CN109558531A - News information method for pushing, device and computer equipment - Google Patents
News information method for pushing, device and computer equipment Download PDFInfo
- Publication number
- CN109558531A CN109558531A CN201811257177.4A CN201811257177A CN109558531A CN 109558531 A CN109558531 A CN 109558531A CN 201811257177 A CN201811257177 A CN 201811257177A CN 109558531 A CN109558531 A CN 109558531A
- Authority
- CN
- China
- Prior art keywords
- news information
- news
- information
- processed
- pushed
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention provides a kind of news information method for pushing, device and computer equipments, the present invention relates to field of artificial intelligence, if news information method for pushing includes: to receive news information to check instruction, news information to be processed is obtained from news providers, and obtains targeted news information from news information to be processed;Preview and semantics recognition are carried out to the heading message of targeted news information, obtain corresponding first semantic feature of heading message;Preview and semantics recognition are carried out to the content information of targeted news information, obtain corresponding second semantic feature of content information;It compares the first semantic feature and the second semantic feature to obtain similarity value, similarity value in targeted news information is greater than or equal to the news information of the first preset threshold as news information to be pushed;It treats push news information to classify, push news information is treated according to the classification information that classification obtains and is pushed.
Description
[technical field]
The present invention relates to field of artificial intelligence more particularly to a kind of news information method for pushing, device and calculating
Machine equipment.
[background technique]
News is to understand a main path of internal and international practical work.From the browsing of more original newspaper, magazine, arrive
The internet of modernization, the news browsing of mobile Internet and news push, news still carry the current generation practical work of description
Task.With PC and news push server, such as the universal and various news category client of mobile phone and tablet computer etc.
The appearance of application software (APP), news portal are held, the method for browsing news can be described as diversified.
But the news information of existing news category APP push mode is to be checked record information to push away according to the history of user
Relevant news information is sent, the type of the news information of push is not abundant enough.
[summary of the invention]
In view of this, being used the embodiment of the invention provides a kind of news information method for pushing, device and computer equipment
To solve the problems, such as how to enrich the type of the news information of push.
In a first aspect, the embodiment of the invention provides a kind of news information method for pushing, the news information method for pushing
Include:
If receiving news information checks instruction, obtain news information to be processed from news providers, and from it is described to
It handles and obtains targeted news information in news information;
Preview and semantics recognition are carried out to the heading message of the targeted news information, it is corresponding to obtain the heading message
First semantic feature;
Preview and semantics recognition are carried out to the content information of the targeted news information, it is corresponding to obtain the content information
Second semantic feature;
It compares first semantic feature and second semantic feature to obtain similarity value, the target is new
It hears similarity value in information and is greater than or equal to the news information of the second preset threshold as the news information to be pushed;
Classify to the news information to be pushed, the classification information obtained according to classification believes the news to be pushed
Breath is pushed.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, if described connect
It receives news information and checks instruction, include: from the step of news providers acquisition news information to be processed
If receiving the news information checks instruction, the mark that currently can provide the news providers of news information is obtained
Know information;
Based on the identification information, the news information to be processed is obtained from corresponding news providers.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, it is described from correspondence
News providers obtain news information to be processed the step of include:
The first time when news information checks instruction is once received before obtaining;
Obtain the second time being currently received when the news information checks instruction;
The first time and second time are in from the corresponding news providers acquisition news information generation time
Between news information, and the news information that will acquire is as the news information to be processed.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, described from institute
Stating the step of targeted news information is obtained in news information to be processed includes:
It is corresponding by amount of reading to obtain the news information to be processed, and will be read in the news information to be processed
Reading amount is greater than the news information of the first preset threshold as targeted news information.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, it is described to described
News information to be pushed is classified, the step pushed according to the classification information that classification obtains to the news information to be pushed
Suddenly include:
The attribute-bit for obtaining the news information to be pushed, is classified based on the attribute-bit, obtains inhomogeneity
Not corresponding news information quantity;
The obtained classification that will classify and corresponding news information quantity of all categories are associated, with news information list
Form the news information to be pushed is pushed.
The aspect and any possible implementation manners as described above, it is further provided a kind of implementation, it is described to classify
Obtained classification and corresponding news information quantity of all categories is associated, and forms news information list, and to described
After the step of news information list is pushed, the method also includes:
If receiving the selection instruction of input, selected classification is determined according to the selection instruction, and by the institute
News information associated by the classification of selection is shown.
A technical solution in above-mentioned technical proposal has the following beneficial effects:
In the embodiment of the present invention, when carrying out the push of news information, obtains correspond to from corresponding news providers first
News information to be processed, and targeted news information is obtained from news information to be processed, then to obtained targeted news
The heading message and content information that information is included carry out preview and semantics recognition, respectively obtain corresponding first semantic feature
And second semantic feature, and then the first semantic feature and the second semantic feature are subjected to similarity comparison, by targeted news
The news information that similarity value is greater than the first preset threshold in information is used as news information to be pushed, and finally treats push news letter
Breath carries out statistic of classification, treats push news information according to obtained classification information and is pushed.It realizes and is carrying out news letter
When the push of breath, the rich of news information ensure that, effectively eliminate title party news information.
Second aspect, the embodiment of the invention provides a kind of news information driving means, the news information driving means
Include:
Module is obtained, if checking instruction for receiving news information, obtains news letter to be processed from news providers
Breath, and targeted news information is obtained from the news information to be processed;
First identification module carries out preview and semantics recognition for the heading message to the targeted news information, obtains
Corresponding first semantic feature of the heading message;
Second identification module carries out preview and semantics recognition for the content information to the targeted news information, obtains
Corresponding second semantic feature of the content information;
Comparing calculation module, it is similar for comparing to obtain first semantic feature to second semantic feature
Angle value, using similarity value in the targeted news information be greater than or equal to the first preset threshold news information as described in wait push away
Send news information;
Pushing module, for classifying to the news information to be pushed, the classification information obtained according to classification is to institute
News information to be pushed is stated to be pushed.
The third aspect the embodiment of the invention provides a kind of computer equipment, including memory, processor and is stored in
In the memory and the computer program that can run on the processor, when the processor executes the computer program
Realize news information method for pushing as described in relation to the first aspect.
Fourth aspect, the embodiment of the invention provides a kind of computer readable storage mediums, comprising: computer is executable to be referred to
It enables, when the computer executable instructions are run to execute news information method for pushing as described in relation to the first aspect.
A technical solution in above-mentioned technical proposal has the following beneficial effects:
In the embodiment of the present invention, when carrying out the push of news information, obtains correspond to from corresponding news providers first
News information to be processed, and targeted news information is obtained from news information to be processed, then to obtained targeted news
The heading message and content information that information is included carry out preview and semantics recognition, respectively obtain corresponding first semantic feature
And second semantic feature, and then the first semantic feature and the second semantic feature are subjected to similarity comparison, by targeted news
The news information that similarity value is greater than the first preset threshold in information is used as news information to be pushed, and finally treats push news letter
Breath carries out statistic of classification, treats push news information according to obtained classification information and is pushed.It realizes and is carrying out news letter
When the push of breath, the rich of news information ensure that, effectively eliminate title party news information.
[Detailed description of the invention]
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for this field
For those of ordinary skill, without any creative labor, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is a kind of flow chart of optional news information method for pushing provided by the embodiment of the present invention;
Fig. 2 is a kind of schematic diagram of optional news information driving means provided by the embodiment of the present invention;
Fig. 3 is a kind of functional block diagram of optional computer equipment provided by the embodiment of the present invention.
[specific embodiment]
For a better understanding of the technical solution of the present invention, being retouched in detail to the embodiment of the present invention with reference to the accompanying drawing
It states.
It will be appreciated that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Base
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts it is all its
Its embodiment, shall fall within the protection scope of the present invention.
The term used in embodiments of the present invention is only to be not intended to be limiting merely for for the purpose of describing particular embodiments
The present invention.In the embodiment of the present invention and the "an" of singular used in the attached claims, " described " and "the"
It is also intended to including most forms, unless the context clearly indicates other meaning.
It should be appreciated that term "and/or" used herein is only a kind of incidence relation for describing affiliated partner, indicate
There may be three kinds of relationships, for example, A and/or B, can indicate: individualism A, exist simultaneously A and B, individualism B these three
Situation.In addition, character "/" herein, typicallys represent the relationship that forward-backward correlation object is a kind of "or".
Depending on context, word as used in this " if " can be construed to " ... when " or " when ...
When " or " in response to determination " or " in response to detection ".Similarly, depend on context, phrase " if it is determined that " or " if detection
(condition or event of statement) " can be construed to " when determining " or " in response to determination " or " when the detection (condition of statement
Or event) when " or " in response to detection (condition or event of statement) ".
It is not enough enriched for the push of news information in the prior art and checks that the problem of mode complexity, the embodiment of the present invention mention
A kind of news information method for pushing has been supplied, has obtained corresponding news information to be processed from corresponding news providers first, then
Preview and semantics recognition are carried out to obtained news information to be processed, to be screened to obtain wait push away to news information to be processed
News information is sent, push news information is finally treated and carries out statistic of classification, push news letter is treated according to obtained classification information
Breath is pushed.It realizes when carrying out the push of news information, ensure that the rich of news information, while by news
Information carries out sifting sort, facilitates user that can more fast and accurately look into the news information for oneself wanting to check
It sees.
In one embodiment, as shown in Figure 1, providing a kind of news information method for pushing, method includes the following steps:
S102 obtains news information to be processed from news providers if receiving news information checks instruction, and to
It handles and obtains targeted news information in news information.
Wherein, news information checks that instruction refers to that triggering carries out the command information of news information acquisition, can be user's
Command information caused by news information refresh operation, be also possible to carry out news when checking this application program or terminal it is initial
Starting.News providers, which refer to, provides the medium of news information, for example, carry out the various application programs checked of news information or
Website.
Specifically, when receiving news information and checking instruction, corresponding news letter is obtained from corresponding news providers
Breath, and using acquired news information as news information to be processed, it is new that target is then obtained from news information to be processed
Hear information.In practical applications, user usually uses terminal and carries out checking for news information, or using accordingly using journey
Sequence carries out checking for news information, is illustrated for convenience, carries out news information using terminal as user in the present embodiment
The main body checked.
In the present embodiment, it needs to carry out when checking of news information in user, news letter is issued by corresponding operation
Breath checks instruction, and terminal is when receiving news information and checking instruction, from the news providers that can carry out news information acquisition
Obtain corresponding news information, and using acquired news information as news information to be processed, so can according to obtain to
The news information that processing news information is finally pushed.
S104 carries out preview and semantics recognition to the heading message of targeted news information, obtains heading message corresponding the
One semantic feature.
Wherein, the first semantic feature is the characteristic information of heading message, by carrying out preview and semantic knowledge to heading message
Not to obtain the characteristic information of heading message.
Specifically, after obtaining targeted news information, preview is carried out to heading message corresponding to targeted news information
And semantics recognition, to obtain the first semantic feature corresponding to heading message.
Semantics recognition is to be interpreted by the content for being included to text information, and simplest is also to be easiest to expect
Semantics recognition is Segmentation Algorithm, i.e. maximum matching method, since heading message is usually in short to state, to target
When the heading message of information carries out semantics recognition, Segmentation Algorithm can be used, the content of heading message is identified.This
Algorithm is that the reading habit based on people obtains corresponding recognition result, and people is also word for word to read in from left to right when reading, because
This maximum matching method is consistent with the habit of people.
When carrying out semantics recognition to heading message, there are also being exactly that heading message is carried out word segmentation processing, then basis is divided
The quantity of word determines more correctly participle mode, and then the accurate meaning of determining heading message.Specifically, for a kind of participle
Scheme, how many word of the inside just penalize how many points, as soon as and every occur adding not at the individual character of word and penalizing one point, for different
For participle scheme, best participle scheme, that is, the least scheme of point penalty.And then it reads corresponding to best point this scheme
Meaning information, as the first semantic feature corresponding to heading message.
S106 carries out preview and semantics recognition to the content information of targeted news information, obtains content information corresponding the
Two semantic features.
Wherein, the second semantic feature is the characteristic information of content information, by carrying out preview and semantic knowledge to content information
Not to obtain the characteristic information of content information.
Specifically, after obtaining targeted news information, preview is carried out to content information corresponding to targeted news information
And semantics recognition, to obtain the second semantic feature corresponding to content information.
When the content information to targeted news information carries out preview and semantics recognition, wrapped by obtaining in content information
The frequency of occurrence contained reaches the word of certain number, then carries out sentence recombination according to each word, obtains corresponding to content information
The second semantic feature.When carrying out word acquisition, not all word all has the qualification recombinated as sentence, leads to
In normal situation, only can just will do it acquisition, such as name, place name and movement title etc. to specific word has particular meaning
Word, carry out the recombination of sentence, to obtained word then to obtain summary sentence corresponding to content information, and then basis
Obtained summary sentence obtains corresponding second semantic feature.
S108 compares the first semantic feature and the second semantic feature to obtain similarity value, obtains targeted news letter
The news information that similarity value is greater than or equal to the second preset threshold in breath is used as news information to be pushed.
Specifically, when carrying out preview and semantics recognition to targeted news information, respectively to the heading message of news information
Preview is carried out with content information and carries out semantics recognition, respectively obtains corresponding first semantic feature of heading message and content letter
Corresponding second semantic feature is ceased, the first semantic feature and the second semantic feature are then subjected to similarity comparison, obtains target
The news that the similarity of the first semantic feature and the second semantic feature is more than or equal to the second preset threshold in news information is believed
Breath is used as news information to be pushed.
In practical applications, the case where not being consistent due to the title there are news information with content information, as " title
Party " news information, therefore after obtaining targeted news information, it needs effectively to be filtered " title party " news information, because
This needs to carry out preview and semantics recognition respectively to the heading message and content information of news information, corresponding to obtain heading message
The first semantic feature and corresponding second semantic feature of content information, then utilize calculating formula of similarity, by the first language
Adopted feature and the second semantic feature export the similarity value of the two as input, last according to the judgement of obtained similarity value
Whether this news information is " title party " news information.
It should be noted that there are many calculations of similarity value, common calculation include Euclidean distance,
Manhatton distance, Minkowski distance, cosine similarity, Jaccard Similarity and Pearson correlation coefficients.?
In the embodiment of the present invention, corresponding character array can be converted by the first semantic feature and the second semantic feature, it is then sharp
Similarity between the two is determined with character array.For example, the character array that the first semantic feature converts is
0111011000111001101001011, the character array that the second semantic feature converts is
0101011100110101101001010, corresponding similarity value is then calculated, as example, similarity value at this time
For 21/25=84%, finally it is compared to obtained similarity value and preset threshold to judge whether it is " title party " news
Information.
Specifically, when obtaining news information to be processed from corresponding news providers, to news information institute to be processed
The news information content for including carries out preview and semantics recognition, then screens to news information to be processed, to obtain wait push away
Send news information.
After completing to the acquisition of news information, need to handle acquired news information to be processed, in reality
In the application of border, not all news information is all user or the required news information of public personnel, it is therefore desirable to right
News information is screened, therefore carrying out screening is to obtain the news information for meeting user's public demand and user demand.It is right
In news information, usually there is such problems, for example, news information check demand is low, news information content it is not true with
And there is any discrepancy with content information for news information title, for the problem whether news information is true, needs to carry out news information
The staff of audit carries out judgement determination, but for screening out that news information demand is low and title is not consistent with content
News information can be screened by preview to news information and semantics recognition to realize.Therefore, obtain it is to be processed
When news information, by performing corresponding processing to news information to be processed, for example preview and semantics recognition, screening are obtained more
Add the news information for meeting public demand.
S110 treats push news information and classifies, treats push news according to the classification information classified
Information is pushed.
Specifically, it is obtaining when pushing news information, is treating push news information and carry out classification processing, to obtain difference
News information classification, and then different classifications is associated with corresponding news information, to carry out news information to be pushed
Push.
News information caused by daily is various, and generic is also various.It is right for different users
The demand of different classes of news information is different, for example, can may more pay close attention to sport category for the people for liking movement
News information can may more pay close attention to current events class news information for the elderly, may more can for young star-pursuing family
Class news information is entertained when concern.When direct major general's news information carries out push display, due to being specifically displayed without rule
Property, that is, various different classes of news informations intersect display so that user is carrying out when checking of news information, need into
Row searches oneself required news information when being just capable of determining whether, therefore is obtaining when pushing news information, treats push
News information carries out classification processing, to obtain different classifications, and then shows the news letter of corresponding classification according to different needs
Breath.
According to above-mentioned news information method for pushing, when carrying out the push of news information, provided first from corresponding news
Quotient obtains corresponding news information to be processed, then carries out preview and semantics recognition to obtained news information to be processed, with
News information to be processed is screened to obtain news information to be pushed, push news information is finally treated and carries out statistic of classification,
Push news information is treated according to obtained classification information to be pushed.It realizes when carrying out the push of news information, guarantees
The type of the news information of push it is rich, while by carrying out sifting sort to news information, facilitate the user can be more
Add and fast and accurately the news information for oneself wanting to check is checked.
In one embodiment, if receiving news information checks instruction, news to be processed is obtained from news providers
Information, comprising the following steps:
S202 obtains the news offer that can currently carry out news information acquisition if receiving news information checks instruction
Quotient's information.
S204 is based on news providers information, obtains news information to be processed from corresponding news providers.
Specifically, when receiving news information and checking instruction, the news of news information acquisition can currently be carried out by, which obtaining, is mentioned
For quotient's information, news to be processed is then obtained from corresponding news information provider according to determining news information provider information
Information.
In practical applications, the news providers that can carry out news information acquisition can be variation, with specific reference to user
Use demand determine.For showing the news providers for existing and carrying out news information report, different news providers institutes
The news information mainly reported be also it is different, than if any news providers be more concerned with the report of topical news, have
News providers more focus on the reports of sports news or entertainment news, therefore carrying out news information acquisition, Ke Yixuan
The current news providers for carrying out news information acquisition of the selection of selecting property.
Optionally, when obtaining corresponding news information from each news providers, due to eventually believing each news
Breath carries out classification processing, therefore when carrying out the acquisition of news information, can be according to the classification of news information from specific news
The acquisition of news information is carried out in provider, for example, A class news information is on a news providers when being obtained, it can be more
It is comprehensive to obtain A class news information, then can directly be carried out on a news providers when carrying out the acquisition of news information
It obtains, it is ensured that the acquisition of news information has specific aim, so that the acquisition of news information is more accurate and reliable.Meanwhile
When carrying out the acquisition of news information in this manner, directly the division that obtained news information carries out classification can be handled,
Avoid the processing of secondary classification bring secondary data.
In one embodiment, include: from the step of corresponding news providers acquisition news information to be processed
Step S302 once receives first time when news information checks instruction, and obtains and currently connect before obtaining
Receive the second time when news information checks instruction.
Step S304 obtains news information from corresponding news providers and generates the time in first time and the second time
Between news information, and using news information as news information to be processed.
Specifically, when obtaining news information to be processed from corresponding news providers, it is first determined news to be processed
Therefore the time segment information of acquisition of information once receives the first time that news information checks instruction before acquisition is adjacent, and
Acquisition is currently received the second time that news information checks instruction, will then when obtaining news information on news providers
News information generates the time in the news information at the first time between the second time as news information to be processed.
In practical applications, when carrying out the acquisition of news information, in order to guarantee the timeliness of news information and not weigh
Renaturation carries out the setting of period according to the historical time information that user's news information is checked, will use when news information is obtained
The news information that family had been checked is filtered.A preceding user is obtained at this time carries out the first time that news information is checked,
Specially user passes through the temporal information that operation triggering terminal carries out news information push, then from each news providers
When carrying out the acquisition acquisition of news information, only the acquisition news information generation time is in new between first time and current time
Information is heard, the repetition push of news information can be effectively avoided in this way.
In one embodiment, preview and semantics recognition are carried out to news information to be processed, screening obtains news to be pushed
Information, comprising: it is corresponding by amount of reading to obtain news information to be processed, and screens in news information to be processed by amount of reading
Greater than the first preset threshold news information as targeted news information.
Wherein, number which is read by other users is referred to by amount of reading information.
Specifically, in the news information to be processed obtained from news providers, preview and semantic knowledge are not carried out directly
Not, but first obtain then news information to be processed is corresponding to be screened by amount of reading, it will be in news information to be processed
News information to be processed by amount of reading less than the first preset threshold is filtered deletion, to obtain being greater than or being waited by amount of reading
In the news information to be processed of the first preset threshold, and using the news to be processed obtained at this time as targeted news information, finally
Preview and semantics recognition are carried out to targeted news information again, to obtain news information to be pushed.Wherein, the tool of the first preset threshold
Body set-up mode is unlimited, and other than the value of default, user can be with self-setting.
In actual application process, when carrying out the acquisition of news information within a certain period of time, acquired news letter
Breath will be thousands of, but not all news information is therefore, to carry out news information required for user
Screening when, the foundation that news information to be processed can be screened, while being screened according to the amount of reading of news information
Processing except amount of reading, can also be included comment amount and hot value etc..For news information to be processed, if a certain item is new
When hearing the amount of reading of information less than preset threshold, will not directly it be sieved using this news information as news information to be pushed
Choosing filters out, and can just be used as targeted news only for the news information to be processed for being more than or equal to preset threshold by amount of reading
Information, and carry out preview and semantics recognition processing.It can effectively avoid the data volume of news information excessive in this way and cause to ring
Slow problem is answered, and then improves the speed of response.
In one embodiment, it treats push news information to classify, and is treated according to the classification information that classification obtains
Pushing the step of news information is pushed includes:
Step S502 is obtained the attribute-bit of news information to be pushed, is classified based on attribute-bit, obtains inhomogeneity
Not corresponding news information quantity;
Step S504, the obtained classification that will classify and corresponding news information quantity are associated, and form news information column
Table is treated push news information and is pushed.
Wherein, attribute-bit is classification information belonging to news information, and attribute expression can be text, be also possible to number
Or number etc..Under normal conditions, when carrying out editor's push to news information, corresponding category can be configured to news information
Property mark, and have corresponding incidence relation with corresponding news information, when obtaining news information, corresponding attribute-bit
It will be read, using as the standard classified.News information list is to treat push news information to be counted to obtain
List, specifically can be as shown in table 1 below, but be not limited to the classification that only table 1 is included.
Table 1
Serial number | Classification | Quantity |
1 | Sport | 12 |
2 | Amusement | 7 |
3 | Finance and economics | 5 |
4 | It is military | 6 |
Specifically, it is obtaining when pushing news information, the attribute-bit of information to be pushed is being identified, then basis
The corresponding attribute-bit of news information to be pushed is classified, the classification and corresponding news information quantity that classification is obtained
It is associated, to form news information list as listed in Table 1, and then treats push news information and pushed.
In practical applications, different news informations has different classification informations, treats push news information and is divided
Class processing more intuitive can know the number of the different classes of news information for having that in current acquired information
Amount.
Optionally, after forming news information list and treating the step of push news information is pushed further include:
If receiving the selection instruction of input, determine selected classification, and by news information associated by classification into
Row display.
Specifically, after treating push news information and being classified, user selects respective classes according to the demand of itself
News information checked, after user has determined selected classification, by news information corresponding to this classification carry out
Display.
Optionally, in news information check interface when, that is, user had been selected it is required check it is new
When hearing the classification of information, when carrying out the refreshing of news information again, it can obtain after pushing news information at this time, directly
The selected news information of user is shown on interface, that is, no longer Display Category information allows user to carry out classification letter at this time
The selection of breath, but directly such other news information is obtained and pushed.Meanwhile in news information Flushing success,
One virtual key of display can be generated on chivalrous display interface, user can re-start news by clicking this virtual key
The selection of information category.
Embodiment two
Based on news information method for pushing provided by embodiment one, the embodiment of the present invention, which further provides, realizes above-mentioned side
The Installation practice of each step and method in method embodiment.
In a first aspect, the embodiment of the invention also provides a kind of news information driving means, with reference to Fig. 2, the news information
Driving means 600 includes:
Module 61 is obtained, if checking instruction for receiving news information, obtains news to be processed from news providers
Information, and targeted news information is obtained from news information to be processed;
First identification module 62 carries out preview and semantics recognition for the heading message to targeted news information, is marked
Inscribe corresponding first semantic feature of information;
Second identification module 63 carries out preview and semantics recognition for the content information to targeted news information, obtains interior
Hold corresponding second semantic feature of information;
Comparing calculation module 64, for comparing the first semantic feature and the second semantic feature to obtain similarity value,
Similarity value in targeted news information is greater than or equal to the news information of the first preset threshold as news information to be pushed;
Pushing module 65 classifies for treating push news information, is treated and pushed away according to the classification information that classification obtains
News information is sent to be pushed.
Second aspect, the embodiment of the invention also provides a kind of computer equipments.Referring to FIG. 3, the computer equipment 700
Include: memory 71, processor 72 and is stored in the calculating that can be run in the memory 71 and on the processor 72
Machine program, the processor 72 realize that the described in any item news informations of embodiment one such as push when executing the computer program
Method.
As each unit in this present embodiment be able to carry out it is above-mentioned shown in news information method for pushing, the present embodiment is detailed
The part carefully described can refer to the related description to news information method for pushing part described in embodiment one.
At least one technical solution provided by the embodiment of the present invention has the advantages that
In the embodiment of the present invention, when carrying out the push of news information, obtains correspond to from corresponding news providers first
News information to be processed, preview and semantics recognition then are carried out to obtained news information to be processed, to be processed new
It hears information to be screened to obtain news information to be pushed, finally treats push news information and carry out statistic of classification, according to what is obtained
Classification information is treated push news information and is pushed.It realizes when carrying out the push of news information, ensure that news information
It is rich, while by news information carry out sifting sort, facilitate user that can more fast and accurately be thought oneself
The news information to be checked is checked.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided by the present invention, it should be understood that disclosed system, device and method can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only a kind of logical function partition, there may be another division manner in actual implementation, for example, multiple units or group
Part can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown
Or the mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, device or unit it is indirect
Coupling or communication connection can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of hardware adds SFU software functional unit.
The above-mentioned integrated unit being realized in the form of SFU software functional unit can store and computer-readable deposit at one
In storage media.Above-mentioned SFU software functional unit is stored in a storage medium, including some instructions are used so that a computer
It is each that device (can be personal computer, server or network equipment etc.) or processor (Processor) execute the present invention
The part steps of embodiment the method.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (Read-
Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic or disk etc. it is various
It can store the medium of program code.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Within mind and principle, any modification, equivalent substitution, improvement and etc. done be should be included within the scope of the present invention.
Claims (9)
1. a kind of news information method for pushing, which is characterized in that the news information method for pushing includes:
If receiving news information checks instruction, news information to be processed is obtained from news providers, and from described to be processed
Targeted news information is obtained in news information;
Preview and semantics recognition are carried out to the heading message of the targeted news information, obtain the heading message corresponding first
Semantic feature;
Preview and semantics recognition are carried out to the content information of the targeted news information, obtain the content information corresponding second
Semantic feature;
It compares first semantic feature and second semantic feature to obtain similarity value, the targeted news is believed
Similarity value is greater than or equal to the news information of the first preset threshold as the news information to be pushed in breath;
Classify to the news information to be pushed, according to the obtained classification information of classification to the news information to be pushed into
Row push.
2. news information method for pushing according to claim 1, which is characterized in that if the news information that receives is looked into
It sees instruction, obtains news information to be processed from news providers, comprising:
If receiving the news information checks instruction, the mark letter that currently can provide the news providers of news information is obtained
Breath;
Based on the identification information, the news information to be processed is obtained from corresponding news providers.
3. news information method for pushing according to claim 2, which is characterized in that described to be obtained from corresponding news providers
Take the news information to be processed, comprising:
The first time when news information checks instruction is once received before obtaining;
Obtain the second time being currently received when the news information checks instruction;
It is between the first time and second time from the corresponding news providers acquisition news information generation time
News information, and the news information that will acquire is as the news information to be processed.
4. news information method for pushing according to claim 1, which is characterized in that described from the news information to be processed
Middle acquisition targeted news information, comprising:
It is corresponding by amount of reading to obtain the news information to be processed, and by the news information to be processed by amount of reading
Greater than the second preset threshold news information as targeted news information.
5. news information method for pushing according to claim 4, which is characterized in that described to the news information to be pushed
Classify, the news information to be pushed pushed according to the classification information that classification obtains, comprising:
The attribute-bit for obtaining the news information to be pushed, is classified, it is different classes of right to obtain based on the attribute-bit
The news information quantity answered;
The obtained classification that will classify and corresponding news information quantity of all categories are associated, with the shape of news information list
Formula pushes the news information to be pushed.
6. news information method for pushing according to any one of claims 1-5, which is characterized in that described to obtain classification
Classification and corresponding news information quantity of all categories be associated, to described wait push in the form of news information list
After news information is pushed, the method also includes:
If receiving the selection instruction of input, selected classification is determined according to the selection instruction, and will be described selected
Classification associated by news information shown.
7. a kind of news information driving means, which is characterized in that the news information driving means includes:
Module is obtained, if checking instruction for receiving news information, obtains news information to be processed from news providers, and
Targeted news information is obtained from the news information to be processed;
First identification module carries out preview and semantics recognition for the heading message to the targeted news information, obtains described
Corresponding first semantic feature of heading message;
Second identification module carries out preview and semantics recognition for the content information to the targeted news information, obtains described
Corresponding second semantic feature of content information;
Comparing calculation module, for comparing first semantic feature and second semantic feature to obtain similarity
Value, using similarity value in the targeted news information be greater than or equal to the first preset threshold news information as described in wait push
News information;
Pushing module, for classifying to the news information to be pushed, according to the obtained classification information of classification to it is described to
Push news information is pushed.
8. a kind of computer equipment, including memory, processor and storage are in the memory and can be in the processor
The computer program of upper operation, which is characterized in that the processor realized when executing the computer program as claim 1 to
6 described in any item news information method for pushing.
9. a kind of computer readable storage medium, including memory, processor and storage are in the memory and can be in institute
State the computer program run on processor, which is characterized in that the processor is realized when executing the computer program as weighed
Benefit requires 1 to 6 described in any item news information method for pushing.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811257177.4A CN109558531A (en) | 2018-10-26 | 2018-10-26 | News information method for pushing, device and computer equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811257177.4A CN109558531A (en) | 2018-10-26 | 2018-10-26 | News information method for pushing, device and computer equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109558531A true CN109558531A (en) | 2019-04-02 |
Family
ID=65865318
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811257177.4A Pending CN109558531A (en) | 2018-10-26 | 2018-10-26 | News information method for pushing, device and computer equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109558531A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112153424A (en) * | 2020-09-23 | 2020-12-29 | 腾讯科技(深圳)有限公司 | Content pushing method and device, electronic equipment and storage medium |
CN113794625A (en) * | 2021-09-10 | 2021-12-14 | 泰康保险集团股份有限公司 | Interrogation system, method, equipment and medium |
CN114500680A (en) * | 2022-04-19 | 2022-05-13 | 创思(广州)电子科技有限公司 | Multi-channel intersection data classification type information transmission algorithm |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104657496A (en) * | 2015-03-09 | 2015-05-27 | 杭州朗和科技有限公司 | Method and equipment for calculating information hot value |
CN105095368A (en) * | 2015-06-29 | 2015-11-25 | 北京金山安全软件有限公司 | Method and device for sequencing news information |
CN108304379A (en) * | 2018-01-15 | 2018-07-20 | 腾讯科技(深圳)有限公司 | A kind of article recognition methods, device and storage medium |
CN108509417A (en) * | 2018-03-20 | 2018-09-07 | 腾讯科技(深圳)有限公司 | Title generation method and equipment, storage medium, server |
-
2018
- 2018-10-26 CN CN201811257177.4A patent/CN109558531A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104657496A (en) * | 2015-03-09 | 2015-05-27 | 杭州朗和科技有限公司 | Method and equipment for calculating information hot value |
CN105095368A (en) * | 2015-06-29 | 2015-11-25 | 北京金山安全软件有限公司 | Method and device for sequencing news information |
CN108304379A (en) * | 2018-01-15 | 2018-07-20 | 腾讯科技(深圳)有限公司 | A kind of article recognition methods, device and storage medium |
CN108509417A (en) * | 2018-03-20 | 2018-09-07 | 腾讯科技(深圳)有限公司 | Title generation method and equipment, storage medium, server |
Non-Patent Citations (2)
Title |
---|
王志超,翁楠,王宇: ""基于主题句相似度的标题党新闻鉴别技术研究"", 现代图书情报技术, no. 212, pages 48 - 52 * |
王志超,翁楠,王宇: "基于主题句相似度的标题党新闻鉴别技术研究", pages 48 - 52 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112153424A (en) * | 2020-09-23 | 2020-12-29 | 腾讯科技(深圳)有限公司 | Content pushing method and device, electronic equipment and storage medium |
CN112153424B (en) * | 2020-09-23 | 2024-01-26 | 腾讯科技(深圳)有限公司 | Content pushing method, device, electronic equipment and storage medium |
CN113794625A (en) * | 2021-09-10 | 2021-12-14 | 泰康保险集团股份有限公司 | Interrogation system, method, equipment and medium |
CN114500680A (en) * | 2022-04-19 | 2022-05-13 | 创思(广州)电子科技有限公司 | Multi-channel intersection data classification type information transmission algorithm |
CN114500680B (en) * | 2022-04-19 | 2022-09-13 | 创思(广州)电子科技有限公司 | Multi-channel intersection data classification type information transmission method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11194965B2 (en) | Keyword extraction method and apparatus, storage medium, and electronic apparatus | |
CN107797984B (en) | Intelligent interaction method, equipment and storage medium | |
US9449271B2 (en) | Classifying resources using a deep network | |
CN109299271B (en) | Training sample generation method, text data method, public opinion event classification method and related equipment | |
US11176453B2 (en) | System and method for detangling of interleaved conversations in communication platforms | |
CN110909182B (en) | Multimedia resource searching method, device, computer equipment and storage medium | |
CN104899306B (en) | Information processing method, information display method and device | |
CA2984904A1 (en) | Social media events detection and verification | |
CN101256591A (en) | Principles and methods for personalizing newsfeeds via an analysis of information novelty and dynamics | |
CN107071554B (en) | Method for recognizing semantics and device | |
JP6776310B2 (en) | User-Real-time feedback information provision methods and systems associated with input content | |
CN108133058B (en) | Video retrieval method | |
CN109558531A (en) | News information method for pushing, device and computer equipment | |
CN113569037A (en) | Message processing method and device and readable storage medium | |
CN110175264A (en) | Construction method, server and the computer readable storage medium of video user portrait | |
CN107977678A (en) | Method and apparatus for output information | |
KR20140119269A (en) | Apparatus and system for detecting complex issues based on social media analysis and method thereof | |
CN108984514A (en) | Acquisition methods and device, storage medium, the processor of word | |
CN105045882B (en) | A kind of hot word processing method and processing device | |
CN110765348A (en) | Hot word recommendation method and device, electronic equipment and storage medium | |
CN109933709B (en) | Public opinion tracking method and device for video text combined data and computer equipment | |
CN109660621A (en) | A kind of content delivery method and service equipment | |
CN113573128A (en) | Audio processing method, device, terminal and storage medium | |
US11206236B2 (en) | Systems and methods to prioritize chat rooms using machine learning | |
CN110674632A (en) | Method and device for determining security level, storage medium and 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 |