CN110516227A - Title text generation method, device, electronic equipment and computer-readable medium - Google Patents
Title text generation method, device, electronic equipment and computer-readable medium Download PDFInfo
- Publication number
- CN110516227A CN110516227A CN201910235235.1A CN201910235235A CN110516227A CN 110516227 A CN110516227 A CN 110516227A CN 201910235235 A CN201910235235 A CN 201910235235A CN 110516227 A CN110516227 A CN 110516227A
- Authority
- CN
- China
- Prior art keywords
- data
- news
- news data
- characteristic parameter
- writing characteristic
- 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
- Machine Translation (AREA)
Abstract
This disclosure relates to a kind of title text generation method, device, electronic equipment and computer-readable medium.This method comprises: obtaining the first news data based on preset condition；At least one second news data is obtained based on first news data；Writing characteristic parameter is determined based on target object；The writing characteristic parameter and at least one second news data are subjected to Data Fusion to generate headline；And using the headline as the title text of first news data to be shown.This disclosure relates to title text generation method, device, electronic equipment and computer-readable medium, can quickly generate the headline with personal characteristics and interest automatically.
Description
Technical field
This disclosure relates to computer information processing field, in particular to a kind of title text generation method, device,
Electronic equipment and computer-readable medium.
Background technique
With the emergence and development of current new media, hot news is continued to bring out, and dissemination of news is getting faster.One news
The report of different angle can be carried out by media, consequent is that the quantity of newsletter archive is more and more, journalist
Workload it is increasing.During existing news is shown, often directly use headline as the displaying title of related news.
For longer headline, but user likes shorter title, is checked on the mobile apparatus with facilitating.
Moreover, the rhythm with dissemination of news is getting faster, needs journalist to report one with faster speed and disappear
Breath, such case substantially increase the workload that journalist writes contribution, also require journalist with speed faster
Degree writes contribution.And the title author in need of news contemplates refinement, occupies many time.Moreover, the prior art
The generations of all Domestic News be required to lead to the text of Domestic News by writing and edit generation by website staff
Chapter formation efficiency is lower；Workload is too big, and content is easy duplicate deficiency.
Therefore, it is necessary to a kind of new title text generation method, device, electronic equipment and computer-readable mediums.
Above- mentioned information are only used for reinforcing the understanding to the background of the disclosure, therefore it disclosed in the background technology part
It may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
In view of this, the disclosure provides a kind of title text generation method, device, electronic equipment and computer-readable Jie
Matter can quickly generate the headline with personal characteristics and interest automatically.
Other characteristics and advantages of the disclosure will be apparent from by the following detailed description, or partially by the disclosure
Practice and acquistion.
According to the one side of the disclosure, a kind of title text generation method is proposed, this method comprises: obtaining based on preset condition
Take the first news data；At least one second news data is obtained based on first news data；It is determined based on target object
Writing characteristic parameter；It is new to generate that the writing characteristic parameter and at least one second news data are subjected to Data Fusion
Hear title；And using the headline as the title text of first news data to be shown.
In a kind of exemplary embodiment of the disclosure, the preset condition includes aging condition, temperature condition, data source
Condition；Based on preset condition obtain the first news data include following situations at least one: when to the publication of real-time news data
Between carry out Screening Treatment, to filter out first news data for meeting aging condition；To the news heat of real-time news data
Degree carries out Screening Treatment, to filter out first news data for meeting temperature condition；And the hair to real-time news data
Cloth platform carries out Screening Treatment, to filter out first news data for meeting data source condition.
In a kind of exemplary embodiment of the disclosure, at least one second news is obtained based on first news data
Data comprise determining that the reversed viewpoint data of first news data；And at least based on the reversed viewpoint data acquisition
One the second news data.
In a kind of exemplary embodiment of the disclosure, it is based on described at least one second news of reversed viewpoint data acquisition
Data include: to determine keyword and/or key object based on the reversed viewpoint data；Obtain first news data
Associated data；And by the keyword and/or the key object to extract at least one in the associated data second new
Hear data.
In a kind of exemplary embodiment of the disclosure, determine that writing characteristic parameter includes: based on mesh based on target object
It marks object and the writing characteristic parameter is determined by writing characteristic library；The writing characteristic library includes the multiple of multiple target objects
Various dimensions writing characteristic parameter.
In a kind of exemplary embodiment of the disclosure, by the writing characteristic parameter and at least one second news data
It includes: that the writing characteristic parameter and at least one second news data is defeated that Data Fusion, which is carried out, to generate headline
Enter in data fusion model to generate the headline.
In a kind of exemplary embodiment of the disclosure, by the writing characteristic parameter and at least one second news data
It includes: to determine weight at least one described second news data that Data Fusion, which is carried out, to generate headline；It will be described
Writing characteristic parameter inputs the data fusion model at least one described second news data with weight, obtains output
Data；And word processing is carried out to generate the headline to the output data.
In a kind of exemplary embodiment of the disclosure, further includes: by history news data to machine learning algorithm
Initial model is trained to obtain the data fusion model.
In a kind of exemplary embodiment of the disclosure, by history news data to the initial model of machine learning algorithm
Being trained to obtain the data fusion model includes: to obtain multiple training datas by history news data；By the instruction
Practice data to be labeled to generate training set data and verifying collection data；By training set data input machine learning algorithm
It is trained in initial model, data is collected by the verifying, tune ginseng is carried out to training result；And it is obtained after training
The data fusion model.
According to the one side of the disclosure, a kind of title text generating means are proposed, which includes: the first news template,
For obtaining the first news data based on preset condition；Second news template, for based on first news data obtain to
Few second news data；Characteristic parameter module, for determining writing characteristic parameter based on target object；Data fusion mould
Block, for the writing characteristic parameter and at least one second news data to be carried out Data Fusion to generate news mark
Topic；And news display module, for using the headline as the title text of first news data to open up
Show.
According to the one side of the disclosure, a kind of electronic equipment is proposed, which includes: one or more processors；
Storage device, for storing one or more programs；When one or more programs are executed by one or more processors, so that one
A or multiple processors realize such as methodology above.
According to the one side of the disclosure, it proposes a kind of computer-readable medium, is stored thereon with computer program, the program
Method as mentioned in the above is realized when being executed by processor.
According to title text generation method, device, electronic equipment and the computer-readable medium of the disclosure, based on described the
One news data obtains at least one second news data；Writing characteristic parameter is determined based on target object；The writing is special
It levies parameter and at least one second news data carries out Data Fusion in a manner of generating headline, it can automatically quickly
Generation have personal characteristics and interest headline.
It should be understood that the above general description and the following detailed description are merely exemplary, this can not be limited
It is open.
Detailed description of the invention
Its example embodiment is described in detail by referring to accompanying drawing, above and other target, feature and the advantage of the disclosure will
It becomes more fully apparent.Drawings discussed below is only some embodiments of the present disclosure, for the ordinary skill of this field
For personnel, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is the system scenarios frame of a kind of title text generation method shown according to an exemplary embodiment and device
Figure.
Fig. 2 is a kind of flow chart of title text generation method shown according to an exemplary embodiment.
Fig. 3 is a kind of flow chart of the title text generation method shown according to another exemplary embodiment.
Fig. 4 is a kind of flow chart of the title text generation method shown according to another exemplary embodiment.
Fig. 5 is a kind of block diagram of title text generating means shown according to an exemplary embodiment.
Fig. 6 is the block diagram of a kind of electronic equipment shown according to an exemplary embodiment.
Fig. 7 is that a kind of computer readable storage medium schematic diagram is shown according to an exemplary embodiment.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be real in a variety of forms
It applies, and is not understood as limited to embodiment set forth herein；On the contrary, thesing embodiments are provided so that the disclosure will be comprehensively and complete
It is whole, and the design of example embodiment is comprehensively communicated to those skilled in the art.Identical appended drawing reference indicates in figure
Same or similar part, thus repetition thereof will be omitted.
In addition, described feature, structure or characteristic can be incorporated in one or more implementations in any suitable manner
In example.In the following description, many details are provided to provide and fully understand to embodiment of the disclosure.However,
It will be appreciated by persons skilled in the art that can with technical solution of the disclosure without one or more in specific detail,
Or it can be using other methods, constituent element, device, step etc..In other cases, it is not shown in detail or describes known side
Method, device, realization or operation are to avoid fuzzy all aspects of this disclosure.
Block diagram shown in the drawings is only functional entity, not necessarily must be corresponding with physically separate entity.
I.e., it is possible to realize these functional entitys using software form, or realized in one or more hardware modules or integrated circuit
These functional entitys, or these functional entitys are realized in heterogeneous networks and/or processor device and/or microcontroller device.
Flow chart shown in the drawings is merely illustrative, it is not necessary to including all content and operation/step,
It is not required to execute by described sequence.For example, some operation/steps can also decompose, and some operation/steps can close
And or part merge, therefore the sequence actually executed is possible to change according to the actual situation.
It should be understood that although herein various assemblies may be described using term first, second, third, etc., these groups
Part should not be limited by these terms.These terms are to distinguish a component and another component.Therefore, first group be discussed herein below
Part can be described as the second component without departing from the teaching of disclosure concept.As used herein, term " and/or " include associated
All combinations for listing any of project and one or more.
It will be understood by those skilled in the art that attached drawing is the schematic diagram of example embodiment, module or process in attached drawing
Necessary to not necessarily implementing the disclosure, therefore it cannot be used for the protection scope of the limitation disclosure.
Fig. 1 is the system scenarios frame of a kind of title text generation method shown according to an exemplary embodiment and device
Figure.
As shown in Figure 1, system architecture 100 may include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 to provide the medium of communication link.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 101,102,103 and be interacted by network 104 with server 105, to receive or send out
Send message etc..Various telecommunication customer end applications, such as the application of shopping class, net can be installed on terminal device 101,102,103
The application of page browsing device, searching class application, instant messaging tools, mailbox client, social platform software etc..
Terminal device 101,102,103 can be the various electronic equipments with display screen and supported web page browsing, packet
Include but be not limited to smart phone, tablet computer, pocket computer on knee and desktop computer etc..
User can be based on preset condition by terminal device 101,102,103 and obtain the first news data, terminal device
101,102,103 at least one second news data for example can be obtained based on first news data；Terminal device 101,
102,103 writing characteristic parameter for example can be determined based on target object；Terminal device 101,102,103 can be for example by the writing
Characteristic parameter and at least one second news data carry out Data Fusion to generate headline；And terminal device 101,
It 102,103 can be for example using the headline as the title text of first news data to be shown.
Terminal device 101,102,103 can also for example by history news data to the initial model of machine learning algorithm into
Row training is to obtain the data fusion model.
Server 105 can be to provide the server of various services, such as utilize terminal device 101,102,103 to user
The first acquired news data provides the background server supported.Server 105 can be to the first news data received
It carries out the processing such as analyzing, and processing result is fed back into terminal device.
User can obtain the first news data by terminal device 101,102,103, and terminal device 101,102,103 can example
It such as will acquire the first news data to be forwarded in server 105, server 105 can be obtained for example based on first news data
At least one second news data；Server 105 for example can determine writing characteristic parameter based on target object；Server 105 can
Such as the writing characteristic parameter and at least one second news data are subjected to Data Fusion to generate headline；With
And server 105 can be for example using the headline as the title text of first news data to be shown.
Server 105 can be also for example trained by initial model of the history news data to machine learning algorithm to obtain
Take the data fusion model.
Server 105 can be the server of an entity, also may be, for example, multiple server compositions, needs to illustrate
Be, title text generation method provided by the embodiment of the present disclosure can by server 105 and/or terminal device 101,102,
103 execute, and correspondingly, title text generating means can be set in server 105 and/or terminal device 101,102,103.
And the request end for being supplied to user's the first news data input of progress is normally in terminal device 101,102,103.
According to the title text generation method and device of the application, intelligence writing and personal presentation, and when foundation background into
The title of row fusion, generation has obvious timeliness and personal presentation.
Fig. 2 is a kind of flow chart of title text generation method shown according to an exemplary embodiment.Title text is raw
Step S202 to S210 is included at least at method 20.
As shown in Fig. 2, obtaining the first news data based on preset condition in S202.The preset condition includes timeliness
Condition, temperature condition, data source condition；
In one embodiment, based on preset condition obtain the first news data include following situations at least one: to real time new
The issuing time for hearing data carries out Screening Treatment, to filter out first news data for meeting aging condition；To real time new
The news temperature for hearing data carries out Screening Treatment, to filter out first news data for meeting temperature condition；And to reality
When news data distribution platform carry out Screening Treatment, to filter out first news data for meeting data source condition.
In S204, at least one second news data is obtained based on first news data.
In one embodiment, at least one second news data is obtained based on first news data to comprise determining that
The reversed viewpoint data of first news data；And it is based at least one second news number of the reversed viewpoint data acquisition
According to.
It more specifically, include: based on described anti-based on described at least one second news data of reversed viewpoint data acquisition
Keyword and/or key object are determined to viewpoint data；Obtain the associated data of first news data；And by described
Keyword and/or the key object extract at least one second news data in the associated data.
In one embodiment, the acquisition of reversed viewpoint data can be from the comment of news, with the keyword for centainly negating
Search is searched for as path, such as than more sensitive " no " or similar word, or by a user for opposition label.
In S206, writing characteristic parameter is determined based on target object.Can include: writing characteristic is passed through based on target object
Library determines the writing characteristic parameter；The writing characteristic library includes multiple various dimensions writing characteristics ginseng of multiple target objects
Number.
Wherein, the writing characteristic library including multiple authors, in writing characteristic library, the multidimensional including multiple authors can be established
Writing characteristic parameter is spent, various dimensions may include the common rhetoric mode of author, everyday words, place, even commonly use character relation etc..
It specifically can be for example, the various news manuscripts delivered by A author or other works documents acquisition various dimensions be write
Make characteristic parameter, specifically can be by word processor, the various news manuscripts or other works documents delivered A author
In each character be labeled, judge each character probability that perhaps word occurs by the more character of frequency of occurrence or
Word, the writing characteristic parameter as author A.
In one embodiment, TextRank(keyword extraction algorithm can also be passed through) extract the writing characteristic of author A
Parameter, TextRank is the link analysis technology at initial stage, after Google is commercially available unprecedented success, the algorithm
The computation model extremely paid close attention to as other search engines and academia.Important link analysis technologies many now be all
It is derived on the basis of PageRank algorithm.PageRank is a kind of method of grade/importance for presentation web page, is
For measuring the fine or not sole criterion an of website.Integrated Title mark and Keywords mark etc. all its
After his factor, it can be adjusted by PageRank as a result, those is made to have more the webpage of " grade/importance " in search result
Another website ranking is promoted, to improve the correlation and quality of search result.For its rank from 0 to 10 grade, 10 grades are full marks.
PR value is higher, and the explanation webpage is more welcome (more important).
Based on above thought, it can regard each word in A author's article as a website, assign different initial values
Later, the different grade of different words is determined by TextRank algorithm, to determine the writing characteristic parameter of A author.
In S208, the writing characteristic parameter and at least one second news data are subjected to Data Fusion with life
At headline.It can be for example, by the writing characteristic parameter and at least one second news data input data Fusion Model
To generate the headline.
In one embodiment, the writing characteristic parameter and at least one second news data are carried out at data fusion
Reason includes: to determine weight at least one described second news data to generate headline；By the writing characteristic parameter with
The data fusion model is inputted at least one second news data described in weight, obtains output data；And to institute
It states output data and carries out word processing to generate the headline.
It in one embodiment, may be, for example, that at least one described second news data determines weight；And it is write described
Make characteristic parameter and input the data fusion model at least one described second news data with weight, melts described in generation
Close news data.The initial news data that different data source obtains can have different weights, can such as website A be amount of reading
With the higher portal website of occupation rate of market, the website B is the high news platform of status grade, and the website C is small-scale to be applicable in
Forum can distribute higher weight then for the second news data of the website A and the website B, and the second news data of the website C, which is distributed, to be handed over
The weight at bottom, in favor of the amount of reading of the convergent journalism title ultimately generated.
In one embodiment, further includes: instructed by initial model of the history news data to machine learning algorithm
Practice to obtain the data fusion model.The content of this part will be described in detail in the corresponding embodiment of Fig. 4.
In S210, using the headline as the title text of first news data to be shown.Wherein,
The headline is proposed in the first news data in the form of question sentence.
It more specifically can be such as: the first news data are as follows: polybag pollutes environment；
The reversed viewpoint data determined based on first news data are as follows: polybag is free from environmental pollution；
The writing characteristic parameter and at least one second news data are carried out Data Fusion can to generate headline
Are as follows: macromolecule chemical combination not welding,
According to the title text generation method of the disclosure, at least one second news number is obtained based on first news data
According to；Writing characteristic parameter is determined based on target object；The writing characteristic parameter and at least one second news data are carried out
Data Fusion can quickly generate the news with personal characteristics and interest in a manner of generating headline automatically
Title.
It will be clearly understood that the present disclosure describes how to form and use particular example, but the principle of the disclosure is not limited to
These exemplary any details.On the contrary, the introduction based on disclosure disclosure, these principles can be applied to many other
Embodiment.
Fig. 3 is a kind of flow chart of the title text generation method shown according to another exemplary embodiment.It is shown in Fig. 3
Process 30 is to S204 in process shown in Fig. 2 " obtaining at least one second news data based on first news data "
Detailed description.
As shown in figure 3, determining the reversed viewpoint data of first news data in S302.It can be for example from news
In comment, with centainly negate keyword search as path, such as than more sensitive " no " or similar word, or by point
Oppose that the user of label searches for and then obtain reversed viewpoint data.
In S304, keyword and/or key object are determined based on the reversed viewpoint data.It can be to the second news data
Semantic analysis is carried out, to extract the keyword in the second news data.It in one embodiment, can be for example new by obtaining second
The mode of keyword in news determines the viewpoint in the first news data.The extraction of keyword: TF- can be carried out by the following method
IDF,TextRank,Rake,Topic-Model.Wherein, the keyword in the first news data, TF- are determined by TF-IDF
The basic thought of IDF is: the importance of word is directly proportional to the number that it occurs hereof, but simultaneously can be as it is in corpus
The frequency occurred in library is inversely proportional decline.
In one embodiment, key object may be, for example, the user for holding reversed viewpoint.
In one embodiment, the first news data may be, for example, real-time hot news data, can pass through text semanteme point
The mode of analysis extracts the viewpoint in the first news data.After determining the viewpoint in the first news, it can also continue to pass through key
The mode of word determines the reversed viewpoint of the first news data.It can be for example, the keyword in the first news data be " plastics ", " product
Pole ", " pollution ", then the reversed viewpoint data of the first news may be, for example, " passiveness ", " environmental protection " etc..
In S306, the associated data of first news data is obtained.The associated data of first news can for and first
Data have other Website News data of same keyword.
In S308, at least one is extracted in the associated data by the keyword and/or the key object
Second news data.Based on the keyword and/or the key object, the news datas of other websites is extracted using as second
News data.
More specifically, multiple second news datas are extracted in multiple websites, can be multiple by the reading quantity of news
News data is ranked up, and forward multiple second news datas of preferential selected and sorted are to make subsequent processing.
Fig. 4 is a kind of flow chart of the title text generation method shown according to another exemplary embodiment.It is shown in Fig. 4
Process 40 is to " being trained by initial model of the history news data to machine learning algorithm to obtain the data and melt
The detailed description of molding type ".
As shown in figure 4, obtaining multiple training datas by history news data in S402.
In S404, the training data is labeled to generate training set data and verifying collection data.
In S406, it will be trained in the initial model of training set data input machine learning algorithm, pass through institute
It states verifying collection data and tune ginseng is carried out to training result.
In S408, the data fusion model is obtained after training.
In the training process of machine mould, it can split data into:
Training set (Training Set): helping training pattern, is briefly exactly to determine that fitting is bent by the data of training set
The parameter of line.
Verifying collection (Validation Set): for doing model selection (model selection), that is, the final of model is done
Optimization and determine, for the building of submodel
Then data mark is carried out to data, data are labeled as training sample and label.Label may be, for example, in the present embodiment
Merge correct label with merge error label.
Above-mentioned data are input in machine learning model, the data fusion model is obtained by machine learning model.
Wherein, the machine learning model in the application may be, for example: supervised learning and unsupervised learning two major classes.
Supervised learning can include: linear classifier (such as LR), support vector machines (SVM), naive Bayesian (NB), k nearest neighbor
(KNN), decision tree (DT), integrated model (RF/GDBT etc.)；Linear regression, k nearest neighbor (KNN), returns support vector machines (SVM)
Set (DT), integrated model (ExtraTrees/RF/GDBT)
Unsupervised learning can include: data clusters (K-means)/Data Dimensionality Reduction (PCA) etc..
According to the title text generation method of the disclosure, by way of machine learning model, write in conjunction with intelligence and a
People's characteristic, and background is merged when foundation, has obvious timeliness and personal presentation, content has individual character and timeliness
It will be appreciated by those skilled in the art that realizing that all or part of the steps of above-described embodiment is implemented as by CPU execution
Computer program.When the computer program is executed by CPU, above-mentioned function defined by the above method that the disclosure provides is executed
Energy.The program can store in a kind of computer readable storage medium, which can be read-only memory, magnetic
Disk or CD etc..
Further, it should be noted that above-mentioned attached drawing is only the place according to included by the method for disclosure exemplary embodiment
Reason schematically illustrates, rather than limits purpose.It can be readily appreciated that above-mentioned processing shown in the drawings is not indicated or is limited at these
The time sequencing of reason.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
Following is embodiment of the present disclosure, can be used for executing embodiments of the present disclosure.It is real for disclosure device
Undisclosed details in example is applied, embodiments of the present disclosure is please referred to.
Fig. 5 is a kind of block diagram of title text generating means shown according to an exemplary embodiment.As shown in figure 5, mark
Inscribing text generating apparatus 50 includes: the first news template 502, the second news template 504, characteristic parameter module 506, data fusion
Module 508 and news display module 510.
First news template 502 is used to obtain the first news data based on preset condition；The preset condition includes timeliness
Condition, temperature condition, data source condition；
In one embodiment, based on preset condition obtain the first news data include following situations at least one: to real time new
The issuing time for hearing data carries out Screening Treatment, to filter out first news data for meeting aging condition；To real time new
The news temperature for hearing data carries out Screening Treatment, to filter out first news data for meeting temperature condition；And to reality
When news data distribution platform carry out Screening Treatment, to filter out first news data for meeting data source condition.
Second news template 504 is used to obtain at least one second news data based on first news data；Include:
Determine the reversed viewpoint data of first news data；And at least one is second new based on the reversed viewpoint data acquisition
Hear data.
It more specifically, include: based on described anti-based on described at least one second news data of reversed viewpoint data acquisition
Keyword and/or key object are determined to viewpoint data；Obtain the associated data of first news data；And by described
Keyword and/or the key object extract at least one second news data in the associated data.
Characteristic parameter module 506 is used to determine writing characteristic parameter based on target object；Can include: it is logical based on target object
It crosses writing characteristic library and determines the writing characteristic parameter；The writing characteristic library includes that multiple various dimensions of multiple target objects are write
Make characteristic parameter.
Data fusion module 508 is used to the writing characteristic parameter carrying out data at least one second news data to melt
Processing is closed to generate headline；It can be for example, by the writing characteristic parameter and at least one second news data input data
To generate the headline in Fusion Model.
In one embodiment, the writing characteristic parameter and at least one second news data are carried out at data fusion
Reason includes: to determine weight at least one described second news data to generate headline；By the writing characteristic parameter with
The data fusion model is inputted at least one second news data described in weight, obtains output data；And to institute
It states output data and carries out word processing to generate the headline.
News display module 510 is used for using the headline as the title text of first news data to carry out
It shows.Wherein, the headline is proposed in the first news data in the form of question sentence.
According to the title text generating means of the disclosure, at least one second news is obtained based on first news data
Data；Writing characteristic parameter is determined based on target object；By the writing characteristic parameter and at least one second news data into
Row Data Fusion can be generated quickly new with personal characteristics and interest automatically in a manner of generating headline
Hear title.
Fig. 6 is the block diagram of a kind of electronic equipment shown according to an exemplary embodiment.
The electronic equipment 200 of this embodiment according to the disclosure is described referring to Fig. 6.The electronics that Fig. 6 is shown
Equipment 200 is only an example, should not function to the embodiment of the present disclosure and use scope bring any restrictions.
As shown in fig. 6, electronic equipment 200 is showed in the form of universal computing device.The component of electronic equipment 200 can wrap
It includes but is not limited to: at least one processing unit 210, at least one storage unit 220, (including the storage of the different system components of connection
Unit 220 and processing unit 210) bus 230, display unit 240 etc..
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 210
Row, so that the processing unit 210 executes described in this specification above-mentioned electronic prescription circulation processing method part according to this
The step of disclosing various illustrative embodiments.For example, the processing unit 210 can be executed such as Fig. 2, Fig. 3, shown in Fig. 4
The step of.
The storage unit 220 may include the readable medium of volatile memory cell form, such as random access memory
Unit (RAM) 2201 and/or cache memory unit 2202 can further include read-only memory unit (ROM) 2203.
The storage unit 220 can also include program/practical work with one group of (at least one) program module 2205
Tool 2204, such program module 2205 includes but is not limited to: operating system, one or more application program, other programs
It may include the realization of network environment in module and program data, each of these examples or certain combination.
Bus 230 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 200 can also be with one or more external equipment 300(such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 200 communicate, and/or with make
Any equipment (such as the router, modulation /demodulation that the electronic equipment 200 can be communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 250.Also, electronic equipment 200 can be with
By network adapter 260 and one or more network (such as Local Area Network, wide area network (WAN) and/or public network,
Such as internet) communication.Network adapter 260 can be communicated by bus 230 with other modules of electronic equipment 200.It should
Understand, although not shown in the drawings, other hardware and/or software module can be used in conjunction with electronic equipment 200, including but unlimited
In: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and number
According to backup storage system etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server or network equipment etc.) executes the above method according to disclosure embodiment.
Fig. 7 schematically shows a kind of computer readable storage medium schematic diagram in disclosure exemplary embodiment.
Refering to what is shown in Fig. 7, describing the program product for realizing the above method according to embodiment of the present disclosure
400, can using portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device,
Such as it is run on PC.However, the program product of the disclosure is without being limited thereto, in this document, readable storage medium storing program for executing can be with
To be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
It is in connection.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random-access memory (ram), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
The computer readable storage medium may include in a base band or the data as the propagation of carrier wave a part are believed
Number, wherein carrying readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetism
Signal, optical signal or above-mentioned any appropriate combination.Readable storage medium storing program for executing can also be any other than readable storage medium storing program for executing
Readable medium, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or
Person's program in connection.The program code for including on readable storage medium storing program for executing can transmit with any suitable medium, packet
Include but be not limited to wireless, wired, optical cable, RF etc. or above-mentioned any appropriate combination.
Can with any combination of one or more programming languages come write for execute the disclosure operation program
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and executes in equipment, partly executes on a user device, being executed as an independent software package, partially in user's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including Local Area Network or wide area network
(WAN), it is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
Above-mentioned computer-readable medium carries one or more program, when said one or multiple programs are by one
When the equipment executes, so that the computer-readable medium implements function such as: obtaining the first news data based on preset condition；Base
At least one second news data is obtained in first news data；Writing characteristic parameter is determined based on target object；By institute
It states writing characteristic parameter and at least one second news data carries out Data Fusion to generate headline；And it will be described
Headline as first news data title text to be shown.
It will be appreciated by those skilled in the art that above-mentioned each module can be distributed in device according to the description of embodiment, it can also
Uniquely it is different from one or more devices of the present embodiment with carrying out corresponding change.The module of above-described embodiment can be merged into
One module, can also be further split into multiple submodule.
By the description of above embodiment, those skilled in the art is it can be readily appreciated that example embodiment described herein
It can also be realized in such a way that software is in conjunction with necessary hardware by software realization.Therefore, implemented according to the disclosure
The technical solution of example can be embodied in the form of software products, which can store in a non-volatile memories
In medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) or on network, including some instructions are so that a calculating equipment (can
To be personal computer, server, mobile terminal or network equipment etc.) it executes according to the method for the embodiment of the present disclosure.
It is particularly shown and described the exemplary embodiment of the disclosure above.It should be appreciated that the present disclosure is not limited to
Detailed construction, set-up mode or implementation method described herein；On the contrary, disclosure intention covers included in appended claims
Various modifications and equivalence setting in spirit and scope.
In addition, structure shown by this specification Figure of description, ratio, size etc., only to cooperate specification institute
Disclosure, for skilled in the art realises that be not limited to the enforceable qualifications of the disclosure with reading, therefore
Do not have technical essential meaning, the modification of any structure, the change of proportionate relationship or the adjustment of size are not influencing the disclosure
Under the technical effect and achieved purpose that can be generated, it should all still fall in technology contents disclosed in the disclosure and obtain and can cover
In the range of.Meanwhile cited such as "upper" in this specification, " first ", " second " and " one " term, be also only and be convenient for
Narration is illustrated, rather than to limit the enforceable range of the disclosure, relativeness is altered or modified, without substantive change
Under technology contents, when being also considered as the enforceable scope of the disclosure.
Claims (10)
1. a kind of title text generation method characterized by comprising
The first news data is obtained based on preset condition；
At least one second news data is obtained based on first news data；
Writing characteristic parameter is determined based on target object；
The writing characteristic parameter and at least one second news data are subjected to Data Fusion to generate headline；With
And
Using the headline as the title text of first news data to be shown.
2. the method as described in claim 1, which is characterized in that the preset condition includes aging condition, temperature condition, data
Source condition；
Based on preset condition obtain the first news data include following situations at least one:
Screening Treatment is carried out to the issuing time of real-time news data, to filter out the first news number for meeting aging condition
According to；
Screening Treatment is carried out to the news temperature of real-time news data, to filter out the first news number for meeting temperature condition
According to；And
Screening Treatment is carried out to the distribution platform of real-time news data, to filter out first news for meeting data source condition
Data.
3. the method as described in claim 1, which is characterized in that it is second new to obtain at least one based on first news data
Hearing data includes:
Determine the reversed viewpoint data of first news data；And
Based on described at least one second news data of reversed viewpoint data acquisition.
4. the method as described in claim 1, which is characterized in that determine that writing characteristic parameter includes: based on target object
The writing characteristic parameter is determined by writing characteristic library based on target object；
The writing characteristic library includes multiple various dimensions writing characteristic parameters of multiple target objects.
5. the method as described in claim 1, which is characterized in that by the writing characteristic parameter and at least one second news number
Include: according to Data Fusion is carried out to generate headline
By in the writing characteristic parameter and at least one second news data input data Fusion Model to generate the news
Title.
6. method as claimed in claim 5, which is characterized in that by the writing characteristic parameter and at least one second news number
Include: according to Data Fusion is carried out to generate headline
Weight is determined at least one described second news data；
The writing characteristic parameter is inputted into the data fusion mould with at least one second news data described in weight
Type obtains output data；And
Word processing is carried out to generate the headline to the output data.
7. method as claimed in claim 5, which is characterized in that further include:
It is trained by initial model of the history news data to machine learning algorithm to obtain the data fusion model.
8. a kind of title text generating means characterized by comprising
First news template, for obtaining the first news data based on preset condition；
Second news template, for obtaining at least one second news data based on first news data；
Characteristic parameter module, for determining writing characteristic parameter based on target object；
Data fusion module, for the writing characteristic parameter and at least one second news data to be carried out Data Fusion
To generate headline；And
News display module, for using the headline as the title text of first news data to be shown.
9. a kind of electronic equipment characterized by comprising
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now method as described in any in claim 1-7.
10. a kind of computer-readable medium, is stored thereon with computer program, which is characterized in that described program is held by processor
The method as described in any in claim 1-7 is realized when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910235235.1A CN110516227A (en) | 2019-03-28 | 2019-03-28 | Title text generation method, device, electronic equipment and computer-readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910235235.1A CN110516227A (en) | 2019-03-28 | 2019-03-28 | Title text generation method, device, electronic equipment and computer-readable medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110516227A true CN110516227A (en) | 2019-11-29 |
Family
ID=68622489
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910235235.1A Pending CN110516227A (en) | 2019-03-28 | 2019-03-28 | Title text generation method, device, electronic equipment and computer-readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110516227A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112307176A (en) * | 2020-03-09 | 2021-02-02 | 北京字节跳动网络技术有限公司 | Method and device for guiding user to write |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101751455A (en) * | 2009-12-31 | 2010-06-23 | 浙江大学 | Method for automatically generating title by adopting artificial intelligence technology |
| CN105786853A (en) * | 2014-12-22 | 2016-07-20 | 北京奇虎科技有限公司 | Display method and system for smart abstract of forum post |
| CN106959945A (en) * | 2017-03-23 | 2017-07-18 | 北京百度网讯科技有限公司 | The method and apparatus that slug is generated for news based on artificial intelligence |
| CN106970898A (en) * | 2017-03-31 | 2017-07-21 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating article |
| CN106997370A (en) * | 2015-08-07 | 2017-08-01 | 谷歌公司 | Text classification and conversion based on author |
| US20170221105A1 (en) * | 2016-02-01 | 2017-08-03 | International Business Machines Corporation | Online article headline generation |
| CN108460150A (en) * | 2018-03-23 | 2018-08-28 | 北京奇虎科技有限公司 | The processing method and processing device of headline |
| CN108491512A (en) * | 2018-03-23 | 2018-09-04 | 北京奇虎科技有限公司 | The method of abstracting and device of headline |
| 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 |
| CN108932335A (en) * | 2018-07-10 | 2018-12-04 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus generating official documents and correspondence |
| CN109446505A (en) * | 2018-10-31 | 2019-03-08 | 广东小天才科技有限公司 | A kind of model essay generation method and system |
| CN109492112A (en) * | 2018-10-24 | 2019-03-19 | 北京百科康讯科技有限公司 | A kind of method of the computer aided writing scientific popular article of knowledge based map |
-
2019
- 2019-03-28 CN CN201910235235.1A patent/CN110516227A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101751455A (en) * | 2009-12-31 | 2010-06-23 | 浙江大学 | Method for automatically generating title by adopting artificial intelligence technology |
| CN105786853A (en) * | 2014-12-22 | 2016-07-20 | 北京奇虎科技有限公司 | Display method and system for smart abstract of forum post |
| CN106997370A (en) * | 2015-08-07 | 2017-08-01 | 谷歌公司 | Text classification and conversion based on author |
| US20170221105A1 (en) * | 2016-02-01 | 2017-08-03 | International Business Machines Corporation | Online article headline generation |
| CN106959945A (en) * | 2017-03-23 | 2017-07-18 | 北京百度网讯科技有限公司 | The method and apparatus that slug is generated for news based on artificial intelligence |
| CN106970898A (en) * | 2017-03-31 | 2017-07-21 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating article |
| 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 |
| CN108460150A (en) * | 2018-03-23 | 2018-08-28 | 北京奇虎科技有限公司 | The processing method and processing device of headline |
| CN108491512A (en) * | 2018-03-23 | 2018-09-04 | 北京奇虎科技有限公司 | The method of abstracting and device of headline |
| CN108932335A (en) * | 2018-07-10 | 2018-12-04 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus generating official documents and correspondence |
| CN109492112A (en) * | 2018-10-24 | 2019-03-19 | 北京百科康讯科技有限公司 | A kind of method of the computer aided writing scientific popular article of knowledge based map |
| CN109446505A (en) * | 2018-10-31 | 2019-03-08 | 广东小天才科技有限公司 | A kind of model essay generation method and system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112307176A (en) * | 2020-03-09 | 2021-02-02 | 北京字节跳动网络技术有限公司 | Method and device for guiding user to write |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11023505B2 (en) | Method and apparatus for pushing information | |
| Tang et al. | Patentminer: topic-driven patent analysis and mining | |
| CN109934721A (en) | Finance product recommended method, device, equipment and storage medium | |
| US11995409B2 (en) | Content generation using target content derived modeling and unsupervised language modeling | |
| CN104598607B (en) | Recommend the method and system of search phrase | |
| KR102355212B1 (en) | Browsing images via mined hyperlinked text snippets | |
| CN109918653B (en) | Training method, device and equipment for determining related topics and model of text data | |
| Zhao et al. | A context-based framework for resource citation classification in scientific literatures | |
| Munne et al. | Entity alignment via summary and attribute embeddings | |
| Bai et al. | A rumor detection model incorporating propagation path contextual semantics and user information | |
| CN110516227A (en) | Title text generation method, device, electronic equipment and computer-readable medium | |
| Shu et al. | Automatic extraction of web page text information based on network topology coincidence degree | |
| CN110110303A (en) | Newsletter archive generation method, device, electronic equipment and computer-readable medium | |
| Dziczkowski et al. | An opinion mining approach for web user identification and clients' behaviour analysis | |
| Kumar et al. | Sentiment analysis using bi-directional recurrent neural network for Telugu movies | |
| US11429687B2 (en) | Context based URL resource prediction and delivery | |
| US11120204B2 (en) | Comment-based article augmentation | |
| Zhang et al. | Answering product-related questions with heterogeneous information | |
| Gangurde et al. | Biogeography optimization algorithm based next web page prediction using weblog and web content features | |
| Wang | Personalized recommendation system based on vocal characteristics | |
| Saeidmehr et al. | Systematic review using a spiral approach with machine learning | |
| Kumar et al. | Diving into a sea of opinions: Multi-modal abstractive summarization with comment sensitivity | |
| Pagi et al. | Opinion content extraction from web pages using embedded semantic term tree kernels | |
| Moreno et al. | A Content-Based Multi Label Classification Model to Suggest Tags for Posts in Stack Overflow | |
| Singh | Information Retrieval Based on the Sequential Hypertext Induced Topic Search in Web Pages |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191129 |
|
| WD01 | Invention patent application deemed withdrawn after publication |