific algorithm in A comprises:
s1, determining occupation, address and the like of the user according to the basic information of the user;
s2, screening out users with the same occupation, address and other information as the current user, and extracting the logistics services selected by the users to form a logistics service set to be recommended;
s3, according to all current order information, counting the logistics service top n with the most selected times as default recommendation;
s4, solving an intersection of the default recommendation set and the logistics service set to be recommended to obtain a recommendation set, and if the number of logistics services in the recommendation set can meet the recommendation number requirement, recommending in the mode; and if the number of the logistics services cannot meet the requirement of the recommended number, calculating a difference set between the default recommended set and the recommended set, and filling insufficient items with the logistics services in the difference set to form a final recommended set for recommendation.
7. The logistics service recommendation method of claim 5, wherein: the recommendation algorithm based on the service similarity is as follows:
Figure FDA0002314353250000021
wherein S isabRepresenting the degree of similarity between the logistics services a, b after normalization, aiAnd biRespectively representing the scores of the logistics services a and b on the attribute i;
the calculation formula of the preference value of the user is as follows:
Figure FDA0002314353250000022
wherein, PijIndicating the preference value of user i for the logistics service j,
Figure FDA0002314353250000031
the value k of the credit for the user i on the feature k of the logistics service j is {1,2, …, m }, wkAnd expressing the weight corresponding to the characteristic k, wherein the scoring value is determined by the satisfaction degree of each item of information of the user on the characteristic.
8. The logistics service recommendation method of claim 5, wherein: the collaborative filtering recommendation algorithm adopts a Singular Value Decomposition (SVD) method to simplify data.
9. A logistics service coordination method is used for realizing low-delay logistics service recommendation and is characterized by mainly comprising the following steps:
step B1, after the user accesses the cloud server, each edge computing node registers to the cloud server, and starts a heartbeat subprocess for reporting node state information to the cloud server;
step B2, after the request information of the user is sent to the cloud server, the cloud server selects the optimal edge computing node by adopting a proper comparison rule according to the current resources of each edge computing node and the relative positions of the user and each edge computing node;
step B3, the cloud server sends the screened ip address of the optimal edge computing node to a user, and the user establishes connection with the edge computing node;
and step B4, after the connection between the user and the edge computing node is successfully established, the user can use the functions provided by the logistics information platform.
10. The logistics service coordination method according to claim 9, wherein said registered information comprises: the geographical location of the edge compute node, the ip address of the edge compute node, the state of the edge compute node, and the resources of the edge compute node.
CN201911271590.0A 2019-12-12 2019-12-12 Logistics information platform, logistics service recommendation method and logistics service coordination method Withdrawn CN111104593A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911271590.0A CN111104593A (en) 2019-12-12 2019-12-12 Logistics information platform, logistics service recommendation method and logistics service coordination method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911271590.0A CN111104593A (en) 2019-12-12 2019-12-12 Logistics information platform, logistics service recommendation method and logistics service coordination method

Publications (1)

Publication Number Publication Date
CN111104593A true CN111104593A (en) 2020-05-05

Family

ID=70422094

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911271590.0A Withdrawn CN111104593A (en) 2019-12-12 2019-12-12 Logistics information platform, logistics service recommendation method and logistics service coordination method

Country Status (1)

Country Link
CN (1) CN111104593A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112264309A (en) * 2020-09-30 2021-01-26 北京京东振世信息技术有限公司 Package sorting method, server and storage medium
CN113205292A (en) * 2021-04-25 2021-08-03 上海优备艾佳供应链管理有限公司 Logistics order recommendation method and device, electronic equipment and storage medium
CN115796731A (en) * 2023-02-06 2023-03-14 智旦运宝宝(福建)科技有限公司 Logistics transportation management method and device based on big data and storage medium

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112264309A (en) * 2020-09-30 2021-01-26 北京京东振世信息技术有限公司 Package sorting method, server and storage medium
CN113205292A (en) * 2021-04-25 2021-08-03 上海优备艾佳供应链管理有限公司 Logistics order recommendation method and device, electronic equipment and storage medium
CN115796731A (en) * 2023-02-06 2023-03-14 智旦运宝宝(福建)科技有限公司 Logistics transportation management method and device based on big data and storage medium

Similar Documents

Publication Publication Date Title
US20230275817A1 (en) Parallel computational framework and application server for determining path connectivity
US11323347B2 (en) Systems and methods for social graph data analytics to determine connectivity within a community
CN103841122B (en) Target object information recommends method, server and client
CN112015998B (en) Commodity recommendation method based on user portrait
US10311106B2 (en) Social graph visualization and user interface
JP6753578B2 (en) Methods and equipment for selecting and recommending presentation targets on electronic distribution platforms
CN111104593A (en) Logistics information platform, logistics service recommendation method and logistics service coordination method
CN102903047A (en) Method and device for releasing commodity information
CN102663627A (en) Personalized recommendation method
WO2011106897A1 (en) Systems and methods for conducting more reliable assessments with connectivity statistics
WO2019218654A1 (en) Product ordering method
CN107092647B (en) Method and device for providing resource combination
CN111310032B (en) Resource recommendation method, device, computer equipment and readable storage medium
CN111078997B (en) Information recommendation method and device
CN111626767A (en) Resource data distribution method, device and equipment
CN111460301B (en) Object pushing method and device, electronic equipment and storage medium
CN116188050A (en) Takeaway platform information processing system based on data analysis
CN116595262A (en) Travel scheme recommendation method and device, electronic equipment and computer storage medium
CN112667869A (en) Data processing method, device, system and storage medium
CN109741140A (en) A kind of e-commerce system
CN110992109B (en) Real estate customer analysis method, apparatus and storage medium based on association rule
CN112182429A (en) New customer product and service recommendation method and system based on position information
CN112330037B (en) Method and device for predicting inventory proportion of new product and server
CN113763111A (en) Article collocation method, device and storage medium
CN115456686A (en) Gift selling and giving management system and application thereof

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
WW01 Invention patent application withdrawn after publication

Application publication date: 20200505

WW01 Invention patent application withdrawn after publication