WO2021134944A1 - Mobile news client-based evaluation method and system therefor - Google Patents
Mobile news client-based evaluation method and system therefor Download PDFInfo
- Publication number
- WO2021134944A1 WO2021134944A1 PCT/CN2020/082285 CN2020082285W WO2021134944A1 WO 2021134944 A1 WO2021134944 A1 WO 2021134944A1 CN 2020082285 W CN2020082285 W CN 2020082285W WO 2021134944 A1 WO2021134944 A1 WO 2021134944A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- content
- evaluation
- recommended
- news
- recommended content
- Prior art date
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims description 13
- 238000004519 manufacturing process Methods 0.000 claims description 11
- 238000013441 quality evaluation Methods 0.000 claims description 5
- 230000006399 behavior Effects 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000001303 quality assessment method Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 230000003997 social interaction Effects 0.000 description 1
Images
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
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Definitions
- the invention belongs to the field of Internet news information operation and service platforms, and specifically relates to an evaluation method and system based on a mobile news client.
- Content acquisition method create the same number of threads according to the number of news clients acquired, acquire the number of CPU cores of the system's central processing unit, and bind each thread to the corresponding CPU core according to preset rules; bind the same CPU core
- the data in all the preset analysis queues on the above is stored in the corresponding preset output queue.
- the data in the preset output queue is transferred to the preset database, so as to be based on the data in the preset database Realize the supervision of news client data.
- the evaluation indicators of the recommendation system generally come from multiple dimensions: user experience, algorithm accuracy, and business goals.
- the method of directly acquiring the column content of each news client makes it difficult for the recommendation system to evaluate the recommended content of each user;
- the purpose of the present invention is to propose an evaluation method and system based on mobile news clients, by acquiring personalized recommended content of the mobile news client, real-time analysis of recommended content, Dimensional evaluation of the credibility of recommended content.
- An evaluation method based on mobile news clients including:
- Step 1 Obtain recommended content: simulate a user portrait requesting data from the server, collect the pushed content returned by the server and store it in the database;
- Step 2 Evaluate the recommended content from the two dimensions of quality and timeliness;
- Step 3 Feedback the final result of the evaluation.
- step 1 the specific method of step 1 is as follows: firstly set user operation instructions in advance, including: refresh, read, and like, then simulate user operation instructions, and transmit them to the virtualized news client and news client via adb. According to the instruction, data is requested from the server by simulating a click, and the server returns the pushed personalized content to the news client. Finally, the hook server is used to obtain the recommended content from the news client and save the recommended content in the database.
- step 2 the specific method of content quality evaluation in step 2 is as follows: firstly perform bad content recognition: adopt the method of sequence labeling, construct a large number of training data for marking bad content vocabulary, and conduct model training; use the obtained recommendation data for training A good model makes predictions and judges whether it contains bad content words, if it does, extract and record it, if it does not, then perform "title party content” identification;
- the "Title Party” content recognition use a two-class model to construct a large amount of training data, and use the title and the article body as the model input. The title and the article are marked as 1, and the title and the article are not marked as 0 for classification. Model training; input the title and article text of the obtained recommendation data into the model to determine whether it is the content of "Title Party";
- timeliness index and quality index obtained in step 2 are calculated, and the average value is taken as the final result.
- the present invention also provides a system for implementing the above evaluation method, including a recommended content acquisition module, a content credibility evaluation module, and an evaluation result feedback module;
- the recommended content acquisition module includes: simulated user portrait data request module: simulates the user's browsing, clicking, and sharing behaviors to form a preset user portrait, and requests data from the news client to the server according to the preset user portrait;
- Server push module The server pushes personalized recommended news information content to the news client;
- Content collection module use hook server to obtain recommended content from news clients
- Data saving module save the collected content to the database
- Quality assessment module detect whether the recommended content contains bad content or "headline party" content.
- the present invention has the following beneficial effects:
- personalized recommended content acquisition from the mobile news client APP side can simulate real-time acquisition of content recommended by different users based on different user portraits;
- Fig. 1 is a schematic diagram of a data collection method of a news client in the prior art
- Figure 2 is a schematic diagram of the evaluation system of the mobile news client of the present invention.
- Figure 3 is a schematic diagram of a recommended content acquisition module in the evaluation system of the present invention.
- Fig. 5 is a flowchart of the content evaluation method in the evaluation method of the present invention.
- FIG. 1 a schematic diagram of a data collection method for news clients in the prior art.
- the same number of threads are created according to the number of news clients obtained, the number of cores of the central processing unit CPU of the system is obtained, and each of the The thread is bound to the corresponding CPU core; the data in all the preset analysis queues on the same CPU core is stored in the corresponding preset output queue, and the data in the preset output queue is transmitted when an output instruction is received In the preset database, in order to realize the supervision of the news client data based on the data in the preset database.
- This collection method is a way to directly obtain the column content of each news client, which makes it difficult to evaluate the recommended content of each user with respect to the recommendation system.
- the present invention provides an evaluation method based on a mobile news client, including:
- Step 1 Obtain recommended content: simulate a user portrait requesting data from the server, collect the pushed content returned by the server and store it in the database;
- Step 2 Evaluate the recommended content from the two dimensions of quality and timeliness;
- Step 3 Feedback the final result of the evaluation.
- the method for obtaining recommended content in the evaluation method of the present invention is specifically:
- set user operation instructions in advance including: refresh, read, and like
- simulate user operation instructions and transmit them to the virtualized news client through adb.
- the news client requests data from the server by simulating clicks according to the instructions, and the server Then return the pushed personalized content to the news client, and finally use the hook server to obtain the recommended content from the news client, and save the recommended content in the database.
- the "Title Party” content recognition use a two-class model to construct a large amount of training data, and use the title and the article body as the model input. The title and the article are marked as 1, and the title and the article are not marked as 0 for classification.
- Model training input the title and article text of the obtained recommendation data into the model to determine whether it is the content of "Title Party”; finally calculate the quality index of the content, the formula is:
- Q is the ratio of the number of recommended content detected that do not meet the content quality requirements at a certain moment in the total recommended number
- U is the total number of simulated different user portraits
- q i is the recommended content obtained from the user portrait of i is not meeting the content quality requirements
- All i is the total number of recommended content obtained by the portrait of user i.
- the recommended content production time is the number of recommendations in the last 72 hours accounting for the total recommended number, the production time for obtaining the recommended content, and the calculated production time is 72 hours.
- T is the ratio of the number of recommended content with a production time of 72 hours to the total recommended content
- U is the total number of simulated different user portraits
- t i is the number of recommended content obtained by user i that does not meet the timeliness requirements
- ALL i is the total number of recommended content obtained by the portrait of user i.
- step 3 the data obtained by simulating different user portraits at each moment are passed through the above-mentioned evaluation method to obtain the timeliness index and the quality index, and the average value is taken as the final result and fed back to the monitoring platform.
- the present invention also provides a system for realizing the above-mentioned evaluation and monitoring method based on news clients, including a recommended content acquisition module, a content credibility evaluation module, and an evaluation result feedback module;
- the recommended content acquisition module includes:
- Simulate user portrait data request module simulate the user's browsing, clicking, and sharing behaviors to form a preset user portrait, and request data from the news client to the server according to the preset user portrait;
- Server push module The server pushes personalized recommended news information content to the news client;
- Content collection module use hook server to obtain recommended content from news clients
- Data saving module save the collected content to the database
- the content credibility evaluation module includes:
- Timeliness evaluation module Evaluate the real-time performance of the recommendation system through the recommendation rate of news in the last n days, N ⁇ 3;
- Quality assessment module detect whether the recommended content contains bad content or "headline party" content.
- the news client-based evaluation method disclosed in the present invention collects personalized recommended content from the mobile news client APP side, which can simulate real-time collection of content recommended by different users according to different user portraits, and similar users ( The recommended content of users with similar user portraits does not need to be collected all, and it is more flexible.
- the scale of collected content can be freely controlled, and the scale of collected personalized content can be adjusted freely according to relevant rules; in terms of content evaluation, from timeliness and quality
- the dimensionality evaluates the credibility of the recommended content of news information, which can well reflect the real-time nature of news information and the quality of article content.
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Information Transfer Between Computers (AREA)
Abstract
Description
Claims (6)
- 一种基于移动新闻客户端的评估方法,包括:An evaluation method based on mobile news clients, including:步骤一:推荐内容的获取:模拟用户画像向服务器请求数据,采集服务器返回的推送内容并储存在数据库中;Step 1: Obtain recommended content: simulate a user portrait requesting data from the server, collect the pushed content returned by the server and store it in the database;步骤二:对推荐内容从内容质量评估和时效评估两个维度进行评估;Step 2: Evaluate the recommended content from two dimensions: content quality evaluation and timeliness evaluation;步骤三:反馈评估的最终结果。Step 3: Feedback the final result of the evaluation.
- 根据权利要求1所述的基于移动新闻客户端的评估方法,其特征在于,所述步骤一具体方法为:The evaluation method based on a mobile news client according to claim 1, wherein the specific method of step one is:首先预先设定好用户操作指令,包括:刷新、阅读、点赞,然后模拟用户操作指令,通过adb方式传输给虚拟化的新闻客户端,新闻客户端根据指令通过模拟点击向服务器请求数据,服务器则向新闻客户端返回推送的个性化内容,最后利用hook服务器从新闻客户端中获取推荐内容,并将推荐内容保存到数据库中。First, set user operation instructions in advance, including: refresh, read, and like, then simulate user operation instructions, and transmit them to the virtualized news client through adb. The news client requests data from the server by simulating clicks according to the instructions, and the server Then return the pushed personalized content to the news client, and finally use the hook server to obtain the recommended content from the news client, and save the recommended content in the database.
- 根据权利要求2所述新闻客户端的评估方法,其特征在于:所述步骤二中内容质量评估的具体方法为:The evaluation method of the news client according to claim 2, wherein the specific method of the content quality evaluation in the second step is:首先进行不良内容识别:采用序列标注的方法,构建大量标记不良内容词汇的训练数据,进行模型训练;将获取到的推荐数据使用训练好的模型进行预测,判断是否包含不良内容词语,若包含则提取并记录,若不包含,则进行“标题党内容”识别;First, perform bad content recognition: use sequence labeling to construct a large number of training data for marking bad content vocabulary, and perform model training; use the trained model to predict the obtained recommendation data to determine whether it contains bad content words, and if it does, Extract and record, if not included, identify the "title party content";所述“标题党”内容识别:采用二分类的模型,构建大量训练数据,将标题与文章正文共同作为模型输入,标题与文章相符的标记为1,标题与文章不符的标记为0,进行分类模型训练;将获取到的推荐数据的标题与文章正文输入到模型中,判断是否为“标题党”内容;The "Title Party" content recognition: use a two-class model to construct a large amount of training data, and use the title and the article body as the model input. The title and the article are marked as 1, and the title and the article are not marked as 0 for classification. Model training; input the title and article text of the obtained recommendation data into the model to determine whether it is the content of "Title Party";最后计算内容的质量指标,公式为:Finally, the quality index of the content is calculated, and the formula is:其中:Q为某时刻检测不符合内容质量要求的推荐内容数量占总推荐数量的比率,U为模拟不同用户画像的总数量,q i为i用户画像获取到推荐内容中为不符合内容质量要求的数量,ALL i为i用户画像获取到推荐内容的总数量。 Among them: Q is the ratio of the number of recommended content detected that do not meet the content quality requirements at a certain moment in the total recommended number, U is the total number of simulated different user portraits, and q i is the recommended content obtained from the user portrait of i is not meeting the content quality requirements All i is the total number of recommended content obtained by the portrait of user i.
- 根据权利要求2所述新闻客户端的评估方法,其特征在于,所述步骤二中时效评估的具体方法为:The evaluation method of the news client according to claim 2, wherein the specific method of the timeliness evaluation in the second step is:通过最近n天内容推荐率来评估***的实时性,取n=3,即推荐内容生产时间为最近72小时内的推荐数量占总推荐数量,获取推荐内容的生产时间,计算生产时间为72小时内的数据占比,公式为:Evaluate the real-time performance of the system by the content recommendation rate in the last n days, and take n=3, that is, the recommended content production time is the number of recommendations in the last 72 hours accounting for the total recommended number, the production time for obtaining the recommended content, and the calculated production time is 72 hours The proportion of data within, the formula is:其中,T为生产时间为72小时的推荐内容数量占总推荐内容的比率,U为模拟不同用户画像的总数量,t i为i用户画像获取到推荐内容中为不符合时效要求的数量,ALL i为i用户画像获取到推荐内容的总数量。 Among them, T is the ratio of the number of recommended content with a production time of 72 hours to the total recommended content, U is the total number of simulated different user portraits, t i is the number of recommended content obtained by user i that does not meet the timeliness requirements, ALL i is the total number of recommended content obtained by the portrait of user i.
- 根据权利要求2所述新闻客户端的评估方法,其特征在于,所述步骤三具体方法为:The method for evaluating news clients according to claim 2, wherein the specific method of step three is:计算步骤二中得到的时效指标和质量指标,取平均值作为最终结果。Calculate the timeliness index and quality index obtained in step two, and take the average value as the final result.
- 一种新闻客户端的评估***,其特征在于:包括推荐内容获取模块、内容可信度评估模块和评估结果反馈模块;An evaluation system for news clients, which is characterized in that it includes a recommended content acquisition module, a content credibility evaluation module, and an evaluation result feedback module;所述推荐内容获取模块包括:The recommended content acquisition module includes:模拟用户画像数据请求子模块:模拟用户进行浏览、点击、分享行为,形成预设的户画像,按照预设的用户画像从新闻客户端向服务器请求数据;Simulate user portrait data request sub-module: simulate the user's browsing, clicking, and sharing behaviors to form a preset user portrait, and request data from the news client to the server according to the preset user portrait;服务器推送子模块:服务器向新闻客户端推送个性化推荐的新闻信息内容;Server push sub-module: the server pushes personalized recommended news information content to the news client;内容采集子模块:利用hook服务器从新闻客户端中获取推荐内容;Content collection sub-module: use hook server to obtain recommended content from news clients;数据保存子模块:将采集到的内容保存到数据库中;Data saving sub-module: save the collected content to the database;所述内容可信度评估模块包括:The content credibility evaluation module includes:时效评估子模块:通过最近n天新闻推荐率来评估推荐***的实时性,N<=3;Timeliness evaluation sub-module: evaluate the real-time performance of the recommendation system through the recommendation rate of news in the last n days, N<=3;质量评估子模块:检测推荐内容中是否含有不良内容或“标题党”内容;Quality evaluation sub-module: detect whether the recommended content contains bad content or "headline party" content;所述评估结果反馈模块,将每个时刻模拟不同用户画像获取到的数据经过评估得到时效指标和质量指标,取平均值作为最终结果反馈给监控平台。The evaluation result feedback module evaluates the data obtained by simulating different user portraits at each moment to obtain the timeliness index and the quality index, and the average value is taken as the final result and fed back to the monitoring platform.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2020335019A AU2020335019B2 (en) | 2019-12-31 | 2020-03-31 | Evaluation method based on mobile news client and system thereof |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911409113.6A CN111143688B (en) | 2019-12-31 | 2019-12-31 | Evaluation method and system based on mobile news client |
CN201911409113.6 | 2019-12-31 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021134944A1 true WO2021134944A1 (en) | 2021-07-08 |
Family
ID=70522566
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2020/082285 WO2021134944A1 (en) | 2019-12-31 | 2020-03-31 | Mobile news client-based evaluation method and system therefor |
Country Status (3)
Country | Link |
---|---|
CN (1) | CN111143688B (en) |
AU (1) | AU2020335019B2 (en) |
WO (1) | WO2021134944A1 (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117291690B (en) * | 2023-11-23 | 2024-06-07 | 五五海淘(上海)科技股份有限公司 | Intelligent product sales recommendation method based on data analysis |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103365902A (en) * | 2012-03-31 | 2013-10-23 | 北大方正集团有限公司 | Method and device for evaluating Internet News |
US20140047118A1 (en) * | 2008-09-29 | 2014-02-13 | Amazon Technologies, Inc. | Optimizing resource configurations |
CN107818156A (en) * | 2017-10-31 | 2018-03-20 | 广东思域信息科技有限公司 | A kind of real time individual news recommends method and system |
CN107968842A (en) * | 2017-12-26 | 2018-04-27 | 百度在线网络技术(北京)有限公司 | News push method, apparatus and equipment based on distributed system |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20150046425A1 (en) * | 2013-08-06 | 2015-02-12 | Hsiu-Ping Lin | Methods and systems for searching software applications |
US9992690B2 (en) * | 2013-10-11 | 2018-06-05 | Textron Innovations, Inc. | Placed wireless instruments for predicting quality of service |
CN109684582A (en) * | 2018-11-08 | 2019-04-26 | 张耀伦 | A kind of evaluating system and method for information resources |
CN110413890A (en) * | 2019-07-29 | 2019-11-05 | 武汉匠楚科技有限公司 | A kind of method that news recommender system polymerization news is presented |
-
2019
- 2019-12-31 CN CN201911409113.6A patent/CN111143688B/en active Active
-
2020
- 2020-03-31 WO PCT/CN2020/082285 patent/WO2021134944A1/en active Application Filing
- 2020-03-31 AU AU2020335019A patent/AU2020335019B2/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140047118A1 (en) * | 2008-09-29 | 2014-02-13 | Amazon Technologies, Inc. | Optimizing resource configurations |
CN103365902A (en) * | 2012-03-31 | 2013-10-23 | 北大方正集团有限公司 | Method and device for evaluating Internet News |
CN107818156A (en) * | 2017-10-31 | 2018-03-20 | 广东思域信息科技有限公司 | A kind of real time individual news recommends method and system |
CN107968842A (en) * | 2017-12-26 | 2018-04-27 | 百度在线网络技术(北京)有限公司 | News push method, apparatus and equipment based on distributed system |
Non-Patent Citations (3)
Title |
---|
CHEN, MING: "Study and Implementation of Microblog Oriented Text Quality Evaluation and Classification", CHINESE MASTER’S THESES FULL-TEXT DATABASE, 1 November 2015 (2015-11-01), pages 1 - 68, XP055826746 * |
HONG XIA: "The Research on Data Quality Analysis and Evaluation of Information System and the Application in Labor Mraket", CHINESE MASTER’S THESES FULL-TEXT DATABASE, 1 February 2009 (2009-02-01), pages 1 - 72, XP055826018 * |
LIU JIN-HUI;CUI XIANG-YANG;YANG FAN;LIU LI-YAN: "Design and Implementation of a Combined Recommendation System Based on Spring Boot and User Portrait", ELECTRONIC COMPONENT AND INFORMATION TECHNOLOGY, vol. 3, no. 5, 31 May 2019 (2019-05-31), pages 24 - 29, XP055826751, ISSN: 2096-4455, DOI: 10.19772/j.cnki.2096-4455.2019.5.007 * |
Also Published As
Publication number | Publication date |
---|---|
CN111143688B (en) | 2021-03-02 |
AU2020335019A1 (en) | 2021-07-15 |
AU2020335019B2 (en) | 2022-06-16 |
CN111143688A (en) | 2020-05-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021031566A1 (en) | Multi-task learning-based facial beauty prediction method | |
US20210182611A1 (en) | Training data acquisition method and device, server and storage medium | |
US7421429B2 (en) | Generate blog context ranking using track-back weight, context weight and, cumulative comment weight | |
US9208441B2 (en) | Information processing apparatus, information processing method, and program | |
CN111885399B (en) | Content distribution method, device, electronic equipment and storage medium | |
CN109033408B (en) | Information pushing method and device, computer readable storage medium and electronic equipment | |
TW201706884A (en) | Data analysis system, data analysis method, data analysis program, and storage medium | |
US20180060426A1 (en) | Systems and methods for issue management | |
CN105894253A (en) | Method and device for automatic pushing of job application demand | |
CN112104642A (en) | Abnormal account number determination method and related device | |
CN108829652A (en) | A kind of picture labeling system based on crowdsourcing | |
JP2018509664A (en) | Model generation method, word weighting method, apparatus, device, and computer storage medium | |
WO2020237898A1 (en) | Personalized recommendation method for online education system, terminal and storage medium | |
CN111177559A (en) | Text travel service recommendation method and device, electronic equipment and storage medium | |
CN107809370B (en) | User recommendation method and device | |
Huna et al. | Exploiting content quality and question difficulty in CQA reputation systems | |
CN111723256A (en) | Government affair user portrait construction method and system based on information resource library | |
KR20200145299A (en) | Intelligent recruitment support platform based on online interview video analysis and social media information analysis | |
CN116303663A (en) | User affinity calculation method and system based on content social platform | |
WO2021134944A1 (en) | Mobile news client-based evaluation method and system therefor | |
CN113469752A (en) | Content recommendation method and device, storage medium and electronic equipment | |
WO2020119533A1 (en) | Public sentiment warning method and apparatus based on recurrent neural network algorithm, terminal and medium | |
CN111552882A (en) | News influence calculation method and device, computer equipment and storage medium | |
CN108259588A (en) | A kind of method for pushing and device of the cultural cloud platform based on big data | |
CN112257517A (en) | Scenic spot recommendation system based on scenic spot clustering and group emotion recognition |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
ENP | Entry into the national phase |
Ref document number: 2020335019 Country of ref document: AU Date of ref document: 20200331 Kind code of ref document: A |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20910306 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20910306 Country of ref document: EP Kind code of ref document: A1 |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20910306 Country of ref document: EP Kind code of ref document: A1 |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 12.01.2023) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20910306 Country of ref document: EP Kind code of ref document: A1 |