CN102799662B - Method, the Apparatus and system of network address is recommended based on domain name access historical record - Google Patents
Method, the Apparatus and system of network address is recommended based on domain name access historical record Download PDFInfo
- Publication number
- CN102799662B CN102799662B CN201210239708.3A CN201210239708A CN102799662B CN 102799662 B CN102799662 B CN 102799662B CN 201210239708 A CN201210239708 A CN 201210239708A CN 102799662 B CN102799662 B CN 102799662B
- Authority
- CN
- China
- Prior art keywords
- domain name
- user
- website
- domain
- access
- 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
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000004891 communication Methods 0.000 claims description 9
- 230000002829 reductive effect Effects 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
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
- G06F16/954—Navigation, e.g. using categorised browsing
-
- 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
-
- 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
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
- G06F16/9562—Bookmark management
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)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses method, the Apparatus and system of recommending network address based on domain name access historical record, wherein, described method comprises: the domain name access historical record obtaining user; Domain name access history record comprises the domain name of the website that this user accessed; Obtain the class label of each domain name difference correspondence in domain name access history record; According to domain name access history record and described class label, obtain target class distinguishing label; The candidate's domain name for recommending is obtained according to described target class distinguishing label; Determine to recommend network address based on described candidate's domain name; Recommendation network address is represented in the navigation page that this user browses.By the present invention, when user's navigation page, for it provides the network address more meeting user interest and pay close attention to, can achieve and provide personalized Web side navigation for different users.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method, a device and a system for recommending a website based on a domain name access history record.
Background
With the development of computer technology and the increasing scale of internet users, more and more internet users use personal computers to obtain various required information through the internet. Meanwhile, more and more websites are provided for providing information services for internet users, the number of internet webpages is increased at an incredible speed every day, and internet information is increased explosively. For users, it is often necessary to quickly locate a website or required information most suitable for their own needs in internet information in a large amount, such as the internet address navigation service, by a certain means.
The website navigation is a website station which integrates a plurality of websites and classifies the websites according to certain conditions, and mainly provides website navigation service for users. The website navigation can enable a user to conveniently find a website needed by the user for browsing and information retrieval through a link provided by a website navigation page without memorizing the website of the website. Meanwhile, some of the existing website navigation also provides some practical functions, such as number query, mailbox login, hot news, search engine entry and the like, and provides convenience for the internet surfing of the user to a certain extent. According to statistics, a considerable proportion of internet users set the homepage of the browser as a website navigation page at present, and it is also demonstrated from one side that the website navigation service really has the function of facilitating the browsing of the user in practical application, so that the website navigation service is popular with many users.
However, in the existing website navigation service technology, most of the navigation contents are static pages manually recommended by operation and maintenance personnel of website navigation products, although the page contents may be designed to many categories, the coverage of the website navigation contents is extremely limited compared with the information amount which is huge in quantity and also increases at a high speed on the internet, and in addition, the single service of the static pages cannot adapt to the requirement of personalized browsing of internet users. Therefore, a technical problem to be solved by those skilled in the art is to provide a website navigation recommendation method to provide personalized website navigation for different users.
Disclosure of Invention
The invention provides a method, a device and a system for recommending websites based on domain name access history records, which can provide websites more conforming to the attention of a user when the user browses navigation pages, and realize personalized website navigation for different users.
The invention provides the following scheme:
a method for recommending websites based on domain name access history records comprises the following steps:
acquiring a domain name access history record of a user; the domain name access history record comprises domain names of websites accessed by the user;
acquiring category labels respectively corresponding to the domain names in the domain name access history record;
acquiring a target class label according to the domain name access history record and the class label;
obtaining a candidate domain name for recommendation according to the target category label;
determining a recommended website based on the candidate domain name;
displaying a recommended website in a navigation page browsed by the user;
wherein the determining a recommended website based on the candidate domain name comprises: and sequencing the candidate domain names, and determining the recommended website according to the sequencing result.
Optionally, the obtaining of the domain name access history of the user includes:
receiving a domain name access history record uploaded by a client and corresponding user identification information;
displaying a recommended website in a navigation page browsed by the user, wherein the recommended website comprises the following steps:
and pushing the recommended website to a corresponding client according to the user identification information so as to display the recommended website in a navigation page browsed by the user corresponding to the user identification information.
Optionally, the method further includes:
storing the user identification information, a target category label corresponding to the user identification information, and a recommended website corresponding to the user identification information;
the pushing the recommended website to a corresponding client according to the user identification information comprises:
and when the user browses the navigation page, transmitting the target category tag corresponding to the user identification information and the recommended website corresponding to the user identification information to the client according to the user identification information uploaded by the client, so that the client can display the category tag and the recommended website in the navigation page browsed by the user.
Optionally, the obtaining of the category label corresponding to each domain name in the domain name access history record includes:
acquiring category labels corresponding to the domain names in the domain name access history record according to a pre-established database, wherein the database is used for storing the corresponding relation between the domain names and the labels;
or,
acquiring webpage information corresponding to each domain name in the domain name access history record, and performing text analysis on the webpage information to acquire category labels corresponding to the domain names respectively.
Optionally, the domain name access history record further includes access time corresponding to each domain name and access times corresponding to each domain name; the obtaining of the target category label according to the domain name access history record and the category label includes:
and acquiring a target category label according to the domain name of the website accessed by the user, the access time corresponding to each domain name and the access times corresponding to each domain name.
Optionally, the obtaining a target category label according to the domain name of the website visited by the user, the visit time corresponding to each domain name, and the visit times corresponding to each domain name includes:
and giving weight factors to each domain name in the domain name access history record in a mode that the access time is gradually reduced from near to far, taking the product of the access times corresponding to each domain name and the corresponding weight factor as the weight corresponding to each domain name, and determining the class label corresponding to the domain name reaching the preset weight threshold as a target class label.
Optionally, the obtaining of the candidate domain name for recommendation according to the target category label includes:
counting the access frequency of the user to each domain name under the target class label of the user, and determining the domain name with the access frequency meeting the preset condition as a candidate domain name for recommendation;
and/or the presence of a gas in the gas,
counting the global access quantity of each domain name under the target class label, and determining the domain name of which the global access quantity meets the preset condition as a candidate domain name for recommendation; the global access amount is the sum of the access amounts of all the counted users;
and/or the presence of a gas in the gas,
dividing all domain names under the target class labels into two subsets, wherein the domain names appearing in the user domain name access history record form a first subset, and the domain names not appearing in the user domain name access history record form a second subset; respectively calculating website similarity between each domain name in the second subset and each domain name in the first subset, and determining the domain names with the website similarity reaching preset conditions in the second subset as candidate domain names for recommendation;
and/or the presence of a gas in the gas,
and determining the clicked recommended website in the historical recommendation result of the user as a candidate domain name for recommendation.
Optionally, the sorting the candidate domain names, and determining the recommended website according to the sorting result includes:
sorting the candidate domain names according to the access times corresponding to the domain names in the user domain name access history record, and taking the domain names meeting the preset ranking condition as recommended websites;
and/or the presence of a gas in the gas,
and acquiring the preference score of the user for the candidate domain name according to the clicking condition of the user on the website in the historical recommendation result, and taking the domain name with the preference score meeting the preset conditions as the recommended website.
An apparatus for recommending a website based on a domain name access history, comprising:
the record acquisition unit is used for acquiring a domain name access history record of a user; the domain name access history record comprises domain names of websites accessed by the user;
a domain name category label obtaining unit, configured to obtain a category label corresponding to each domain name in the domain name access history record;
a target category label obtaining unit, configured to obtain a target category label according to the domain name access history and the category label;
a candidate domain name obtaining unit, configured to obtain a candidate domain name for recommendation according to the target category label;
a recommended website determining unit, configured to determine a recommended website based on the candidate domain name;
the display unit is used for displaying the recommended website in the navigation page browsed by the user;
the recommended website determining unit comprises a sorting subunit, wherein the sorting subunit is used for sorting the candidate domain names and determining the recommended websites according to a sorting result.
Optionally, the domain name class label obtaining unit includes:
a first domain name category label obtaining subunit, configured to obtain, according to a pre-established database, category labels respectively corresponding to domain names in the domain name access history, where the database is used to store a correspondence between domain names and labels;
or,
and the second domain name category label obtaining subunit is used for obtaining the webpage information corresponding to each domain name in the domain name access history record, and obtaining the category label corresponding to each domain name by performing text analysis on the webpage information.
Optionally, the domain name access history record further includes access time corresponding to each domain name and access times corresponding to each domain name; the object class label acquiring unit includes:
and the first target category label obtaining subunit is used for obtaining the target category labels according to the domain names of the websites visited by the user, the access time corresponding to each domain name and the access times corresponding to each domain name.
Optionally, the first target category label obtaining subunit is specifically configured to: and giving weight factors to each domain name in the domain name access history record in a mode that the access time is gradually reduced from near to far, taking the product of the access times corresponding to each domain name and the corresponding weight factor as the weight corresponding to each domain name, and determining the class label corresponding to the domain name reaching the preset weight threshold as a target class label.
Optionally, the candidate domain name obtaining unit includes:
the first candidate domain name acquisition subunit is used for counting the access frequency of the user to each domain name under the target class label, and determining the domain name with the access frequency meeting the preset conditions as a candidate domain name for recommendation;
and/or the presence of a gas in the gas,
the second candidate domain name acquisition subunit is used for counting the global access quantity of each domain name under the target class label and determining the domain name of which the global access quantity meets the preset condition as a candidate domain name for recommendation; the global access amount is the sum of the access amounts of all the counted users;
and/or the presence of a gas in the gas,
a third candidate domain name obtaining subunit, configured to divide all domain names under the target class label into two subsets, where domain names appearing in the user domain name access history form a first subset, and domain names not appearing in the user domain name access history form a second subset; respectively calculating website similarity between each domain name in the second subset and each domain name in the first subset, and determining the domain names with the website similarity reaching preset conditions in the second subset as candidate domain names for recommendation;
and/or the presence of a gas in the gas,
and the fourth candidate domain name acquisition subunit is used for determining the clicked recommended website in the historical recommendation result of the user as the candidate domain name for recommendation.
Optionally, the sorting subunit is specifically configured to:
sorting the candidate domain names according to the access times corresponding to the domain names in the user domain name access history record, and taking the domain names meeting the preset ranking condition as recommended websites;
and/or the presence of a gas in the gas,
and acquiring the preference score of the user for the candidate domain name according to the clicking condition of the user on the website in the historical recommendation result, and taking the domain name with the preference score meeting the preset conditions as the recommended website.
A system for recommending websites based on domain name access history records comprises a client and a server, wherein:
the client comprises:
the information acquisition unit is used for acquiring a domain name access history record of a user; the domain name access history record comprises domain names of websites accessed by the user;
the first communication unit is used for uploading the domain name access history record and the corresponding user identification information to a server;
the server side comprises:
a domain name category label obtaining unit, configured to obtain a category label corresponding to each domain name in the domain name access history record;
a target category label obtaining unit, configured to obtain a target category label according to the domain name access history and the category label;
a candidate domain name obtaining unit, configured to obtain a candidate domain name for recommendation according to the target category label;
a recommended website determining unit, configured to determine a recommended website based on the candidate domain name;
the second communication unit is used for pushing the recommended website to a corresponding client according to the user identification information;
the recommended website determining unit comprises a sorting subunit, wherein the sorting subunit is used for sorting the candidate domain names and determining the recommended websites according to a sorting result;
the client further comprises:
and the display unit is used for displaying the recommended website in the navigation page browsed by the user.
Optionally, the server further includes:
the storage unit is used for storing the user identification information, the target category label corresponding to the user identification information and the recommended website corresponding to the user identification information;
the second communication unit is specifically configured to: and when the user browses the navigation page, transmitting the target category tag corresponding to the user identification information and the recommended website corresponding to the user identification information to the client according to the user identification information uploaded by the client, so that the client can display the category tag and the recommended website in the navigation page browsed by the user.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
by the method and the device, the domain name access history record of the user can be acquired, wherein the domain name access history record comprises the domain name of the website accessed by the user; then, obtaining the class labels respectively corresponding to the domain names in the domain name access history record, thereby realizing the classification of the domain names accessed by the user; according to the domain name access history record and the class label, a target class label can be obtained, so that the class of the domain name which is more interesting to the user is obtained; the candidate domain name used for recommendation is obtained according to the target category label, so that the obtained candidate domain name can better accord with the interest of the user; and displaying the recommended website in the navigation page browsed by the user based on the candidate domain name. Therefore, when the user browses the navigation page, the website which is more in line with the user interest is provided for the user, and personalized website navigation is provided for different users.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a flow chart of a method provided by an embodiment of the present invention;
FIG. 2 is a schematic diagram of an apparatus provided by an embodiment of the present invention;
fig. 3 is a schematic diagram of a system provided by an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments that can be derived by one of ordinary skill in the art from the embodiments given herein are intended to be within the scope of the present invention. The method for recommending a website provided by the embodiment of the invention is described in detail below, and with reference to fig. 1, the method comprises the following steps:
s101: acquiring a domain name access history record of a user; the domain name access history record comprises domain names of websites accessed by the user;
a domain name is the name of a computer or group of computers on the internet, consisting of a string of names separated by dots, used to identify the electronic position of the computer, e.g., abc. In short, a domain name is a name registered on the internet by a computer or a group of computers, and a user can access the corresponding computer or group of computers through the registered name. This name may contain some information of the registrant, such as a company or organization name, service content, and the like. And the domain names have level differences, such as the above-mentioned abc.com is a top-level domain name, the top-level domain name is distributed by a special international organization, and a second-level domain name and a third-level domain name can exist under the top-level domain name, for example, the news. Some second-level domain names, especially those registered for some commercial organizations, may be used to distinguish and highlight different service tiles, whereas different service tiles may often be reflected by different second-level domain names, such as news.
For a user, a domain name usually represents a website, each webpage browsed by the user is a file preset in a certain folder downloaded from a server of the website, and domain name information contained in a website can be obtained by browsing the website of the webpage by the user, for example, the website visited by the user is sport, abc, com/football/fifa2010/123.htm, and the domain name contained therein can be obtained: sports. In the method provided by the embodiment of the invention, the domain name access history of the user is acquired, wherein the acquired domain name access history can include the domain name of the website accessed by the user. In addition, the browsing frequency of a user to a certain website or a certain type of websites can often reflect the preference degree of the user to the website or the website type, so the domain name access history record of the user can also comprise the number of times of accessing the domain name, which is used for reflecting the preference degree of the user to a certain website; in addition, the domain names visited by the user in the near future often have higher attention degree than domain names visited in the far future, so the domain name visit history record of the user can also contain corresponding time information for visiting each domain name.
Specifically, when the domain name access history of the user is obtained, the domain name access history of the user may be recorded by a computer program of the user, for example, by a browser having a domain name access history obtaining function, when the user browses a web page; or recording the domain name access history of the user when the user browses the webpage through a plug-in of a browser with a domain name access history acquisition function; for example, by having software capable of monitoring the browsing behavior of the user, when the user browses a web page through a browser, the website information browsed by the user can be monitored, and the domain name of the website is extracted from the website information, so as to obtain the domain name access history of the user.
In addition, the domain name access history of the user can be acquired by using a client/server side mode, the client can be a browser, a browser plug-in and other application programs with a domain name access history acquisition function, and the domain name access history of the user is acquired through the client and uploaded to the server side. Specifically, the domain name access history of the user is acquired at the client and uploaded to the server, or the domain name access history of the user is acquired in real time and uploaded to the server when the user accesses the website by the client; or when the user accesses the website, the domain name access information of the user is recorded as a log file, and the log file is uploaded to the server under certain conditions. The certain condition here may be that the client periodically transmits the log file to the server, for example, the client transmits the log file to the server every week, or the log file is uploaded to the server when the log file reaches a certain disk space occupation amount, for example, each time the log file reaches 100KB in size. In order to identify different users, a corresponding unique user identification information may be generated for each user at the client, or, of course, a request may be sent from the client to the server, and then the server allocates a corresponding unique user identification information to the user. The client side can upload the identification information of the user to the server side at the same time of uploading the domain name access history of the user.
S102: acquiring category labels respectively corresponding to the domain names in the domain name access history record;
after the domain name access history of the user is obtained, the category label of each domain name in the domain name access history of the user can be obtained. A category label of a domain name is generally an information category of a web page included in a web page under the domain name, such as sports, abc.com, and a web page under the domain name may include various aspects of sports information, and then the category label of the domain name may be determined as "sports"; com, and the web pages below it may contain information of various fashion trends, the category label of the domain name may be determined as "fashion".
Specifically, when the category labels respectively corresponding to the domain names in the domain name access history are obtained, the commonly used domain names may be collected in advance, then the category labels are added to the domain names in a manner of manual labeling or the like, and a database is established for storing the corresponding relationship between the domain names and the category labels. In this way, when the category label of a domain name needs to be obtained, the category label corresponding to each domain name can be determined according to the pre-established database storing the preset correspondence between the domain name and the label, and specifically, the category label corresponding to the domain name can be obtained by searching in the database according to the domain name information; alternatively, the information in the web page corresponding to each domain name in the domain name access history, such as the title, text and other contents of the web page, may be obtained, the subject classification of the information in the web page may be obtained by performing text analysis on the web page information, and then the category label corresponding to each domain name may be obtained. For example, for the domain name of sports, abc.com, assuming that the title of the web page corresponding to the domain name is "abc sports", the category label of the domain name can be analyzed as "sports" through the title. Specifically, when text analysis is performed on webpage information, the text information in the webpage can be captured and then word segmentation analysis is performed, and how to capture the text information and how to perform word segmentation analysis can be realized by the prior art, which is not repeated herein.
S103: acquiring a target class label according to the domain name access history record and the class label;
the history of the user's visit to the domain name may generally reflect which category of information the user has a higher degree of attention to, for example, if a user visits a sports website frequently, it may reflect that the user has a higher degree of attention to the sports information. The category of the domain name accessed by the user can be represented by the category label of each domain name accessed by the user. The domain name category with higher attention of the user, namely the target category label with more interest of the user, can be obtained according to the domain name access history record and the category label of the domain name. In the domain name access history record of the user, the website domain name that the user has visited may be included, and information that may reflect the degree of attention of the user to the domain name may also be included, such as access time, access times, and the like corresponding to each domain name. According to the website domain names visited by the user, the information of the attention degree of the user to the domain names, such as the visit time and the visit times corresponding to each domain name, and the category labels corresponding to the visited domain names of the user can be reflected, so that the category labels which are just interested by the user are determined.
Specifically, when the target category label is determined according to the user domain name access history and the category label corresponding to the domain name accessed by the user, the target category label can be determined according to the total number of times that the user accesses the domain name under each label, and the total number of times that the user accesses the domain name under a certain category label is large, which generally indicates that the user has a high degree of attention to such information, so that the category label representing the category of the domain name can be determined as the target category label in which the user is interested. Specifically, the category labels of the first few bits with the larger total number of domain name visits may be used as the target category labels interested by the user, or a threshold may be preset, and the category labels with the total number of domain name visits reaching the preset threshold may be used as the target category labels interested by the user.
In addition, the target category labels in which the user is interested can be determined according to the access time of the user to each domain name under the category labels, because the user usually has higher attention to domain names accessed in the near future compared with domain names accessed in the far future. Specifically, a weight factor may be given to each domain name in the domain name access history record in a manner that the access time decreases from near to far, the product of the access times corresponding to each domain name and the corresponding weight factor is used as the weight corresponding to each domain name, and the class label corresponding to the domain name that reaches the preset weight threshold is determined as the target class label. For example, if the information in the domain name access history is the access record of the user from 6 month 1 to 6 month 30, the weight factor for 6 month 1 is set to 1,6 month 2 is set to 2, 6 month 3 is set to 3, and so on, 6 month 30 is set to 30, and then the weight of the domain name is obtained by multiplying the access frequency of the domain name by the corresponding weight factor. For example, if the access time of a certain domain name sport.abc.com is 6 months and 10 days, the corresponding weight factor is 10, and the number of accesses is 10, the finally calculated weight is 100; com is 6 months and 20 days, the corresponding weight factor is 20, the number of accesses is 8, and the final calculated weight is 160. It can be seen that although the number of accesses by the user to sports.abc.com is slightly greater than that to yule.abc.com, the former is slightly lower than the latter in the weight calculated finally.
It should be noted that the foregoing description of the weight factors is only for convenience of understanding, and the size of the weight factors may be set according to actual requirements in practical applications, and in addition, the weight factors are not necessarily increased or decreased in units of days, and may also be in units of hours, for example. It should be noted that, in the information recorded in the domain name access history record, the number of times of access corresponding to a domain name may be multiple times, and at this time, the access time corresponding to the domain name may be the time of the last access.
S104: obtaining a candidate domain name for recommendation according to the target category label;
the target category label is generally a category label in which the user is interested, and may reflect a domain name category with a relatively high attention of the user, so that a candidate domain name for recommendation may be obtained according to the target category label. In specific implementation, the following implementation modes can be provided:
1) and counting the access frequency of the user to each domain name under the target category label, and determining the domain name with the access frequency meeting the preset conditions as a candidate domain name for recommendation. The domain name is a domain name which the user has visited once, and the frequency of visiting the domain name or domains by the user reflects the preference degree of the user for the domain name or domains to a certain extent, that is, the domain name which the user frequently visits can be used as a candidate domain name for recommendation.
2) And counting the global access quantity of each domain name under the target class label, and determining the domain name of which the global access quantity meets the preset condition as a candidate domain name for recommendation. And the global access amount is the sum of the access amounts of all the counted users. Compared with the information of the internet which is too expensive, the amount of information which can be accessed by each user is very limited, and when the website is recommended to the user, a domain name of which the global access amount meets certain preset conditions under a certain class of labels can be considered as a candidate domain name, so that more choices are provided for the user. In specific implementation, the global access amount of each domain name may be respectively counted (that is, the counted access times of all users to the domain name are added), when a user is recommended, after a target class label is determined, all domain names under the class label are found in the database, and then the domain name with a larger global access amount under the target class label is determined as a candidate domain name for recommendation. For example, the target category label of interest to the user a includes "sports", and in the database, the category of "sports" includes domain name 1, domain name 2, domain name 3, and the like, where domain name 1 and domain name 2 may not be the domain names visited by the user a, but the global access amount of the two domain names is relatively large, and then the two domain names can be used as candidate domain names for recommendation.
3) Dividing all domain names under the target class labels into two subsets, wherein the domain names appearing in the user domain name access history record form a first subset, and the domain names not appearing in the user domain name access history record form a second subset; and respectively calculating the website similarity between each domain name in the second subset and each domain name in the first subset, and determining the domain name with the website similarity reaching the preset condition in the second subset as a candidate domain name for recommendation. Similar to the second method, when selecting the candidate domain name for recommendation, the determination is also made based on all domain names under the target category label in which the user is interested, but the selection is based on the global access amount of each domain name, and the similarity between the domain name not visited by the user and the visited domain name on the website content. That is, if one domain name has the same category label as another domain name, and if the user has visited one of the domain names, the probability that the user will visit the other domain name is also higher, and therefore, the domain name can also be used as a candidate domain name for recommendation. The method for calculating the similarity of the websites can be the same as that in the prior art, and is not described herein again. As for the preset condition, a similarity threshold may be preset, and if the similarity threshold is larger than the threshold, the recommendation may be made, and so on.
4) And determining the clicked recommended website in the historical recommendation result of the user as a candidate domain name for recommendation. In practical application, after the recommendation result is determined, the recommendation result is displayed to a user in a relatively fixed area of a webpage for the user to click. If the user clicks the recommended website in the historical recommendation result, the historical recommended website meets the requirements of the user to a certain extent, so that the website clicked by the user in the historical recommendation result can be continuously used as a candidate domain name for recommendation.
In addition, several of the above implementations can be applied in combination, so that the candidate domain names for recommendation can better meet the interest of the user.
S105: determining a recommended website based on the candidate domain name;
the candidate domain names obtained through the steps are domain names which are more relevant to attention tendency and are further visited by the user, and can be displayed to the user as recommended websites on a navigation page browsed by the user. The display area of the navigation page is usually limited, so that all the candidate domain names can be displayed for the user in a scrolling manner on the navigation page; in addition, the candidate domain names can be further sorted firstly, and the sorted result is displayed to the user so as to better meet the requirements of the user. Specifically, when the candidate domain names are sorted and the sorted result is displayed to the user, the candidate domain names can be sorted according to the access times corresponding to the domain names in the user domain name access history record, and the domain names meeting the preset ranking condition are displayed to the user as recommended websites; the preference score of the user for the candidate domain name can be obtained according to the clicking condition of the user on the website in the historical recommendation result, and the domain name with the preference score meeting the preset conditions is used as the recommended website to be displayed to the user; and the two methods are combined to make the recommended website displayed in the navigation page more fit with the interest of the user. When the recommended website is displayed to the user, the category label to which the domain name corresponding to the recommended website belongs can be displayed to the user at the same time, so that the user can browse interested websites better. Of course, in the above several sorting manners, because only two factors, that is, the access condition of the current user and/or the click condition in the recommendation result, are considered, if only several domain names ranked in front after sorting are recommended to the user, a website that has a large global access amount and is not visited by the user or has a high website similarity to the domain name visited by the user may not be recommended, and therefore, in practical applications, a region may be reserved in the recommendation result display region for displaying the domain name that has not been visited by the user before but is likely to be interested by the user, so as to expand the recommendation range.
S106: and displaying the recommended website in the navigation page browsed by the user.
After the website for recommending to the user is obtained, the recommended website can be presented in a navigation page browsed by the user. That is, a user can see an area in a navigation page, where the displayed content is a website recommended to the user according to the access history of the user, in other words, when different users navigate the same website in a browser, the website in the area may be different, thereby showing personalization among different users.
In a specific implementation, the execution subject of the foregoing steps S101 to S105 may be an application program of a client, that is, the foregoing technical solution provided in the embodiment of the present invention is implemented by a client program alone, and of course, a database and the like that need to be used may be stored in the local of the client in advance, and the database may also be updated by a server, and the like. Alternatively, the method provided by the embodiment of the present invention may also be implemented in a client/server manner. At this time, the domain name access condition of the user can be collected by the client, then uploaded to the server, further analyzed and calculated by the server, and a target category label interested by the user, a candidate domain name recommended to the user and the like are determined, then pushed to the client, and displayed to the user by the client. Certainly, since the same server generally corresponds to a plurality of clients, the server needs to distinguish information uploaded by different clients, and at this time, the client uploads user identification information while uploading a domain name access record, so that the server can distinguish different users according to the user identification information uploaded by the client, and a recommended website is displayed in a navigation page browsed by the user corresponding to the user identification information. The server side can also store information such as user identification information, a target category label which is corresponding to the user identification information and is interested by the user, a recommended website which is corresponding to the user identification information and the like, and when the user browses a navigation page, the target category label which is corresponding to the user identification information and is interested by the user and the recommended website which is corresponding to the user identification information are transmitted to the client side according to the user identification information uploaded by the client side, so that the client side can display the category label and the recommended website in the navigation page browsed by the user.
The user identification information may be ID information automatically generated for the user when the user installs the client program, and such IDs generally have uniqueness, so that the client can upload the ID information when uploading the user identification information. Of course, it could also be the user's IP address, or the user's account information in case of a login, etc.
In summary, by the method provided by the embodiment of the present invention, a domain name access history of a user can be obtained, where the domain name access history includes a domain name of a website accessed by the user; then, obtaining the class labels respectively corresponding to the domain names in the domain name access history record, thereby realizing the classification of the domain names accessed by the user; according to the domain name access history record and the class label, a target class label can be obtained, so that the class of the domain name which is more interesting to the user is obtained; the candidate domain name used for recommendation is obtained according to the target category label, so that the obtained candidate domain name can better accord with interest attention of the user; and displaying the recommended website in the navigation page browsed by the user based on the candidate domain name. Therefore, when the user browses the navigation page, the website which is more in line with the interest attention of the user is provided for the user, and personalized website navigation is provided for different users.
Corresponding to the method for recommending a website provided in the embodiment of the present invention, the embodiment of the present invention further provides a device for recommending a website, referring to fig. 2, where the device may specifically include:
a record acquisition unit 201, configured to acquire a domain name access history record of a user; the domain name access history record comprises domain names of websites accessed by the user;
a domain name category label obtaining unit 202, configured to obtain a category label corresponding to each domain name in the domain name access history record;
a target category label obtaining unit 203, configured to obtain a target category label according to the domain name access history and the category label;
a candidate domain name obtaining unit 204, configured to obtain a candidate domain name for recommendation according to the target category label;
a recommended website determining unit 205, configured to determine a recommended website based on the candidate domain name;
the presentation unit 206 is configured to present the recommended website in the navigation page browsed by the user.
The domain name class label obtaining unit 202 may include:
a first domain name category label obtaining subunit, configured to obtain, according to a pre-established database, category labels respectively corresponding to domain names in the domain name access history, where the database is used to store a correspondence between domain names and labels;
or,
and the second domain name category label obtaining subunit is used for obtaining the webpage information corresponding to each domain name in the domain name access history record, and obtaining the category label corresponding to each domain name by performing text analysis on the webpage information.
The domain name access history record can also comprise access time corresponding to each domain name and access times corresponding to each domain name; the object class label acquiring unit 203 at this time may include:
and the first target category label obtaining subunit is used for obtaining the target category labels according to the domain names of the websites visited by the user, the access time corresponding to each domain name and the access times corresponding to each domain name. Here, the first target category tag obtaining subunit may specifically be configured to: and giving weight factors to each domain name in the domain name access history record in a mode that the access time is gradually reduced from near to far, taking the product of the access times corresponding to each domain name and the corresponding weight factor as the weight corresponding to each domain name, and determining the class label corresponding to the domain name reaching the preset weight threshold as a target class label.
The candidate domain name obtaining unit 204 may include:
the first candidate domain name acquisition subunit is used for counting the access frequency of the user to each domain name under the target class label, and determining the domain name with the access frequency meeting the preset conditions as a candidate domain name for recommendation;
and/or the presence of a gas in the gas,
the second candidate domain name acquisition subunit is used for counting the global access quantity of each domain name under the target class label and determining the domain name of which the global access quantity meets the preset condition as a candidate domain name for recommendation; the global access amount is the sum of the access amounts of all the counted users;
and/or the presence of a gas in the gas,
a third candidate domain name obtaining subunit, configured to divide all domain names under the target class label into two subsets, where domain names appearing in the user domain name access history form a first subset, and domain names not appearing in the user domain name access history form a second subset; respectively calculating website similarity between each domain name in the second subset and each domain name in the first subset, and determining the domain names with the website similarity reaching preset conditions in the second subset as candidate domain names for recommendation;
and/or the presence of a gas in the gas,
and the fourth candidate domain name acquisition subunit is used for determining the clicked recommended website in the historical recommendation result of the user as the candidate domain name for recommendation.
In order to present the preferred domain name to the user, the recommended website determining unit 205 may include:
and the sorting subunit is used for sorting the candidate domain names and determining the recommended website according to the sorting result.
The sorting subunit may be specifically configured to:
sorting the candidate domain names according to the access times corresponding to the domain names in the user domain name access history record, and displaying the domain names meeting the preset ranking condition as recommended websites to the user;
and/or the presence of a gas in the gas,
and according to the clicking condition of the user on the website in the historical recommendation result, acquiring the preference score of the user on the candidate domain name, and showing the domain name with the preference score meeting the preset conditions as the recommended website to the user.
In summary, with the device provided by the embodiment of the present invention, a domain name access history of a user can be obtained, where the domain name access history includes a domain name of a website accessed by the user; then, obtaining the class labels respectively corresponding to the domain names in the domain name access history record, thereby realizing the classification of the domain names accessed by the user; according to the domain name access history record and the class label, a target class label can be obtained, so that the class of the domain name which is more interesting to the user is obtained; the candidate domain name used for recommendation is obtained according to the target category label, so that the obtained candidate domain name can better accord with interest attention of the user; and displaying the recommended website in the navigation page browsed by the user based on the candidate domain name. Therefore, when the user browses the navigation page, the website which is more in line with the interest attention of the user is provided for the user, and personalized website navigation is provided for different users.
In addition, corresponding to the method and the apparatus for recommending a website provided by the embodiment of the present invention, the embodiment of the present invention further provides a system for recommending a website, referring to fig. 3, the system includes a client 301 and a server 302, where:
the client 301 includes:
an information acquisition unit 3011, configured to acquire a domain name access history of a user; the domain name access history record comprises domain names of websites accessed by the user;
a first communication unit 3012, configured to upload the domain name access history record and corresponding user identification information to a server;
the server 302 includes:
a domain name category label obtaining unit 3021, configured to obtain category labels corresponding to the domain names in the domain name access history record respectively;
a target category label obtaining unit 3022, configured to obtain a target category label according to the domain name access history and the category label;
a candidate domain name obtaining unit 3023, configured to obtain a candidate domain name for recommendation according to the target category label;
a recommended website determining unit 3024, configured to determine a recommended website based on the candidate domain name;
the second communication unit 3025 is configured to push the recommended website to a corresponding client according to the user identification information;
the client 301 further includes:
the presentation unit 3013 is configured to present a recommended website in the navigation page browsed by the user.
In practical applications, the server 302 may further include:
the storage unit is used for storing the user identification information, the target category label corresponding to the user identification information and the recommended website corresponding to the user identification information;
at this time, the second communication unit 3024 is specifically configured to: and when the user browses the navigation page, transmitting the target category tag corresponding to the user identification information and the recommended website corresponding to the user identification information to the client according to the user identification information uploaded by the client, so that the client can display the category tag and the recommended website in the navigation page browsed by the user.
From the above description of the embodiments, it is clear to those skilled in the art that the present invention can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which may be stored in a storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the embodiments or some parts of the embodiments.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for apparatus or system embodiments, since they are substantially similar to method embodiments, they are described in relative terms, as long as they are described in partial descriptions of method embodiments. The above-described embodiments of the apparatus and system are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The method, the device and the system for recommending the website provided by the invention are introduced in detail, a specific example is applied in the text to explain the principle and the implementation mode of the invention, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (16)
1. A method for recommending a website based on a domain name access history record is characterized by comprising the following steps:
acquiring category labels respectively corresponding to all domain names in a domain name access history record of a user;
determining a target class label according to the domain name access history of the user and the class label;
determining a candidate domain name for recommendation according to the target category label;
sorting the candidate domain names, and determining a recommended website according to a sorting result;
and displaying the recommended website in a navigation page browsed by the user.
2. The method of claim 1, wherein obtaining the domain name access history of the user comprises:
receiving a domain name access history record uploaded by a client and corresponding user identification information;
displaying a recommended website in a navigation page browsed by the user, wherein the recommended website comprises the following steps:
and pushing the recommended website to a corresponding client according to the user identification information so as to display the recommended website in a navigation page browsed by the user corresponding to the user identification information.
3. The method of claim 2, further comprising:
storing the user identification information, a target category label corresponding to the user identification information, and a recommended website corresponding to the user identification information;
the pushing the recommended website to a corresponding client according to the user identification information comprises:
and when the user browses the navigation page, transmitting the target category tag corresponding to the user identification information and the recommended website corresponding to the user identification information to the client according to the user identification information uploaded by the client, so that the client can display the category tag and the recommended website in the navigation page browsed by the user.
4. The method according to any one of claims 1 to 3, wherein the obtaining of the category label corresponding to each domain name in the domain name access history record comprises:
acquiring category labels corresponding to the domain names in the domain name access history record according to a pre-established database, wherein the database is used for storing the corresponding relation between the domain names and the labels;
or,
acquiring webpage information corresponding to each domain name in the domain name access history record, and performing text analysis on the webpage information to acquire category labels corresponding to the domain names respectively.
5. The method according to any one of claims 1 to 3, wherein the domain name access history record further includes access time corresponding to each domain name and access times corresponding to each domain name; the obtaining of the target category label according to the domain name access history record and the category label includes:
and acquiring a target category label according to the domain name of the website accessed by the user, the access time corresponding to each domain name and the access times corresponding to each domain name.
6. The method according to claim 5, wherein the obtaining the target category label according to the domain name of the website visited by the user, the visit time corresponding to each domain name, and the visit times corresponding to each domain name comprises:
and giving weight factors to each domain name in the domain name access history record in a mode that the access time is gradually reduced from near to far, taking the product of the access times corresponding to each domain name and the corresponding weight factor as the weight corresponding to each domain name, and determining the class label corresponding to the domain name reaching the preset weight threshold as a target class label.
7. The method according to any one of claims 1 to 3, wherein the obtaining of the candidate domain name for recommendation according to the target category label comprises:
counting the access frequency of the user to each domain name under the target class label of the user, and determining the domain name with the access frequency meeting the preset condition as a candidate domain name for recommendation;
and/or the presence of a gas in the gas,
counting the global access quantity of each domain name under the target class label, and determining the domain name of which the global access quantity meets the preset condition as a candidate domain name for recommendation; the global access amount is the sum of the access amounts of all the counted users;
and/or the presence of a gas in the gas,
dividing all domain names under the target class labels into two subsets, wherein the domain names appearing in the user domain name access history record form a first subset, and the domain names not appearing in the user domain name access history record form a second subset; respectively calculating website similarity between each domain name in the second subset and each domain name in the first subset, and determining the domain names with the website similarity reaching preset conditions in the second subset as candidate domain names for recommendation;
and/or the presence of a gas in the gas,
and determining the clicked recommended website in the historical recommendation result of the user as a candidate domain name for recommendation.
8. The method according to claim 1, wherein the sorting the candidate domain names and the determining the recommended website according to the sorting result comprises:
sorting the candidate domain names according to the access times corresponding to the domain names in the user domain name access history record, and taking the domain names meeting the preset ranking condition as recommended websites;
and/or the presence of a gas in the gas,
and acquiring the preference score of the user for the candidate domain name according to the clicking condition of the user on the website in the historical recommendation result, and taking the domain name with the preference score meeting the preset conditions as the recommended website.
9. An apparatus for recommending a website based on a domain name access history record, comprising:
the domain name category label acquiring unit is used for acquiring category labels corresponding to domain names in a domain name access history record of a user;
a target category label obtaining unit, configured to determine a target category label according to the domain name access history of the user and the category label;
a candidate domain name obtaining unit, configured to determine a candidate domain name for recommendation according to the target category label;
the recommended website determining unit comprises a sorting subunit, the sorting subunit is used for sorting the candidate domain names and determining the recommended websites according to a sorting result;
and the display unit is used for displaying the recommended website in the navigation page browsed by the user.
10. The apparatus according to claim 9, wherein the domain name class label obtaining unit includes:
a first domain name category label obtaining subunit, configured to obtain, according to a pre-established database, category labels respectively corresponding to domain names in the domain name access history, where the database is used to store a correspondence between domain names and labels;
or,
and the second domain name category label obtaining subunit is used for obtaining the webpage information corresponding to each domain name in the domain name access history record, and obtaining the category label corresponding to each domain name by performing text analysis on the webpage information.
11. The apparatus according to claim 9, wherein the domain name access history record further includes access time corresponding to each domain name and access times corresponding to each domain name; the object class label acquiring unit includes:
and the first target category label obtaining subunit is used for obtaining the target category labels according to the domain names of the websites visited by the user, the access time corresponding to each domain name and the access times corresponding to each domain name.
12. The apparatus according to claim 11, wherein the first object class tag obtaining subunit is specifically configured to: and giving weight factors to each domain name in the domain name access history record in a mode that the access time is gradually reduced from near to far, taking the product of the access times corresponding to each domain name and the corresponding weight factor as the weight corresponding to each domain name, and determining the class label corresponding to the domain name reaching the preset weight threshold as a target class label.
13. The apparatus of claim 9, wherein the candidate domain name obtaining unit comprises:
the first candidate domain name acquisition subunit is used for counting the access frequency of the user to each domain name under the target class label, and determining the domain name with the access frequency meeting the preset conditions as a candidate domain name for recommendation;
and/or the presence of a gas in the gas,
the second candidate domain name acquisition subunit is used for counting the global access quantity of each domain name under the target class label and determining the domain name of which the global access quantity meets the preset condition as a candidate domain name for recommendation; the global access amount is the sum of the access amounts of all the counted users;
and/or the presence of a gas in the gas,
a third candidate domain name obtaining subunit, configured to divide all domain names under the target class label into two subsets, where domain names appearing in the user domain name access history form a first subset, and domain names not appearing in the user domain name access history form a second subset; respectively calculating website similarity between each domain name in the second subset and each domain name in the first subset, and determining the domain names with the website similarity reaching preset conditions in the second subset as candidate domain names for recommendation;
and/or the presence of a gas in the gas,
and the fourth candidate domain name acquisition subunit is used for determining the clicked recommended website in the historical recommendation result of the user as the candidate domain name for recommendation.
14. The apparatus according to claim 9, wherein the ordering subunit is specifically configured to:
sorting the candidate domain names according to the access times corresponding to the domain names in the user domain name access history record, and taking the domain names meeting the preset ranking condition as recommended websites;
and/or the presence of a gas in the gas,
and acquiring the preference score of the user for the candidate domain name according to the clicking condition of the user on the website in the historical recommendation result, and taking the domain name with the preference score meeting the preset conditions as the recommended website.
15. A system for recommending websites based on domain name access history records is characterized by comprising a client and a server, wherein:
the client comprises:
the information acquisition unit is used for acquiring a domain name access history record of a user; the domain name access history record comprises domain names of websites accessed by the user;
the first communication unit is used for uploading the domain name access history record and the corresponding user identification information to a server;
the server side comprises:
a domain name category label obtaining unit, configured to obtain a category label corresponding to each domain name in the domain name access history record;
a target category label obtaining unit, configured to determine a target category label according to the domain name access history and the category label;
a candidate domain name obtaining unit, configured to determine a candidate domain name for recommendation according to the target category label;
a recommended website determining unit, configured to perform ranking based on the candidate domain name, and determine a recommended website according to a ranking result;
the second communication unit is used for pushing the recommended website to a corresponding client according to the user identification information;
the client further comprises:
and the display unit is used for displaying the recommended website in the navigation page browsed by the user.
16. The system of claim 15, wherein the server further comprises:
the storage unit is used for storing the user identification information, the target category label corresponding to the user identification information and the recommended website corresponding to the user identification information;
the second communication unit is specifically configured to: and when the user browses the navigation page, transmitting the target category tag corresponding to the user identification information and the recommended website corresponding to the user identification information to the client according to the user identification information uploaded by the client, so that the client can display the category tag and the recommended website in the navigation page browsed by the user.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610170286.7A CN105868291A (en) | 2012-07-10 | 2012-07-10 | Website address recommendation method, apparatus and system |
| CN201210239708.3A CN102799662B (en) | 2012-07-10 | 2012-07-10 | Method, the Apparatus and system of network address is recommended based on domain name access historical record |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210239708.3A CN102799662B (en) | 2012-07-10 | 2012-07-10 | Method, the Apparatus and system of network address is recommended based on domain name access historical record |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610170286.7A Division CN105868291A (en) | 2012-07-10 | 2012-07-10 | Website address recommendation method, apparatus and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102799662A CN102799662A (en) | 2012-11-28 |
| CN102799662B true CN102799662B (en) | 2016-04-20 |
Family
ID=47198772
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610170286.7A Pending CN105868291A (en) | 2012-07-10 | 2012-07-10 | Website address recommendation method, apparatus and system |
| CN201210239708.3A Active CN102799662B (en) | 2012-07-10 | 2012-07-10 | Method, the Apparatus and system of network address is recommended based on domain name access historical record |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610170286.7A Pending CN105868291A (en) | 2012-07-10 | 2012-07-10 | Website address recommendation method, apparatus and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN105868291A (en) |
Families Citing this family (53)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103049497A (en) * | 2012-12-07 | 2013-04-17 | 北京奇虎科技有限公司 | Method and device for website navigation |
| CN103034707A (en) * | 2012-12-07 | 2013-04-10 | 北京奇虎科技有限公司 | Website navigation method, device and browser client |
| CN103870512A (en) * | 2012-12-18 | 2014-06-18 | 腾讯科技（深圳）有限公司 | Method and device for generating user interest label |
| CN103078967B (en) * | 2013-01-11 | 2016-06-01 | 北京奇虎科技有限公司 | A kind of generate conventional network address client terminal, server, system and method |
| CN103944935A (en) * | 2013-01-21 | 2014-07-23 | 深圳市世纪光速信息技术有限公司 | Method and device for releasing web site information |
| CN103997507B (en) * | 2013-02-20 | 2018-09-07 | 腾讯科技（深圳）有限公司 | A kind of method for pushing and device of information |
| CN104156356B (en) * | 2013-05-13 | 2019-08-23 | 腾讯科技（深圳）有限公司 | Personalized Navigation page generation method and device |
| CN110059255B (en) * | 2013-05-31 | 2022-09-13 | 腾讯科技（深圳）有限公司 | Browser navigation method, device and medium |
| CN104753979B (en) * | 2013-12-25 | 2018-12-28 | 腾讯科技（深圳）有限公司 | A kind of method, server, terminal and system showing site information |
| CN103701951B (en) * | 2013-12-27 | 2018-03-06 | 北京奇安信科技有限公司 | The analysis method of website visiting record and the analytical equipment of website visiting record |
| CN104767770B (en) * | 2014-01-02 | 2019-08-13 | 腾讯科技（深圳）有限公司 | The method for pushing and server of quick links |
| CN103902685A (en) * | 2014-03-25 | 2014-07-02 | 百度在线网络技术（北京）有限公司 | Data recommendation method and device |
| CN103973834B (en) * | 2014-05-12 | 2017-07-25 | 重庆邮电大学 | A kind of DNS name resolution accelerating method and device based on home gateway |
| CN104077713B (en) * | 2014-06-16 | 2017-11-03 | 微梦创科网络科技（中国）有限公司 | Access need assessment, advertisement sending method and the system of the user of website |
| CN104156232B (en) * | 2014-07-18 | 2018-09-07 | 百度在线网络技术（北京）有限公司 | The non-linear method and apparatus redirected of the page is used under linear page structure |
| CN104216965B (en) * | 2014-08-21 | 2018-11-20 | 北京金山安全软件有限公司 | Information recommendation method and device |
| CN105989122A (en) * | 2015-02-12 | 2016-10-05 | 广东欧珀移动通信有限公司 | Application recommendation method and device |
| CN105117434A (en) * | 2015-08-07 | 2015-12-02 | 北京品友互动信息技术有限公司 | Webpage classification method and webpage classification system |
| WO2017028099A1 (en) * | 2015-08-16 | 2017-02-23 | 常平 | Website recommendation method and website recommendation system |
| WO2017028095A1 (en) * | 2015-08-16 | 2017-02-23 | 常平 | Method and data processing system for identifying user interest according to website browsing time |
| CN105243144A (en) * | 2015-10-15 | 2016-01-13 | 桂林电子科技大学 | Method and device for recommending interesting labels |
| CN106649316B (en) * | 2015-10-29 | 2020-11-27 | 北京国双科技有限公司 | Video pushing method and device |
| CN106649347A (en) * | 2015-10-30 | 2017-05-10 | 北京国双科技有限公司 | Interest information identification method and apparatus |
| CN105426432A (en) * | 2015-11-02 | 2016-03-23 | 广东欧珀移动通信有限公司 | Website ranking method and device |
| CN105488205B (en) * | 2015-12-09 | 2019-05-03 | 百度在线网络技术（北京）有限公司 | Page generation method and device |
| CN105426537A (en) * | 2015-12-21 | 2016-03-23 | 北京奇虎科技有限公司 | Recommendation method for navigation page search keywords and terminal equipment |
| CN105577668A (en) * | 2015-12-25 | 2016-05-11 | 北京奇虎科技有限公司 | Network connection control method and device |
| CN107368488A (en) | 2016-05-12 | 2017-11-21 | 阿里巴巴集团控股有限公司 | A kind of method for determining user behavior preference, the methods of exhibiting and device of recommendation information |
| CN105956161B (en) * | 2016-05-17 | 2019-07-02 | 北京奇虎科技有限公司 | A kind of information recommendation method and device |
| CN106202513A (en) * | 2016-07-21 | 2016-12-07 | 乐视控股（北京）有限公司 | Method and apparatus is recommended by the main website that browses of browser |
| CN106469206A (en) * | 2016-08-31 | 2017-03-01 | 广州酷狗计算机科技有限公司 | The method and apparatus of pushed information |
| CN108073613A (en) * | 2016-11-14 | 2018-05-25 | 腾讯科技（深圳）有限公司 | Method for sending information and device |
| CN107045525B (en) * | 2016-12-30 | 2020-12-01 | 江苏号百信息服务有限公司 | Broadband speed-up method, intelligent navigation system and intelligent navigation network |
| CN107094134A (en) * | 2017-03-09 | 2017-08-25 | 咪咕数字传媒有限公司 | A kind of method and client of access website |
| CN107220318A (en) * | 2017-05-18 | 2017-09-29 | 重庆大学 | A kind of method for determining special student groups online feature |
| CN109561162A (en) * | 2017-09-26 | 2019-04-02 | 北京国双科技有限公司 | Excavate the method and device that user accesses hobby |
| CN107944026A (en) * | 2017-12-12 | 2018-04-20 | 百度在线网络技术（北京）有限公司 | A kind of method, apparatus, server and the storage medium of atlas personalized recommendation |
| CN108665347A (en) * | 2018-05-07 | 2018-10-16 | 平安普惠企业管理有限公司 | Products Show method, apparatus, equipment and storage medium based on user demand |
| CN109361929B (en) * | 2018-09-28 | 2021-05-28 | 武汉斗鱼网络科技有限公司 | Method for determining live broadcast room label and related equipment |
| CN109636497A (en) * | 2018-10-26 | 2019-04-16 | 平安科技（深圳）有限公司 | A kind of Products Show method and apparatus |
| CN109597928B (en) * | 2018-12-05 | 2022-12-16 | 云南电网有限责任公司信息中心 | Unstructured text acquisition method supporting user policy configuration and based on Web network |
| CN109658206B (en) * | 2019-01-14 | 2022-07-26 | 京东方科技集团股份有限公司 | Information recommendation method and device |
| CN109977296B (en) * | 2019-01-17 | 2022-04-05 | 苏州达家迎信息技术有限公司 | Information pushing method, device, equipment and storage medium |
| CN109783740A (en) * | 2019-01-24 | 2019-05-21 | 北京字节跳动网络技术有限公司 | Pay close attention to the sort method and device of the page |
| CN110213234B (en) * | 2019-04-30 | 2022-06-28 | 深圳市腾讯计算机***有限公司 | Application program file developer identification method, device, equipment and storage medium |
| CN110457627B (en) * | 2019-07-04 | 2022-05-17 | 杭州安恒信息技术股份有限公司 | Method for optimizing website by using web audit |
| CN111538910A (en) * | 2020-06-23 | 2020-08-14 | 上海摩莱信息科技有限公司 | Intelligent recommendation method and device and computer storage medium |
| CN111767439B (en) * | 2020-06-28 | 2023-12-15 | 百度在线网络技术（北京）有限公司 | Recommendation method, device and medium based on page classification labels |
| CN112559923A (en) * | 2020-12-16 | 2021-03-26 | 平安银行股份有限公司 | Website resource recommendation method and device, electronic equipment and computer storage medium |
| CN112818262B (en) * | 2021-01-28 | 2023-07-21 | 上海博泰悦臻网络技术服务有限公司 | Map POI searching method, system, equipment and medium based on user data |
| CN113536108A (en) * | 2021-05-31 | 2021-10-22 | 珠海大横琴科技发展有限公司 | Information recommendation method and device |
| CN113505289A (en) * | 2021-06-09 | 2021-10-15 | 聘聘云(上海)智能科技有限公司 | Information processing method and apparatus, storage medium, and electronic apparatus |
| CN114780882B (en) * | 2022-03-26 | 2023-12-05 | 深圳市安睿信科技有限公司 | Internet webpage display management method, equipment and computer storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101968802A (en) * | 2010-09-30 | 2011-02-09 | 百度在线网络技术（北京）有限公司 | Method and equipment for recommending content of Internet based on user browse behavior |
| CN102316166A (en) * | 2011-09-26 | 2012-01-11 | 中国科学院计算机网络信息中心 | Website recommending method and system and network server |
| CN102354315A (en) * | 2011-09-22 | 2012-02-15 | 奇智软件（北京）有限公司 | Generation method of site navigation page and device thereof |
| CN102542055A (en) * | 2011-12-29 | 2012-07-04 | 潍坊中创软件工程有限责任公司 | Website directory display method and system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003157259A (en) * | 2001-09-05 | 2003-05-30 | Fuji Xerox Co Ltd | Information retrieval system |
| CN102332020B (en) * | 2011-09-22 | 2015-09-30 | 北京奇虎科技有限公司 | A kind of generation method and apparatus of website navigation page |
-
2012
- 2012-07-10 CN CN201610170286.7A patent/CN105868291A/en active Pending
- 2012-07-10 CN CN201210239708.3A patent/CN102799662B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101968802A (en) * | 2010-09-30 | 2011-02-09 | 百度在线网络技术（北京）有限公司 | Method and equipment for recommending content of Internet based on user browse behavior |
| CN102354315A (en) * | 2011-09-22 | 2012-02-15 | 奇智软件（北京）有限公司 | Generation method of site navigation page and device thereof |
| CN102316166A (en) * | 2011-09-26 | 2012-01-11 | 中国科学院计算机网络信息中心 | Website recommending method and system and network server |
| CN102542055A (en) * | 2011-12-29 | 2012-07-04 | 潍坊中创软件工程有限责任公司 | Website directory display method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102799662A (en) | 2012-11-28 |
| CN105868291A (en) | 2016-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102799662B (en) | Method, the Apparatus and system of network address is recommended based on domain name access historical record | |
| CN107862553B (en) | Advertisement real-time recommendation method and device, terminal equipment and storage medium | |
| CN108197331B (en) | User interest exploration method and device | |
| Bennett et al. | Inferring and using location metadata to personalize web search | |
| CN102693271B (en) | A kind of network information recommending method and system | |
| CN103886090B (en) | Content recommendation method and device based on user preferences | |
| JP5572596B2 (en) | Personalize the ordering of place content in search results | |
| US8112308B1 (en) | Targeting using generated bundles of content sources | |
| US8738654B2 (en) | Objective and subjective ranking of comments | |
| JP5596152B2 (en) | Information matching method and system on electronic commerce website | |
| US8209616B2 (en) | System and method for interfacing a web browser widget with social indexing | |
| US20120198056A1 (en) | Techniques for Analyzing Website Content | |
| US11127065B2 (en) | System and method for recommending entities based on interest indicators | |
| US8868570B1 (en) | Selection and display of online content items | |
| US20160042403A1 (en) | Extraction device, extraction method, and non-transitory computer readable storage medium | |
| US20110246277A1 (en) | Multi-factor promotional offer suggestion | |
| US20080208975A1 (en) | Methods, systems, and computer program products for accessing a discussion forum and for associating network content for use in performing a search of a network database | |
| CN102037464A (en) | Search results with most clicked next objects | |
| US9864768B2 (en) | Surfacing actions from social data | |
| WO2007059087A2 (en) | Selecting advertisements in social bookmarking system | |
| WO2004088540A1 (en) | Method and system for generating a search result list based on local information | |
| CN104462336A (en) | Information pushing method and device | |
| CN105812830A (en) | Recommendation method and system of hotel service content | |
| KR100987058B1 (en) | Method and system for providing advertising service using the keywords of internet contents and program recording medium | |
| CN103186666A (en) | Method, device and equipment for searching based on favorites |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220721 Address after: Room 801, 8th floor, No. 104, floors 1-19, building 2, yard 6, Jiuxianqiao Road, Chaoyang District, Beijing 100015 Patentee after: BEIJING QIHOO TECHNOLOGY Co.,Ltd. Address before: Room 112, block D, No. 28, Xinjiekou outer street, Xicheng District, Beijing 100016 (Desheng Park) Patentee before: BEIJING QIHOO TECHNOLOGY Co.,Ltd. Patentee before: Qizhi software (Beijing) Co.,Ltd. |