CN112749990A - Data analysis method and system based on tourist identity - Google Patents
Data analysis method and system based on tourist identity Download PDFInfo
- Publication number
- CN112749990A CN112749990A CN202110118157.4A CN202110118157A CN112749990A CN 112749990 A CN112749990 A CN 112749990A CN 202110118157 A CN202110118157 A CN 202110118157A CN 112749990 A CN112749990 A CN 112749990A
- Authority
- CN
- China
- Prior art keywords
- data
- user
- behavior
- neural network
- collected
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3438—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment monitoring of user actions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Computational Linguistics (AREA)
- Quality & Reliability (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Biophysics (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a data analysis method and a data analysis system based on tourist identities, wherein the data analysis method comprises the following steps: s1, collecting the use data of the user; s2, formatting the collected usage data; s3, building a neural network model for obtaining the classification level of the user, and inputting the processed formatted data serving as a training sample into the neural network model for training; and S4, establishing a user level library for the trained deep neural network, and performing big data analysis on users using the software products in the identity of tourists through the user level library. The system comprises a user behavior acquisition buried point and a level behavior database. By solving the contradiction between the user experience and the enterprise data collection, the invention not only can optimize the development strategy of the enterprise and seek the development trend, but also can provide personalized service for the user, provide the user experience, and simultaneously increase the stickiness of the user to the product and promote the development of the enterprise.
Description
Technical Field
The invention relates to the technical field of big data analysis, in particular to a service system and a service method based on tourist identities.
Background
In the present society, because the development of internet brings huge convenience for people, and the development of internet enterprise also can not leave user's demand, therefore big data analysis application is born, can let enterprise analysis user's demand point through the analysis to big data, promotes the internet enterprise to improve its service, promotes user experience, promotes user to its dependence and the loyalty of service, attracts more user groups simultaneously. The analysis of the big data is generally performed on the basis of the condition that the user has an account, group information such as age, gender and the like generally exists in the account of the user, and valuable information is obtained through big data processing such as classification, statistics, analysis and the like of a user group and then is used for adjusting enterprises.
The existing account registration mode is generally mailbox registration or mobile phone number registration, especially the complicated password management of people, and the existing account registration mode is mainly a mode that the mobile phone number receives an authentication code, but, based on internet-based oversight and privacy concerns of the user, internet service providers generally allow the user to use in the manner of a guest, namely, when the user uses the internet service, the user does not register and log in the account, the process of applying for the account is avoided, the experience of the user can be improved, but at the same time, the users in the part cannot determine the usage groups of the users, so that the usage data of the usage groups of the users based on the login of the tourists cannot be classified and analyzed for the Internet enterprises, therefore, the utilization value of enterprises is not high, and how to collect big data aiming at the users of the tourist identities is also a part which is being considered and overcome by each internet enterprise.
The user service is well done at all, and the user service is more and more personalized at present, so that the analysis of user behaviors and habits receives more and more attention from enterprises. While finer granularity user behavior data is more important, the finest granularity is certainly accurate to the account level of each person, but collecting the data requires the user to register or log in our application, but the user does not want to register or log in under any circumstances, which forms a contradiction between the user experience problem and enterprise data collection.
Disclosure of Invention
The invention aims to provide a data analysis method based on the identity of a tourist, which is used for carrying out group analysis on the use data of a user group and optimizing the service of an internet platform when the user uses internet service in the identity of the tourist, and a data analysis system based on the identity of the tourist adopting the method.
The technical scheme adopted by the invention is as follows:
a data analysis method based on tourist identities comprises the following steps:
s1, collecting the use data of the user;
s2, formatting the collected usage data;
s3, building a neural network model for obtaining the classification level of the user, and inputting the processed formatted data serving as a training sample into the neural network model for training;
and S4, establishing a user level library for the trained deep neural network, and performing big data analysis on users using the software products in the identity of tourists through the user level library.
As a further optimization of the method of the present invention, in step S1 of the present invention, the collected user usage data includes search records, mouse click records, mouse track records, user access page addresses in the mouse staying area, user access content and staying time of the user on the data terminal, and the collected data is preprocessed to screen effective data;
the data end comprises a fixed host end and a mobile terminal.
As a further optimization of the method of the present invention, in step S1 of the present invention, the usage data of the user is collected through a web behavior script tool, which is developed based on javascript language.
As a further optimization of the method of the present invention, in step S2 of the present invention, the process of formatting the collected usage data includes cleaning and analyzing the data, defining a standardized storage format of the data as required, processing the data according to the standardized storage format, and storing the processed data in a database.
As a further optimization of the method of the present invention, in step S3 of the present invention, the neural network model is trained by means of supervised learning, and processed into a class library for determining the granularity of the user according to the result, where the class represents a user group of a certain kind of behavior habits, and the minimum granularity is the granularity of an individual.
As a further optimization of the method of the present invention, in step S4 of the present invention, behavior data is collected for users using software products in guest identity, and after processing the collected data, the data is sent to a trained neural network for user classification level discrimination, and corresponding behavior data is communicated and stored in a behavior level database for big data analysis.
The invention also provides a data analysis system based on the identity of the tourist, which comprises a user behavior acquisition buried point and a level behavior database; wherein the content of the first and second substances,
the user behavior acquisition buried points are used for acquiring user use data and classifying the acquired data according to classification levels;
and the level behavior database is used for storing the classified user groups and corresponding behavior data so as to be used for the system to analyze big data.
As further optimization of the system, the user behavior acquisition embedded point comprises an acquisition component and a data analysis component, the acquisition component comprises a network behavior script and a data formatting component, the network behavior script is used for acquiring behavior data of a user, the data formatting component is used for carrying out standardized processing on the acquired behavior data, the analysis component is built based on a neural network model, and the neural network model is required to be trained through a training sample and then put into use.
As a further optimization of the system of the present invention, the training process of the neural network model of the analysis component of the present invention comprises:
s1, collecting the use data of the user through the network behavior script;
s2, formatting the collected use data;
and S3, building a neural network model, taking the formatted use data as a training sample, and carrying out supervised training on the neural network model.
As a further optimization of the system, the use data of the user collected by the network behavior script comprises search records, mouse click records, mouse track records, user access page addresses of mouse staying areas, user access contents and staying time of the user on a data end, the collected data are preprocessed, effective data are screened, and the collected data are subjected to standardized processing through a data formatting component.
The invention has the following advantages:
by solving the contradiction between user experience and enterprise data collection, the invention enables the user to classify the user into classes by collecting the behavior data of the user and carrying out artificial intelligence analysis under the tourist mode, so that the classification is carried out from the tree-shaped group to the individual with the smallest class, and the big data analysis is carried out by combining the behavior data, thereby not only optimizing the development strategy of the enterprise and seeking the development trend, but also providing personalized service for the user, providing the user experience, increasing the stickiness of the user to the product and promoting the development of the enterprise.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
The invention is further described below with reference to the accompanying drawings:
FIG. 1 is a schematic diagram of data collection and processing in the present invention;
fig. 2 is a schematic view of the present invention as a whole.
Detailed Description
The present invention is further described in the following with reference to the drawings and the specific embodiments so that those skilled in the art can better understand the present invention and can implement the present invention, but the embodiments are not to be construed as limiting the present invention, and the embodiments and the technical features of the embodiments can be combined with each other without conflict.
It is to be understood that the terms first, second, and the like in the description of the embodiments of the invention are used for distinguishing between the descriptions and not necessarily for describing a sequential or chronological order. The "plurality" in the embodiment of the present invention means two or more.
The term "and/or" in the embodiment of the present invention is only an association relationship describing an associated object, and indicates that three relationships may exist, for example, a and/or B may indicate: a exists alone, B exists alone, and A and B exist at the same time. In addition, the character "/" herein generally indicates that the former and latter associated objects are in an "or" relationship.
The embodiment provides a data analysis method based on tourist identities, which comprises the following steps:
s1, collecting usage data of the user, as shown in fig. 1, there is no limitation on the data end used by the user, the data end used by the user may be a fixed host end, such as a computer end, or a mobile device end, such as a mobile phone and a tablet computer, and the current internet service side generally has a computer terminal and a mobile terminal product, and the collection method is to collect the usage data of the user by developing a network behavior script through javascript language.
The collected user use data comprises multi-dimensional information such as search records, mouse click records, mouse track records, mouse stay area user access page addresses, user access contents, stay time and the like of the user on a data terminal, multi-dimensional collected data is formed, the collected data is preprocessed, effective data is screened, and the data is stored in a temporary database so as to be convenient for subsequent analysis and arrangement;
s2, formatting the collected usage data; the above-mentioned collection mode is that its type and storage format are relatively disorderly, in order to facilitate the subsequent data processing, need carry on the standardized processing to the data collected, specifically, carry on the course formatted to the said service data of the mobile phone include washing, analysis process to the data, and then define the standardized storage format of the data according to needs, store the data into the database after processing according to the standardized storage format, we define the database as the standard library of the data;
s3, establishing a neural network model for obtaining user levels, inputting the processed formatted data into the neural network model as training samples for training, inputting the input data in a standard library into the neural network model for learning, comparing and analyzing the obtained result with the actual situation of the user, adjusting the model according to the result to continue machine learning, finally obtaining a more accurate identification result, processing the result to form a level library for judging the user granularity according to the user behavior, for example, the minimum granularity can even achieve the personal account level, namely, the behavior data of the user logging in the account is taken as the basis, namely the 'weak account' database, wherein the level can be in a large range, represents a user group of a certain behavior habit, and can be in a small or even reach the personal granularity, if the sex classification level is adopted, the tourist is female according to the behavior data analysis of the tourist identity, further, under the classification condition of the female, age group classification can be additionally arranged, the large classes can be in parallel relation, the small classes and the large classes are in tree-shaped hierarchical relation until the minimum hierarchical level is classified to a personal level, and the analysis mode can refer to a method for analyzing the large data through a registered account;
s4, establishing a user level library for the trained deep neural network, and performing big data analysis on users using software products in the form of tourist identities through the user level library; specifically, the neural network model trained in the step S3 is applied to a software product, and is used as a buried point analysis component, behavior data of a user is acquired through buried points, the acquired behavior data is classified into levels through the neural network model after being formatted, a level behavior database is established in combination with the acquired behavior data of the user, and each class corresponds to each other, and the data in the database is analyzed, so that development layout of enterprise products can be optimized, deployment can be optimized, iteration of the products can be adjusted in time, social development rules can be adapted, meanwhile, an internet service policy can be used for personalized services for users with guest identities, user experience can be further improved, and product dependency of the users can be improved. Meanwhile, in the using process, the behavior data of the user of the mobile phone is also synchronized into the standard library of the data, and the method can be used for continuously training, iterating and updating the neural network model, improving the preparation rate of neural network model identification and enabling the neural network model to be more intelligent.
The embodiment also provides a data analysis system based on the identity of the tourist, which comprises a user behavior acquisition buried point and a level behavior database; wherein the content of the first and second substances,
the user behavior acquisition embedded point is used for acquiring user use data and grading the acquired data, the user behavior acquisition embedded point comprises an acquisition component and an analysis component, the acquisition component comprises a network behavior script and a data formatting component, the user use data acquired by the network behavior script comprises search records, mouse click records, mouse track records, user access page addresses of mouse staying areas, user access contents and staying time of users on a data terminal, the acquired data are preprocessed, effective data are screened, the acquired data are standardized by the data formatting component, the analysis component is built based on a neural network model, and the neural network model is trained through a training sample and then put into use;
and the level behavior database is used for storing the divided level data.
As a preferred embodiment, the training process of the neural network model of the analysis component includes:
s1, acquiring use data of a user through the network behavior script, wherein the use data is also search records, mouse click records, mouse track records, user access page addresses of mouse staying areas, user access contents and staying time of the user on a data terminal, preprocessing the collected data, and screening effective data;
s2, formatting the collected use data;
and S3, building a neural network model, taking the formatted use data as a training sample, and carrying out supervised training on the neural network model.
The present embodiment also provides a software product comprising a user layer, a verification layer and a service layer, wherein the verification layer comprises signing the data analysis system.
The above-mentioned embodiments are merely preferred embodiments for fully illustrating the present invention, and the scope of the present invention is not limited thereto. The equivalent substitution or change made by the technical personnel in the technical field on the basis of the invention is all within the protection scope of the invention. The protection scope of the invention is subject to the claims.
Claims (10)
1. A data analysis method based on tourist identities is characterized in that: the method comprises the following steps:
s1, collecting the use data of the user;
s2, formatting the collected usage data;
s3, building a neural network model for obtaining the classification level of the user, and inputting the processed formatted data serving as a training sample into the neural network model for training;
and S4, establishing a user level library for the trained deep neural network, and performing big data analysis on users using the software products in the identity of tourists through the user level library.
2. The method of claim 1, wherein:
in step S1, the collected user usage data includes search records, mouse click records, mouse track records, user access page addresses in mouse staying areas, user access contents, and staying time of the user on the data terminal, and the collected data is preprocessed to screen effective data;
the data end comprises a fixed host end and a mobile terminal.
3. The method of claim 2, wherein:
in step S1, the usage data of the user is collected by a network behavior script tool, which is developed based on javascript language.
4. The method of claim 2, wherein:
in step S2, the process of formatting the collected usage data includes cleaning and analyzing the data, defining a standardized storage format of the data as needed, processing the data according to the standardized storage format, and storing the processed data in a database.
5. The method of claim 1, wherein:
in step S3, the neural network model is trained in a supervised learning manner, and processed into a level library for determining the granularity of the user according to the result, where the level represents a user group of a certain kind of behavior habits, and the minimum granularity is the granularity of an individual.
6. The method of claim 1, wherein:
in step S4, behavior data is collected for a user using the software product in the guest identity, the collected data is processed and then sent to a trained neural network to determine the classification level of the user, and corresponding behavior data is communicated and stored in a behavior level database to perform big data analysis.
7. A data analysis system based on guest identity, characterized by: the method comprises a user behavior acquisition buried point and a level behavior database; wherein the content of the first and second substances,
the user behavior acquisition buried points are used for acquiring user use data and classifying the acquired data according to classification levels;
and the level behavior database is used for storing the classified user groups and corresponding behavior data so as to be used for the system to analyze big data.
8. The system of claim 7, wherein:
the user behavior collection buried point comprises a collection assembly and a data analysis assembly, the collection assembly comprises a network behavior script and a data formatting assembly, the network behavior script is used for collecting behavior data of a user, the data formatting assembly is used for carrying out standardized processing on the collected behavior data, the analysis assembly is built based on a neural network model, and the neural network model is put into use after being trained through a training sample.
9. The system of claim 8, wherein:
the training process of the neural network model of the analysis component comprises the following steps:
s1, collecting the use data of the user through the network behavior script;
s2, formatting the collected use data;
and S3, building a neural network model, taking the formatted use data as a training sample, and carrying out supervised training on the neural network model.
10. The system of claim 9, wherein: the user use data collected by the network behavior script comprises search records, mouse click records, mouse track records, user access page addresses in mouse staying areas, user access contents and staying time of users on a data terminal, the collected data are preprocessed, effective data are screened, and the collected data are subjected to standardized processing through a data formatting component.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110118157.4A CN112749990B (en) | 2021-01-28 | 2021-01-28 | Data analysis method and system based on tourist identity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110118157.4A CN112749990B (en) | 2021-01-28 | 2021-01-28 | Data analysis method and system based on tourist identity |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112749990A true CN112749990A (en) | 2021-05-04 |
| CN112749990B CN112749990B (en) | 2022-07-26 |
Family
ID=75653283
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110118157.4A Active CN112749990B (en) | 2021-01-28 | 2021-01-28 | Data analysis method and system based on tourist identity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112749990B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105005876A (en) * | 2015-08-13 | 2015-10-28 | 沈阳思哲数据技术有限公司 | Client behavior acquiring and analyzing system and the using method |
| CN110543474A (en) * | 2019-08-21 | 2019-12-06 | 河海大学 | User behavior analysis method and device based on full-buried point and potential factor model |
| CN110555170A (en) * | 2019-09-12 | 2019-12-10 | 山东爱城市网信息技术有限公司 | System and method for optimizing user experience |
-
2021
- 2021-01-28 CN CN202110118157.4A patent/CN112749990B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105005876A (en) * | 2015-08-13 | 2015-10-28 | 沈阳思哲数据技术有限公司 | Client behavior acquiring and analyzing system and the using method |
| CN110543474A (en) * | 2019-08-21 | 2019-12-06 | 河海大学 | User behavior analysis method and device based on full-buried point and potential factor model |
| CN110555170A (en) * | 2019-09-12 | 2019-12-10 | 山东爱城市网信息技术有限公司 | System and method for optimizing user experience |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112749990B (en) | 2022-07-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230013306A1 (en) | Sensitive Data Classification | |
| Baglioni et al. | Preprocessing and mining web log data for web personalization | |
| CN111191122A (en) | Learning resource recommendation system based on user portrait | |
| US8972397B2 (en) | Auto-detection of historical search context | |
| US20100211551A1 (en) | Method, system, and computer readable recording medium for filtering obscene contents | |
| CN103218431A (en) | System and method for identifying and automatically acquiring webpage information | |
| CN113011889B (en) | Account anomaly identification method, system, device, equipment and medium | |
| CN112329816A (en) | Data classification method and device, electronic equipment and readable storage medium | |
| CN114329455B (en) | User abnormal behavior detection method and device based on heterogeneous graph embedding | |
| CN111447575A (en) | Short message pushing method, device, equipment and storage medium | |
| CN111475365A (en) | Label type AB testing method and system based on cookie | |
| Martín-Guerrero et al. | Studying the feasibility of a recommender in a citizen web portal based on user modeling and clustering algorithms | |
| CN113420018A (en) | User behavior data analysis method, device, equipment and storage medium | |
| CN112966162A (en) | Scientific and technological resource integration method and device based on data warehouse and middleware | |
| EP3812925A1 (en) | Contribution information extraction control device and contribution information extraction control program | |
| CN112749990B (en) | Data analysis method and system based on tourist identity | |
| CN116318974A (en) | Site risk identification method and device, computer readable medium and electronic equipment | |
| CN116958622A (en) | Data classification method, device, equipment, medium and program product | |
| CN115062013A (en) | Information recommendation method, device, equipment and storage medium | |
| Bayat et al. | Estimation of Twitter user's nationality based on friends and followers information | |
| CN109885647B (en) | User history verification method, device, electronic equipment and storage medium | |
| Gopala Krishnan et al. | Predictive algorithm and criteria to perform big data analytics | |
| Sudhakar et al. | Web User Profile Generation and Discovery Analysis using LSTM Architecture | |
| CN111143653A (en) | Credibility verification method for mass science popularization resources | |
| CN110610378A (en) | Product demand analysis method and device, computer equipment and storage medium |
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 |