CN102651033A - Method and device for recommending online resource - Google Patents
Method and device for recommending online resource Download PDFInfo
- Publication number
- CN102651033A CN102651033A CN2012101019542A CN201210101954A CN102651033A CN 102651033 A CN102651033 A CN 102651033A CN 2012101019542 A CN2012101019542 A CN 2012101019542A CN 201210101954 A CN201210101954 A CN 201210101954A CN 102651033 A CN102651033 A CN 102651033A
- Authority
- CN
- China
- Prior art keywords
- user
- resource
- online
- quality
- success ratio
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and device for recommending an online resource on the basis of a quality control model. The quality control model comprises a user quality classifying sub-model and an online utilization success rate calculation sub-model of the quality of each user, wherein the user quality classifying sub-model is obtained by clustering the quality data of user history; and the online utilization success rate calculation sub-model corresponds to each resource type and is established by using resource utilization data of the user history. The recommending method comprises the following steps of: S1, determining the quality type of the current user by using the user quality classifying sub-model according to the real-time quality data generated when the current user sends a request; S2, determining the online utilization success rate of the quality of each resource corresponding to the quality type of the current user by using the online utilization success rate calculation sub-model; and S3, according to the online utilization success rate of the quality of each resource, which is determined in the step S2, recommending the required online resource to the current user. The utilization success rate of the online resource can be improved, and better experience is brought to the user.
Description
[technical field]
The present invention relates to technical field of the computer network, particularly a kind of recommend method of online resource and device.
[background technology]
Along with the variation of the lifting of the network bandwidth and user's custom, mainly be online utilization to network resources demand now, for example online playing audio frequency, online playing video etc.When the user need obtain certain online resource; Usually adopt the mode of vertical search; In the search box of browser, import resource information; Send to search server in the request that browser comprises this resource information, return the online resource corresponding to browser, and recommend the user and supply the user to select online utilization with this resource information by search server.For example; The user imports " king of K song " and clicks audio types to carry out vertical search in the search box of browser; After browser sends to search server with request; Just can get access to " king of K song " corresponding online song that search server returns, and recommend the user and supply user's online test listening.
Yet, in the prior art when online resource is recommended the user, normally based on online resource quality, downloading rate of the readability of online resource, online resource etc. for example.This will cause, though though come the front online resource its have higher quality because user quality is lower, for example user's network speed is lower, and can't the high-quality online resource of smooth playing, makes the use failure of online resource.It is thus clear that the use success ratio that conventional online resource recommendation mode is brought is lower, user experience is relatively poor.
[summary of the invention]
In view of this, the invention provides a kind of recommend method and device of online resource, so that improve the use success ratio of online resource, thus bring experience preferably to the user.
Concrete technical scheme is following:
A kind of recommend method of online resource; Based on Quality Control Model; Comprise in the said Quality Control Model: utilize the historical qualitative data of user to carry out the user quality classification submodel that cluster obtains; And the online use success ratio of each user quality that each resource class that utilizes the historical resource of user to use data to set up is corresponding is calculated submodel; Said recommend method comprises:
S1, the real-time qualitative data when sending request according to the active user utilize said user quality classification submodel to confirm the quality category that the active user is affiliated;
S2, utilize said online use success ratio to calculate submodel, confirm the online use success ratio of each resource quality that quality category under the said active user is corresponding;
The online use success ratio of S3, each resource quality of confirming according to said step S2 is recommended the online resource of being asked to said active user.
According to one preferred embodiment of the present invention, said qualitative data comprises at least a in user side network speed, request time or the positional information.
According to one preferred embodiment of the present invention, this method also comprises:
In the user uses the process of online resource, collect qualitative data, and use finish after, the qualitative data of collecting is write down or reports server with the form of daily record, supply to set up said user quality classification submodel.
According to one preferred embodiment of the present invention, set up said online use success ratio and calculate submodel and specifically comprise: utilize the historical online resource of user to obtain the data of success or not, statistics different quality classification user is respectively for the use success ratio of each resource class.
According to one preferred embodiment of the present invention, said step S3 specifically comprises: from the online resource that said active user asked, select to satisfy the online resource of the resource quality of presetting online use success ratio requirement and recommend to said active user; Perhaps,
According to online use success ratio the online resource that said active user asked is sorted the back to said active user's recommendation; Perhaps,
Satisfying under the prerequisite of presetting online use success ratio requirement, recommending the online resource of being asked according to online resource quality height to said active user.
A kind of recommendation apparatus of online resource; Based on Quality Control Model; Comprise in the said Quality Control Model: utilize the historical qualitative data of user to carry out the user quality classification submodel that cluster obtains; And the online use success ratio of each user quality that each resource class that utilizes the historical resource of user to use data to set up is corresponding is calculated submodel; Said recommendation apparatus comprises:
Data collection module is used to collect user's real-time qualitative data;
Quality category is confirmed the unit, is used for sending according to the active user the real-time qualitative data in when request, utilizes said user quality classification submodel to confirm the quality category under the active user;
Success ratio is confirmed the unit, is used to utilize said online use success ratio to calculate submodel, confirms the online use success ratio of each resource quality that the affiliated quality category of said active user is corresponding;
The resource recommendation unit is used for confirming according to said success ratio the online use success ratio of each resource quality that the unit is confirmed, recommends the online resource of being asked to said active user.
According to one preferred embodiment of the present invention, said qualitative data comprises at least a in user side network speed, request time or the positional information.
According to one preferred embodiment of the present invention, this recommendation apparatus also comprises: the first modelling unit is used to utilize the historical qualitative data of user to carry out cluster and obtains user quality classification submodel;
Said data collection module; Also be used for using the process of online resource to collect qualitative data the user; And after use finishing, the qualitative data of collecting is write down or reports server with the form of daily record, supply the said first modelling unit to obtain said user quality classification submodel.
According to one preferred embodiment of the present invention; This recommendation apparatus also comprises: the second modelling subelement; Be used to utilize the historical online resource of user to obtain the data of success or not; Statistics different quality classification user for the use success ratio of each resource class, calculates submodel thereby set up online use success ratio respectively.
According to one preferred embodiment of the present invention, said resource recommendation unit is selected to satisfy the online resource of the resource quality of presetting online use success ratio requirement and is recommended to said active user from the online resource that said active user asked; Perhaps,
According to online use success ratio the online resource that said active user asked is sorted the back to said active user's recommendation; Perhaps,
Satisfying under the prerequisite of presetting online use success ratio requirement, recommending the online resource of being asked according to online resource quality height to said active user.
Can find out by above technical scheme; Real-time qualitative data when recommend method provided by the invention at first sends request according to the active user with device is determined the quality category under the user; When from the online resource that the active user asked, determining again, satisfy the online resource that online success ratio requires and recommend with this user's quality category coupling.Thereby guarantee that as much as possible online resource successfully uses, promptly improved the use success ratio and the user experience of online resource.
[description of drawings]
The recommend method process flow diagram of the online resource that Fig. 1 provides for the embodiment of the invention;
The recommendation apparatus structural drawing of the online resource that Fig. 2 provides for the embodiment of the invention.
[embodiment]
In order to make the object of the invention, technical scheme and advantage clearer, describe the present invention below in conjunction with accompanying drawing and specific embodiment.
Find through analyzing; Often the user is when utilizing online resource; Main demand is online playing success ratio and fluency, and next is only resource quality (for example tonequality, sharpness) and waits other demands, therefore if improve success ratio; Then need realize the coupling of resource quality and user quality, this coupling is judged through Quality Control Model.The present invention just is based on this proposition, at first two kinds of involved submodels of Quality Control Model is described: user quality classification submodel and online use success ratio are calculated submodel.
User quality classification submodel is to utilize the historical qualitative data of user to carry out cluster to obtain, and wherein the historical qualitative data of user obtains from the online resource usage log.Can collect the real-time qualitative data that the user asks online resource at every turn; Include but not limited to: at least a in the network speed of user side (user uses the network speed of online resource), request time or the positional information; Wherein each user can adopt cookie or user name etc. to identify; Request time can be date and time information, week information or period information etc., positional information can be ip address or geographical location information etc.The mode of collecting these qualitative datas can be through embedding the js code in the webpage player, in the user uses the process of online resource, collect qualitative data, and use finish after, the information of collecting is write down or reports server with the form of daily record.
When carrying out cluster, carry out according to the qualitative data of collecting, same user can be divided into an above mass classification.For example:
According to the network speed of each user when using online resource; The user is divided into highspeed user, middling speed user and low speed user; Wherein network speed is that the above user of 60kbps is divided into the highspeed user; Network speed is that the user of 30kbps-60kbps is divided into the middling speed user, and network speed is that the user of 0-30kbps is divided into low speed user.
According to the request time of each user, the user is divided into user's peak period, common period user and unexpected winner period user to online resource.Wherein, Request time be 10 to 8 of at 17 in afternoon and evenings to evening 10 user be divided into user's peak period; Request time is that the user of 2:00 AM to 8 is divided into unexpected winner period user, and request time is divided into common period user for the user of other periods.Also can directly divide the user according to the period at request time place; For example be divided into respectively: 0 o'clock user, 4 o'clock users, 8 o'clock users, 12 o'clock users to 15 o'clock period to 11 o'clock period to 7 o'clock period to 3 o'clock period; 16 o'clock users to 19 o'clock period, 20 o'clock users to 23 o'clock period.
According to each user position information, the user is divided into the user of each province.
Also can integrate user's request time, user side network speed and positional information and be divided into big type, for example, network speed is that 60kbps is above, request time is divided into one type 10 Beijing users at 17 in afternoon.Certainly class of subscriber can also adopt other to divide the mode of quality category, gives an example no longer one by one at this.In addition, can adopt the mode of above-mentioned absolute classification, can adopt the mode of calculating the probability that corresponds to each quality category based on real-time qualitative data yet, the concrete mode classification embodiment of the invention of user quality classification does not limit.
It is to utilize the historical resource of user to use data to set up that online use success ratio is calculated submodel; After each user is carried out the classification of quality category; Utilize the historical online resource of user to obtain the data of success or not; For the use success ratio of each resource class, a class user can adopt a class user to use the ratio of the b class resource quantity of successful online resource quantity of b class resource and a class user request for the use success ratio of b class resource to statistics different quality classification user respectively.
Wherein the resource class of online resource can be divided according to the quality of online resource, for example according to the size of resource or service speed etc., each online resource is divided into high-quality resource, fair average quality resource and inferior quality resource.Wherein the service speed of resource belongs to the embodiment of testing the speed of content distributing network (CDN, Content Delivery Network) node server usually through resource.
For example, through statistics obtain that network speed is that 60kbps is above, request time is 60%, is 92%, is 98% for the use success ratio of inferior quality resource for the use success ratio of fair average quality resource for the use success ratio of high-quality resource to Beijing user at 17 in afternoon at 10.
Realize that to how utilizing above-mentioned submodel the method for online resource recommendation describes below in conjunction with Fig. 1, as shown in Figure 1, this method may further comprise the steps:
Step 101: the real-time qualitative data when asking online resource according to the active user, utilize user quality classification submodel to confirm the quality category that the active user is affiliated.
Real-time qualitative data when the active user asks online resource can include but not limited to: at least a in user side network speed (in real time network speed), request time or the positional information; Behind the real-time qualitative data input user quality classification submodel when active user is asked online resource, can obtain the affiliated quality category of active user.
For example; Real-time qualitative data when the active user asks online resource is: real-time network speed 70kbps; Request time is that 13 points, positional information are Beijing, then import behind the user quality classification submodel with the active user be divided into that real-time network speed is more than the 60kbps, request time is 10 these classifications of Beijing user at 17 in afternoon.
Step 102: utilize online use success ratio to calculate submodel, confirm the online use success ratio of each resource quality that the affiliated quality category of active user is corresponding.
Continue and go up example; With real-time network speed be more than the 60kbps, request time uses success ratios to calculate submodels at 10 these classification Input Online of Beijing user at 17 in afternoon; Can determine the online use success ratio of each corresponding resource quality of quality category under the active user, promptly be 60%, be 92%, be 98% for the use success ratio of inferior quality resource for the use success ratio of fair average quality resource for the use success ratio of high-quality resource.
Step 103: the online use success ratio of each resource quality of confirming according to step 102, recommend the online resource of being asked to the active user.
In this step; Can at first confirm the online resource that the user asked; Promptly confirm the online resource that all are corresponding according to the resource information of user input, the resource quality of these online resources differs, for example user's input " king of K song " and click audio types when carrying out vertical search; At first determine the audio resource that all " kings of K song " hit, but possibly have high-quality resource, fair average quality resource and inferior quality resource in these resources.So how these online resources are recommended to the user, then can be adopted different strategies, include but not limited to following several kinds:
Recommendation strategy one, selection are satisfied the online resource of the resource quality of preset online use success ratio requirement and are recommended to the active user.
Suppose that it is more than 90% that preset online use success ratio requires; The real-time network speed of then in last example, mentioning is more than the 60kbps, request time is 10 Beijing users at 17 in afternoon; Can select fair average quality resource and inferior quality resource recommendation to give the active user; And the use success ratio of high-quality resource is not owing to below preset online use success ratio requires, therefore can recommend the active user.
Recommend strategy two, according to online use success ratio the online resource that the user asked sorted and then recommend to the active user.That is to say, the online resource of all users request is all recommended the user, but according to online use success ratio online resource is sorted when recommending.
Recommend strategy three, satisfying under the prerequisite of presetting online use success ratio requirement, recommend the online resource of being asked according to online resource quality height to the active user.
Still the preset online use success ratio requirement of hypothesis is more than 90%; The real-time network speed of then in last example, mentioning is more than the 60kbps, request time is 10 Beijing users at 17 in afternoon; Can select fair average quality resource and inferior quality resource recommendation to give the active user, supply the active user preferentially to select before in recommendation process, the fair average quality resource being come quality resource such as low.
It more than is the detailed description that method provided by the present invention is carried out; Describe in the face of device provided by the present invention down; Equally, the recommendation apparatus of online resource provided by the present invention specifically comprises based on Quality Control Model: utilize the historical qualitative data of user to carry out the user quality classification submodel that cluster obtains; And the online use success ratio of each user quality that each resource class that utilizes the historical resource of user to use data to set up is corresponding is calculated submodel.As shown in Figure 2, the recommendation apparatus of online resource can comprise: data collection module 201, quality category confirm that unit 202, success ratio confirm unit 203 and resource recommendation unit 204.
Quality category confirms that unit 202 sends the real-time qualitative data in when request according to the active user, utilizes user quality classification submodel to confirm the quality category under the active user.This moment, in real time qualitative data comprised at least a in real-time network speed, request time or the positional information of user side.
Success ratio confirms that unit 203 utilizes online use success ratio to calculate submodel, confirms the online use success ratio of each resource quality that the affiliated quality category of active user is corresponding.
The online use success ratio of each resource quality that unit 203 is confirmed is confirmed according to success ratio in resource recommendation unit 204, recommends the online resource of being asked to the active user.Can at first confirm the online resource that the user asked; Promptly confirm the online resource that all are corresponding according to the resource information of user's input; The resource quality of these online resources differs, with these online resources when the user recommends, can adopt but be not limited to following several kinds the strategy:
Recommend strategy one, from the online resource that the active user asked, select to satisfy the online resource of the resource quality that preset online use success ratio requires and recommend to the active user.
Recommend strategy two, according to online use success ratio the online resource that the active user asked sorted and then recommend to the active user.
Recommend strategy three, satisfying under the prerequisite of presetting online use success ratio requirement, recommend the online resource of being asked according to online resource quality height to the active user.
In order to realize the foundation of above-mentioned two kinds of submodels, this recommendation apparatus can further include: the first modelling unit 205 is used to utilize the historical qualitative data of user to carry out cluster and obtains user quality classification submodel.When carrying out cluster, carry out according to the qualitative data of collecting, same user can be divided into an above mass classification.
In addition; This recommendation apparatus also comprises: the second modelling subelement 206; Be used to utilize the historical online resource of user to obtain the data of success or not, statistics different quality classification user for the use success ratio of each resource class, calculates submodel thereby set up online use success ratio respectively.Wherein, the historical online resource of the user data of obtaining success or not also can be obtained by data collection module 201.
Above-mentioned recommend method provided by the invention and recommendation apparatus realize at server end, receive the request that the user sends through browser or client after, recommend the online resource that the user asked to browser or client.
In addition, need to prove that the online resource that the present invention relates to can include but not limited to: online audio resource, Online Video resource etc.
The above is merely preferred embodiment of the present invention, and is in order to restriction the present invention, not all within spirit of the present invention and principle, any modification of being made, is equal to replacement, improvement etc., all should be included within the scope that the present invention protects.
Claims (10)
1. the recommend method of an online resource; Based on Quality Control Model; It is characterized in that; Comprise in the said Quality Control Model: utilize the historical qualitative data of user to carry out the user quality classification submodel that cluster obtains, and the online use success ratio of each user quality that each resource class that utilizes the historical resource of user to use data to set up is corresponding is calculated submodel; Said recommend method comprises:
S1, the real-time qualitative data when sending request according to the active user utilize said user quality classification submodel to confirm the quality category that the active user is affiliated;
S2, utilize said online use success ratio to calculate submodel, confirm the online use success ratio of each resource quality that quality category under the said active user is corresponding;
The online use success ratio of S3, each resource quality of confirming according to said step S2 is recommended the online resource of being asked to said active user.
2. method according to claim 1 is characterized in that, said qualitative data comprises at least a in user side network speed, request time or the positional information.
3. method according to claim 1 and 2 is characterized in that, this method also comprises:
In the user uses the process of online resource, collect qualitative data, and use finish after, the qualitative data of collecting is write down or reports server with the form of daily record, supply to set up said user quality classification submodel.
4. method according to claim 1; It is characterized in that; Setting up said online use success ratio calculates submodel and specifically comprise: utilize the historical online resource of user to obtain the data of success or not, statistics different quality classification user is respectively for the use success ratio of each resource class.
5. method according to claim 1; It is characterized in that; Said step S3 specifically comprises: from the online resource that said active user asked, select to satisfy the online resource of the resource quality of presetting online use success ratio requirement and recommend to said active user; Perhaps,
According to online use success ratio the online resource that said active user asked is sorted the back to said active user's recommendation; Perhaps,
Satisfying under the prerequisite of presetting online use success ratio requirement, recommending the online resource of being asked according to online resource quality height to said active user.
6. the recommendation apparatus of an online resource; Based on Quality Control Model; It is characterized in that; Comprise in the said Quality Control Model: utilize the historical qualitative data of user to carry out the user quality classification submodel that cluster obtains, and the online use success ratio of each user quality that each resource class that utilizes the historical resource of user to use data to set up is corresponding is calculated submodel; Said recommendation apparatus comprises:
Data collection module is used to collect user's qualitative data;
Quality category is confirmed the unit, is used for sending according to the active user the real-time qualitative data in when request, utilizes said user quality classification submodel to confirm the quality category under the active user;
Success ratio is confirmed the unit, is used to utilize said online use success ratio to calculate submodel, confirms the online use success ratio of each resource quality that the affiliated quality category of said active user is corresponding;
The resource recommendation unit is used for confirming according to said success ratio the online use success ratio of each resource quality that the unit is confirmed, recommends the online resource of being asked to said active user.
7. recommendation apparatus according to claim 6 is characterized in that, said qualitative data comprises at least a in user side network speed, request time or the positional information.
8. according to claim 6 or 7 described recommendation apparatus, it is characterized in that this recommendation apparatus also comprises: the first modelling unit is used to utilize the historical qualitative data of user to carry out cluster and obtains user quality classification submodel;
Said data collection module; Also be used for using the process of online resource to collect qualitative data the user; And after use finishing, the qualitative data of collecting is write down or reports server with the form of daily record, supply the said first modelling unit to obtain said user quality classification submodel.
9. recommendation apparatus according to claim 6; It is characterized in that; This recommendation apparatus also comprises: the second modelling subelement; Be used to utilize the historical online resource of user to obtain the data of success or not, statistics different quality classification user for the use success ratio of each resource class, calculates submodel thereby set up online use success ratio respectively.
10. recommendation apparatus according to claim 6; It is characterized in that; Said resource recommendation unit is selected to satisfy the online resource of the resource quality of presetting online use success ratio requirement and is recommended to said active user from the online resource that said active user asked; Perhaps,
According to online use success ratio the online resource that said active user asked is sorted the back to said active user's recommendation; Perhaps,
Satisfying under the prerequisite of presetting online use success ratio requirement, recommending the online resource of being asked according to online resource quality height to said active user.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210101954.2A CN102651033B (en) | 2012-04-09 | 2012-04-09 | A kind of recommend method of online resource and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210101954.2A CN102651033B (en) | 2012-04-09 | 2012-04-09 | A kind of recommend method of online resource and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102651033A true CN102651033A (en) | 2012-08-29 |
CN102651033B CN102651033B (en) | 2016-04-27 |
Family
ID=46693041
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210101954.2A Active CN102651033B (en) | 2012-04-09 | 2012-04-09 | A kind of recommend method of online resource and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102651033B (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104363302A (en) * | 2014-11-27 | 2015-02-18 | 北京奇艺世纪科技有限公司 | Method and device for downloading file offline |
CN104427361A (en) * | 2013-09-02 | 2015-03-18 | 大同股份有限公司 | Television service system and method for providing video and audio service |
CN104768069A (en) * | 2015-04-02 | 2015-07-08 | 天脉聚源(北京)传媒科技有限公司 | Data projection method, device and system |
CN105160225A (en) * | 2015-08-18 | 2015-12-16 | 宇龙计算机通信科技(深圳)有限公司 | Electronic equipment operation method and apparatus |
CN103685397B (en) * | 2012-09-14 | 2017-04-05 | 百度在线网络技术(北京)有限公司 | Based on the reminding method of the download/play quality of high in the clouds analysis, system and device |
CN107004205A (en) * | 2014-07-01 | 2017-08-01 | 谷歌公司 | The system and method for the intention type of online content are proposed to be used in advertiser |
CN108415992A (en) * | 2018-02-12 | 2018-08-17 | 百度在线网络技术(北京)有限公司 | Resource recommendation method, device and computer equipment |
CN108550046A (en) * | 2018-03-07 | 2018-09-18 | 阿里巴巴集团控股有限公司 | A kind of resource and market recommendation method, apparatus and electronic equipment |
CN108647293A (en) * | 2018-05-07 | 2018-10-12 | 广州虎牙信息科技有限公司 | Video recommendation method, device, storage medium and server |
CN111311357A (en) * | 2020-01-20 | 2020-06-19 | 昊居科技有限公司 | House transaction information management method and system |
CN111385659A (en) * | 2018-12-29 | 2020-07-07 | 广州市百果园信息技术有限公司 | Video recommendation method, device, equipment and storage medium |
CN112559873A (en) * | 2020-12-21 | 2021-03-26 | 周欢 | User recommendation system based on intelligent education |
CN114092162A (en) * | 2022-01-21 | 2022-02-25 | 北京达佳互联信息技术有限公司 | Recommendation quality determination method, and training method and device of recommendation quality determination model |
CN115378878A (en) * | 2021-05-21 | 2022-11-22 | 北京字跳网络技术有限公司 | CDN scheduling method, device, equipment and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090138443A1 (en) * | 2007-11-23 | 2009-05-28 | Institute For Information Industry | Method and system for searching for a knowledge owner in a network community |
CN101615197A (en) * | 2009-07-30 | 2009-12-30 | 浙江大学 | A kind of personalized network resource recommended method of connection speed Network Based |
CN102054003A (en) * | 2009-11-04 | 2011-05-11 | 北京搜狗科技发展有限公司 | Methods and systems for recommending network information and creating network resource index |
-
2012
- 2012-04-09 CN CN201210101954.2A patent/CN102651033B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090138443A1 (en) * | 2007-11-23 | 2009-05-28 | Institute For Information Industry | Method and system for searching for a knowledge owner in a network community |
CN101615197A (en) * | 2009-07-30 | 2009-12-30 | 浙江大学 | A kind of personalized network resource recommended method of connection speed Network Based |
CN102054003A (en) * | 2009-11-04 | 2011-05-11 | 北京搜狗科技发展有限公司 | Methods and systems for recommending network information and creating network resource index |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103685397B (en) * | 2012-09-14 | 2017-04-05 | 百度在线网络技术(北京)有限公司 | Based on the reminding method of the download/play quality of high in the clouds analysis, system and device |
CN104427361A (en) * | 2013-09-02 | 2015-03-18 | 大同股份有限公司 | Television service system and method for providing video and audio service |
CN112633914A (en) * | 2014-07-01 | 2021-04-09 | 谷歌有限责任公司 | System and method for suggesting creative types for online content items to advertisers |
CN107004205A (en) * | 2014-07-01 | 2017-08-01 | 谷歌公司 | The system and method for the intention type of online content are proposed to be used in advertiser |
CN104363302A (en) * | 2014-11-27 | 2015-02-18 | 北京奇艺世纪科技有限公司 | Method and device for downloading file offline |
CN104768069A (en) * | 2015-04-02 | 2015-07-08 | 天脉聚源(北京)传媒科技有限公司 | Data projection method, device and system |
CN104768069B (en) * | 2015-04-02 | 2017-10-03 | 天脉聚源(北京)传媒科技有限公司 | A kind of data projection method, apparatus and system |
CN105160225A (en) * | 2015-08-18 | 2015-12-16 | 宇龙计算机通信科技(深圳)有限公司 | Electronic equipment operation method and apparatus |
CN108415992B (en) * | 2018-02-12 | 2022-03-04 | 百度在线网络技术(北京)有限公司 | Resource recommendation method and device and computer equipment |
CN108415992A (en) * | 2018-02-12 | 2018-08-17 | 百度在线网络技术(北京)有限公司 | Resource recommendation method, device and computer equipment |
CN108550046B (en) * | 2018-03-07 | 2021-03-02 | 创新先进技术有限公司 | Resource and marketing recommendation method and device and electronic equipment |
CN108550046A (en) * | 2018-03-07 | 2018-09-18 | 阿里巴巴集团控股有限公司 | A kind of resource and market recommendation method, apparatus and electronic equipment |
CN108647293A (en) * | 2018-05-07 | 2018-10-12 | 广州虎牙信息科技有限公司 | Video recommendation method, device, storage medium and server |
CN108647293B (en) * | 2018-05-07 | 2022-02-01 | 广州虎牙信息科技有限公司 | Video recommendation method and device, storage medium and server |
CN111385659A (en) * | 2018-12-29 | 2020-07-07 | 广州市百果园信息技术有限公司 | Video recommendation method, device, equipment and storage medium |
CN111311357B (en) * | 2020-01-20 | 2024-05-03 | 昊居科技有限公司 | House transaction information management method and system |
CN111311357A (en) * | 2020-01-20 | 2020-06-19 | 昊居科技有限公司 | House transaction information management method and system |
CN112559873A (en) * | 2020-12-21 | 2021-03-26 | 周欢 | User recommendation system based on intelligent education |
CN112559873B (en) * | 2020-12-21 | 2021-08-13 | 融易学控股(深圳)有限公司 | User recommendation system based on intelligent education |
CN115378878A (en) * | 2021-05-21 | 2022-11-22 | 北京字跳网络技术有限公司 | CDN scheduling method, device, equipment and storage medium |
WO2022242470A1 (en) * | 2021-05-21 | 2022-11-24 | 北京字跳网络技术有限公司 | Cdn scheduling method, apparatus and device, and storage medium |
CN115378878B (en) * | 2021-05-21 | 2023-11-14 | 北京字跳网络技术有限公司 | CDN scheduling method, device, equipment and storage medium |
CN114092162B (en) * | 2022-01-21 | 2022-07-01 | 北京达佳互联信息技术有限公司 | Recommendation quality determination method, and training method and device of recommendation quality determination model |
CN114092162A (en) * | 2022-01-21 | 2022-02-25 | 北京达佳互联信息技术有限公司 | Recommendation quality determination method, and training method and device of recommendation quality determination model |
Also Published As
Publication number | Publication date |
---|---|
CN102651033B (en) | 2016-04-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102651033A (en) | Method and device for recommending online resource | |
CN103295147B (en) | method, device and system for advertising | |
CN103684874B (en) | Method and device for automatically distributing online customer service executives to conduct customer service | |
JP6157021B2 (en) | Method and apparatus for sharing online media impression data | |
CN110222880B (en) | Service risk determining method, model training method and data processing method | |
CN105451087A (en) | Pushing method, terminals, historical data server and system for barrage information | |
CN104243598B (en) | A kind of information recommendation method and device | |
CN104284216A (en) | Method and system for generating video highlight clip | |
CN104536965B (en) | A kind of data query display systems under the conditions of big data and method | |
CN103647800A (en) | Method and system of recommending application resources | |
CN102880676A (en) | Statistical method for user behavior data and user behavior data statistical system | |
CN110363621B (en) | Order information pushing system based on artificial intelligence technology | |
CN105163142A (en) | User preference determination method, video recommendation method, user preference determination system and video recommendation system | |
CN103310087A (en) | Service data statistic analysis method and device | |
CN109656685A (en) | Container resource regulating method and system, server and computer readable storage medium | |
CN103136621B (en) | Engineering is submitted to a higher level for approval or revision the online management method of auditing flow of list | |
CN103441902B (en) | Flow production method based on Streaming Media user behavior analysis | |
CN104537011A (en) | Singing ranking method and device | |
CN112199521B (en) | Automatic media asset arranging method, device and system, electronic device and storage medium | |
CN103814580B (en) | The method that interactive service is provided and the server in interactive service network | |
CN109542848A (en) | A kind of vehicle-mounted media file fast scanning method and system | |
CN113625936A (en) | Data processing method, device, storage medium and equipment | |
CN103136622A (en) | On-line management method for project contracting enterprise evaluation | |
CN110109757B (en) | High-performance computing method based on cloud computing | |
CN101276377B (en) | Method, system for acquiring resource related information and application in search engine |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |