CN109145221A - Content recommendation method and device, electronic equipment, readable storage medium storing program for executing - Google Patents
Content recommendation method and device, electronic equipment, readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN109145221A CN109145221A CN201811054068.2A CN201811054068A CN109145221A CN 109145221 A CN109145221 A CN 109145221A CN 201811054068 A CN201811054068 A CN 201811054068A CN 109145221 A CN109145221 A CN 109145221A
- Authority
- CN
- China
- Prior art keywords
- feedback
- recommendation
- user
- negative
- time
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A kind of content recommendation method and device, electronic equipment, readable storage medium storing program for executing provided in an embodiment of the present invention, are related to Internet technical field, and the content recommendation method includes: to obtain at least one recommendation to be recommended.Determine at least one described recommendation to include the second recommendation marked in the preference information of user.Wherein, the preference information includes the recommendation and feedback parameter that the user does not like.The feedback parameter includes feedback time and/or Times of Feedback.Determine whether the feedback parameter meets preset condition.When the feedback parameter meets preset condition, recommend second recommendation to the user.Whether reach preset condition to the second recommendation of lead referral by judging feedback time and/or Times of Feedback, can to avoid user due to do not like in short term or maloperation and cause the second recommendation not to be pushed permanently.Therefore practicability is stronger, and more humanized.
Description
Technical field
The present invention relates to Internet technical fields, set in particular to a kind of content recommendation method and device, electronics
Standby, readable storage medium storing program for executing.
Background technique
At present when carrying out web page browsing or reading article by APP, webpage or APP server can be according to the one of user
Like preference recommendation, make that user receives is oneself favorite content as far as possible.Therefore, server can pass through net
Perhaps APP offer setting options user can be set or feed back the article not liked or content type (in industry to page browsing device
Referred to as negative-feedback), server can according to the setting or feedback of user, will substantially it is permanent no longer push or recommend with not
The associated article of article or content or content liked.Therefore, user did not received recommendation or push once for permanent yet
Content through negative-feedback.Although this kind of method can shield the content of user's once negative-feedback, but one one-tenth not always
Become, it is inflexible.
Summary of the invention
The purpose of the present invention is to provide a kind of content recommendation method and device, electronic equipment, readable storage medium storing program for executing, energy
Enough solve the above problems;In order to achieve the above purpose;The technical solution taken of the invention is as follows:
In a first aspect, the embodiment of the invention provides a kind of content recommendation methods, comprising:
Obtain at least one recommendation to be recommended;
It include that the user marked in the preference information with user does not like at least one recommendation described in determining
Relevant second recommendation of the first joyous recommendation;Wherein, the preference information further includes feedback parameter;The feedback ginseng
Number includes the feedback time and/or Times of Feedback for feeding back first recommendation;
Determine whether the feedback parameter of first recommendation meets preset condition;
When the feedback parameter meets preset condition, recommend second recommendation to the user.
Optionally, whether the determination feedback parameter meets preset condition and includes:
Determine whether the Times of Feedback is less than preset times.
Determine whether the feedback time apart from current point in time is more than preset duration.Wherein, small in the Times of Feedback
When the preset times, or when the feedback time is more than preset duration apart from current point in time, characterize the feedback
Parameter meets the preset condition.
It optionally, include second marked in the negative-feedback log of user in determining at least one described recommendation
Before recommendation, the method also includes:
Highest at least two channel of the degree of correlation is determined according to the feature of the recommendation not liked;
It is respectively configured at least two channel and does not like reason;
At least two channel and the reason that do not like are sent to client.
Optionally, described by least two channel and it is described do not like after reason is sent to the client,
The method also includes:
Receive the negative-feedback log for the user that the client returns;The negative-feedback log includes that user does not like
Channel and the reasons why do not like;
Obtain the relevant historical negative-feedback number for the recommendation channel not liked with the user;
It is generated according to the negative-feedback log, the feedback time of the reception negative-feedback log and the negative-feedback number
The preference information.
Optionally, if the client does not return to the negative-feedback log, the method also includes:
Determine that highest first channel of the degree of correlation described at least two channel is the channel that the user does not like;
Determine that current time is the feedback time;
Obtain the relevant historical negative-feedback number for the channel not liked with the user;
The preference information is generated according to first channel, the feedback time and the negative-feedback number.
Second aspect, the embodiment of the invention provides a kind of content recommendation device, described device includes:
Module is obtained, for obtaining at least one recommendation to be recommended.
Confirmation module includes the marked in the preference information of user at least one described recommendation for determining
Two recommendations;Wherein, the preference information includes that the user does not like recommendation and feedback parameter;The feedback parameter
Including feedback time and/or Times of Feedback.
Judgment module, for determining whether the feedback parameter meets preset condition.
Recommending module, for recommending described second to recommend to the user when the feedback parameter meets preset condition
Content.
Optionally, the judgment module, for determining whether the Times of Feedback is less than preset times;Determine the feedback
Whether time gap current point in time is more than preset duration;Wherein, when the Times of Feedback is less than the preset times, or
When the feedback time is more than preset duration apart from current point in time, characterizes the feedback parameter and meet the preset condition.
Optionally, described device further include:
Negative-feedback log acquisition module, the negative-feedback log of the user for receiving client return.It is described negative anti-
The reasons why feedback log includes the recommendation that user does not like and does not like.
Negative-feedback number obtains module, for obtaining the relevant historical negative-feedback for the recommendation not liked with the user
Number.
Preference information obtains module, for the feedback time according to the negative-feedback log, the reception negative-feedback log
And the negative-feedback number generates the preference information.
The third aspect, the embodiment of the invention provides a kind of electronic equipment, including processor and memory, the storages
Device is stored with computer-readable instruction fetch, and when the computer-readable instruction fetch is executed by the processor, operation is such as above-mentioned
Step in first aspect the method.
Fourth aspect, the embodiment of the invention provides a kind of readable storage medium storing program for executing, are stored thereon with computer program, described
The step in above-mentioned first aspect method is run when computer program is executed by processor.
A kind of content recommendation method and device, electronic equipment, readable storage medium storing program for executing provided in embodiments of the present invention, leads to
Cross judge feedback time and/or Times of Feedback whether reach preset condition and to the second recommendation of lead referral, can be to avoid
User due to do not like in short term or maloperation and cause the second recommendation not to be pushed permanently.Therefore practicability is stronger, and
It is more humanized.
Other features and advantages of the present invention will be illustrated in subsequent specification, also, partly be become from specification
It is clear that by implementing understanding of the embodiment of the present invention.The objectives and other advantages of the invention can be by written theory
Specifically noted structure is achieved and obtained in bright book, claims and attached drawing.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is a kind of flow diagram of content recommendation method provided in an embodiment of the present invention;
Fig. 2 is the flow diagram of another content recommendation method provided in an embodiment of the present invention;
Fig. 3 is the flow diagram of another content recommendation method provided in an embodiment of the present invention;
Fig. 4 is the flow diagram of another content recommendation method provided in an embodiment of the present invention;
Fig. 5 is the flow diagram of another content recommendation method provided in an embodiment of the present invention;
Fig. 6 is a kind of connection schematic diagram of content recommendation device provided in an embodiment of the present invention;
Fig. 7 is a kind of connection schematic diagram of content recommendation device provided in an embodiment of the present invention.
Appended drawing reference summarizes:
10- content recommendation device;11- obtains module;12- confirmation module;13 judgment modules;14- recommending module;
110- negative-feedback log acquisition module;112- negative-feedback number obtains module;113- preference information obtains module.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings is implemented
The component of example can be arranged and be designed with a variety of different configurations.
Therefore, the detailed description of the embodiment of the present invention provided in the accompanying drawings is not intended to limit below claimed
The scope of the present invention, but be merely representative of selected embodiment of the invention.Based on the embodiments of the present invention, this field is common
Technical staff's every other embodiment obtained without creative efforts belongs to the model that the present invention protects
It encloses.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.
In the description of the present invention, it should be noted that term " center ", "upper", "lower", "left", "right", "vertical",
The orientation or positional relationship of the instructions such as "horizontal", "inner", "outside" is to be based on the orientation or positional relationship shown in the drawings, or be somebody's turn to do
Invention product using when the orientation or positional relationship usually put, be merely for convenience of description of the present invention and simplification of the description, without
It is that the device of indication or suggestion meaning or element must have a particular orientation, be constructed and operated in a specific orientation, therefore not
It can be interpreted as limitation of the present invention.In addition, term " first ", " second ", " third " etc. are only used for distinguishing description, and cannot manage
Solution is indication or suggestion relative importance.In addition, the terms such as term "horizontal", "vertical", " pendency " are not offered as requiring component
Abswolute level or pendency, but can be slightly tilted.If "horizontal" only refers to that its direction is more horizontal with respect to for "vertical",
It is not to indicate that the structure is had to fully horizontally, but can be slightly tilted.
In the description of the present invention, it is also necessary to which explanation is unless specifically defined or limited otherwise, term " setting ",
" installation ", " connected ", " connection " shall be understood in a broad sense, for example, it may be fixedly connected, may be a detachable connection or one
Connect to body;It can be mechanical connection, be also possible to be electrically connected;It can be directly connected, it can also be indirect by intermediary
It is connected, can be the connection inside two elements.For the ordinary skill in the art, on being understood with concrete condition
State the concrete meaning of term in the present invention.
Fig. 1 is please referred to, is a kind of content recommendation method provided in an embodiment of the present invention, comprising:
S100: at least one recommendation to be recommended is obtained.
S110: determine at least one described recommendation to include in the second recommendation marked in the preference information of user
Hold.Wherein, the preference information includes the recommendation and feedback parameter that the user does not like.The feedback parameter includes anti-
Present time and/or Times of Feedback.
S120: determine whether the feedback parameter meets preset condition.
S130: when the feedback parameter meets preset condition, recommend second recommendation to the user.
Therefore, in embodiments of the present invention, by judging whether feedback time and/or Times of Feedback reach preset condition
To the second recommendation of lead referral, can to avoid user due to do not like in short term or maloperation and cause the second recommendation
It can not receive.Therefore practicability is stronger, and more humanized.
The detailed implementation process of each step is described more fully below.
Optionally, when the operation of web browser or APP is opened in input, server can be held user based on the operation
Row step S100 obtains at least one recommendation to be recommended.At least one recommendation can be an article, when
So, in practice, content to be recommended is also possible to other contents, such as video.One content to be recommended can correspond to one
A or multiple channels.
Next step S110 is executed, that is, determines that at least one described recommendation include in the preference information with user
Relevant second recommendation of the first recommendation that the user indicated does not like.Optionally, server can be safeguarded each
The user of user draws a portrait, and record has the preference information of user in user's portrait, such as preference information includes what user did not liked
Recommendation and feedback parameter.The feedback parameter includes feedback time and/or Times of Feedback.It will later about feedback parameter
It describes in detail.
It, can be by the preference of at least one recommendation and user for being got in step S100 when executing step S110
The recommendation not liked in information is compared, determine at least one recommendation whether comprising with the recommendation that does not like
The relevant recommendation of content.Specifically, can determine that each recommendation is corresponding according to the feature of at least one recommendation
Channel directly two channels are compared if what is recorded in preference information is channel;If what is recorded in preference information is
The specific recommendations such as article or video, then determine channel according to the feature of the recommendation recorded in preference information, then
Channel is compared again.Regardless of mode, if channel is identical, characterizes the identical content to be recommended of channel and preference is believed
The recommendation not liked marked in breath is consistent.Certainly, if what is recorded in preference information is specific article or video etc.
Directly recommendation can also be compared for recommendation, if the similarity of two contents is greater than preset threshold, it is determined that phase
It is consistent to be greater than the recommendation not liked marked in the content to be recommended and preference information of preset threshold like degree.
For example, the content to be recommended got in step S100 include three contents, respectively content a, content b and
Content c.It include content a+, content d and content e in the content not liked recorded in user preference information.In will be described
Hold a, the content b and the content c and content a+, content d and content e successively to compare, discovery content a+ and content a belongs to together
It is related to content a+ then to characterize content a for one channel.Then content a is indicating with preference information of determining in step S110
Relevant second recommendation of content a+ that does not like of user.
Next step S120 is executed, that is, determines whether the feedback parameter of the first recommendation meets preset condition.
Continue by taking previous example as an example, that is, determines whether the feedback parameter of content a+ meets preset condition.
Optionally, referring to Fig. 2, in embodiments of the present invention, S120: determining the feedback parameter of the first recommendation
Whether meeting preset condition includes:
S121: determine whether the Times of Feedback is less than preset times.
S122: determine whether the feedback time apart from current point in time is more than preset duration;Wherein, in the feedback time
When number is less than the preset times, or when the feedback time is more than preset duration apart from current point in time, described in characterization
Feedback parameter meets the preset condition.
Further, the preset duration can be two weeks, and the preset times can be for three times.Certainly when described default
The long and preset times can be configured according to the actual situation, not limited here.For example, when user feeds back not for the first time
When liking certain class content, the preset duration be can be set to one week, described when user feeds back again does not like this kind of content
Preset duration can be set to two weeks.The preset times also may be set according to actual conditions.
Continue by taking previous example as an example, it is assumed that the negative-feedback number of content a+ is 1 time, is less than preset times 3 times, then may be used
To determine that the feedback parameter of content a+ meets preset condition.Assuming that the feedback time of content a+ apart from current point in time when it is a length of
1 month, more than preset duration one week, then it can determine that the feedback parameter of content a+ meets preset condition.It is of course also possible to be
It is pre- to determine that feedback parameter meets less than preset times and when feedback time is more than preset duration apart from current point in time for Times of Feedback
If condition.
When feedback parameter meets preset condition, step S130 is executed, i.e., is recommended in second recommendation to the user
Hold.Continue by taking previous example as an example, i.e., to user's recommendation a.Certainly, also to user's recommendation b and content c.
If using method in the prior art, because content a+ is by Negative Feedback mistake, then in feedback content a,
Because content a is related to content a+, content a would not recommend user again, but use the side in the embodiment of the present invention
Method, content a can still recommend user, be soundd out again user, avoid user from not liking in short term only and cause can not
Receive this content.
Next it will be described in detail the implementation process for generating preference information.
Optionally, referring to Fig. 3, in step S110: before, the method also includes:
S200: highest at least two channel of the degree of correlation is determined according to the feature of the recommendation not liked.
S210: it is respectively configured at least two channel and does not like reason.
S220: at least two channel and the reason that do not like are sent to client.
Further, the content that the preference information is included is the content not liked and the number not liked, then each
When the secondary recommendation to user, the relationship of the content to be recommended and the preference information will be all judged.Such as: it is pushed away when described
It is associated content that content, which is recommended, with the content inside preference information, then sees whether the content to be recommended meets preset item
Part is recommended phase user if closing preset condition, if not satisfied, not recommending.When in the recommendation and preference information
The content in face is not associated content, then directly recommends to user.
Optionally, referring to Fig. 4, before step S220, the method also includes:
S230: the negative-feedback log for the user that the client returns is received;The negative-feedback log includes user
The channel not liked and the reasons why not liking.
S240: the relevant historical negative-feedback number for the recommendation channel not liked with the user is obtained.
S250: according to the feedback time and the negative-feedback time of the negative-feedback log, the reception negative-feedback log
Number generates the preference information.
For example, when carrying out webpage recommending, the small high and sportsman Xiao Wang of the entitled sportsman for the content recommended
Table tennis match;For this kind of article, extracted keyword can be small high, Xiao Wang and table tennis match;When user does not like
When, interface will pop up these options, and user can choose one or more in these options.Choosing based on user's selection
, preference information is written into the option of user's selection, when to user's recommendation, will be masked in write-in preference information
Hold.But relatively do not want to take the trouble for certain customers, option will not be screened, an option write-in can be defaulted at random at this time
In the preference information.
In such as such as this article " platform matchmaker exposes star 1 and is caught also with 2 marriage of star at mystery ", technology can be identified first
The maximally related content of this article, for example be " amusement ", " star 1 ", " star 2 ", " content quality is poor " etc..These contents are to use
Family carries out the option that can be seen when negative-feedback.When article recommends user, and user does not like when carrying out negative-feedback operation, just
It can facilitate the reasons why user does not like this article accurately with these options.After user operates, time etc. can be believed
Breath is recorded in user preference information, and the article recommended again later will be filtered according to these signals
Optionally, referring to Fig. 5, if the client does not return to the negative-feedback log, the method also includes:
S231: determine that the highest first channel user of the degree of correlation described at least two channel does not like
Channel;
S232: determine that current time is the feedback time;
S233: the relevant historical negative-feedback number for the channel not liked with the user is obtained;
The preference information is generated according to first channel, the feedback time and the negative-feedback number.Into one
Step, every time to user's recommendation when, the field that institute's recommendation is related to can be not single field than wide,
But push the content in several fields to user together, avoid the received information of user excessively single, it is difficult to obtain user and like
Field.
For example, content when recommending every time to user can be with sports content, entertainment content, finance-content, military content etc.
Multiple contents in, according to the reasons why not liking, select subsequent push when user does not like certain a kind of content
Mode.
Such as: when the reasons why content recommended to the user is the change of team message of basket baller xx, and user does not like is xx;
At this point, xx is only recorded the preference information into user by system, system still can recommend the change of team of basket baller yy to user
Information.If the reasons why user does not like is basketball, the content in relation to basketball will not be recommended to user, but can be to user
Recommend football, table tennis or tennis etc..The hobby that the user can further be expanded in this way, makes the received message of user
More generalization.
Optionally, referring to Fig. 6, the embodiment of the invention provides a kind of content recommendation device 10, described device 10 includes:
Module 11 is obtained, for obtaining at least one recommendation to be recommended.
Confirmation module 12, for determining at least one described recommendation marked in the preference information including user
Second recommendation;Wherein, the preference information includes that the user does not like recommendation and feedback parameter;The feedback ginseng
Number includes feedback time and/or Times of Feedback.
Judgment module 13, for determining whether the feedback parameter meets preset condition.
Recommending module 14, for recommending described second to push away to the user when the feedback parameter meets preset condition
Recommend content.
Optionally, the judgment module 13, for determining whether the Times of Feedback is less than preset times;It determines described anti-
Present whether time gap current point in time is more than preset duration;Wherein, when the Times of Feedback is less than the preset times, or
Person characterizes the feedback parameter and meets the default item when the feedback time is more than preset duration apart from current point in time
Part.
Optionally, referring to Fig. 7, described device 10 further include:
Negative-feedback log acquisition module 110, the negative-feedback log of the user for receiving client return.It is described negative
The reasons why feedback log includes the recommendation that user does not like and does not like.
Negative-feedback number obtains module 112, and the relevant historical for obtaining the recommendation not liked with the user is negative
Times of Feedback.
Preference information obtains module 113, for according to the negative-feedback log, receive the feedback of the negative-feedback log when
Between and the negative-feedback number generate the preference information.
Optionally, the embodiment of the invention also provides a kind of electronic equipment, including processor and memory, the storages
Device is stored with computer-readable instruction fetch, and when the computer-readable instruction fetch is executed by the processor, operation is such as above-mentioned
Step in first aspect the method.
Fourth aspect, the embodiment of the invention also provides a kind of readable storage medium storing program for executing, are stored thereon with computer program, institute
State the step run in above-mentioned first aspect method when computer program is executed by processor.
A kind of content recommendation method and device, electronic equipment, readable storage medium storing program for executing provided in an embodiment of the present invention, comprising:
Obtain at least one recommendation to be recommended.Determine to include institute in the preference information of user at least one described recommendation
Second recommendation of mark.Wherein, the preference information includes that the user does not like recommendation and feedback parameter.It is described
Feedback parameter includes feedback time and/or Times of Feedback.Determine whether the feedback parameter meets preset condition.In the feedback
When parameter meets preset condition, recommend second recommendation to the user.By judging feedback time and/or feedback time
Whether number reaches preset condition to the second recommendation of lead referral, can grasp to avoid user due to not liking or missing in short term
Make and causes the second recommendation that can not receive.Therefore practicability is stronger, and more humanized.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of content recommendation method characterized by comprising
Obtain at least one recommendation to be recommended;
It include that the user marked in the preference information with user does not like at least one recommendation described in determining
Relevant second recommendation of first recommendation;Wherein, the preference information further includes feedback parameter;The feedback parameter packet
Include the feedback time and/or Times of Feedback for feeding back first recommendation;
Determine whether the feedback parameter of first recommendation meets preset condition;
When the feedback parameter meets preset condition, recommend second recommendation to the user.
2. content recommendation method according to claim 1, which is characterized in that whether the determination feedback parameter meets
Preset condition includes:
Determine whether the Times of Feedback is less than preset times;
Determine whether the feedback time apart from current point in time is more than preset duration;Wherein, it is less than institute in the Times of Feedback
When stating preset times, or when the feedback time is more than preset duration apart from current point in time, characterize the feedback parameter
Meet the preset condition.
3. content recommendation method according to claim 1, which is characterized in that in determining at least one described recommendation
Before second recommendation marked in negative-feedback log including user, the method also includes:
Highest at least two channel of the degree of correlation is determined according to the feature of the recommendation not liked;
It is respectively configured at least two channel and does not like reason;
At least two channel and the reason that do not like are sent to client.
4. content recommendation method according to claim 3, which is characterized in that described by least two channel and institute
It states and does not like reason and be sent to after the client, the method also includes:
Receive the negative-feedback log for the user that the client returns;The negative-feedback log includes the frequency that user does not like
Road and the reasons why not liking;
Obtain the relevant historical negative-feedback number for the recommendation channel not liked with the user;
According to the negative-feedback log, receive described in the feedback time and negative-feedback number generation of the negative-feedback log
Preference information.
5. content recommendation method according to claim 3, which is characterized in that if the client does not return to the negative-feedback
Log, the method also includes:
Determine that highest first channel of the degree of correlation described at least two channel is the channel that the user does not like;
Determine that current time is the feedback time;
Obtain the relevant historical negative-feedback number for the channel not liked with the user;
The preference information is generated according to first channel, the feedback time and the negative-feedback number.
6. a kind of content recommendation device, which is characterized in that described device includes:
Module is obtained, for obtaining at least one recommendation to be recommended;
Confirmation module is pushed away for marked in the preference information including user at least one determining described recommendation second
Recommend content;Wherein, the preference information includes that the user does not like recommendation and feedback parameter;The feedback parameter includes
Feedback time and/or Times of Feedback;
Judgment module, for determining whether the feedback parameter meets preset condition;
Recommending module, for recommending second recommendation to the user when the feedback parameter meets preset condition.
7. device according to claim 6, which is characterized in that the judgment module, for determining that the Times of Feedback is
It is no to be less than preset times;Determine whether the feedback time apart from current point in time is more than preset duration;Wherein, in the feedback
When number is less than the preset times, or when the feedback time is more than preset duration apart from current point in time, characterize institute
It states feedback parameter and meets the preset condition.
8. device according to claim 6, which is characterized in that described device further include:
Negative-feedback log acquisition module, the negative-feedback log of the user for receiving client return;The negative-feedback day
The reasons why will includes the recommendation that user does not like and does not like;
Negative-feedback number obtains module, for obtaining the relevant historical negative-feedback time for the recommendation not liked with the user
Number;
Preference information obtains module, for according to the negative-feedback log, receive the negative-feedback log feedback time and
The negative-feedback number generates the preference information.
9. a kind of electronic equipment, which is characterized in that including processor and memory, the memory is stored with computer-readable
Instruction fetch is executed when the computer-readable instruction fetch is run by the processor such as any claim in claim 1-5
Step in the method.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
It executes when being run by processor such as the step in any the method for claim 1-5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811054068.2A CN109145221B (en) | 2018-09-10 | 2018-09-10 | Content recommendation method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811054068.2A CN109145221B (en) | 2018-09-10 | 2018-09-10 | Content recommendation method and device, electronic equipment and readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109145221A true CN109145221A (en) | 2019-01-04 |
CN109145221B CN109145221B (en) | 2021-05-28 |
Family
ID=64824470
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811054068.2A Active CN109145221B (en) | 2018-09-10 | 2018-09-10 | Content recommendation method and device, electronic equipment and readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109145221B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111523050A (en) * | 2020-04-16 | 2020-08-11 | 咪咕文化科技有限公司 | Content recommendation method, server and storage medium |
CN111753182A (en) * | 2019-03-28 | 2020-10-09 | 北京达佳互联信息技术有限公司 | Multimedia information recommendation method and device, electronic equipment and readable storage medium |
CN111753177A (en) * | 2019-03-11 | 2020-10-09 | 阿里巴巴集团控股有限公司 | Personalized recommendation method and device and computer storage medium |
CN112906387A (en) * | 2020-12-25 | 2021-06-04 | 北京百度网讯科技有限公司 | Risk content identification method, apparatus, device, medium, and computer program product |
CN112905904A (en) * | 2019-11-19 | 2021-06-04 | 北京达佳互联信息技术有限公司 | Recommendation method, recommendation device, server and storage medium |
CN113343024A (en) * | 2021-08-04 | 2021-09-03 | 北京达佳互联信息技术有限公司 | Object recommendation method and device, electronic equipment and storage medium |
CN113518263A (en) * | 2021-07-23 | 2021-10-19 | 南京炫佳网络科技有限公司 | Video recommendation method and device for interactive network television, television and storage medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6138128A (en) * | 1997-04-02 | 2000-10-24 | Microsoft Corp. | Sharing and organizing world wide web references using distinctive characters |
CN1708986A (en) * | 2002-11-08 | 2005-12-14 | 皇家飞利浦电子股份有限公司 | Apparatus and method to provide a recommendation of content |
US20080294621A1 (en) * | 2007-05-25 | 2008-11-27 | Issar Amit Kanigsberg | Recommendation systems and methods using interest correlation |
CN101840301A (en) * | 2009-03-18 | 2010-09-22 | 索尼公司 | Signal conditioning package and information processing method |
US20130174189A1 (en) * | 2002-08-23 | 2013-07-04 | Microsoft Corporation | Media Recommendations Based on Negative Feedback |
CN103823908A (en) * | 2014-03-21 | 2014-05-28 | 北京飞流九天科技有限公司 | Method and server for content recommendation on basis of user preferences |
US20160292765A1 (en) * | 2015-04-01 | 2016-10-06 | Amazon Technologies, Inc. | Data collection for creating apparel size distributions |
CN106651448A (en) * | 2016-12-23 | 2017-05-10 | 腾讯科技(深圳)有限公司 | Advertisement information sending method, apparatus and system |
-
2018
- 2018-09-10 CN CN201811054068.2A patent/CN109145221B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6138128A (en) * | 1997-04-02 | 2000-10-24 | Microsoft Corp. | Sharing and organizing world wide web references using distinctive characters |
US20130174189A1 (en) * | 2002-08-23 | 2013-07-04 | Microsoft Corporation | Media Recommendations Based on Negative Feedback |
CN1708986A (en) * | 2002-11-08 | 2005-12-14 | 皇家飞利浦电子股份有限公司 | Apparatus and method to provide a recommendation of content |
US20080294621A1 (en) * | 2007-05-25 | 2008-11-27 | Issar Amit Kanigsberg | Recommendation systems and methods using interest correlation |
CN101840301A (en) * | 2009-03-18 | 2010-09-22 | 索尼公司 | Signal conditioning package and information processing method |
CN103823908A (en) * | 2014-03-21 | 2014-05-28 | 北京飞流九天科技有限公司 | Method and server for content recommendation on basis of user preferences |
US20160292765A1 (en) * | 2015-04-01 | 2016-10-06 | Amazon Technologies, Inc. | Data collection for creating apparel size distributions |
CN106651448A (en) * | 2016-12-23 | 2017-05-10 | 腾讯科技(深圳)有限公司 | Advertisement information sending method, apparatus and system |
Non-Patent Citations (2)
Title |
---|
蔡宇辰: ""一种基于负反馈的协同过滤推荐系统"", 《电脑知识与技术》 * |
邢星、贾志淳、杨玉强: ""一种基于用户反馈的时间感知推荐方法"", 《计算机工程与应用》 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111753177A (en) * | 2019-03-11 | 2020-10-09 | 阿里巴巴集团控股有限公司 | Personalized recommendation method and device and computer storage medium |
CN111753182A (en) * | 2019-03-28 | 2020-10-09 | 北京达佳互联信息技术有限公司 | Multimedia information recommendation method and device, electronic equipment and readable storage medium |
CN111753182B (en) * | 2019-03-28 | 2024-05-17 | 北京达佳互联信息技术有限公司 | Multimedia information recommendation method and device, electronic equipment and readable storage medium |
CN112905904A (en) * | 2019-11-19 | 2021-06-04 | 北京达佳互联信息技术有限公司 | Recommendation method, recommendation device, server and storage medium |
CN112905904B (en) * | 2019-11-19 | 2024-01-26 | 北京达佳互联信息技术有限公司 | Recommendation method, recommendation device, server and storage medium |
CN111523050A (en) * | 2020-04-16 | 2020-08-11 | 咪咕文化科技有限公司 | Content recommendation method, server and storage medium |
CN111523050B (en) * | 2020-04-16 | 2023-09-19 | 咪咕文化科技有限公司 | Content recommendation method, server and storage medium |
CN112906387A (en) * | 2020-12-25 | 2021-06-04 | 北京百度网讯科技有限公司 | Risk content identification method, apparatus, device, medium, and computer program product |
CN112906387B (en) * | 2020-12-25 | 2023-08-04 | 北京百度网讯科技有限公司 | Risk content identification method, apparatus, device, medium and computer program product |
CN113518263A (en) * | 2021-07-23 | 2021-10-19 | 南京炫佳网络科技有限公司 | Video recommendation method and device for interactive network television, television and storage medium |
CN113343024A (en) * | 2021-08-04 | 2021-09-03 | 北京达佳互联信息技术有限公司 | Object recommendation method and device, electronic equipment and storage medium |
CN113343024B (en) * | 2021-08-04 | 2021-12-07 | 北京达佳互联信息技术有限公司 | Object recommendation method and device, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN109145221B (en) | 2021-05-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109145221A (en) | Content recommendation method and device, electronic equipment, readable storage medium storing program for executing | |
CN104537115B (en) | The heuristic approach and device of user interest | |
US9165071B2 (en) | Method and system for indicating a validity rating of an entity | |
US9972055B2 (en) | Fact checking method and system utilizing social networking information | |
CN104769957B (en) | Identification and the method and apparatus that internet accessible content is presented | |
US9235603B2 (en) | Activity based search | |
WO2017000109A1 (en) | Search method, search apparatus, user equipment, and computer program product | |
CN103412881B (en) | The method and system of Search Results are provided | |
US20160105520A1 (en) | Method, apparatus, and system for pushing network content | |
US20120317046A1 (en) | Candidate fact checking method and system | |
US20170188093A1 (en) | Method and electronic device for grading-based program playing based on face recognition | |
CN106096366A (en) | A kind of information processing method, device and equipment | |
WO2019109724A1 (en) | Item recommendation method and device | |
US20170161391A1 (en) | Method and electronic device for video recommendation | |
WO2017167088A1 (en) | A user relationship based multimedia recommendation method and apparatus | |
CN105824961B (en) | A kind of label determines method and device | |
CN109982106A (en) | A kind of video recommendation method, server, client and electronic equipment | |
CN109005423A (en) | A kind of video broadcasting method and device | |
CN105095743B (en) | Method and device for setting locking strategy and electronic equipment | |
US10037550B2 (en) | System and method for identifying offline consumer interests for online personalization by leveraging multimedia inputs | |
CN111523041B (en) | Recommendation method of heat data, computing device and computer storage medium | |
US20170237727A1 (en) | System and method for a single field based authentication | |
US8610836B2 (en) | Electronic display device | |
KR101866964B1 (en) | Relay apparatus and method for streaming media | |
CN110909243A (en) | Television terminal content recommendation method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |