CN110503453A - Customer-action analysis method, apparatus, computer equipment and storage medium - Google Patents
Customer-action analysis method, apparatus, computer equipment and storage medium Download PDFInfo
- Publication number
- CN110503453A CN110503453A CN201910606166.0A CN201910606166A CN110503453A CN 110503453 A CN110503453 A CN 110503453A CN 201910606166 A CN201910606166 A CN 201910606166A CN 110503453 A CN110503453 A CN 110503453A
- Authority
- CN
- China
- Prior art keywords
- consumption
- user
- label
- subtab
- attribute tags
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
-
- 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
- G06Q30/0203—Market surveys; Market polls
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses customer-action analysis method, apparatus, computer equipment and storage mediums, carry out preliminary analysis to the personal information data of user by the way of labeling, the user of same label is placed in identity set;Behavioural analysis is carried out to the consumption information of each user respectively by way of labeling again, to mark off with the corresponding user group of identical consumer behavior, the consumption propensity of user group's preference is determined according to consumer behavior, obtains corresponding consumption location information to obtain the consumption propensity of the user group.The present invention carries out the consumption preferences analysis of various dimensions consumption label based on the consumption information of user, and the analysis result of acquisition is more specific and comprehensive, has the data acquisition system having significant practical applications.
Description
Technical field
The present invention relates to financial fields more particularly to customer-action analysis method, apparatus, computer equipment and storage to be situated between
Matter.
Background technique
Consumer behavior research is most common, most frequently implement one research in market survey.Refer to and is to consumer
It obtains, use various action and the quantitative studies for the decision processes that these action are determined in advance used by article and qualitative grind
Study carefully.The research can also understand consumer is how to consume in addition to will be seen that consumer is how to obtain product and service
Product.Therefore, it is the basis of marketing decision-making, inseparable with the marketing activity of enterprise market.For point of consumer behaviour
Although the time of analysis only decades, caused multi-party concern, different subjects from different area researches, visit
Rope proposes buying behavior mode with their own characteristics, these modes are for understanding fully specific purchase in Enterprises Marketing activity
Person's behavior and its with enterprise's items market policy, the relationship of method and strategy, grasp regularity to induce advantageous buying behavior
There is important reference value.But the form that the analysis of existing consumer behaviour generallys use questionnaire survey obtains data
Source needs to expend a large amount of manpower and material resources, primarily directed to entity industry, such as market purchase analysis dimension it is limited can not be complete
The consumer behavior of the reflection consumer in face.
Summary of the invention
Analysis for existing consumer behaviour needs to expend a large amount of manpower and material resources and analyzes the limited problem of dimension,
A kind of customer-action analysis side counted to the consumer behavior of user that can reduce the comprehensive various dimensions of manpower and material resources is now provided
Method, device, computer equipment and storage medium.
To achieve the above object, the present invention provides a kind of customer-action analysis method, provides the data in a storing data source
Library, the data source are the personal information data of user;The described method includes:
The personal information data for obtaining user from the database, by people's information data and pre-stored attribute tags
It is matched, forms the attribute tags of user;
The user property label for obtaining all users carries out similarity mode to all user property labels, by attribute mark
It signs identical user to combine, forms a properties user set;
Customer consumption information is obtained, the consumption information of user is matched with preset consumption label, and based on consumption
Label generates consumption combination tag corresponding with the consumption information;
Together by the corresponding user property label aggregation of identical consumption combination tag, it generates and applies tag set, it is each
Using the corresponding corresponding consumption location information of tag set.
Preferably, from the database obtain user personal information data, by people's information data with it is pre-stored
Attribute tags are matched, and the attribute tags of user are formed, comprising:
The personal information data of the user are extracted from the database;
Each single item personal data in personal information data are matched with pre-stored attribute tags, with obtain with
The matched attribute tags of all personal data of user;
The attribute tags include: gender, and/or educational background and/or marital status and/or nationality and/or city, and/
Or age level.
Preferably, the personal information data for obtaining user from the database, by personal data and pre-stored category
Property label is matched, and forms the attribute tags of user further include: the user in the database is updated with predetermined period
Personal information data, updated personal information data are matched with pre-stored attribute tags, form user's
Attribute tags.
Preferably, the consumption label includes: consumption pattern, consumption interest, spending limit and consuming frequency;
The corresponding label of the consumption pattern includes: quick payment subtab and cCredit card payment subtab;
The corresponding label of the consumption interest includes: trip class subtab, body-building class subtab, viewing class subtab, meal
Drink class subtab, mother and baby's class subtab, the competing class subtab of electricity, insurance class subtab, digital class subtab, makeups personal nursing class
Subtab, nutrition and health class subtab and dress ornament class subtab;
The corresponding label of the spending limit is the label of spending amount in preset cost section;
The corresponding label of the consuming frequency is the label for the number consumed in preset time.
Preferably, customer consumption information is obtained, the consumption information of user is matched with preset consumption label, and base
Consumption combination tag corresponding with the consumption information is generated in consumption label, comprising:
The consumption information for extracting the user carries out parsing to the consumption information and obtains at least one consumption data, point
Not each consumption data is matched with the subtab in the consumption label, is obtained and the consumption data is matched disappears
Take subtab;
Consumption combination tag corresponding with the consumption information is generated based on the consumption subtab.
Preferably, customer consumption information is obtained, the consumption information of user is matched with preset consumption label, and base
Consumption combination tag corresponding with the consumption information is generated in consumption label, further includes:
The consumption combination tag is updated with predetermined period.
Preferably, in the step S4, together by the corresponding user property label aggregation of identical consumption combination tag,
It generates and applies tag set, the corresponding corresponding consumption location information of each application tag set, comprising:
The attribute tags that identical consumption combination tag corresponds to user are flocked together to form an attribute tags set, to this
The attribute tags of user carry out statistical classification in attribute tags set, obtain each attribute tags in the attribute tags set
Percentage will consume the attribute tags of combination tag and percentage greater than preset threshold and combine generation using tally set
It closes.
To achieve the above object, the present invention provides a kind of customer-action analysis device, comprising:
Storage unit, source, the data source are the personal information data of user for storing data;
Attribute transposition unit, for obtaining the personal information data of user from the database, by people's information data with
Pre-stored attribute tags are matched, and the attribute tags of user are formed;
Taxon carries out similarity to all user property labels for obtaining the user property label of all users
Matching, the identical user of attribute tags is combined, and forms a properties user set;
Processing unit, for obtaining customer consumption information, by the consumption information of user and the progress of preset consumption label
Match, and consumption combination tag corresponding with the consumption information is generated based on consumption label;
Polymerized unit, for the corresponding user property label aggregation of identical consumption combination tag together, to be generated application
Tag set, the corresponding corresponding consumption location information of each application tag set.
To achieve the above object, the present invention provides a kind of computer equipment, the computer equipment, including memory, place
The computer program managing device and storage on a memory and can running on a processor, the processor execute the computer
The step of above method is realized when program.
To achieve the above object, the present invention provides a kind of computer readable storage medium, is stored thereon with computer program,
The step of above method is realized when the computer program is executed by processor.
Customer-action analysis method, apparatus, computer equipment and storage medium provided by the invention, using the side of labeling
Formula carries out preliminary analysis to the personal information data of user, and the user of same label is placed in identity set;Pass through label again
The mode of change carries out behavioural analysis to the consumption information of each user respectively, to mark off corresponding with identical consumer behavior
User group, determines the consumption propensity of user group's preference according to consumer behavior, obtain corresponding consumption location information to
Obtain the consumption propensity of the user group.The present invention carries out the consumption of various dimensions consumption label based on the consumption information of user
The analysis result of preference analysis, acquisition is more specific and comprehensive, has the data acquisition system having significant practical applications.
Detailed description of the invention
Fig. 1 is a kind of flow chart of embodiment of customer-action analysis method of the present invention;
Fig. 2 is the flow chart of another embodiment of customer-action analysis method of the present invention;
Fig. 3 is a kind of module map of embodiment of customer-action analysis device of the present invention;
Fig. 4 is the hardware structure schematic diagram of one embodiment of computer equipment of the present invention.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only to explain the application, not
For limiting the application.Based on the embodiment in the application, those of ordinary skill in the art are not before making creative work
Every other embodiment obtained is put, shall fall in the protection scope of this application.
Customer-action analysis method, apparatus, computer equipment and storage medium of the invention is suitable for precisely pushing, is a
Property the fields such as marketing and risk prevention system, provide it is a kind of from multiple angles consider consumer consumption behavior analysis method.Using
The mode of labeling carries out preliminary analysis to the personal information data of user, and the user of same label is placed in identity set;
Behavioural analysis is carried out to the consumption information of each user respectively by way of labeling again, to mark off with identical consumption
The corresponding user group of behavior determines the consumption propensity of user group's preference according to consumer behavior, and it is fixed to obtain corresponding consumption
Position information is to obtain the consumption propensity of the user group.The present invention carries out various dimensions consumption based on the consumption information of user
The consumption preferences of label are analyzed, and the analysis result of acquisition is more specific and comprehensive, has the data acquisition system having significant practical applications.
Embodiment one
Referring to Fig. 1, a kind of customer-action analysis method of the present embodiment, can provide using in the financial systems such as bank
The database in one storing data source, the data source are the personal information data of user;The described method includes:
S1. the personal information data for obtaining user from the database, by people's information data and pre-stored attribute
Label is matched, and the attribute tags of user are formed;
In practical applications, the personal information data of user can be Shen card information, information of insuring and the use of user's submission
What family used credit card includes the information of users personal data with card (consumption) data etc..
The step S1, from the database obtain user personal information data, by people's information data with deposit in advance
The attribute tags of storage are matched, and the attribute tags of user are formed, comprising:
The personal information data of the user are extracted from the database;
Each single item personal data in personal information data are matched with pre-stored attribute tags, with obtain with
The matched attribute tags of all personal data of user;
It should be noted that the personal information data of user carry out pretreatment refer to the personal information data of user into
Row screening and filtering filters out the information unrelated with attribute tags, such as political affiliation situation, cell-phone number, E-mail address information.With
The corresponding mark of each item data in the personal information data at family, portion identification is associated with attribute tags, when being pre-processed
The mark of item data each in personal information data mark corresponding with attribute tags is matched, unmatched mark is filtered out
Know, extracts the corresponding data of matched mark.
The attribute tags include: gender, and/or educational background and/or marital status and/or nationality and/or city, and/
Or age level.
Specifically, the corresponding attribute tags of gender include: male's subtab, women subtab;The corresponding attribute mark of educational background
Label include: junior college or less academic subtab, post-secondary education label, academic certificates at or above the junior college level label;The corresponding attribute mark of marital status
Label include: married subtab, unmarried subtab;The corresponding attribute tags of nationality need to be specific nationality's subtab;City is corresponding
Attribute tags need to be specific city subtab;The corresponding attribute tags of age level can include: children (0 to 6 year old) sub- mark
Label, juvenile (7 to 17 years old) subtab, youth (18 to 35 years old) subtab, middle age (36 to 45 years old) subtab, person in middle and old age (46 to
65 years old) subtab, old age (65 years old+) subtab.
Since the age of user can change over time, and other data will not be again after acquiring for the first time substantially
It changes.Therefore step S1 may also include that the user in the database is updated with predetermined period (such as: 1 year)
People's information data (mainly age information), by updated personal information data and the progress of pre-stored attribute tags
Match, form the attribute tags of user, to guarantee the accuracy of personal information data.
S2. the user property label for obtaining all users carries out similarity mode to all user property labels, by attribute
The identical user of label combines, and forms a properties user set;
In this step, user's Preliminary division is formed properties user set, realizes basis by identical attribute subtab
The purpose that the personal information data of user divide user crowd.
S3. customer consumption information is obtained, the consumption information of user is matched with preset consumption label, and is based on disappearing
Take label and generates consumption combination tag corresponding with the consumption information;
Further, the consumption label includes: consumption pattern, consumption interest, spending limit and consuming frequency.
The corresponding label of the consumption pattern includes: quick payment subtab and cCredit card payment subtab.
The corresponding label of the consumption interest includes: that trip class subtab (such as: aircraft, train, self-driving, ride by public transport subway
Vehicle etc.), body-building class subtab, viewing class subtab, food and drink class subtab, mother and baby's class subtab, the competing class subtab of electricity, insurance class
Subtab, digital class subtab, makeups personal nursing class subtab, nutrition and health class subtab and dress ornament class subtab.
The corresponding label of the spending limit is the label of spending amount in preset cost section.
For example and without limitation, the corresponding label of the spending limit can include: less than 10 metaclass subtabs, be greater than or
More than or equal to 100 and it is less than equal to 10 and less than 50 metaclass subtabs more than or equal to 50 and less than 100 metaclass subtabs
200 metaclass subtabs are greater than or equal to 500 and less than 800 metaclass marks more than or equal to 200 and less than 500 metaclass subtabs
Label are greater than or equal to 800 and are greater than less than 1000 metaclass subtabs more than or equal to 1000 and less than 3000 metaclass subtabs
Or equal to 3000 and less than 5000 metaclass subtabs, it is greater than or equal to 5000 subtabs.
It should be understood that also classification division can be carried out to spending limit according to each consumption interest corresponding label, such as:
The corresponding spending limit subtab of viewing class subtab can include: less than 10 yuan (containing) class subtabs, 10-30 (contain)
Metaclass subtab is greater than 30 metaclass subtabs;
The corresponding spending limit subtab of food and drink class subtab can include: less than 20 yuan (containing) class subtabs, 20-50 member
(containing) class subtab is greater than 50 metaclass subtabs;
The corresponding spending limit subtab of self-driving class subtab (can be consumed and be determined by oiling class) can include: less than 100
First (containing) class subtab, 100-200 member (containing) class subtab, is greater than 200 metaclass subtabs.
The corresponding label of the consuming frequency is the label for the number consumed in preset time.
Consuming frequency is to consume in the recent period to user with class discrimination, and it is accumulative to carry out polymerization to the consumption stroke count of positive and negative transaction.
Wherein for there is the case where negative transaction, by the negative transaction repeatedly occurred with the progress of the conditions such as customer ID, authorization code, exchange hour
Polymerization is handled after grouping, and the identical data of polymerizing condition are only counted once, with the result after polymerization with the data accumulation knot just traded
Fruit is consuming frequency after doing difference set.This is the daily data for changing and updating.Wherein, polymerization result=negative transaction set of positive transaction set-.
The step S3 obtains customer consumption information, the consumption information of user is matched with preset consumption label,
And consumption combination tag corresponding with the consumption information is generated based on consumption label, it may include (referring to Fig. 2):
S31. the consumption information for extracting the user carries out parsing to the consumption information and obtains at least one consumption number
According to each consumption data is matched with the subtab in the consumption label respectively, is obtained and the consumption data
The consumption subtab matched;
S32. consumption combination tag corresponding with the consumption information is generated based on the consumption subtab.
In this step, consumption combination tag (corresponding with consumer behavior) is that user is based on the basis of consumption interest, In
In different time points, to the behavior label for the amount of money that different merchandise classifications are consumed by different consumption patterns.
Such as: the Mr. Wang for being born on January 2nd, 2001 buys film certificate flower by Taobao in the birthday on January 2nd, 2019 month
Take 9.9 yuan.The corresponding label of the consumer behavior is as follows:
Attribute tags: juvenile -> young (through age tag update);
Label: consumption pattern-quick payment (Taobao's purchase) is consumed, 9.9 yuan of spending limit-cost, consumes interest-viewing
Class (purchase film certificate).Consumption combination tag is according to this are as follows: viewing class, less than 10 yuan, and quick payment.
Consumption combination tag is to form consumption pattern, consuming frequency, consumption interest, spending limit tag combination together
Label.The consumer behavior of user can be embodied by consuming combination tag.
It should be understood that the step S3 may also include that
The consumption combination tag is updated with predetermined period (such as one day), to guarantee the real-time of consumption information.
S4. together by the corresponding user property label aggregation of identical consumption combination tag, generate and apply tag set, often
The corresponding corresponding consumption location information of one application tag set.
Specifically, the attribute tags that identical consumption combination tag corresponds to user are flocked together to form an attribute tags collection
It closes, statistical classification is carried out to the attribute tags of user in the attribute tags set, obtains each attribute tags in the attribute tags
Percentage in set will consume the attribute tags of combination tag and percentage greater than preset threshold and combine generation application
Tag set.
Wherein, preset threshold can be 0.75,0.8 or 0.85 etc., which can be set according to the actual situation.
It is described consumption location information be with it is described using tag set it is corresponding consumption location information composition consumer behavior
Predictive information.
Consumption location information reflects various contents such as the level of consumption of user, consumption propensity.According to the consumption
Location information can push the product or service high with its hobby, the focus degree of correlation to user, promote the experience effect of user
Fruit realizes the purpose of personalized words marketing, can also carry out corresponding risk prevention system according to the consumption location information.According to what is generated
When can meet the user crowd of the same category under square one using tag set, corresponding consumer behavior is pushed.By disappearing
The ecological chain that data are energized is made in the focusing for taking behavior.
In the present embodiment, preliminary analysis is carried out to the personal information data of user by the way of labeling, it will be identical
The user of label is placed in identity set;Behavior point is carried out to the consumption information of each user respectively by way of labeling again
Analysis, to mark off with the corresponding user group of identical consumer behavior, determines user group's preference according to consumer behavior
Consumption propensity obtains corresponding consumption location information to obtain the consumption propensity of the user group.The present invention is disappeared with user's
The consumption preferences analysis of various dimensions consumption label is carried out based on charge information, the analysis result of acquisition is more specific and comprehensive, has
The data acquisition system of practical application meaning.
Embodiment two
As shown in figure 3, a kind of customer-action analysis device 1, comprising: storage unit 11, Attribute transposition unit 12, grouping sheet
Member 13, processing unit 14 and polymerized unit 15;Wherein:
Storage unit 11, source, the data source are the personal information data of user for storing data;
Attribute transposition unit 12, for obtaining the personal information data of user from the database, by people's information data
It is matched with pre-stored attribute tags, forms the attribute tags of user;
In practical applications, the personal information data of user can be Shen card information, information of insuring and the use of user's submission
What family used credit card includes the information of users personal data with card (consumption) data etc..
It is specific that attribute tagsization are carried out to the personal information data of the user can include:
The personal information data of the user are extracted from the database;
Each single item personal data in personal information data are matched with pre-stored attribute tags, with obtain with
The matched attribute tags of all personal data of user;
It should be noted that the personal information data of user carry out pretreatment refer to the personal information data of user into
Row screening and filtering filters out the information unrelated with attribute tags, such as political affiliation situation, cell-phone number, E-mail address information.
The attribute tags include: gender, and/or educational background and/or marital status and/or nationality and/or city, and/
Or age level.
Specifically, the corresponding attribute tags of gender include: male's subtab, women subtab;The corresponding attribute mark of educational background
Label include: junior college or less academic subtab, post-secondary education label, academic certificates at or above the junior college level label;The corresponding attribute mark of marital status
Label include: married subtab, unmarried subtab;The corresponding attribute tags of nationality need to be specific nationality's subtab;City is corresponding
Attribute tags need to be specific city subtab;The corresponding attribute tags of age level can include: children (0 to 6 year old) sub- mark
Label, juvenile (7 to 17 years old) subtab, youth (18 to 35 years old) subtab, middle age (36 to 45 years old) subtab, person in middle and old age (46 to
65 years old) subtab, old age (65 years old+) subtab.
Since the age of user can change over time, and other data will not be again after acquiring for the first time substantially
It changes.Therefore step S1 may also include that the personal information data for updating the user with predetermined period (such as: 1 year) are (main
If age information), attribute tags are carried out based on updated personal information data, to guarantee the accurate of personal information data
Property.
Taxon 13 carries out all user property labels similar for obtaining the user property label of all users
Degree matching, the identical user of attribute tags is combined, and forms a properties user set;
User's Preliminary division is formed properties user set, realizes the individual according to user by identical attribute subtab
The purpose that information data divides user crowd.
Processing unit 14 carries out the consumption information of user and preset consumption label for obtaining customer consumption information
Matching, and consumption combination tag corresponding with the consumption information is generated based on consumption label;
Further, the consumption label can include: consumption pattern, consumption interest, spending limit and consuming frequency.
The corresponding label of the consumption pattern includes: quick payment subtab and cCredit card payment subtab.
The corresponding label of the consumption interest includes: that trip class subtab (such as: aircraft, train, self-driving, ride by public transport subway
Vehicle etc.), body-building class subtab, viewing class subtab, food and drink class subtab, mother and baby's class subtab, the competing class subtab of electricity, insurance class
Subtab, digital class subtab, makeups personal nursing class subtab, nutrition and health class subtab and dress ornament class subtab.
The corresponding label of the spending limit is the label of spending amount in preset cost section.
For example and without limitation, the corresponding label of the spending limit can include: less than 10 metaclass subtabs, be greater than or
More than or equal to 100 and it is less than equal to 10 and less than 50 metaclass subtabs more than or equal to 50 and less than 100 metaclass subtabs
200 metaclass subtabs are greater than or equal to 500 and less than 800 metaclass marks more than or equal to 200 and less than 500 metaclass subtabs
Label are greater than or equal to 800 and are greater than less than 1000 metaclass subtabs more than or equal to 1000 and less than 3000 metaclass subtabs
Or equal to 3000 and less than 5000 metaclass subtabs, it is greater than or equal to 5000 subtabs.
It should be understood that also classification division can be carried out to spending limit according to each consumption interest corresponding label, such as:
The corresponding spending limit subtab of viewing class subtab can include: less than 10 yuan (containing) class subtabs, 10-30 (contain)
Metaclass subtab is greater than 30 metaclass subtabs;
The corresponding spending limit subtab of food and drink class subtab can include: less than 20 yuan (containing) class subtabs, 20-50 member
(containing) class subtab is greater than 50 metaclass subtabs;
The corresponding spending limit subtab of self-driving class subtab (can be consumed and be determined by oiling class) can include: less than 100
First (containing) class subtab, 100-200 member (containing) class subtab, is greater than 200 metaclass subtabs.
The corresponding label of the consuming frequency is the label for the number consumed in preset time.
Consuming frequency is to consume in the recent period to user with class discrimination, and it is accumulative to carry out polymerization to the consumption stroke count of positive and negative transaction.
Wherein for there is the case where negative transaction, by the negative transaction repeatedly occurred with the progress of the conditions such as customer ID, authorization code, exchange hour
Polymerization is handled after grouping, and the identical data of polymerizing condition are only counted once, with the result after polymerization with the data accumulation knot just traded
Fruit is consuming frequency after doing difference set.This is the daily data for changing and updating.Wherein, polymerization result=negative transaction set of positive transaction set-.
The processing unit 14 obtains customer consumption information, by the consumption information of user and the progress of preset consumption label
Match, and corresponding with consumption information consumption combination tag generated based on consumption label, it may include process have:
The consumption information for extracting the user carries out parsing to the consumption information and obtains at least one consumption data, point
Not each consumption data is matched with the subtab in the consumption label, is obtained and the consumption data is matched disappears
Take subtab;
Consumption combination tag corresponding with the consumption information is generated based on the consumption subtab.
Wherein, consumption combination tag (corresponding with consumer behavior) is that user is based on the basis of consumption interest, when different
Between point on, to the behavior label for the amount of money that different merchandise classifications are consumed by different consumption patterns.
Such as: the Mr. Wang for being born on January 2nd, 2001 buys film certificate flower by Taobao in the birthday on January 2nd, 2019 month
Take 9.9 yuan.The corresponding label of the consumer behavior is as follows:
Attribute tags: juvenile -> young (through age tag update);
Label: consumption pattern-quick payment (Taobao's purchase) is consumed, 9.9 yuan of spending limit-cost, consumes interest-viewing
Class (purchase film certificate).Consumption combination tag is according to this are as follows: viewing class, 9.9 yuan, and quick payment.
Consumption combination tag is to form consumption pattern, consuming frequency, consumption interest, spending limit tag combination together
Label.The consumer behavior of user can be embodied by consuming combination tag.
It should be understood that the step S3 may also include that
The consumption combination tag is updated with predetermined period (such as one day), to guarantee the real-time of consumption information.
Polymerized unit 15, for together, generation to be answered by the corresponding user property label aggregation of identical consumption combination tag
With tag set, the corresponding corresponding consumption location information of each application tag set.
Specifically, the attribute tags that identical consumption combination tag corresponds to user are flocked together to form an attribute tags collection
It closes, statistical classification is carried out to the attribute tags of user in the attribute tags set, obtains each attribute tags in the attribute tags
Percentage in set will consume the attribute tags of combination tag and percentage greater than preset threshold and combine generation application
Tag set.
Wherein, preset threshold can be 0.75,0.8 or 0.85 etc., which can be set according to the actual situation.
It is described consumption location information be with it is described using tag set it is corresponding consumption location information composition consumer behavior
Predictive information.
Consumption location information reflects various contents such as the level of consumption of user, consumption propensity.According to the consumption
Location information can push the product or service high with its hobby, the focus degree of correlation to user, promote the experience effect of user
Fruit realizes the purpose of personalized words marketing, can also carry out corresponding risk prevention system according to the consumption location information.According to what is generated
When can meet the user crowd of the same category under square one using tag set, corresponding consumer behavior is pushed.By disappearing
The ecological chain that data are energized is made in the focusing for taking behavior.
In the present embodiment, preliminary analysis is carried out to the personal information data of user by the way of labeling, it will be identical
The user of label is placed in identity set;Behavior point is carried out to the consumption information of each user respectively by way of labeling again
Analysis, to mark off with the corresponding user group of identical consumer behavior, determines user group's preference according to consumer behavior
Consumption propensity obtains corresponding consumption location information to obtain the consumption propensity of the user group.The present invention is disappeared with user's
The consumption preferences analysis of various dimensions consumption label is carried out based on charge information, the analysis result of acquisition is more specific and comprehensive, has
The data acquisition system of practical application meaning.
Embodiment three
To achieve the above object, the present invention also provides a kind of computer equipment 2, which includes multiple calculating
Machine equipment 2, the component part of the customer-action analysis device 1 of embodiment two are dispersed in different computer equipments 2, are calculated
Machine equipment 2 can be execute the smart phone of program, tablet computer, laptop, desktop computer, rack-mount server,
Blade server, tower server or Cabinet-type server are (including composed by independent server or multiple servers
Server cluster) etc..The computer equipment 2 of the present embodiment includes, but is not limited to: that company can be in communication with each other by system bus
Memory 21, processor 23, network interface 22 and the customer-action analysis device 1 connect (with reference to Fig. 4).It should be pointed out that
Fig. 4 illustrates only the computer equipment 2 with component-, it should be understood that be not required for implementing all components shown,
The implementation that can be substituted is more or less component.
In the present embodiment, the memory 21 includes at least a type of computer readable storage medium, described readable
Storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory etc.), random access storage device
(RAM), static random-access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory
(EEPROM), programmable read only memory (PROM), magnetic storage, disk, CD etc..In some embodiments, memory
21 can be the internal storage unit 11 of computer equipment 2, such as the hard disk or memory of the computer equipment 2.In other realities
It applies in example, what memory 21 was also possible to be equipped on the External memory equipment of computer equipment 2, such as the computer equipment 2 inserts
Connect formula hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash memory
Block (Flash Card) etc..Certainly, the memory 21 can also both include the internal storage unit 11 of computer equipment 2 or wrap
Include its External memory equipment.In the present embodiment, memory 21 commonly used in storage be installed on computer equipment 2 operating system and
Types of applications software, for example, embodiment one customer-action analysis method program code etc..In addition, memory 21 can also be used
In temporarily storing the Various types of data that has exported or will export.
The processor 23 can be in some embodiments central processing unit (Central Processing Unit,
CPU), controller, microcontroller, microprocessor or other data processing chips.The processor 23 is commonly used in control computer
The overall operation of equipment 2 for example executes control relevant to the computer equipment 2 progress data interaction or communication and processing
Deng.In the present embodiment, the processor 23 is for running the program code stored in the memory 21 or processing data, example
Customer-action analysis device 1 as described in running.
The network interface 22 may include radio network interface or wired network interface, which is commonly used in
Communication connection is established between the computer equipment 2 and other computer equipments 2.For example, the network interface 22 is for passing through
The computer equipment 2 is connected by network with exterior terminal, establishes data between the computer equipment 2 and exterior terminal
Transmission channel and communication connection etc..The network can be intranet (Intranet), internet (Internet), the whole world
Mobile communcations system (Global Systemof Mobile communication, GSM), wideband code division multiple access (Wideband
Code DivisionMultiple Access, WCDMA), 4G network, 5G network, bluetooth (Bluetooth), Wi-Fi etc. is wireless
Or cable network.
It should be pointed out that Fig. 4 illustrates only the computer equipment 2 with component 21-23, it should be understood that simultaneously
All components shown realistic are not applied, the implementation that can be substituted is more or less component.
In the present embodiment, the customer-action analysis device 1 being stored in memory 21 can also be divided into one
A or multiple program modules, one or more of program modules are stored in memory 21, and by one or more
Processor (the present embodiment is processor 23) is performed, to complete the present invention.
Example IV:
To achieve the above object, the present invention also provides a kind of computer readable storage mediums comprising multiple storage mediums,
Such as flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory), random access storage device (RAM), static state
Random access storage device (SRAM), electrically erasable programmable read-only memory (EEPROM), may be programmed read-only memory (ROM)
Read-only memory (PROM), magnetic storage, disk, CD, server, App are stored thereon with computer using store etc.
Program, program realize corresponding function when being executed by processor 23.The computer readable storage medium of the present embodiment disappears for storing
Take behavioural analysis device 1, the customer-action analysis method of embodiment one is realized when being executed by processor 23.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of customer-action analysis method, which is characterized in that provide the database in a storing data source, the data source is to use
The personal information data at family;The described method includes:
The personal information data for obtaining user from the database, people's information data and pre-stored attribute tags are carried out
Matching, forms the attribute tags of user;
The user property label for obtaining all users carries out similarity mode to all user property labels, by attribute tags phase
Same user combines, and forms a properties user set;
Customer consumption information is obtained, the consumption information of user is matched with preset consumption label, and based on consumption label
Generate consumption combination tag corresponding with the consumption information;
Together by the corresponding user property label aggregation of identical consumption combination tag, it generates and applies tag set, each application
The corresponding corresponding consumption location information of tag set.
2. customer-action analysis method according to claim 1, which is characterized in that obtain user's from the database
People's information data is matched with pre-stored attribute tags, forms the attribute tags of user by personal information data, packet
It includes:
The personal information data of the user are extracted from the database;
Each single item personal data in personal information data are matched with pre-stored attribute tags, with acquisition and user
The matched attribute tags of all personal data;
The attribute tags include: gender, and/or educational background and/or marital status and/or nationality and/or city and/or year
Age grade section.
3. customer-action analysis method according to claim 1, which is characterized in that obtain user's from the database
Personal data are matched with pre-stored attribute tags, form the attribute tags of user by personal information data further include:
The personal information data that the user in the database is updated with predetermined period, by updated personal information data and in advance
The attribute tags first stored are matched, and the attribute tags of user are formed.
4. customer-action analysis method according to claim 1, which is characterized in that the consumption label includes: consumer
Formula, consumption interest, spending limit and consuming frequency;
The corresponding label of the consumption pattern includes: quick payment subtab and cCredit card payment subtab;
The corresponding label of the consumption interest includes: trip class subtab, body-building class subtab, viewing class subtab, food and drink class
Subtab, mother and baby's class subtab, the competing class subtab of electricity, insurance class subtab, digital class subtab, makeups personal nursing class sub- mark
Label, nutrition and health class subtab and dress ornament class subtab;
The corresponding label of the spending limit is the label of spending amount in preset cost section;
The corresponding label of the consuming frequency is the label for the number consumed in preset time.
5. customer-action analysis method according to claim 4, which is characterized in that customer consumption information is obtained, by user
Consumption information matched with preset consumption label, and corresponding with consumption information consumption is generated based on consumption label
Combination tag, comprising:
The consumption information for extracting the user carries out parsing to the consumption information and obtains at least one consumption data, respectively often
One consumption data is matched with the subtab in the consumption label, is obtained and matched consumption of the consumption data
Label;
Consumption combination tag corresponding with the consumption information is generated based on the consumption subtab.
6. customer-action analysis method according to claim 5, which is characterized in that the acquisition customer consumption information, it will
The consumption information of user is matched with preset consumption label, and corresponding with the consumption information based on consumption label generation
Consume combination tag, further includes:
The consumption combination tag is updated with predetermined period.
7. customer-action analysis method according to claim 4, which is characterized in that identical consumption combination tag is corresponding
User property label aggregation together, generates and applies tag set, the corresponding corresponding consumption positioning letter of each application tag set
Breath, comprising:
The attribute tags that identical consumption combination tag corresponds to user are flocked together to form an attribute tags set, to the attribute
The attribute tags of user carry out statistical classification in tag set, obtain percentage of each attribute tags in the attribute tags set
Than will consume the attribute tags of combination tag and percentage greater than preset threshold and combine generation using tag set.
8. a kind of customer-action analysis device characterized by comprising
Storage unit, source, the data source are the personal information data of user for storing data;
Attribute transposition unit, for obtaining the personal information data of user from the storage unit, by people's information data and in advance
The attribute tags first stored are matched, and the attribute tags of user are formed;
Taxon carries out similarity mode to all user property labels for obtaining the user property label of all users,
The identical user of attribute tags is combined, a properties user set is formed;
Processing unit matches the consumption information of user with preset consumption label for obtaining customer consumption information, and
Consumption combination tag corresponding with the consumption information is generated based on consumption label;
Polymerized unit, for together, generating and applying label the corresponding user property label aggregation of identical consumption combination tag
Set, the corresponding corresponding consumption location information of each application tag set.
9. a kind of computer equipment, the computer equipment, including memory, processor and storage are on a memory and can be
The computer program run on processor, the processor realize any one of claim 1 to 7 when executing the computer program
The step of the method.
10. a kind of computer readable storage medium, is stored thereon with computer program, it is characterised in that: the computer program
The step of any one of claim 1 to 7 the method is realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910606166.0A CN110503453A (en) | 2019-07-05 | 2019-07-05 | Customer-action analysis method, apparatus, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910606166.0A CN110503453A (en) | 2019-07-05 | 2019-07-05 | Customer-action analysis method, apparatus, computer equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110503453A true CN110503453A (en) | 2019-11-26 |
Family
ID=68586110
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910606166.0A Pending CN110503453A (en) | 2019-07-05 | 2019-07-05 | Customer-action analysis method, apparatus, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110503453A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111078816A (en) * | 2019-12-16 | 2020-04-28 | 秒针信息技术有限公司 | Position-based analysis method and device, terminal and storage medium |
CN112084242A (en) * | 2020-09-02 | 2020-12-15 | 深圳市铭数信息有限公司 | Consumption information display method, device, terminal and medium |
CN112258209A (en) * | 2020-09-01 | 2021-01-22 | 武汉策微信息科技有限公司 | Intelligent grading and tracking system for clients |
CN112561642A (en) * | 2020-12-16 | 2021-03-26 | 中国平安人寿保险股份有限公司 | Multidimensional product comparison analysis method and device, computer equipment and storage medium |
CN116823382A (en) * | 2023-05-17 | 2023-09-29 | 南京邮电大学 | Product popularization method based on big data |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106790570A (en) * | 2016-12-27 | 2017-05-31 | 山东开创云软件有限公司 | A kind of consumer behaviour analysis and management system and its analysis method |
CN108769190A (en) * | 2018-05-28 | 2018-11-06 | 广州招点信息科技有限公司 | A kind of activity invitation method for pushing and system based on consumer consumption behavior |
CN109118283A (en) * | 2018-08-10 | 2019-01-01 | 云南数金科技有限公司 | Precision marketing service system based on big data |
CN109711872A (en) * | 2018-12-14 | 2019-05-03 | 中国平安人寿保险股份有限公司 | Advertisement placement method and device based on big data analysis |
CN109919652A (en) * | 2019-01-17 | 2019-06-21 | 平安城市建设科技(深圳)有限公司 | User group's classification method, device, equipment and storage medium |
CN109934721A (en) * | 2019-01-18 | 2019-06-25 | 深圳壹账通智能科技有限公司 | Finance product recommended method, device, equipment and storage medium |
-
2019
- 2019-07-05 CN CN201910606166.0A patent/CN110503453A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106790570A (en) * | 2016-12-27 | 2017-05-31 | 山东开创云软件有限公司 | A kind of consumer behaviour analysis and management system and its analysis method |
CN108769190A (en) * | 2018-05-28 | 2018-11-06 | 广州招点信息科技有限公司 | A kind of activity invitation method for pushing and system based on consumer consumption behavior |
CN109118283A (en) * | 2018-08-10 | 2019-01-01 | 云南数金科技有限公司 | Precision marketing service system based on big data |
CN109711872A (en) * | 2018-12-14 | 2019-05-03 | 中国平安人寿保险股份有限公司 | Advertisement placement method and device based on big data analysis |
CN109919652A (en) * | 2019-01-17 | 2019-06-21 | 平安城市建设科技(深圳)有限公司 | User group's classification method, device, equipment and storage medium |
CN109934721A (en) * | 2019-01-18 | 2019-06-25 | 深圳壹账通智能科技有限公司 | Finance product recommended method, device, equipment and storage medium |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111078816A (en) * | 2019-12-16 | 2020-04-28 | 秒针信息技术有限公司 | Position-based analysis method and device, terminal and storage medium |
CN111078816B (en) * | 2019-12-16 | 2023-08-25 | 秒针信息技术有限公司 | Position-based analysis method, device, terminal and storage medium |
CN112258209A (en) * | 2020-09-01 | 2021-01-22 | 武汉策微信息科技有限公司 | Intelligent grading and tracking system for clients |
CN112084242A (en) * | 2020-09-02 | 2020-12-15 | 深圳市铭数信息有限公司 | Consumption information display method, device, terminal and medium |
CN112561642A (en) * | 2020-12-16 | 2021-03-26 | 中国平安人寿保险股份有限公司 | Multidimensional product comparison analysis method and device, computer equipment and storage medium |
CN112561642B (en) * | 2020-12-16 | 2024-04-09 | 中国平安人寿保险股份有限公司 | Multi-dimensional product comparison analysis method and device, computer equipment and storage medium |
CN116823382A (en) * | 2023-05-17 | 2023-09-29 | 南京邮电大学 | Product popularization method based on big data |
CN116823382B (en) * | 2023-05-17 | 2024-01-05 | 南京邮电大学 | Product popularization method based on big data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110503453A (en) | Customer-action analysis method, apparatus, computer equipment and storage medium | |
US10733647B2 (en) | Cumulative evaluation and review systems and methods | |
US20190205993A1 (en) | Transaction data categorizer system and method | |
WO2020001106A1 (en) | Classification model training method and store classification method and device | |
CN109934619A (en) | User's portrait tag modeling method, apparatus, electronic equipment and readable storage medium storing program for executing | |
US10902341B1 (en) | Machine learning based list recommendations | |
Tsai et al. | Customer segmentation issues and strategies for an automobile dealership with two clustering techniques | |
US11080624B2 (en) | Application programming interface for a learning concierge system and method | |
CN106611344A (en) | Method and device for mining potential customers | |
Kumar et al. | Data mining and machine learning in retail business: developing efficiencies for better customer retention | |
Surma | Business intelligence: making decisions through data analytics | |
CN110033331A (en) | Method, system and terminal device for issuing coupons | |
CN109902250A (en) | Sharing method, sharing means, computer equipment and the storage medium of questionnaire survey | |
US20130204823A1 (en) | Tools and methods for determining relationship values | |
CN108628866A (en) | The method and apparatus of data fusion | |
CN109118316A (en) | The recognition methods of shop authenticity and device on line | |
CN111784449A (en) | Data pushing method, data pushing equipment, storage medium and device | |
US20130262355A1 (en) | Tools and methods for determining semantic relationship indexes | |
CN110992111A (en) | Image mining method for applicant user based on big data | |
Leimeister et al. | RFID as enabler for the boundless real-time organisation: empirical insights from Germany | |
Rezaei et al. | Apps shoppers' behaviour and the moderating effect of product standardisation/brand recognition: A maximum likelihood estimation approach | |
CN114996579A (en) | Information pushing method and device, electronic equipment and computer readable medium | |
CN110020118A (en) | A kind of method and device calculating similarity between user | |
Sadeek et al. | Assessment of text-generated supply chain risks considering news and social media during disruptive events | |
Parr-Rud | Drive your business with predictive analytics |
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 |