CN108093303A - A kind of video pushing method and device - Google Patents

A kind of video pushing method and device Download PDF

Info

Publication number
CN108093303A
CN108093303A CN201611042601.4A CN201611042601A CN108093303A CN 108093303 A CN108093303 A CN 108093303A CN 201611042601 A CN201611042601 A CN 201611042601A CN 108093303 A CN108093303 A CN 108093303A
Authority
CN
China
Prior art keywords
town
region
user
category
address
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.)
Pending
Application number
CN201611042601.4A
Other languages
Chinese (zh)
Inventor
张欢
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Excellent Friends Bullock Media Development Co
Original Assignee
Shenzhen Excellent Friends Bullock Media Development Co
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Excellent Friends Bullock Media Development Co filed Critical Shenzhen Excellent Friends Bullock Media Development Co
Priority to CN201611042601.4A priority Critical patent/CN108093303A/en
Publication of CN108093303A publication Critical patent/CN108093303A/en
Pending legal-status Critical Current

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/4508Management of client data or end-user data
    • H04N21/4524Management of client data or end-user data involving the geographical location of the client
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/466Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4668Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/60Network structure or processes for video distribution between server and client or between remote clients; Control signalling between clients, server and network components; Transmission of management data between server and client, e.g. sending from server to client commands for recording incoming content stream; Communication details between server and client 
    • H04N21/63Control signaling related to video distribution between client, server and network components; Network processes for video distribution between server and clients or between remote clients, e.g. transmitting basic layer and enhancement layers over different transmission paths, setting up a peer-to-peer communication via Internet between remote STB's; Communication protocols; Addressing
    • H04N21/64Addressing

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)

Abstract

An embodiment of the present invention provides a kind of video pushing method and device, to solve the problems, such as be user's pushing video in the prior art when there are video recommendations precision it is relatively low.Method includes:Obtain the common IP address of user, the common IP address of user is included in the IP address of user and distributed areas concentrate on the IP address under same geographic area;According to the administrative region and its town and country classification information included in the coverage of each common IP address, the town and country classification of user is determined, town and country classification includes city and rural area;It is user's pushing video with reference to the town and country classification of user.

Description

A kind of video pushing method and device
Technical field
The present invention relates to Internet technical field more particularly to a kind of video pushing methods and device.
Background technology
User by internet when appreciating video frequency program, and since video type is numerous, video is found in order to save user The time and efforts of program, while the audience ratings of video is improved, it can be to user's pushing video.
At present, it is normally based on the geography that Internet protocol (Internet Protocol, IP) address location of user arrives Position is user's pushing video, i.e., by inquiring about IP address information bank, determines the provincial, and municipal level belonging to the IP address that user uses, then The factors such as the audience ratings with reference to video in the provincial, and municipal level recommend video for user.Since the geographic range of provincial, and municipal level covering is larger, And Geographic mapping precision is relatively low, when the relevant information with reference to provincial, and municipal level is that user recommends video, the video of recommendation is not easy It is easily accepted by a user, the precision of video recommendations is relatively low, and then causes video push ineffective.
Therefore, in the prior art for user's pushing video when there are video recommendations precision it is relatively low the problem of.
The content of the invention
The embodiment of the present invention provides a kind of video pushing method and device, to solve in the prior art as user's pushing video When there are video recommendations precision it is relatively low the problem of.
In a first aspect, the embodiment of the present invention provides a kind of video pushing method, including:
Obtain the common IP address of user, the common IP address of user includes in the IP address of user and distributed areas collection In IP address under same geographic area;
According to the administrative region and its town and country classification information included in the coverage of each common IP address, determine to use The town and country classification at family, town and country classification include city and rural area;
It is user's pushing video with reference to the town and country classification of user.
In a kind of possible design, determine the administrative region included in the coverage of each common IP address and its The method of town and country classification information, specifically includes:
Based on third party's geo-location interface, inquiry obtains the coverage of each common IP address;
Determine the town and country classification of each administrative region included in the coverage of each common IP address.
In a kind of possible design, according to the administrative region included in the coverage of each common IP address and its Town and country classification information determines the town and country classification of user, specifically includes:
The capped number of each administrative region included in the coverage of each common IP address is determined respectively, it is administrative The capped number in region is equal to the summation of the number of the coverage covering administrative region of the common IP address of user;
According to the capped number of administrative region, the administrative region included in the coverage to commonly using IP address is divided Class, each category regions include at least one administrative region;
The town and country classification of each administrative region, calculates at least one administrative region included according to each category regions To the corresponding town and country classification of each category regions;
The town and country classification of user is determined according to the corresponding town and country classification of each category regions.
In a kind of possible design, according to the capped number of administrative region, in the coverage to commonly using IP address Comprising administrative region classify, including:
It is first category region by the administrative division that capped number is greater than or equal to first number threshold value;
Capped number is greater than or equal to second number threshold value and less than the administrative division of first number threshold value For second category region;
It is the 3rd category regions by the administrative division that capped number is less than second number threshold value;
The town and country classification of user is determined according to the corresponding town and country classification of each category regions, is specifically included:
When the corresponding town and country classification in first category region town and country classification corresponding with second category region is identical, by the first kind The corresponding town and country classification in other region is determined as the town and country classification of user;
During corresponding with the second category region town and country classification difference of the corresponding town and country classification in first category region, calculate respectively The probability of the probability in first category region, the probability in second category region and the 3rd category regions, by the highest classification area of probability The corresponding town and country classification in domain is determined as the town and country classification of user.
In a kind of possible design, the corresponding town and country classification in first category region town and country corresponding with second category region During classification difference, probability, the probability and three classes in second category region in first category region are calculated respectively by the following formula The probability in other region:
Probability=(areas for the administrative region number * category regions that category regions include)/(all categories region includes The gross area for the administrative region that administrative region sum * all categories region includes) * constants.
In a kind of possible design, with reference to the town and country classification of user, it is user's pushing video, specifically includes:
The historical data of different type video is watched according to the town and country classification of user and user, evaluates user to inhomogeneity The fancy grade of type video;
It is user's pushing video according to user to the fancy grade of different type video.
Second aspect, the embodiment of the present invention provide a kind of video push device, including:
Acquiring unit, for obtaining the common IP address of user, the common IP address of user includes in the IP address of user, And distributed areas concentrate on the IP address under same geographic area;
Determination unit, for determining the administration included in the coverage of each common IP address of acquiring unit acquisition Region and its town and country classification information;The administration included in the coverage of each common IP address obtained according to acquiring unit Region and its town and country classification information, determine the town and country classification of user, and town and country classification includes city and rural area;
Push unit is user's pushing video for the town and country classification of the user determined with reference to determination unit.
In a kind of possible design, determination unit is in the row for determining to be included in each coverage for commonly using IP address When administrative division domain and its town and country classification information, it is specifically used for:
Based on third party's geo-location interface, inquiry obtains the coverage of each common IP address;
Determine the town and country classification of each administrative region included in the coverage of each common IP address.
In a kind of possible design, row that determination unit is included in the coverage according to each common IP address Administrative division domain and its town and country classification information when determining the town and country classification of user, are specifically used for:
The capped number of each administrative region included in the coverage of each common IP address is determined respectively, it is administrative The capped number in region is equal to the summation of the number of the coverage covering administrative region of the common IP address of user;
According to the capped number of administrative region, the administrative region included in the coverage to commonly using IP address is divided Class, each category regions include at least one administrative region;
The town and country classification of each administrative region, calculates at least one administrative region included according to each category regions To the corresponding town and country classification of each category regions;
The town and country classification of user is determined according to the corresponding town and country classification of each category regions.
In a kind of possible design, determination unit is in the capped number according to administrative region, to commonly using IP address The administrative region included in coverage is classified, and is specifically used for:
It is first category region by the administrative division that capped number is greater than or equal to first number threshold value;
Capped number is greater than or equal to second number threshold value and less than the administrative division of first number threshold value For second category region;
It is the 3rd category regions by the administrative division that capped number is less than second number threshold value;
Determination unit is specific to use when determining the town and country classification of user according to the corresponding town and country classification of each category regions In:
When the corresponding town and country classification in first category region town and country classification corresponding with second category region is identical, by the first kind The corresponding town and country classification in other region is determined as the town and country classification of user;
During corresponding with the second category region town and country classification difference of the corresponding town and country classification in first category region, calculate respectively The probability of the probability in first category region, the probability in second category region and the 3rd category regions, by the highest classification area of probability The corresponding town and country classification in domain is determined as the town and country classification of user.
In a kind of possible design, the corresponding town and country classification in first category region town and country corresponding with second category region During classification difference, probability, the probability and three classes in second category region in first category region are calculated respectively by the following formula The probability in other region:
Probability=(areas for the administrative region number * category regions that category regions include)/(all categories region includes The gross area for the administrative region that administrative region sum * all categories region includes) * constants.
In a kind of possible design, push unit is combining the town and country classification for the user that determination unit determines, is user During pushing video, it is specifically used for:
The town and country classification of the user determined according to determination unit and user watch the historical data of different type video, assessment Go out fancy grade of the user to different type video;
It is user's pushing video according to user to the fancy grade of different type video.
In a kind of video pushing method provided in an embodiment of the present invention and device, the common IP address of user is obtained, is used In IP address of the common IP address at family including user and distributed areas concentrate on the IP address under same geographic area, determine The administrative region included in the coverage of each common IP address and its town and country classification information, according to each common IP address Coverage in the administrative region that is included and its town and country classification information determine the town and country classification of user, town and country classification includes city City and rural area are user's pushing video with reference to the town and country classification of user.By method and device provided in an embodiment of the present invention, The precision of Geographic mapping can be improved, realize for user recommend video when video recommendations precision raising, solve For user's pushing video when there are video recommendations precision it is relatively low the problem of.
Description of the drawings
Fig. 1 is a kind of flow diagram of video pushing method provided in an embodiment of the present invention;
Fig. 2 is a kind of flow diagram of the town and country classification method of definite user provided in an embodiment of the present invention;
Fig. 3 is a kind of structure diagram of common IP address cover provided in an embodiment of the present invention;
Fig. 4 is the structure diagram of another common IP address cover provided in an embodiment of the present invention;
Fig. 5 is a kind of structure diagram of video push device provided in an embodiment of the present invention;
Fig. 6 is the structure diagram of another video push device provided in an embodiment of the present invention.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, is not whole embodiments.It is based on Embodiment in the present invention, those of ordinary skill in the art are obtained every other without making creative work Embodiment belongs to the scope of protection of the invention.
The embodiment of the present invention is suitable for the scene of video push, and video push scene refers to that user appreciates by internet During video frequency program, the time and efforts of video frequency program is found in order to save user, while improves the audience ratings of video, is pushed away to user Send video.In order to solve the problems, such as in the prior art be user's pushing video when there are video recommendations precision it is relatively low, this hair Bright embodiment provides a kind of video pushing method and device.
The each embodiment of the present invention is described in detail with reference to Figure of description.It is it should be noted that of the invention The displaying order of embodiment only represents the sequencing of embodiment, does not represent the quality for the technical solution that embodiment is provided.
Embodiment one:
An embodiment of the present invention provides a kind of video pushing method, as shown in Figure 1, this method includes:
Step 101:Obtain the common IP address of user, the common IP address of the user include in the IP address of user and Distributed areas concentrate on the IP address under same geographic area.
The IP address of user can embody user using IP when where geographical location, the common IP address of user include but It is not limited to:Distributed areas concentration, the IP address under same geographic area in the IP address of user.It can be realized by the following method Obtain the common IP address of user:
Obtain at least one IP address that user uses.Such as when can obtain user from the authentication record of user and logging in Used IP address preserves related data when user logs in every time in the authentication record of user, every including user Secondary used IP address when logging in.It, can be from the authentication information of user since user may be logged in by different terminals Obtain at least one IP address that user uses.
After obtaining at least one IP address that user uses, determine the geographical distribution situation of at least one IP address, lead to Cross IP address can navigate to user using the IP address when where geographical location;According to the ground of definite at least one IP address Distribution situation is managed, distributed areas at least one IP address is chosen and concentrates on IP address under same geographic area as user Common IP address.
Exemplified by being same city by same geographic area, at least one IP address of IP address information library inquiry user is utilized Geographical distribution, including user use IP address when where province, city rank geographical location.If at least one IP that user uses More than 80% integrated distribution of geographical location that each IP address navigates in address then chooses location distribution in same city Common IP address of the IP address as the user in the city.
In the present embodiment determine user at least one IP address geographical distribution situation method include but not limited to Under type:Published IP address information bank, such as ipip.net, purity IP storehouses are inquired about, inquires about the official of IP address distributor gear Party database, as Asia Pacific Internet Information Center (Asia-Pacific Network Information Centre, APNIC) etc..
Optionally, if the location distribution that navigates to of the IP address that user uses is different at two or more Geographic area, and the IP address quantity of two or more regional distributions is close, then with illustrating the IP of the user Location does not have integrated distribution in same geographic area, can do abnormality processing to the user at this time.Abnormality processing can include not adopting It is user's pushing video with method provided in this embodiment, the prior art can be used as user's pushing video;Abnormality processing also may be used To include choosing the common IP address of user by other methods.
It should be noted that in the present embodiment after the geographical distribution situation of at least one IP address of user is determined, The method that common IP address is chosen at least one IP address includes but is not limited to the method for above-mentioned offer, can also adopt With other methods, such as can be according to the geographical distribution situation of at least one IP address of user, with choosing at least one IP Common IP address of IP address of the integrated distribution under two geographic areas as user in location.
In the embodiment of the present invention, at least one IP address of user is obtained, and determine at least one IP address of user Geographical distribution situation chooses at least one IP address IP address of the integrated distribution under same geographic area as the normal of user With IP address, give up other non-common IP address, reduce standard of these non-common IP address to user's Geographic mapping The influence of true property.
Step 102:Believed according to the administrative region included in the coverage of each common IP address and its town and country classification Breath determines the town and country classification of the user.
In the present embodiment, the town and country classification of user can include city and rural area.According to actual conditions, the town and country class of user Other classifications can also not included.
Can be realized by the following method the administrative region that is included in the coverage according to each common IP address and its Town and country classification information determines the town and country classification of the user:
Step 1:Determine the coverage of common IP address.
The coverage of each common IP address is the geographical coverage area belonging to each common IP address.Due to IP address Distribution there is dynamic, equiprobable is distributed in geographical location corresponding to IP address positions corresponding longitude and latitude with the IP address In geographical coverage area centered on degree, the geographical location where the IP address may be the geographic area model belonging to the IP address Interior any point is enclosed, i.e. geographical location where the IP address may be any point in the coverage of the IP address.
For each common IP address, using by third party's real time bidding data (Real Time Bidding Asia, RTBAsia) the RTBAsia geo-locations interface polls that provider provides commonly use the coverage of IP address, coverage to this Longitude and latitude Range Representation can be used, such as commonly use point, the circle of radius R centered on the value of the corresponding longitude of IP address, latitude The coverage of IP address is commonly used as this in domain.
It should be noted that for each common IP address in the present embodiment, except utilizing RTBAsia geo-location interfaces Outside the coverage for inquiring the common IP address, other third party's interfaces or data base querying can also be utilized common to this The coverage of IP address.
Step 2:Determine the town and country classification of each administrative region included in the coverage of each common IP address.
The latitude and longitude information and town and country division code corresponding to national different administrative regions can be obtained in advance, administrative region Town and country division code is used to indicate the town and country classification of the administrative region.For the coverage of each common IP address, according to covering The latitude and longitude information of the corresponding longitude and latitude scope of lid scope administrative region different with the whole nation, determines what is included in the coverage Administrative region divides code further according to the town and country of the administrative region included in coverage, determines to be included in coverage Administrative region town and country classification.
Step 3:Believed according to the administrative region included in the coverage of each common IP address and its town and country classification Breath determines the town and country classification of user.
Since the common IP address of user can have rows that are multiple, and being included in the coverage of each common IP address Administrative division domain can have the coverage of multiple, different common IP address there may be overlapping, cause same administrative region may By the coverage multi-fold of different common IP address, therefore it is non-equal-probability distribution that user, which is located in different administrative regions, 's.In view of this factor, as shown in Fig. 2, the town and country classification for determining user can be realized by following steps:
Step 201:The coating of each administrative region included in the coverage of each common IP address is determined respectively Lid number.
For each administrative region included in the coverage of each common IP address, the administrative region is counted respectively Capped number.For any one administrative region, calculating the method for the capped number of the administrative region includes:Work as administration When region is covered by the coverage of a common IP address, the capped number of the administrative region adds one, the quilt of administrative region Degree of covering covers the summation of the number of the administrative region equal to the coverage of the common IP address of user.
The each administrative region included in the coverage of each common IP address can only be by same common IP address Coverage covering once, and the administrative region at least by the coverage covering of common IP address once, so appointing The maximum of the capped number value of each administrative region included in the coverage for a common IP address of anticipating is normal With the number of IP address, minimum value 1.
For example, the common IP address of a user has IP1, IP2, IP3, the covering of the common IP address of definite the user In the range of the administrative region that is included as shown in Table 1.
Table one
Common IP address The administrative region included in the coverage of common IP address
IP1 Administrative region A, B, C, D
IP2 Administrative region A, B, E
IP3 Administrative region A, C, F
Pass through table one:The capped number of administrative region A is 3 times, and the capped number of administrative region B, C are 2 times, The capped number of administrative region D, E, F are 1 time.
Step 202:According to the capped number of administrative region, the administration to being included in the coverage of common IP address Region is classified, and each category regions include at least one administrative region.
After the capped number of each administrative region included in the coverage for determining each common IP address, press According to the capped number of administrative region, the administrative region included in the coverage of common IP address is divided into following three classes:
It is first category region by the administrative division that capped number is greater than or equal to first number threshold value;
Capped number is greater than or equal to second number threshold value and less than the administrative division of first number threshold value For second category region;
It is the 3rd category regions by the administrative division that capped number is less than second number threshold value;
Wherein, the quantity of each category regions including administrative region is at least one, first number threshold value and second number Threshold value can be set according to actual needs.
For example, first number threshold value to be arranged to the number of common IP address, second number threshold value is arranged to common IP The half of address number.At this point, according to the capped number of administrative region, by what is included in the coverage of common IP address Administrative region is divided into following three classes:
The administrative division that capped number is equal to the number of common IP address is first category region, the i.e. first kind The administrative region that other region includes is covered by the coverage of all common IP address.
Capped number is greater than or equal to the half of common IP address number and less than the administration of common IP address number Region division is second category region, i.e., the administrative region that second category region includes is by the coverage half of common IP address Above geographical coverage area is covered.
The administrative division that capped number is less than to the half of common IP address number is the 3rd category regions, i.e., the By the coverage of common IP address, the geographical coverage area of less than half covers for the administrative region that three category regions include.
By taking table one as an example, first category region include administrative region A, second category region include administrative region B, C, the 3rd Category regions include administrative region region D, E, F.
By taking Fig. 3 as an example, a border circular areas represents the coverage of a common IP address, a delta domain representation Town and country classification is the administrative region of rural one, and square region domain representation town and country classification is an administrative region in city. Administrative region all in Fig. 3 is divided into three classes by the capped number of administrative region:The part of three border circular areas overlappings Represent first category region, the part of any two border circular areas overlapping represents second category region, any one border circular areas Individually part represents the 3rd category regions.
It should be noted that the quilt of the administrative region in the present embodiment in the case where determining the coverage covering of common IP address It, can also be by setting except the administrative region under the coverage of common IP address is covered is divided into three classes after degree of covering Put the administrative region under first number threshold value and second number threshold value cover the coverage of common IP address be divided into two classes or Other more than two classes classifications.
Step 203:The town and country class of each administrative region at least one administrative region included according to each category regions Not, the corresponding town and country class of each category regions is calculated using k nearest neighbor (K-Nearest Neighbor, KNN) sorting algorithm Not.
For any one category regions, the corresponding town and country classification in category region can be obtained by following steps:
Step 1:Inside a category regions, the center geographical location for the administrative region that category region includes is taken to make Centered on point, which represents the administrative region belonging to it;Again by the central point with it belonging to the adjacent institute in administrative region The central point for having administrative region is connected, and category region is divided into several broken line triangle regions.
As shown in figure 4, a border circular areas represents the coverage of a common IP address, a delta domain representation Town and country classification is the administrative region of rural one, and square region domain representation town and country classification is an administrative region in city, The first category region of three border circular areas overlappings is divided into several broken line triangle regions.
Step 2:The town and country classification in each broken line triangle region in category regions is determined respectively.
For any one broken line triangle region, determining the town and country class method for distinguishing in the broken line triangle region includes: Choose the city of the administrative region in broken line triangle region belonging to two or more vertex (i.e. the central point of administrative region) Town and country classification of township's classification as the broken line triangle region.For example, when broken line triangle region there are two or two with When the town and country classification of administrative region belonging to upper vertex is city, then the town and country classification in the broken line triangle region is city.
Step 3:According to the town and country classification in each broken line triangle region in a category regions, the category is determined respectively The town and country classification in region is the probability in city and the town and country classification in category region is rural probability.
Exemplified by calculating the town and country classifications of category regions as the probability in city, it is city to calculate town and country classification in category region The sum of the area in all broken line triangle regions N in the sum of the area in all broken line triangle regions in city M and category region, Ratio is as the probability that the town and country classification in category region is city using M and N.Wherein, using in broken line triangle region three The distance between a vertex calculates the area in the broken line triangle region.Similarly, the town and country classification of category regions can be calculated Belong to rural probability.
Step 4:It is that rural is general in the probability and the town and country classification of category regions that the town and country classification of category regions is city In rate, town and country classification of the corresponding town and country classification of greater probability as category region is selected.
For example, in Fig. 3 first category region as shown in figure 4, there is 10 broken line triangle regions in first category region, The town and country classification for wherein having the administrative region there are two 6 broken line triangle regions or belonging to more than two vertex is city, because The town and country classification in this this 6 broken line triangle region is city.Calculate the sum of area in this 6 broken line triangle regions and first The ratio of the area of category regions, the ratio are that the town and country classification in first category region is the probability in city, similarly, can be calculated Town and country classification to first category region is rural probability.When the town and country classification in first category region is more than for the probability in city When the town and country classification in first category region is rural probability, then the town and country classification in first category region is city;Conversely, first The town and country classification of category regions is rural area.
It should be noted that each classification including but not limited to is calculated using KNN sorting algorithms in the present embodiment The corresponding town and country classification in region.
Step 204:Based on probability statistics, the town and country class of user is determined according to the corresponding town and country classification of each category regions Not.
Since the corresponding geographical location of user has high probability to be distributed in by time of the coverage covering of common IP address In the more administrative region of number, so the corresponding geographical location of user has high probability to be distributed in first category region and the second class In other region.Therefore in town and country classification corresponding according to each category regions, if the corresponding town and country classification in first category region Town and country classification corresponding with second category region is identical, then the corresponding town and country classification in first category region is determined as to the city of user Township's classification.
If the corresponding town and country classification in first category region town and country classification corresponding from second category region is different, due to user Corresponding location distribution is substantially non-equal, therefore calculates the town and country classification category of user respectively by the following formula In first category region, second category region, the corresponding town and country classification of the 3rd category regions probability, choose the highest class of probability Town and country classification of the corresponding town and country classification in other region as the user:
Probability=(areas for the administrative region number * category regions that category regions include)/(all categories region includes The gross area for the administrative region that administrative region sum * all categories region includes) * constants.
Wherein, constant can be pre-set, and the value range of constant is between 0 to 1.For example, in above-mentioned formula, first category The constant in region is 0.6, and the constant in second category region is 0.3, and the constant of the 3rd category regions is 0.1.
By taking Fig. 4 as an example, it is assumed that the corresponding town and country classification in first category region be city, the corresponding town and country in second category region Classification is rural area, and the corresponding town and country classification of the 3rd category regions is rural area, then the corresponding town and country classification in first category region and the The corresponding town and country classification of two category regions is different.The town and country classification for calculating user respectively belongs to first category region, second category Region, the probability of the corresponding town and country classification of the 3rd category regions:
The probability of the corresponding town and country classification in first category region=(areas of 10* category regions)/(28* all categories area The gross area for the administrative region that domain includes) * 0.6;
The probability of the corresponding town and country classification in second category region=(areas of 7* category regions)/(28* all categories region Including administrative region the gross area) * 0.3;
The probability of the corresponding town and country classification of 3rd category regions=(areas of 11* category regions)/(28* all categories area The gross area for the administrative region that domain includes) * 0.1.
According to above-mentioned result of calculation, probability, the second class from the corresponding town and country classification in first category region calculated In the probability of the corresponding town and country classification in other region, the probability of the corresponding town and country classification of the 3rd category regions, it is highest to choose probability Town and country classification of the corresponding town and country classification of category regions as the user.
Step 103:It is user's pushing video with reference to the town and country classification of user.
The historical data that different type video is watched according to all users determines initial score matrix, wherein the initial score Element representation user in matrix watches the initial score of video, which, which is equal to, refers to user's viewing video length and video The fraction that the ratio of total duration is converted to, fraction are taken between 1 to 10.For example, a user watches the duration of fashion video with being somebody's turn to do The ratio of fashion video total duration is 3/5, then the user is 6 for the initial score of fashion video.
In initial score matrix, the initial of different video type is commented with the same user of each element representation in a line Point, the number of elements that a line includes is equal to the quantity of video type;Each element representation different user is regarded to same in same row The initial score of frequency type, the number of elements that a row include are equal to the quantity of user.Since user may not watch all classes The video of type, so alternating least-squares (Alternating can be used there are unknown element in the initial score matrix Least Squares, ALS) collaborative filtering solve unknown element in initial score matrix, be calculated it is complete just Beginning rating matrix.Wherein, the specific meaning that the row and column of initial score matrix represents can exchange.
The operation principle of the collaborative filtering of ALS is in the embodiment of the present invention:User is initially commented different types of After sub-matrix A is similar to two matrix Us, the product of V, use norm (Frobenius) | | A-UVT | | it is missed to quantify reconstruct Difference, i.e., the error sum of squares between each element and reconstruct.ALS first random can generate U (0), then fix it and solve V (0), Fixed V (0) solves U (1), so alternately goes down.Because reconstructed error can be all reduced per single-step iteration, and error is that have Lower bound, so ALS is bound to restrain, and then solve the unknown element in initial score matrix A.
According to the town and country classification of user, the user of different town and country classifications is set to watch corresponding scoring power during video respectively Weight, scoring weight represent that the user of different town and country classifications watches the ratio of different type video.By the scoring weight of urban subscriber 1 is arranged to, the scoring weight of rural user is arranged to B, and B is that rural user regards different video type compared with urban subscriber The viewing ratio of frequency, the numerical values recited of B can be set according to type video.
It is seen for example, table two is the city/rural area user counted according to the historical data of user's viewing different type video See the ratio of different type video, the secondary series of table two represents that the urban subscriber of viewing different video type accounts for all urban subscribers Ratio, the 3rd row of table two represent that the rural user of viewing different video type accounts for the ratio of all rural users, table two 4th row represent rural user compared with urban subscriber to the viewing ratio of the video of different video type.
Table two
In the initial score matrix after the solution of ALS collaborative filterings, user is chosen to all video types Initial score, with reference to the town and country classification of the user, by the user to the initial score of all video types and the scoring of the user Multiplied by weight evaluates fancy grade of the user to different type video.It chooses in the highest video type of fancy grade Video pushes for the user.
Wherein, urban subscriber for a type video fancy grade directly by the urban subscriber in initial score matrix In corresponding initial score represent that rural user is initially commenting for the fancy grade of a type video equal to rural area user Corresponding initial score is multiplied by B in sub-matrix.
Preferably, for user's pushing video when, can also according to user watch video historical data, filter out the use The video being had already viewed in the highest video type of family fancy grade scoring, the video do not watched for user's push.
It should be noted that after evaluating user in the present embodiment to the fancy grade of all video types, can also lead to It is the user's push that the fancy grade for choosing user, which is crossed, higher than other methods such as the videos in the video type of predetermined threshold value.
In a kind of pushing video method that the embodiment of the present invention proposes, the common IP address of user is obtained, user's is common In IP address of the IP address including user and distributed areas concentrate on the IP address under same geographic area, determine each common The administrative region included in the coverage of IP address and its town and country classification information, according to the covering model of each common IP address It encloses interior included administrative region and its town and country classification information determines the town and country classification of user, town and country classification includes city and township Village is user's pushing video with reference to the town and country classification of user.Therefore, by method provided in an embodiment of the present invention, can improve The precision of Geographic mapping, realize for user recommend video when video recommendations precision raising, solve to push away for user When sending video there are video recommendations precision it is relatively low the problem of.
Embodiment two:
With reference to above example one, the embodiment of the present invention additionally provides a kind of video push device, the video push device The method that the corresponding embodiments of Fig. 1 provide can be realized, as shown in fig.5, video push device 500 includes:Acquiring unit 501st, determination unit 502, push unit 503.
Acquiring unit 501, for obtaining the common IP address of user, the common IP address of user includes the IP address of user In and distributed areas concentrate on IP address under same geographic area;
Determination unit 502, for determining to be included in the coverage of each common IP address of the acquisition of acquiring unit 501 Administrative region and its town and country classification information;Institute in each coverage for commonly using IP address obtained according to acquiring unit 501 Comprising administrative region and its town and country classification information, determine the town and country classification of user, town and country classification includes city and rural area;
Push unit 503 is user's pushing video for combining the town and country classification for the user that determination unit 502 determines.
Optionally, determination unit 502 is included in the coverage for determining each common IP address administrative region and During its town and country classification information, it is specifically used for:
Based on third party's geo-location interface, inquiry obtains the coverage of each common IP address;
Determine the town and country classification of each administrative region included in the coverage of each common IP address.
Optionally, determination unit 502 is included in the coverage according to each common IP address administrative region and Its town and country classification information when determining the town and country classification of user, is specifically used for:
The capped number of each administrative region included in the coverage of each common IP address is determined respectively, it is administrative The capped number in region is equal to the summation of the number of the coverage covering administrative region of the common IP address of user;
According to the capped number of administrative region, the administrative region included in the coverage to commonly using IP address is divided Class, each category regions include at least one administrative region;
The town and country classification of each administrative region, calculates at least one administrative region included according to each category regions To the corresponding town and country classification of each category regions;
The town and country classification of user is determined according to the corresponding town and country classification of each category regions.
Optionally, determination unit 502 is in the capped number according to administrative region, the coverage to commonly using IP address Comprising administrative region classify, be specifically used for:
It is first category region by the administrative division that capped number is greater than or equal to first number threshold value;
Capped number is greater than or equal to second number threshold value and less than the administrative division of first number threshold value For second category region;
It is the 3rd category regions by the administrative division that capped number is less than second number threshold value;
Determination unit 502 according to the corresponding town and country classification of each category regions when determining the town and country classification of user, specifically For:
When the corresponding town and country classification in first category region town and country classification corresponding with second category region is identical, by the first kind The corresponding town and country classification in other region is determined as the town and country classification of user;
During corresponding with the second category region town and country classification difference of the corresponding town and country classification in first category region, calculate respectively The probability of the probability in first category region, the probability in second category region and the 3rd category regions, by the highest classification area of probability The corresponding town and country classification in domain is determined as the town and country classification of user.
Optionally, during corresponding with the second category region town and country classification difference of the corresponding town and country classification in first category region, Calculate the general of the probability in first category region, the probability in second category region and the 3rd category regions respectively by the following formula Rate:
Probability=(areas for the administrative region number * category regions that category regions include)/(all categories region includes The gross area for the administrative region that administrative region sum * all categories region includes) * constants.
Optionally, push unit 503 is combining the town and country classification for the user that determination unit 502 determines, is regarded for user's push During frequency, it is specifically used for:
The town and country classification of the user determined according to determination unit and user watch the historical data of different type video, assessment Go out fancy grade of the user to different type video;
It is user's pushing video according to user to the fancy grade of different type video.
It is only a kind of logic function it should be noted that being schematical to the division of unit in the embodiment of the present invention Division, can there is other dividing mode in actual implementation.In addition, each functional unit in each embodiment of the application can be with It is integrated in a processing unit or unit is individually physically present, it can also two or more unit collection Into in a unit.The form that hardware had both may be employed in above-mentioned integrated unit is realized, can also use SFU software functional unit Form realize.
If the integrated unit is realized in the form of SFU software functional unit and is independent production marketing or use When, it can be stored in a computer read/write memory medium.Based on such understanding, the technical solution of the application is substantially The part to contribute in other words to the prior art or all or part of the technical solution can be in the form of software products It embodies, which is stored in a storage medium, is used including some instructions so that a computer It is each that equipment (can be personal computer, server or the network equipment etc.) or processor (processor) perform the application The all or part of step of embodiment the method.And foregoing storage medium includes:USB flash disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disc or CD Etc. the various media that can store program code.
Based on above example, the embodiment of the present invention additionally provides a kind of video push device, which can It realizes the method that the corresponding embodiments of Fig. 1 provide, can be identical equipment with the video push device shown in Fig. 5.Refering to Fig. 6 Shown, video push device 600 includes:Processor 601, communication interface 602, bus 603 and memory 604, wherein:
Processor 601 for reading the program in memory 604, performs following process:
Processor 601, for obtaining the common IP address of user, the common IP address of user includes the IP address of user In and distributed areas concentrate on IP address under same geographic area;
Processor 601, for determining the administrative region and its town and country that are included in the coverage of each common IP address Classification information;According to the administrative region and its town and country classification information included in the coverage of each common IP address, determine The town and country classification of user, town and country classification include city and rural area;
Processor 601 is user's pushing video for combining the town and country classification of definite user.
Optionally, processor 601 is included in the coverage for determining each common IP address administrative region and its During the classification information of town and country, it is specifically used for:
Based on third party's geo-location interface, inquiry obtains the coverage of each common IP address;
Determine the town and country classification of each administrative region included in the coverage of each common IP address.
Optionally, processor 601 is included in the coverage according to each common IP address administrative region and its Town and country classification information when determining the town and country classification of user, is specifically used for:
The capped number of each administrative region included in the coverage of each common IP address is determined respectively, it is administrative The capped number in region is equal to the summation of the number of the coverage covering administrative region of the common IP address of user;
According to the capped number of administrative region, the administrative region included in the coverage to commonly using IP address is divided Class, each category regions include at least one administrative region;
The town and country classification of each administrative region, calculates at least one administrative region included according to each category regions To the corresponding town and country classification of each category regions;
The town and country classification of user is determined according to the corresponding town and country classification of each category regions.
Optionally, processor 601 wraps in the capped number according to administrative region, the coverage to commonly using IP address The administrative region contained is classified, and is specifically used for:
It is first category region by the administrative division that capped number is greater than or equal to first number threshold value;
Capped number is greater than or equal to second number threshold value and less than the administrative division of first number threshold value For second category region;
It is the 3rd category regions by the administrative division that capped number is less than second number threshold value;
Processor 601 is specific to use when determining the town and country classification of user according to the corresponding town and country classification of each category regions In:
When the corresponding town and country classification in first category region town and country classification corresponding with second category region is identical, by the first kind The corresponding town and country classification in other region is determined as the town and country classification of user;
During corresponding with the second category region town and country classification difference of the corresponding town and country classification in first category region, calculate respectively The probability of the probability in first category region, the probability in second category region and the 3rd category regions, by the highest classification area of probability The corresponding town and country classification in domain is determined as the town and country classification of user.
Optionally, during corresponding with the second category region town and country classification difference of the corresponding town and country classification in first category region, Calculate the general of the probability in first category region, the probability in second category region and the 3rd category regions respectively by the following formula Rate:
Probability=(areas for the administrative region number * category regions that category regions include)/(all categories region includes The gross area for the administrative region that administrative region sum * all categories region includes) * constants.
Optionally, processor 601 is combining the town and country classification of user, when being user's pushing video, is specifically used for:
The town and country classification of the user determined according to determination unit and user watch the historical data of different type video, assessment Go out fancy grade of the user to different type video;
It is user's pushing video according to user to the fancy grade of different type video.
Communication interface 602, under the control of processor 601, sending and receiving data.
Processor 601, communication interface 602 and memory 604 are connected with each other by bus 603;Bus 603 can be outer If component connection standard (peripheral component interconnect, PCI) bus or expanding the industrial standard structure (extended industry standard architecture, EISA) bus etc..It is total that the bus can be divided into address Line, data/address bus, controlling bus etc..
Wherein, in figure 6, bus architecture can include the bus and bridge of any number of interconnection, specifically by processor 601 The various circuits for the memory that the one or more processors and memory 604 of representative represent link together.Bus architecture is also Various other circuits of such as peripheral equipment, voltage-stablizer and management circuit or the like can be linked together, these are all It is it is known in the art, therefore, no longer it is described further herein.Bus interface provides interface.Communication interface 602 It can be multiple element, i.e., including transmitter and communication interface, provide to communicate with various other devices over a transmission medium Unit.Processor 601 is responsible for bus architecture and common processing, and memory 604 can store processor 601 and perform Used data during operation.
Optionally, processor 601 can be central processing unit, application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-Programmable Gate Array, ) or Complex Programmable Logic Devices (Complex Programmable Logic Device, CPLD) FPGA.
By a kind of video push device provided in an embodiment of the present invention, video when recommending video for user can be realized The raising of the precision of recommendation, solve the problems, such as user's pushing video when there are video recommendations precision it is relatively low.
It should be understood by those skilled in the art that, the embodiment of the present invention can be provided as method, system or computer program Product.Therefore, the reality in terms of complete hardware embodiment, complete software embodiment or combination software and hardware can be used in the present invention Apply the form of example.Moreover, the computer for wherein including computer usable program code in one or more can be used in the present invention The computer program production that usable storage medium is implemented on (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) The form of product.
The present invention be with reference to according to the method for the embodiment of the present invention, the flow of equipment (system) and computer program product Figure and/or block diagram describe.It should be understood that it can be realized by computer program instructions every first-class in flowchart and/or the block diagram The combination of flow and/or box in journey and/or box and flowchart and/or the block diagram.These computer programs can be provided The processor of all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce A raw machine so that the instruction performed by computer or the processor of other programmable data processing devices is generated for real The device for the function of being specified in present one flow of flow chart or one box of multiple flows and/or block diagram or multiple boxes.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing devices with spy Determine in the computer-readable memory that mode works so that the instruction generation being stored in the computer-readable memory includes referring to Make the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one box of block diagram or The function of being specified in multiple boxes.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that counted Series of operation steps is performed on calculation machine or other programmable devices to generate computer implemented processing, so as in computer or The instruction offer performed on other programmable devices is used to implement in one flow of flow chart or multiple flows and/or block diagram one The step of function of being specified in a box or multiple boxes.
Although preferred embodiments of the present invention have been described, but those skilled in the art once know basic creation Property concept, then can make these embodiments other change and modification.So appended claims be intended to be construed to include it is excellent It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, those skilled in the art can carry out the embodiment of the present invention various modification and variations without departing from this hair The spirit and scope of bright embodiment.In this way, if these modifications and variations of the embodiment of the present invention belong to the claims in the present invention And its within the scope of equivalent technologies, then the present invention is also intended to comprising including these modification and variations.

Claims (12)

1. a kind of video pushing method, which is characterized in that including:
Obtain the common IP address of user, the common IP address of the user includes in the IP address of the user and distributed area Domain concentrates on the IP address under same geographic area;
According to the administrative region and its town and country classification information included in the coverage of each common IP address, institute is determined The town and country classification of user is stated, the town and country classification includes city and rural area;
It is user's pushing video with reference to the town and country classification of the user.
2. the method as described in claim 1, which is characterized in that determine to be wrapped in the coverage of each common IP address The administrative region contained and its method of town and country classification information, specifically include:
Based on third party's geo-location interface, inquiry obtains the coverage of each common IP address;
Determine the town and country classification of each administrative region included in the coverage of each common IP address.
3. the method as described in claim 1, which is characterized in that in the coverage of each common IP address of the basis Comprising administrative region and its town and country classification information, determine the town and country classification of the user, specifically include:
The capped number of each administrative region included in the coverage of each common IP address, institute are determined respectively The coverage for the common IP address that the capped number for stating administrative region is equal to the user covers time of the administrative region Several summations;
According to the capped number of administrative region, the administrative region included in the coverage of the common IP address is carried out Classification, each category regions include at least one administrative region;
The town and country classification of each administrative region at least one administrative region included according to each category regions is calculated every The corresponding town and country classification of a category regions;
The town and country classification of the user is determined according to the corresponding town and country classification of each category regions.
4. method as claimed in claim 3, which is characterized in that the capped number according to administrative region, to described normal Classified with the administrative region included in the coverage of IP address, including:
It is first category region by the administrative division that capped number is greater than or equal to first number threshold value;
Capped number is greater than or equal to second number threshold value and less than the administrative division of first number threshold value For second category region;
It is the 3rd category regions by the administrative division that capped number is less than second number threshold value;
The town and country classification of the user is determined according to the corresponding town and country classification of each category regions, is specifically included:
When the corresponding town and country classification in first category region town and country classification corresponding with the second category region is identical, by institute State the town and country classification that the corresponding town and country classification in first category region is determined as the user;
During corresponding with the second category region town and country classification difference of the corresponding town and country classification in the first category region, respectively The probability of the probability in the first category region, the probability in second category region and the 3rd category regions is calculated, by probability highest The corresponding town and country classification of category regions be determined as the town and country classification of the user.
5. method as claimed in claim 4, which is characterized in that the corresponding town and country classification in the first category region and described the During the corresponding town and country classification difference of two category regions, calculated respectively by the following formula the first category region probability, The probability of the probability of two category regions and the 3rd category regions:
Probability=(areas for the administrative region number * category regions that category regions include)/(administration that all categories region includes The gross area for the administrative region that region sum * all categories region includes) * constants.
6. the method as described in claim 1, which is characterized in that the town and country classification of the user with reference to described in is the user Pushing video specifically includes:
The historical data of different type video is watched according to the town and country classification of the user and the user, evaluates the user To the fancy grade of different type video;
It is user's pushing video according to the user to the fancy grade of different type video.
7. a kind of video push device, which is characterized in that including:
Acquiring unit, for obtaining the common IP address of user, the common IP address of the user is with including the IP of the user In location and distributed areas concentrate on the IP address under same geographic area;
Determination unit, for determining what is included in the coverage of each common IP address of the acquiring unit acquisition Administrative region and its town and country classification information;According to the administrative region included in the coverage of each common IP address and Its town and country classification information, determines the town and country classification of the user, and the town and country classification includes city and rural area;
Push unit is user's pushing video for the town and country classification of the user determined with reference to the determination unit.
8. device as claimed in claim 7, which is characterized in that the determination unit is determining each common IP address When the administrative region included in coverage and its town and country classification information, it is specifically used for:
Based on third party's geo-location interface, inquiry obtains the coverage of each common IP address;
Determine the town and country classification of each administrative region included in the coverage of each common IP address.
9. device as claimed in claim 7, which is characterized in that the determination unit is according to each common IP address The administrative region included in coverage and its town and country classification information, when determining the town and country classification of the user, are specifically used for:
The capped number of each administrative region included in the coverage of each common IP address is determined respectively, it is described The capped number of administrative region is equal to the number of the coverage covering administrative region of the common IP address of the user Summation;
According to the capped number of administrative region, the administrative region included in the coverage of the common IP address is divided Class, each category regions include at least one administrative region;
The town and country classification of each administrative region at least one administrative region included according to each category regions is calculated every The corresponding town and country classification of a category regions;
The town and country classification of the user is determined according to the corresponding town and country classification of each category regions.
10. device as claimed in claim 9, which is characterized in that the determination unit is in the coating according to administrative region Lid number when classifying to the administrative region included in the coverage of the common IP address, is specifically used for:
It is first category region by the administrative division that capped number is greater than or equal to first number threshold value;
Capped number is greater than or equal to second number threshold value and less than the administrative division of first number threshold value For second category region;
It is the 3rd category regions by the administrative division that capped number is less than second number threshold value;
The determination unit when determining the town and country classification of the user according to the corresponding town and country classification of each category regions, It is specifically used for:
When the corresponding town and country classification in first category region town and country classification corresponding with the second category region is identical, by institute State the town and country classification that the corresponding town and country classification in first category region is determined as the user;
During corresponding with the second category region town and country classification difference of the corresponding town and country classification in the first category region, respectively The probability of the probability in the first category region, the probability in second category region and the 3rd category regions is calculated, by probability highest The corresponding town and country classification of category regions be determined as the town and country classification of the user.
11. device as claimed in claim 10, which is characterized in that the determination unit is corresponding in the first category region During corresponding with the second category region town and country classification difference of town and country classification, it is specifically used for:
Calculate the probability in the first category region, the probability in second category region and the 3rd classification area respectively by the following formula The probability in domain:
Probability=(areas for the administrative region number * category regions that category regions include)/(administration that all categories region includes The gross area for the administrative region that region sum * all categories region includes) * constants.
12. device as claimed in claim 7, which is characterized in that the push unit is specifically used for:
The town and country classification of the user determined according to the determination unit and the user watch the history of different type video Data evaluate fancy grade of the user to different type video;
It is user's pushing video according to the user to the fancy grade of different type video.
CN201611042601.4A 2016-11-23 2016-11-23 A kind of video pushing method and device Pending CN108093303A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611042601.4A CN108093303A (en) 2016-11-23 2016-11-23 A kind of video pushing method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611042601.4A CN108093303A (en) 2016-11-23 2016-11-23 A kind of video pushing method and device

Publications (1)

Publication Number Publication Date
CN108093303A true CN108093303A (en) 2018-05-29

Family

ID=62170169

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611042601.4A Pending CN108093303A (en) 2016-11-23 2016-11-23 A kind of video pushing method and device

Country Status (1)

Country Link
CN (1) CN108093303A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109460512A (en) * 2018-10-25 2019-03-12 腾讯科技(北京)有限公司 Recommendation information processing method, device, equipment and storage medium
CN110674344A (en) * 2019-08-28 2020-01-10 北京爱奇艺智慧娱乐科技有限公司 Method, device, equipment and storage medium for generating model and recommending film
CN111262744A (en) * 2020-01-20 2020-06-09 北京字节跳动网络技术有限公司 Multimedia information transmitting method, backup server and medium
CN111385657A (en) * 2018-12-28 2020-07-07 广州市百果园信息技术有限公司 Video recommendation method and device, storage medium and computer equipment

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101621740A (en) * 2009-07-24 2010-01-06 深圳市零距网络科技有限公司 Intelligent and mobile network multimedia terminal
US20120109944A1 (en) * 2010-11-03 2012-05-03 Verizon Patent And Licensing Inc. Location-based recommendations
CN103248723A (en) * 2013-04-10 2013-08-14 腾讯科技(深圳)有限公司 Determination method and device for IP address area
CN103888837A (en) * 2014-03-21 2014-06-25 北京金山网络科技有限公司 Video information pushing method and device
CN105611331A (en) * 2015-12-28 2016-05-25 康佳集团股份有限公司 Video pushing method and system based on smart television

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101621740A (en) * 2009-07-24 2010-01-06 深圳市零距网络科技有限公司 Intelligent and mobile network multimedia terminal
US20120109944A1 (en) * 2010-11-03 2012-05-03 Verizon Patent And Licensing Inc. Location-based recommendations
CN103248723A (en) * 2013-04-10 2013-08-14 腾讯科技(深圳)有限公司 Determination method and device for IP address area
CN103888837A (en) * 2014-03-21 2014-06-25 北京金山网络科技有限公司 Video information pushing method and device
CN105611331A (en) * 2015-12-28 2016-05-25 康佳集团股份有限公司 Video pushing method and system based on smart television

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109460512A (en) * 2018-10-25 2019-03-12 腾讯科技(北京)有限公司 Recommendation information processing method, device, equipment and storage medium
CN109460512B (en) * 2018-10-25 2022-04-22 腾讯科技(北京)有限公司 Recommendation information processing method, device, equipment and storage medium
CN111385657A (en) * 2018-12-28 2020-07-07 广州市百果园信息技术有限公司 Video recommendation method and device, storage medium and computer equipment
CN110674344A (en) * 2019-08-28 2020-01-10 北京爱奇艺智慧娱乐科技有限公司 Method, device, equipment and storage medium for generating model and recommending film
CN111262744A (en) * 2020-01-20 2020-06-09 北京字节跳动网络技术有限公司 Multimedia information transmitting method, backup server and medium

Similar Documents

Publication Publication Date Title
CN108093303A (en) A kind of video pushing method and device
Stepan et al. Incorporating spatial, temporal, and social context in recommendations for location-based social networks
CN104143005B (en) A kind of related search system and method
CN105007217B (en) The system and method for social relationships is found by the GEOGRAPHICAL INDICATION with time attribute
CN106776930B (en) A kind of location recommendation method incorporating time and geographical location information
CN107146089A (en) The single recognition methods of one kind brush and device, electronic equipment
CN108011987A (en) IP address localization method and device, electronic equipment and storage medium
CN105868291A (en) Website address recommendation method, apparatus and system
CN107248116A (en) A kind of activity recommendation method and mobile terminal
CN105468598A (en) Friend recommendation method and device
KR101427233B1 (en) System and Method of Recommendation Number of Lotto Lottery Number for Providing Lotto Lottery for Increasing Winning Ration Using Data Mining
CN107172452A (en) Direct broadcasting room recommends method and device
KR20180101472A (en) Method and device for identifying the type of geographic location in which a user is located
US10984426B2 (en) Modeling comparable properties where the subject property is a condominium property
WO2013039573A2 (en) System and method for providing internet and mobile based social/geo/promo link promotional and coupon data sets for end user display of interactive location-based advertising, location-based deals and offers and location-based services, ad links, promotions, mobile coupons, promotions and sale of consumer, business, government, sports, or educational related products, goods, gambling, or services, integrated with 3d spatial geomapping, mobile mapping, company and local information for selected worldwide locations and social shopping and social networking
CN106971345A (en) A kind of location recommendation method based on position social networks
CN105677846A (en) Recommendation system and construction method thereof
Hong et al. Residents' perception of flood risk and urban stream restoration using multi‐criteria decision analysis
CN108664654A (en) A kind of main broadcaster's recommendation method and device based on user's similarity
CN106162544A (en) A kind of generation method and apparatus of geography fence
CN107092645A (en) A kind of library resource management method and device
CN109669999A (en) The generation method and device in interest region, storage medium, electronic device
CN109447689A (en) Consumer's risk portrait generation method, device, equipment and readable storage medium storing program for executing
Olivier et al. Multi‐scale sampling boosts inferences from beta diversity patterns in coastal forests of South Africa
WO2016135297A1 (en) Method and system for generation of parameters

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
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20180529

WD01 Invention patent application deemed withdrawn after publication