Shulou(Shulou.com)06/01 Report--

This article is about how to accurately manage data based on smart tags on the Internet. The editor thinks it is very practical, so share it with you as a reference and follow the editor to have a look.

First, scene analysis 1. Scene case

Friends in the Internet industry must have known or heard of the following scenarios:

Ali: thousands of people thousand faces, meaning that different users use Ali-related products feel different, such as Alipay home page recommendation content, and other relevant recommendation stream information is completely different.

Tencent: social advertising, advertising information in different users' moments or other media scenarios is different and will be recommended based on user characteristics.

Headline: information value, according to the user browsing information, analyze the user's relevant preferences, recommend the relevant information flow according to the analysis results, the more attention to a certain type of content, the more relevant information is obtained.

For example, the logic of the above scenarios is: based on the continuous analysis of the user's behavior, generate the user's feature portrait, and then customize the relevant content based on the user tag.

2. Basic concepts

From the above scenario, two concepts are derived:

User portrait

User profile, as an effective tool to outline the target user and contact the user demand and design direction, forms the user profile by visualizing the data associated with the user. User portrait has been widely used in various fields, and it was initially applied in the field of e-commerce. Under the background of big data era, user information is flooded in the network, abstracting each specific information of users into tags, and using these tags to specify the image of users, so as to provide targeted services for users.

Label data

Tags are very common in daily life, such as product labels, personal labels, industry labels, such as 996 when you think of programmers, and plaid shirts when you mention programmers.

Tags integrate scattered multi-party data into a unified technical platform, standardize and subdivide these data, and carry out structured storage and update management. so that the line of business can push these subdivision results to the platform in the existing interactive marketing environment to generate value. these data are called tag data, which is often called tag library. The concept of data label is also hot in the development of big data in recent years.

Label value

The basis of fine operation, effectively improve the accuracy and efficiency of traffic.

Help the product quickly locate the people who need it and carry out accurate marketing

It can help customers cut into the market cycle faster.

Make in-depth prediction and analysis of customers and make timely response

Development of Intelligent recommendation system based on tag

Insight into industry characteristics based on the analysis of certain types of users

The core value of tags, or the most commonly used scenarios: real-time intelligent recommendation, accurate digital marketing.

Second, data label 1, label division

Attribute tag

Attribute tags change the least, for example, after the user's real name authentication, obtain relevant tags based on identity information: gender, birthday, date of birth, age, and other related tags. The frequency of change is small, and it is the most accurate.

Behavior label

Behavior tags are obtained by users through a series of operations on the product, based on behavior log analysis, such as purchasing power, consumption hobbies, seasonal consumption tags and so on. On the APP of information flow, through the relevant browsing behavior, constantly recommending the content that users are interested in is based on this logic.

Rule label

Configure specified rules according to the requirements of the business scenario, and generate analysis results based on the rules, for example:

Active users for nearly 7 days: users who log in every day for nearly 7 days are generated as rules

Lost users: without any operation within six months, you can issue high discount coupons

Potential users: use or generate browsing data, but no transaction occurs

Such tags can be based on dynamic rule configuration, after calculation and analysis, generate description results, that is, rule tags.

Fit label

The tags of the fitting class are the most complex, through the above tags, intelligent combination analysis, the predicted value given, such as: unmarried, browsing the relevant wedding content, through the analysis to predict that the user will hold a wedding, get a fitting result: predict that you will get married. This prediction logic can also be performed in reverse, with users buying baby products: predicting married childbearing.

This is a common saying in the data age: after a user operates on an application, the result of algorithm analysis may be more true than the user's description of himself.

2. Label processing process

data acquisition

There are relatively many channels for data collection, such as various business lines within the same APP: shopping, payment, financial management, takeout, information browsing and so on. It is transmitted to a unified data aggregation platform through data channels. Only with the support of these massive log data can we have the basic conditions of data analysis. Whether it is data intelligence, deep learning, algorithms and so on are based on the basic conditions of massive data, so that valuable analysis results can be obtained.

Data processing

Combined with the above business, through the processing, analysis and extraction of massive data to obtain relatively accurate user tags, there is also a key step, that is, the existing user tags are constantly verified and repaired. especially the related tags of rule class and fit class.

Tag library

Through the tag library, manage complex tag results, in addition to complex tags, and timeline-based tag changes, label data here, has been of considerable value, you can open some fee-based services around the tag library, such as common, users browse certain goods in an e-commerce APP, you can see product recommendations on a certain information flow platform. The era of big data is so intelligent and suffocating.

Label service

After a large circle of data is converted into labels, it is natural to return to the business level. Through the analysis of the users of the label data, we can carry out related operations such as accurate marketing and intelligent recommendation, and the trading volume can be increased in e-commerce applications. Information flow can better attract users.

Application layer

Develop the above services into services, integrate them into the application level, constantly improve the quality of application services, attract users and provide services. Of course, the user's data is constantly generated at the application level, and a complete closed-loop process is finally formed when it is transferred to the data acquisition service.

3. Application case

From the process and business level description is simple, to the development level will become complex and difficult to deal with, which may be the gap between product and development.

Data type of the label

The analysis results of different tags need to be described by different data types. in the label system, the data types commonly used to describe tags are as follows: enumeration, numerical value, date, Boolean, text type. Different types require different analysis processes.

Goods and labels

A basic case is provided here, which uses the label of the commodity to analyze the goods, such as the origin, price, status and other conditions of the goods, to find out how many qualified goods are in the product library.

Data table design

Mainly divided into four tables: label classification, tag library, tag value, label data.

CREATE TABLE `ID', INT (11) NOT NULL AUTO_INCREMENT COMMENT 'primary key ID', `catalog_ name` VARCHAR (50) NOT NULL DEFAULT' 'COMMENT' name', `create_ datetime NOT NULL DEFAULT CURRENT_TIMESTAMP COMMENT 'creation time', `update_ time`datetime DEFAULT NULL COMMENT 'update time', `state`INT (1) DEFAULT'1' COMMENT 'status 1 enabled, 2 disabled' PRIMARY KEY (`id`) ENGINE = INNODB DEFAULT CHARSET = utf8 COMMENT = 'tag level directory' CREATE TABLE `tc_tag_ cloud` (`id`INT (11) NOT NULL AUTO_INCREMENT COMMENT 'primary key ID', `tag_ id` INT (11) NOT NULL COMMENT' directory ID', `tag_ name` VARCHAR''COMMENT' tag name', `tag_ code` INT (11) DEFAULT NULL COMMENT 'tag coding', `bind_ column`VARCHAR 'DEFAULT' 'COMMENT' bound data column', `data_ type` INT (2) NOT NULL COMMENT'1 enumeration, 2 numeric values, 3 dates 4 Boolean, 5 value type', 'create_ time` datetime NOT NULL DEFAULT CURRENT_TIMESTAMP COMMENT' creation time', `update_ time` datetime DEFAULT NULL COMMENT 'update time', `remark` VARCHAR (150) DEFAULT NULL COMMENT 'remarks', `state` INT (1) DEFAULT'1' COMMENT 'status 1 enabled, 2 disabled', PRIMARY KEY (`id`) ENGINE = INNODB DEFAULT CHARSET = utf8 COMMENT = 'tag cloud' CREATE TABLE `tag_code_ index` (`tag_ code` INT (11) NOT NULL COMMENT 'tag coding', `data_ value` VARCHAR 'NOT NULL COMMENT' enumerated value', `create_ time`datetime NOT NULL DEFAULT CURRENT_TIMESTAMP COMMENT 'creation time', KEY `tag_code_ index` (`tag_ code`) ENGINE = INNODB DEFAULT CHARSET = utf8 COMMENT = 'tag enumerated value' CREATE TABLE `product_ INT (11) NOT NULL AUTO_INCREMENT COMMENT 'key ID', `product_ name` VARCHAR', `unit_ price` DECIMAL (10,2) DEFAULT '0.00' COMMENT' unit price, `is_ shelves`INT (1) whether DEFAULT'1' COMMENT'is on the shelves: 1 No, 2 Yes', `origin_ place` VARCHAR 'COMMENT' Origin' `Time`datetime NOT NULL DEFAULT CURRENT_TIMESTAMP COMMENT 'creation time', PRIMARY KEY (`id`) ENGINE = INNODB DEFAULT CHARSET = utf8 COMMENT = 'tag dataset'

Analog input interface

The parameters here should be dynamically selected and organized together based on requirements:

For example, the list of tag values given here in the picture is called enumerated values.

@ RestControllerpublic class AnalyzeController {@ Resource private TagDataSetService tagDataSetService; @ GetMapping ("/ analyze") public String analyze () {List tagParamList = new ArrayList (); TagParam tagParam1 = new TagParam (1, "origin", "origin_place"); List valueList1 = new ArrayList (); valueList1.add ("Shenzhen"); valueList1.add ("Guangdong"); tagParam1.setValueList (valueList1) TagParamList.add (tagParam1); TagParam tagParam2 = new TagParam (2, "price", "unit_price"); List valueList2 = new ArrayList (); valueList2.add ("1999"); tagParam2.setValueList (valueList2); tagParamList.add (tagParam2); TagParam tagParam3 = new TagParam (3, "date of production", "create_time"); List valueList3 = new ArrayList () ValueList3.add ("2020-05-01 13:43:54"); tagParam3.setValueList (valueList3); tagParamList.add (tagParam3); TagParam tagParam4 = new TagParam (4, "whether on the shelf", "is_shelves"); List valueList4 = new ArrayList (); valueList4.add ("1"); tagParam4.setValueList (valueList4); tagParamList.add (tagParam4) TagParam tagParam5 = new TagParam (5, "product name", "product_name"); List valueList5 = new ArrayList (); valueList5.add ("smart"); tagParam5.setValueList (valueList5); tagParamList.add (tagParam5); Integer count = tagDataSetService.analyze (tagParamList); return "Result:" + count;}}

Parameter parsing query

Through the analysis of the parameters, the SQL statement of the query is finally formed, and the accurate result data is obtained.

@ Servicepublic class TagDataSetServiceImpl extends ServiceImpl implements TagDataSetService {@ Resource private TagDataSetMapper tagDataSetMapper; @ Override public Integer analyze (List tagParamList) {StringBuffer querySQL = new StringBuffer (); for (TagParam tagParam:tagParamList) {querySQL.append ("AND"); querySQL.append (tagParam.getBindColumn ()) / / 1 enumeration, 2 numeric values, 3 dates, 4 Boolean, 5 value types List valueList = tagParam.getValueList (); switch (tagParam.getDataType ()) {case 1: querySQL.append ("IN ("); for (int I = 0; I)

< valueList.size() ;i++){ if (i != valueList.size()-1){ querySQL.append("'").append(valueList.get(i)).append("',"); } else { querySQL.append("'").append(valueList.get(i)).append("'"); } } querySQL.append(" )") ; break; case 2: querySQL.append("=").append(tagParam.getValueList().get(0)) ; break; case 3: querySQL.append(">

='") .append (tagParam.getValueList () .get (0)) .append ("'"); break; case 4: querySQL.append (" = ") .append (tagParam.getValueList () .get (0)); break Case 5: querySQL.append ("LIKE'%") .append (tagParam.getValueList () .get (0)) .append ("%'"); break; default: break }} / * final execution of SQL SELECT COUNT (*) FROM tc_tag_data_set WHERE 1 = 1 AND origin_place IN ('Shenzhen' 'Guangdong') AND unit_price = 1999 AND create_time > = '2020-05-01 13 Fringe 43 AND is_shelves = 1 AND product_name LIKE'% Smart%'* / String whereCondition = String.valueOf (querySQL) Return tagDataSetMapper.analyze (whereCondition);}}

Some people may say, isn't this just a query process? If there is such a doubt, replace the above case with a user query, the value of the tag data will be more intuitive.

Intelligent Portrait 1. Basic Concepts

User portrait

As an effective tool to outline the target user and contact the user demand and design direction, user profile has been widely used in various fields. At first, it was applied in the field of e-commerce, under the background of big data era, user information was flooded in the network, each specific information of users was abstracted into tags, and these tags were used to specify the image of users, so as to provide targeted services for users.

Industry portrait

Through the comprehensive analysis of industry attribute tags and user tags under the industry, industry analysis reports are generated to provide valuable guidance, which is a very popular application in the past two years.

Portrait completion

Through the continuous analysis of user data, enrich the tag library, make the user's portrait more rich and three-dimensional.

2. Portrait report

Through the analysis of tag data, an analysis report is generated, which contains rich user tag statistics.

For example: post-90s Portrait report

Internet users must have seen this report more or less. Mainly some label statistics, common label display, or which groups have the greatest impact on the post-90s values, sources of income, academic qualifications and other analysis and interpretation.

Thank you for reading! This is the end of this article on "how to accurately manage data based on smart tags on the Internet". I hope the above content can be of some help to you, so that you can learn more knowledge. If you think the article is good, you can share it for more people to see!

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.