CN110400076A - A kind of method of accurate analysis user behavior and feature - Google Patents
A kind of method of accurate analysis user behavior and feature Download PDFInfo
- Publication number
- CN110400076A CN110400076A CN201910675194.8A CN201910675194A CN110400076A CN 110400076 A CN110400076 A CN 110400076A CN 201910675194 A CN201910675194 A CN 201910675194A CN 110400076 A CN110400076 A CN 110400076A
- Authority
- CN
- China
- Prior art keywords
- user
- analysis
- behavior
- feature
- event
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/08—Insurance
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Human Resources & Organizations (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses the methods of a kind of precisely analysis user behavior and feature, including retaining analysis, funnel analysis, event analysis, method portrait analysis and extract user behavior and feature, result is parsed and generates specific Visual Chart and is shown, the intuitive data of user is obtained and analyzes conclusion comprehensively;By building user's portrait, using natural language, the technologies such as machine learning various dimensions user tag that business is complicated and changeable combines together the present invention, then analyzes its important feature, visualization is understood, to more accurately be inferred to user's real demand;The products characteristics under different insurance scenes, different links have been caught, comprehensive analysis has been carried out to product, has promoted the effect of application analysis, has improved the efficiency of decision-making;By the research to target user, so that all people for participating in products is all based on consistent user and discuss and decision, it is easy to constrain each side and be able to maintain in the same general orientation, improve the efficiency of decision.
Description
Technical field
The present invention relates to big data analysis field, specially a kind of method of precisely analysis user behavior and feature.
Background technique
There is huge user data in insurance company at present, these data are exactly a great wealth resources bank, enumerates
The basic attribute data of a large number of users: gender, age, user site, life, educational background, mutual-action behavior, hobby, etc..In
In Product Desing Flow, the participant of links is very more, and disagreement is always inevitable, and the efficiency of decision-making undoubtedly affects project
Progress.These attribute datas disclose the user behavior and user characteristics of people, these data are extracted, and process, and integrate, whole
It closes, to be instructed to drive business to increase for strategic decision.Currently, still such technology is not answered in insurance field
With.
Summary of the invention
The purpose of the present invention is to provide the methods of a kind of precisely analysis user behavior and feature, to solve above-mentioned background skill
The problem of being proposed in art.
To achieve the above object, the invention provides the following technical scheme: a kind of side of precisely analysis user behavior and feature
Method comprises the following specific steps that:
S1: it retains analysis: analyzing the participation situation or active degree of user, investigate the retention ratio for carrying out the user of initial behavior,
And retention ratio is calculated, graphically showed, when analysis user's concussion phase, selection phase and the stage of stable development three make
The trend of phase;
S2: funnel analysis: " digital footprint " data of user on APP, the networks such as PC webpage are acquired and carry out process
Analysis, analysis parameter are the conversion and loss of each step in process, carry out behavioural analysis, flow to website user and APP user
The days regular data operations such as monitoring, product objective conversion, hold two complementary type indexs of conversion ratio and turnover rate, obtain user behavior
State and from each phase user conversion ratio situation of origin-to-destination;
S3: the influence that the generation of certain behavior event is worth business organization event analysis: is studied using behavior event analysis method
And influence degree, the user behavior or business procedure of tracking or record, including user's registration, browsing product details page, successfully
Core guarantor etc., it is associated all because of the reason of usually excavating user behavior event behind, reciprocal effect by research and event generation
Deng;
S4: it portrait analysis: is abstracted with information such as the attribute of user, user preference, living habit, user behaviors and generates outgoing label
Change user model to draw a portrait as user;
S5: the data that system is obtained by above-mentioned retention analysis, funnel analysis, event analysis and portrait analysis extract user
The method of behavior and feature, result is parsed and generates specific Visual Chart shows, and obtains the intuitive data of user
Analysis conclusion comprehensively.
As a preferred solution of the present invention, the retention ratio refers to that the user in the unit time retains quantity, retains figure
The horizontal axis of table is the time, and the longitudinal axis is retention ratio, for intuitively showing the situation of change of retention ratio.
As a preferred solution of the present invention, the participation situation of the user or the analysis parameter of active degree include using
Amount amount, user's retention ratio, the number that Adds User, the retention ratio of next day or one day, channel retention ratio, retention ratio classical data school
It tests, user retains key factor etc..
As a preferred solution of the present invention, the foundation of the labeling user model passes through weight distribution, weight meter
The forms such as calculation, mathematical modeling are formed.
As a preferred solution of the present invention, during the event analysis, behavior of the user to multiple commodity is obtained
Record, and determine product features vector of each commodity in preset product features space in multiple commodity, it obtains by institute
The product features matrix for stating the product features vector composition of multiple commodity, according to same user to the behavior record of same commodity,
It calculates the user to score to the preference degree of the commodity, so that the behavioural characteristic to user is analyzed.
As a preferred solution of the present invention, in the funnel analysis, it is based on Network Data Capture, by the webpage of user
Browsing carries out regional division, and records residence time and login frequency of the user in each region, and calculate user
Active level in each region.
As a preferred solution of the present invention, in retention analysis, for loss user with the shape of short message questionnaire
Formula carries out Drain Causes investigation, and summarizes and show that loss factor is reported.
Compared with prior art, the beneficial effects of the present invention are:
1. the present invention is acquired by building user's portrait from " digital footprint " of the user on APP, the networks such as PC webpage,
It arranges and sorts out, after the personalized labels data for forming user, using natural language, the technologies such as machine learning answer business
Miscellaneous changeable various dimensions user tag combines together, then analyzes its important feature, understands visualization, thus more accurate
Be inferred to user's real demand.
2. the present invention has caught the products characteristics under different insurance scenes, different links, comprehensive point has been carried out to product
Analysis, more fully recognizes so that having to product, promotes the effect of application analysis, improves the efficiency of decision-making;By using target
The research at family makes all people for participating in products be all based on consistent user and discusses and decision, it is easy to constrain each Fang Nengbao
It holds in the same general orientation, improves the efficiency of decision.
Detailed description of the invention
Fig. 1 is overall flow schematic diagram of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Referring to Fig. 1, the present invention provides a kind of technical solution: a method of precisely analysis user behavior and feature, packet
Include following specific steps:
S1: it retains analysis: analyzing the participation situation or active degree of user, investigate the retention ratio for carrying out the user of initial behavior,
And retention ratio is calculated, graphically showed, when analysis user's concussion phase, selection phase and the stage of stable development three make
The trend of phase;
S2: funnel analysis: " digital footprint " data of user on APP, the networks such as PC webpage are acquired and carry out process
Analysis, analysis parameter are the conversion and loss of each step in process, carry out behavioural analysis, flow to website user and APP user
The days regular data operations such as monitoring, product objective conversion, hold two complementary type indexs of conversion ratio and turnover rate, obtain user behavior
State and from each phase user conversion ratio situation of origin-to-destination;
S3: the influence that the generation of certain behavior event is worth business organization event analysis: is studied using behavior event analysis method
And influence degree, the user behavior or business procedure of tracking or record, including user's registration, browsing product details page, successfully
Core guarantor etc., it is associated all because of the reason of usually excavating user behavior event behind, reciprocal effect by research and event generation
Deng;
S4: it portrait analysis: is abstracted with information such as the attribute of user, user preference, living habit, user behaviors and generates outgoing label
Change user model to draw a portrait as user;
S5: the data that system is obtained by above-mentioned retention analysis, funnel analysis, event analysis and portrait analysis extract user
The method of behavior and feature, result is parsed and generates specific Visual Chart shows, and obtains the intuitive data of user
Analysis conclusion comprehensively.
Further, the retention ratio refers to that the user in the unit time retains quantity, and the horizontal axis for retaining chart is the time, indulges
Axis is retention ratio, for intuitively showing the situation of change of retention ratio.
Further, the participation situation of the user or the analysis parameter of active degree include number of users, user's retention
Rate, the number that Adds User, the retention ratio of next day or one day, channel retention ratio, the classical data check of retention ratio, user retain it is important because
Element etc..
Further, the foundation of the labeling user model passes through the forms such as weight distribution, weight calculation, mathematical modeling
It is formed.
Further, during the event analysis, user is obtained to the behavior record of multiple commodity, and determine multiple quotient
Product features vector of each commodity in preset product features space in product obtains special by the commodity of the multiple commodity
The product features matrix of sign vector composition calculates the user to the commodity according to same user to the behavior record of same commodity
Preference degree scoring, so that the behavioural characteristic to user is analyzed.
Further, in the funnel analysis, it is based on Network Data Capture, the web page browsing of user is subjected to regional draw
Point, and residence time and login frequency of the user in each region are recorded, and calculate work of the user in each region
Traverse degree.
Further, in the retention analysis, Drain Causes tune is carried out in the form of short message questionnaire for the user of loss
It looks into, and summarizes and show that loss factor is reported.
The present invention participates in situation/active degree by retaining analysis, analysis user, investigates the user for carrying out initial behavior
In, how many people will do it subsequent behavior, this is the important method for being worth height to user for measuring product;Pass through funnel point
Analysis, science reflection user behavior state and from each phase user conversion ratio situation of origin-to-destination;Pass through event analysis, research
The influence and influence degree that the generation of certain behavior event is worth business organization;System extracts user's row by the above method
It for the method with feature, result is parsed and generates specific Visual Chart shows, and then available user is intuitive
Data analyze conclusion comprehensively, to drive business to increase, provide guidance for strategic decision, building user's portrait exists from user
" digital footprint " on the networks such as APP, PC webpage is acquired, and is arranged and is sorted out, in the personalized labels data for forming user
Afterwards, using natural language, the technologies such as machine learning various dimensions user tag that business is complicated and changeable combines together, then right
Its important feature is analyzed, and visualization is understood, to more accurately be inferred to user's real demand.The present invention has caught difference
Insure the products characteristics under scene, different links, comprehensive analysis has been carried out to product, has more fully been recognized so that having to product
Know, promote the effect of application analysis, improves the efficiency of decision-making;By the research to target user, make all participation products
People is all based on consistent user and discusses and decision, it is easy to constrain each side and be able to maintain in the same general orientation, raising is determined
The efficiency of plan.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of variations, modification, replacement can be carried out to these embodiments without departing from the principles and spirit of the present invention by understanding
And modification, the scope of the present invention is defined by the appended.
Claims (7)
1. a kind of method of precisely analysis user behavior and feature, which is characterized in that comprise the following specific steps that:
S1: it retains analysis: analyzing the participation situation or active degree of user, investigate the retention ratio for carrying out the user of initial behavior,
And retention ratio is calculated, graphically showed, when analysis user's concussion phase, selection phase and the stage of stable development three make
The trend of phase;
S2: funnel analysis: " digital footprint " data of user on APP, the networks such as PC webpage are acquired and carry out process
Analysis, analysis parameter are the conversion and loss of each step in process, carry out behavioural analysis, flow to website user and APP user
The days regular data operations such as monitoring, product objective conversion, hold two complementary type indexs of conversion ratio and turnover rate, obtain user behavior
State and from each phase user conversion ratio situation of origin-to-destination;
S3: the influence that the generation of certain behavior event is worth business organization event analysis: is studied using behavior event analysis method
And influence degree, the user behavior or business procedure of tracking or record, including user's registration, browsing product details page, successfully
Core guarantor etc., it is associated all because of the reason of usually excavating user behavior event behind, reciprocal effect by research and event generation
Deng;
S4: it portrait analysis: is abstracted with information such as the attribute of user, user preference, living habit, user behaviors and generates outgoing label
Change user model to draw a portrait as user;
S5: the data that system is obtained by above-mentioned retention analysis, funnel analysis, event analysis and portrait analysis extract user
The method of behavior and feature, result is parsed and generates specific Visual Chart shows, and obtains the intuitive data of user
Analysis conclusion comprehensively.
2. the method for a kind of precisely analysis user behavior and feature according to claim 1, it is characterised in that: the retention
Rate refers to that the user in the unit time retains quantity, and the horizontal axis for retaining chart is the time, and the longitudinal axis is retention ratio, is stayed for intuitively showing
Deposit the situation of change of rate.
3. the method for a kind of precisely analysis user behavior and feature according to claim 1, it is characterised in that: the user
Participation situation or the analysis parameter of active degree includes number of users, user's retention ratio, the number that Adds User, next day or one day stay
Deposit rate, channel retention ratio, the classical data check of retention ratio, user's retention key factor etc..
4. the method for a kind of precisely analysis user behavior and feature according to claim 1, it is characterised in that: the label
The foundation for changing user model is formed by forms such as weight distribution, weight calculation, mathematical modelings.
5. the method for a kind of precisely analysis user behavior and feature according to claim 1, it is characterised in that: the event
In analytic process, user is obtained to the behavior record of multiple commodity, and determines each commodity in multiple commodity in preset quotient
Product features vector in product feature space obtains the product features square being made of the product features vector of the multiple commodity
Battle array calculates the user and scores the preference degree of the commodity, thus to user according to same user to the behavior record of same commodity
Behavioural characteristic analyzed.
6. the method for a kind of precisely analysis user behavior and feature according to claim 1, it is characterised in that: the funnel
In analysis, it is based on Network Data Capture, the web page browsing of user is subjected to regional division, and record user in each region
Residence time and log in frequency, and calculate active level of the user in each region.
7. the method for a kind of precisely analysis user behavior and feature according to claim 1, it is characterised in that: the retention
In analysis, Drain Causes investigation is carried out in the form of short message questionnaire for the user of loss, and summarize and show that loss factor is reported.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910675194.8A CN110400076A (en) | 2019-07-25 | 2019-07-25 | A kind of method of accurate analysis user behavior and feature |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910675194.8A CN110400076A (en) | 2019-07-25 | 2019-07-25 | A kind of method of accurate analysis user behavior and feature |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110400076A true CN110400076A (en) | 2019-11-01 |
Family
ID=68325094
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910675194.8A Withdrawn CN110400076A (en) | 2019-07-25 | 2019-07-25 | A kind of method of accurate analysis user behavior and feature |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110400076A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111489263A (en) * | 2019-11-20 | 2020-08-04 | 北京中人网信息咨询股份有限公司 | Humanized behavior model analysis self-drawing system |
CN114092138A (en) * | 2021-11-10 | 2022-02-25 | 建信金融科技有限责任公司 | User behavior analysis method, device, equipment and storage medium |
CN114119257A (en) * | 2021-11-16 | 2022-03-01 | 上海镁信健康科技有限公司 | Management system based on insurance data |
-
2019
- 2019-07-25 CN CN201910675194.8A patent/CN110400076A/en not_active Withdrawn
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111489263A (en) * | 2019-11-20 | 2020-08-04 | 北京中人网信息咨询股份有限公司 | Humanized behavior model analysis self-drawing system |
CN114092138A (en) * | 2021-11-10 | 2022-02-25 | 建信金融科技有限责任公司 | User behavior analysis method, device, equipment and storage medium |
CN114119257A (en) * | 2021-11-16 | 2022-03-01 | 上海镁信健康科技有限公司 | Management system based on insurance data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Recker et al. | How good is BPMN really? Insights from theory and practice | |
CN106528693A (en) | Individualized learning-oriented educational resource recommendation method and system | |
CN103714139B (en) | Parallel data mining method for identifying a mass of mobile client bases | |
CN110400076A (en) | A kind of method of accurate analysis user behavior and feature | |
CN103338403B (en) | Individual character program commending method in radio data system and this system | |
Wong | Messagelens: A visual analytics system to support multifaceted exploration of mooc forum discussions | |
CN108520365A (en) | Education decision system based on big data analysis | |
Keramati et al. | Multidimensional appraisal of customer relationship management: integrating balanced scorecard and multi criteria decision making approaches | |
CN109934673A (en) | A kind of intelligent sales lead distribution method based on recommender system | |
CN102819580A (en) | Monitoring method and system of advertisements of internet third-part media website | |
Thomas et al. | Export behaviour: directions for future research | |
CN103440328A (en) | User classification method based on mouse behaviors | |
Acevedo et al. | A proposal to a decision support system with learning analytics | |
Canello et al. | Investigating space‐time patterns of regional industrial resilience through a micro‐level approach: An application to the Italian wine industry | |
Bao et al. | The role of big data-based precision marketing in firm performance | |
Lim | Managing technological development: A study of Vietnam’s telecommunication goods industry | |
Lease et al. | Crowdsourcing for search and data mining | |
CN106168975A (en) | The acquisition methods of targeted customer's concentration and device | |
BODLE et al. | Enhancing user interaction on cms solution | |
Xu et al. | An application of big data learning analysis based on MOOC platform | |
CN103294686A (en) | Method and system for identifying webpage spam user and spam webpage | |
CN109872188A (en) | Assets suggest generation method, device, computer equipment and storage medium | |
CN114691892A (en) | Retired soldier occupation planning method and retired soldier occupation planning system based on big data | |
Bele et al. | Business intelligence in e-learning | |
Romano et al. | Towards a weighted voting system for Q&A sites |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20191101 |
|
WW01 | Invention patent application withdrawn after publication |