CN112215658B - Big data-based address selection method, device, computer equipment and storage medium - Google Patents

Big data-based address selection method, device, computer equipment and storage medium Download PDF

Info

Publication number
CN112215658B
CN112215658B CN202011104776.XA CN202011104776A CN112215658B CN 112215658 B CN112215658 B CN 112215658B CN 202011104776 A CN202011104776 A CN 202011104776A CN 112215658 B CN112215658 B CN 112215658B
Authority
CN
China
Prior art keywords
user
target client
address
users
portrait
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.)
Active
Application number
CN202011104776.XA
Other languages
Chinese (zh)
Other versions
CN112215658A (en
Inventor
巴豪
赵媛媛
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.)
Ping An International Smart City Technology Co Ltd
Original Assignee
Ping An International Smart City Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Ping An International Smart City Technology Co Ltd filed Critical Ping An International Smart City Technology Co Ltd
Priority to CN202011104776.XA priority Critical patent/CN112215658B/en
Publication of CN112215658A publication Critical patent/CN112215658A/en
Application granted granted Critical
Publication of CN112215658B publication Critical patent/CN112215658B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0204—Market segmentation
    • G06Q30/0205—Location or geographical consideration
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • 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
    • 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
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Finance (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Accounting & Taxation (AREA)
  • Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Business, Economics & Management (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Game Theory and Decision Science (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Marketing (AREA)
  • Probability & Statistics with Applications (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The embodiment of the application belongs to the field of big data, is applied to the field of intelligent communities, and relates to an address selecting method based on big data, which comprises the steps of obtaining positioning information of an object to be addressed and a target client group, establishing an address selecting object portrait according to the positioning information and the target client group, the method comprises the steps of obtaining basic characteristics and user behavior characteristics of each user from a preset database, constructing user portraits according to the basic characteristics and the user behavior characteristics, classifying all users according to similarity among the user portraits to obtain different user classes, and determining alternative addresses based on address object portraits and the user classes. The application also provides an address selecting device based on big data, a computer device and a storage medium. In addition, the present application relates to blockchain technology, and the basic characteristics and user behavior characteristics of a user can be stored in a blockchain. The application can avoid blind address selection under the support of big data, and the address selection is more comprehensive and reliable, thereby improving the accuracy of address selection.

Description

Big data-based address selection method, device, computer equipment and storage medium
Technical Field
The present application relates to the field of big data processing technologies, and in particular, to a method and apparatus for selecting addresses based on big data, a computer device, and a storage medium.
Background
With the development of smart cities, consumers are mainly convenient for demands of merchants, and in order for the merchants to better serve the consumers, the key is how to select sites for shops, wherein the sites are an important decision for influencing the business operation. At present, the shop site selection is mainly performed by collecting and researching the data of the area and the passenger flow volume, but the site selection mode is time-consuming and labor-consuming, and the site selection result is not comprehensive and accurate enough.
Disclosure of Invention
The embodiment of the application aims to provide a big data-based address selection method, a big data-based address selection device, computer equipment and a storage medium, so as to solve the problems of time and labor waste, low efficiency and low accuracy of a related address selection mode.
In order to solve the technical problems, the embodiment of the application provides an address selecting method based on big data, which adopts the following technical scheme:
obtaining positioning information and a target client group of an object to be addressed, and establishing an address object portrait according to the positioning information and the target client group;
acquiring basic characteristics and user behavior characteristics of each user from a preset database, and constructing a user portrait according to the basic characteristics and the user behavior characteristics;
classifying all users according to the similarity among the user figures to obtain different user classes; and
An alternative address is determined based on the address object representation and the user class.
Further, the step of creating the address object representation according to the positioning information and the target client group includes:
Respectively extracting features of the positioning information and the target client group to obtain corresponding address selecting object features and target client features;
Generating a target client label and a weight corresponding to the target client label according to the address object characteristics and the target client characteristics;
And constructing an address selecting object portrait according to the target client label and the weight corresponding to the target client label.
Further, the step of generating the target client tag and the weight corresponding to the target client tag according to the address object feature and the target client feature includes:
Classifying target client groups based on the address object features and the target client features, and calibrating target client labels with the characteristics of the target client groups for target clients of different categories;
and giving weight to the target client label according to the frequency or the proportion of the occurrence of the target client label.
Further, the step of constructing a user representation from the basic features and the user behavior features includes:
generating a user tag and a weight corresponding to the user tag according to the basic feature and the user behavior feature;
and constructing the user portrait according to the user tag and the weight corresponding to the user tag.
Further, the step of classifying all users according to the similarity between the user portraits includes:
randomly selecting a preset number of first users from all users, and setting the first users as the center point of a cluster; the preset number is the number of clustered class clusters;
Clustering users except the first user into the clusters closest to the user portrait similarity of the first user according to the user portrait;
Updating the center point based on the obtained user portraits of each user in the class cluster;
And re-clustering the users in the class clusters based on the updated center point until the users included in the updated class clusters are the same as the users included in the class clusters after the previous clustering, and stopping re-clustering to obtain all class clusters of the target area.
Further, the step of determining an alternative address based on the address object representation and the user class includes:
Calculating the matching degree between the address object portrait and the user portrait of each type of user;
screening out the user class with the highest matching degree and determining the alternative address of the object to be addressed according to the user class.
Further, the step of calculating the matching degree between the address object portrait and the user portrait of each type of user includes:
Calculating the similarity between the target client group and each user class;
and determining the similarity as the matching degree of the object to be addressed and each type of user.
In order to solve the technical problems, the embodiment of the application also provides an address selecting device based on big data, which adopts the following technical scheme:
The address object portrait construction module is used for acquiring positioning information of an object to be addressed and a target client group, and establishing an address object portrait according to the positioning information and the target client group;
the user portrait construction module is used for acquiring basic characteristics and user behavior characteristics of each user from a preset database and constructing user portraits according to the basic characteristics and the user behavior characteristics;
the classification module is used for classifying all users according to the similarity among the user figures to obtain different user classes; and
And the address selecting module is used for determining an alternative address based on the address selecting object portrait and the user class.
In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical schemes:
The computer device comprises a memory having stored therein computer readable instructions which when executed by the processor implement the steps of the big data based addressing method as described above.
In order to solve the above technical problems, an embodiment of the present application further provides a computer readable storage medium, which adopts the following technical schemes:
the computer readable storage medium has stored thereon computer readable instructions which when executed by a processor implement the steps of the big data based addressing method as described above.
Compared with the prior art, the embodiment of the application has the following main beneficial effects:
The method comprises the steps of obtaining positioning information and a target client group of an object to be addressed, establishing an object image of the address according to the positioning information and the target client group, obtaining basic characteristics and user behavior characteristics of each user from a preset database, constructing a user image according to the basic characteristics and the user behavior characteristics, classifying all users according to similarity among the user images to obtain different user classes, and determining an alternative address based on the object image of the address and a classification result; according to the application, the constructed address-selecting object portrait and the user portrait are used for selecting addresses, so that the addresses are not blindly selected under the support of big data, the addresses are more comprehensive and reliable, the accuracy of the addresses is improved, and the accurate positioning of the user group is further realized.
Drawings
In order to more clearly illustrate the solution of the present application, a brief description will be given below of the drawings required for the description of the embodiments of the present application, it being apparent that the drawings in the following description are some embodiments of the present application, and that other drawings may be obtained from these drawings without the exercise of inventive effort for a person of ordinary skill in the art.
FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 is a flow chart of one embodiment of a big data based addressing method in accordance with the present application;
FIG. 3 is a flow chart of one embodiment of step S201 in FIG. 2;
FIG. 4 is a flow chart of one embodiment of step S203 of FIG. 2;
FIG. 5 is a flow chart of one embodiment of step S204 of FIG. 2;
FIG. 6 is a schematic diagram of one embodiment of a big data based addressing device according to the present application;
FIG. 7 is a schematic diagram of an embodiment of a computer device in accordance with the application.
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the applications herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having" and any variations thereof in the description of the application and the claims and the description of the drawings above are intended to cover a non-exclusive inclusion. The terms first, second and the like in the description and in the claims or in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
In order to make the person skilled in the art better understand the solution of the present application, the technical solution of the embodiment of the present application will be clearly and completely described below with reference to the accompanying drawings.
In order to solve the problems of time and labor waste, low efficiency and low accuracy of the related site selection mode, the application provides a site selection method based on big data, which can be applied to a system architecture 100 shown in fig. 1, wherein the system architecture 100 can comprise terminal equipment 101, 102 and 103, a network 104 and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication client applications, such as a web browser application, a shopping class application, a search class application, an instant messaging tool, a mailbox client, social platform software, etc., may be installed on the terminal devices 101, 102, 103.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablet computers, electronic book readers, MP3 players (Moving Picture Experts Group Audio Layer III, dynamic video expert compression standard audio plane 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic video expert compression standard audio plane 4) players, laptop and desktop computers, and the like.
The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminal devices 101, 102, 103.
It should be noted that, the method for selecting an address based on big data provided by the embodiment of the present application is generally executed by a server or a terminal device, and correspondingly, the device for selecting an address based on big data is generally disposed in the server or the terminal device.
It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow chart of one embodiment of a big data based addressing method in accordance with the present application is shown. The big data-based address selection method comprises the following steps:
step S201, obtaining positioning information of the object to be addressed and a target client group, and establishing an image of the object to be addressed according to the positioning information and the target client group.
It should be noted that, the object to be addressed is a shop or store that needs to be laid out on line. In general, in order to perform the down-line layout in the city, it is necessary to analyze according to the location information of the object to be addressed and the targeted target customer group, so as to select an appropriate shop address for the object to be addressed.
In this embodiment, the positioning information includes an address object type and a product feature, where the address object type includes a bank, a food, a garment, a make-up, a dessert drink, a supermarket convenience, fresh fruits and vegetables, and the product feature includes a product classification, a brand, a price, and the like; the target client group is a client group aimed by the object to be addressed.
Step S202, basic characteristics and user behavior characteristics of each user are obtained from a preset database, and a user portrait is constructed according to the basic characteristics and the user behavior characteristics.
In this embodiment, the preset database refers to a place including an application program, a website, and the like where user data can be acquired. The basic characteristics of the user comprise gender, age, address and travel track, and the behavior characteristics of the user comprise life habits such as eating and wearing, buying frequency, demand degree and the like.
For example, when the user is a vehicle owner, the basic features of the user include gender, age, address and start and stop positions of frequent activities, and the basic features of the user can be obtained from a preset application program, such as a traffic police star user APP; the user behavior characteristics comprise the access times, access frequency, access residence time, preference for purchasing articles and the like of a user to a certain site selection object type, and the user behavior characteristics can be acquired by acquiring third party user data provided by a third party platform. The third party user data mainly comprises the steps that the third party platform locates the position information of the user server side through navigation, and obtains consumption information at different positions, so that consumption trends of users are summarized, for example, users pay by using a certain payment APP, the consumption information and the consumption address of the users are reserved on the APP, and the APP background can gather and output the information to the third party user data.
It is emphasized that the user's basic features and user behavior features may also be stored in nodes of a blockchain in order to further ensure privacy and security of the user's basic features and user behavior features.
The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The blockchain (Blockchain), essentially a de-centralized database, is a string of data blocks that are generated in association using cryptographic methods, each of which contains information from a batch of network transactions for verifying the validity (anti-counterfeit) of its information and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
Step S203, classifying all users according to the similarity between the user portraits to obtain different user classes.
In this embodiment, the users may be classified using a clustering algorithm, including but not limited to a K-means clustering algorithm, a mean shift clustering algorithm, a density-based clustering algorithm.
In this embodiment, all users are clustered according to the similarity between the user images, so that the users can be divided into a plurality of user class clusters, and the user preference in the same class cluster is similar. Therefore, after clustering, users with similar preferences can be divided together to obtain a plurality of groups with different preferences.
Step S204, determining an alternative address based on the address object portrait and the user class.
In this embodiment, each type of user is analyzed according to the address object image, and the matching degree between each type of user and the object to be addressed is analyzed, so as to determine the alternative address for the address object.
The method comprises the steps of obtaining positioning information and a target client group of an object to be addressed, establishing an object image of the address according to the positioning information and the target client group, obtaining basic characteristics and user behavior characteristics of each user from a preset database, constructing a user image according to the basic characteristics and the user behavior characteristics, classifying all users according to similarity among the user images to obtain different user classes, and determining an alternative address based on the object image of the address and a classification result; the constructed address selecting object image and the user image are used for selecting addresses, so that the addresses are not blindly selected under the support of big data, the addresses are more comprehensive and reliable, the accuracy of the addresses is improved, and the accurate positioning of the user group is further realized.
In some optional implementations of the present embodiment, referring to fig. 3, a method for creating an address object representation according to positioning information and a target client group in step S201 specifically includes the following steps:
Step S301, feature extraction is performed on the positioning information and the target client group respectively, and corresponding site selection object features and target client features are obtained.
Specifically, the positioning information can perform feature extraction according to the type of the address object and the characteristics of the product, the target client group can perform feature extraction according to the basic characteristics and the behavior characteristics of each client in the group, and the feature extraction can be performed by adopting but not limited to keyword extraction based on a TextRank algorithm and TF-IDF algorithm.
Step S302, generating a target client label and a weight corresponding to the target client label according to the address object characteristics and the target client characteristics.
In this embodiment, the target client tag characterizes the content, which indicates that the target client has interests, preferences, demands, etc. for the object to be addressed; the weight represents the index, represents the interest and preference index of the target client, and possibly represents the demand level of the target client, and can be simply understood as credibility, probability and the like. For example, labeling and weighting a certain two target clients is noted as: the A target client drink 0.8 and the B target client drink 0.6 indicate that the A target client likes the drink to 80 percent and the B target client drink to 0.6 indicate that the B target client likes the brand to 60 percent.
In some alternative implementations, the specific method of step S302 includes the steps of:
Classifying the target client groups based on the address object features and the target client features, and calibrating target client labels with the characteristics of the target client groups for target clients of different categories;
The target client tag is weighted according to the frequency or specific gravity of occurrence of the target client tag.
Specifically, the target client tags may be classified into product demand, consumption characteristics, channel characteristics, track characteristics, and the like according to actual needs. The channel characteristics are that the consumption mode of the target client is online consumption or offline consumption, in particular to card swiping payment, cash payment or code scanning payment and the like; the track characteristics refer to a travel mode, a travel track and a movement range of a target client.
The target customer label is given a weight according to the frequency or the specific gravity of the occurrence of the target customer label, for example, in the cosmetic product, the probability of purchasing grade level 1 is 0.6, the probability of purchasing grade level 2 is 0.2, the probability of purchasing grade level 3 is 0.1, different weights are given according to different probabilities, and the larger the probability is, the larger the weight is. It should be noted that the grade of the cosmetic product is classified according to the location of the product brand, the popularity of the product, the history of the product brand, and the like, and the probability is the proportion of the number of times of purchasing a product of a certain grade to the sum of the number of times of purchasing all the products.
The method comprises the steps of calibrating target client labels with target client group characteristics for different target clients according to classification results, and giving weights to the target client labels according to the occurrence frequency or specific gravity of the target client labels, so that the accuracy of constructing the site selection object portrait in the follow-up process can be improved.
Step S303, constructing an address selecting object portrait according to the target client label and the weight corresponding to the target client label.
According to the application, the corresponding address selecting object characteristics and target client characteristics are obtained by respectively extracting the positioning information and the target client groups, the target client labels and the weights corresponding to the target client labels are generated according to the address selecting object characteristics and the target client characteristics, the address selecting object portrait is constructed according to the target client labels and the weights corresponding to the target client labels, and the address selecting object portrait is constructed according to the target client labels and the weights corresponding to the target client labels, so that the constructed address selecting object portrait is more comprehensive and accurate.
In some optional implementations of the present embodiment, the method of step S202 specifically includes the following steps:
generating a user tag and a weight corresponding to the user tag according to the basic feature and the user behavior feature;
and constructing the user portrait according to the user labels and the weights corresponding to the user labels.
The user tag represents the user's interest, preference, demand, etc. in the product; the weight represents an interest preference index of the user for the product. In this embodiment, the weight may be given to the user tag according to the frequency or the specific gravity of the user tag, and the specific method is the same as the above-mentioned method for giving the weight to the target client tag according to the frequency or the specific gravity of the target client tag, which will not be described herein.
According to the application, the user portrait is constructed according to the user labels and the weights corresponding to the user labels, so that the constructed user portrait is more comprehensive and accurate.
In some alternative implementations, referring to fig. 4, the specific method of step S203 includes the steps of:
Step S401, randomly selecting a preset number of first users from all users, and setting the first users as the center point of a cluster; the preset number is the number of clustered class clusters.
For example, if the number of class clusters attempted to be clustered is 10, 10 first users are randomly selected from all users, and the first users are respectively set as the center points of one class cluster, so that the center points of the class clusters with the preset number of 10 can be obtained.
Step S402, clustering the users except the first user into the clusters closest to the user portrait similarity of the first user according to the user portrait.
As a possible implementation manner, for each remaining user, according to the user portrait of the user and the center point of the class cluster, the similarity between the user and the center point of each class cluster is obtained, and the user is clustered into the class cluster with the highest similarity with the center point.
When the similarity between the user and the center point is obtained, the similarity between each label in the user image of the user and the corresponding label in the center point can be obtained first. Specifically, the similarity between the tag and the corresponding tag in the center point may be calculated using the euclidean distance, the manhattan distance, the cosine similarity, and the like.
Step S403, updating the center point based on the obtained user portrait of each user in the class cluster.
After clustering the remaining users except the first user, all users are divided into a preset number of class clusters. Because of the primary clustering, the accuracy of the clustering result is not high, and the center point can be updated based on the obtained user portraits of each user in the class cluster.
As an example, for each class cluster, the label data of the same label of all users in the class cluster may be added and averaged, and the average value of the label data of all labels is updated to be a new center point.
And step S404, re-clustering the users in the class clusters based on the updated central point until the users included in the updated class clusters are the same as the users included in the class clusters after the previous clustering, and stopping re-clustering to obtain all the class clusters of the target area.
In this embodiment, after updating the center point, clustering may be performed again according to the method in step S402, and then updating the center point until the users included in the updated class cluster are the same as the users included in the class cluster after the previous clustering, that is, the clustering converges, and then the re-clustering is stopped, so as to finally obtain all the class clusters.
In this embodiment, users with high similarity are clustered together by clustering, and the clustering center is updated until convergence is achieved to improve accuracy of a clustering result.
In some alternative implementations, referring to fig. 5, the step S204 specifically includes the following steps:
step S501, a matching degree between the address object portrait and the user portrait of each type of user is calculated.
Specifically, the similarity between the target client group and each user class is calculated, and the similarity is determined as the matching degree of the object to be addressed and each user class.
In this embodiment, the similarity may be calculated by using a method including, but not limited to, cosine similarity and a jaccard coefficient, specifically, the similarity between the target client group and each type of user may be calculated according to the target client tag and the weight corresponding to the user tag, and the similarity is determined as the matching degree between the object to be addressed and each type of user, and the higher the similarity is, the higher the matching degree is.
In the embodiment, the matching degree is determined through the similarity, so that the address of the object to be addressed is more reliable and accurate, and the accurate positioning of the object to be addressed to the target client group is realized.
Step S502, screening out the preset number of user classes with highest matching degree, and determining the alternative addresses of the objects to be addressed according to the user classes.
It should be appreciated that the user profile for each user in the user class includes, among other things, the user's trajectory characteristics, from which the user's frequent range of motion may be determined, and from which the location of the object to be addressed is determined for all users in the user class.
According to the application, the matching degree between the address selecting object portrait and the user portrait of each type of user is calculated, and the address is selected for the address selecting object according to the matching degree, so that the address selecting accuracy of the address selecting object can be improved.
The application is operational with numerous general purpose or special purpose computer system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The method can be applied to the field of smart communities, thereby promoting the construction of smart cities.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by computer readable instructions stored in a computer readable storage medium that, when executed, may comprise the steps of the embodiments of the methods described above. The storage medium may be a nonvolatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
With further reference to fig. 6, as an implementation of the method shown in fig. 2, the present application provides an embodiment of a location selection device based on big data, where the embodiment of the device corresponds to the embodiment of the method shown in fig. 2, and the device may be specifically applied to various electronic devices.
As shown in fig. 6, the addressing device 600 based on big data according to the present embodiment includes: an address object representation construction module 601, a user representation construction module 602, a classification module 603 and an address selection module 604. Wherein:
the address object portrait construction module 601 is used for acquiring positioning information of an object to be addressed and a target client group, and establishing an address object portrait according to the positioning information and the target client group;
the user portrait construction module 602 is used for acquiring basic characteristics and user behavior characteristics of each user from a preset database, and constructing a user portrait according to the basic characteristics and the user behavior characteristics;
The classification module 603 is configured to classify all users according to the similarity between the user portraits, so as to obtain different user classes;
An addressing module 604 is used to determine an alternative address based on the addressing object representation and the user class.
It is emphasized that the user's basic features and user behavior features may also be stored in nodes of a blockchain in order to further ensure privacy and security of the user's basic features and user behavior features.
The address selecting device based on big data acquires positioning information and a target client group of an object to be addressed, establishes an address selecting object portrait according to the positioning information and the target client group, acquires basic characteristics and user behavior characteristics of each user from a preset database, constructs the user portrait according to the basic characteristics and the user behavior characteristics, classifies all users according to the similarity between the user portraits to obtain different user classes, and determines an alternative address based on the address selecting object portrait and a classification result; the constructed address selecting object image and the user image are used for selecting addresses, so that the addresses are not blindly selected under the support of big data, the addresses are more comprehensive and reliable, the accuracy of the addresses is improved, and the accurate positioning of the user group is further realized.
In some optional implementations of the present embodiment, the address object representation construction module 601 specifically includes a feature extraction sub-module, a generation sub-module, and a construction sub-module;
the feature extraction submodule is used for respectively carrying out feature extraction on the positioning information and the target client group to obtain corresponding site selection object features and target client features;
The generation submodule is used for generating a target client label and a weight corresponding to the target client label according to the address object characteristics and the target client characteristics;
The construction sub-module is used for constructing the address selecting object portrait according to the target client label and the weight corresponding to the target client label.
In some alternative implementations, the generating submodule is further used for classifying the target client groups based on the address object features and the target client features, and calibrating target client labels with the characteristics of the target client groups for target clients of different categories; the target client tag is weighted according to the frequency or specific gravity of occurrence of the target client tag.
And constructing the image of the address selection object through the target client label and the weight corresponding to the target client label, so that the constructed image of the address selection object is more comprehensive and accurate.
In some alternative implementations of the present embodiment, the user portrayal construction module 602 is further configured to: generating a user tag and a weight corresponding to the user tag according to the basic feature and the user behavior feature; and constructing the user portrait according to the user tag and the weight corresponding to the user tag.
The user portrait is constructed according to the user labels and the weights corresponding to the user labels, so that the constructed user portrait is more comprehensive and accurate.
In some optional implementations of the present embodiment, the classification module 603 is specifically configured to:
randomly selecting a preset number of first users from all users, and setting the first users as the center point of a cluster; the preset number is the number of clustered class clusters;
clustering users except the first user into the clusters closest to the user portrait similarity of the first user according to the user portrait;
Updating the center point based on the obtained user portraits of each user in the class cluster;
And re-clustering the users in the class clusters based on the updated center point until the users included in the updated class clusters are the same as the users included in the class clusters after the previous clustering, and stopping re-clustering to obtain all class clusters of the target area.
And (3) aggregating users with high similarity through clustering, and updating a clustering center until convergence is achieved so as to improve the accuracy of a clustering result.
In some optional implementations of this embodiment, the addressing module 604 includes a computing unit, an addressing unit, where the computing unit is configured to calculate a degree of matching between the addressing object representation and user representations of each type of user; the address selecting unit is used for screening out the user class with the highest matching degree and determining the alternative address of the object to be addressed according to the user class.
In some optional implementations, the computing unit is further configured to calculate a similarity between the target client group and each user class, and determine the similarity as a match between the object to be addressed and the users of each class.
By calculating the matching degree between the address selecting object portrait and the user portrait of each type of user and selecting the address for the address selecting object according to the matching degree, the accuracy of the address selecting object can be improved.
In order to solve the technical problems, the embodiment of the application also provides computer equipment. Referring specifically to fig. 7, fig. 7 is a basic structural block diagram of a computer device according to the present embodiment.
The computer device 7 comprises a memory 71, a processor 72, a network interface 73 communicatively connected to each other via a system bus. It should be noted that only computer device 7 having components 71-73 is shown in the figures, but it should be understood that not all of the illustrated components are required to be implemented and that more or fewer components may be implemented instead. It will be appreciated by those skilled in the art that the computer device herein is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and its hardware includes, but is not limited to, a microprocessor, an Application SPECIFIC INTEGRATED Circuit (ASIC), a Programmable gate array (Field-Programmable GATE ARRAY, FPGA), a digital Processor (DIGITAL SIGNAL Processor, DSP), an embedded device, and the like.
The computer equipment can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing equipment. The computer equipment can perform man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch pad or voice control equipment and the like.
The memory 71 includes at least one type of readable storage medium including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the storage 71 may be an internal storage unit of the computer device 7, such as a hard disk or a memory of the computer device 7. In other embodiments, the memory 71 may also be an external storage device of the computer device 7, such as a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD) or the like, which are provided on the computer device 7. Of course, the memory 71 may also comprise both an internal memory unit of the computer device 7 and an external memory device. In this embodiment, the memory 71 is generally used to store an operating system and various application software installed on the computer device 7, such as computer readable instructions of a location selection method based on big data. Further, the memory 71 may be used to temporarily store various types of data that have been output or are to be output.
The processor 72 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 72 is typically used to control the overall operation of the computer device 7. In this embodiment, the processor 72 is configured to execute computer readable instructions stored in the memory 71 or process data, such as computer readable instructions for executing the big data based addressing method.
The network interface 73 may comprise a wireless network interface or a wired network interface, which network interface 73 is typically used for establishing a communication connection between the computer device 7 and other electronic devices.
According to the embodiment, the steps of the address selecting method based on big data in the embodiment are realized when the processor executes the computer readable instructions stored in the memory, the address is selected through the constructed address selecting object image and the user image, the address is not blindly selected any more under the support of the big data, the address is more comprehensive and reliable, the address selecting accuracy is improved, and the accurate positioning of the user group is further realized.
The application also provides another embodiment, namely a computer readable storage medium which stores computer readable instructions, wherein the computer readable instructions can be executed by at least one processor, so that the at least one processor executes the steps of the address selection method based on big data, and the constructed address selection object image and the user image are used for carrying out address selection, so that the address selection is not blind any more, the address selection is more comprehensive and reliable, the address selection accuracy is improved, and the accurate positioning of a user group is further realized.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present application.
It is apparent that the above-described embodiments are only some embodiments of the present application, but not all embodiments, and the preferred embodiments of the present application are shown in the drawings, which do not limit the scope of the patent claims. This application may be embodied in many different forms, but rather, embodiments are provided in order to provide a thorough and complete understanding of the present disclosure. Although the application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing description, or equivalents may be substituted for elements thereof. All equivalent structures made by the content of the specification and the drawings of the application are directly or indirectly applied to other related technical fields, and are also within the scope of the application.

Claims (6)

1. The site selection method based on big data is characterized by comprising the following steps:
obtaining positioning information and a target client group of an object to be addressed, and establishing an address object portrait according to the positioning information and the target client group;
acquiring basic characteristics and user behavior characteristics of each user from a preset database, and constructing a user portrait according to the basic characteristics and the user behavior characteristics;
classifying all users according to the similarity among the user figures to obtain different user classes; and
Determining an alternative address based on the address object representation and the user class;
Wherein the step of determining an alternative address based on the address object representation and the user class comprises:
Calculating the matching degree between the address object portrait and the user portrait of each type of user;
Screening out the preset number of user classes with highest matching degree, determining the activity range of each user according to the track characteristics of the user portraits of each user in the user classes, and determining the alternative addresses of the objects to be addressed according to the activity ranges of all users in the user classes;
the step of establishing the address object portrait according to the positioning information and the target client group comprises the following steps:
Respectively extracting features of the positioning information and the target client group to obtain corresponding address selecting object features and target client features;
Generating a target client label and a weight corresponding to the target client label according to the address object characteristics and the target client characteristics;
constructing an address selecting object portrait according to the target client label and the weight corresponding to the target client label;
The step of generating a target client tag and a weight corresponding to the target client tag according to the address object feature and the target client feature comprises the following steps:
Classifying target client groups based on the address object features and the target client features, and calibrating target client labels with the characteristics of the target client groups for target clients of different categories;
Giving weight to the target client label according to the frequency or specific gravity of the target client label;
wherein, the step of classifying all users according to the similarity between the user portraits comprises the following steps:
randomly selecting a preset number of first users from all users, and setting the first users as the center point of a cluster; the preset number is the number of clustered class clusters;
Clustering users except the first user into the clusters closest to the user portrait similarity of the first user according to the user portrait;
Updating the center point based on the obtained user portraits of each user in the class cluster;
and re-clustering the users in the class clusters based on the updated center point until the users included in the updated class clusters are the same as the users included in the class clusters after the previous clustering, stopping re-clustering, and obtaining all class clusters of the target area.
2. The big data based addressing method of claim 1, wherein said step of constructing a user representation from said basic features and said user behavior features comprises:
generating a user tag and a weight corresponding to the user tag according to the basic feature and the user behavior feature;
and constructing the user portrait according to the user tag and the weight corresponding to the user tag.
3. The big data based addressing method of claim 1, wherein the step of calculating a degree of matching between the addressing object representation and the user representations of each class of users comprises:
Calculating the similarity between the target client group and each user class;
and determining the similarity as the matching degree of the object to be addressed and each type of user.
4. An address selecting device based on big data, comprising:
The address object portrait construction module is used for acquiring positioning information of an object to be addressed and a target client group, and establishing an address object portrait according to the positioning information and the target client group;
the user portrait construction module is used for acquiring basic characteristics and user behavior characteristics of each user from a preset database and constructing user portraits according to the basic characteristics and the user behavior characteristics;
the classification module is used for classifying all users according to the similarity among the user figures to obtain different user classes; and
An address selecting module for determining an alternative address based on the address selecting object representation and the classification result;
the addressing module comprises a computing unit and an addressing unit, wherein:
the computing unit is used for computing the matching degree between the address object portrait and the user portrait of each type of user;
The address selecting unit is used for screening out the preset number of user classes with highest matching degree, determining the activity range of each user according to the track characteristics of the user portraits of each user in the user classes, and determining the alternative addresses of the objects to be addressed according to the activity ranges of all users in the user classes;
the site selection object portrait construction module comprises a feature extraction sub-module, a generation sub-module and a construction sub-module;
the feature extraction submodule is used for respectively carrying out feature extraction on the positioning information and the target client group to obtain corresponding site selection object features and target client features;
The generation submodule is used for generating a target client label and a weight corresponding to the target client label according to the address object characteristics and the target client characteristics;
The construction sub-module is used for constructing an address selection object portrait according to the weight corresponding to the target client label;
The generation sub-module is further used for classifying the target client groups based on the address object characteristics and the target client characteristics, and calibrating target client labels with the characteristics of the target client groups for target clients of different categories; giving weight to the target client label according to the frequency or specific gravity of the target client label;
The classification module is used for:
randomly selecting a preset number of first users from all users, and setting the first users as the center point of a cluster; the preset number is the number of clustered class clusters;
clustering users except the first user into the clusters closest to the user portrait similarity of the first user according to the user portrait;
Updating the center point based on the obtained user portraits of each user in the class cluster;
And re-clustering the users in the class clusters based on the updated center point until the users included in the updated class clusters are the same as the users included in the class clusters after the previous clustering, and stopping re-clustering to obtain all class clusters of the target area.
5. A computer device comprising a memory having stored therein computer readable instructions which when executed implement the steps of the big data based addressing method of any of claims 1 to 3.
6. A computer readable storage medium having stored thereon computer readable instructions which when executed by a processor implement the steps of the big data based addressing method of any of claims 1 to 3.
CN202011104776.XA 2020-10-15 2020-10-15 Big data-based address selection method, device, computer equipment and storage medium Active CN112215658B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011104776.XA CN112215658B (en) 2020-10-15 2020-10-15 Big data-based address selection method, device, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011104776.XA CN112215658B (en) 2020-10-15 2020-10-15 Big data-based address selection method, device, computer equipment and storage medium

Publications (2)

Publication Number Publication Date
CN112215658A CN112215658A (en) 2021-01-12
CN112215658B true CN112215658B (en) 2024-08-20

Family

ID=74054713

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011104776.XA Active CN112215658B (en) 2020-10-15 2020-10-15 Big data-based address selection method, device, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN112215658B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112783984A (en) * 2021-02-10 2021-05-11 中国人民银行数字货币研究所 Information display method and device
CN113379464B (en) * 2021-06-29 2023-12-05 北京百度网讯科技有限公司 Block chain-based site selection method, device, equipment and storage medium
CN113449922B (en) * 2021-07-09 2024-06-28 中国银行股份有限公司 Bank outlet address selection method and device
CN113706222B (en) * 2021-09-18 2023-12-22 口碑(上海)信息技术有限公司 Store site selection method and device
CN113743999B (en) * 2021-11-08 2022-02-11 江苏荣泽信息科技股份有限公司 Block chain-based chain brand site selection management system for multi-region marketing strategy

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109377328A (en) * 2018-12-19 2019-02-22 口口相传(北京)网络技术有限公司 The recommended method and device in businessman shops geographical location

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CA2745536A1 (en) * 2010-07-06 2012-01-06 Omar M. Sheikh Improving the relevancy of advertising material through user-defined preference filters, location and permission information
CN104750751B (en) * 2013-12-31 2018-02-23 华为技术有限公司 Track data mask method and device
CN109949063B (en) * 2017-12-20 2021-08-06 中移(苏州)软件技术有限公司 Address determination method and device, electronic equipment and readable storage medium
CN108108451A (en) * 2017-12-27 2018-06-01 合肥美的智能科技有限公司 The group of subscribers portrait acquisition methods and device of group
CN111242666A (en) * 2018-11-29 2020-06-05 Tcl集团股份有限公司 Store site selection method based on big data analysis, storage medium and server
CN111626777B (en) * 2020-05-25 2023-04-18 泰康保险集团股份有限公司 Site selection method, site selection decision system, storage medium and electronic equipment

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109377328A (en) * 2018-12-19 2019-02-22 口口相传(北京)网络技术有限公司 The recommended method and device in businessman shops geographical location

Also Published As

Publication number Publication date
CN112215658A (en) 2021-01-12

Similar Documents

Publication Publication Date Title
CN112215658B (en) Big data-based address selection method, device, computer equipment and storage medium
CN112148987B (en) Message pushing method based on target object activity and related equipment
US10235425B2 (en) Entity fingerprints
CN113643103B (en) Product recommendation method, device, equipment and storage medium based on user similarity
CN107730389A (en) Electronic installation, insurance products recommend method and computer-readable recording medium
CN109190044A (en) Personalized recommendation method, device, server and medium
US20100306318A1 (en) Apparatuses, methods, and systems for a graphical code-serving interface
CN109471978B (en) Electronic resource recommendation method and device
CN102132301A (en) System and method for online advertising using user social information
US10074097B2 (en) Classification engine for classifying businesses based on power consumption
CN113220734A (en) Course recommendation method and device, computer equipment and storage medium
CN112668482B (en) Face recognition training method, device, computer equipment and storage medium
EP2678809A1 (en) Entity fingerprints
US12019852B2 (en) Systems and methods for orienting webpage content based on user attention
CN111369301A (en) Transaction evaluation method, device and terminal
CN113360788A (en) Address recommendation method, device, equipment and storage medium
CN112182390B (en) Mail pushing method, device, computer equipment and storage medium
CN117314586A (en) Product recommendation method, device, computer equipment and storage medium
CN114240553A (en) Recommendation method, device and equipment for vehicle insurance products and storage medium
US10832276B2 (en) Systems and methods for ad placement in content streams
CN110929175A (en) Method, device, system and medium for evaluating user evaluation
KR20200042232A (en) Method for providing advertisement solution
KR102213191B1 (en) Apparatus and method for providing information based on behavior data
US20230099904A1 (en) Machine learning model prediction of interest in an object
JP2024145614A (en) Information processing device, information distribution system, and method for generating machine learning model

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
GR01 Patent grant
GR01 Patent grant