CN108920611B - Article generation method, device, equipment and storage medium - Google Patents
Article generation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN108920611B CN108920611B CN201810687705.3A CN201810687705A CN108920611B CN 108920611 B CN108920611 B CN 108920611B CN 201810687705 A CN201810687705 A CN 201810687705A CN 108920611 B CN108920611 B CN 108920611B
- Authority
- CN
- China
- Prior art keywords
- article
- target
- comment information
- module
- target article
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/12—Use of codes for handling textual entities
Abstract
The embodiment of the present application provides a kind of article generation method, device, equipment and storage medium, by obtaining target article and user to the comment information of the target article;Selected from the comment information of the target article one as target comment information;Based on preset abstract extraction tool, the clip Text of the target article is extracted;Article is generated based on the clip Text and the target comment information.Technical solution provided by the present application can be realized automatically generating for article, improve article formation efficiency, reduce cost of labor.
Description
Technical field
The invention relates to field of artificial intelligence more particularly to a kind of article generation method, device, equipment and
Storage medium.
Background technique
In the cybertimes of information overabundance, how high quality is provided for user in time, the article of high temperature is each network letter
Cease the focus that platform is concerned about.Current existing web documents generation method mainly includes two kinds, one is rely on body at one's own expense or
Writer is employed to go to write the article of high quality, another kind is to remove construction article in the way of semi-automatic, is constructed in article
Still there is part need of work manually to participate in the process, article formation efficiency is lower, higher cost, and is difficult to timely and accurately
The hot spot article that focus incident forms high temperature is held, timeliness is poor.
Summary of the invention
The embodiment of the present application provides a kind of article generation method, device, equipment and storage medium, to realize article from
It is dynamic to generate, article formation efficiency is improved, cost of labor is reduced.
The embodiment of the present application first aspect provides a kind of article generation method, comprising: obtains target article and user couple
The comment information of the target article;Selected from the comment information of the target article one as target comment information;Base
In preset abstract extraction tool, the clip Text of the target article is extracted;It is commented based on the clip Text and the target
Article is generated by information.
The embodiment of the present application second aspect provides a kind of article generating means, comprising: module is obtained, for obtaining target text
The comment information of chapter and user to the target article;Selecting module, for being selected from the comment information of the target article
It selects one and is used as target comment information;Extraction module extracts the target article for being based on preset abstract extraction tool
Clip Text;Article generation module, for generating article based on the clip Text and the target comment information.
The embodiment of the present application third aspect provides a kind of computer equipment, comprising: one or more processors;Storage dress
It sets, 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 realize the method as described in above-mentioned first aspect.
The embodiment of the present application fourth aspect provides a kind of computer readable storage medium, is stored thereon with computer program,
The method as described in above-mentioned first aspect is realized when the program is executed by processor.
Based on aspects above, the embodiment of the present application believes the comment of target article by obtaining target article and user
Breath selects one to extract target as target comment information, and based on abstract extraction tool from the comment information of target article
The clip Text of article, to generate article based on clip Text and target comment information.Shown due to the embodiment of the present application and is based on
The clip Text of the comment information of user and article automatically generates article, thus eliminates artificial in article generating process
Intervene, improves the formation efficiency of article, reduce cost of labor.In addition, due to can actively be obtained in the embodiment of the present application
Target article, and article is generated according to the comment information of target article and clip Text, therefore, it is possible to pass through setting target article
Acquisition modes improve the timeliness of the article of generation.
It should be appreciated that content described in foregoing invention content part is not intended to limit the pass of embodiments herein
Key or important feature, it is also non-for limiting scope of the present application.The other feature of this public affairs application will be become by description below
It is readily appreciated that.
Detailed description of the invention
Fig. 1 is a kind of flow chart of article generation method provided by the embodiments of the present application;
Fig. 2 is the execution method flow diagram of step S11 provided by the embodiments of the present application a kind of;
Fig. 3 is the execution method flow diagram of step S11 provided by the embodiments of the present application a kind of;
Fig. 4 is a kind of structural schematic diagram of article generating means provided by the embodiments of the present application;
Fig. 5 is a kind of structural schematic diagram for obtaining module 41 provided in this embodiment;
Fig. 6 is a kind of structural schematic diagram for obtaining module 41 provided in this embodiment.
Specific embodiment
Embodiments herein is more fully described below with reference to accompanying drawings.Although showing that the application's is certain in attached drawing
Embodiment, it should be understood that, the application can be realized by various forms, and should not be construed as being limited to this
In the embodiment that illustrates, providing these embodiments on the contrary is in order to more thorough and be fully understood by the application.It should be understood that
It is that being given for example only property of the accompanying drawings and embodiments effect of the application is not intended to limit the protection scope of the application.
The specification and claims of the embodiment of the present application and the term " first " in above-mentioned attached drawing, " second ", "
Three ", the (if present)s such as " 4th " are to be used to distinguish similar objects, without for describing specific sequence or successive time
Sequence.It should be understood that the data used in this way are interchangeable under appropriate circumstances, for example so as to the embodiment of the present application described herein
It can be performed in other sequences than those illustrated or described herein.In addition, term " includes " and " having " and he
Any deformation, it is intended that cover it is non-exclusive include, for example, contain the process, method of a series of steps or units,
System, product or equipment those of are not necessarily limited to be clearly listed step or unit, but may include being not clearly listed
Or the other step or units intrinsic for these process, methods, product or equipment.
By the introduction of background technology part it is found that the prior art is more or less required to manually in terms of web documents generation
It is participated in, cost of labor is higher, and the formation efficiency of article is lower.And it is limited by the ability that people obtains information, usually
Current focus incident can not be promptly and accurately got, thus can not also generate corresponding hot spot article based on focus incident,
The timeliness and popular degree that article generates are poor.
In view of the foregoing defects the prior art has, the embodiment of the present application is supplied to a kind of article generation method, the party
Method generates new article to the evaluation information of article according to the clip Text of article and user by obtaining article automatically,
To realize automatically generating for article, the manual intervention in article generating process is eliminated, the formation efficiency of article is improved,
Reduce cost of labor.And can also by being configured to specific article acquisition modes, come reach obtain hot spot article and
Its purpose commented on, thus the comment information of content and user based on hot spot article to the hot spot article, it will be able in time
New hot spot article is effectively generated, the timeliness and popular degree of article are improved.
The technical solution of the embodiment of the present application is specifically described below with reference to attached drawing.
Fig. 1 is a kind of flow chart of article generation method provided by the embodiments of the present application, and this method can be by a kind of article
Generating means execute.Referring to Fig. 1, the method comprising the steps of S11-S14:
S11, target article and user are obtained to the comment information of the target article.
Target article in the present embodiment refers to the article for meeting preset condition.Specifically meet as target article needs
What preset condition, which can according to need, is set, in the present embodiment without limitation.For example, in a kind of possible design,
Target article can be the article in preassigned website, chained address or microblog account.In alternatively possible design
In, target article can be the article including target keyword, wherein target keyword refers to that search rate is more than preset threshold
Keyword.Or in another possible design, target article can also be default microblog account it is of interest other are micro-
The article that rich account is issued.Certainly it is above-mentioned it is several it is possible design only to facilitate understand carried out illustrate without
It is uniquely to limit.In addition, it is necessary to illustrate, the target article in the present embodiment refers to an article rather than plurality of articles.?
That is the present embodiment is to generate new article to the comment information of this article based on the content of article and user.
In addition, for the comment information of target article, due to providing platform (such as microblogging, news website in general information
Deng) in the lower section of article releasing position can provide the comment plate of this article, user can be same to the comment information of article
It is obtained in the comment plate of article, that is to say, that user can be from target for the comment information of target article in the present embodiment
It is obtained in the corresponding comment plate of article.Certainly it is merely for convenience of understanding a kind of provided acquisition side of comment information here
Formula is not excluded for that other acquisition modes can also be used in other designs, that is to say, that the specific acquisition modes of comment information
It can according to need or concrete scene is set, rather than be limited only to a certain specific mode.
S12, selected from the comment information of the target article one as target comment information.
Wherein, the present embodiment method of selection target comment information from the comment information of target article may include as follows
It is several:
In a kind of possible design, most comment informations can will be thumbed up in all comment informations of target article
As target comment information.
In another possible design, it can will be responded most comments in all comment informations of target article and believe
Breath is used as target comment information.
In another possible design, preset scoring model can be inputted with the comment information of target article (for example, can
Using one scoring model for being used to give a mark to comment information of NB Algorithm training) in, by corresponding marking point
The highest comment information of number is as target comment information.
In another possible design, one can also be randomly choosed from the comment information of target article as target
Comment information.
Certainly above-mentioned several possible designs be intended merely to exemplary illustration how selection target comment information, rather than
Unique restriction to the application.In fact, which or which comment information is selected to can according to need as target comment information
It is set, and is not limited to another specific mode.
S13, it is based on preset abstract extraction tool, extracts the clip Text of the target article.
Wherein, abstract extraction tool is that one kind that the prior art provides can extract the tool of article abstract content,
Similarly to the prior art, therefore, specific extracting method is referred to the prior art, in the present embodiment for effect in the present embodiment
No longer repeated.
S14, article is generated based on the clip Text and the target comment information.
The present embodiment is generated newly by inputting preset template for the clip Text of target article and target comment information
Article.
The present embodiment is by obtaining target article and user to the comment information of target article, from the comment of target article
Selected in information one as target comment information, and based on abstract extraction tool extract target article clip Text, thus
Article is generated based on clip Text and target comment information.Since the present embodiment shows plucking for comment information based on user and article
Content is wanted to automatically generate article, thus eliminates the manual intervention in article generating process, improves the generation effect of article
Rate reduces cost of labor.In addition, by can actively obtain target article, and commenting according to target article in this present embodiment
Article is generated by information and clip Text, therefore, it is possible to improve the article of generation by the acquisition modes that target article is arranged
Timeliness.
Above-described embodiment is further optimized and extended with reference to the accompanying drawing.
Fig. 2 is the execution method flow diagram of step S11 provided by the embodiments of the present application a kind of, as shown in Fig. 2, in Fig. 1 reality
On the basis of applying example, the method comprising the steps of S21-S23:
S21, the first article including target keyword is obtained, wherein the search rate of the target keyword is more than default
Threshold value.
It, can be by being monitored to search engine in a kind of possible design, obtaining search rate is more than default threshold
The keyword of value is based on target keyword as target keyword, and obtaining from database or the network media includes target
The article of keyword, i.e. the first article.Even for treatment effeciency the considerations of, the present embodiment after getting above-mentioned article,
Similarity calculation can also be carried out between the title and target keyword of above-mentioned article, be more than the text of preset threshold by similarity
The first article of Zhang Zuowei.
In alternatively possible design, it can be based on statistical method, be more than by the number occurred in text library
The keyword of preset times, as target keyword, further, then obtaining from database or the network media includes target
The article of keyword is as the first article.
What needs to be explained here is that above two mode, uses merely to two kinds for clearly illustrating and enumerating are most possible
Mode, but not all mode.
If in S22, the first article including the target keyword including the chained address of other articles, described in acquisition
Second article corresponding to chained address.
As an example it is assumed that including the chained address of five other articles in article A, then this five links are loaded respectively
Address, to obtain article on this five chained addresses as the second article.Certainly it only illustrates rather than here pair
Unique restriction of we.
S23, an article is extracted as target from the article set that first article and second article are constituted
Article, and user is obtained to the comment information of the target article.
Wherein, in a kind of possible design, the present embodiment can be from the article collection of the first article and the second article composition
Click volume is extracted in conjunction in highest article as target article.
In alternatively possible design, the present embodiment can be constituted from the first article and the second article in article set with
Machine extracts an article as target article.
In another possible design, the present embodiment can be from the article set that the first article and the second article are constituted
The most article of the number being forwarded is extracted as target article.
What needs to be explained here is that above-mentioned several ways, merely to clear explanation and most possibly using for enumerating is several
Kind mode, but not all mode.
The present embodiment to include target of the search rate more than preset threshold in the first article by obtaining the first article
Keyword extracts the chained address of other articles from the first article, the second article on those chained addresses is obtained, from first
Select an article as target article in the article set that article and the second article are constituted.The present embodiment, which can ensure to extract, to be obtained
Target article in include hot information, realize and obtain hot spot article (i.e. target article) in time, based on hot spot article and
The comment information of hot spot article generates the purpose of new hot spot article.Improve the popular degree of the article of generation.
Fig. 3 is the execution method flow diagram of step S11 provided by the embodiments of the present application a kind of, as shown in figure 3, in Fig. 1 reality
On the basis of applying example, the method comprising the steps of S31-S32:
The article and/or the default microblog account that S31, the default microblog account of acquisition are issued microblog account of interest
The article of publication.
For example, can preset it is some from media or the microblog account of official media, by the way of periodically obtaining from
Article is obtained in those microblog accounts, and/or obtains article from those microblogging accounts microblog account of interest.Or it can also be with
According to the account of account and/or concern that preset microblog account and those microblog accounts are forwarded, account column are established
Table, periodically based on obtaining article from one or more accounts in account list.Certainly here merely to clear done
It illustrates rather than uniquely limits.
S32, one is selected from all articles got as target article, and obtain user to the target article
Comment information.
Wherein, the method for selection target article, which can according to need, is set, and is not specifically limited in the present embodiment.For
It being easy to understand, the property of can be exemplified is interpreted as selecting one from all articles and thumb up several highests in the present embodiment, or
Click volume highest, or the most article of number is commented on as target article.
The present embodiment microblogging account of interest by the article and/or default microblog account that obtain default microblog account publication
Number publication article, one is selected from all articles got as target article, can effectively widen target article
Channel is obtained, the rich of article is improved, provides strong guarantee to generate high quality articles.
Fig. 4 is a kind of structural schematic diagram of article generating means provided by the embodiments of the present application, as shown in figure 4, the device
40 include:
Module 41 is obtained, for obtaining target article and user to the comment information of the target article;
Selecting module 42, for selected from the comment information of the target article one as target comment information;
Extraction module 43 extracts the clip Text of the target article for being based on preset abstract extraction tool;
Article generation module 44, for generating article based on the clip Text and the target comment information.
In a kind of possible design, the selecting module 42, comprising:
Submodule of giving a mark beats correspondence for inputting the comment information of the target article in preset scoring model
Divide the highest comment information of score as target comment information.
The device 40 that the present embodiment passes through can be used in executing the scheme of Fig. 1 embodiment, executive mode and beneficial effect
It is similar, it repeats no more herein.
Fig. 5 is a kind of structural schematic diagram for obtaining module 41 provided in this embodiment, as shown in figure 5, in Fig. 4 embodiment
On the basis of, obtain module 41, comprising:
First acquisition submodule 411, for obtaining the first article including target keyword, wherein the target keyword
Search rate be more than preset threshold;
Second acquisition submodule 412, for including the link of other articles in the first article of the target keyword
When address, the second article corresponding to the chained address is obtained;
First extracting sub-module 413, for being mentioned from the article set that first article and second article are constituted
It takes an article as target article, and obtains user to the comment information of the target article.
In a kind of possible design, first extracting sub-module 413 specifically can be used for:
The highest article conduct of click volume is extracted from the article set that first article and second article are constituted
Target article.
Device provided in this embodiment can be used in executing the technical solution of Fig. 2 embodiment, executive mode and beneficial effect
Fruit seemingly, repeats no more herein.
Fig. 6 is a kind of structural schematic diagram for obtaining module 41 provided in this embodiment, as shown in fig. 6, in Fig. 4 embodiment
On the basis of, obtain module 41, comprising:
Third acquisition submodule 414, for obtaining the article and/or the default microblogging account that default microblog account is issued
The article of number microblog account of interest publication;
Second extracting sub-module 415 and is obtained for selecting one from all articles got as target article
Comment information of the user to the target article.
Wherein, in a kind of possible design, second extracting sub-module 415 specifically can be used for:
Selecting one to thumb up several highests from all articles got, perhaps click volume highest or comment number are most
Article as target article.
Device provided in this embodiment can be used in executing the technical solution of Fig. 3 embodiment, executive mode and beneficial effect
Fruit seemingly, repeats no more herein.
The embodiment of the present application also provides a kind of computer equipment, comprising: one or more processors;
Storage device, for storing one or more programs, when one or more of programs are one or more of
Processor executes, so that one or more of processors realize method described in any of the above-described embodiment.
The embodiment of the present application is also provided in a kind of computer readable storage medium, is stored thereon with computer program, the journey
Method described in any of the above-described embodiment is realized when sequence is executed by processor.
Function described herein can be executed at least partly by one or more hardware logic components.Example
Such as, without limitation, the hardware logic component for the exemplary type that can be used includes: field programmable gate array (FPGA), dedicated
Integrated circuit (ASIC), Application Specific Standard Product (ASSP), the system (SOC) of system on chip, load programmable logic device
(CPLD) etc..
For implement disclosed method program code can using any combination of one or more programming languages come
It writes.These program codes can be supplied to the place of general purpose computer, special purpose computer or other programmable data processing units
Device or controller are managed, so that program code makes defined in flowchart and or block diagram when by processor or controller execution
Function/operation is carried out.Program code can be executed completely on machine, partly be executed on machine, as stand alone software
Is executed on machine and partly execute or executed on remote machine or server completely on the remote machine to packet portion.
In the context of the disclosure, machine readable media can be tangible medium, may include or is stored for
The program that instruction execution system, device or equipment are used or is used in combination with instruction execution system, device or equipment.Machine can
Reading medium can be machine-readable signal medium or machine-readable storage medium.Machine readable media can include but is not limited to electricity
Son, magnetic, optical, electromagnetism, infrared or semiconductor system, device or equipment or above content any conjunction
Suitable combination.The more specific example of machine readable storage medium will include the electrical connection of line based on one or more, portable meter
Calculation machine disk, hard disk, random access memory (RAM), read-only memory (ROM), Erasable Programmable Read Only Memory EPROM (EPROM
Or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage facilities or
Any appropriate combination of above content.
Although this should be understood as requiring operating in this way with shown in addition, depicting each operation using certain order
Certain order out executes in sequential order, or requires the operation of all diagrams that should be performed to obtain desired result.
Under certain environment, multitask and parallel processing be may be advantageous.Similarly, although containing several tools in being discussed above
Body realizes details, but these are not construed as the limitation to the scope of the present disclosure.In the context of individual embodiment
Described in certain features can also realize in combination in single realize.On the contrary, in the described in the text up and down individually realized
Various features can also realize individually or in any suitable subcombination in multiple realizations.
Although having used specific to this theme of the language description of structure feature and/or method logical action, answer
When understanding that theme defined in the appended claims is not necessarily limited to special characteristic described above or movement.On on the contrary,
Special characteristic described in face and movement are only to realize the exemplary forms of claims.
Claims (10)
1. a kind of article generation method characterized by comprising
Target article and user are obtained to the comment information of the target article;
Selected from the comment information of the target article one as target comment information;
Based on preset abstract extraction tool, the clip Text of the target article is extracted;
Article is generated based on the clip Text and the target comment information;
Wherein, it is described selected from the comment information of the target article one as target comment information, comprising:
The comment information of the target article is inputted in preset scoring model, by the corresponding highest comment information of score of giving a mark
As target comment information;
It is wherein, described to obtain target article and user to the comment information of the target article, comprising:
The first article including target keyword is obtained, wherein the search rate of the target keyword is more than preset threshold;
If including the chained address of other articles in the first article including the target keyword, the chained address is obtained
The second corresponding article;
An article is extracted from the article set that first article and second article are constituted as target article, and is obtained
Family is taken to the comment information of the target article.
2. the method according to claim 1, wherein described constituted from first article and second article
Article set in extract an article as target article, comprising:
The highest article of click volume is extracted from the article set that first article and second article are constituted as target
Article.
3. the method according to claim 1, wherein the acquisition target article and user are to the target text
The comment information of chapter, comprising:
The text of the article and/or the default microblog account that the default microblog account of acquisition is issued microblog account publication of interest
Chapter;
One is selected from all articles got as target article, and obtains user and the comment of the target article is believed
Breath.
4. according to the method described in claim 3, it is characterized in that, it is described selected from all articles got one as
Target article, comprising:
One is selected to thumb up several highests perhaps click volume highest or the most text of comment number from all articles got
Zhang Zuowei target article.
5. a kind of article generating means characterized by comprising
Module is obtained, for obtaining target article and user to the comment information of the target article;
Selecting module, for selected from the comment information of the target article one as target comment information;
Extraction module extracts the clip Text of the target article for being based on preset abstract extraction tool;
Article generation module, for generating article based on the clip Text and the target comment information;
Wherein, the selecting module, comprising:
Submodule of giving a mark divides corresponding marking for inputting the comment information of the target article in preset scoring model
The highest comment information of number is as target comment information;
Wherein, the acquisition module, comprising:
First acquisition submodule, for obtaining the first article including target keyword, wherein the search of the target keyword
Frequency is more than preset threshold;
Second acquisition submodule, when for including the chained address of other articles in the first article of the target keyword,
Obtain the second article corresponding to the chained address;
First extracting sub-module, for extracting a text from the article set that first article and second article are constituted
Zhang Zuowei target article, and user is obtained to the comment information of the target article.
6. device according to claim 5, which is characterized in that first extracting sub-module is specifically used for:
The highest article of click volume is extracted from the article set that first article and second article are constituted as target
Article.
7. device according to claim 5, which is characterized in that the acquisition module, comprising:
Third acquisition submodule, the article and/or the default microblog account for obtaining default microblog account publication are of interest
Microblog account publication article;
Second extracting sub-module and obtains user couple for selecting one from all articles got as target article
The comment information of the target article.
8. device according to claim 7, which is characterized in that second extracting sub-module is specifically used for:
One is selected to thumb up several highests perhaps click volume highest or the most text of comment number from all articles got
Zhang Zuowei target article.
9. a kind of computer equipment characterized by comprising
One or more processors;
Storage device, for storing one or more programs, when one or more of programs are by one or more of processing
Device executes, so that one or more of processors realize such as method of any of claims 1-4.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
Such as method of any of claims 1-4 is realized when execution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810687705.3A CN108920611B (en) | 2018-06-28 | 2018-06-28 | Article generation method, device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810687705.3A CN108920611B (en) | 2018-06-28 | 2018-06-28 | Article generation method, device, equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108920611A CN108920611A (en) | 2018-11-30 |
CN108920611B true CN108920611B (en) | 2019-10-01 |
Family
ID=64421950
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810687705.3A Active CN108920611B (en) | 2018-06-28 | 2018-06-28 | Article generation method, device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108920611B (en) |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109657043B (en) * | 2018-12-14 | 2022-01-04 | 北京百度网讯科技有限公司 | Method, device and equipment for automatically generating article and storage medium |
CN110245334B (en) * | 2019-06-25 | 2023-06-16 | 北京百度网讯科技有限公司 | Method and device for outputting information |
CN110688832B (en) * | 2019-10-10 | 2023-06-09 | 河北省讯飞人工智能研究院 | Comment generation method, comment generation device, comment generation equipment and storage medium |
CN112560461A (en) * | 2020-12-11 | 2021-03-26 | 北京百度网讯科技有限公司 | News clue generation method and device, electronic equipment and storage medium |
CN112948706B (en) * | 2021-01-21 | 2023-01-31 | 上海观察者信息技术有限公司 | Article generation method and device based on comment recommendation and storage medium |
CN112883716B (en) * | 2021-02-03 | 2022-05-03 | 重庆邮电大学 | Twitter abstract generation method based on topic correlation |
CN113239309A (en) * | 2021-06-15 | 2021-08-10 | 广州聚焦网络技术有限公司 | Content creation method and device suitable for marketing promotion |
CN114417808B (en) * | 2022-02-25 | 2023-04-07 | 北京百度网讯科技有限公司 | Article generation method and device, electronic equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8515828B1 (en) * | 2012-05-29 | 2013-08-20 | Google Inc. | Providing product recommendations through keyword extraction from negative reviews |
CN103957275A (en) * | 2014-05-19 | 2014-07-30 | 北京奇虎科技有限公司 | Pushing method, client terminal, server and system for user commenting information |
CN106294425A (en) * | 2015-05-26 | 2017-01-04 | 富泰华工业(深圳)有限公司 | The automatic image-text method of abstracting of commodity network of relation article and system |
CN108153723A (en) * | 2017-12-27 | 2018-06-12 | 北京百度网讯科技有限公司 | Hot spot information comment generation method, device and terminal device |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107291780B (en) * | 2016-04-12 | 2021-05-28 | 腾讯科技(深圳)有限公司 | User comment information display method and device |
CN107391729B (en) * | 2017-08-02 | 2018-09-04 | 掌阅科技股份有限公司 | Sort method, electronic equipment and the computer storage media of user comment |
CN107657056B (en) * | 2017-10-18 | 2022-02-18 | 北京百度网讯科技有限公司 | Method and device for displaying comment information based on artificial intelligence |
-
2018
- 2018-06-28 CN CN201810687705.3A patent/CN108920611B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8515828B1 (en) * | 2012-05-29 | 2013-08-20 | Google Inc. | Providing product recommendations through keyword extraction from negative reviews |
CN103957275A (en) * | 2014-05-19 | 2014-07-30 | 北京奇虎科技有限公司 | Pushing method, client terminal, server and system for user commenting information |
CN106294425A (en) * | 2015-05-26 | 2017-01-04 | 富泰华工业(深圳)有限公司 | The automatic image-text method of abstracting of commodity network of relation article and system |
CN108153723A (en) * | 2017-12-27 | 2018-06-12 | 北京百度网讯科技有限公司 | Hot spot information comment generation method, device and terminal device |
Also Published As
Publication number | Publication date |
---|---|
CN108920611A (en) | 2018-11-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108920611B (en) | Article generation method, device, equipment and storage medium | |
CN106934012B (en) | Natural language question-answering implementation method and system based on knowledge graph | |
CN105095211B (en) | The acquisition methods and device of multi-medium data | |
CN107025239B (en) | Sensitive word filtering method and device | |
CN109800431B (en) | Event information keyword extracting and monitoring method and system and storage and processing device | |
CN106776574B (en) | User comment text mining method and device | |
CN106033416A (en) | A string processing method and device | |
CN104750705A (en) | Information returning method and device | |
JP6526470B2 (en) | Pre-construction method of vocabulary semantic patterns for text analysis and response system | |
CN103077163B (en) | Data preprocessing method, device and system | |
CN109960814B (en) | Model parameter searching method and device | |
CN109684402A (en) | One kind being based on big data platform metadata genetic connection implementation method | |
CN103500158A (en) | Method and device for annotating electronic document | |
Mane et al. | Predicting student admission decisions by association rule mining with pattern growth approach | |
Vishwakarma et al. | A comparative study of K-means and K-medoid clustering for social media text mining | |
CN110263021B (en) | Theme library generation method based on personalized label system | |
JP6365274B2 (en) | Common operation information generation program, common operation information generation method, and common operation information generation device | |
CN105488105A (en) | Establishment method for information extraction template and knowledge data processing method and apparatus | |
CN106844553B (en) | Data detection and expansion method and device based on sample data | |
KR101761177B1 (en) | Method for mining important pattern of high rank k, apparatus performing the same and storage medium storing the same | |
CN103778220A (en) | Decision support method and device based on cloud computing | |
CN104298975B (en) | A kind of distributed image recognition methods | |
CN104820661A (en) | Exploratory data analysis system based on business object | |
CN106933797B (en) | Target information generation method and device | |
JP2009181301A (en) | Expression template generating system, its method, and its program |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |