CN107748801A - News recommends method, apparatus, terminal device and computer-readable recording medium - Google Patents
News recommends method, apparatus, terminal device and computer-readable recording medium Download PDFInfo
- Publication number
- CN107748801A CN107748801A CN201711138838.7A CN201711138838A CN107748801A CN 107748801 A CN107748801 A CN 107748801A CN 201711138838 A CN201711138838 A CN 201711138838A CN 107748801 A CN107748801 A CN 107748801A
- Authority
- CN
- China
- Prior art keywords
- news
- recommended
- alternative
- determined
- belonging
- 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention proposes that a kind of news recommends method, apparatus, terminal device and computer-readable recording medium, wherein, this method includes：Obtain news to be recommended；Using default space-division method, the object space belonging to the news to be recommended is determined；According to the object space belonging to the recommendation news, it is determined that the first alternative news associated with the news to be recommended.Thus, by the way that the first alternative news for belonging to the same space with news to be recommended is recommended into user, it ensure that the first alternative news is semantic related to news to be recommended, so that recommendation results are more accurate, Consumer's Experience is more preferable.
Description
Technical field
The present invention relates to field of computer technology, more particularly to a kind of news to recommend method, apparatus, terminal device and calculating
Machine readable storage medium storing program for executing.
Background technology
With the rapid development of information technology and internet, Internet news more and more welcomed by the people, turn into people
A kind of main approach of information is obtained in daily life.In recent years with the development of mobile interchange, except widely known each
Big website and network are from outside media platform (for example, microblogging etc.), and numerous news content providers are also by can be applied to move
Application software (APP) on communication products provides a user substantial amounts of Domestic News.
Existing news recommends method, after the search statement of user is got, or on the basis of Present News, mainly
News index is carried out by way of inverted index, so as to which the news recalled is recommended into user.However, inverted index mode is only
Only be to be recalled based on word frequency statistical, have ignored recommend in news the content that is included of remainder and search statement or
The correlation of Present News.For example, when being recalled to search statement " Army Day ", only can be by " for army building " " section " in each news
Frequency of occurrence be included in statistics, and other words related to " Army Day " such as " Aug. 1st ", " reviewing troops ", " August 1 Nanchang Uprising " word
The frequency will not be included in statistics, so as to which news and the semantic dependency of search statement or Present News recommended for user are poor, standard
True property is low, and recommendation effect and Consumer's Experience are bad.
The content of the invention
It is contemplated that at least solves one of technical problem in correlation technique to a certain extent.
Therefore, the present invention proposes that a kind of news recommends method, by will belong to the first of the same space with news to be recommended
Alternative news recommends user, ensure that the first alternative news is semantic related to news to be recommended, so that recommendation results are more
Accurately, Consumer's Experience is more preferable.
The present invention also proposes a kind of news recommendation apparatus.
The present invention also proposes a kind of terminal device.
The present invention also proposes a kind of computer-readable recording medium.
First aspect present invention embodiment proposes a kind of news and recommends method, including：Obtain news to be recommended；Using pre-
If space-division method, determine the object space belonging to the news to be recommended；According to the mesh belonging to the news to be recommended
Space is marked, it is determined that the first alternative news associated with the news to be recommended.
The news of the embodiment of the present invention recommends method, after news to be recommended is obtained, is divided by using default space
Method, the object space belonging to news to be recommended is determined, so as to the object space according to belonging to news to be recommended, it is determined that with waiting to push away
Recommend the first alternative news of news association.Thus, by the way that the first alternative news for belonging to the same space with news to be recommended is pushed away
Recommend to user, ensure that the first alternative news is semantic related to news to be recommended, so that recommendation results are more accurate, user's body
Test more preferable.
Second aspect of the present invention embodiment proposes a kind of news recommendation apparatus, including：Acquisition module, wait to push away for obtaining
Recommend news；First determining module, for utilizing default space-division method, determine the target empty belonging to the news to be recommended
Between；Second determining module, for the object space according to belonging to the news to be recommended, it is determined that being associated with the news to be recommended
The first alternative news.
The news recommendation apparatus of the embodiment of the present invention, after news to be recommended is obtained, divided by using default space
Method, the object space belonging to news to be recommended is determined, so as to the object space according to belonging to news to be recommended, it is determined that with waiting to push away
Recommend the first alternative news of news association.Thus, by the way that the first alternative news for belonging to the same space with news to be recommended is pushed away
Recommend to user, ensure that the first alternative news is semantic related to news to be recommended, so that recommendation results are more accurate, user's body
Test more preferable.
Third aspect present invention embodiment proposes a kind of terminal device, including：
Memory, processor and the computer program that can be run on the memory and on the processor is stored in,
Characterized in that, realize that news as described in relation to the first aspect recommends method during the computing device described program.
Fourth aspect present invention embodiment proposes a kind of computer-readable recording medium, is stored thereon with computer journey
Sequence, realize that news as described in relation to the first aspect recommends method when said program is executed by a processor.
Brief description of the drawings
Of the invention above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Substantially and it is readily appreciated that, wherein：
Fig. 1 is that the news of one embodiment of the invention recommends the flow chart of method；
Fig. 2 is that the news of another embodiment of the present invention recommends the flow chart of method；
Fig. 3 is the structural representation of the news recommendation apparatus of one embodiment of the invention；
Fig. 4 is the structural representation of the news recommendation apparatus of another embodiment of the present invention；
Fig. 5 is the structural representation of the terminal device of one embodiment of the invention.
Embodiment
Embodiments of the invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning to end
Same or similar label represents same or similar element or the element with same or like function.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to for explaining the present invention, and is not considered as limiting the invention.
Specifically, various embodiments of the present invention recommend method for existing news, after the search statement of user is got,
Or on the basis of Present News, news index is mainly carried out by way of inverted index, so as to which the news recalled be recommended
To user, recalled however, inverted index mode is only based on word frequency statisticses mode, have ignored and recommend its remaining part in news
Point included content and the correlation of search statement or Present News, so as to be the news that user recommends and search statement or ought
The semantic dependency of preceding news is poor, and accuracy is low, the problem of recommendation effect and bad Consumer's Experience, proposes a kind of news recommendation side
Method.
News provided in an embodiment of the present invention recommends method, after news to be recommended is obtained, by using default space
Division methods, the object space belonging to news to be recommended is determined, so as to the object space according to belonging to news to be recommended, it is determined that with
First alternative news of news association to be recommended.Thus, by the way that the first alternative new of the same space will be belonged to news to be recommended
News recommends user, ensure that the first alternative news is semantic related to news to be recommended, so that recommendation results are more accurate, uses
Family experience is more preferable.
Fig. 1 is that the news of one embodiment of the invention recommends the flow chart of method.
As shown in figure 1, the news recommends method to include：
Step 101, news to be recommended is obtained.
Wherein, news provided in an embodiment of the present invention recommends the executive agent of method, is provided in an embodiment of the present invention new
Recommendation apparatus is heard, the device can be configured in any terminal device, to carry out news recommendation.
Wherein, news to be recommended, can be the search statement of any news in news storehouse or user's input,
It can also be Present News.
Step 102, using default space-division method, the object space belonging to news to be recommended is determined.
Wherein, space-division method, can be approximate KNN algorithm (Approximate Nearest Neighbor,
Abbreviation ANN) or other methods, the application this is not construed as limiting.
Specifically, after getting news to be recommended, can according to corresponding to news to be recommended bag of words vector, determine to be recommended
Object space belonging to news.
That is, before step 102, can also include：
Determine bag of words vector corresponding to news to be recommended.
Wherein, bag of words vector can be bag of words vector corresponding to the title or summary of news to be recommended or wait to push away
Recommend bag of words vector corresponding to the particular content of news.In addition, the element in bag of words vector can be the title of news to be recommended, pluck
Will or particular content in, the frequency or the word frequency of each word-reverse document-frequency (Term that each word occurs
Frequency-Inverse Document Frequency, abbreviation TF-IDF) value etc., it is not restricted herein.
Specifically, dictionary can be pre-set according to each news in news storehouse, and set for each word in dictionary
One position or index, so as to after news to be recommended is got, the call number of each word be utilized, determine news to be recommended
Corresponding bag of words vector.
Such as, it is assumed that the element in bag of words vector, to recommend the frequency that each word occurs in the title of news, dictionary is
Dictionary=1. " Bob ", 2. " likes ", and 3. " to ", 4. " play ", 5. " basketball ", 6. " also ", 7.
" football ", 8. " games ", 9. " Jim ", 10. " too " }, wherein " 1 " to " 10 " is respectively to be indexed corresponding to each word.When
News to be recommended is " during Bob likes to play basketball, Jim likes too ", because " likes " is waiting to push away
Recommend in news and occur twice, " Bob ", " to ", " play ", " basketball ", " Jim ", " too " go out in news to be recommended
Now once, " also ", " football ", " games " do not occur in news to be recommended, then, can according to the call number of dictionary
To determine that bag of words vector is [1,2,1,1,1,0,0,0,1,1] corresponding to news to be recommended.
Accordingly, step 102 can specifically include：
According to bag of words vector corresponding to news to be recommended, using approximate KNN algorithm, determine belonging to news to be recommended
Object space.
Wherein, approximate KNN algorithm, can be local sensitivity Hash, accidental projection forest, k- dimensions (k-
Dimensionaltree, abbreviation k-d) tree scheduling algorithm.
Specifically, using approximate KNN algorithm, when determining the object space belonging to news to be recommended, can pre-set
The division condition in space, so as to after bag of words vector corresponding to news to be recommended is determined, can according to default condition, it is determined that
Object space belonging to news to be recommended.
As an example it is assumed that carry out space division, news storehouse according to whether the weights of each element in bag of words vector are more than 5
In news A, B, C, D, E, F respectively corresponding to bag of words vector for [1,8,6,7,0,1], [4,3,1,0,0,1], [2,1,1,1,
0,0]、[6,3,1,4,2,0]、[7,6,2,0,0,1]、[8,1,1,0,0,1].Due to news A, B, C respectively corresponding to bag of words to
The weights of first element are less than 5 in amount, and the weights of first element are more than 5 in bag of words vector corresponding to news D, E, F difference,
Therefore news A, B, C can be divided into a of space, news D, E, F is divided into the b of space.
Further, space can also further be divided to the news in space a and b.Due to bag of words corresponding to news A to
The weights of second element are more than 5 in amount, and the weights of second element are less than 5 in bag of words vector corresponding to news B, C difference, then
News A in a of space can be divided into the a1 of space, news B, C in a of space is divided into the a2 of space.Due to news
D, the weights of second element are less than 5 in bag of words vector corresponding to F difference, second element in bag of words vector corresponding to news E
Weights be more than 5, then news D, F in the b of space can be divided into the b1 of space, the news E in the b of space is divided into space
In b2.
Using approximate KNN algorithm, when substantial amounts of news can be included in news storehouse, still can quickly determine
Object space belonging to news to be recommended.
Step 103, the object space according to belonging to news to be recommended, it is determined that first associated with news to be recommended is alternative new
Hear.
Wherein, the first alternative news is in news storehouse, to the semantic related news of news to be recommended.
It should be noted that the first alternative news, it may be possible to news item, it is also possible to a plurality of news.
It is understood that by above-mentioned space-division method, semantic related news can be divided into the same space
In.And the degree of correlation of the news in the same space may be different, in embodiments of the present invention, can also determine in the same space
Any news and other news between degree of correlation, so as to according to degree of correlation, it is determined that first associated with any news is standby
Select news.
Specifically, step 103 can include：
Determine each similarity between each news and news to be recommended in object space；
According to each similarity, the first alternative news is determined.
Wherein, similarity, for characterizing the degree of correlation in object space between each news and news to be recommended, similarity is got over
Greatly, represent that the degree of correlation between each news and news to be recommended is bigger, on the contrary it is smaller.
Specifically, can be by calculating in object space between each news and news to be recommended respectively corresponding bag of words vector
Cosine similarity, Pearson correlation coefficients etc., determine each similarity between each news and news to be recommended, and according to similarity
Size, each news in object space is ranked up, so as to which the maximum news of similarity to be defined as closing with news to be recommended
First alternative news of connection.
It is understood that using the above method, semantic related each news in news storehouse can be divided into same sky
Between in, and according to the similarity in the same space between any news and other news, it is determined that associated with any news first
Alternative news.When any news in news storehouse is Present News, if getting the recommendation request of user, you can it is determined that current
Space belonging to news, and then from the news for belonging to the same space with it, the first alternative news associated with it is chosen, recommend
To user, so as to realize that the news of semantic correlation redirects., can also be by above-mentioned when getting the search statement of user's input
Method, the space belonging to search statement is determined, and from the news for belonging to the same space with it, chosen related to search statement
First alternative news, recommends user.
Specifically, in the embodiment of the present invention, because each word in each news carries out space division, the same space
Interior news is semantic related, therefore from each news for belonging to the same space with news to be recommended, selection with news to be recommended
First alternative news of association, higher with the semantic dependency and accuracy of news to be recommended, recommendation effect is more preferable.
The news of the embodiment of the present invention recommends method, after news to be recommended is obtained, is divided by using default space
Method, the object space belonging to news to be recommended is determined, so as to the object space according to belonging to news to be recommended, it is determined that with waiting to push away
Recommend the first alternative news of news association.Thus, by the way that the first alternative news for belonging to the same space with news to be recommended is pushed away
Recommend to user, ensure that the first alternative news is semantic related to news to be recommended, so that recommendation results are more accurate, user's body
Test more preferable.
, can be by default space-division method by above-mentioned analysis, will be semantic related each new in news storehouse
News is divided into the same space, so as to when recommending news for user, belong to same from Present News or search statement
In the news in space, choose and recommend user to its semantic related alternative news.In practice, user it may be desirable that
Obtain and belong to same topic but the different recommendation news of content from Present News or search statement, with reference to Fig. 2, for above-mentioned
Situation is specifically described.
Fig. 2 is that the news of another embodiment of the present invention recommends the flow chart of method.
As shown in Fig. 2 news provided in an embodiment of the present invention recommends method, after recommendation news is obtained, can also include：
Step 201, according to the word frequency of news to be recommended-reverse document-frequency, the class belonging to news to be recommended is determined.
Specifically, after getting news to be recommended, can according to word frequency-reverse document-frequency of news to be recommended, it is determined that
The preferable word of class discrimination ability in news to be recommended, so as to the class according to belonging to the word of determination, determine news to be recommended
Affiliated class.
Pair step 202, the news for belonging to mutually similar with news to be recommended carries out space division, it is determined that with news category to be recommended
In the news agregator of different spaces.
Step 203, according to the similarity of each news in news agregator and news to be recommended, it is determined that the with association to be recommended
Two alternative news.
Wherein, the second alternative news is the news related to media event to be recommended in news storehouse.
It should be noted that the second alternative news, it may be possible to news item, it is also possible to a plurality of news.
Specifically, carry out space division by the way that mutually similar news will be belonged to news to be recommended, it is determined that with it is to be recommended new
The news agregator for belonging to different spaces is heard, and determines the similarity of each news and news to be recommended in news agregator, it may be determined that
Belong to same class with news to be recommended but belong to the second alternative news of different spaces.
During specific implementation, step 203 can be accomplished by the following way：
Determine that news maximum with news similarity to be recommended and belonging to different spaces is alternative for each second in news agregator
News.
Specifically, it may be determined that each similarity in news agregator between each news and news to be recommended, and according to similarity
Size, each news in news agregator is ranked up, so as to by similarity maximum and belong to different spaces with news to be recommended
News be defined as the second alternative news.
Specific space partition process and resemblance determination, the associated description of above-described embodiment is referred to, herein
Do not repeat.
It is understood that by the above method, each news in news storehouse can be subjected to hierarchical clustering, so that will
The news for belonging to same topic is divided into same class, and by carrying out space division to belonging to of a sort news, it can incite somebody to action
Belong to same topic, but belong to the news of different event, be divided into different spaces, and then belong to according to each news and with it
In the similarity of each news that is mutually similar but belonging to different spaces, it is determined that the second alternative news associated with each news.
When any news in news storehouse is Present News, redirected or recommendation request if getting, you can according to current
The word frequency of news-reverse document-frequency, the class belonging to Present News is determined, and then belong to mutually similar but category from Present News
In the news agregator of different spaces, the similarity of each news in Present News and news agregator, choose and current new
The second alternative news of association is heard, recommends user.When getting the search statement of user's input, above-mentioned side can also be passed through
Method, according to the word frequency of search statement-reverse document-frequency, the class belonging to search statement is determined, and then belong to from search statement
It is mutually similar but belong in the news agregator of different spaces, the similarity of each news in search statement and news agregator, choosing
The alternative news of second associated with search statement is taken, recommends user.
Because the second alternative news and news to be recommended belong to same class, but belong to different spaces, and in same class
News belongs to same topic, and the news in different spaces belongs to different event, so as to be jumped to from Present News or search statement
During the second alternative news, it is possible to achieve the news of different event redirects in topic.
The news of the embodiment of the present invention recommends method, after news to be recommended is got, first pair with news category to be recommended
Space division is carried out in mutually similar news, it is determined that belonging to the news agregator of different spaces with news to be recommended, then according to new
Hear the similarity of each news and news to be recommended in set, it is determined that the second alternative news with association to be recommended, thus, pass through by
The the second alternative news for belonging to mutually similar with news to be recommended and belonging to different spaces recommends user, ensure that second is alternative
News belongs to same topic with news to be recommended, and the similarity avoided between the two in literal and content is too high so that
Recommendation results are more rich, and Consumer's Experience is more preferable.
Fig. 3 is the structural representation of the news recommendation apparatus of one embodiment of the invention.
As shown in figure 3, the news recommendation apparatus includes：
Acquisition module 31, for obtaining news to be recommended；
First determining module 32, for utilizing default space-division method, determine the target empty belonging to news to be recommended
Between；
Second determining module 33, for the object space according to belonging to news to be recommended, it is determined that being associated with news to be recommended
The first alternative news.
Specifically, news recommendation apparatus provided in an embodiment of the present invention, can perform news provided in an embodiment of the present invention
Recommendation method, the device can be configured in any terminal device, to generate focus information comment.
Wherein, the first alternative news is and the semantic related news of news to be recommended.
In a kind of possible way of realization of the embodiment of the present application, above-mentioned second determining module 33, it is specifically used for：
Determine each similarity between each news and news to be recommended in object space；
According to each similarity, the first alternative news is determined.
It should be noted that foregoing recommend the explanation of embodiment of the method to be also applied for the news of the embodiment news
Recommendation apparatus, here is omitted.
The news recommendation apparatus of the embodiment of the present invention, after news to be recommended is obtained, divided by using default space
Method, the object space belonging to news to be recommended is determined, so as to the object space according to belonging to news to be recommended, it is determined that with waiting to push away
Recommend the first alternative news of news association.Thus, by the way that the first alternative news for belonging to the same space with news to be recommended is pushed away
Recommend to user, ensure that the first alternative news is semantic related to news to be recommended, so that recommendation results are more accurate, user's body
Test more preferable.
Fig. 4 is the structural representation of the news recommendation apparatus of another embodiment of the present invention.
As shown in figure 4, on the basis of Fig. 3, the news recommendation apparatus, in addition to：
3rd determining module 41, for determining bag of words vector corresponding to news to be recommended.
4th determining module 42, for the word frequency according to news to be recommended-reverse document-frequency, determine news institute to be recommended
The class of category.
5th determining module 43, belong to mutually similar news progress space division with news to be recommended for, it is determined that with
News to be recommended belongs to the news agregator of different spaces.
6th determining module 44, for the similarity according to each news in news agregator and news to be recommended, it is determined that with treating
Recommend the second alternative news of association.
Wherein, the second alternative news is the news related to media event to be recommended.
In a kind of possible way of realization of the embodiment of the present application, above-mentioned first determining module 32, it is specifically used for：
According to bag of words vector corresponding to news to be recommended, using approximate KNN algorithm, determine belonging to news to be recommended
Object space.
In the alternatively possible way of realization of the embodiment of the present application, above-mentioned 6th determining module 44, it is specifically used for：
Determine that news maximum with news similarity to be recommended and belonging to different spaces is alternative for each second in news agregator
News.
It should be noted that foregoing recommend the explanation of embodiment of the method to be also applied for the news of the embodiment news
Recommendation apparatus, here is omitted.
The news recommendation apparatus of the embodiment of the present invention, after news to be recommended is obtained, divided by using default space
Method, the object space belonging to news to be recommended is determined, so as to the object space according to belonging to news to be recommended, it is determined that with waiting to push away
Recommend the first alternative news of news association.Thus, by the way that the first alternative news for belonging to the same space with news to be recommended is pushed away
Recommend to user, ensure that the first alternative news is semantic related to news to be recommended, so that recommendation results are more accurate, user's body
Test more preferable.
Fig. 5 is a kind of structural representation of terminal device provided in an embodiment of the present invention.
As shown in figure 5, the terminal device includes：
Memory 51, processor 52 and it is stored in the computer program that can be run on memory 51 and on the processor 52.
Processor 52 realizes that the news provided in above-described embodiment recommends method when performing described program.
Wherein, terminal device can be computer, mobile phone, wearable device etc..
Further, terminal device also includes：
Communication interface 53, for the communication between memory 51 and processor 52.
Memory 51, for depositing the computer program that can be run on the processor 52.
Memory 51 may include high-speed RAM memory, it is also possible to also including nonvolatile memory (non-volatile
Memory), a for example, at least magnetic disk storage.
Processor 52, realize that the news described in above-described embodiment recommends method during for performing described program.
If memory 51, processor 52 and the independent realization of communication interface 53, communication interface 53, memory 51 and processing
Device 52 can be connected with each other by bus and complete mutual communication.The bus can be industry standard architecture
(Industry Standard Architecture, abbreviation ISA) bus, external equipment interconnection (Peripheral
Component Interconnect, abbreviation PCI) bus or extended industry-standard architecture (Extended Industry
Standard Architecture, abbreviation EISA) bus etc..The bus can be divided into address bus, data/address bus, control
Bus etc..For ease of representing, only represented in Fig. 5 with a thick line, it is not intended that an only bus or a type of total
Line.
Alternatively, in specific implementation, if memory 51, processor 52 and communication interface 53, are integrated in chip piece
Upper realization, then memory 51, processor 52 and communication interface 53 can complete mutual communication by internal interface.
Processor 52 can be a central processing unit (Central Processing Unit, abbreviation CPU), either
Specific integrated circuit (Application Specific Integrated Circuit, abbreviation ASIC), or be arranged to
Implement one or more integrated circuits of the embodiment of the present invention.
Fourth aspect present invention embodiment proposes a kind of computer-readable recording medium, is stored thereon with computer journey
Sequence, realize that the news in previous embodiment such as recommends method when the program is executed by processor.
Fifth aspect present invention embodiment proposes a kind of computer program product, when in the computer program product
When instruction is by computing device, performs the news in previous embodiment such as and recommend method.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or the spy for combining the embodiment or example description
Point is contained at least one embodiment or example of the present invention.In this manual, to the schematic representation of above-mentioned term not
Identical embodiment or example must be directed to.Moreover, specific features, structure, material or the feature of description can be with office
Combined in an appropriate manner in one or more embodiments or example.In addition, in the case of not conflicting, the skill of this area
Art personnel can be tied the different embodiments or example and the feature of different embodiments or example described in this specification
Close and combine.
In addition, term " first ", " second " are only used for describing purpose, and it is not intended that instruction or hint relative importance
Or the implicit quantity for indicating indicated technical characteristic.Thus, define " first ", the feature of " second " can be expressed or
Implicitly include at least one this feature.In the description of the invention, " multiple " are meant that at least two, such as two, three
It is individual etc., unless otherwise specifically defined.
Any process or method described otherwise above description in flow chart or herein is construed as, and represents to include
Module, fragment or the portion of the code of the executable instruction of one or more the step of being used to realize custom logic function or process
Point, and the scope of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discuss suitable
Sequence, including according to involved function by it is basic simultaneously in the way of or in the opposite order, carry out perform function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system including the system of processor or other can be held from instruction
The system of row system, device or equipment instruction fetch and execute instruction) use, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium " can any can be included, store, communicate, propagate or pass
Defeated program is for instruction execution system, device or equipment or the dress used with reference to these instruction execution systems, device or equipment
Put.The more specifically example (non-exhaustive list) of computer-readable medium includes following：Electricity with one or more wiring
Connecting portion (electronic installation), portable computer diskette box (magnetic device), random access memory (RAM), read-only storage
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device, and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, computer-readable medium, which can even is that, to print the paper of described program thereon or other are suitable
Medium, because can then enter edlin, interpretation or if necessary with it for example by carrying out optical scanner to paper or other media
His suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each several part of the present invention can be realized with hardware, software, firmware or combinations thereof.Above-mentioned
In embodiment, software that multiple steps or method can be performed in memory and by suitable instruction execution system with storage
Or firmware is realized.If, and in another embodiment, can be with well known in the art for example, realized with hardware
Any one of row technology or their combination are realized：With the logic gates for realizing logic function to data-signal
Discrete logic, have suitable combinational logic gate circuit application specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are appreciated that to realize all or part of step that above-described embodiment method carries
Suddenly it is that by program the hardware of correlation can be instructed to complete, described program can be stored in a kind of computer-readable storage medium
In matter, the program upon execution, including one or a combination set of the step of embodiment of the method.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing module, can also
That unit is individually physically present, can also two or more units be integrated in a module.Above-mentioned integrated mould
Block can both be realized in the form of hardware, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized in the form of software function module and as independent production marketing or in use, can also be stored in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only storage, disk or CD etc..Although have been shown and retouch above
Embodiments of the invention are stated, it is to be understood that above-described embodiment is exemplary, it is impossible to be interpreted as the limit to the present invention
System, one of ordinary skill in the art can be changed to above-described embodiment, change, replace and become within the scope of the invention
Type.
Claims (14)
1. a kind of news recommends method, it is characterised in that including：
Obtain news to be recommended；
Using default space-division method, the object space belonging to the news to be recommended is determined；
According to the object space belonging to the news to be recommended, it is determined that the first alternative news associated with the news to be recommended.
2. the method as described in claim 1, it is characterised in that the object space determined belonging to the news to be recommended it
Before, in addition to：
Determine bag of words vector corresponding to the news to be recommended；
The object space determined belonging to the news to be recommended, including：
According to bag of words vector corresponding to the news to be recommended, using approximate KNN algorithm, the news institute to be recommended is determined
The object space of category.
3. the method as described in claim 1, it is characterised in that it is described determine to associate with the news to be recommended it is first alternative
News, including：
Determine each similarity between each news and the news to be recommended in the object space；
According to each similarity, the described first alternative news is determined.
4. the method as described in claim 1-3 is any, it is characterised in that after the acquisition news to be recommended, in addition to：
According to the word frequency of the news to be recommended-reverse document-frequency, the class belonging to the news to be recommended is determined；
Pair belonging to mutually similar news with the news to be recommended carries out space division, it is determined that belonging to not with the news to be recommended
The news agregator of isospace；
According to the similarity of each news in the news agregator and the news to be recommended, it is determined that the with the association to be recommended
Two alternative news.
5. method as claimed in claim 4, it is characterised in that the determination is alternative new with the second of the association to be recommended
Hear, including：
Determine maximum with the news similarity to be recommended in the news agregator and belong to the news of different spaces for each second
Alternative news.
6. method as claimed in claim 4, it is characterised in that the first alternative news is semantic with the news to be recommended
Related news, the second alternative news is the news related to the media event to be recommended.
A kind of 7. news recommendation apparatus, it is characterised in that including：
Acquisition module, for obtaining news to be recommended；
First determining module, for utilizing default space-division method, determine the object space belonging to the news to be recommended；
Second determining module, for the object space according to belonging to the news to be recommended, it is determined that being closed with the news to be recommended
First alternative news of connection.
8. device as claimed in claim 7, it is characterised in that also include：
3rd determining module, for determining bag of words vector corresponding to the news to be recommended；
First determining module, is specifically used for：
According to bag of words vector corresponding to the news to be recommended, using approximate KNN algorithm, the news institute to be recommended is determined
The object space of category.
9. device as claimed in claim 7, it is characterised in that second determining module, be specifically used for：
Determine each similarity between each news and the news to be recommended in the object space；
According to each similarity, the described first alternative news is determined.
10. the device as described in claim 7-9 is any, it is characterised in that also include：
4th determining module, for the word frequency according to the news to be recommended-reverse document-frequency, determine the news to be recommended
Affiliated class；
5th determining module, belong to mutually similar news progress space division with the news to be recommended for, it is determined that and institute
State the news agregator that news to be recommended belongs to different spaces；
6th determining module, for the similarity according to each news in the news agregator and the news to be recommended, it is determined that with
Second alternative news of the association to be recommended.
11. device as claimed in claim 10, it is characterised in that the 6th determining module, be specifically used for：
Determine maximum with the news similarity to be recommended in the news agregator and belong to the news of different spaces for each second
Alternative news.
12. device as claimed in claim 10, it is characterised in that the first alternative news be and the news language to be recommended
Adopted related news, the second alternative news is the news related to the media event to be recommended.
13. a kind of terminal device, including：
Memory, processor and the computer program that can be run on the memory and on the processor is stored in, it is special
Sign is, the news recommendation method as described in any in claim 1-6 is realized during the computing device described program.
14. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that described program is processed
Realize that the news as described in any in claim 1-6 recommends method when device performs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711138838.7A CN107748801B (en) | 2017-11-16 | 2017-11-16 | News recommendation method and device, terminal equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711138838.7A CN107748801B (en) | 2017-11-16 | 2017-11-16 | News recommendation method and device, terminal equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107748801A true CN107748801A (en) | 2018-03-02 |
| CN107748801B CN107748801B (en) | 2022-04-29 |
Family
ID=61251220
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711138838.7A Active CN107748801B (en) | 2017-11-16 | 2017-11-16 | News recommendation method and device, terminal equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107748801B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109684553A (en) * | 2018-12-26 | 2019-04-26 | 北京百度网讯科技有限公司 | For obtaining the method and device of information |
| CN110245243A (en) * | 2019-06-20 | 2019-09-17 | 北京百度网讯科技有限公司 | The method and apparatus of news retrieval, electronic equipment, computer-readable medium |
| CN112613296A (en) * | 2020-12-07 | 2021-04-06 | 深圳价值在线信息科技股份有限公司 | News importance degree acquisition method and device, terminal equipment and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102708198A (en) * | 2012-05-16 | 2012-10-03 | 杭州通策会综合服务有限公司 | Individualized network advertisement pushing method |
| CN103793476A (en) * | 2014-01-08 | 2014-05-14 | 西安电子科技大学 | Network community based collaborative filtering recommendation method |
| CN104102639A (en) * | 2013-04-02 | 2014-10-15 | 腾讯科技（深圳）有限公司 | Text classification based promotion triggering method and device |
| CN104572855A (en) * | 2014-12-17 | 2015-04-29 | 深圳先进技术研究院 | News recommendation method and device |
| CN104933074A (en) * | 2014-03-20 | 2015-09-23 | 华为技术有限公司 | News ordering method and device and terminal equipment |
| CN105022840A (en) * | 2015-08-18 | 2015-11-04 | 新华网股份有限公司 | News information processing method, news recommendation method and related devices |
| CN106294618A (en) * | 2016-08-01 | 2017-01-04 | 北京百度网讯科技有限公司 | Searching method and device |
| CN106407239A (en) * | 2015-08-03 | 2017-02-15 | 阿里巴巴集团控股有限公司 | Methods and apparatuses used for recommending information and assisting in recommending information |
| US20170132230A1 (en) * | 2015-11-09 | 2017-05-11 | WP Company LLC d/b/a The Washington Post | Systems and methods for recommending temporally relevant news content using implicit feedback data |
-
2017
- 2017-11-16 CN CN201711138838.7A patent/CN107748801B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102708198A (en) * | 2012-05-16 | 2012-10-03 | 杭州通策会综合服务有限公司 | Individualized network advertisement pushing method |
| CN104102639A (en) * | 2013-04-02 | 2014-10-15 | 腾讯科技（深圳）有限公司 | Text classification based promotion triggering method and device |
| CN103793476A (en) * | 2014-01-08 | 2014-05-14 | 西安电子科技大学 | Network community based collaborative filtering recommendation method |
| CN104933074A (en) * | 2014-03-20 | 2015-09-23 | 华为技术有限公司 | News ordering method and device and terminal equipment |
| CN104572855A (en) * | 2014-12-17 | 2015-04-29 | 深圳先进技术研究院 | News recommendation method and device |
| CN106407239A (en) * | 2015-08-03 | 2017-02-15 | 阿里巴巴集团控股有限公司 | Methods and apparatuses used for recommending information and assisting in recommending information |
| CN105022840A (en) * | 2015-08-18 | 2015-11-04 | 新华网股份有限公司 | News information processing method, news recommendation method and related devices |
| US20170132230A1 (en) * | 2015-11-09 | 2017-05-11 | WP Company LLC d/b/a The Washington Post | Systems and methods for recommending temporally relevant news content using implicit feedback data |
| CN106294618A (en) * | 2016-08-01 | 2017-01-04 | 北京百度网讯科技有限公司 | Searching method and device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109684553A (en) * | 2018-12-26 | 2019-04-26 | 北京百度网讯科技有限公司 | For obtaining the method and device of information |
| CN110245243A (en) * | 2019-06-20 | 2019-09-17 | 北京百度网讯科技有限公司 | The method and apparatus of news retrieval, electronic equipment, computer-readable medium |
| CN112613296A (en) * | 2020-12-07 | 2021-04-06 | 深圳价值在线信息科技股份有限公司 | News importance degree acquisition method and device, terminal equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107748801B (en) | 2022-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104462364B (en) | Method and device is recommended in search | |
| CN108491529A (en) | Information recommendation method and device | |
| CN109189991A (en) | Repeat video frequency identifying method, device, terminal and computer readable storage medium | |
| CN109255126A (en) | Article recommended method and device | |
| KR101330158B1 (en) | Method for analyzing text emotion index and computer readable medium | |
| CN106940726B (en) | Creative automatic generation method and terminal based on knowledge network | |
| CN106844341A (en) | News in brief extracting method and device based on artificial intelligence | |
| CN107330023A (en) | Content of text based on focus recommends method and apparatus | |
| CN111767713B (en) | Keyword extraction method and device, electronic equipment and storage medium | |
| CN109325146A (en) | A kind of video recommendation method, device, storage medium and server | |
| CN110275952A (en) | News recommended method, device and medium based on user's short-term interest | |
| CN107885888A (en) | Information processing method and device, terminal device and computer-readable recording medium | |
| CN110110139A (en) | The method, apparatus and electronic equipment that a kind of pair of recommendation results explain | |
| CN109657044A (en) | Data retrieval method, data reordering method, device, terminal and storage medium | |
| CN107748801A (en) | News recommends method, apparatus, terminal device and computer-readable recording medium | |
| CN109359196A (en) | Text Multimodal presentation method and device | |
| CN110069739A (en) | The page preloads method and device | |
| CN107203265A (en) | Information interacting method and device | |
| CN111159563A (en) | Method, device and equipment for determining user interest point information and storage medium | |
| CN108604248A (en) | Utilize the notes providing method and device of the correlation calculations based on artificial intelligence | |
| CN109657043B (en) | Method, device and equipment for automatically generating article and storage medium | |
| CN112989118B (en) | Video recall method and device | |
| CN110232071A (en) | Search method, device and storage medium, the electronic device of drug data | |
| CN108021713B (en) | Document clustering method and device | |
| Gao et al. | Learning to respond with your favorite stickers: A framework of unifying multi-modality and user preference in multi-turn dialog |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |