CN107748802A - Polymerizable clc method and device - Google Patents
Polymerizable clc method and device Download PDFInfo
- Publication number
- CN107748802A CN107748802A CN201711145235.XA CN201711145235A CN107748802A CN 107748802 A CN107748802 A CN 107748802A CN 201711145235 A CN201711145235 A CN 201711145235A CN 107748802 A CN107748802 A CN 107748802A
- Authority
- CN
- China
- Prior art keywords
- interest
- news data
- point
- focus point
- focus
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/34—Browsing; Visualisation therefor
- G06F16/345—Summarisation for human users
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention proposes a kind of polymerizable clc method and device, and wherein method includes:Obtain search daily record;According to the temperature information of search term in search daily record, the focus point of interest in search term is obtained;Obtain a plurality of news data for meeting preparatory condition;News data is labeled according to focus point of interest, determines the assessment fraction of focus point of interest included in news data and focus point of interest;For each focus point of interest, acquisition includes focus point of interest, and including the assessment fraction of focus point of interest meet at least one news data of preset fraction threshold value, according at least one news data, generation hot news polymerization article corresponding with focus point of interest, so as to get comprehensive focus point of interest, and it is directed to each focus point of interest, can be according to the hot news generation hot news polymerization article very high with focus point of interest correlation, efficiency high and accuracy rate height, and need not manually participate in, reduce polymerizable clc cost.
Description
Technical field
The present invention relates to Internet technical field, more particularly to a kind of polymerizable clc method and device.
Background technology
At present, the information on internet is in the growth of explosion type, around the tendency application and production of internet data expansion
Product just constantly attract attention, such as hot news polymerization article.In the prior art, generate hot news polymerization article when, be by
Editor person picks out hot news from the news data of magnanimity, obtains the summary info in hot news, and editor obtains focus
News Aggreagation article, wastes time and energy, and obtain hot news polymerization article covering focus point of interest it is not comprehensive, efficiency it is low and
Accuracy rate is low.
The content of the invention
It is contemplated that at least solves one of technical problem in correlation technique to a certain extent.
Therefore, first purpose of the present invention is to propose a kind of polymerizable clc method, it is hot in the prior art for solving
Put the problem of news Aggreagation article formation efficiency is low and accuracy rate is low.
Second object of the present invention is to propose a kind of polymerizable clc device.
Third object of the present invention is to propose another polymerizable clc device.
Fourth object of the present invention is to propose a kind of non-transitorycomputer readable storage medium.
The 5th purpose of the present invention is to propose a kind of computer program product.
For the above-mentioned purpose, first aspect present invention embodiment proposes a kind of polymerizable clc method, including:
Obtain search daily record;The search daily record includes:The temperature information of multiple search terms and the search term;
According to the temperature information of the search term, the focus point of interest in the search term is obtained;
Obtain a plurality of news data for meeting preparatory condition;
The news data is labeled according to the focus point of interest, determines heat included in the news data
The assessment fraction of point point of interest and the focus point of interest;
For each focus point of interest, acquisition includes the focus point of interest, and including the focus point of interest comment
Estimate at least one news data that fraction meets preset fraction threshold value, according at least one news data, generation with it is described
Hot news corresponding to focus point of interest polymerize article.
Further, the temperature information according to the search term, the focus point of interest in the search term is obtained, wrapped
Include:
By the temperature information of multiple search terms and the search term, default temperature model is inputted, obtains the search
Focus search term in word;
According to the focus search term, default entity dictionary is inquired about, judges whether include in fact in the focus search term
Body;Focus search term including entity is defined as candidate's point of interest;
Hit rate of the candidate's point of interest in news data sample is obtained, the candidate is determined according to the hit rate
Focus point of interest in point of interest.
Further, the hit rate for obtaining candidate's point of interest in news data sample, according to the hit
Rate determines the focus point of interest in candidate's point of interest, including:
Obtain news data sample;
The a plurality of news data in the news data sample is labeled according to candidate's point of interest, acquisition includes
The news data bar number of candidate's point of interest;
According to the news data bar number including candidate's point of interest and the total number of the news data sample, calculate
The hit rate of candidate's point of interest;
Corresponding hit rate is more than to candidate's point of interest of predetermined probabilities threshold value, is defined as focus point of interest.
Further, the acquisition meets a plurality of news data of preparatory condition, including:
Obtain news database;
By the news data in the news database, default low-quality model is inputted, obtains point of the news data
Class;
Classification meets a plurality of news data of preparatory condition corresponding to obtaining.
Further, it is described that the news data is labeled according to the focus point of interest, determine the news number
The assessment fraction of included focus point of interest and the focus point of interest in, including:
For each bar news data, the news data is labeled, obtains heat included in the news data
Point point of interest;
Obtain occurrence number of the focus point of interest in the news data;
According to occurrence number of the focus point of interest in the news data, the assessment of the focus point of interest is calculated
Fraction.
Further, it is described according at least one news data, generate focus corresponding with the focus point of interest
News Aggreagation article, including:
Summarization generation is carried out at least one news data, obtains and is plucked corresponding at least one news data
Will;
Summary and article template according to corresponding at least one news data, generation and the focus point of interest pair
The hot news polymerization article answered.
The polymerizable clc method of the embodiment of the present invention, daily record is searched for by obtaining;Search daily record includes:Multiple search terms
And the temperature information of search term;According to the temperature information of search term, the focus point of interest in search term is obtained;Obtain and meet in advance
If a plurality of news data of condition;News data is labeled according to focus point of interest, determined in news data included
The assessment fraction of focus point of interest and focus point of interest;For each focus point of interest, acquisition includes focus point of interest, and wraps
The assessment fraction of the focus point of interest included meets at least one news data of preset fraction threshold value, according at least one news number
According to generation hot news polymerization article corresponding with focus point of interest, so as to get comprehensive focus point of interest, and pin
, can be according to the hot news generation hot news polymerization text very high with focus point of interest correlation to each focus point of interest
Chapter, efficiency high and accuracy rate are high, and need not manually participate in, and reduce polymerizable clc cost.
For the above-mentioned purpose, second aspect of the present invention embodiment proposes a kind of polymerizable clc device, including:
Acquisition module, daily record is searched for for obtaining;The search daily record includes:Multiple search terms and the search term
Temperature information;
The acquisition module, is additionally operable to the temperature information according to the search term, and the focus obtained in the search term is emerging
Interesting point;
The acquisition module, it is additionally operable to obtain a plurality of news data for meeting preparatory condition;
Labeling module, for being labeled according to the focus point of interest to the news data, determine the news number
The assessment fraction of included focus point of interest and the focus point of interest in;
Generation module, for for each focus point of interest, acquisition includes the focus point of interest, and including the heat
The assessment fraction of point point of interest meets at least one news data of preset fraction threshold value, according at least one news number
According to generation hot news polymerization article corresponding with the focus point of interest.
Further, the acquisition module includes:
Input block, for by the temperature information of multiple search terms and the search term, inputting default temperature model,
Obtain the focus search term in the search term;
Query unit, for according to the focus search term, inquiring about default entity dictionary, judging the focus search term
In whether include entity;Focus search term including entity is defined as candidate's point of interest;
Determining unit, for obtaining hit rate of the candidate's point of interest in news data sample, according to the hit
Rate determines the focus point of interest in candidate's point of interest.
Further, the determining unit is specifically used for,
Obtain news data sample;
The a plurality of news data in the news data sample is labeled according to candidate's point of interest, acquisition includes
The news data bar number of candidate's point of interest;
According to the news data bar number including candidate's point of interest and the total number of the news data sample, calculate
The hit rate of candidate's point of interest;
Corresponding hit rate is more than to candidate's point of interest of predetermined probabilities threshold value, is defined as focus point of interest.
Further, the acquisition module is specifically used for,
Obtain news database;
By the news data in the news database, default low-quality model is inputted, obtains point of the news data
Class;
Classification meets a plurality of news data of preparatory condition corresponding to obtaining.
Further, the labeling module is specifically used for,
For each bar news data, the news data is labeled, obtains heat included in the news data
Point point of interest;
Obtain occurrence number of the focus point of interest in the news data;
According to occurrence number of the focus point of interest in the news data, the assessment of the focus point of interest is calculated
Fraction.
Further, the generation module is specifically used for,
Summarization generation is carried out at least one news data, obtains and is plucked corresponding at least one news data
Will;
Summary and article template according to corresponding at least one news data, generation and the focus point of interest pair
The hot news polymerization article answered.
The polymerizable clc device of the embodiment of the present invention, daily record is searched for by obtaining;Search daily record includes:Multiple search terms
And the temperature information of search term;According to the temperature information of search term, the focus point of interest in search term is obtained;Obtain and meet in advance
If a plurality of news data of condition;News data is labeled according to focus point of interest, determined in news data included
The assessment fraction of focus point of interest and focus point of interest;For each focus point of interest, acquisition includes focus point of interest, and wraps
The assessment fraction of the focus point of interest included meets at least one news data of preset fraction threshold value, according at least one news number
According to generation hot news polymerization article corresponding with focus point of interest, so as to get comprehensive focus point of interest, and pin
, can be according to the hot news generation hot news polymerization text very high with focus point of interest correlation to each focus point of interest
Chapter, efficiency high and accuracy rate are high, and need not manually participate in, and reduce polymerizable clc cost.
For the above-mentioned purpose, third aspect present invention embodiment proposes another polymerizable clc device, including:Storage
Device, processor and storage are on a memory and the computer program that can run on a processor, it is characterised in that the processor
Polymerizable clc method as described above is realized when performing described program.
To achieve these goals, fourth aspect present invention embodiment proposes a kind of computer-readable recording medium, its
On be stored with computer program, the program realizes polymerizable clc method as described above when being executed by processor.
To achieve these goals, fifth aspect present invention embodiment proposes a kind of computer program product, when described
When instruction processing unit in computer program product performs, a kind of polymerizable clc method is performed, methods described includes:
Obtain search daily record;The search daily record includes:The temperature information of multiple search terms and the search term;
According to the temperature information of the search term, the focus point of interest in the search term is obtained;
Obtain a plurality of news data for meeting preparatory condition;
The news data is labeled according to the focus point of interest, determines heat included in the news data
The assessment fraction of point point of interest and the focus point of interest;
For each focus point of interest, acquisition includes the focus point of interest, and including the focus point of interest comment
Estimate at least one news data that fraction meets preset fraction threshold value, according at least one news data, generation with it is described
Hot news corresponding to focus point of interest polymerize article.
The additional aspect of the present invention and advantage will be set forth in part in the description, and will partly become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Brief description of the drawings
Of the invention above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Substantially and it is readily appreciated that, wherein:
Fig. 1 is a kind of schematic flow sheet of polymerizable clc method provided in an embodiment of the present invention;
Fig. 2 a-2c are the schematic diagram of at least one news data;
Fig. 3 is that the hot news of generation polymerize the schematic diagram of article;
Fig. 4 is the schematic flow sheet of another polymerizable clc method provided in an embodiment of the present invention;
Fig. 5 is a kind of structural representation of polymerizable clc device provided in an embodiment of the present invention;
Fig. 6 is the structural representation of another polymerizable clc device provided in an embodiment of the present invention;
Fig. 7 is the structural representation of another polymerizable clc device provided in an embodiment of the present invention.
Embodiment
Embodiments of the invention are described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning to end
Same or similar label represents same or similar element or the element with same or like function.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to for explaining the present invention, and is not considered as limiting the invention.
Below with reference to the accompanying drawings the polymerizable clc method and device of the embodiment of the present invention is described.
Fig. 1 is a kind of schematic flow sheet of polymerizable clc method provided in an embodiment of the present invention.As shown in figure 1, this article
Polymerization comprises the following steps:
S101, obtain search daily record;Search daily record includes:The temperature information of multiple search terms and search term.
The executive agent of polymerizable clc method provided by the invention is polymerizable clc device, and polymerizable clc device can be hard
Part equipment, the software installed on such as server etc., or hardware device.Wherein, server for example can be search engine pair
The background server answered.Wherein, search daily record can obtain from search engine.The temperature information of search term can include following ginseng
In number any one or it is multiple:Total temperature, search term heat unit interval in of the search term in preset time period
Degree.Wherein, temperature refers to the number that search term is clicked on by user in a search engine, or secondary to what is searched for by user
Number.
S102, the temperature information according to search term, obtain the focus point of interest in search term.
In the present embodiment, polymerizable clc device can be according to the temperature information of search term, and obtaining in search term has necessarily
Total temperature or in certain unit interval temperature focus search term.
S103, acquisition meet a plurality of news data of preparatory condition.
In the present embodiment, the process that polymerizable clc device performs step 103 is specifically as follows, and obtains news database;Will
News data in news database, default low-quality model is inputted, obtains the classification of news data;Classification is full corresponding to obtaining
The a plurality of news data of sufficient preparatory condition.
Wherein, the input of low-quality model can be each bar news data, and output can be the classification of each bar news data.It is low
Matter model can obtain the feature in each bar news data, such as advertisement, yellow anti-etc.;Feature in each bar news data is true
Determine the classification of news data;When the classification of news data meets preparatory condition, by news data be defined as treating in step 104 into
The news data of rower note.For example, the classification in news data be not advertisement, it is yellow anti-etc. when, determine news data to be pending
The news data of mark.Low-quality model can be trained in advance according to each bar news data and its classification, or according to each bar
News data, feature and its classification are trained in advance.
In the present embodiment, by the use of low-quality model, the low-quality news including advertisement, the yellow feature such as anti-can be filtered out
Data, the quality of news data to be marked is improved, further improve the quality of the hot news polymerization article of generation, improve heat
The reading quantity of point news Aggreagation article.
In addition, it is necessary to explanation, news database can the mode of cluster hadoop in a distributed manner stored.It is corresponding
, polymerizable clc device can carry out distributed treatment to the news database stored in distributed type assemblies, obtain corresponding point
Class meets a plurality of news data of preparatory condition, so as to further improve polymerizable clc efficiency.
S104, according to focus point of interest news data is labeled, determines focus interest included in news data
The assessment fraction of point and focus point of interest.
Wherein, step 104 can specifically include:For each bar news data, news data is labeled, obtains news
Included focus point of interest in data;Obtain occurrence number of the focus point of interest in news data;According to focus point of interest
Occurrence number in news data, calculate the assessment fraction of focus point of interest.
S105, for each focus point of interest, acquisition includes focus point of interest, and including the assessment of focus point of interest divide
Number meets at least one news data of preset fraction threshold value, according at least one news data, generation and focus point of interest pair
The hot news polymerization article answered.
Wherein, step 105 can specifically include:Summarization generation is carried out at least one news data, obtains at least one
Made a summary corresponding to news data;Summary and article template according to corresponding at least one news data, generation and focus interest
Hot news polymerization article corresponding to point.As shown in figs. 2 a-2 c, Fig. 2 a-2c are the schematic diagram of at least one news data;Such as figure
Shown in 3, Fig. 3 is that the hot news of generation polymerize the schematic diagram of article, in Fig. 3, " daily Honda important news is selected | trendy Honda
CRV will come, and cash is also worth buying" can be in the a-2c of Fig. 2 according to news data generation hot news polymerization article.
In the present embodiment, polymerizable clc device can quickly obtain readding in news data according to summarization generation instrument
The strong summary of the property read, then multiple summaries are polymerize, it is new with reference to article template generation focus corresponding with focus point of interest
Polymerization article is heard, so as to improve the ageing of the hot news of generation polymerization article.
In the present embodiment, according to including focus point of interest, and including the assessment fraction of focus point of interest meet default point
At least one news data of number threshold value, hot news polymerization article corresponding with focus point of interest is generated, is included without using
The assessment fraction of focus point of interest be unsatisfactory for the news data of preset fraction threshold value, it is possible to increase the news number of article to be generated
According to the degree of correlation between focus point of interest, so improve focus point of interest polymerize article with the hot news of generation between phase
Guan Du.
The polymerizable clc method of the embodiment of the present invention, daily record is searched for by obtaining;Search daily record includes:Multiple search terms
And the temperature information of search term;According to the temperature information of search term, the focus point of interest in search term is obtained;Obtain and meet in advance
If a plurality of news data of condition;News data is labeled according to focus point of interest, determined in news data included
The assessment fraction of focus point of interest and focus point of interest;For each focus point of interest, acquisition includes focus point of interest, and wraps
The assessment fraction of the focus point of interest included meets at least one news data of preset fraction threshold value, according at least one news number
According to generation hot news polymerization article corresponding with focus point of interest, so as to get comprehensive focus point of interest, and pin
, can be according to the hot news generation hot news polymerization text very high with focus point of interest correlation to each focus point of interest
Chapter, efficiency high and accuracy rate are high, and need not manually participate in, and reduce polymerizable clc cost.
Fig. 4 is the schematic flow sheet of another polymerizable clc method provided in an embodiment of the present invention, as shown in figure 4, in Fig. 1
On the basis of illustrated embodiment, step 102 specifically may comprise steps of:
S1021, the temperature information by multiple search terms and search term, default temperature model is inputted, obtain search term
In focus search term.
Wherein, the input of temperature model can be the temperature information of search term and search term, and output can be search term
Type;The type includes:Focus search term or non-hot search term.In addition, the output of temperature model can also be 0 or
1,0 expression search term is non-hot search term, and 1 represents that search term is focus search term.Temperature model can be according to search term
Temperature information, and the type of search term carry out training in advance.
S1022, according to focus search term, inquire about default entity dictionary, judge whether include entity in focus search term;
Focus search term including entity is defined as candidate's point of interest.
Wherein, entity refers to the word with certain physical meaning, such as Beijing, amusement etc..
S1023, hit rate of candidate's point of interest in news data sample is obtained, candidate's point of interest is determined according to hit rate
In focus point of interest.
Wherein, the process of polymerizable clc device execution step 1023 is specifically as follows, and obtains news data sample;According to time
Select point of interest to be labeled a plurality of news data in news data sample, obtain the news data bar for including candidate's point of interest
Number;According to news data bar number and the total number of news data sample including candidate's point of interest, candidate's point of interest is calculated
Hit rate;Corresponding hit rate is more than to candidate's point of interest of predetermined probabilities threshold value, is defined as focus point of interest.
In the present embodiment, corresponding hit rate is more than to candidate's point of interest of predetermined probabilities threshold value, is defined as focus interest
Point, the word that point of interest is not suitable as in candidate's point of interest can be removed, so as to improve the accuracy of focus point of interest.
In addition, in order to further improve the accuracy of focus point of interest, before step 1023, described method can also wrap
Include:Deduplication operation and decontamination operation are carried out to candidate's point of interest, removes repetition candidate's point of interest in candidate's point of interest, removes
The relatively low candidate's point of interest of importance in candidate's point of interest, and the higher multiple candidate's points of interest of similarity are merged into one
Candidate's point of interest.The method of decontamination can be word frequency-reverse document-frequency algorithm (term frequency-inverse
Document frequency, TF-IDF).
The polymerizable clc method of the embodiment of the present invention, daily record is searched for by obtaining;Search daily record includes:Multiple search terms
And the temperature information of search term;By the temperature information of multiple search terms and search term, default temperature model is inputted, is obtained
Focus search term in search term;According to focus search term, default entity dictionary is inquired about, judges whether wrapped in focus search term
Include entity;Focus search term including entity is defined as candidate's point of interest;Candidate's point of interest is obtained in news data sample
Hit rate, the focus point of interest in candidate's point of interest is determined according to hit rate;Obtain a plurality of news number for meeting preparatory condition
According to;News data is labeled according to focus point of interest, determines focus point of interest and focus included in news data
The assessment fraction of point of interest;For each focus point of interest, acquisition includes focus point of interest, and including focus point of interest comment
Estimate at least one news data that fraction meets preset fraction threshold value, according at least one news data, generation and focus interest
Hot news polymerization article, so as to get comprehensive focus point of interest, and is directed to each focus point of interest corresponding to point,
Can be according to the hot news generation hot news polymerization article very high with focus point of interest correlation, efficiency high and accuracy rate
Height, and need not manually participate in, reduce polymerizable clc cost.
Fig. 5 is a kind of structural representation of polymerizable clc device provided in an embodiment of the present invention.As shown in figure 5, including:Obtain
Modulus block 51, labeling module 52 and generation module 53.
Wherein, acquisition module 51, daily record is searched for for obtaining;The search daily record includes:Multiple search terms and institute
State the temperature information of search term;
The acquisition module 51, the temperature information according to the search term is additionally operable to, obtains the focus in the search term
Point of interest;
The acquisition module 51, it is additionally operable to obtain a plurality of news data for meeting preparatory condition;
Labeling module 52, for being labeled according to the focus point of interest to the news data, determine the news
The assessment fraction of included focus point of interest and the focus point of interest in data;
Generation module 53, for for each focus point of interest, acquisition includes the focus point of interest, and including it is described
The assessment fraction of focus point of interest meets at least one news data of preset fraction threshold value, according at least one news number
According to generation hot news polymerization article corresponding with the focus point of interest.
Polymerizable clc device provided by the invention can be hardware device, pacify on such as server etc., or hardware device
The software of dress.Wherein, server for example can be background server corresponding to search engine.Wherein, searching for daily record can be from searching
Index holds up acquisition.The temperature information of search term can be including any one in following parameter or multiple:Search term is default
The temperature of total temperature, search term in unit interval in period.Wherein, temperature refers to search term in a search engine
The number clicked on by user, or by user to the number searched for.
Further, on the basis of above-described embodiment, the acquisition module 51 is specifically used for,
Obtain news database;
By the news data in the news database, default low-quality model is inputted, obtains point of the news data
Class;
Classification meets a plurality of news data of preparatory condition corresponding to obtaining.
Wherein, the input of low-quality model can be each bar news data, and output can be the classification of each bar news data.It is low
Matter model can obtain the feature in each bar news data, such as advertisement, yellow anti-etc.;Feature in each bar news data is true
Determine the classification of news data;When the classification of news data meets preparatory condition, by news data be defined as treating in step 104 into
The news data of rower note.For example, the classification in news data be not advertisement, it is yellow anti-etc. when, determine news data to be pending
The news data of mark.Low-quality model can be trained in advance according to each bar news data and its classification, or according to each bar
News data, feature and its classification are trained in advance.
In the present embodiment, by the use of low-quality model, the low-quality news including advertisement, the yellow feature such as anti-can be filtered out
Data, the quality of news data to be marked is improved, further improve the quality of the hot news polymerization article of generation, improve heat
The reading quantity of point news Aggreagation article.
Further, on the basis of above-described embodiment, the labeling module 52 is specifically used for,
For each bar news data, the news data is labeled, obtains heat included in the news data
Point point of interest;
Obtain occurrence number of the focus point of interest in the news data;
According to occurrence number of the focus point of interest in the news data, the assessment of the focus point of interest is calculated
Fraction.
Further, on the basis of above-described embodiment, the generation module 53 is specifically used for,
Summarization generation is carried out at least one news data, obtains and is plucked corresponding at least one news data
Will;
Summary and article template according to corresponding at least one news data, generation and the focus point of interest pair
The hot news polymerization article answered.
In the present embodiment, polymerizable clc device can quickly obtain readding in news data according to summarization generation instrument
The strong summary of the property read, then multiple summaries are polymerize, it is new with reference to article template generation focus corresponding with focus point of interest
Polymerization article is heard, so as to improve the ageing of the hot news of generation polymerization article.
In the present embodiment, according to including focus point of interest, and including the assessment fraction of focus point of interest meet default point
At least one news data of number threshold value, hot news polymerization article corresponding with focus point of interest is generated, is included without using
The assessment fraction of focus point of interest be unsatisfactory for the news data of preset fraction threshold value, it is possible to increase the news number of article to be generated
According to the degree of correlation between focus point of interest, so improve focus point of interest polymerize article with the hot news of generation between phase
Guan Du.
The polymerizable clc device of the embodiment of the present invention, daily record is searched for by obtaining;Search daily record includes:Multiple search terms
And the temperature information of search term;According to the temperature information of search term, the focus point of interest in search term is obtained;Obtain and meet in advance
If a plurality of news data of condition;News data is labeled according to focus point of interest, determined in news data included
The assessment fraction of focus point of interest and focus point of interest;For each focus point of interest, acquisition includes focus point of interest, and wraps
The assessment fraction of the focus point of interest included meets at least one news data of preset fraction threshold value, according at least one news number
According to generation hot news polymerization article corresponding with focus point of interest, so as to get comprehensive focus point of interest, and pin
, can be according to the hot news generation hot news polymerization text very high with focus point of interest correlation to each focus point of interest
Chapter, efficiency high and accuracy rate are high, and need not manually participate in, and reduce polymerizable clc cost.
Further, with reference to reference to figure 6, on the basis of embodiment illustrated in fig. 5, the acquisition module 51 includes:Input
Unit 511, query unit 512 and determining unit 513.
Wherein, input block 511, for the temperature information of multiple search terms and the search term, input is default
Temperature model, obtain the focus search term in the search term;
Query unit 512, for according to the focus search term, inquiring about default entity dictionary, judging that the focus is searched
Whether include entity in rope word;Focus search term including entity is defined as candidate's point of interest;
Determining unit 513, for obtaining hit rate of the candidate's point of interest in news data sample, according to the life
Middle rate determines the focus point of interest in candidate's point of interest.
Wherein, the input of temperature model can be the temperature information of search term and search term, and output can be search term
Type;The type includes:Focus search term or non-hot search term.In addition, the output of temperature model can also be 0 or
1,0 expression search term is non-hot search term, and 1 represents that search term is focus search term.Temperature model can be according to search term
Temperature information, and the type of search term carry out training in advance.
Further, the determining unit 513 is specifically used for,
Obtain news data sample;
The a plurality of news data in the news data sample is labeled according to candidate's point of interest, acquisition includes
The news data bar number of candidate's point of interest;
According to the news data bar number including candidate's point of interest and the total number of the news data sample, calculate
The hit rate of candidate's point of interest;
Corresponding hit rate is more than to candidate's point of interest of predetermined probabilities threshold value, is defined as focus point of interest.
In the present embodiment, corresponding hit rate is more than to candidate's point of interest of predetermined probabilities threshold value, is defined as focus interest
Point, the word that point of interest is not suitable as in candidate's point of interest can be removed, so as to improve the accuracy of focus point of interest.
In addition, in order to further improve the accuracy of focus point of interest, polymerizable clc device can be also used for, emerging to candidate
Interest point carries out deduplication operation and decontamination operation, removes repetition candidate's point of interest in candidate's point of interest, removes candidate's point of interest
The relatively low candidate's point of interest of middle importance, and the higher multiple candidate's points of interest of similarity are merged into candidate's interest
Point.The method of decontamination can be word frequency-reverse document-frequency algorithm (term frequency-inverse document
Frequency, TF-IDF).
The polymerizable clc device of the embodiment of the present invention, daily record is searched for by obtaining;Search daily record includes:Multiple search terms
And the temperature information of search term;By the temperature information of multiple search terms and search term, default temperature model is inputted, is obtained
Focus search term in search term;According to focus search term, default entity dictionary is inquired about, judges whether wrapped in focus search term
Include entity;Focus search term including entity is defined as candidate's point of interest;Candidate's point of interest is obtained in news data sample
Hit rate, the focus point of interest in candidate's point of interest is determined according to hit rate;Obtain a plurality of news number for meeting preparatory condition
According to;News data is labeled according to focus point of interest, determines focus point of interest and focus included in news data
The assessment fraction of point of interest;For each focus point of interest, acquisition includes focus point of interest, and including focus point of interest comment
Estimate at least one news data that fraction meets preset fraction threshold value, according at least one news data, generation and focus interest
Hot news polymerization article, so as to get comprehensive focus point of interest, and is directed to each focus point of interest corresponding to point,
Can be according to the hot news generation hot news polymerization article very high with focus point of interest correlation, efficiency high and accuracy rate
Height, and need not manually participate in, reduce polymerizable clc cost.
Fig. 7 is the structural representation of another polymerizable clc device provided in an embodiment of the present invention.This article polyplant
Including:
Memory 1001, processor 1002 and it is stored in the calculating that can be run on memory 1001 and on processor 1002
Machine program.
Processor 1002 realizes the polymerizable clc method provided in above-described embodiment when performing described program.
Further, polymerizable clc device also includes:
Communication interface 1003, for the communication between memory 1001 and processor 1002.
Memory 1001, for depositing the computer program that can be run on processor 1002.
Memory 1001 may include high-speed RAM memory, it is also possible to also including nonvolatile memory (non-
Volatile memory), a for example, at least magnetic disk storage.
Processor 1002, the polymerizable clc method described in above-described embodiment is realized during for performing described program.
If memory 1001, processor 1002 and the independent realization of communication interface 1003, communication interface 1003, memory
1001 and processor 1002 can be connected with each other by bus and complete mutual communication.The bus can be industrial standard
Architecture (Industry Standard Architecture, referred to as ISA) bus, external equipment interconnection
(Peripheral Component, referred to as PCI) bus or extended industry-standard architecture (Extended Industry
Standard Architecture, referred to as EISA) bus etc..The bus can be divided into address bus, data/address bus, control
Bus processed etc..For ease of representing, only represented in Fig. 7 with a thick line, it is not intended that an only bus or a type of
Bus.
Optionally, in specific implementation, if memory 1001, processor 1002 and communication interface 1003, are integrated in one
Realized on block chip, then memory 1001, processor 1002 and communication interface 1003 can be completed mutual by internal interface
Communication.
Processor 1002 is probably a central processing unit (Central Processing Unit, referred to as CPU), or
Person is specific integrated circuit (Application Specific Integrated Circuit, referred to as ASIC), or quilt
It is configured to implement one or more integrated circuits of the embodiment of the present invention.
The present invention also provides a kind of computer-readable recording medium, is stored thereon with computer program, the program is processed
Device realizes polymerizable clc method as described above when performing.
The present invention also provides a kind of computer program product, when the instruction processing unit in the computer program product performs
When, a kind of polymerizable clc method is performed, methods described includes:
Obtain search daily record;The search daily record includes:The temperature information of multiple search terms and the search term;
According to the temperature information of the search term, the focus point of interest in the search term is obtained;
Obtain a plurality of news data for meeting preparatory condition;
The news data is labeled according to the focus point of interest, determines heat included in the news data
The assessment fraction of point point of interest and the focus point of interest;
For each focus point of interest, acquisition includes the focus point of interest, and including the focus point of interest comment
Estimate at least one news data that fraction meets preset fraction threshold value, according at least one news data, generation with it is described
Hot news corresponding to focus point of interest polymerize article.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or the spy for combining the embodiment or example description
Point is contained at least one embodiment or example of the present invention.In this manual, to the schematic representation of above-mentioned term not
Identical embodiment or example must be directed to.Moreover, specific features, structure, material or the feature of description can be with office
Combined in an appropriate manner in one or more embodiments or example.In addition, in the case of not conflicting, the skill of this area
Art personnel can be tied the different embodiments or example and the feature of different embodiments or example described in this specification
Close and combine.
In addition, term " first ", " second " are only used for describing purpose, and it is not intended that instruction or hint relative importance
Or the implicit quantity for indicating indicated technical characteristic.Thus, define " first ", the feature of " second " can be expressed or
Implicitly include at least one this feature.In the description of the invention, " multiple " are meant that at least two, such as two, three
It is individual etc., unless otherwise specifically defined.
Any process or method described otherwise above description in flow chart or herein is construed as, and represents to include
Module, fragment or the portion of the code of the executable instruction of one or more the step of being used to realize custom logic function or process
Point, and the scope of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discuss suitable
Sequence, including according to involved function by it is basic simultaneously in the way of or in the opposite order, carry out perform function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system including the system of processor or other can be held from instruction
The system of row system, device or equipment instruction fetch and execute instruction) use, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium " can any can be included, store, communicate, propagate or pass
Defeated program is for instruction execution system, device or equipment or the dress used with reference to these instruction execution systems, device or equipment
Put.The more specifically example (non-exhaustive list) of computer-readable medium includes following:Electricity with one or more wiring
Connecting portion (electronic installation), portable computer diskette box (magnetic device), random access memory (RAM), read-only storage
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device, and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, computer-readable medium, which can even is that, to print the paper of described program thereon or other are suitable
Medium, because can then enter edlin, interpretation or if necessary with it for example by carrying out optical scanner to paper or other media
His suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each several part of the present invention can be realized with hardware, software, firmware or combinations thereof.Above-mentioned
In embodiment, software that multiple steps or method can be performed in memory and by suitable instruction execution system with storage
Or firmware is realized.Such as, if realized with hardware with another embodiment, following skill well known in the art can be used
Any one of art or their combination are realized:With the logic gates for realizing logic function to data-signal from
Logic circuit is dissipated, the application specific integrated circuit with suitable combinational logic gate circuit, programmable gate array (PGA), scene can compile
Journey gate array (FPGA) etc..
Those skilled in the art are appreciated that to realize all or part of step that above-described embodiment method carries
Suddenly it is that by program the hardware of correlation can be instructed to complete, described program can be stored in a kind of computer-readable storage medium
In matter, the program upon execution, including one or a combination set of the step of embodiment of the method.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing module, can also
That unit is individually physically present, can also two or more units be integrated in a module.Above-mentioned integrated mould
Block can both be realized in the form of hardware, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized in the form of software function module and as independent production marketing or in use, can also be stored in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only storage, disk or CD etc..Although have been shown and retouch above
Embodiments of the invention are stated, it is to be understood that above-described embodiment is exemplary, it is impossible to be interpreted as the limit to the present invention
System, one of ordinary skill in the art can be changed to above-described embodiment, change, replace and become within the scope of the invention
Type.
Claims (15)
- A kind of 1. polymerizable clc method, it is characterised in that including:Obtain search daily record;The search daily record includes:The temperature information of multiple search terms and the search term;According to the temperature information of the search term, the focus point of interest in the search term is obtained;Obtain a plurality of news data for meeting preparatory condition;The news data is labeled according to the focus point of interest, determines that focus included in the news data is emerging The assessment fraction of interest point and the focus point of interest;For each focus point of interest, acquisition includes the focus point of interest, and including the assessment of the focus point of interest divide Number meets at least one news data of preset fraction threshold value, according at least one news data, generation and the focus Hot news corresponding to point of interest polymerize article.
- 2. according to the method for claim 1, it is characterised in that the temperature information according to the search term, obtain institute The focus point of interest in search term is stated, including:By the temperature information of multiple search terms and the search term, default temperature model is inputted, is obtained in the search term Focus search term;According to the focus search term, default entity dictionary is inquired about, judges whether include entity in the focus search term;Will Focus search term including entity is defined as candidate's point of interest;Hit rate of the candidate's point of interest in news data sample is obtained, candidate's interest is determined according to the hit rate Focus point of interest in point.
- 3. according to the method for claim 2, it is characterised in that described to obtain candidate's point of interest in news data sample In hit rate, the focus point of interest in candidate's point of interest is determined according to the hit rate, including:Obtain news data sample;The a plurality of news data in the news data sample is labeled according to candidate's point of interest, obtained described in including The news data bar number of candidate's point of interest;According to the news data bar number including candidate's point of interest and the total number of the news data sample, described in calculating The hit rate of candidate's point of interest;Corresponding hit rate is more than to candidate's point of interest of predetermined probabilities threshold value, is defined as focus point of interest.
- 4. according to the method for claim 1, it is characterised in that it is described to obtain a plurality of news data for meeting preparatory condition, Including:Obtain news database;By the news data in the news database, default low-quality model is inputted, obtains the classification of the news data;Classification meets a plurality of news data of preparatory condition corresponding to obtaining.
- 5. according to the method for claim 1, it is characterised in that it is described according to the focus point of interest to the news data It is labeled, determines the assessment fraction of focus point of interest included in the news data and the focus point of interest, bag Include:For each bar news data, the news data is labeled, it is emerging to obtain focus included in the news data Interesting point;Obtain occurrence number of the focus point of interest in the news data;According to occurrence number of the focus point of interest in the news data, the assessment point of the focus point of interest is calculated Number.
- 6. according to the method for claim 1, it is characterised in that it is described according at least one news data, generation with Hot news corresponding to the focus point of interest polymerize article, including:Summarization generation is carried out at least one news data, obtains and is made a summary corresponding at least one news data;Summary and article template according to corresponding at least one news data, generation are corresponding with the focus point of interest Hot news polymerize article.
- A kind of 7. polymerizable clc device, it is characterised in that including:Acquisition module, daily record is searched for for obtaining;The search daily record includes:The heat of multiple search terms and the search term Spend information;The acquisition module, the temperature information according to the search term is additionally operable to, obtains the focus point of interest in the search term;The acquisition module, it is additionally operable to obtain a plurality of news data for meeting preparatory condition;Labeling module, for being labeled according to the focus point of interest to the news data, determine in the news data Included focus point of interest and the assessment fraction of the focus point of interest;Generation module, for for each focus point of interest, acquisition includes the focus point of interest, and including the focus it is emerging The assessment fraction of interest point meets at least one news data of preset fraction threshold value, raw according at least one news data It polymerize article into hot news corresponding with the focus point of interest.
- 8. device according to claim 7, it is characterised in that the acquisition module includes:Input block, for by the temperature information of multiple search terms and the search term, inputting default temperature model, obtain Focus search term in the search term;Query unit, for according to the focus search term, inquiring about default entity dictionary, judge be in the focus search term It is no including entity;Focus search term including entity is defined as candidate's point of interest;Determining unit, it is true according to the hit rate for obtaining hit rate of the candidate's point of interest in news data sample Focus point of interest in fixed candidate's point of interest.
- 9. device according to claim 8, it is characterised in that the determining unit is specifically used for,Obtain news data sample;The a plurality of news data in the news data sample is labeled according to candidate's point of interest, obtained described in including The news data bar number of candidate's point of interest;According to the news data bar number including candidate's point of interest and the total number of the news data sample, described in calculating The hit rate of candidate's point of interest;Corresponding hit rate is more than to candidate's point of interest of predetermined probabilities threshold value, is defined as focus point of interest.
- 10. device according to claim 7, it is characterised in that the acquisition module is specifically used for,Obtain news database;By the news data in the news database, default low-quality model is inputted, obtains the classification of the news data;Classification meets a plurality of news data of preparatory condition corresponding to obtaining.
- 11. device according to claim 7, it is characterised in that the labeling module is specifically used for,For each bar news data, the news data is labeled, it is emerging to obtain focus included in the news data Interesting point;Obtain occurrence number of the focus point of interest in the news data;According to occurrence number of the focus point of interest in the news data, the assessment point of the focus point of interest is calculated Number.
- 12. device according to claim 7, it is characterised in that the generation module is specifically used for,Summarization generation is carried out at least one news data, obtains and is made a summary corresponding at least one news data;Summary and article template according to corresponding at least one news data, generation are corresponding with the focus point of interest Hot news polymerize article.
- A kind of 13. polymerizable clc device, it is characterised in that including:Memory, processor and storage are on a memory and the computer program that can run on a processor, it is characterised in that institute The polymerizable clc method as described in any in claim 1-6 is realized when stating computing device described program.
- 14. a kind of non-transitorycomputer readable storage medium, is stored thereon with computer program, it is characterised in that the program The polymerizable clc method as described in any in claim 1-6 is realized when being executed by processor.
- 15. a kind of computer program product, when the instruction processing unit in the computer program product performs, perform a kind of text Chapter polymerization, methods described include:Obtain search daily record;The search daily record includes:The temperature information of multiple search terms and the search term;According to the temperature information of the search term, the focus point of interest in the search term is obtained;Obtain a plurality of news data for meeting preparatory condition;The news data is labeled according to the focus point of interest, determines that focus included in the news data is emerging The assessment fraction of interest point and the focus point of interest;For each focus point of interest, acquisition includes the focus point of interest, and including the assessment of the focus point of interest divide Number meets at least one news data of preset fraction threshold value, according at least one news data, generation and the focus Hot news corresponding to point of interest polymerize article.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711145235.XA CN107748802A (en) | 2017-11-17 | 2017-11-17 | Polymerizable clc method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711145235.XA CN107748802A (en) | 2017-11-17 | 2017-11-17 | Polymerizable clc method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107748802A true CN107748802A (en) | 2018-03-02 |
Family
ID=61251508
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711145235.XA Pending CN107748802A (en) | 2017-11-17 | 2017-11-17 | Polymerizable clc method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107748802A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108345698A (en) * | 2018-03-22 | 2018-07-31 | 北京百度网讯科技有限公司 | Article focus method for digging and device |
CN109033050A (en) * | 2018-06-29 | 2018-12-18 | 北京百度网讯科技有限公司 | Article generation method, equipment and storage medium |
CN109657043A (en) * | 2018-12-14 | 2019-04-19 | 北京百度网讯科技有限公司 | Automatically generate the method, apparatus, equipment and storage medium of article |
CN109960756A (en) * | 2019-03-19 | 2019-07-02 | 国家计算机网络与信息安全管理中心 | Media event information inductive method |
CN111814036A (en) * | 2019-12-10 | 2020-10-23 | 北京嘀嘀无限科技发展有限公司 | Wireless hotspot and interest point matching method based on search engine, electronic device and storage medium |
CN112000868A (en) * | 2020-08-31 | 2020-11-27 | 上海微趣网络科技有限公司 | Information gathering display device and method |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102737036A (en) * | 2011-04-07 | 2012-10-17 | 腾讯科技(深圳)有限公司 | Method and device for acquiring hot spot value words |
CN103049443A (en) * | 2011-10-12 | 2013-04-17 | 腾讯科技(深圳)有限公司 | Method and device for mining hot-spot words |
CN103164427A (en) * | 2011-12-13 | 2013-06-19 | 中国移动通信集团公司 | Method and device of news aggregation |
CN103235800A (en) * | 2013-04-15 | 2013-08-07 | 百度在线网络技术(北京)有限公司 | Preview method and preview system of search results |
CN103246644A (en) * | 2013-04-02 | 2013-08-14 | 亿赞普(北京)科技有限公司 | Method and device for processing Internet public opinion information |
CN103425741A (en) * | 2013-07-16 | 2013-12-04 | 北京中科汇联信息技术有限公司 | Information exhibiting method and device |
CN103955529A (en) * | 2014-05-12 | 2014-07-30 | 中国科学院计算机网络信息中心 | Internet information searching and aggregating presentation method |
US20170171324A1 (en) * | 2013-02-26 | 2017-06-15 | PortAura Group | Method and system for providing recommendations using location information |
-
2017
- 2017-11-17 CN CN201711145235.XA patent/CN107748802A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102737036A (en) * | 2011-04-07 | 2012-10-17 | 腾讯科技(深圳)有限公司 | Method and device for acquiring hot spot value words |
CN103049443A (en) * | 2011-10-12 | 2013-04-17 | 腾讯科技(深圳)有限公司 | Method and device for mining hot-spot words |
CN103164427A (en) * | 2011-12-13 | 2013-06-19 | 中国移动通信集团公司 | Method and device of news aggregation |
US20170171324A1 (en) * | 2013-02-26 | 2017-06-15 | PortAura Group | Method and system for providing recommendations using location information |
CN103246644A (en) * | 2013-04-02 | 2013-08-14 | 亿赞普(北京)科技有限公司 | Method and device for processing Internet public opinion information |
CN103235800A (en) * | 2013-04-15 | 2013-08-07 | 百度在线网络技术(北京)有限公司 | Preview method and preview system of search results |
CN103425741A (en) * | 2013-07-16 | 2013-12-04 | 北京中科汇联信息技术有限公司 | Information exhibiting method and device |
CN103955529A (en) * | 2014-05-12 | 2014-07-30 | 中国科学院计算机网络信息中心 | Internet information searching and aggregating presentation method |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108345698A (en) * | 2018-03-22 | 2018-07-31 | 北京百度网讯科技有限公司 | Article focus method for digging and device |
CN108345698B (en) * | 2018-03-22 | 2022-03-11 | 北京百度网讯科技有限公司 | Method and device for mining attention points of articles |
CN109033050A (en) * | 2018-06-29 | 2018-12-18 | 北京百度网讯科技有限公司 | Article generation method, equipment and storage medium |
CN109657043A (en) * | 2018-12-14 | 2019-04-19 | 北京百度网讯科技有限公司 | Automatically generate the method, apparatus, equipment and storage medium of article |
CN109960756A (en) * | 2019-03-19 | 2019-07-02 | 国家计算机网络与信息安全管理中心 | Media event information inductive method |
CN111814036A (en) * | 2019-12-10 | 2020-10-23 | 北京嘀嘀无限科技发展有限公司 | Wireless hotspot and interest point matching method based on search engine, electronic device and storage medium |
CN112000868A (en) * | 2020-08-31 | 2020-11-27 | 上海微趣网络科技有限公司 | Information gathering display device and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107748802A (en) | Polymerizable clc method and device | |
CN108182279B (en) | Object classification method, device and computer equipment based on text feature | |
CN106815192B (en) | Model training method and device and sentence emotion recognition method and device | |
CN108280114B (en) | Deep learning-based user literature reading interest analysis method | |
CN106294635B (en) | Application program searching method, the training method of deep neural network model and device | |
CN110188350B (en) | Text consistency calculation method and device | |
JP5387578B2 (en) | Information analysis apparatus, information analysis method, and program | |
CN113159095A (en) | Model training method, image retrieval method and device | |
CN111798273A (en) | Training method of purchase probability prediction model of product and purchase probability prediction method | |
JP6909633B2 (en) | Evaluation device, evaluation method, and evaluation program | |
CN110046298B (en) | Query word recommendation method and device, terminal device and computer readable medium | |
CN109992646A (en) | The extracting method and device of text label | |
CN107463661A (en) | The introduction method and device of data | |
CN109710841A (en) | Comment on recommended method and device | |
CN109344399A (en) | A kind of Text similarity computing method based on the two-way lstm neural network of stacking | |
CN107122492A (en) | Lyric generation method and device based on picture content | |
CN108897852A (en) | Judgment method, device and the equipment of conversation content continuity | |
CN110222654A (en) | Text segmenting method, device, equipment and storage medium | |
CN107885888A (en) | Information processing method and device, terminal device and computer-readable recording medium | |
CN109472017A (en) | Obtain the method and device that judgement document the court to be generated thinks section relevant information | |
CN110187760A (en) | Intelligent interactive method and device | |
CN107025312A (en) | Information providing method and device based on video content | |
CN109819002A (en) | Data push method and device, storage medium and electronic device | |
Fernandes et al. | Applying deep neural networks to named entity recognition in portuguese texts | |
Ebert et al. | A linguistically informed convolutional neural network |
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 |