CN107748801B - News recommendation method and device, terminal equipment and computer readable storage medium - Google Patents
News recommendation method and device, terminal equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN107748801B CN107748801B CN201711138838.7A CN201711138838A CN107748801B CN 107748801 B CN107748801 B CN 107748801B CN 201711138838 A CN201711138838 A CN 201711138838A CN 107748801 B CN107748801 B CN 107748801B
- Authority
- CN
- China
- Prior art keywords
- news
- recommended
- determining
- belongs
- space
- 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.)
- Active
Links
Images
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 invention provides a news recommendation method, a news recommendation device, terminal equipment and a computer readable storage medium, wherein the method comprises the following steps: acquiring news to be recommended; determining a target space to which the news to be recommended belongs by using a preset space division method; and determining first alternative news related to the news to be recommended according to the target space to which the recommended news belongs. Therefore, the first alternative news belonging to the same space with the news to be recommended is recommended to the user, the semantic correlation between the first alternative news and the news to be recommended is guaranteed, the recommendation result is more accurate, and the user experience is better.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a news recommendation method, an apparatus, a terminal device, and a computer-readable storage medium.
Background
With the rapid development of information technology and the internet, network news is more and more popular with people and becomes a main way for people to acquire information in daily life. With the development of mobile internet in recent years, besides the well-known large websites and network self-media platforms (e.g., microblog, etc.), many news content providers provide users with a large amount of news information through application software (APP) applicable to mobile communication products.
In the existing news recommending method, after search sentences of a user are obtained or on the basis of current news, news indexing is mainly carried out in an inverted indexing mode, so that recalled news is recommended to the user. However, the inverted index method is only based on the word frequency statistics method for recalling, and the relevance of the content contained in the rest part of the recommended news and the search sentences or the current news is ignored. For example, when a search sentence "army building festival" is recalled, only the frequency of occurrence of "army building" and "festival" in each news is counted, but the frequency of other words related to "army building festival" such as "eight", "read soldier" and "nan chang suggestive" is not counted, so that the news recommended to the user has poor semantic relevance to the search sentence or the current news, low accuracy, and poor recommendation effect and user experience.
Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the related art.
Therefore, the invention provides a news recommending method, which recommends the first alternative news belonging to the same space with the news to be recommended to a user, so that the semantics of the first alternative news and the news to be recommended are ensured to be related, the recommending result is more accurate, and the user experience is better.
The invention further provides a news recommending device.
The invention also provides the terminal equipment.
The invention also provides a computer readable storage medium.
An embodiment of a first aspect of the present invention provides a news recommendation method, including: acquiring news to be recommended; determining a target space to which the news to be recommended belongs by using a preset space division method; and determining first alternative news related to the news to be recommended according to the target space to which the news to be recommended belongs.
According to the news recommending method, after the news to be recommended is obtained, the target space to which the news to be recommended belongs is determined by using the preset space dividing method, and therefore the first alternative news related to the news to be recommended is determined according to the target space to which the news to be recommended belongs. Therefore, the first alternative news belonging to the same space with the news to be recommended is recommended to the user, the semantic correlation between the first alternative news and the news to be recommended is guaranteed, the recommendation result is more accurate, and the user experience is better.
An embodiment of a second aspect of the present invention provides a news recommendation apparatus, including: the acquisition module is used for acquiring news to be recommended; the first determining module is used for determining a target space to which the news to be recommended belongs by using a preset space division method; and the second determining module is used for determining first alternative news related to the news to be recommended according to the target space to which the news to be recommended belongs.
According to the news recommending device, after the news to be recommended is obtained, the target space to which the news to be recommended belongs is determined by using the preset space dividing method, and therefore the first alternative news related to the news to be recommended is determined according to the target space to which the news to be recommended belongs. Therefore, the first alternative news belonging to the same space with the news to be recommended is recommended to the user, the semantic correlation between the first alternative news and the news to be recommended is guaranteed, the recommendation result is more accurate, and the user experience is better.
An embodiment of a third aspect of the present invention provides a terminal device, including:
memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the news recommendation method according to the first aspect when executing the program.
A fourth aspect of the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the news recommendation method according to the first aspect.
Drawings
The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow diagram of a news recommendation method in accordance with one embodiment of the present invention;
FIG. 2 is a flow chart of a news recommendation method according to another embodiment of the present invention;
fig. 3 is a schematic structural diagram of a news recommender in accordance with an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a news recommender in accordance with another embodiment of the present invention;
fig. 5 is a schematic structural diagram of a terminal device according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
Specifically, each embodiment of the present invention provides a news recommendation method for solving the problems of poor semantic relevance, low accuracy, poor recommendation effect and poor user experience of news recommended by a user and search sentences or current news by mainly performing news indexing in an inverted indexing manner after the search sentences of the user are acquired or on the basis of the current news, however, the inverted indexing manner is only based on word frequency statistics to perform recall, and the relevance of the content contained in the rest of the recommended news and the search sentences or the current news is ignored.
According to the news recommending method provided by the embodiment of the invention, after the news to be recommended is obtained, the target space to which the news to be recommended belongs is determined by using the preset space dividing method, so that the first alternative news related to the news to be recommended is determined according to the target space to which the news to be recommended belongs. Therefore, the first alternative news belonging to the same space with the news to be recommended is recommended to the user, the semantic correlation between the first alternative news and the news to be recommended is guaranteed, the recommendation result is more accurate, and the user experience is better.
Fig. 1 is a flowchart of a news recommendation method according to an embodiment of the present invention.
As shown in fig. 1, the news recommendation method includes:
The execution subject of the news recommendation method provided by the embodiment of the invention is the news recommendation device provided by the embodiment of the invention, and the device can be configured in any terminal equipment to perform news recommendation.
The news to be recommended may be any news in a news library, search sentences input by a user, or current news.
And step 102, determining a target space to which news to be recommended belongs by using a preset space division method.
The space division method may be an Approximate Nearest Neighbor Algorithm (ANN) or other methods, which is not limited in this application.
Specifically, after the news to be recommended is obtained, the target space to which the news to be recommended belongs can be determined according to the bag-of-word vector corresponding to the news to be recommended.
That is, before step 102, the method may further include:
and determining a bag-of-words vector corresponding to the news to be recommended.
The bag-of-word vector may be a bag-of-word vector corresponding to a title or an abstract of the news to be recommended, or a bag-of-word vector corresponding to specific content of the news to be recommended. In addition, the elements in the bag-of-words vector may be a title, an abstract, or a Frequency of occurrence of each word in the specific content of the news to be recommended, or a Term Frequency-Inverse file Frequency (TF-IDF) value of each word, and the like, which is not limited herein.
Specifically, a dictionary can be preset according to each news in the news library, and a position or an index is set for each word in the dictionary, so that after the news to be recommended is obtained, a bag-of-word vector corresponding to the news to be recommended can be determined by using the index number of each word.
For example, suppose an element in a bag-of-words vector is the frequency of occurrence of each word in a title of recommended news, and the Dictionary is Dictionary {1. "Bob", 2. "like", 3. "to", 4. "play", 5. "baseball", 6. "also", 7. "football", 8. "games", 9. "Jim", 10. "to", where "1" to "10" are indexes corresponding to each word, respectively. When the news to be recommended is "Bob liks to play baseball, Jim liks to", since "liks" appears twice in the news to be recommended, "Bob", "to", "play", "baseball", "Jim", and "too" all appear once in the news to be recommended, "also", "football", and "games" do not appear in the news to be recommended, the corresponding bag-of-words vector of the news to be recommended can be determined as [1,2,1,1,1,0,0,0,1,1] according to the index number of the dictionary.
Correspondingly, step 102 may specifically include:
and determining a target space to which the news to be recommended belongs by using an approximate nearest neighbor algorithm according to the bag-of-word vector corresponding to the news to be recommended.
The approximate nearest neighbor algorithm may be a locality sensitive hash, a random projection forest, a k-dimensional (k-dimensional, abbreviated as k-d) tree, or the like.
Specifically, when the target space to which the news to be recommended belongs is determined by using the approximate nearest neighbor algorithm, the space division condition can be preset, so that after the bag-of-word vector corresponding to the news to be recommended is determined, the target space to which the news to be recommended belongs can be determined according to the preset condition.
For example, assuming that space division is performed according to whether the weight of each element in the bag-of-word vector is greater than 5, the bag-of-word vectors corresponding to news A, B, C, D, E, F in the news library are [1,8,6,7,0,1], [4,3,1,0,0,1], [2,1,1, 0,0], [6,3,1,4,2,0], [7,6,2,0,0,1], [8,1,1,0,0,1], respectively. Since the weight of the first element in the bag-of-words vector corresponding to news A, B, C is less than 5, and the weight of the first element in the bag-of-words vector corresponding to news D, E, F is greater than 5, news A, B, C can be divided into space a, and news D, E, F can be divided into space b.
Further, the news in the spaces a and b can be further divided into spaces. Since the weight of the second element in the bag-of-words vector corresponding to news a is greater than 5, and the weights of the second elements in the bag-of-words vectors corresponding to news B, C are less than 5, news a in space a can be divided into space a1, and news B, C in space a can be divided into space a 2. Since the weight of the second element in the bag-of-words vector corresponding to the news D, F is less than 5, and the weight of the second element in the bag-of-words vector corresponding to the news E is greater than 5, the news D, F in the space b can be divided into the space b1, and the news E in the space b can be divided into the space b 2.
By utilizing the approximate nearest neighbor algorithm, when a news library contains a large number of news, the target space to which the news to be recommended belongs can be still quickly determined.
The first alternative news is news semantically related to news to be recommended in a news library.
It should be noted that the first candidate news may be one piece of news or multiple pieces of news.
It will be appreciated that semantically related news can be partitioned into the same space by the above-described spatial partitioning method. While the news in the same space may have different degrees of relevance, in the embodiment of the present invention, the degree of relevance between any news and other news in the same space may also be determined, so that the first candidate news associated with any news is determined according to the degree of relevance.
Specifically, step 103 may include:
determining similarity between each news in the target space and the news to be recommended;
and determining the first candidate news according to the similarity.
The similarity is used for representing the correlation degree between each news and the news to be recommended in the target space, and the larger the similarity is, the larger the correlation degree between each news and the news to be recommended is, and the smaller the similarity is.
Specifically, the cosine similarity, the pearson correlation coefficient and the like between the word bag vectors respectively corresponding to the news and the news to be recommended in the target space can be calculated, the similarity between the news and the news to be recommended is determined, the news in the target space is sequenced according to the similarity, and therefore the news with the maximum similarity is determined as the first candidate news related to the news to be recommended.
It can be understood that, by using the above method, the semantically related news in the news library can be divided into the same space, and the first candidate news related to any news is determined according to the similarity between any news and other news in the same space. When any news in the news library is current news, if a recommendation request of a user is obtained, the space to which the current news belongs can be determined, and then first alternative news related to the current news is selected from the news belonging to the same space and recommended to the user, so that news skip related to semantics is achieved. When the search sentence input by the user is acquired, the space to which the search sentence belongs can be determined by the method, and the first candidate news related to the search sentence is selected from the news belonging to the same space and recommended to the user.
Specifically, in the embodiment of the invention, because the space division is carried out according to each word in each news, and the news in the same space is semantically related, the semantic relevance and accuracy between the first alternative news which is selected from the news belonging to the same space with the news to be recommended and is related to the news to be recommended are higher, and the recommendation effect is better.
According to the news recommending method, after the news to be recommended is obtained, the target space to which the news to be recommended belongs is determined by using the preset space dividing method, and therefore the first alternative news related to the news to be recommended is determined according to the target space to which the news to be recommended belongs. Therefore, the first alternative news belonging to the same space with the news to be recommended is recommended to the user, the semantic correlation between the first alternative news and the news to be recommended is guaranteed, the recommendation result is more accurate, and the user experience is better.
Through the analysis, each news related to the semantics in the news library can be divided into the same space through a preset space division method, so that when the news is recommended to the user, the alternative news related to the semantics can be selected from the news belonging to the same space with the current news or the search sentences and recommended to the user. In practical applications, the user may also want to obtain recommended news that belongs to the same topic as the current news or search sentence but has a different content, which is described in detail below with reference to fig. 2.
Fig. 2 is a flowchart of a news recommendation method according to another embodiment of the present invention.
As shown in fig. 2, after acquiring the recommended news, the news recommendation method provided in the embodiment of the present invention may further include:
Specifically, after the news to be recommended is acquired, the words with better category distinguishing capability in the news to be recommended can be determined according to the word frequency-reverse file frequency of the news to be recommended, so that the category to which the news to be recommended belongs is determined according to the determined category to which the words belong.
And 203, determining second alternative news related to the news to be recommended according to the similarity between each news in the news set and the news to be recommended.
And the second candidate news is news related to the news event to be recommended in the news library.
It should be noted that the second candidate news may be one piece of news or multiple pieces of news.
Specifically, news belonging to the same type as the news to be recommended are spatially divided, a news set belonging to a different space from the news to be recommended is determined, and the similarity between each news in the news set and the news to be recommended is determined, so that second alternative news belonging to the same type as the news to be recommended but belonging to a different space can be determined.
In a specific implementation, step 203 may be implemented by:
and determining the news which has the maximum similarity with the news to be recommended and belongs to different spaces in the news set as each second candidate news.
Specifically, the similarity between each news in the news set and the news to be recommended can be determined, and each news in the news set is sorted according to the similarity, so that the news with the highest similarity and different space from the news to be recommended is determined as the second candidate news.
For a specific space division process and a similarity determination process, reference may be made to the related description of the foregoing embodiments, which is not repeated herein.
It can be understood that, by the above method, the news in the news library can be hierarchically clustered, so that the news belonging to the same topic can be divided into the same class, and the news belonging to the same topic but different events can be divided into different spaces by spatially dividing the news belonging to the same class, and then the second alternative news associated with each news is determined according to the similarity between each news and the news belonging to the same class but different spaces.
When any news in the news library is current news, if a skip request or a recommendation request is obtained, the category to which the current news belongs can be determined according to the word frequency-reverse file frequency of the current news, and then a second alternative news related to the current news is selected from a news set which belongs to the same category as the current news but belongs to a different space according to the similarity of the current news and each news in the news set and is recommended to a user. When the search sentence input by the user is obtained, the method can also be used for determining the class to which the search sentence belongs according to the word frequency-reverse file frequency of the search sentence, and further selecting second alternative news related to the search sentence from a news set which belongs to the same type as the search sentence and belongs to a different space according to the similarity between the search sentence and each news in the news set, and recommending the second alternative news to the user.
The second alternative news and the news to be recommended belong to the same category but belong to different spaces, the news in the same category belong to the same topic, and the news in different spaces belong to different events, so that when the current news or the search sentences jump to the second alternative news, the jumping of the news of different events in the topic can be realized.
According to the news recommending method, after the news to be recommended is obtained, the news which is the same as the news to be recommended is divided spatially, the news set which is different from the news to be recommended is determined, and then the second alternative news related to the news to be recommended is determined according to the similarity between each news in the news set and the news to be recommended.
Fig. 3 is a schematic structural diagram of a news recommendation apparatus according to an embodiment of the present invention.
As shown in fig. 3, the news recommender includes:
the obtaining module 31 is configured to obtain news to be recommended;
the first determining module 32 is configured to determine, by using a preset space division method, a target space to which news to be recommended belongs;
the second determining module 33 is configured to determine, according to the target space to which the news to be recommended belongs, first candidate news related to the news to be recommended.
Specifically, the news recommendation apparatus provided in the embodiment of the present invention may be configured in any terminal device to generate a hotspot information review article.
The first candidate news is news semantically related to news to be recommended.
In a possible implementation form of the embodiment of the present application, the second determining module 33 is specifically configured to:
determining similarity between each news in the target space and the news to be recommended;
and determining the first candidate news according to the similarity.
It should be noted that the foregoing explanation on the embodiment of the news recommendation method is also applicable to the news recommendation apparatus of this embodiment, and details are not repeated here.
According to the news recommending device, after the news to be recommended is obtained, the target space to which the news to be recommended belongs is determined by using the preset space dividing method, and therefore the first alternative news related to the news to be recommended is determined according to the target space to which the news to be recommended belongs. Therefore, the first alternative news belonging to the same space with the news to be recommended is recommended to the user, the semantic correlation between the first alternative news and the news to be recommended is guaranteed, the recommendation result is more accurate, and the user experience is better.
Fig. 4 is a schematic structural diagram of a news recommender according to another embodiment of the present invention.
As shown in fig. 4, on the basis of fig. 3, the news recommender further includes:
and a third determining module 41, configured to determine a bag-of-words vector corresponding to the news to be recommended.
And the fourth determining module 42 is configured to determine the category to which the news to be recommended belongs according to the word frequency of the news to be recommended — the reverse file frequency.
The fifth determining module 43 is configured to perform spatial division on news that belong to the same category as the news to be recommended, and determine a news set that belongs to a different space from the news to be recommended.
And a sixth determining module 44, configured to determine, according to the similarity between each news in the news set and the news to be recommended, a second candidate news related to the news to be recommended.
And the second candidate news is news related to the news event to be recommended.
In a possible implementation form of the embodiment of the present application, the first determining module 32 is specifically configured to:
and determining a target space to which the news to be recommended belongs by using an approximate nearest neighbor algorithm according to the bag-of-word vector corresponding to the news to be recommended.
In another possible implementation form of the embodiment of the present application, the sixth determining module 44 is specifically configured to:
and determining the news which has the maximum similarity with the news to be recommended and belongs to different spaces in the news set as each second candidate news.
It should be noted that the foregoing explanation on the embodiment of the news recommendation method is also applicable to the news recommendation apparatus of this embodiment, and details are not repeated here.
According to the news recommending device, after the news to be recommended is obtained, the target space to which the news to be recommended belongs is determined by using the preset space dividing method, and therefore the first alternative news related to the news to be recommended is determined according to the target space to which the news to be recommended belongs. Therefore, the first alternative news belonging to the same space with the news to be recommended is recommended to the user, the semantic correlation between the first alternative news and the news to be recommended is guaranteed, the recommendation result is more accurate, and the user experience is better.
Fig. 5 is a schematic structural diagram of a terminal device according to an embodiment of the present invention.
As shown in fig. 5, the terminal device includes:
a memory 51, a processor 52 and a computer program stored on the memory 51 and executable on the processor 52.
The processor 52, when executing the program, implements the news recommendation method provided in the above-described embodiment.
The terminal equipment can be a computer, a mobile phone, wearable equipment and the like.
Further, the terminal device further includes:
a communication interface 53 for communication between the memory 51 and the processor 52.
A memory 51 for storing a computer program operable on the processor 52.
The memory 51 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
And a processor 52, configured to implement the news recommendation method according to the foregoing embodiment when executing the program.
If the memory 51, the processor 52 and the communication interface 53 are implemented independently, the communication interface 53, the memory 51 and the processor 52 may be connected to each other through a bus and perform communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 5, but this does not mean only one bus or one type of bus.
Alternatively, in practical implementation, if the memory 51, the processor 52 and the communication interface 53 are integrated on one chip, the memory 51, the processor 52 and the communication interface 53 may complete communication with each other through an internal interface.
A fourth aspect embodiment of the present invention proposes a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a news recommendation method as in the preceding embodiments.
A fifth aspect embodiment of the present invention provides a computer program product, wherein when the instructions in the computer program product are executed by a processor, the news recommendation method in the foregoing embodiments is performed.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (8)
1. A news recommendation method, comprising:
acquiring news to be recommended;
determining a target space to which the news to be recommended belongs by using a preset space division method;
determining first alternative news related to the news to be recommended according to a target space to which the news to be recommended belongs;
after obtaining the news to be recommended, the method further includes:
determining the class to which the news to be recommended belongs according to the word frequency-reverse file frequency of the news to be recommended;
performing space division on news belonging to the same kind as the news to be recommended so as to divide the news belonging to the same topic but different events into different spaces, and determining a news set belonging to different spaces with the news to be recommended;
determining second alternative news related to the news to be recommended according to the similarity between each news in the news set and the news to be recommended, wherein the second alternative news has the largest similarity with the news to be recommended, belongs to the same class and belongs to different spaces;
before determining the target space to which the news to be recommended belongs, the method further includes:
determining a bag-of-words vector corresponding to the news to be recommended;
the determining the target space to which the news to be recommended belongs includes:
and determining a target space to which the news to be recommended belongs by using an approximate nearest neighbor algorithm according to the bag-of-word vector corresponding to the news to be recommended.
2. The method of claim 1, wherein the determining the first alternative news associated with the news to be recommended comprises:
determining similarity between each news in the target space and the news to be recommended;
and determining the first candidate news according to the similarity.
3. The method of claim 1, wherein the first candidate news is news semantically related to the news to be recommended, and the second candidate news is news related to the news event to be recommended.
4. A news recommender, comprising:
the acquisition module is used for acquiring news to be recommended;
the first determining module is used for determining a target space to which the news to be recommended belongs by using a preset space division method;
the second determining module is used for determining first alternative news related to the news to be recommended according to the target space to which the news to be recommended belongs;
wherein, still include:
the fourth determining module is used for determining the class to which the news to be recommended belongs according to the word frequency-reverse file frequency of the news to be recommended;
the fifth determining module is used for carrying out space division on the news which belong to the same type as the news to be recommended so as to divide the news which belong to the same topic but belong to different events into different spaces, and determining a news set which belongs to different spaces with the news to be recommended;
a sixth determining module, configured to determine, according to a similarity between each news in the news set and the news to be recommended, a second candidate news associated with the news to be recommended, where the second candidate news has a greatest similarity with the news to be recommended, belongs to the same class, and belongs to a different space;
wherein, still include:
the third determining module is used for determining a bag-of-words vector corresponding to the news to be recommended;
the first determining module is specifically configured to:
and determining a target space to which the news to be recommended belongs by using an approximate nearest neighbor algorithm according to the bag-of-word vector corresponding to the news to be recommended.
5. The apparatus of claim 4, wherein the second determining module is specifically configured to:
determining similarity between each news in the target space and the news to be recommended;
and determining the first candidate news according to the similarity.
6. The apparatus of claim 4, wherein the first candidate news is news semantically related to the news to be recommended, and the second candidate news is news related to the news event to be recommended.
7. A terminal device, comprising:
memory, processor and computer program stored on the memory and executable on the processor, characterized in that the processor implements the news recommendation method as claimed in any one of claims 1-3 when executing the program.
8. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a news recommendation method as claimed in any one of claims 1-3.
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 CN107748801A (en) | 2018-03-02 |
| CN107748801B true 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) |
Families Citing this family (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 |
| CN110245243B (en) * | 2019-06-20 | 2022-02-01 | 北京百度网讯科技有限公司 | News retrieval method and device, electronic equipment and 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 (5)
| 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 |
| 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 |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103793476B (en) * | 2014-01-08 | 2017-02-15 | 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 |
| US10977322B2 (en) * | 2015-11-09 | 2021-04-13 | WP Company, LLC | 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 (5)
| 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 |
| 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 |
| CN106294618A (en) * | 2016-08-01 | 2017-01-04 | 北京百度网讯科技有限公司 | Searching method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107748801A (en) | 2018-03-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108268617B (en) | User intention determining method and device | |
| US8463785B2 (en) | Method and system for generating search collection of query | |
| CN109657213B (en) | Text similarity detection method and device and electronic equipment | |
| CN107729578B (en) | Music recommendation method and device | |
| CN107748801B (en) | News recommendation method and device, terminal equipment and computer readable storage medium | |
| US20110202533A1 (en) | Dynamic Search Interaction | |
| CN109508391B (en) | Input prediction method and device based on knowledge graph and electronic equipment | |
| CN108491540B (en) | Text information pushing method and device and intelligent terminal | |
| CN108509479B (en) | Entity recommendation method and device, terminal and readable storage medium | |
| CN110704677B (en) | Program recommendation method and device, readable storage medium and terminal equipment | |
| CN107977445B (en) | Application program recommendation method and device | |
| CN103793439B (en) | A kind of real-time retrieval information acquisition method, device and server | |
| US20160357857A1 (en) | Apparatus, system and method for string disambiguation and entity ranking | |
| CN110275952A (en) | News recommended method, device and medium based on user's short-term interest | |
| CN111159563B (en) | Method, device, equipment and storage medium for determining user interest point information | |
| US20140236969A1 (en) | Apparatus and method for recommending contents based on metadata graph | |
| CN106294794A (en) | A kind of content recommendation method and device | |
| CN108536786A (en) | A kind of information recommendation method, device, server and storage medium | |
| JP2015106347A (en) | Recommendation device and recommendation method | |
| CN111241040B (en) | Information acquisition method and device, electronic equipment and computer storage medium | |
| CN106033417B (en) | Method and device for sequencing series of video search | |
| KR20170030434A (en) | Method and system for extracting sentences | |
| CN107656927B (en) | Feature selection method and device | |
| CN116226515B (en) | Search result ordering method and device, electronic equipment and storage medium | |
| CN112507229A (en) | Document recommendation method and system and computer equipment |
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 |