CN112016017A - Method and device for determining characteristic data - Google Patents

Abstract

The invention discloses a method and a device for determining characteristic data, and relates to the technical field of computers. One embodiment of the method comprises: acquiring label information of a current page and portrait information of a target user accessing the current page; determining a related user list corresponding to a target user according to the portrait information of the target user, and acquiring an access page list corresponding to the related user list; selecting a target page from the access page list according to the tag information of the current page, and acquiring a characteristic data pool corresponding to the target page; and determining feature data matched with the target user from the feature data pool by combining the portrait information of the target user. According to the embodiment, the target page corresponding to the user and the matched feature data are determined through the label information and the user image information of the current page, so that the feature data can be quickly acquired when the user accesses the target page, and the effects of improving the response performance of the page and reducing the response time are achieved.

Description

Method and apparatus for determining characteristic data

technical field

The present invention relates to the field of computer technology, and in particular, to a method and apparatus for determining characteristic data.

Background technique

In recent years, with the rapid development of computer technology and the Internet, users have higher requirements for the loading performance of visiting web pages. If the page loading does not meet the user's needs, the user may directly close the page, resulting in a decrease in page visits. In order to meet user needs, the current page contains a lot of feature information related to user needs, resulting in very large content of the entire page, which affects the loading performance of the page. Therefore, how to determine the characteristic data for different users has important research significance.

When the current user accesses a page with feature data, the feature data interface is called in real time to obtain the corresponding feature data, or the feature data of all pages and all users is pre-cached based on the user-page relationship. In the process of implementing the present invention, the inventor found that there are at least the following problems in the prior art: 1. The response duration of the existing feature data depends on the feature data interface called, and the feature data duration of the entire page is proportional to the number of feature data in the page, Therefore, the response time of the entire page will be increased, and the user experience will be affected. Second, the storage space required for all caches is large, and the cache is based on the relationship between user pages, and the hit rate is very low.

SUMMARY OF THE INVENTION

In view of this, embodiments of the present invention provide a method and apparatus for determining feature data, which can quickly acquire feature data when a user accesses a target page, thereby improving page response performance and reducing response time.

To achieve the above object, according to a first aspect of the embodiments of the present invention, a method for determining characteristic data is provided.

A method for determining feature data according to an embodiment of the present invention includes: acquiring label information of a current page and portrait information of a target user accessing the current page; related user list, and obtain the access page list corresponding to the related user list; according to the label information of the current page, select a target page from the access page list, and obtain the feature data pool corresponding to the target page; For the portrait information of the target user, characteristic data matching the target user is determined from the characteristic data pool.

Optionally, determining the relevant user list corresponding to the target user according to the profile information of the target user includes: obtaining a user set from a user page access database; for each user in the user set, obtaining the profile information of each user, and calculate the user correlation between the target user and each user according to the profile information of the target user and the profile information of each user; The user relevancy between each user is described, and a related user list corresponding to the target user is selected from the user set in combination with a preset user relevancy threshold.

Optionally, selecting a target page from the access page list according to the tag information of the current page includes: for each access page in the access page list, acquiring the tag information of each access page; according to The label information of the current page and the label information of each visited page are calculated, and the page correlation degree between the current page and each visited page is calculated; The target page is selected from the visited page list in combination with a preset page relevancy threshold.

Optionally, according to the label information of the current page and the label information of each visited page, calculating the page relevance between the current page and each visited page includes: determining the page correlation of the current page. category information and identification information in the tag information, and category information and identification information in the tag information of each visited page; according to the category information of the current page and the category information of each visited page , calculate the first page correlation between the current page and each visited page; according to the identification information of the current page and the identification information of each visited page, calculate the current page and the each visited page. The second page relevance between each visited page; the page relevance between the current page and each of the visited pages is calculated according to the first page relevance and the second page relevance.

Optionally, after determining the feature data matching the target user from the feature data pool, the method further includes: caching the feature data; receiving a request from the target user to access the target page, directly Load the cached feature data.

To achieve the above object, according to a second aspect of the embodiments of the present invention, an apparatus for determining feature data is provided.

An apparatus for determining feature data according to an embodiment of the present invention includes: an acquisition module, configured to acquire label information of a current page and portrait information of a target user accessing the current page; a first determination module, configured to User's portrait information, determine the relevant user list corresponding to the target user, and obtain the access page list corresponding to the relevant user list; the selection module is used to select from the access page list according to the label information of the current page. A target page is selected, and a feature data pool corresponding to the target page is obtained; a second determination module is configured to determine feature data matching the target user from the feature data pool in combination with the profile information of the target user.

Optionally, the first determining module is further configured to: obtain a user set from a user page access database; for each user in the user set, obtain the portrait information of each user, and analyze the information according to the target user. The profile information and the profile information of each user, calculate the user correlation between the target user and each user; according to the user correlation between the target user and each user, and In combination with a preset user relevancy threshold, a related user list corresponding to the target user is selected from the user set.

Optionally, the selection module is further configured to: for each access page in the access page list, obtain the tag information of each access page; according to the tag information of the current page and the each access page the tag information, calculate the page correlation between the current page and each visited page; according to the page correlation between the current page and each visited page, combined with the preset page correlation Threshold, select the target page from the visited page list.

Optionally, the selection module is further configured to: determine the category information and identification information in the tag information of the current page, and the category information and identification information in the tag information of each visited page; The category information of the current page and the category information of each visited page are calculated, and the first page correlation degree between the current page and each visited page is calculated; the identification information of each visited page, and calculate the second page relevance between the current page and each visited page; according to the first page relevance and the second page relevance, calculate the Page relevance between the current page and each of the visited pages.

Optionally, the apparatus further includes a cache module, configured to: cache the feature data; receive a request from the target user to access the target page, and directly load the cached feature data.

To achieve the above object, according to a third aspect of the embodiments of the present invention, an electronic device is provided.

An electronic device according to an embodiment of the present invention includes: one or more processors; and a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more programs The processor implements the method for determining characteristic data according to the embodiment of the present invention.

To achieve the above object, according to a fourth aspect of the embodiments of the present invention, a computer-readable medium is provided.

A computer-readable medium of an embodiment of the present invention stores a computer program thereon, and when the program is executed by a processor, the method for determining characteristic data of the embodiment of the present invention is implemented.

An embodiment of the above invention has the following advantages or beneficial effects: the target page corresponding to the target user can be determined through the tag information of the current page and the portrait information of the target user accessing the current page, and the feature data pool of the target page can be obtained, Finally, the feature data that matches the target user is selected from the feature data pool in combination with the target user's portrait information, so that the feature data can be quickly obtained when the target user accesses the target page, which replaces the real-time call feature data interface in the prior art and reduces the It reduces the processing time of feature data, and achieves the effect of improving the response performance of the page and reducing the response time. In addition, by introducing the target user portrait information and the label information of the current page, the corresponding target page is determined based on the current page accessed by the target user, and the feature data of the target page is acquired in advance, compared to caching all the feature data of the billion-level page, Greatly saves storage space and reduces costs. In addition, by introducing user portrait information and page label information, the accuracy of determining the target page is improved in the entire processing process, the hit rate of the feature data is improved, and the response performance of the page is further improved.

Further effects of the above non-conventional alternatives will be described below in conjunction with specific embodiments.

Description of drawings

The accompanying drawings are used for better understanding of the present invention and do not constitute an improper limitation of the present invention. in:

1 is a schematic diagram of main steps of a method for determining feature data according to an embodiment of the present invention;

2 is a schematic diagram of a category information relationship of a page according to an embodiment of the present invention;

3 is a schematic diagram of main steps of a method for determining feature data according to an embodiment of the present invention;

4 is a schematic diagram of main modules of an apparatus for determining feature data according to an embodiment of the present invention;

5 is an exemplary system architecture diagram to which an embodiment of the present invention may be applied;

FIG. 6 is a schematic structural diagram of a computer system suitable for implementing a terminal device or a server according to an embodiment of the present invention.

Detailed ways

Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, which include various details of the embodiments of the present invention to facilitate understanding and should be considered as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted from the following description for clarity and conciseness.

For a page containing feature data, the page also has static data, and the static data may mainly include cascading style sheets on the page, scripting languages, and content of static web page fragments with low real-time requirements. Since the content displayed by static data is consistent for all users and will not change within a certain period of time, static data can be cached in advance through caching technology, which can reduce the server's page rendering processing, reduce request back-to-source processing and reduce server processing pressure , to improve the response speed and performance of requests.

The feature data is the recommendation data determined based on the profile information of the visiting user, and there are certain differences in the recommendation data on different pages and different time periods. The method for determining feature data in the prior art has the problem of increasing the response time of the entire page depending on the feature data interface called, and the storage space required for all caches is large, and the cache is based on the relationship between user pages, and the hit rate is very low. Therefore, in view of the problem of page loading performance with characteristic data, the present invention proposes a method to introduce the portrait information of the target user accessing the current page and the label information of the current page, and determine the target page to visit in the future based on the current page accessed by the target user, and advance Get the feature data in the target page. When the target user accesses the target page, the feature data can be quickly obtained to complete the page display, thereby improving the page loading performance.

FIG. 1 is a schematic diagram of main steps of a method for determining feature data according to an embodiment of the present invention. As a referenced embodiment of the present invention, as shown in FIG. 1 , the main steps of the method for determining feature data in the embodiment of the present invention may include steps S101 to S104.

Step S101: Obtain the label information of the current page and the portrait information of the target user accessing the current page.

The current page in this embodiment of the present invention refers to the page that the user is visiting, and the label information of the current page may include category information of the page and identification information of the page. The target user in this embodiment of the present invention refers to a user who is accessing the current page, and the portrait information of the target user may include a unique identifier of the user, basic information of the user, browsing information of the user, information of the user's operation behavior, and the like. Considering that the purpose of the present invention is to determine the characteristic data, that is, to determine the data that the target user is interested in next, it is necessary to combine the portrait information of the target user and the label information of the current page to determine the next page of the target user to visit, and then The characteristic data of the next page to be accessed, that is, the data that the user is interested in, can be determined.

Step S102: Determine a related user list corresponding to the target user according to the profile information of the target user, and obtain a list of access pages corresponding to the related user list.

In this embodiment of the present invention, before determining the feature data, it is necessary to determine multiple target pages that the target user may visit next. In the embodiment of the present invention, it is obtained by using the page access list of the user with a high degree of relevance to the target user. Therefore, it is necessary to first calculate the relevant user list corresponding to the target user, that is, to calculate the user with a high degree of relevance to the target user. These users with high relevance to the target user form a related user list.

As another parameterizable embodiment of the present invention, determining the related user list corresponding to the target user according to the portrait information of the target user may include steps S1021, S1022 and S1023.

Step S1021: obtaining the user set from the user page access database, wherein the user page access database stores the access relationship data between the user and the page, and the user set can be filtered out from the database;

Step S1022: For each user in the user set, obtain the profile information of each user, and calculate the user correlation between the target user and each user according to the profile information of the target user and the profile information of each user. It uses the portrait information to calculate the user correlation between each user in the user set and the target user.

At present, the website has collected the user's portrait information. In step S101, the introduction portrait information may include the user's unique identifier, the user's basic information, the user's browsing information, and the user's operation behavior information. Therefore, the correlation between users can be calculated through these portrait information, and the specific calculation method is as follows.

User u _i can be defined through portrait information, as follows:

u _i =[x _i1 ... x _il ... x _iN ] ^T , (1≤l≤N)

Among them, x _il is the portrait information of the user, and the user is described through N different portrait information. The correlation between users R _user (u _i , u _j ) can be expressed as:

Among them, the larger the value of the calculation result of R _user (u _i , u _j ) is, the higher the correlation between users u _i and u _j is.

Step S1023: According to the user relevancy between the target user and each user, and in combination with a preset user relevancy threshold, select a related user list corresponding to the target user from the user set.

The user relevancy threshold here can be a certain value. For example, if the relevancy between the target user and a user A is greater than this value, it means that user A is a related user of the target user and can be added to the related user list. Or the user relevancy threshold is a number, the relevancy of each user in the user set and the target user can be sorted, and the users corresponding to M relevancy degrees with higher relevancy can be selected, and the users corresponding to these higher relevancy degrees are composed of A list of related users for the target user. For example, the values of R _user (u _i , u _j ) are sorted in descending order, and the top M users with high relevancy are obtained to construct a related user list U _t of the target user.

It can be seen from steps S1021 to S1023 that in this embodiment of the present invention, when determining the relevant user list of the target user, the portrait information of the target user is considered, and users similar to the portrait information of the target user are constructed as the relevant users of the target user. User list, which can improve the accuracy of the target page. After the related user list of the target user is obtained, the access page list corresponding to the related user list can be directly obtained, that is, the access page list corresponding to the user in the target user list is directly extracted from the user list database. It should be noted here that when extracting the access page list corresponding to the user in the target user list, the time information can be considered. Set, say, within a week) at 1:00 PM, a list of pages visited by users in the target user list. Of course, other information may also be considered when extracting the access page list corresponding to the user in the target user list, which is not limited here.

Step S103: According to the tag information of the current page, select a target page from the list of access pages, and acquire a feature data pool corresponding to the target page.

After the access page list is acquired in step S102, a target page may be selected from the access page list in combination with the tag information of the current page. As another referenced embodiment of the embodiment of the present invention, selecting a target page from a list of access pages according to the tag information of the current page may include steps S1031 to S1033.

Step S1031: For each access page in the access page list, obtain the tag information of each access page, the tag information of the page mentioned in the above step S101 may include the category information of the page and the identification information of the page, wherein the category The information refers to the category information of the page, and FIG. 2 is a schematic diagram of the category information relationship of the page according to an embodiment of the present invention. As can be seen from Figure 2, the figure corresponds to the first-level page category, second-level page category, third-level page category and other category information of the page in turn. The lowest layer (ie, the leaf layer) identifies the page. For the page p1 in 2, its first-level page category is category root (ie, the root node), its second-level page category is category 1, and its third-level page category is 11. For the category level of a certain library management system, the first-level category can be Chinese books; the second-level category can be philosophy, social science, natural science and comprehensive books; the third-level category can be the second-level category Philosophy includes Fundamental issues of philosophy, materialism and idealism, etc. The identification information of the page may include basic information such as the unique identification of the page and the attribute information of the page. Since the current page accessed by the target user has a certain relationship with the page accessed by the target user next, in the embodiment of the present invention, when determining the feature data, the label information of the current page is considered, which can improve the accuracy.

Step S1032: Calculate the page correlation between the current page and each visited page according to the label information of the current page and the label information of each visited page. The tag information of the page mentioned in both steps S101 and S1031 above may include category information of the page and identification information of the page. Therefore, the page correlation between the current page and each visited page in the embodiment of the present invention is calculated by using the category information of the page and the identification information of the page. In the embodiment of the present invention, calculating the page relevancy between the current page and each visited page may include:

Step S10321: Determine the category information and identification information in the tag information of the current page, and the category information and identification information in the tag information of each accessed page, wherein the category information and identification information have been specifically explained above, this Tired everywhere.

Step S10322: Calculate the first page correlation between the current page and each visited page according to the category information of the current page and the category information of each visited page, wherein the calculation formula of the first page correlation is as follows:

Among them, d(pi) represents the path length from page pi to the first-level page category (ie root node), and L( _pi , p _j ) _represents the common ancestor of _{pages pi and p j with the} largest path (for example, The first common parent class of page p1 and page p2 is "category 11", and the path length from this class to the root node "category root" is the largest, so "category 11" is the maximum path of p1 and p2 common ancestor). The first page correlation degree R ₁ (pi , p _j ) between two pages has a value range of [0, 1], and when _{pi =p j ,} the correlation degree is the largest and is 1.

Step S10323: Calculate the second page correlation between the current page and each visited page according to the identification information of the current page and the identification information of each visited page. In the embodiment of the present invention, the second page correlation between the two pages is The calculation method of the degree is the same as the calculation method of the user correlation degree between two users. In combination with the identification information of the page (such as unique identification, attribute information, etc.), the first page correlation degree R ₀ ( p _i ,p _j ), which will not be repeated here.

Step S10324: Calculate the page relevance between the current page and each visited page according to the first page relevance and the second page relevance.

In step S10322, the first page correlation degree R ₁ (p _i , p _j ) between the current page and each visited page is calculated, and the second page between the current page and each visited page is calculated in step S10323 Relevance R ₀ (pi ,p _j ), the page relevance R( _pi ,p _j ) ₌ R ₀ ( _pi ,p _j )*R ₁ between the current page and each visited page can be calculated ( _{pi ,p j )} .

Step S1033: According to the page relevance between the current page and each visited page, and in combination with a preset page relevance threshold, select a target page from the visited page list.

The page relevance threshold here can be a certain value. For example, if the relevance between the current page and a visited page W is greater than this value, it means that the visited page W is the target page, and what needs to be noted here is the number of target pages. at least 1. Or the page relevancy threshold is a number, you can sort the page relevancy between each accessed page and the current page in the access page list, and select the access pages corresponding to the K relevancy degrees with higher relevancy. The corresponding access pages are all target pages.

It is also mentioned in step S103 that after acquiring the target page, the feature data pool corresponding to the target page needs to be acquired. The feature data pool here can be regarded as a large database, which stores the feature data corresponding to each page, and each page corresponds to at least one feature data, because for different users, the feature data recommended for this user is are not the same, so two users have opened a connection to the same page, and the feature data recommended for the two users can also be different.

Therefore, in step S104, the characteristic data matching the target user is determined from the characteristic data pool in combination with the portrait information of the target user. For example, when visiting page p1, the feature corresponding to male is D1, and the feature data corresponding to female is D2; when visiting page p2, the feature corresponding to male is D3, and the feature data corresponding to female is D4. If the current target user is male, he will obtain the recommendation data D1 of the p1 page and the recommendation data D3 of the p2 page.

The purpose of determining the feature data in the embodiment of the present invention is to quickly obtain the feature data when the target user opens the target page, speed up the response speed of the page, and improve the response performance of the page. Therefore, as another reference embodiment of the embodiment of the present invention, after determining the feature data matching the target user from the feature data pool, the method for determining feature data in the embodiment of the present invention may further include: caching feature data; receiving The request of the target user to access the target page directly loads the cached feature data. That is, the feature data is cached, so that when the target user accesses the target page, the feature data corresponding to the target page can be quickly obtained from the cache.

It should be noted that the number of target pages determined in the embodiment of the present invention is at least one, and therefore the number of characteristic data finally determined is also at least one. That is to say, using the method for determining feature data in the embodiment of the present invention, first, obtain the user page access relational database, use the portrait information of the target user, the user set in the database, and the portrait information of the users in the user set to calculate the user in the user set. The correlation between the target user and the target user is to obtain the access page list corresponding to the user with a high degree of correlation; At least one page is determined as a target page; finally, the characteristic data of at least one target page is obtained in combination with the portrait information of the target user, and when the target user accesses the target page, the characteristic data is directly returned.

FIG. 3 is a schematic diagram of main steps of a method for determining feature data according to an embodiment of the present invention. As shown in FIG. 3 , the main steps of the method for determining characteristic data according to the embodiment of the present invention may include:

Step S301: Obtain the label information of the current page and the portrait information of the target user accessing the current page;

Step S302: Obtain the user set from the user page access database, and calculate the user correlation between each user in the user set and the target user, wherein the calculation method of the user correlation has been specifically explained in the above step S1022, which is not exhausted here. stated;

Step S303: According to the user relevancy between the target user and each user, and in combination with a preset user relevancy threshold, select a relevant user list corresponding to the target user from the user set, and obtain the access page list corresponding to the relevant user list ;

Step S304: Calculate the page correlation between each visited page and the current page in the visited page list, wherein the calculation method of the page correlation has been explained in detail in steps S10321 to S10324 above, and will not be described here;

Step S305: According to the page relevancy between the current page and each accessed page, combined with a preset page relevancy threshold, select the target page from the access page list, and obtain the feature data pool corresponding to the target page;

Step S306: Combine the portrait information of the target user, determine the characteristic data matching the target user from the characteristic data pool;

Step S307: Cache feature data, and directly load the cached feature data when receiving a request from the target user to access the target page.

It should be noted that the number of target pages in the above steps S301 to S307 is at least one, and according to the user's portrait information, the number of feature data determined to match the target user is the same as the number of target pages. That is, for a target page, a characteristic data is finally determined, and when the target user accesses a certain target page, the characteristic data corresponding to the target page can be directly obtained from the cache.

According to the technical solution for determining feature data in the embodiment of the present invention, the target page corresponding to the target user can be determined through the tag information of the current page and the portrait information of the target user accessing the current page, and the feature data pool of the target page can be obtained, and finally The feature data that matches the target user is selected from the feature data pool in combination with the target user's portrait information, so that the feature data can be quickly obtained when the target user accesses the target page, which replaces the real-time call feature data interface in the prior art and reduces the The processing time of the feature data can improve the response performance of the page and reduce the response time. In addition, by introducing the target user portrait information and the label information of the current page, the corresponding target page is determined based on the current page accessed by the target user, and the feature data of the target page is acquired in advance, compared to caching all the feature data of the billion-level page, Greatly saves storage space and reduces costs. In addition, by introducing user portrait information and page label information, the accuracy of determining the target page is improved in the entire processing process, the hit rate of the feature data is improved, and the response performance of the page is further improved.

FIG. 4 is a schematic diagram of main modules of an apparatus for determining feature data according to an embodiment of the present invention. As shown in FIG. 4 , the apparatus 400 for determining feature data according to the embodiment of the present invention mainly includes the following modules: an acquisition module 401 , a first determination module 402 , a selection module 403 , and a second determination module 404 .

Wherein, the obtaining module 401 can be used to obtain the label information of the current page and the portrait information of the target user accessing the current page; the first determining module 402 can be used to determine the relevant user list corresponding to the target user according to the portrait information of the target user, and obtain the relevant user list. The access page list corresponding to the user list; the selection module 403 can be used to select the target page from the access page list according to the label information of the current page, and obtain the feature data pool corresponding to the target page; the second determination module 404 can be used to combine the target user's Portrait information, from the feature data pool to determine the feature data that matches the target user.

In this embodiment of the present invention, the first determining module 402 may be further configured to: obtain a user set from the user page access database; for each user in the user set, obtain the portrait information of each user, and according to the portrait information of the target user and each user's portrait information According to the user relevancy between the target user and each user, combined with the preset user relevancy threshold, select the target from the user set A list of related users corresponding to the user.

In this embodiment of the present invention, the selection module 403 may be further configured to: for each access page in the access page list, obtain the tag information of each access page; calculate the current page according to the tag information of the current page and the tag information of each accessed page Page relevance between each visited page; according to the page relevance between the current page and each visited page, combined with a preset page relevance threshold, select the target page from the visited page list.

In this embodiment of the present invention, the selection module 403 may be further configured to: determine the category information and identification information in the tag information of the current page, and the category information and identification information in the tag information of each accessed page; according to the category information of the current page The first page correlation degree between the current page and each visited page is calculated; according to the identification information of the current page and the identification information of each visited page, the relationship between the current page and each visited page is calculated. The second page relevance between the visited pages; the page relevance between the current page and each visited page is calculated according to the first page relevance and the second page relevance.

In this embodiment of the present invention, the device further includes a cache module (not shown in the figure), which can be used to: cache feature data; receive a request from a target user to access a target page, and directly load the cached feature data.

As can be seen from the above description, the device for determining feature data according to the embodiment of the present invention can determine the target page corresponding to the target user through the label information of the current page and the portrait information of the target user accessing the current page, and obtain the features of the target page. Data pool, and finally select the feature data that matches the target user from the feature data pool in combination with the target user's portrait information, so that when the target user accesses the target page, the feature data can be quickly obtained, instead of calling the feature data in real time in the prior art. The interface reduces the processing time of feature data, and achieves the effect of improving the response performance of the page and reducing the response time. In addition, by introducing the target user portrait information and the label information of the current page, the corresponding target page is determined based on the current page accessed by the target user, and the feature data of the target page is acquired in advance, compared to caching all the feature data of the billion-level page, Greatly saves storage space and reduces costs. In addition, by introducing user portrait information and page label information, the accuracy of determining the target page is improved in the entire processing process, the hit rate of the feature data is improved, and the response performance of the page is further improved.

FIG. 5 shows an exemplary system architecture 500 of a method for determining characteristic data or an apparatus for determining characteristic data to which embodiments of the present invention may be applied.

As shown in FIG. 5 , the system architecture 500 may include terminal devices 501 , 502 , and 503 , a network 504 and a server 505 . The network 504 is a medium used to provide a communication link between the terminal devices 501 , 502 , 503 and the server 505 . Network 504 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user can use the terminal devices 501, 502, 503 to interact with the server 505 through the network 504 to receive or send messages and the like. Various communication client applications may be installed on the terminal devices 501 , 502 and 503 , such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only examples).

The terminal devices 501, 502, 503 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

The server 505 may be a server that provides various services, for example, a background management server that provides support for shopping websites browsed by the terminal devices 501 , 502 , and 503 (just an example). The background management server can analyze and process the received product information query request and other data, and feed back the processing results (such as target push information, product information—just an example) to the terminal device.

It should be noted that the method for determining characteristic data provided in the embodiment of the present invention is generally performed by the server 505 , and accordingly, the apparatus for determining characteristic data is generally set in the server 505 .

It should be understood that the numbers of terminal devices, networks and servers in FIG. 5 are only illustrative. There can be any number of terminal devices, networks and servers according to implementation needs.

Referring to FIG. 6 below, it shows a schematic structural diagram of a computer system 600 suitable for implementing a terminal device according to an embodiment of the present invention. The terminal device shown in FIG. 6 is only an example, and should not impose any limitations on the functions and scope of use of the embodiments of the present invention.

As shown in FIG. 6, a computer system 600 includes a central processing unit (CPU) 601, which can be loaded into a random access memory (RAM) 603 according to a program stored in a read only memory (ROM) 602 or a program from a storage section 608 Instead, various appropriate actions and processes are performed. In the RAM 603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601 , the ROM 602 , and the RAM 603 are connected to each other through a bus 604 . An input/output (I/O) interface 605 is also connected to bus 604 .

The following components are connected to the I/O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc. ; and a communication section 609 including a network interface card such as a LAN card, a modem, and the like. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I/O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is mounted on the drive 610 as needed so that a computer program read therefrom is installed into the storage section 608 as needed.

In particular, the processes described above with reference to the flowcharts may be implemented as computer software programs in accordance with the disclosed embodiments of the present invention. For example, embodiments disclosed herein include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the method illustrated in the flowchart. In such an embodiment, the computer program may be downloaded and installed from the network via the communication portion 609 and/or installed from the removable medium 611 . When the computer program is executed by the central processing unit (CPU) 601, the above-described functions defined in the system of the present invention are performed.

It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples of computer readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), fiber optics, portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. In the present invention, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code therein. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device . Program code embodied on a computer readable medium may be transmitted using any suitable medium including, but not limited to, wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more logical functions for implementing the specified functions executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams or flowchart illustrations, and combinations of blocks in the block diagrams or flowchart illustrations, can be implemented in special purpose hardware-based systems that perform the specified functions or operations, or can be implemented using A combination of dedicated hardware and computer instructions is implemented.

The modules involved in the embodiments of the present invention may be implemented in a software manner, and may also be implemented in a hardware manner. The described modules can also be provided in the processor, for example, it can be described as: a processor includes an acquisition module, a first determination module, a selection module and a second determination module. Among them, the names of these modules do not constitute a limitation of the module itself under certain circumstances. For example, the acquisition module can also be described as "obtaining the label information of the current page and the portrait information of the target user who accesses the current page. module".

As another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or may exist alone without being assembled into the device. The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by a device, the device includes: acquiring the label information of the current page and the portrait information of the target user accessing the current page; The portrait information of the target user, determine the relevant user list corresponding to the target user, and obtain the access page list corresponding to the relevant user list; according to the tag information of the current page, select the target page from the access page list, and obtain the characteristic data corresponding to the target page. Pool; combined with the target user's portrait information, determine the feature data matching the target user from the feature data pool.

According to the technical solution of the embodiment of the present invention, the target page corresponding to the target user can be determined through the tag information of the current page and the portrait information of the target user accessing the current page, and the feature data pool of the target page can be obtained, and finally combined with the target user's The portrait information selects the feature data that matches the target user from the feature data pool, so that the feature data can be quickly obtained when the target user accesses the target page, which replaces the real-time call feature data interface in the prior art and reduces the processing of feature data. time, to achieve the effect of improving the response performance of the page and reducing the response time. In addition, by introducing the target user portrait information and the label information of the current page, the corresponding target page is determined based on the current page accessed by the target user, and the feature data of the target page is acquired in advance, compared to caching all the feature data of the billion-level page, Greatly saves storage space and reduces costs. In addition, by introducing user portrait information and page label information, the accuracy of determining the target page is improved in the entire processing process, the hit rate of the feature data is improved, and the response performance of the page is further improved.

The above-mentioned specific embodiments do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims (12)

1. a method for determining characteristic data, is characterized in that, comprises: Obtain the label information of the current page and the portrait information of the target user accessing the current page; According to the profile information of the target user, determine the relevant user list corresponding to the target user, and obtain the access page list corresponding to the relevant user list; According to the label information of the current page, select a target page from the access page list, and obtain the feature data pool corresponding to the target page; In combination with the profile information of the target user, characteristic data matching the target user is determined from the characteristic data pool. 2. The method according to claim 1, wherein determining the relevant user list corresponding to the target user according to the profile information of the target user, comprising: Get the user collection from the user page access database; For each user in the user set, obtain the profile information of each user, and calculate the target user and each user according to the profile information of the target user and the profile information of each user user relevance between According to the user relevancy between the target user and each user, and in combination with a preset user relevancy threshold, a related user list corresponding to the target user is selected from the user set. 3. The method according to claim 1, wherein, according to the label information of the current page, selecting a target page from the access page list, comprising: For each access page in the access page list, obtain the label information of each access page; According to the label information of the current page and the label information of each visited page, calculate the page relevance between the current page and each visited page; The target page is selected from the visited page list according to the page relevancy between the current page and each visited page and in combination with a preset page relevancy threshold. 4. The method according to claim 3, wherein, according to the label information of the current page and the label information of each visited page, the page between the current page and the each visited page is calculated Relevance, including: Determine the category information and identification information in the tag information of the current page, and the category information and identification information in the tag information of each visited page; According to the category information of the current page and the category information of each visited page, calculating the first page correlation between the current page and each of the visited pages; According to the identification information of the current page and the identification information of each visited page, calculating a second page correlation between the current page and each of the visited pages; According to the first page relevancy degree and the second page relevancy degree, the page relevancy degree between the current page and each visited page is calculated. 5. The method according to claim 1, wherein after determining the characteristic data matching the target user from the characteristic data pool, the method further comprises: cache the feature data; A request from the target user to access the target page is received, and the cached feature data is directly loaded. 6. A device for determining characteristic data, comprising: an acquisition module for acquiring the label information of the current page and the portrait information of the target user accessing the current page; a first determining module, configured to determine the relevant user list corresponding to the target user according to the profile information of the target user, and obtain the access page list corresponding to the relevant user list; a selection module, configured to select a target page from the access page list according to the label information of the current page, and obtain a feature data pool corresponding to the target page; The second determination module is configured to determine the characteristic data matching the target user from the characteristic data pool in combination with the portrait information of the target user. 7. The apparatus according to claim 6, wherein the first determining module is further configured to: Get the user collection from the user page access database; For each user in the user set, obtain the profile information of each user, and calculate the target user and each user according to the profile information of the target user and the profile information of each user user relevance between According to the user relevancy between the target user and each user, and in combination with a preset user relevancy threshold, a related user list corresponding to the target user is selected from the user set. 8. The apparatus according to claim 6, wherein the selection module is further configured to: For each access page in the access page list, obtain the label information of each access page; According to the label information of the current page and the label information of each visited page, calculate the page relevance between the current page and each visited page; The target page is selected from the visited page list according to the page relevance between the current page and each of the visited pages and in combination with a preset page relevance threshold. 9. The apparatus according to claim 8, wherein the selection module is further configured to: Determine the category information and identification information in the tag information of the current page, and the category information and identification information in the tag information of each visited page; According to the category information of the current page and the category information of each visited page, calculating the first page relevance between the current page and each of the visited pages; According to the identification information of the current page and the identification information of each visited page, calculating a second page correlation between the current page and each of the visited pages; According to the first page relevancy degree and the second page relevancy degree, the page relevancy degree between the current page and each visited page is calculated. 10. The apparatus according to claim 6, wherein the apparatus further comprises a cache module for: cache the feature data; A request from the target user to access the target page is received, and the cached feature data is directly loaded. 11. An electronic device, characterized in that, comprising: one or more processors; storage means for storing one or more programs, The one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-5. 12. A computer-readable medium on which a computer program is stored, characterized in that, when the program is executed by a processor, the method according to any one of claims 1-5 is implemented.

Images