CN104699696A - File recommendation method and device - Google Patents
File recommendation method and device Download PDFInfo
- Publication number
- CN104699696A CN104699696A CN201310652678.3A CN201310652678A CN104699696A CN 104699696 A CN104699696 A CN 104699696A CN 201310652678 A CN201310652678 A CN 201310652678A CN 104699696 A CN104699696 A CN 104699696A
- Authority
- CN
- China
- Prior art keywords
- title
- keyword
- weight
- file
- frequency
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/10—File systems; File servers
- G06F16/14—Details of searching files based on file metadata
- G06F16/148—File search processing
Abstract
The invention discloses a file recommendation method and a file recommendation device, and belongs to the technical field of network. The method comprises segmenting words of a first name to obtain a first keyword set; acquiring at least one second name and a second keyword set according to a preset corresponding relation, wherein the preset corresponding relation comprises a corresponding relation between a keyword and a file name comprising the keyword; acquiring the same keyword in the first keyword set and the corresponding second keyword set of each second name as a matching keyword; acquiring the weight of the matching keyword, comprised in each second name, in the first name; determining the second name to be recommended; and recommending a file indicated by the determined second name. According to the file recommendation method and the file recommendation device, the weight is determined according to the word class of the matching keyword, the second name to be recommended is determined from multiple alternative second names according to the weight, the relevancy of the name of the finally recommended file and the name of the currently opened file is improved, and the success rate of recommendation is increased.
Description
Technical field
The present invention relates to networking technology area, particularly a kind of file recommendation method and device.
Background technology
In daily Above-the-line, user at every moment facing to various information, but is difficult to therefrom filter out oneself real interested information.For the ease of the screening of user, server can browse record, hobby etc. according to user, for user recommends it may interested information.
For video, when recommending video, server can for user recommend the type belonging to current broadcasting video under the most popular video, as, when current broadcasting video is the video of " physical culture " type, server is video the most popular under user's recommendation " physical culture " type.Or server calculates the LD(Levenshtein Distance between the title of each video and the title of current broadcasting video, editing distance), by the LD between title and the title of current broadcasting video apart from minimum video recommendations to user.
During the most popular under recommending the type belonging to the current broadcasting video video, the degree of correlation of the video that this is the most popular and current broadcasting video may be very low, and then cause recommending success ratio low; And server is when adopting the method calculating LD distance to recommend video, LD distance mechanically can only measure the difference of copy editor's aspect between different video title, make finally to determine that the video name of recommendation and current broadcasting video name semantically may differ greatly, the video degree of correlation can be caused equally very low, and then cause recommending success ratio very low.
Summary of the invention
In order to solve the problem of prior art, embodiments provide a kind of file recommendation method and device.Described technical scheme is as follows:
First aspect, provides a kind of file recommendation method, and described method comprises:
Carry out participle to the first title, obtain the first keyword set, described first place is called the current title opened file, and described first keyword set comprises at least one keyword that described first title participle obtains;
According to default corresponding relation, obtain at least one second title and the second keyword set corresponding at least one second title described, described second place is called the file name that the keyword in described first keyword set is corresponding, and described default corresponding relation comprises keyword and comprises the corresponding relation between the file name of described keyword;
Obtain keyword identical in described first keyword set the second keyword set corresponding with each second title, using described identical keyword as matching keywords;
Obtain the weight of matching keywords in described first title that described each second title comprises;
According to the weight of matching keywords in described first title that described each second title comprises, determine the second title to be recommended;
Recommend the described file indicated by the second title determined.
Second aspect, provide a kind of file recommendation device, described device comprises:
First participle module, for carrying out participle to the first title, obtains the first keyword set, and described first place is called the current title opened file, and described first keyword set comprises at least one keyword that described first title participle obtains;
Second set acquisition module, corresponding relation is preset for basis, obtain at least one second title and the second keyword set corresponding at least one second title described, described second place is called the file name that the keyword in described first keyword set is corresponding, and described default corresponding relation comprises keyword and comprises the corresponding relation between the file name of described keyword;
Matching module, for obtaining keyword identical in described first keyword set the second keyword set corresponding with each second title, using described identical keyword as matching keywords;
Weight Acquisition module, for obtaining the weight of matching keywords in described first title that described each second title comprises;
Title determination module, for the weight of matching keywords in described first title comprised according to described each second title, determines the second title to be recommended;
Recommending module, for recommending the file indicated by described the second title determined.
The beneficial effect that the technical scheme that the embodiment of the present invention provides is brought is:
The method and apparatus that the embodiment of the present invention provides, by processing current the first title opened file, obtain multiple the second alternative title, according to this first title, each second title is mated, determine the matching keywords that each second title comprises, and according to the part of speech determination weight of matching keywords, thus from multiple the second alternative title, determine the second title to be recommended according to weight, and the file indicated by the second title recommending this to determine, improve the final file name of recommendation and the degree of correlation of the current title opened file, improve recommendation success ratio.
Accompanying drawing explanation
In order to be illustrated more clearly in the technical scheme in the embodiment of the present invention, below the accompanying drawing used required in describing embodiment is briefly described, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the process flow diagram of a kind of file recommendation method that the embodiment of the present invention provides;
Fig. 2 is the process flow diagram of a kind of file recommendation method that the embodiment of the present invention provides;
Fig. 3 is a kind of file recommendation apparatus structure schematic diagram that the embodiment of the present invention provides;
Fig. 4 is a kind of server architecture schematic diagram that the embodiment of the present invention provides.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
Fig. 1 is the process flow diagram of a kind of file recommendation method that the embodiment of the present invention provides.The executive agent of this inventive embodiments is server, and see Fig. 1, described method comprises:
101, carry out participle to the first title, obtain the first keyword set, this first place is called the current title opened file, and this first keyword set comprises at least one keyword that this first title participle obtains.
102, according to presetting corresponding relation, obtain the second keyword set that at least one second title is corresponding with this at least one second title, this second place is called the file name that the keyword in this first keyword set is corresponding, and this default corresponding relation comprises the corresponding relation between keyword and the file name comprising this keyword.
103, keyword identical in this first keyword set second keyword set corresponding with each second title is obtained, using this identical keyword as matching keywords.
104, the weight of matching keywords in this first title that this each second title comprises is obtained.
105, according to the weight of matching keywords in this first title that this each second title comprises, the second title to be recommended is determined.
106, the file indicated by the second title recommending this to determine.
The method that the embodiment of the present invention provides, by processing current the first title opened file, obtain multiple the second alternative title, according to this first title, each second title is mated, determine the matching keywords that each second title comprises, and according to the part of speech determination weight of matching keywords, thus from multiple the second alternative title, determine the second title to be recommended according to weight, and the file indicated by the second title recommending this to determine, improve the final file name of recommendation and the degree of correlation of the current title opened file, improve recommendation success ratio.
Alternatively, according to default corresponding relation, the second keyword set obtaining at least one second title corresponding with this at least one second title comprises:
According to this default corresponding relation, obtain this at least one second title;
Each second title for this at least one second title, carries out participle to this second title, obtains the second keyword set, and this second keyword set comprises at least one keyword that this second title participle obtains.
Alternatively, before obtaining matching keywords that this each second title the comprises weight in this first title, the method also comprises:
According at least one item in the type of each keyword in this first keyword set and the frequency of occurrences, obtain the weight of this each keyword in this first title.
Alternatively, according at least one item in the type of each keyword in this first keyword set and the frequency of occurrences, obtain the weight of this each keyword in this first title and comprise:
The weight rank corresponding according to the type of this each keyword, be this each keyword assignment weight according to weight rank order from high to low, the weight that the high keyword of weight rank is distributed is greater than the weight that the low keyword of weight rank distributes; Or,
Be this each keyword assignment weight according to the frequency of occurrences order from high to low of this each keyword, the weight that the keyword making the frequency of occurrences high distributes is greater than the weight that the low keyword of the frequency of occurrences distributes; Or,
The weight rank corresponding according to the type of this each keyword, be this each keyword assignment weight according to weight rank order from high to low, the weight that the high keyword of weight rank is distributed is greater than the weight that the low keyword of weight rank distributes;
According to the frequency of occurrences of this each keyword, the weight that this each keyword distributes is adjusted.
Alternatively, the type of this keyword comprises noun, verb or function word, and the weight of noun is superior to the weight rank of verb and function word;
The frequency of occurrences of this keyword is the frequency that this keyword occurs in the file name stored, or, the frequency of occurrences of this keyword is the frequency that this keyword occurs in other file name of the specified class stored, and this appointment classification is for deserving the classification belonging to front opening file.
Alternatively, in noun, the weight of name is superior to the weight rank of other nouns.
Alternatively, according to the weight of matching keywords in this first title that this each second title comprises, determine that the second title to be recommended comprises:
According to the weight of matching keywords in this first title that this each second title comprises, determine the weight of this each second title;
According to the weight order from big to small of this each second title, the second title of preset number is defined as this second title to be recommended.
Alternatively, according to the weight of matching keywords in this first title that this each second title comprises, determine that the weight of this each second title comprises:
The weight of matching keywords in this first title that this each second title is comprised be defined as the weight of this each second title with value; Or,
The issuing time of file indicated by this each second title, determine the time weighting of this each second title, according to preset ratio, to being weighted with value and this time weighting of the weight of matching keywords in this first title that this each second title comprises, obtain weighted sum, this weighted sum is defined as the weight of this each second title.
Above-mentioned all alternatives, can adopt and combine arbitrarily formation optional embodiment of the present invention, this is no longer going to repeat them.
Fig. 2 is the process flow diagram of a kind of file recommendation method that the embodiment of the present invention provides.The executive agent of this inventive embodiments is server, and see Fig. 2, described method comprises:
201, this server carries out participle to the first title, obtains the first keyword set, and this first place is called the current title opened file, and this first keyword set comprises at least one keyword that this first title participle obtains.
The embodiment of the present invention is applied to user's opened file, this server according to the current title opened file, under user recommends the scene of alternative document.This server can for current open file the server that associates or with the functional module in the current server that associates of opening file, the embodiment of the present invention does not limit this.
Further, the embodiment of the present invention is applied under the current name opened file is called the scene of the self-defining title of publisher.Different from the title that movie name or TV play title etc. have provided when issuing, the self-defining title of publisher may be very long or very short, it may be a simple word, also may be a complicated sentence, the embodiment of the present invention namely according to the self-defining personalized name of publisher, for user recommends file.
Wherein, video file, audio file or text etc. that this file can provide for server, the audio file that the network video file provided as video website server, audio frequency website provide or document sharing server the network documentation etc. that provides, the embodiment of the present invention does not limit this.
Particularly, this server, when detecting that user opens file, obtains the current name opened file and is referred to as first place and claims, and carry out participle to this first title, obtain at least one keyword of this first title, this at least one keyword is formed this first keyword set.
Such as, this first place is called " clothes worn when Liu Dehua attends the concert of a schoolmate ", then carry out participle to this first title, obtains this first keyword set { Liu Dehua, a schoolmate, concert, clothes }.
Wherein, this server is when to this first title participle, and can adopt the segmenting method of segmenting method based on string matching or Corpus--based Method, the embodiment of the present invention does not limit this.
202, this server is according to default corresponding relation, obtain this at least one second title, this second place is called the file name that the keyword in this first keyword set is corresponding, and this default corresponding relation comprises the corresponding relation between keyword and the file name comprising this keyword.
Wherein, this first keyword set comprises at least one keyword, and for each keyword in this first keyword set, this server, by this default corresponding relation of inquiry, can obtain comprising the file name of any one or the multiple keyword in this first keyword set.
Such as, the corresponding relation between the keyword in this first title, this first keyword set and second place corresponding to each keyword are referred to as is as shown in table 1.
Table 1
Alternatively, before this step 202, the method also comprises: the file name stored according to this server, sets up this default corresponding relation.
Particularly, this server carries out participle to the title of the All Files stored, and obtains the keyword that each file name comprises; For a keyword, according to the keyword that this each file name comprises, obtain the file name comprising this keyword; Set up the default corresponding relation between this keyword and the file name comprising this keyword.
Further alternatively, this server sets up inverted index to the keyword that each file name comprises, and the inverted index of foundation is defined as this default corresponding relation.
203, each second title for this at least one second title, this server carries out participle to this second title, obtains the second keyword set, and this second keyword set comprises at least one keyword that this second title participle obtains.
Based on the citing of step 202, this second place is called " Liu De China concert complete or collected works ", then this server obtains this second keyword set { Liu Dehua, concert, complete or collected works } after carrying out participle to this second title.
Wherein, this server is when to this second title participle, and also can adopt the segmenting method of segmenting method based on string matching or Corpus--based Method, the embodiment of the present invention does not limit this.
204, this server obtains keyword identical in this first keyword set second keyword set corresponding with each second title, using this identical keyword as matching keywords.
Particularly, for a keyword in this first keyword set, travel through this second keyword set, judge whether comprise this keyword in this second keyword set, when this second keyword set comprises this keyword, using this keyword as matching keywords, continue to carry out above-mentioned judgement to each keyword in this first keyword set, obtain at least one matching keywords.Or, for a keyword in this second keyword set, travel through this first keyword set, judge whether comprise this keyword in this first keyword set, when this first keyword set comprises this keyword, using this keyword as matching keywords, continue to carry out above-mentioned judgement to each keyword in this second keyword set, obtain at least one matching keywords.
Based on the citing of step 201 and step 203, this first keyword set is combined into { Liu Dehua, a schoolmate, concert, clothes }, and this second keyword set is combined into { Liu Dehua, concert, complete or collected works }, then this matching keywords is " Liu Dehua " and " concert ".
205, the weight rank that this server is corresponding according to the type of each keyword in this first keyword set, be this each keyword assignment weight according to weight rank order from high to low, the weight that the high keyword of weight rank is distributed is greater than the weight that the low keyword of weight rank distributes.
In embodiments of the present invention, this first keyword set comprises at least one identical matching keywords with this second keyword set, but this first title and this second title semantically may differ greatly.Therefore, when selecting the second title to be recommended, in order to improve the second title to be recommended and the degree of correlation of this first title, by being the keyword assignment weight in this first keyword set, the corresponding weight determining each second title, to improve the degree of correlation of the second title to be recommended and this first title finally determined.
Particularly, this server presets the weight rank corresponding to type of each keyword, when this server determines the type of each keyword in this first keyword set, the weight rank that the every type preset according to this server is corresponding, determine the weight rank of this each keyword, according to weight rank order from high to low, this each keyword is sorted, and assign weight, the weight that the high keyword of weight rank is distributed is greater than the weight that the low keyword of weight rank distributes.
Alternatively, the weight that in this first keyword set, each keyword distributes be 1 with value.
Further alternatively, the type of this keyword comprises noun, verb or function word, and the weight of noun is superior to the weight rank of verb and function word, and in noun, the weight of name is superior to the weight rank of other nouns.
As, this first place is called " clothes worn when Liu Dehua attends the concert of a schoolmate ", and the weight rank of noun " Liu Dehua " wherein, " schoolmate ", " concert ", " clothes " is higher than that verb " is attended ", the weight rank of " wearing " and function word " ", " time ".
Wherein, the name in noun can be name, place name, organization names, brand name etc., and the embodiment of the present invention does not limit this.The weight of name is superior to the weight rank of other nouns, and the weight as " Liu Dehua ", " schoolmate " is superior to the weight rank of " concert ", " clothes ".
Still be called " clothes worn when Liu Dehua attends the concert of a schoolmate " for this first place, this server is determined " Liu Dehua ", the weight of " schoolmate " is superior to " concert ", the weight rank of " clothes ", " concert ", the weight of " clothes " is superior to " attending ", " wear ", " ", " time " weight rank, then this server can assign weight 0.3 for keyword " Liu Dehua ", for keyword " schoolmate " assigns weight 0.3, for keyword " concert " assigns weight 0.2, for keyword " clothes " assigns weight 0.1, for keyword " attends " to assign weight 0.1, all the other keyword assignment weights 0.
In another embodiment that the embodiment of the present invention provides, this step 205 can be replaced by following steps (1):
(1) be this each keyword assignment weight according to the frequency of occurrences order from high to low of this each keyword, the weight that the keyword making the frequency of occurrences high distributes is greater than the weight that the low keyword of the frequency of occurrences distributes.
In embodiments of the present invention, can think that the keyword that the frequency of occurrences is higher in this first keyword set is more popular, then user is probably interested in the file that the keyword higher to this frequency of occurrences is relevant, namely can assign weight according to the frequency of occurrences of each keyword of this first keyword set.
Alternatively, the frequency of occurrences of this keyword is the frequency that this keyword occurs in the file name stored, or the frequency of occurrences of this keyword is the frequency that this keyword occurs in other file name of the specified class stored, this appointment classification is for deserving the classification belonging to front opening file.
Wherein, deserve front opening file and may belong to some subclass, this subclass also belongs to a certain female classification, then this server can, according to the difference of recommending accuracy requirement, be determined to deserve the appointment classification belonging to front opening file.
The name opened file as current is called " perseverance is won the championship greatly ", belong to the football classification in Sport Class, then this server can calculate this keyword and " to win the championship " frequency of occurrences in the file name of football classification, think that this keyword " is won the championship " to assign weight, instead of calculate this keyword and " to win the championship " frequency of occurrences in the file name of all categories or the frequency of occurrences in the file name of Sport Class.
Further, this frequency of occurrences can be TF(Term Frequency, word frequency) or DF(DocumentFrequency, document-frequency).
Still be called " clothes worn when Liu Dehua attends the concert of a schoolmate " for this first place, this server determines that this first title belongs to singer's classification, then calculate keyword " Liu Dehua ", " schoolmate ", " concert ", " clothes " frequency of occurrences in the file name of singer's classification, if the keyword finally calculated " Liu Dehua ", " schoolmate " and the frequency of occurrences of " concert " are respectively 0.3, 0.2 and 0.1, then this server can according to frequency of occurrences order from high to low, for keyword " Liu Dehua " assigns weight 0.5, for keyword " schoolmate " assigns weight 0.4, for keyword " concert " assigns weight 0.1, all the other keyword assignment weights are 0.
Further alternatively, this server calculates the frequency of occurrences of this each keyword in the file name of this server stores in preset duration.Wherein, this preset duration can be preset by this server.
Above-mentioned steps 205 and step (1) are that the frequency of occurrences of weight rank corresponding according to the type of each keyword in this first keyword set respectively and each keyword assigns weight, in fact, this server can also the weight rank corresponding by the type considering each keyword and the frequency of occurrences assign weight.Namely, in the another embodiment provided in the embodiment of the present invention, this step 205 can also be replaced by following steps (2):
(2) corresponding according to the type of this each keyword weight rank, be this each keyword assignment weight according to weight rank order from high to low, the weight that the high keyword of weight rank is distributed is greater than the weight that the low keyword of weight rank distributes; According to the frequency of occurrences of this each keyword, the weight that this each keyword distributes is adjusted.
In actual applications, can think that the high keyword of the frequency of occurrences is more popular, but the degree of correlation of the second title that the keyword that the frequency of occurrences is high is corresponding and this first title may be very low, user might not be interested in the file indicated by the second title of this hot topic.And in embodiments of the present invention, this server according to weight rank corresponding to the type of each keyword, after this each keyword assignment weight, according to the frequency of occurrences of this each keyword, can also adjust the weight that this each keyword distributes.By the frequency of occurrences of the degree of correlation and this second title that consider this second title and this first title, both can improve the degree of correlation of the second title to be recommended and this first title finally determined, also can the higher file recommendation of the prioritizing selection frequency of occurrences to user.
Further, " according to the frequency of occurrences of this each keyword, adjusting the weight that this each keyword distributes " in this step (2), can adopt any one mode following:
(2-1) according to the frequency of occurrences of this each keyword, determine adjusting range, according to the adjusting range determined, the weight that this each keyword distributes is increased accordingly or reduced.
As, this server is keyword " Liu Dehua ", " schoolmate ", " concert ", " clothes ", the weight of " attending " to distribute is 0.3, 0.3, 0.2, 0.1, 0.1, and calculate keyword " Liu Dehua " during Week, " schoolmate ", " concert ", the frequency of occurrences of " clothes " and " attending " is respectively 0.3, 0.2, 0.1, 0.2 and 0.01, then determine keyword " Liu Dehua ", " schoolmate ", " concert ", the adjusting range of " clothes " and " attending " is 0.025, 0.025,-0.1, 0.15,-0.1, then according to this adjusting range, after this each keyword is adjusted, finally determine that the weight of distributing is 0.275, 0.275, 0.1, 0.25, 0.
(2-2) according to the frequency of occurrences of this each keyword, the weight that the keyword frequency of occurrences being more than or equal to predetermined threshold value distributes increases presets adjustment weight, and the weight that the keyword frequency of occurrences being less than predetermined threshold value distributes reduces described default adjustment weight.
As, this server determines that this predetermined threshold value is 0.2, this presets adjustment weight is 0.05, then when this server is keyword " Liu Dehua ", " schoolmate ", " concert ", " clothes ", the weight of " attending " to distribute is 0.3, 0.3, 0.2, 0.1, 0.1, and calculate keyword " Liu Dehua ", " schoolmate ", " concert ", the frequency of occurrences of " clothes " and " attending " is respectively 0.3, 0.2, 0.1, when 0.2 and 0.01, the frequency of occurrences is more than or equal to the keyword " Liu Dehua " of 0.2, " schoolmate ", the weight that " clothes " distribute increases by 0.05, the frequency of occurrences is less than the keyword " concert " of 0.2, the weight of " attending " to distribute reduces 0.05, then finally determine that the weight of distributing is 0.25, 0.25, 0.15, 0.15, 0.05.
It should be noted that, the embodiment of the present invention performs for this step 205 and is described after this step 204, in fact, this step 205 only need perform after this step 201, before this step 206, namely this step 205 can also perform before this step 204, or perform with this step 204, the execution of the embodiment of the present invention to this step 205 does not limit opportunity simultaneously.
206, this server obtains this weight of matching keywords in this first title included by each second title.
In embodiments of the present invention, this server has determined the weight of each keyword in this first title in this first keyword set, that is to say and determine the weight of each matching keywords in this first title, then this server determines the matching keywords that each second title comprises, and the weight of matching keywords in this first title that each second title comprises.
Based on table 1, suppose that this first place is called " clothes worn when Liu Dehua attends the concert of a schoolmate ", and this server is keyword " Liu Dehua " assigns weight 0.3, for keyword " schoolmate " assigns weight 0.3, for keyword " concert " assigns weight 0.2, for keyword " clothes " assigns weight 0.1, for keyword " attends " to assign weight 0.1, all the other keyword assignment weights 0, then the weight of matching keywords in this first title that each second title that this server is determined comprises can be as shown in table 2.
Table 2
207, the issuing time of this server file indicated by this each second title, determine the time weighting of this each second title, according to preset ratio, to being weighted with value and this time weighting of the weight of matching keywords in this first title that this each second title comprises, obtain weighted sum, this weighted sum is defined as the weight of this each second title.
In embodiments of the present invention, file indicated by second title may be the file of up-to-date issue, also may be announced file morning, and the issuing time of file is different, the interested degree of user is also different, namely issuing time can have influence on the interested degree of user, and then has influence on recommendation success ratio.Therefore, when determining this second title to be recommended, need the issuing time considering file indicated by this each second title.
Particularly, that this server calculates the weight of matching keywords in this first title that this each second title comprises and value, and according to the issuing time of file indicated by this each second title, this each second title is sorted, according to putting in order, for this each second title distributes time weighting, make the time weighting of second title in issuing time evening higher than the time weighting of issuing time the second title early.This server, according to this preset ratio, is weighted this and value and this time weighting, obtains weighted sum, be the weight of each second title.
Wherein, this preset ratio refers to this and the ratio between value and this time weighting, according to this ratio, can to determine when being weighted should and the weighting coefficient of value and this time weighting.This preset ratio can be preset by this server, also in use can be adjusted by this server, the issuing time opened file as current comparatively early time, this time weighting proportion is less, and current open file as ageing stronger types such as " news " file time, this time weighting proportion is comparatively large, and the embodiment of the present invention does not limit this.
Based on table 2, this second place is called " Liu De China concert complete or collected works ", suppose this server be this second title distribute time weighting be 0.4, and this preset ratio is 6:4, then this server calculates the weight of the matching keywords that this second title comprises and value is 0.5, and the weight calculating this second title is 0.5*0.6+0.4*0.4=0.46.
Further, this server can preset the corresponding relation of time interval between issuing time and current time and time weighting, namely the time weighting corresponding to each time interval is determined, then this server can calculate the time interval between the issuing time of file indicated by this each second title and current time, according to the corresponding relation that this presets, determine the time weighting of this each second title.
As, it be the time weighting of second title of 1 day is 0.9 that this server presets this time interval, this time interval is the time weighting of second title of 2 days is 0.8 ... then for second title, when this server determines that the time interval between the issuing time of this file indicated by the second title and current time is 4 days, determine that the time weighting of this second title is 0.6.
It should be noted that, above-mentioned steps 207 is optional step, this server can not also consider the impact of file distribution time, and only according to the weight of matching keywords in this first title included by each second title, determine the weight of each second title, namely, in another embodiment provided in the embodiment of the present invention, this step 207 can be replaced by following steps: the weight of matching keywords in this first title that this each second title is comprised be defined as the weight of this each second title with value.As based on table 2, this second place is called " Liu De China concert complete or collected works ", then this server calculates the weight of the matching keywords that this second title comprises and value is 0.5, namely determines that the weight of this second title is 0.5.
208, this server is according to the weight order from big to small of this each second title, the second title of preset number is defined as this second title to be recommended.
Wherein, this preset number can be preset by this server, or the number of files that can be shown according to the recommendation region in the current display interface opened file by this server is determined, the embodiment of the present invention does not limit this.
Particularly, this server is according to weight order from big to small, this each second title is sorted, and the second title of preset number is defined as this second title to be recommended before coming, so as by come front preset number the second title indicated by file recommendation to user.
209, this server file indicated by the second title of recommending this to determine.
In embodiments of the present invention, this server recommend this to determine the file indicated by the second title time, the chained address of second title that can this be provided to determine on the current display interface opened file, this chained address is for the file indicated by the second title of jumping to this and determining.In addition, this server can also show the thumbnail of the file generated indicated by the second title that this is determined, or relevant information such as display publisher, issuing time etc. etc., the embodiment of the present invention does not limit this.
Further, for multiple the second title that this is determined, can recommend successively according to weight order, can also recommend successively according to issuing time, the embodiment of the present invention does not all limit this.
The method that the embodiment of the present invention provides, by processing current the first title opened file, obtain multiple the second alternative title, according to this first title, each second title is mated, determine the matching keywords that each second title comprises, and according to the part of speech determination weight of matching keywords, thus from multiple the second alternative title, determine the second title to be recommended according to weight, and the file indicated by the second title recommending this to determine, improve the final file name of recommendation and the degree of correlation of the current title opened file, improve recommendation success ratio.Further, consider the factor of the issuing time of file, determine this second title to be recommended to further increase recommendation success ratio by the time weighting calculating this each second title.
Fig. 3 is a kind of file recommendation apparatus structure schematic diagram that the embodiment of the present invention provides, see Fig. 3, this device comprises: first participle module 301, second gathers acquisition module 302, matching module 303, Weight Acquisition module 304, title determination module 305, recommending module 306
Wherein, first participle module 301, for carrying out participle to the first title, obtains the first keyword set, and this first place is called the current title opened file, and this first keyword set comprises at least one keyword that this first title participle obtains;
Second set acquisition module 302 is connected with first participle module 301, corresponding relation is preset for basis, obtain the second keyword set that at least one second title is corresponding with this at least one second title, this second place is called the file name that the keyword in this first keyword set is corresponding, and this default corresponding relation comprises the corresponding relation between keyword and the file name comprising this keyword;
Matching module 303 and second is gathered acquisition module 302 and is connected, for obtaining keyword identical in this first keyword set second keyword set corresponding with each second title, using this identical keyword as matching keywords;
Weight Acquisition module 304 is connected with matching module 303, for obtaining the weight of matching keywords in this first title that this each second title comprises;
Title determination module 305 is connected with Weight Acquisition module 304, for the weight of matching keywords in this first title comprised according to this each second title, determines the second title to be recommended;
Recommending module 306 is connected with title determination module 305, the file indicated by the second title determined for recommending this.
Alternatively, this second set acquisition module 302 comprises:
Second title acquiring unit, for according to this default corresponding relation, obtains this at least one second title;
Second participle unit, for each second title at least one second title for this, carries out participle to this second title, obtains the second keyword set, and this second keyword set comprises at least one keyword that this second title participle obtains.
Alternatively, this device also comprises:
First Weight Acquisition module, for according at least one item in the type of each keyword in this first keyword set and the frequency of occurrences, obtains the weight of this each keyword in this first title.
Alternatively, this first Weight Acquisition module comprises:
First Weight Acquisition unit, for the weight rank corresponding according to the type of this each keyword, be this each keyword assignment weight according to weight rank order from high to low, the weight that the high keyword of weight rank is distributed is greater than the weight that the low keyword of weight rank distributes; Or,
Second Weight Acquisition unit, be this each keyword assignment weight for the order from high to low of the frequency of occurrences according to this each keyword, the weight that the keyword making the frequency of occurrences high distributes is greater than the weight that the low keyword of the frequency of occurrences distributes; Or,
3rd Weight Acquisition unit, for the weight rank corresponding according to the type of this each keyword, be this each keyword assignment weight according to weight rank order from high to low, the weight that the high keyword of weight rank is distributed is greater than the weight that the low keyword of weight rank distributes;
Adjustment unit, for the frequency of occurrences according to this each keyword, adjusts the weight that this each keyword distributes.
Alternatively, the type of this keyword comprises noun, verb or function word, and the weight of noun is superior to the weight rank of verb and function word;
The frequency of occurrences of this keyword is the frequency that this keyword occurs in the file name stored, or, the frequency of occurrences of this keyword is the frequency that this keyword occurs in other file name of the specified class stored, and this appointment classification is for deserving the classification belonging to front opening file.
Alternatively, in noun, the weight of name is superior to the weight rank of other nouns.
Alternatively, this title determination module 305 comprises:
Weight determining unit, for the weight of matching keywords in this first title comprised according to this each second title, determines the weight of this each second title;
Title determining unit to be recommended, for the weight order from big to small according to this each second title, is defined as this second title to be recommended by the second title of preset number.
Alternatively, what this weight determining unit was used for the weight of matching keywords in this first title this each second title comprised is defined as the weight of this each second title with value; Or,
This weight determining unit is used for the issuing time of file indicated by this each second title, determine the time weighting of this each second title, according to preset ratio, to being weighted with value and this time weighting of the weight of matching keywords in this first title that this each second title comprises, obtain weighted sum, this weighted sum is defined as the weight of this each second title.
The device that the embodiment of the present invention provides, by processing current the first title opened file, obtain multiple the second alternative title, according to this first title, each second title is mated, determine the matching keywords that each second title comprises, and according to the part of speech determination weight of matching keywords, thus from multiple the second alternative title, determine the second title to be recommended according to weight, and the file indicated by the second title recommending this to determine, improve the final file name of recommendation and the degree of correlation of the current title opened file, improve recommendation success ratio.
It should be noted that: the file recommendation device that above-described embodiment provides is when recommending file, only be illustrated with the division of above-mentioned each functional module, in practical application, can distribute as required and by above-mentioned functions and be completed by different functional modules, inner structure by server is divided into different functional modules, to complete all or part of function described above.In addition, the file recommendation device that above-described embodiment provides and file recommendation method embodiment belong to same design, and its specific implementation process refers to embodiment of the method, repeats no more here.
Fig. 4 is a kind of server architecture schematic diagram that the embodiment of the present invention provides, this server 400 can produce larger difference because of configuration or performance difference, one or more central processing units (central processing units can be comprised, CPU) 422(such as, one or more processors) and storer 432, one or more store storage medium 430(such as one or more mass memory units of application program 442 or data 444).Wherein, storer 432 and storage medium 430 can be of short duration storages or store lastingly.The program being stored in storage medium 430 can comprise one or more modules (diagram does not mark), and each module can comprise a series of command operatings in server.Further, central processing unit 422 can be set to communicate with storage medium 430, and server 400 performs a series of command operatings in storage medium 430.
Server 400 can also comprise one or more power supplys 426, one or more wired or wireless network interfaces 450, one or more IO interface 458, and/or, one or more operating systems 441, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM etc.
The step performed by server described in above-described embodiment can based on the server architecture shown in this Fig. 4.
One of ordinary skill in the art will appreciate that all or part of step realizing above-described embodiment can have been come by hardware, the hardware that also can carry out instruction relevant by program completes, described program can be stored in a kind of computer-readable recording medium, the above-mentioned storage medium mentioned can be ROM (read-only memory), disk or CD etc.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (16)
1. a file recommendation method, is characterized in that, described method comprises:
Carry out participle to the first title, obtain the first keyword set, described first place is called the current title opened file, and described first keyword set comprises at least one keyword that described first title participle obtains;
According to default corresponding relation, obtain at least one second title and the second keyword set corresponding at least one second title described, described second place is called the file name that the keyword in described first keyword set is corresponding, and described default corresponding relation comprises keyword and comprises the corresponding relation between the file name of described keyword;
Obtain keyword identical in described first keyword set the second keyword set corresponding with each second title, using described identical keyword as matching keywords;
Obtain the weight of matching keywords in described first title that described each second title comprises;
According to the weight of matching keywords in described first title that described each second title comprises, determine the second title to be recommended;
Recommend the described file indicated by the second title determined.
2. method according to claim 1, is characterized in that, according to default corresponding relation, obtains at least one second title and the second keyword set corresponding at least one second title described comprises:
According to described default corresponding relation, obtain at least one second title described;
For each second title at least one second title described, carry out participle, obtain the second keyword set to described second title, described second keyword set comprises at least one keyword that described second title participle obtains.
3. method according to claim 1, is characterized in that, before obtaining matching keywords that described each second title the comprises weight in described first title, described method also comprises:
According at least one item in the type of each keyword in described first keyword set and the frequency of occurrences, obtain the weight of described each keyword in described first title.
4. method according to claim 3, is characterized in that, according at least one item in the type of each keyword in described first keyword set and the frequency of occurrences, obtains the weight of described each keyword in described first title and comprises:
The weight rank corresponding according to the type of described each keyword, be described each keyword assignment weight according to weight rank order from high to low, the weight that the high keyword of weight rank is distributed is greater than the weight that the low keyword of weight rank distributes; Or,
Be described each keyword assignment weight according to the frequency of occurrences order from high to low of described each keyword, the weight that the keyword making the frequency of occurrences high distributes is greater than the weight that the low keyword of the frequency of occurrences distributes; Or,
The weight rank corresponding according to the type of described each keyword, be described each keyword assignment weight according to weight rank order from high to low, the weight that the high keyword of weight rank is distributed is greater than the weight that the low keyword of weight rank distributes;
According to the frequency of occurrences of described each keyword, the weight that described each keyword distributes is adjusted.
5. method according to claim 3, is characterized in that, the type of described keyword comprises noun, verb or function word, and the weight of noun is superior to the weight rank of verb and function word;
The frequency of occurrences of described keyword is the frequency that described keyword occurs in the file name stored, or, the frequency of occurrences of described keyword is the frequency that described keyword occurs in other file name of the specified class stored, and described appointment classification is the described current affiliated classification that opens file.
6. method according to claim 5, is characterized in that, in noun, the weight of name is superior to the weight rank of other nouns.
7. method according to claim 1, is characterized in that, according to the weight of matching keywords in described first title that described each second title comprises, determines that the second title to be recommended comprises:
According to the weight of matching keywords in described first title that described each second title comprises, determine the weight of described each second title;
According to the weight order from big to small of described each second title, the second title of preset number is defined as described second title to be recommended.
8. method according to claim 7, is characterized in that, according to the weight of matching keywords in described first title that described each second title comprises, determines that the weight of described each second title comprises:
The weight of matching keywords in described first title that described each second title is comprised be defined as the weight of described each second title with value; Or,
The issuing time of file indicated by described each second title, determine the time weighting of described each second title, according to preset ratio, to being weighted with value and described time weighting of the weight of matching keywords in described first title that described each second title comprises, obtain weighted sum, described weighted sum is defined as the weight of described each second title.
9. a file recommendation device, is characterized in that, described device comprises:
First participle module, for carrying out participle to the first title, obtains the first keyword set, and described first place is called the current title opened file, and described first keyword set comprises at least one keyword that described first title participle obtains;
Second set acquisition module, corresponding relation is preset for basis, obtain at least one second title and the second keyword set corresponding at least one second title described, described second place is called the file name that the keyword in described first keyword set is corresponding, and described default corresponding relation comprises keyword and comprises the corresponding relation between the file name of described keyword;
Matching module, for obtaining keyword identical in described first keyword set the second keyword set corresponding with each second title, using described identical keyword as matching keywords;
Weight Acquisition module, for obtaining the weight of matching keywords in described first title that described each second title comprises;
Title determination module, for the weight of matching keywords in described first title comprised according to described each second title, determines the second title to be recommended;
Recommending module, for recommending the file indicated by described the second title determined.
10. device according to claim 9, is characterized in that, described second set acquisition module comprises:
Second title acquiring unit, for according to described default corresponding relation, obtains at least one second title described;
Second participle unit, for for each second title at least one second title described, carry out participle to described second title, obtain the second keyword set, described second keyword set comprises at least one keyword that described second title participle obtains.
11. devices according to claim 9, is characterized in that, described device also comprises:
First Weight Acquisition module, for according at least one item in the type of each keyword in described first keyword set and the frequency of occurrences, obtains the weight of described each keyword in described first title.
12. devices according to claim 11, is characterized in that, described first Weight Acquisition module comprises:
First Weight Acquisition unit, for the weight rank corresponding according to the type of described each keyword, be described each keyword assignment weight according to weight rank order from high to low, the weight that the high keyword of weight rank is distributed is greater than the weight that the low keyword of weight rank distributes; Or,
Second Weight Acquisition unit, be described each keyword assignment weight for the order from high to low of the frequency of occurrences according to described each keyword, the weight that the keyword making the frequency of occurrences high distributes is greater than the weight that the low keyword of the frequency of occurrences distributes; Or,
3rd Weight Acquisition unit, for the weight rank corresponding according to the type of described each keyword, be described each keyword assignment weight according to weight rank order from high to low, the weight that the high keyword of weight rank is distributed is greater than the weight that the low keyword of weight rank distributes;
Adjustment unit, for the frequency of occurrences according to described each keyword, adjusts the weight that described each keyword distributes.
13. devices according to claim 11, is characterized in that, the type of described keyword comprises noun, verb or function word, and the weight of noun is superior to the weight rank of verb and function word;
The frequency of occurrences of described keyword is the frequency that described keyword occurs in the file name stored, or, the frequency of occurrences of described keyword is the frequency that described keyword occurs in other file name of the specified class stored, and described appointment classification is the described current affiliated classification that opens file.
14. devices according to claim 13, is characterized in that, in noun, the weight of name is superior to the weight rank of other nouns.
15. devices according to claim 9, is characterized in that, described title determination module comprises:
Weight determining unit, for the weight of matching keywords in described first title comprised according to described each second title, determines the weight of described each second title;
Title determining unit to be recommended, for the weight order from big to small according to described each second title, is defined as described second title to be recommended by the second title of preset number.
16. devices according to claim 15, is characterized in that, what described weight determining unit was used for the weight of matching keywords in described first title described each second title comprised is defined as the weight of described each second title with value; Or,
Described weight determining unit is used for the issuing time of file indicated by described each second title, determine the time weighting of described each second title, according to preset ratio, to being weighted with value and described time weighting of the weight of matching keywords in described first title that described each second title comprises, obtain weighted sum, described weighted sum is defined as the weight of described each second title.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310652678.3A CN104699696B (en) | 2013-12-05 | 2013-12-05 | File recommendation method and device |
| PCT/CN2015/072103 WO2015081909A1 (en) | 2013-12-05 | 2015-02-02 | File recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310652678.3A CN104699696B (en) | 2013-12-05 | 2013-12-05 | File recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104699696A true CN104699696A (en) | 2015-06-10 |
| CN104699696B CN104699696B (en) | 2018-12-28 |
Family
ID=53272920
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310652678.3A Active CN104699696B (en) | 2013-12-05 | 2013-12-05 | File recommendation method and device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN104699696B (en) |
| WO (1) | WO2015081909A1 (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105205159A (en) * | 2015-09-29 | 2015-12-30 | 努比亚技术有限公司 | Automatic information feedback device and method |
| CN106331778A (en) * | 2015-07-06 | 2017-01-11 | 腾讯科技（深圳）有限公司 | Video recommendation method and device |
| CN106708858A (en) * | 2015-11-13 | 2017-05-24 | 阿里巴巴集团控股有限公司 | Information recommendation method and device |
| CN107832405A (en) * | 2017-11-03 | 2018-03-23 | 北京小度互娱科技有限公司 | The method and apparatus for calculating the correlation between title |
| CN107924401A (en) * | 2015-08-24 | 2018-04-17 | 谷歌有限责任公司 | Video recommendations based on video title |
| CN108256010A (en) * | 2018-01-03 | 2018-07-06 | 阿里巴巴集团控股有限公司 | Content recommendation method and device |
| CN109240991A (en) * | 2018-09-26 | 2019-01-18 | Oppo广东移动通信有限公司 | File recommendation method, device, storage medium and intelligent terminal |
| CN110020132A (en) * | 2017-11-03 | 2019-07-16 | 腾讯科技（北京）有限公司 | Keyword recommendation method, calculates equipment and storage medium at device |
| CN112256843A (en) * | 2020-12-22 | 2021-01-22 | 华东交通大学 | News keyword extraction method and system based on TF-IDF method optimization |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109144954B (en) * | 2018-09-18 | 2021-03-16 | 北京字节跳动网络技术有限公司 | Resource recommendation method and device for editing document and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102760124A (en) * | 2011-04-25 | 2012-10-31 | 阿里巴巴集团控股有限公司 | Pushing method and system for recommended data |
| CN102789453A (en) * | 2011-05-16 | 2012-11-21 | 阿里巴巴集团控股有限公司 | Advertising information release method and device |
| CN102799589A (en) * | 2011-05-25 | 2012-11-28 | 阿里巴巴集团控股有限公司 | Information pushing method and device |
| CN103164405A (en) * | 2011-12-08 | 2013-06-19 | 盛乐信息技术（上海）有限公司 | Generation method for relevant video data bank, recommendation method and recommendation system for relevant videos |
| CN103365899A (en) * | 2012-04-01 | 2013-10-23 | 腾讯科技（深圳）有限公司 | Question recommending method and question recommending system both in questions-and-answers community |
| CN103425687A (en) * | 2012-05-21 | 2013-12-04 | 阿里巴巴集团控股有限公司 | Retrieval method and system based on queries |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101079894A (en) * | 2006-12-21 | 2007-11-28 | 腾讯科技（深圳）有限公司 | A system and method for pushing network information |
| US20110218994A1 (en) * | 2010-03-05 | 2011-09-08 | International Business Machines Corporation | Keyword automation of video content |
| CN103106208B (en) * | 2011-11-11 | 2017-09-15 | 中国移动通信集团公司 | A kind of streaming medium content in mobile Internet recommends method and system |
| CN103186550A (en) * | 2011-12-27 | 2013-07-03 | 盛乐信息技术（上海）有限公司 | Method and system for generating video-related video list |
-
2013
- 2013-12-05 CN CN201310652678.3A patent/CN104699696B/en active Active
-
2015
- 2015-02-02 WO PCT/CN2015/072103 patent/WO2015081909A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102760124A (en) * | 2011-04-25 | 2012-10-31 | 阿里巴巴集团控股有限公司 | Pushing method and system for recommended data |
| CN102789453A (en) * | 2011-05-16 | 2012-11-21 | 阿里巴巴集团控股有限公司 | Advertising information release method and device |
| CN102799589A (en) * | 2011-05-25 | 2012-11-28 | 阿里巴巴集团控股有限公司 | Information pushing method and device |
| CN103164405A (en) * | 2011-12-08 | 2013-06-19 | 盛乐信息技术（上海）有限公司 | Generation method for relevant video data bank, recommendation method and recommendation system for relevant videos |
| CN103365899A (en) * | 2012-04-01 | 2013-10-23 | 腾讯科技（深圳）有限公司 | Question recommending method and question recommending system both in questions-and-answers community |
| CN103425687A (en) * | 2012-05-21 | 2013-12-04 | 阿里巴巴集团控股有限公司 | Retrieval method and system based on queries |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10575037B2 (en) | 2015-07-06 | 2020-02-25 | Tencent Technology (Shenzhen) Company Limited | Video recommending method, server, and storage media |
| CN106331778A (en) * | 2015-07-06 | 2017-01-11 | 腾讯科技（深圳）有限公司 | Video recommendation method and device |
| CN107924401A (en) * | 2015-08-24 | 2018-04-17 | 谷歌有限责任公司 | Video recommendations based on video title |
| CN105205159A (en) * | 2015-09-29 | 2015-12-30 | 努比亚技术有限公司 | Automatic information feedback device and method |
| CN105205159B (en) * | 2015-09-29 | 2020-06-02 | 陈中和 | Device and method for automatically feeding back information |
| CN106708858A (en) * | 2015-11-13 | 2017-05-24 | 阿里巴巴集团控股有限公司 | Information recommendation method and device |
| US11113743B2 (en) | 2015-11-13 | 2021-09-07 | Advanced New Technologies Co., Ltd. | Information recommendation based on rule matching |
| US11017451B2 (en) | 2015-11-13 | 2021-05-25 | Advanced New Technologies Co., Ltd. | Information recommendation based on rule matching |
| CN107832405A (en) * | 2017-11-03 | 2018-03-23 | 北京小度互娱科技有限公司 | The method and apparatus for calculating the correlation between title |
| CN110020132A (en) * | 2017-11-03 | 2019-07-16 | 腾讯科技（北京）有限公司 | Keyword recommendation method, calculates equipment and storage medium at device |
| CN110020132B (en) * | 2017-11-03 | 2023-04-11 | 腾讯科技（北京）有限公司 | Keyword recommendation method and device, computing equipment and storage medium |
| CN108256010A (en) * | 2018-01-03 | 2018-07-06 | 阿里巴巴集团控股有限公司 | Content recommendation method and device |
| CN109240991A (en) * | 2018-09-26 | 2019-01-18 | Oppo广东移动通信有限公司 | File recommendation method, device, storage medium and intelligent terminal |
| CN109240991B (en) * | 2018-09-26 | 2021-07-30 | Oppo广东移动通信有限公司 | File recommendation method and device, storage medium and intelligent terminal |
| CN112256843A (en) * | 2020-12-22 | 2021-01-22 | 华东交通大学 | News keyword extraction method and system based on TF-IDF method optimization |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104699696B (en) | 2018-12-28 |
| WO2015081909A1 (en) | 2015-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104699696A (en) | File recommendation method and device | |
| CN104504059B (en) | Multimedia resource recommends method | |
| TWI636416B (en) | Method and system for multi-phase ranking for content personalization | |
| US9507830B2 (en) | Tailoring user experience for unrecognized and new users | |
| CN106331778B (en) | Video recommendation method and device | |
| CN104598505B (en) | Multimedia resource recommends method and device | |
| CN107832437B (en) | Audio/video pushing method, device, equipment and storage medium | |
| US10097897B2 (en) | Enhanced program guide | |
| CN105653705B (en) | Hot event searching method and device | |
| US20150195624A1 (en) | Media-Related Trends | |
| US10296535B2 (en) | Method and system to randomize image matching to find best images to be matched with content items | |
| CN104021140B (en) | A kind of processing method and processing device of Internet video | |
| US10482142B2 (en) | Information processing device, information processing method, and program | |
| TW201342088A (en) | Digital content reordering method and digital content aggregator | |
| US20140074828A1 (en) | Systems and methods for cataloging consumer preferences in creative content | |
| CN103761263A (en) | Method for recommending information for users | |
| JP6538866B2 (en) | Identify content appropriate for children algorithmically without human intervention | |
| CN106326297B (en) | Application program recommendation method and device | |
| WO2012174174A2 (en) | System and method for user preference augmentation through social network inner-circle knowledge discovery | |
| CN103605808A (en) | Search-based UGC (user generated content) recommendation method and search-based UGC recommendation system | |
| US9432477B2 (en) | Identifying matching video content | |
| CN105898421A (en) | Network film and television program intelligent recommendation method and system | |
| Rubinson et al. | Whatever happened to drama? A configurational–comparative analysis of genre trajectory in American Cinema, 1946–2013 | |
| KR101070604B1 (en) | Method on multimedia content matching advertisement on wire or wireless network | |
| CN112163163B (en) | Multi-algorithm fused information recommendation method, device and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |