[go: up one dir, main page]

CN108363709A - Chart recommendation system and method based on user use principal component - Google Patents

Chart recommendation system and method based on user use principal component Download PDF

Info

Publication number
CN108363709A
CN108363709A CN201710428468.4A CN201710428468A CN108363709A CN 108363709 A CN108363709 A CN 108363709A CN 201710428468 A CN201710428468 A CN 201710428468A CN 108363709 A CN108363709 A CN 108363709A
Authority
CN
China
Prior art keywords
chart
user
factor
characterization factor
library
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Withdrawn
Application number
CN201710428468.4A
Other languages
Chinese (zh)
Inventor
吴建州
张恒
李勇波
季统凯
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
G Cloud Technology Co Ltd
Original Assignee
G Cloud Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by G Cloud Technology Co Ltd filed Critical G Cloud Technology Co Ltd
Priority to CN201710428468.4A priority Critical patent/CN108363709A/en
Publication of CN108363709A publication Critical patent/CN108363709A/en
Withdrawn legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/904—Browsing; Visualisation therefor

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention relates to the technical field of data analysis visualization, in particular to a chart recommendation system and method based on user use principal components. The characteristic factor extraction module extracts characteristic factors by analyzing the report data characteristics, matches the characteristic factors with a characteristic factor library, and calculates importance degrees according to the characteristic factor word frequency; the chart scoring recommendation module matches the characteristic factors with a user historical algorithm factor library, calculates the score of the chart characteristic factors, adds the scores of the characteristic factors of the same chart to calculate the final score of the chart, evaluates the chart and recommends the chart to a user; the user historical algorithm factor learning module is used for collecting the historical records of the user selection chart, performing characteristic factor analysis, keyword processing and characteristic factor user score calculation, and continuously perfecting the characteristic factor library and the user historical algorithm factor library. The method can automatically match the user historical algorithm factor library to calculate the chart score, recommend a proper chart, and is suitable for intelligent recommendation of chart selection in data analysis visualization.

Description

一种基于用户使用主成分的图表推荐系统及方法A chart recommendation system and method based on principal components used by users

技术领域technical field

本发明涉及数据分析可视化技术领域，特别是一种基于用户使用主成分的图表推荐系统及方法。The invention relates to the technical field of data analysis and visualization, in particular to a chart recommendation system and method based on principal components used by users.

背景技术Background technique

数据可视化将数据转换成适当的可视化图表，将隐藏在数据中的信息直接展现于人们面前，使数据更加客观、更具说服力。但是可视化图表种类繁多，不同类型的图表满足不同的展示和分析需求。用户在不熟悉这些图表的情况下，很难选择一种合适的图表去展现数据。用户使用图表的业务场景有很多相似之处，用户的历史选择图表记录中包含了使用习惯、业务习惯和数据特征等重要信息，但这些信息未得到充分利用，导致同样的业务数据需要做重复的分析和图表选择。Data visualization converts data into appropriate visual charts, and directly presents the information hidden in the data to people, making the data more objective and convincing. However, there are many types of visual charts, and different types of charts meet different display and analysis requirements. When users are not familiar with these charts, it is difficult to choose a suitable chart to display data. There are many similarities in the business scenarios in which users use charts. The user's historical selection chart records contain important information such as usage habits, business habits, and data characteristics, but this information has not been fully utilized, resulting in the need to repeat the same business data Analysis and chart selection.

发明内容Contents of the invention

本发明解决的技术问题之一在于提供一种基于用户使用主成分的图表推荐系统；可以自动匹配用户历史算法因子库计算图表评分，推荐合适的图表，降低数据可视化的使用门槛，提升用户体验。One of the technical problems solved by the present invention is to provide a chart recommendation system based on the principal components used by users; it can automatically match the user's historical algorithm factor library to calculate chart scores, recommend suitable charts, lower the threshold for using data visualization, and improve user experience.

本发明解决的技术问题之二在于提供一种基于用户使用主成分的图表推荐系统的实现方法。The second technical problem solved by the present invention is to provide a method for realizing a chart recommendation system based on principal components used by users.

本发明解决上述技术问题之一的技术方案是：The technical scheme that the present invention solves one of above-mentioned technical problem is:

所述的方法由特征因子提取模块、图表评分推荐模块和用户历史算法因子学习模块三部份组成；The method is composed of three parts: feature factor extraction module, chart score recommendation module and user history algorithm factor learning module;

所述的特征因子提取模块用于通过分析报表数据维度和度量属性、数字分布规律、数字趋势、时间和地理序列提取特征因子，将特征因子与特征因子库进行匹配，根据特征因子词频计算重要度；The feature factor extraction module is used to extract feature factors by analyzing report data dimensions and measurement attributes, digital distribution rules, digital trends, time and geographical sequences, match feature factors with feature factor libraries, and calculate importance according to feature factor word frequency ;

所述的图表评分推荐模块将特征因子与用户历史算法因子库进行匹配，将特征因子重要度与用户历史评分相乘计算图表特征因子评分，将同一种图表的特征因子评分相加计算图表最终评分，评价图表并推荐给用户；The chart score recommendation module matches the feature factor with the user history algorithm factor library, multiplies the feature factor importance with the user history score to calculate the chart feature factor score, and adds the feature factor scores of the same chart to calculate the final score of the chart , evaluate the graph and recommend it to the user;

所述的用户历史算法因子学习模块通过汇总特征因子生成特征因子集，使用关键词提取算法生成特征因子文章及关键词，更新特征因子库；用户选择图表展示报表后，将图表、特征因子及重要度添加到用户选择图表历史记录中，解析用户历史使用图表记录，使用加权几何平均算法计算用户评分并累积评分次数，更新用户历史算法因子库。The user history algorithm factor learning module generates a feature factor set by summarizing feature factors, uses a keyword extraction algorithm to generate feature factor articles and keywords, and updates the feature factor library; after the user selects a chart to display a report, the chart, feature factor and important Add the degree to the user's selection chart history, analyze the user's historical usage chart record, use the weighted geometric mean algorithm to calculate the user's score and accumulate the number of scores, and update the user history algorithm factor library.

所述的系统由特征因子提取模块、图表评分推荐模块和用户历史算法因子学习模块组成；The system is composed of a feature factor extraction module, a graph score recommendation module and a user history algorithm factor learning module;

特征因子提取模块，分析报表数据特征提取特征因子，将特征因子与特征因子库进行匹配，根据特征因子词频计算重要度；The feature factor extraction module analyzes the report data features to extract feature factors, matches the feature factors with the feature factor library, and calculates the importance according to the feature factor word frequency;

图表评分推荐模块，将特征因子与用户历史算法因子库进行匹配，计算图表特征因子评分，将同一种图表的特征因子评分相加计算图表的最终评分，评价图表并推荐给用户；The chart score recommendation module matches the feature factor with the user's historical algorithm factor library, calculates the chart feature factor score, adds the feature factor scores of the same chart to calculate the final score of the chart, evaluates the chart and recommends it to the user;

用户历史算法因子学习模块，收集用户选择图表的历史记录，进行特征因子分析、关键词处理和特征因子用户评分计算，不断完善特征因子库和用户历史算法因子库，不断提高图表匹配精确度。The user historical algorithm factor learning module collects historical records of user selection charts, performs feature factor analysis, keyword processing, and feature factor user score calculation, continuously improves the feature factor library and user history algorithm factor library, and continuously improves the accuracy of chart matching.

所述的特征因子提取模块，通过分析报表数据维度和度量属性、数字分布规律、数字趋势、时间和地理序列提取特征因子，将特征因子与特征因子库进行匹配，根据特征因子词频计算重要度。The feature factor extraction module extracts feature factors by analyzing report data dimensions and measurement attributes, digital distribution rules, digital trends, time and geographical sequences, matches feature factors with feature factor databases, and calculates importance according to feature factor word frequency.

所述的图表评分推荐模块，将特征因子重要度与用户历史评分相乘计算图表特征因子评分。The chart score recommendation module calculates the chart feature factor score by multiplying the feature factor importance with the user's historical score.

所述的用户历史算法因子学习模块，汇总特征因子生成特征因子集，使用关键词提取算法生成特征因子文章及关键词，更新特征因子库；用户选择图表展示报表后，将图表、特征因子及重要度添加到用户选择图表历史记录中，解析用户历史使用图表记录，使用加权几何平均算法计算用户评分并累积评分次数，更新用户历史算法因子库。The user history algorithm factor learning module summarizes feature factors to generate feature factor sets, uses keyword extraction algorithms to generate feature factor articles and keywords, and updates feature factor libraries; after the user selects a chart to display a report, the chart, feature factors and important Add the degree to the user's selection chart history, analyze the user's historical usage chart record, use the weighted geometric mean algorithm to calculate the user's score and accumulate the number of scores, and update the user history algorithm factor library.

本发明解决上述技术问题之二的技术方案是：The technical scheme that the present invention solves above-mentioned technical problem two is:

所述的方法具体步骤如下：The specific steps of the method are as follows:

第一步，通过分析报表数据维度和度量属性、数字分布规律、数字趋势、时间和地理序列提取特征因子；The first step is to extract characteristic factors by analyzing report data dimensions and measurement attributes, digital distribution rules, digital trends, time and geographical sequences;

第二步，将特征因子与特征因子库进行匹配，根据特征因子词频计算重要度；The second step is to match the feature factor with the feature factor library, and calculate the importance according to the feature factor word frequency;

第三步，将特征因子与用户历史算法因子库匹配，将特征因子重要度与用户历史评分相乘计算图表特征因子评分，将同一种图表的特征因子评分相加计算图表最终评分；The third step is to match the feature factor with the user's historical algorithm factor library, multiply the feature factor importance with the user's historical score to calculate the chart feature factor score, and add the feature factor scores of the same chart to calculate the final score of the chart;

第四步，评价图表的最终评分，将图表推荐给用户；The fourth step is to evaluate the final score of the chart and recommend the chart to the user;

第五步，汇总特征因子生成特征因子集，使用关键词提取算法生成特征因子文章及关键词，更新特征因子库；The fifth step is to summarize the characteristic factors to generate a characteristic factor set, use the keyword extraction algorithm to generate characteristic factor articles and keywords, and update the characteristic factor library;

第六步，将用户选择的图表、特征因子及重要度添加到用户选择图表历史记录中；The sixth step is to add the chart, feature factor and importance selected by the user to the historical record of the chart selected by the user;

第七步，解析用户历史使用图表记录，使用加权几何平均算法重新计算用户评分并累积评分次数，更新用户历史算法因子库。The seventh step is to analyze the user's historical use chart records, use the weighted geometric mean algorithm to recalculate the user ratings and accumulate the number of ratings, and update the user history algorithm factor database.

本发明的有益效果是：The beneficial effects of the present invention are:

根据报表数据的特征因子，自动匹配用户历史算法因子库计算图表评分，推荐合适的图表，降低了数据可视化的使用门槛。According to the characteristic factors of the report data, it automatically matches the user's historical algorithm factor library to calculate the chart score, recommends suitable charts, and lowers the threshold for using data visualization.

根据用户选择可视化图表的历史记录，自动学习不断完善用户历史算法因子库，不断提高推荐图表准确率，提升了用户体验。According to the historical record of the user's selection of visual charts, automatic learning and continuous improvement of the user's historical algorithm factor library, continuous improvement of the accuracy of recommended charts, and improved user experience.

附图说明Description of drawings

下面结合附图对本发明进一步说明：Below in conjunction with accompanying drawing, the present invention is further described:

图1是本发明的架构示意图；Fig. 1 is a schematic diagram of the architecture of the present invention;

图2是本发明特征因子与重要度的示例；Fig. 2 is the example of feature factor and degree of importance of the present invention;

图3是本发明推荐算法因子库中用户评分与评分次数的计算示例；Fig. 3 is the calculation example of user rating and rating times in the recommendation algorithm factor storehouse of the present invention;

图4是本发明图表推荐分值的计算示例。Fig. 4 is a calculation example of chart recommendation scores in the present invention.

具体实施方式Detailed ways

如图1所示，本发明的基于用户使用主成分的图表推荐方法由特征因子提取模块、图表评分推荐模块和用户历史算法因子学习模块三部份组成；特征因子提取模块通过分析报表数据特征提取特征因子，将特征因子与特征因子库进行匹配，根据特征因子词频计算重要度；图表评分推荐模块将特征因子与用户历史算法因子库进行匹配，计算图表特征因子评分，将同一种图表的特征因子评分相加计算图表的最终评分，评价图表并推荐给用户；用户历史算法因子学习模块用于收集用户选择图表的历史记录，进行特征因子分析、关键词处理和特征因子用户评分计算，不断完善特征因子库和用户历史算法因子库，不断提高图表匹配精确度。As shown in Figure 1, the chart recommendation method based on the user's principal component of the present invention is composed of three parts: a feature factor extraction module, a chart score recommendation module, and a user history algorithm factor learning module; the feature factor extraction module is extracted by analyzing report data features Feature factor, match the feature factor with the feature factor library, and calculate the importance according to the feature factor word frequency; the chart score recommendation module matches the feature factor with the user's historical algorithm factor library, calculates the chart feature factor score, and compares the feature factors of the same chart Scores are added to calculate the final score of the chart, evaluate the chart and recommend it to the user; the user history algorithm factor learning module is used to collect the historical records of the user's selection of the chart, perform feature factor analysis, keyword processing and feature factor user score calculation, and continuously improve features The factor library and the user historical algorithm factor library continuously improve the accuracy of chart matching.

特征因子提取模块用于通过分析报表数据维度和度量属性、数字分布规律、数字趋势、时间和地理序列提取特征因子，将特征因子与特征因子库进行匹配，根据特征因子词频计算重要度；The feature factor extraction module is used to extract feature factors by analyzing report data dimensions and measurement attributes, digital distribution rules, digital trends, time and geographical sequences, match feature factors with feature factor databases, and calculate importance according to feature factor word frequency;

图表评分推荐模块将特征因子与用户历史算法因子库进行匹配，将特征因子重要度与用户历史评分相乘计算图表特征因子评分，将同一种图表的特征因子评分相加计算图表最终评分，评价图表并推荐给用户；The chart score recommendation module matches the feature factor with the user's historical algorithm factor library, multiplies the feature factor importance with the user's historical score to calculate the chart feature factor score, and adds the feature factor scores of the same chart to calculate the final score of the chart and evaluate the chart and recommended to users;

用户历史算法因子学习模块通过汇总特征因子生成特征因子集，使用关键词提取算法生成特征因子文章及关键词，更新特征因子库；用户选择图表展示报表后，将图表、特征因子及重要度添加到用户选择图表历史记录中，解析用户历史使用图表记录，使用加权几何平均算法计算用户评分并累积评分次数，更新用户历史算法因子库。The user history algorithm factor learning module generates feature factor sets by summarizing feature factors, uses keyword extraction algorithms to generate feature factor articles and keywords, and updates the feature factor library; after the user selects a chart to display the report, add the chart, feature factor and importance to In the user selection chart history record, analyze the user history use chart record, use the weighted geometric mean algorithm to calculate the user score and accumulate the number of scores, and update the user history algorithm factor library.

在图2中，提取特征因子过程，通过分析报表数据维度和度量属性、数字分布规律、数字趋势、时间和地理序列提取特征因子；根据特征因子库中因子词频，计算特征因子重要度。In Figure 2, the process of extracting feature factors is to extract feature factors by analyzing report data dimensions and measurement attributes, digital distribution rules, digital trends, time and geographical sequences; according to the factor word frequency in the feature factor database, the feature factor importance is calculated.

在图3中，推荐算法因子库学习过程，使用加权几何平均算法计算用户历史评分并累积评分次数。In Figure 3, the recommendation algorithm factor library learning process uses the weighted geometric mean algorithm to calculate the user's historical score and accumulate the number of scores.

在图4中，图表推荐分值计算过程，将特征因子重要度与用户历史评分相乘计算图表特征因子评分，将同一种图表的特征因子评分相加计算图表最终评分。In Figure 4, the chart recommendation score calculation process is to multiply the feature factor importance with the user's historical score to calculate the chart feature factor score, and add the feature factor scores of the same chart to calculate the final score of the chart.

如图1所示，基于用户使用主成分的图表推荐方法的详细实施流程为：As shown in Figure 1, the detailed implementation process of the chart recommendation method based on the user's use of principal components is as follows:

第一步，通过分析报表数据维度和度量属性、数字分布规律、数字趋势、时间和地理序列提取特征因子；The first step is to extract characteristic factors by analyzing report data dimensions and measurement attributes, digital distribution rules, digital trends, time and geographical sequences;

第二步，将特征因子与特征因子库进行匹配，根据特征因子词频计算重要度；The second step is to match the feature factor with the feature factor library, and calculate the importance according to the feature factor word frequency;

第三步，将特征因子与用户历史算法因子库匹配，将特征因子重要度与用户历史评分相乘计算图表特征因子评分，将同一种图表的特征因子评分相加计算图表最终评分；The third step is to match the feature factor with the user's historical algorithm factor library, multiply the feature factor importance with the user's historical score to calculate the chart feature factor score, and add the feature factor scores of the same chart to calculate the final score of the chart;

第四步，评价图表的最终评分，将图表推荐给用户；The fourth step is to evaluate the final score of the chart and recommend the chart to the user;

第五步，汇总特征因子生成特征因子集，使用关键词提取算法生成特征因子文章及关键词，更新特征因子库；The fifth step is to summarize the characteristic factors to generate a characteristic factor set, use the keyword extraction algorithm to generate characteristic factor articles and keywords, and update the characteristic factor library;

第六步，将用户选择的图表、特征因子及重要度添加到用户选择图表历史记录中；The sixth step is to add the chart, feature factor and importance selected by the user to the historical record of the chart selected by the user;

第七步，解析用户历史使用图表记录，使用加权几何平均算法重新计算用户评分并累积评分次数，更新用户历史算法因子库。The seventh step is to analyze the user's historical use chart records, use the weighted geometric mean algorithm to recalculate the user ratings and accumulate the number of ratings, and update the user history algorithm factor database.

Claims (6)

1. a kind of chart commending system using principal component based on user, it is characterised in that：The system is carried by characterization factor Modulus block, chart scoring recommending module and user's history algorithm factor study module composition；
Characterization factor extraction module, analytical statement data characteristics extract characterization factor, and characterization factor and characterization factor library are carried out Matching calculates importance according to characterization factor word frequency；
Chart scoring recommending module, characterization factor is matched with user's history algorithm factor library, calculation chart characterization factor Scoring, the final scoring for addition calculation chart that the characterization factor of same chart is scored, judgement schematics simultaneously recommend user；
User's history algorithm factor study module collects the historical record that user selects chart, carries out characterization factor analysis, key Word processing and characterization factor user, which score, to be calculated, and constantly improve characterization factor library and user's history algorithm factor library are continuously improved Chart matches accuracy.
2. chart commending system according to claim 1, it is characterised in that：The characterization factor extraction module, passes through Analytical statement data dimension and metric attribute, digital distribution rule, digital trend, time and geographic series extract characterization factor, Characterization factor is matched with characterization factor library, importance is calculated according to characterization factor word frequency.
3. chart commending system according to claim 1, it is characterised in that：The chart scoring recommending module, will be special The sign factor importance and user's history scoring calculation chart characterization factor that is multiplied scores.
4. chart commending system according to claim 2, it is characterised in that：The chart scoring recommending module, will be special The sign factor importance and user's history scoring calculation chart characterization factor that is multiplied scores.
5. chart commending system according to any one of claims 1 to 4, it is characterised in that：The user's history algorithm Factor study module, summarize characterization factor generate characterization factor collection, using keyword extraction algorithm generate characterization factor article and Keyword, update characterization factor library；After user selects diagrammatic representation report, chart, characterization factor and importance are added to use Family selects in chart historical record, and parsing user's history uses chart recording, and calculating user using weighted geometric mean algorithm comments Divide and accumulate scoring number, update user's history algorithm factor library.
6. a kind of implementation method of chart commending system according to any one of claims 1 to 5, it is characterised in that：It is described Method be as follows：
The first step passes through analytical statement data dimension and metric attribute, digital distribution rule, digital trend, time and geographical sequence Row extraction characterization factor；
Second step matches characterization factor with characterization factor library, and importance is calculated according to characterization factor word frequency；
Third walks, and characterization factor and user's history algorithm factor storehouse matching score characterization factor importance and user's history Multiplication calculation chart characterization factor scores, and the characterization factor scoring addition calculation chart of same chart is finally scored；
4th step, the final scoring of judgement schematics, user is recommended by chart；
5th step, summarizes characterization factor and generates characterization factor collection, and characterization factor article and pass are generated using keyword extraction algorithm Keyword, update characterization factor library；
Chart, characterization factor and importance that user selects are added to user and selected in chart historical record by the 6th step；
7th step, parsing user's history use chart recording, recalculate user using weighted geometric mean algorithm and score and tire out Product scoring number, update user's history algorithm factor library.
CN201710428468.4A 2017-06-08 2017-06-08 Chart recommendation system and method based on user use principal component Withdrawn CN108363709A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710428468.4A CN108363709A (en) 2017-06-08 2017-06-08 Chart recommendation system and method based on user use principal component

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710428468.4A CN108363709A (en) 2017-06-08 2017-06-08 Chart recommendation system and method based on user use principal component

Publications (1)

Publication Number Publication Date
CN108363709A true CN108363709A (en) 2018-08-03

Family

ID=63010110

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710428468.4A Withdrawn CN108363709A (en) 2017-06-08 2017-06-08 Chart recommendation system and method based on user use principal component

Country Status (1)

Country Link
CN (1) CN108363709A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110134731A (en) * 2019-04-26 2019-08-16 深圳壹账通智能科技有限公司 Data presentation method, device, computer equipment and storage medium
CN111128376A (en) * 2019-11-21 2020-05-08 泰康保险集团股份有限公司 Method and device for recommending evaluation form
CN111476030A (en) * 2020-05-08 2020-07-31 中国科学院计算机网络信息中心 Prospective factor screening method based on deep learning
CN117931776A (en) * 2024-03-21 2024-04-26 广东琴智科技研究院有限公司 Big data storage analysis system platform and method based on virtualization technology

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102937970A (en) * 2011-10-13 2013-02-20 微软公司 Replace data mapping of a suggested chart
CN102968436A (en) * 2011-09-26 2013-03-13 微软公司 Chart recommendations
US20160292197A1 (en) * 2015-03-31 2016-10-06 Ubic, Inc. Data analysis system, data analysis method, data analysis program, and storage medium
CN106127506A (en) * 2016-06-13 2016-11-16 浙江大学 A kind of recommendation method solving commodity cold start-up problem based on Active Learning

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102968436A (en) * 2011-09-26 2013-03-13 微软公司 Chart recommendations
CN102937970A (en) * 2011-10-13 2013-02-20 微软公司 Replace data mapping of a suggested chart
US20160292197A1 (en) * 2015-03-31 2016-10-06 Ubic, Inc. Data analysis system, data analysis method, data analysis program, and storage medium
US20170097983A1 (en) * 2015-03-31 2017-04-06 Ubic, Inc. Data analysis system, data analysis method, data analysis program, and storage medium
CN106127506A (en) * 2016-06-13 2016-11-16 浙江大学 A kind of recommendation method solving commodity cold start-up problem based on Active Learning

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
李超亚: "基于领域特定语言的智能数据可视化引擎", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110134731A (en) * 2019-04-26 2019-08-16 深圳壹账通智能科技有限公司 Data presentation method, device, computer equipment and storage medium
CN111128376A (en) * 2019-11-21 2020-05-08 泰康保险集团股份有限公司 Method and device for recommending evaluation form
CN111128376B (en) * 2019-11-21 2023-06-16 泰康保险集团股份有限公司 Method and device for recommending evaluation form
CN111476030A (en) * 2020-05-08 2020-07-31 中国科学院计算机网络信息中心 Prospective factor screening method based on deep learning
CN117931776A (en) * 2024-03-21 2024-04-26 广东琴智科技研究院有限公司 Big data storage analysis system platform and method based on virtualization technology
CN117931776B (en) * 2024-03-21 2024-06-07 广东琴智科技研究院有限公司 Big data storage analysis system platform and method based on virtualization technology

Similar Documents

Publication Publication Date Title
CN107944913B (en) High-potential user purchase intention prediction method based on big data user behavior analysis
CN106485562B (en) Commodity information recommendation method and system based on user historical behaviors
CN103605815B (en) A kind of merchandise news being applicable to B2B E-commerce platform is classified recommendation method automatically
CN105868310B (en) Data processing method and device and electronic equipment
CN104462383B (en) A kind of film based on a variety of behavior feedbacks of user recommends method
CN108491377A (en) A kind of electric business product comprehensive score method based on multi-dimension information fusion
CN103914783A (en) E-commerce website recommending method based on similarity of users
CN103207914B (en) The preference vector evaluated based on user feedback generates method and system
CN105389713A (en) Mobile data traffic package recommendation algorithm based on user historical data
CN106339502A (en) Modeling recommendation method based on user behavior data fragmentation cluster
CN107220365A (en) Accurate commending system and method based on collaborative filtering and correlation rule parallel processing
CN113407729A (en) Judicial-oriented personalized case recommendation method and system
CN108363709A (en) Chart recommendation system and method based on user use principal component
CN108334592A (en) A kind of personalized recommendation method being combined with collaborative filtering based on content
CN108388660A (en) A kind of improved electric business product pain spot analysis method
US10387805B2 (en) System and method for ranking news feeds
CN111339439A (en) Collaborative filtering recommendation method and device fusing comment text and time sequence effect
CN104615741B (en) Cold-start project recommendation method and device based on cloud computing
CN107193883B (en) Data processing method and system
CN114861079B (en) A collaborative filtering recommendation method and system integrating product features
CN110110220B (en) A recommendation model that integrates social networks and user evaluations
CN117745349B (en) A personalized coupon recommendation method and system based on user characteristics
CN105023178A (en) Main body-based electronic commercere commendation method
CN109508407A (en) The tv product recommended method of time of fusion and Interest Similarity
CN118657592A (en) A personalized recommendation method and system for corporate financial products based on preference analysis

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
WW01 Invention patent application withdrawn after publication

Application publication date: 20180803