CN103389975A - News recommending method and system - Google Patents
News recommending method and system Download PDFInfo
- Publication number
- CN103389975A CN103389975A CN2012101376287A CN201210137628A CN103389975A CN 103389975 A CN103389975 A CN 103389975A CN 2012101376287 A CN2012101376287 A CN 2012101376287A CN 201210137628 A CN201210137628 A CN 201210137628A CN 103389975 A CN103389975 A CN 103389975A
- Authority
- CN
- China
- Prior art keywords
- news
- current demonstration
- subject data
- theme
- match
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention is applied to the field of network technologies and provides a news recommending method and system. The method comprises the steps of: acquiring subject data of news which is currently displayed by a terminal; in a default subject search library, matching related news corresponding to the subject data; and displaying the matched related news in a read page of the currently displayed news. According to the method and the system, the subject data of the news can be acquired automatically according to news content, related news is matched automatically through the subject data of the news, and the matched related news is automatically recommended to a user for reading, so that manual editing is not required, and labor power is saved; and news related to most news subjects can be recommended to the user, so as to help the user to expand reading.
Description
Technical field
The invention belongs to networking technology area, relate in particular to a kind of news recommend method and system.
Background technology
Fast development along with internet, the network data amount constantly increases, also caused problem of information overload when offering convenience for network user's obtaining information, how in the data of magnanimity fast and effeciently Search and Orientation become the developing outstanding problem of current internet to the information that needs, be also the focus of networked information retrieval research.
In order to address the above problem, a lot of news websites news content after all can by the news way of recommendation to user's recommendation and the current demonstration of terminal other relevant news of news, read as expansion, the mode that news is recommended can be recommended the Personalize News information for the user, help the user to find interested content, can effectively help the resource that the user finds quickly and accurately to be needed, have broad application prospects.Yet prior art news recommends generally by the human-edited, to realize, human cost is higher, therefore, can not be applied on a large scale on most of news, usually only has hot news just to have the recommendation of related news.
Summary of the invention
Given this, the invention provides a kind of news recommend method and system, be intended to solve prior art news and recommend generally by the human-edited, to realize, human cost is higher, the problem that can not apply on a large scale.
To achieve these goals, the embodiment of the present invention provides following technical scheme:
The embodiment of the present invention is achieved in that a kind of news recommend method, and described method comprises:
Obtain the subject data of the news of the current demonstration of terminal;
According to the subject data of the news of the current demonstration of obtaining, at the retrieval of preset themes search library and the coupling related news theme corresponding with the subject data of the news of described current demonstration;
The theme of the described related news that match is shown in the read page of news of current demonstration.
The embodiment of the present invention also provides a kind of news commending system, and described system comprises:
Acquiring unit, for the subject data of the news of obtaining the current demonstration of terminal;
Matching unit, be used for the subject data according to the news of the current demonstration of obtaining, at the retrieval of preset themes search library and the coupling related news theme corresponding with the subject data of the news of described current demonstration;
Display unit, for the theme of the described related news that match being shown in the read page of the news of current demonstration.
the embodiment of the present invention compared with prior art, beneficial effect is: when the user reads news, the subject data of the news of the current demonstration of automatic acquisition terminal, in the preset themes search library, mate the related news corresponding with described subject data, and in the read page of the news of current demonstration, show the related news that match, realization is according to news content, automatic acquisition theme of news data, by theme of news data Auto-matching related news, and the related news that will match are recommended user's reading automatically, need not the human-edited, save manpower, and can recommend the news relevant to most of theme of news for the user, help the user to expand reading.
Description of drawings
In order to be illustrated more clearly in the technical scheme of the embodiment of the present invention, in below describing embodiment, the accompanying drawing of required use is briefly described, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skills, under the prerequisite of not paying creative work, can also obtain according to these accompanying drawings other accompanying drawing.
Fig. 1 is the process flow diagram of the realization of the news recommend method that provides of the embodiment of the present invention one;
Fig. 2 is the process flow diagram of the realization of the news recommend method that provides of the embodiment of the present invention two;
Fig. 3 is the structural drawing of the news commending system that provides of the embodiment of the present invention three;
Fig. 4 is the structural drawing of the news commending system that provides of the embodiment of the present invention four.
Embodiment
, in order to make purpose of the present invention, technical scheme and advantage clearer, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
The embodiment of the present invention provides a kind of news recommend method, and described method comprises:
Obtain the subject data of the news of the current demonstration of terminal;
According to the subject data of the news of the current demonstration of obtaining, at the retrieval of preset themes search library and the coupling related news theme corresponding with the subject data of the news of described current demonstration;
The theme of the described related news that match is shown in the read page of news of current demonstration.
The embodiment of the present invention also provides a kind of news commending system, and described system comprises:
Acquiring unit, for the subject data of the news of obtaining the current demonstration of terminal;
Matching unit, be used for the subject data according to the news of the current demonstration of obtaining, at the retrieval of preset themes search library and the coupling related news theme corresponding with the subject data of the news of described current demonstration;
Display unit, for the theme of the described related news that match being shown in the read page of the news of current demonstration.
Below in conjunction with specific embodiment, realization of the present invention is described in detail:
Embodiment one
Fig. 1 shows the process flow diagram of the realization of the news recommend method that the embodiment of the present invention one provides, and details are as follows:
In S101, obtain the subject data of the news of the current demonstration of terminal;
In the present embodiment, the process of subject data of obtaining the news of the current demonstration of terminal comprises:
1, extract the key word of the news of the current demonstration of terminal, specifically can extract by natural language processing algorithm or the matic mould algorithm key word of the news of the current demonstration of terminal.
2, according to described key word, the subject data of the news of the described current demonstration of retrieval in the preset themes search library, wherein, the preset themes search library has been stored the corresponding relation of the key word that network is released news, subject data and news, and theme of news data may be corresponding with a plurality of key words.
In the present embodiment, can adopt the subject data based on the news of the storage of key assignments and the current demonstration of querying method searching terminal, wherein, key assignments can be the object of any non-NULL, for example, it can be numeral or alphabetical etc., in the process of key assignments storage and inquiry, key word and the default key assignments that network can be released news are set up corresponding relation, the user can directly inquire about by key assignments theme of news corresponding to key word that extracts, thereby, realize that theme extracts off-line, guarantees the efficiency of theme inquiry simultaneously to greatest extent.
In S102, according to the subject data of the news of the current demonstration of obtaining, at the retrieval of preset themes search library and the coupling related news theme corresponding with the subject data of the news of described current demonstration;
in the present embodiment, S102 can realize in the following ways: the similarity of the theme of news of the theme of news of the news of the current demonstration of computing terminal and the storage of preset themes search library, according to the similarity of calculating, mate the theme of news corresponding news similar to the theme of news of current demonstration as related news, wherein, the similarity of the theme of news of the theme of news of the news of the current demonstration of computing terminal and the storage of preset themes search library can be used the distance calculating method based on theme vector, for example, the included angle cosine distance calculating method, perhaps based on the distance calculating method of theme set, as the jaccard distance, dice distance etc.
In S103, the theme of the described related news that match is shown in the read page of news of current demonstration.
In the present embodiment,, for the news of current demonstration, find the related news of corresponding news by coupling, in the read page of the news of current demonstration, the related news that automatic Display matches, read as expansion.
In the present embodiment, in the read page of the news of current demonstration, can show the related news that match according to the sequencing of the issuing time of the related news that match, make the user can be in time, preferentially understand and related news that news time of current demonstration is nearest.
In the present embodiment, in the read page of the news of current demonstration, can also show the related news that match according to the descending order of the similarity of the related news that match, make the user can in time, preferentially recognize the related news the highest with the news degree of correlation of current demonstration.
Certainly, can also be according to the weight proportion with news correlation parameter and each parameter, calculate the weighted value of each news, descending according to the weight of related news, show the related news that match, wherein, the news correlation parameter can comprise: news briefing time, news similarity height and news key word etc.
in the embodiment of the present invention, when the user reads news, the subject data of the news of the current demonstration of automatic acquisition terminal, in the preset themes search library, mate the related news corresponding with described subject data, and in the read page of the news of current demonstration, show the related news that match, realization is according to news content, automatic acquisition theme of news data, by theme of news data Auto-matching related news, and the related news that will match are recommended user's reading automatically, need not the human-edited, save manpower, and can recommend the news relevant to most of theme of news for the user, help the user to expand reading.
Embodiment two
Fig. 2 shows the process flow diagram of the realization of the news recommend method that the embodiment of the present invention two provides, and details are as follows:
In S201, extract network and issue the key word of each news, generate the subject data of each news according to described key word.
In the present embodiment, S201 specifically can realize in the following ways:
1, adopt the method for natural language processing, extract network and issue the key word of each news, generate the subject data of each news according to described key word, for example, can adopt the core word extracting method, extract the key word that can embody theme of news in newsletter archive, can be word or phrase;
2, adopt the method for topic model, extract network and issue the key word of each news, generate the subject data of each news according to described key word, for example, can adopt potential semantic indexing model (Latent Semantic Index, LSI), the potential meaning of a word index model of probability (Probabilistic Latent Semantic Index, PLSI), perhaps potential Di Li Cray apportion model (Latent Dirichlet Allocation, the topic model method such as LDA), extract the key word of news.
In S202, the subject data according to the all-network that generates is released news, build the preset themes search library;
In the present embodiment, build the preset themes search library on the basis of the subject data of releasing news according to all-network, the preset themes search library has been stored the corresponding relation of the key word that network is released news, subject data and news.
In S203, obtain the subject data of the news of the current demonstration of terminal;
In S204, according to the subject data of the news of the current demonstration of obtaining, at the retrieval of preset themes search library and the coupling related news theme corresponding with the subject data of the news of described current demonstration;
In S205, the theme of the described related news that match is shown in the read page of news of current demonstration.
In the present embodiment, the implementation of S203 to S205 is similar to the implementation of S101 to S103 in embodiment one, specifically can, with reference to the description of step S101 to S103, not repeat them here.
in the present embodiment, issue the key word of each news by extracting network, generate the subject data of each news according to described key word, the subject data of releasing news according to the all-network that generates, build the preset themes search library, and according to the preset themes search library that builds, automatic acquisition is when the subject data of the news of reading, by subject data Auto-matching related news, and the related news that will match are recommended user's reading automatically, need not the human-edited, save manpower, and can recommend the news relevant to most of theme of news for the user, help the user to expand reading.
Embodiment three
Fig. 3 shows the structural drawing of the news commending system that the embodiment of the present invention three provides, and for convenience of explanation, only shows the part relevant to the embodiment of the present invention.
Described news commending system comprises: acquiring unit 31, matching unit 32 and display unit 33.
Acquiring unit 31, for the subject data of the news of obtaining the current demonstration of terminal;
Optionally, described acquiring unit 31 comprises:
Optionally, described retrieval module 312, concrete being used for according to described key word, adopt the subject data based on the news of the storage of key assignments and the current demonstration of querying method searching terminal in the preset themes search library.
Optionally, described matching unit 32 comprises: computing module 321 and matching module 322.
Optionally, described display unit 33, be used for the read page in the news of current demonstration,, according to the sequencing of the issuing time of the related news that match, shows the related news that match; Perhaps be used for the read page in the news of current demonstration,, according to the descending order of the similarity of the related news that match, show the related news that match.
in the embodiment of the present invention, when the user reads news, the subject data of the news of the current demonstration of acquiring unit automatic acquisition terminal, matching unit is in the preset themes search library, mate the related news corresponding with described subject data, and in the read page of the news of current demonstration, display unit is showed the related news that match, realization is according to news content, the automatic acquisition theme of news, automatically search related news by theme of news, and the related news that will find are recommended user's reading automatically, need not the human-edited, save manpower, and can recommend related news for most of news, help the user to expand reading.
The news commending system that the embodiment of the present invention provides can use in the embodiment of the method one of aforementioned correspondence, and details, referring to the description of above-described embodiment one, do not repeat them here.
Embodiment four
Fig. 4 shows the structural drawing of the news commending system that the embodiment of the present invention four provides, and for convenience of explanation, only shows the part relevant to the embodiment of the present invention.
Described news commending system comprises: generation unit 41, construction unit 42, acquiring unit 43, matching unit 44 and display unit 45.
The difference of the present embodiment and embodiment three is:
The news commending system that the embodiment of the present invention provides can use in the embodiment of the method two of aforementioned correspondence, and details, referring to the description of above-described embodiment two, do not repeat them here.
It should be noted that in said system embodiment, included unit is just divided according to function logic, but is not limited to above-mentioned division, as long as can realize corresponding function; In addition, the concrete title of each functional unit also, just for the ease of mutual differentiation, is not limited to protection scope of the present invention.
In addition, one of ordinary skill in the art will appreciate that all or part of step that realizes in the various embodiments described above method is to come the relevant hardware of instruction to complete by program, corresponding program can be stored in a computer read/write memory medium, described storage medium, as ROM/RAM, disk or CD etc.
The foregoing is only preferred embodiment of the present invention,, not in order to limit the present invention, all any modifications of doing within the spirit and principles in the present invention, be equal to and replace and improvement etc., within all should being included in protection scope of the present invention.
Claims (12)
1. a news recommend method, is characterized in that, described method comprises:
Obtain the subject data of the news of the current demonstration of terminal;
According to the subject data of the news of the current demonstration of obtaining, at the retrieval of preset themes search library and the coupling related news theme corresponding with the subject data of the news of described current demonstration;
The theme of the described related news that match is shown in the read page of news of current demonstration.
2. the method for claim 1, is characterized in that, before the step of the subject data of the described news of obtaining the current demonstration of terminal, described method comprises:
Extract network and issue the key word of each news, generate the subject data of each news according to described key word;
Subject data according to the all-network that generates is released news, build the preset themes search library.
3. method as claimed in claim 1 or 2, is characterized in that, the step of the subject data of the described news of obtaining the current demonstration of terminal is specially:
Extract the key word of the news of the current demonstration of terminal;
According to described key word, the subject data of the news of the described current demonstration of retrieval in the preset themes search library.
4. method as claimed in claim 3, is characterized in that, and is described according to described key word, and the step of the subject data of the news of the described current demonstration of retrieval is specially in the preset themes search library:
, according to described key word, adopt the subject data based on the news of the storage of key assignments and the current demonstration of querying method searching terminal in the preset themes search library.
5. method as claimed in claim 1 or 2, is characterized in that, described step at the retrieval of preset themes search library and the coupling related news theme corresponding with the subject data of the news of described current demonstration comprises:
The similarity of the theme of news of the theme of news of the news of the current demonstration of computing terminal and the storage of preset themes search library;
, according to the similarity of calculating, mate the news similar to the news of current demonstration as related news.
6. method as claimed in claim 1 or 2, is characterized in that, the step that described theme with the described related news that match is shown in the read page of news of current demonstration is specially:
In the read page of the news of current demonstration,, according to the sequencing of the issuing time of the related news that match, show the related news that match; Perhaps
In the read page of the news of current demonstration,, according to the descending order of the similarity of the related news that match, show the related news that match.
7. a news commending system, is characterized in that, described system comprises:
Acquiring unit, for the subject data of the news of obtaining the current demonstration of terminal;
Matching unit, be used for the subject data according to the news of the current demonstration of obtaining, at the retrieval of preset themes search library and the coupling related news theme corresponding with the subject data of the news of described current demonstration;
Display unit, for the theme of the described related news that match being shown in the read page of the news of current demonstration.
8. system as claimed in claim 7, is characterized in that, described system also comprises:
Generation unit, be used for extracting network and issue the key word of each news, generates the subject data of each news according to described key word;
Construction unit, be used for the subject data of according to the all-network that generates, releasing news, and builds the preset themes search library.
9. system as claimed in claim 7 or 8, is characterized in that, described acquiring unit comprises:
Extraction module, for the key word of the news of extracting the current demonstration of terminal;
Retrieval module, be used for according to described key word, the subject data of the news of the described current demonstration of retrieval in the preset themes search library.
10. system as claimed in claim 9, is characterized in that, described retrieval module, adopts the subject data based on the news of the storage of key assignments and the current demonstration of querying method searching terminal at concrete being used for according to described key word in the preset themes search library.
11. system, is characterized in that as claimed in claim 7 or 8, described matching unit comprises:
Computing module, be used for the similarity of the theme of news that theme of news and the preset themes search library of the news of the current demonstration of computing terminal store;
Matching module, be used for mating the news similar to the news of current demonstration as related news according to the similarity of calculating.
12. system, is characterized in that as claimed in claim 7 or 8, described display unit is used for the read page in the news of current demonstration,, according to the sequencing of the issuing time of the related news that match, shows the related news that match; Perhaps be used for the read page in the news of current demonstration,, according to the descending order of the similarity of the related news that match, show the related news that match.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012101376287A CN103389975A (en) | 2012-05-07 | 2012-05-07 | News recommending method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012101376287A CN103389975A (en) | 2012-05-07 | 2012-05-07 | News recommending method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103389975A true CN103389975A (en) | 2013-11-13 |
Family
ID=49534251
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012101376287A Pending CN103389975A (en) | 2012-05-07 | 2012-05-07 | News recommending method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103389975A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103870461A (en) * | 2012-12-10 | 2014-06-18 | 腾讯科技（深圳）有限公司 | Topic recommendation method, device and server |
| CN106202294A (en) * | 2016-07-01 | 2016-12-07 | 北京奇虎科技有限公司 | The related news computational methods merged based on key word and topic model and device |
| CN106202394A (en) * | 2016-07-07 | 2016-12-07 | 腾讯科技（深圳）有限公司 | The recommendation method and system of text information |
| CN106250550A (en) * | 2016-08-12 | 2016-12-21 | 智者四海（北京）技术有限公司 | A kind of method and apparatus of real time correlation news content recommendation |
| WO2017107651A1 (en) * | 2015-12-22 | 2017-06-29 | 北京奇虎科技有限公司 | Method and device for determining relevance between news and for calculating the relevance between news |
| WO2018036272A1 (en) * | 2016-08-22 | 2018-03-01 | 上海壹账通金融科技有限公司 | News content pushing method, electronic device, and computer readable storage medium |
| CN108154390A (en) * | 2017-12-20 | 2018-06-12 | 微梦创科网络科技（中国）有限公司 | Put-on method and device, the storage medium and computing device of advertisement blog article |
| CN108519980A (en) * | 2018-01-31 | 2018-09-11 | 广东易联创富集团有限公司 | News push method, apparatus, platform, computer readable storage medium |
| CN109190011A (en) * | 2018-10-19 | 2019-01-11 | 中国科学院重庆绿色智能技术研究院 | A kind of news passage search method based on LDA topic model |
| CN110837590A (en) * | 2019-10-17 | 2020-02-25 | 浙江大搜车软件技术有限公司 | Information pushing method and device, computer equipment and storage medium |
-
2012
- 2012-05-07 CN CN2012101376287A patent/CN103389975A/en active Pending
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10169449B2 (en) | 2012-12-10 | 2019-01-01 | Tencent Technology (Shenzhen) Company Limited | Method, apparatus, and server for acquiring recommended topic |
| WO2014090007A1 (en) * | 2012-12-10 | 2014-06-19 | 腾讯科技（深圳）有限公司 | Method, device and server for acquiring recommended theme |
| CN103870461A (en) * | 2012-12-10 | 2014-06-18 | 腾讯科技（深圳）有限公司 | Topic recommendation method, device and server |
| WO2017107651A1 (en) * | 2015-12-22 | 2017-06-29 | 北京奇虎科技有限公司 | Method and device for determining relevance between news and for calculating the relevance between news |
| US10217025B2 (en) | 2015-12-22 | 2019-02-26 | Beijing Qihoo Technology Company Limited | Method and apparatus for determining relevance between news and for calculating relevance among multiple pieces of news |
| CN106202294A (en) * | 2016-07-01 | 2016-12-07 | 北京奇虎科技有限公司 | The related news computational methods merged based on key word and topic model and device |
| CN106202294B (en) * | 2016-07-01 | 2020-09-11 | 北京奇虎科技有限公司 | Related news computing method and device based on keyword and topic model fusion |
| CN106202394A (en) * | 2016-07-07 | 2016-12-07 | 腾讯科技（深圳）有限公司 | The recommendation method and system of text information |
| WO2018006703A1 (en) * | 2016-07-07 | 2018-01-11 | 腾讯科技（深圳）有限公司 | Method and system for recommending text content, and storage medium |
| US10783206B2 (en) | 2016-07-07 | 2020-09-22 | Tencent Technology (Shenzhen) Company Limited | Method and system for recommending text content, and storage medium |
| CN106250550A (en) * | 2016-08-12 | 2016-12-21 | 智者四海（北京）技术有限公司 | A kind of method and apparatus of real time correlation news content recommendation |
| WO2018036272A1 (en) * | 2016-08-22 | 2018-03-01 | 上海壹账通金融科技有限公司 | News content pushing method, electronic device, and computer readable storage medium |
| CN108154390A (en) * | 2017-12-20 | 2018-06-12 | 微梦创科网络科技（中国）有限公司 | Put-on method and device, the storage medium and computing device of advertisement blog article |
| CN108154390B (en) * | 2017-12-20 | 2022-01-25 | 微梦创科网络科技（中国）有限公司 | Advertisement blog posting method and device, storage medium and computing equipment |
| CN108519980A (en) * | 2018-01-31 | 2018-09-11 | 广东易联创富集团有限公司 | News push method, apparatus, platform, computer readable storage medium |
| CN109190011A (en) * | 2018-10-19 | 2019-01-11 | 中国科学院重庆绿色智能技术研究院 | A kind of news passage search method based on LDA topic model |
| CN110837590A (en) * | 2019-10-17 | 2020-02-25 | 浙江大搜车软件技术有限公司 | Information pushing method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103389975A (en) | News recommending method and system | |
| US20120179454A1 (en) | Apparatus and method for automatically generating grammar for use in processing natural language | |
| CN106844341B (en) | Artificial intelligence-based news abstract extraction method and device | |
| CN102156711B (en) | Cloud storage based power full text retrieval method and system | |
| US20180150561A1 (en) | Searching method and searching apparatus based on neural network and search engine | |
| CN104239373A (en) | Document tag adding method and document tag adding device | |
| US20220019739A1 (en) | Item Recall Method and System, Electronic Device and Readable Storage Medium | |
| US20140379719A1 (en) | System and method for tagging and searching documents | |
| CN108090178B (en) | Text data analysis method, text data analysis device, server and storage medium | |
| CN105608166A (en) | Label extracting method and device | |
| CN103870000A (en) | Method and device for sorting candidate items generated by input method | |
| WO2015185020A1 (en) | Information category obtaining method and apparatus | |
| CN109325146A (en) | A kind of video recommendation method, device, storage medium and server | |
| CN110377750B (en) | Comment generation method, comment generation device, comment generation model training device and storage medium | |
| CN110334268B (en) | Block chain project hot word generation method and device | |
| CN108875743B (en) | Text recognition method and device | |
| CN103440262A (en) | Image searching system and image searching method basing on relevance feedback and Bag-of-Features | |
| CN114357117A (en) | Transaction information query method and device, computer equipment and storage medium | |
| CN103235773A (en) | Method and device for extracting text labels based on keywords | |
| CN109344325B (en) | Information recommendation method and device based on intelligent conference tablet | |
| CN105659235A (en) | A term searching method for network information and a system thereof | |
| CN108319688A (en) | A kind of method and apparatus for user read prompting | |
| CN111460808B (en) | Synonymous text recognition and content recommendation method and device and electronic equipment | |
| Yu et al. | Role-explicit query identification and intent role annotation | |
| CN113779934B (en) | Multi-mode information extraction method, device, equipment and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| ASS | Succession or assignment of patent right |
Owner name: SHENZHEN SHIJI LIGHT SPEED INFORMATION TECHNOLOGY Free format text: FORMER OWNER: TENGXUN SCI-TECH (SHENZHEN) CO., LTD. Effective date: 20131018 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| COR | Change of bibliographic data |
Free format text: CORRECT: ADDRESS; FROM: 518044 SHENZHEN, GUANGDONG PROVINCE TO: 518057 SHENZHEN, GUANGDONG PROVINCE |
|
| TA01 | Transfer of patent application right |
Effective date of registration: 20131018 Address after: A Tencent Building in Shenzhen Nanshan District City, Guangdong streets in Guangdong province science and technology 518057 16 Applicant after: Shenzhen Shiji Guangsu Information Technology Co., Ltd. Address before: Shenzhen Futian District City, Guangdong province 518044 Zhenxing Road, SEG Science Park 2 East Room 403 Applicant before: Tencent Technology (Shenzhen) Co., Ltd. |
|
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20131113 |