CN104573076A - Social networking site user Chinese remark name system recommendation method - Google Patents
Social networking site user Chinese remark name system recommendation method Download PDFInfo
- Publication number
- CN104573076A CN104573076A CN201510041142.7A CN201510041142A CN104573076A CN 104573076 A CN104573076 A CN 104573076A CN 201510041142 A CN201510041142 A CN 201510041142A CN 104573076 A CN104573076 A CN 104573076A
- Authority
- CN
- China
- Prior art keywords
- user name
- weight
- user
- pending
- high frequency
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a social networking site user Chinese remark name system recommendation method applied to social networking sites. The method includes aiming to arrangement of friend remark names, considering the length factors, composition factors and word frequency factors of net names comprehensively, adopting a weighting computation method, and implementing system intelligent recommendation effectively. The method is adaptive to the situation of large amount of users' net name data, the situation of one user owning different net names and the situation of small amount of one user's net name data.
Description
Technical field
The present invention relates to a kind of social network sites user Chinese remark names system recommendation method.
Background technology
Along with the development of Internet technology, the appearance of social networks has furthered people's distance to each other more, in virtual network world, the identity of people using user name as oneself, is exchanging each other, and existing social network sites is varied, because the situation of user name is special, itself and litigant self do not possess and directly contact, therefore, in social network sites, when two people become good friend, namely both sides can be the other side and arrange remark names, so that in numerous good friend, oneself accurately can learn whom the other side is; Wherein, when user arranges remark names for good friend, existing social network sites system can automatic spring be the remark names that this person recommends, and for this technology, mainly according in social networks, other people carry out statistical weight at the frequency of the remark names appearance in different social circles to the remark names of this people and this people to existing remark names recommend method, occurrence number maximum weights higher, more close to true name; This Measures compare is simple and be effective when network pet name data volume is very large, but for the people of interpersonal relation relative complex, it has much different addresses, and the effect of such Corpus--based Method is just not ideal, and the various pet name is respected title and waited the effect that all can interfere with word frequency statistics; Simultaneously when the network pet name is relatively less time, the effect of Corpus--based Method is not satisfactory too.Therefore, existing system remark names recommend method can not be applicable in the middle of existing social networks.
Summary of the invention
For above-mentioned technical matters, technical matters to be solved by this invention is to provide one and is applied to social network sites, for the setting of remark names between good friend, effectively can realize the social network sites user Chinese remark names system recommendation method that system intelligent is recommended.
The present invention is in order to solve the problems of the technologies described above by the following technical solutions: the present invention devises a kind of social network sites user Chinese remark names system recommendation method, comprises the steps:
Step 001., for targeted customer, obtains all user names corresponding to this user in social network sites, as each pending user name, forms the user name information aggregate of this user;
Step 002., according to default user name length weight and default user name Length Weight setting rule, for each the pending user name in this user's user name information aggregate, judges its length, obtains the user name Length Weight of each pending user name respectively;
Step 003. is according to presetting the conventional Chinese surname basis weight and non-common Chinese surname basis weight that correspond respectively to conventional Chinese surname dictionary and non-common Chinese surname dictionary, for each the pending user name in this user's user name information aggregate, judge whether it comprises Chinese surname respectively, and this involved Chinese surname belongs to conventional Chinese surname dictionary or non-common Chinese surname dictionary, obtains the Chinese surname weight of each pending user name with this respectively;
Wherein, conventional Chinese surname basis weight and non-common Chinese surname basis weight are all greater than user name length weight, and conventional Chinese surname basis weight is greater than non-common Chinese surname basis weight;
Step 004., for this user's user name information aggregate, according to Chinese word frequency, obtains front n the high frequency words that frequency arranges from high to low, form high frequency words set, and each high frequency words in high frequency words set is all corresponding to default high frequency words basis weight, and wherein, n is according to predetermined number;
Step 005. is according to default high frequency words basis weight, for each the pending user name in this user's user name information aggregate, judge whether it comprises the high frequency words in high frequency words set respectively, and comprise the number of high frequency words, obtain the high frequency words weight of each pending user name with this respectively;
Step 006. is for each the pending user name in this user's user name information aggregate, according to the user name Length Weight of pending user name, Chinese surname weight, high frequency words weight, and preset the weight coefficient corresponding respectively to user name length, Chinese surname, high frequency words, be weighted the total weight obtaining and correspond to pending user name;
Step 007. obtains the pending user name that in this user's user name information aggregate, total weight is the highest, as the system recommendation remark names of this user.
As a preferred technical solution of the present invention: in described step 001, the all user names corresponding to this user in described social network sites comprise the current user name of this user in social network sites, all history user names, and all remark names that other users are arranged for this user.
As a preferred technical solution of the present invention: for each the pending user name in this user's user name information aggregate in described step 002, perform as follows respectively:
Obtain the length of pending user name, and judge whether it meets the user name foundation length preset, and is give this pending user name, as the user name Length Weight of this pending user name by default user name length weight; Otherwise obtain the difference of this pending user name length and default user name foundation length, according to default user name Length Weight setting rule, deduct the numerical value corresponding to this difference by default user name length weight, obtain the user name Length Weight of weight as this pending user name.
As a preferred technical solution of the present invention: described default user name foundation length is 2 ~ 4.
As a preferred technical solution of the present invention: for each the pending user name in this user's user name information aggregate in described step 003, perform as follows respectively:
Step 00301. judges whether comprise Chinese surname in pending user name, is enter step 00302, otherwise the Chinese surname weight of giving this pending user name is 0, and the method obtaining this pending user name Chinese surname weight terminates;
Step 00302. judges whether comprise the Chinese surname belonging to conventional Chinese surname dictionary in pending user name, be, give the Chinese surname weight of this pending user name for conventional Chinese surname basis weight, the method obtaining this pending user name Chinese surname weight terminates; Otherwise the Chinese surname weight of giving this pending user name is non-common Chinese surname basis weight, the method obtaining this pending user name Chinese surname weight terminates.
As a preferred technical solution of the present invention: in described step 004, n is 4.
As a preferred technical solution of the present invention: for each the pending user name in this user's user name information aggregate in described step 005, perform as follows respectively:
Step 00501. judges the high frequency words whether comprised in pending user name in high frequency words set, is enter step 00502, otherwise the high frequency words weight of giving this pending user name is 0, and the method obtaining this pending user name high frequency words weight terminates;
Step 00502. obtains the number m that this pending user name comprises high frequency words, and the high frequency words weight of giving this pending user name is high frequency words basis weight × m, and the method obtaining this pending user name high frequency words weight terminates.
A kind of social network sites user Chinese remark names system recommendation method of the present invention adopts above technical scheme compared with prior art, there is following technique effect: the social network sites user Chinese remark names system recommendation method of the present invention's design, be applied to social network sites, for the setting of remark names between good friend, consider the length factor of user name, constituent element, and word factor frequently wherein, adopt the mode of weight calculation, effectively can realize system intelligent to recommend, be not only applicable to the situation that user network name data volume is larger, and a user can also be applicable to have the situation of a lot of different user name and the less situation of a user network name data volume.
Accompanying drawing explanation
Fig. 1 designs the process flow diagram of social network sites user Chinese remark names system recommendation method for the present invention;
Fig. 2 designs the embodiment application module schematic diagram of social network sites user Chinese remark names system recommendation method for the present invention.
Embodiment
Be described in further detail for the specific embodiment of the present invention below in conjunction with Figure of description.
As depicted in figs. 1 and 2, a kind of social network sites user Chinese remark names system recommendation method of the present invention's design is in the middle of actual application, and reality specifically comprises the steps:
Step 001., for targeted customer, obtains all user names corresponding to this user in social network sites, as each pending user name, forms the user name information aggregate of this user, be stored in social network user user name storer; Wherein, all user names corresponding to this user in described social network sites comprise the current user name of this user in social network sites, all history user names, and all remark names that other users are arranged for this user.
In practical application, adopt the realization of social network user user name storer for the storage of the user name information aggregate of user, this wherein, social network user user name storer adopts relational database or nosql database or document data bank and other feasible storage tool, and for each the pending user name stored in social network user user name storer, associated user is for the service time of user name simultaneously, and associate with unique mark of user, and when user revises user name or other people add/revise remark names to this user, new user name can be stored in social network user user name storer by system, and associate with the unique identification of respective user.
Step 002. weight computation module obtains all pending user names of targeted customer from social networks storer according to the unique identification of user, then, weight computation module is according to default user name length weight and default user name Length Weight setting rule, for each the pending user name in this user's user name information aggregate, judge its length, obtain the user name Length Weight of each pending user name respectively; Wherein, for each the pending user name in this user's user name information aggregate, perform as follows respectively:
Be 2-4 word according to the length of usual Chinese name, presetting user name foundation length is 2 ~ 4, therefore, first the length of pending user name is obtained, and judge whether it meets the user name foundation length 2 ~ 4 preset, give this pending user name, as the user name Length Weight of this pending user name by default user name length weight; Otherwise obtain the difference of this pending user name length and default user name foundation length, according to default user name Length Weight setting rule, deduct the numerical value corresponding to this difference by default user name length weight, obtain the user name Length Weight of weight as this pending user name.
Step 003. weight computation module is according to presetting the conventional Chinese surname basis weight and non-common Chinese surname basis weight that correspond respectively to conventional Chinese surname dictionary and non-common Chinese surname dictionary, for each the pending user name in this user's user name information aggregate, judge whether it comprises Chinese surname respectively, and this involved Chinese surname belongs to conventional Chinese surname dictionary or non-common Chinese surname dictionary, obtains the Chinese surname weight of each pending user name with this respectively; Wherein, for each the pending user name in this user's user name information aggregate, perform as follows respectively:
Step 00301. judges whether comprise Chinese surname in pending user name, is enter step 00302, otherwise the Chinese surname weight of giving this pending user name is 0, and the method obtaining this pending user name Chinese surname weight terminates;
Step 00302. judges whether comprise the Chinese surname belonging to conventional Chinese surname dictionary in pending user name, be, give the Chinese surname weight of this pending user name for conventional Chinese surname basis weight, the method obtaining this pending user name Chinese surname weight terminates; Otherwise the Chinese surname weight of giving this pending user name is non-common Chinese surname basis weight, the method obtaining this pending user name Chinese surname weight terminates.Wherein, conventional Chinese surname basis weight and non-common Chinese surname basis weight are all greater than user name length weight, and conventional Chinese surname basis weight is greater than non-common Chinese surname basis weight.
And wherein, conventional Chinese surname dictionary and non-common Chinese surname dictionary, arrange according to the statistical data openly provided on the net and get, comprise conventional two-character surname and monosyllabic name (about 150), non-common Chinese surname dictionary (about 1000) contains most Chinese surname (removing conventional surname).
Step 004. weight computation module is for this user's user name information aggregate, according to Chinese word frequency, obtain front 4 high frequency words that frequency arranges from high to low, form high frequency words set, and each high frequency words in high frequency words set is all corresponding to default high frequency words basis weight.
Step 005. weight computation module is according to default high frequency words basis weight, for each the pending user name in this user's user name information aggregate, judge whether it comprises the high frequency words in high frequency words set respectively, and comprise the number of high frequency words, the high frequency words weight of each pending user name is obtained respectively with this, wherein, for each the pending user name in this user's user name information aggregate, perform as follows respectively:
Step 00501. judges the high frequency words whether comprised in pending user name in high frequency words set, is enter step 00502, otherwise the high frequency words weight of giving this pending user name is 0, and the method obtaining this pending user name high frequency words weight terminates;
Step 00502. obtains the number m that this pending user name comprises high frequency words, and the high frequency words weight of giving this pending user name is high frequency words basis weight × m, and the method obtaining this pending user name high frequency words weight terminates.;
Step 006. is for each the pending user name in this user's user name information aggregate, according to the user name Length Weight of pending user name, Chinese surname weight, high frequency words weight, and preset the weight coefficient corresponding respectively to user name length, Chinese surname, high frequency words, be weighted the total weight obtaining and correspond to pending user name.
Step 007. obtains the pending user name that in this user's user name information aggregate, total weight is the highest, as the system recommendation remark names of this user, is recommended to user by remark names recommendation service module.
The social network sites user Chinese remark names system recommendation method of technique scheme design, be applied to social network sites, for the setting of remark names between good friend, consider length factor, the constituent element of user name, and word factor frequently wherein, adopt the mode of weight calculation, effectively can realize system intelligent to recommend, be not only applicable to the situation that user network name data volume is larger, and a user can also be applicable to have the situation of a lot of different user name and the less situation of a user network name data volume.
In the middle of actual application, be applied to embodiment with reference to said method, specific as follows:
Step 001., for targeted customer, obtains all user names corresponding to this user in social network sites, as each pending user name, forms a user name information aggregate { manager of this user; Zhang Shu; Zhang Guozhong; Eldest brother; Little loyal son; Shanghai company opens; Laonan people; Pirates of the Caribbean Sui; The loyal grandfather of dare-to-die corps; If lofty and unyielding character iron; A Zhong; Faithful pal; South-Korea liquid Chelsea clock; >>> Pie love; Zhong Shu Zhu angle >>>}.
Step 002. is according to default user name length weight L1 and default user name Length Weight setting rule, for each the pending user name in this user's user name information aggregate, judge its length, obtain the user name Length Weight of each pending user name respectively, specific as follows:
{ manager=L1; Zhang uncle=L1; Zhang Guozhong=L1; Eldest brother=L1; Little loyal son=L1; Laonan people=L1; If lofty and unyielding character iron=L1; A Zhong=L1; Faithful pal=L1; South-Korea liquid Chelsea clock=L1}; {=L2 opens in Shanghai company; Pirates of the Caribbean Sui=L3; Loyal grandfather=the L4 of dare-to-die corps; >>> Pie love=L5; Zhong Shu Zhu angle >>>=L6}; Wherein, user name Length Weight L2, L3, L4, L5, L6 are all less than user name Length Weight L1.
Step 003. is according to presetting the conventional Chinese surname basis weight N1 and non-common Chinese surname basis weight N2 that correspond respectively to conventional Chinese surname dictionary and non-common Chinese surname dictionary, for each the pending user name in this user's user name information aggregate, judge whether it comprises Chinese surname respectively, and this involved Chinese surname belongs to conventional Chinese surname dictionary or non-common Chinese surname dictionary, the Chinese surname weight of each pending user name is obtained respectively with this, specific as follows:
" to open " and " clock " belongs to conventional Chinese surname dictionary, then { manager=N1; Zhang uncle=N1; Zhang Guozhong=N1; A Zhong=0; South-Korea liquid Chelsea clock=N1;=N1} opens in Shanghai company; " Sui " and " iron " belongs to non-common Chinese surname dictionary, then { Pirates of the Caribbean Sui=N2; Faithful pal=N2; If lofty and unyielding character iron=N2}; And not containing Chinese surname, then { eldest brother=0 in remaining user name; Little loyal son=0; Laonan people=0; Loyal grandfather=0 of dare-to-die corps; >>> Pie love=0; Zhong Shu Zhu angle >>>=0}.
Step 004., for this user's user name information aggregate, according to Chinese word frequency, obtains front 4 high frequency words that frequency arranges from high to low, forms high frequency words set [loyal: 4, to open: 4, brother: 2, iron: 2].
Step 005. is according to default high frequency words basis weight, for each the pending user name in this user's user name information aggregate, judge whether it comprises the high frequency words in high frequency words set respectively, and comprise the number of high frequency words, the high frequency words weight of each pending user name is obtained respectively with this, specific as follows:
{ manager=W1; Zhang uncle=W2; Zhang Guozhong=W3; If lofty and unyielding character iron=W4; A Zhong=W5; Faithful pal=W6; South-Korea liquid Chelsea clock=W7;=W8 opens in Shanghai company; Eldest brother=W9; Little loyal son=W10; Laonan people=W11; Loyal grandfather=the W12 of dare-to-die corps; >>> Pie love=W13; Zhong Shu Zhu angle >>>=W14; Pirates of the Caribbean Sui=W15}, wherein, wherein Zhang Guozhong=W3 and faithful pal=W6 high frequency words weight rank forward.
Step 006. is for each the pending user name in this user's user name information aggregate, according to the user name Length Weight of pending user name, Chinese surname weight, high frequency words weight, and preset and correspond respectively to the weight coefficient of user name length, Chinese surname, high frequency words, be weighted according to such as drag the total weight obtaining and correspond to pending user name;
f=a*Lm+b*Nm+c*Wm
Wherein, f is total weight of pending user name, and a is the weight coefficient of user name length, and b is the weight coefficient of Chinese surname, and c is the weight coefficient of high frequency words.
Each pending user name in the user name information aggregate of this user sorts by its total weight size by step 007. from high to low, specific as follows: { Zhang Guozhong, faithful pal, Zhang Shu, Zhang handles, A Zhong, eldest brother, if lofty and unyielding character iron, South-Korea liquid Chelsea clock, Shanghai company opens, Laonan people, little loyal son, Pirates of the Caribbean, >>> Pie love, the loyal grandfather of dare-to-die corps, Zhong Shu Zhu angle >>>}, obtain the pending user name " Zhang Guozhong " that in this user's user name information aggregate, total weight is the highest, as the system recommendation remark names of this user.
By reference to the accompanying drawings embodiments of the present invention are explained in detail above, but the present invention is not limited to above-mentioned embodiment, in the ken that those of ordinary skill in the art possess, can also makes a variety of changes under the prerequisite not departing from present inventive concept.
Claims (7)
1. a social network sites user Chinese remark names system recommendation method, is characterized in that, comprise the steps:
Step 001., for targeted customer, obtains all user names corresponding to this user in social network sites, as each pending user name, forms the user name information aggregate of this user;
Step 002., according to default user name length weight and default user name Length Weight setting rule, for each the pending user name in this user's user name information aggregate, judges its length, obtains the user name Length Weight of each pending user name respectively;
Step 003. is according to presetting the conventional Chinese surname basis weight and non-common Chinese surname basis weight that correspond respectively to conventional Chinese surname dictionary and non-common Chinese surname dictionary, for each the pending user name in this user's user name information aggregate, judge whether it comprises Chinese surname respectively, and this involved Chinese surname belongs to conventional Chinese surname dictionary or non-common Chinese surname dictionary, obtains the Chinese surname weight of each pending user name with this respectively;
Wherein, conventional Chinese surname basis weight and non-common Chinese surname basis weight are all greater than user name length weight, and conventional Chinese surname basis weight is greater than non-common Chinese surname basis weight;
Step 004., for this user's user name information aggregate, according to Chinese word frequency, obtains front n the high frequency words that frequency arranges from high to low, form high frequency words set, and each high frequency words in high frequency words set is all corresponding to default high frequency words basis weight, and wherein, n is according to predetermined number;
Step 005. is according to default high frequency words basis weight, for each the pending user name in this user's user name information aggregate, judge whether it comprises the high frequency words in high frequency words set respectively, and comprise the number of high frequency words, obtain the high frequency words weight of each pending user name with this respectively;
Step 006. is for each the pending user name in this user's user name information aggregate, according to the user name Length Weight of pending user name, Chinese surname weight, high frequency words weight, and preset the weight coefficient corresponding respectively to user name length, Chinese surname, high frequency words, be weighted the total weight obtaining and correspond to pending user name;
Step 007. obtains the pending user name that in this user's user name information aggregate, total weight is the highest, as the system recommendation remark names of this user.
2. a kind of social network sites user Chinese remark names system recommendation method according to claim 1, it is characterized in that, in described step 001, the all user names corresponding to this user in described social network sites comprise the current user name of this user in social network sites, all history user names, and all remark names that other users are arranged for this user.
3. a kind of social network sites user Chinese remark names system recommendation method according to claim 1, is characterized in that, for each the pending user name in this user's user name information aggregate in described step 002, perform as follows respectively:
Obtain the length of pending user name, and judge whether it meets the user name foundation length preset, and is give this pending user name, as the user name Length Weight of this pending user name by default user name length weight; Otherwise obtain the difference of this pending user name length and default user name foundation length, according to default user name Length Weight setting rule, deduct the numerical value corresponding to this difference by default user name length weight, obtain the user name Length Weight of weight as this pending user name.
4. a kind of social network sites user Chinese remark names system recommendation method according to claim 3, is characterized in that: described default user name foundation length is 2 ~ 4.
5. a kind of social network sites user Chinese remark names system recommendation method according to claim 1, is characterized in that, for each the pending user name in this user's user name information aggregate in described step 003, perform as follows respectively:
Step 00301. judges whether comprise Chinese surname in pending user name, is enter step 00302, otherwise the Chinese surname weight of giving this pending user name is 0, and the method obtaining this pending user name Chinese surname weight terminates;
Step 00302. judges whether comprise the Chinese surname belonging to conventional Chinese surname dictionary in pending user name, be, give the Chinese surname weight of this pending user name for conventional Chinese surname basis weight, the method obtaining this pending user name Chinese surname weight terminates; Otherwise the Chinese surname weight of giving this pending user name is non-common Chinese surname basis weight, the method obtaining this pending user name Chinese surname weight terminates.
6. a kind of social network sites user Chinese remark names system recommendation method according to claim 1, it is characterized in that, in described step 004, n is 4.
7. a kind of social network sites user Chinese remark names system recommendation method according to claim 1, is characterized in that, for each the pending user name in this user's user name information aggregate in described step 005, perform as follows respectively:
Step 00501. judges the high frequency words whether comprised in pending user name in high frequency words set, is enter step 00502, otherwise the high frequency words weight of giving this pending user name is 0, and the method obtaining this pending user name high frequency words weight terminates;
Step 00502. obtains the number m that this pending user name comprises high frequency words, and the high frequency words weight of giving this pending user name is high frequency words basis weight × m, and the method obtaining this pending user name high frequency words weight terminates.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510041142.7A CN104573076B (en) | 2015-01-27 | 2015-01-27 | A kind of Chinese remark names system recommendation method of social network sites user |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510041142.7A CN104573076B (en) | 2015-01-27 | 2015-01-27 | A kind of Chinese remark names system recommendation method of social network sites user |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104573076A true CN104573076A (en) | 2015-04-29 |
CN104573076B CN104573076B (en) | 2017-11-03 |
Family
ID=53089138
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510041142.7A Active CN104573076B (en) | 2015-01-27 | 2015-01-27 | A kind of Chinese remark names system recommendation method of social network sites user |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104573076B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105530167A (en) * | 2015-12-14 | 2016-04-27 | 小米科技有限责任公司 | Method and device for setting group name card |
CN106021235A (en) * | 2016-06-01 | 2016-10-12 | 腾讯科技(深圳)有限公司 | Data mining processing method and device |
CN111552798A (en) * | 2020-04-30 | 2020-08-18 | 腾讯科技(深圳)有限公司 | Name information processing method and device based on name prediction model and electronic equipment |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101499091A (en) * | 2009-03-17 | 2009-08-05 | 辽宁般若网络科技有限公司 | Web page representative words recommending method |
CN102081627A (en) * | 2009-11-27 | 2011-06-01 | 北京金山软件有限公司 | Method and system for determining contribution degree of word in text |
CN102768659A (en) * | 2011-05-03 | 2012-11-07 | 阿里巴巴集团控股有限公司 | Method and system for identifying repeated account |
CN103279515A (en) * | 2013-05-23 | 2013-09-04 | 微梦创科网络科技(中国)有限公司 | Recommendation method based on microblog groups and microblog group recommendation device |
CN103473313A (en) * | 2013-09-11 | 2013-12-25 | 百度在线网络技术(北京)有限公司 | Establishment method and device for name dictionary of input method |
WO2014023123A1 (en) * | 2012-08-08 | 2014-02-13 | Tencent Technology (Shenzhen) Company Limited | A user recommendation method and a user recommendation system using the same |
-
2015
- 2015-01-27 CN CN201510041142.7A patent/CN104573076B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101499091A (en) * | 2009-03-17 | 2009-08-05 | 辽宁般若网络科技有限公司 | Web page representative words recommending method |
CN102081627A (en) * | 2009-11-27 | 2011-06-01 | 北京金山软件有限公司 | Method and system for determining contribution degree of word in text |
CN102768659A (en) * | 2011-05-03 | 2012-11-07 | 阿里巴巴集团控股有限公司 | Method and system for identifying repeated account |
WO2014023123A1 (en) * | 2012-08-08 | 2014-02-13 | Tencent Technology (Shenzhen) Company Limited | A user recommendation method and a user recommendation system using the same |
CN103279515A (en) * | 2013-05-23 | 2013-09-04 | 微梦创科网络科技(中国)有限公司 | Recommendation method based on microblog groups and microblog group recommendation device |
CN103473313A (en) * | 2013-09-11 | 2013-12-25 | 百度在线网络技术(北京)有限公司 | Establishment method and device for name dictionary of input method |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105530167A (en) * | 2015-12-14 | 2016-04-27 | 小米科技有限责任公司 | Method and device for setting group name card |
CN105530167B (en) * | 2015-12-14 | 2018-11-30 | 小米科技有限责任公司 | The setting method and device of group's business card |
CN106021235A (en) * | 2016-06-01 | 2016-10-12 | 腾讯科技(深圳)有限公司 | Data mining processing method and device |
CN106021235B (en) * | 2016-06-01 | 2019-01-29 | 腾讯科技(深圳)有限公司 | A kind of data mining processing method and device |
CN111552798A (en) * | 2020-04-30 | 2020-08-18 | 腾讯科技(深圳)有限公司 | Name information processing method and device based on name prediction model and electronic equipment |
CN111552798B (en) * | 2020-04-30 | 2021-06-04 | 腾讯科技(深圳)有限公司 | Name information processing method and device based on name prediction model and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN104573076B (en) | 2017-11-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104572889B (en) | A kind of search word recommends methods, devices and systems | |
CN105095219B (en) | Micro-blog recommendation method and terminal | |
CN105528248B (en) | Intelligent perception incentive mechanism under multitask collaboration application | |
CN107784066A (en) | Information recommendation method, device, server and storage medium | |
CN109360057A (en) | Information-pushing method, device, computer equipment and storage medium | |
CN108665064A (en) | Neural network model training, object recommendation method and device | |
CN103886048B (en) | Cluster-based increment digital book recommendation method | |
CN110060129A (en) | A kind of air ticket intelligent recommendation method | |
CN108460082A (en) | A kind of recommendation method and device, electronic equipment | |
CN104573076A (en) | Social networking site user Chinese remark name system recommendation method | |
CN104731866A (en) | Individual gourmet recommending method based on position | |
CN109117742A (en) | Gestures detection model treatment method, apparatus, equipment and storage medium | |
CN105653640A (en) | Collaborative filtering recommendation method based on trust mechanism | |
CN107145506A (en) | A kind of means of agricultural production Method of Commodity Recommendation of the improvement based on content | |
CN107357845A (en) | A kind of tour interest commending system and recommendation method based on Spark | |
CN105871585A (en) | Terminal association method and device | |
CN110334278A (en) | A kind of web services recommended method based on improvement deep learning | |
CN109447312A (en) | Route planning method, device, electronic equipment and readable storage medium storing program for executing | |
CN103902549A (en) | Search data sorting method and device and data searching method and device | |
CN102945273A (en) | Method and equipment for providing search results | |
CN102664744A (en) | Group-sending recommendation method in network message communication | |
CN106802958B (en) | Conversion method and system of the CAD data to GIS data | |
CN107368499A (en) | A kind of client's tag modeling and recommendation method and device | |
CN109871493A (en) | Friend-making matching process, device, computer equipment and readable storage medium storing program for executing | |
CN104765868A (en) | Page display method for data query |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20230613 Address after: 710077 No. 678, Kunyuan Road, Chang'an District, Xi'an, Shaanxi Patentee after: XI'AN FENGHUO SOFTWARE TECHNOLOGY CO.,LTD. Address before: 210019 26F, building a, Fenghuo science and technology building, 88 yunlongshan Road, Jianye District, Nanjing City, Jiangsu Province Patentee before: NANJING FIBERHOME TELECOMMUNICATION TECHNOLOGIES Co.,Ltd. |