CN107273538B - Information recommendation method, device and server - Google Patents
Information recommendation method, device and server Download PDFInfo
- Publication number
- CN107273538B CN107273538B CN201710530877.5A CN201710530877A CN107273538B CN 107273538 B CN107273538 B CN 107273538B CN 201710530877 A CN201710530877 A CN 201710530877A CN 107273538 B CN107273538 B CN 107273538B
- Authority
- CN
- China
- Prior art keywords
- user
- information
- group
- click
- crowd
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The embodiment of the invention provides an information recommendation method, an information recommendation device and a server, wherein the method comprises the following steps: recommending information to each user in the first group according to the historical user record corresponding to each information in the information set; selecting information with exposure times lower than a preset threshold value from the information set as recommendation information, recommending the recommendation information to each user in a second group respectively, and updating historical user records corresponding to each information in the information set and user records in an updated user list respectively according to feedback results of each user in the second group on the recommendation information, wherein the users in the first group and the users in the second group are users with new user labels in the user list, and the number of the users in the second group is less than that of the users in the first group. The method improves the accuracy rate of recommendation to the new user and further improves the experience of the new user.
Description
Technical Field
The invention relates to the field of computer application, in particular to an information recommendation method, an information recommendation device and a server.
Background
With the rapid development of the internet, the information received by users every day begins to expand. At present, some methods for recommending information according to the past behavior habits of users exist, but the method cannot solve the problem of a new user, and how to recommend interesting information to the new user becomes a problem to be solved urgently.
Disclosure of Invention
In view of the above, an object of the embodiments of the present invention is to provide an information recommendation method, an information recommendation apparatus and a server, so as to solve the above problems.
In order to achieve the above purpose, the embodiment of the present invention adopts the following technical solutions:
in a first aspect, an embodiment of the present invention provides an information recommendation method, where the method includes: recommending information to each user in the first group according to the historical user record corresponding to each information in the information set; selecting information with exposure times lower than a preset threshold value from the information set as recommendation information, recommending the recommendation information to each user in a second group respectively, and updating historical user records corresponding to each information in the information set and user records in an updated user list respectively according to feedback results of each user in the second group on the recommendation information, wherein the users in the first group and the users in the second group are users with new user labels in the user list, and the number of the users in the second group is less than that of the users in the first group.
In a second aspect, an embodiment of the present invention provides an information recommendation method, where the method includes: according to the crowd label corresponding to the user with the new user label, querying a historical user record corresponding to each piece of information in an information set, and obtaining the click rate of each piece of information in the crowd with the crowd label; calculating a click index corresponding to each piece of information according to the crowd label and the click rate of each piece of information in the crowd with the crowd label; and recommending information to the user with the new user label according to each click index.
In a third aspect, an embodiment of the present invention provides an information recommendation apparatus, where the apparatus includes: the first recommending module is used for recommending information to each user in the first group according to the historical user record corresponding to each information in the information set; and the second recommending module is used for selecting information with the exposure times lower than a preset threshold value from the information set as recommending information, recommending the recommending information to each user in a second group respectively, and updating the historical user record corresponding to each information in the information set and the user record in the user list respectively according to the feedback result of each user in the second group on the recommending information, wherein the users in the first group and the users in the second group are both users in the user list with new user labels, and the number of the users in the second group is less than that of the users in the first group.
In a fourth aspect, an embodiment of the present invention provides an information recommendation apparatus, where the apparatus includes: the query module is used for querying the historical user record corresponding to each piece of information in the information set according to the crowd label corresponding to the user with the new user label, and acquiring the click rate of each piece of information in the crowd with the crowd label; the calculation module is used for calculating a click index corresponding to each piece of information according to the crowd label and the click rate of each piece of information in the crowd with the crowd label; and the third recommending module is used for recommending information to the user with the new user label according to each click index.
In a fifth aspect, embodiments of the present invention provide a server, including a memory and a processor, the memory coupled to the processor, the memory storing instructions that, when executed by the processor, cause the processor to: recommending information to each user in the first group according to the historical user record corresponding to each information in the information set; selecting information with exposure times lower than a preset threshold value from the information set as recommendation information, recommending the recommendation information to each user in a second group respectively, and updating historical user records corresponding to each information in the information set and user records in an updated user list respectively according to feedback results of each user in the second group on the recommendation information, wherein the users in the first group and the users in the second group are users with new user labels in the user list, and the number of the users in the second group is less than that of the users in the first group.
In a sixth aspect, embodiments of the present invention provide a server, including a memory and a processor, the memory coupled to the processor, the memory storing instructions that, when executed by the processor, cause the processor to: according to the crowd label corresponding to the user with the new user label, querying a historical user record corresponding to each piece of information in an information set, and obtaining the click rate of each piece of information in the crowd with the crowd label; calculating a click index corresponding to each piece of information according to the crowd label and the click rate of each piece of information in the crowd with the crowd label; and recommending information to the user with the new user label according to each click index.
Compared with the prior art, the information recommendation method, the information recommendation device and the server provided by the embodiment of the invention recommend information to each user in the first group respectively according to the historical user record corresponding to each information in the information set; selecting information with exposure times lower than a preset threshold value from the information set as recommendation information, recommending the recommendation information to each user in a second group respectively, and updating the historical user record corresponding to each information in the information set and the user record in the user list respectively according to the feedback result of each user in the second group to the recommendation information, wherein the users in the first group and the users in the second group are both users with new user labels in the user list, and the number of users in the second group is less than that of the first group, the scheme recommends information to a small part of new users in a 'heuristic recommendation' mode, finds high-quality information according to the feedback of the part of users, and recommends information which is verified to be high-quality to a large part of new users according to the historical user record corresponding to each information in the information set, the accuracy rate of recommending to the new user is improved, and the experience of the new user is further improved.
According to the information recommendation method, the information recommendation device and the server provided by the embodiment of the invention, according to the crowd label corresponding to the user with the new user label, the historical user record corresponding to each piece of information in the information set is inquired, and the click rate of each piece of information in the crowd with the crowd label is obtained; calculating a click index corresponding to each piece of information according to the crowd label and the click rate of each piece of information in the crowd with the crowd label; according to the click indexes, information is recommended to the user with the new user label, according to the scheme, the information which is verified to be high-quality information is recommended to the new user according to other historical user records corresponding to the information in the information set, the accuracy rate of recommending to the new user is improved, and the experience of the new user is further improved.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a schematic diagram of a server interacting with a user terminal according to an embodiment of the present invention.
Fig. 2 is a block diagram of a server according to an embodiment of the present invention.
Fig. 3 is a flowchart of an information recommendation method according to a first embodiment of the invention.
FIG. 4 is a flowchart of a first part of an information recommendation method according to a first embodiment of the present invention.
FIG. 5 is a flowchart of a second part of an information recommendation method according to a first embodiment of the present invention.
FIG. 6 is a flowchart of a third part of an information recommendation method according to a first embodiment of the present invention.
FIG. 7 is a fourth flowchart illustrating an information recommendation method according to a first embodiment of the present invention.
FIG. 8 is a flowchart illustrating an information recommendation method according to a second embodiment of the present invention.
FIG. 9 is a partial flowchart of an information recommendation method according to a second embodiment of the present invention.
Fig. 10 is a block diagram of an information recommendation device according to a third embodiment of the present invention.
Fig. 11 is a block diagram of an information recommendation apparatus according to a fourth embodiment of the present 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. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present invention, the terms "first", "third", etc. are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
Fig. 1 is a schematic diagram illustrating an interaction between a server 200 and a user terminal 100 according to an embodiment of the present invention. The server 200 is communicatively connected to one or more user terminals 100 via a network for data communication or interaction. The server 200 may be a web server, a database server, or the like. The user terminal 100 may be a Personal Computer (PC), a tablet PC, a smart phone, a wearable device, or the like.
Fig. 2 shows a block schematic diagram of a server 200 applicable in an embodiment of the invention. The server 200 includes a memory 201, a processor 202, and a network module 203.
The memory 201 may be used to store software programs and modules, such as program instructions/modules corresponding to the information recommendation method and apparatus in the embodiments of the present invention, and the processor 202 executes various functional applications and data processing by operating the software programs and modules stored in the memory 201, so as to implement the information recommendation method in the embodiments of the present invention. Memory 201 may include high speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. Further, the software programs and modules in the memory 201 may further include: an operating system 221 and a service module 222. The operating system 221, which may be LINUX, UNIX, WINDOWS, for example, may include various software components and/or drivers for managing system tasks (e.g., memory management, storage device control, power management, etc.), and may communicate with various hardware or software components to provide an operating environment for other software components. The service module 222 runs on the basis of the operating system 221, and monitors a request from the network through the network service of the operating system 221, completes corresponding data processing according to the request, and returns a processing result to the client. That is, the service module 222 is used to provide network services to clients.
The network module 203 is used for receiving and transmitting network signals. The network signal may include a wireless signal or a wired signal.
It will be appreciated that the configuration shown in fig. 2 is merely illustrative and that the server 200 may include more or fewer components than shown in fig. 2 or may have a different configuration than shown in fig. 2. The components shown in fig. 2 may be implemented in hardware, software, or a combination thereof. In addition, the server in the embodiment of the present invention may further include a plurality of servers with different specific functions.
Fig. 3 is a flowchart illustrating an information recommendation method according to a first embodiment of the present invention, referring to fig. 3, the information recommendation method is executed in the server, and the method includes:
step S300, recommending information to each user in the first group according to the historical user record corresponding to each information in the information set.
There are many embodiments of information, such as news information, video, push advertisements, Taobao links, video, etc.
Further, in the era of mobile applications, users are more willing to learn some fresh information through some short videos, so as an implementation manner, the information is a short video with a playing time length less than a preset time length. The preset time period may be set according to a requirement, for example, 10 seconds, 30 seconds, one minute, and the like.
In one embodiment, the historical user record corresponding to each piece of information includes an information identification number, a crowd tag, the number of exposures of the piece of information corresponding to the information identification number in the crowd having the crowd tag, the number of clicks, and the click rate.
As a specific implementation manner, the information set includes the historical user records corresponding to each piece of information, the information is a short video, and the historical user records corresponding to each short video are stored in the database in a list manner, which is shown in the following table 1:
TABLE 1
| Short video identification number | Crowd label | Number of exposures | Number of clicks | Click rate |
| 12345 | Male sex | 300 | 60 | 0.2 |
| 12345 | Female with a view to preventing the formation of wrinkles | 500 | 50 | 0.1 |
| 67890 | College student | 500 | 150 | 0.3 |
| … | … | … | … |
Each record in the table is determined by the short video identification number and the crowd label, and each record represents the exposure times, the click times and the click rate of the short video corresponding to the short video identification number in the crowd with the crowd label. Wherein, the click rate is the number of clicks/number of exposures.
When an operator adds a new short video into the short video set, initializing data as a short video identification number, wherein the short video identification number is a unique identifier of the short video; the crowd label is a label in the short video set; the exposure times are initialized to 0; the number of clicks is initialized to 0; the click rate is initialized to 0.
As an embodiment, referring to fig. 4, step S300 may include:
step S310, according to the historical user records corresponding to each piece of information in the information set, calculating the click indexes of each piece of information corresponding to each user in the first group.
As a specific implementation manner, referring to fig. 5, step S310 may include:
step S311, obtaining the crowd label of each user in the first crowd, respectively.
And the users in the first group are users in the user list with new user labels. As an embodiment, the new user tag is a new user tag. That is, the users in the first group are all new users.
The crowd label for each user in the first group may be obtained by querying a list of users.
As an embodiment, the user list may be stored in the database in a list form, and the specific storage manner is shown in table 2 below:
TABLE 2
| User identification number | Crowd label | New user label |
| 1 | Male sex | 1 |
| 1 | College student | 1 |
| 2 | Female with a view to preventing the formation of wrinkles | 0 |
| 3 | College student | 1 |
| … | … | … |
Each record in the table is determined by the user identification number and the crowd label, and each record represents that the user is the user under the crowd label and whether the user is a new user. Wherein, the new user label is 1, which represents that the user is a new user.
Further, there are many ways to acquire the new user tag, for example: acquiring gender, region, occupation information and the like of a user through personal registration information of the user; judging whether the user is an online game user or not through the application installed by the user; the user recommends a batch of tags to the user when starting the product for the first time, the tags of interest selected by the user.
Step S312, querying a historical user record corresponding to each piece of information in the information set according to the crowd label of each user, and obtaining the click rate of each piece of information corresponding to each user.
Taking user 1 in the first group as an example, first, the user 1 in the user list (shown in table 2) is queried for the crowd label, where the crowd label of user 1 includes: male and college students.
According to the crowd labels of the user 1, namely, males and college students, historical user records corresponding to all information in an information set (shown in table 1) are inquired, and the click rate of all information corresponding to each user is obtained. That is, in the lookup table 1, the owned crowd label is the click rate of the male to each video, and the owned crowd label is the click rate of the college student to each video.
Step S313, according to the crowd label of each user and the click rate of each information corresponding to each user, respectively calculating the click index of each information corresponding to each user.
In one embodiment, the click rate of each piece of information in the crowd having the crowd tag of the user is added to be used as the click index corresponding to each piece of information corresponding to the user. Specifically, the calculation can be performed according to the following formula:
wherein ctri，tThe click rate of the information i for the crowd with the user label t; utu，tIndicates whether user u has user tag t (0 indicates not, 1 indicates yes)；eu，iIs the click index of user u on information i.
Step S320, recommending information to each user in the first group according to each click index.
As an embodiment, referring to fig. 6, step S320 may include:
step S321, sorting the information corresponding to each user according to the click indexes corresponding to each user in the first group.
For example, for the user a, the click indexes of the user a on each piece of information are calculated according to a formula, and sorting is performed according to the click indexes of each piece of information in a descending order.
Step S322, selecting and recommending a preset number of recommendation information for each user according to the corresponding sorting result of each user.
Wherein, the preset number can be set according to the requirement. For example, 100 pieces of recommendation information are selected and recommended for each of the users.
Step S400, selecting information with exposure times lower than a preset threshold value from the information set as recommendation information, and recommending the recommendation information to each user in the second group respectively.
And all the users in the second group are users with new user tags in the user list, and the number of the users in the second group is less than that of the users in the first group.
As an embodiment, referring to fig. 7, the first population and the second population may be obtained according to a predetermined rule, and the method further includes:
step S410, obtaining a plurality of users having new user tags from the user list.
As an embodiment, the new user tag is a new user tag. Referring to table 2, a plurality of users having new user tags are obtained from table 2.
Step S420, dividing the plurality of users having the new user tags into a first group and a second group according to a ratio.
Wherein, the proportion can be set according to the requirements of users. For example, if 100 users having new user tags are obtained from the user list, 90% of the users are classified into a first group, and 10% of the users are classified into a second group.
The number of exposures refers to the number of times information appears on the user's screen. For example, an exposure is an information that appears once on the user's screen.
The preset threshold value can be set according to requirements. For example, the value may be 500, that is, information with exposure times lower than 500 times is selected from the information set as recommendation information, and the recommendation information is recommended to each user in the second group.
Step S500, updating the historical user record corresponding to each information in the information set and updating the user record in the user list according to the feedback result of each user in the second group to the recommended information.
As an embodiment, the feedback result includes information of each user in the second group and information of whether each user clicks the recommendation information. As a specific embodiment, if the information is short video, the feedback data of each user can be seen in the following table 3:
TABLE 3
| User identification number | Short video identification number | Exposure click data |
| 1 | 11 | 1 |
| 1 | 22 | 0 |
| 2 | 11 | －1 |
| … | … | … |
Wherein, the value of the exposure click data is-1, which indicates that the short video is not exposed, the value of the exposure click data is 0, which indicates that the short video is exposed to the user but the user does not click, and the value of the exposure click data is 1, which indicates that the short video is exposed and the user clicks.
The updating of the historical user record corresponding to each information in the information set includes: and updating the exposure times, click times and click rates of the information corresponding to the feedback result in the information set in the crowd having the crowd labels of the users in the second crowd.
As a specific embodiment, the updating can be performed according to the following formula:
(1) updating the number of exposures show of information i in the population of user population tags ti，t
showi，t←showi，t+∑u∈Uutu，t*f(is_clicku，i)
Wherein the function f (is _ click)u，i) The definition is as follows:
wherein, (is _ click)u，i) Is the value of the exposure click data in the user feedback result, utu，tShow if user u is the user with the crowd tag t (0 means not yes, 1 means yes), showi，tIndicating the number of exposures of the information i in the population of the user population tag t.
(2) Updating click times of information i in crowd of user crowd label ti，t
Wherein g (is _ click)u，i) The function is defined as follows:
wherein is _ clicku，iIs the value of the exposure click data in the user feedback result, utu，tIndicates whether user u is a user with a crowd tag t (0 indicates not, 1 indicates yes), clicki，tIndicating the number of clicks of the information i in the user population tag t.
(3) Click rate ctr of updated information i in crowd of user crowd label ti，t
Wherein ctri，tClick rate of information i in the population of user population labels ti，tShow the number of clicks, show, of information i in the user population tag ti，tIndicating the number of exposures of the information i in the population of the user population tag t.
The updating the user record in the user list comprises: and updating the new user label of the user corresponding to the feedback result in the user list.
As a specific embodiment, the updating can be performed according to the following formula:
wherein g (is _ click)u，i) Definition of function asThe following:
wherein the sgn (x) function is defined as follows:
wherein I represents an information set; is _ new _ useruIs the value of the new user tag in the user list (1 indicates a new user, 0 indicates not a new user); is _ clicku，iIs the value of the exposure click data in the user feedback result.
According to the information recommendation method provided by the embodiment of the invention, information is respectively recommended to each user in a first group according to the historical user record corresponding to each information in the information set; selecting information with exposure times lower than a preset threshold value from the information set as recommendation information, recommending the recommendation information to each user in a second group respectively, and updating the historical user record corresponding to each information in the information set and the user record in the user list respectively according to the feedback result of each user in the second group to the recommendation information, wherein the users in the first group and the users in the second group are both users with new user labels in the user list, and the number of users in the second group is less than that of the first group, the scheme recommends information to a small part of new users in a 'heuristic recommendation' mode, finds high-quality information according to the feedback of the part of users, and recommends information which is verified to be high-quality to a large part of new users according to the historical user record corresponding to each information in the information set, the accuracy rate of recommending to the new user is improved, and the experience of the new user is further improved.
Fig. 8 is a flowchart illustrating an information recommendation method according to a second embodiment of the present invention, referring to fig. 8, the information recommendation method is executed in the server, and the method includes:
step S610, according to the crowd label corresponding to the user having the new user label, querying the historical user record corresponding to each information in the information set, and obtaining the click rate of each information in the crowd having the crowd label.
In one embodiment, the information is short information with a playing time length shorter than a preset time length.
Step S620, calculating a click index corresponding to each piece of information according to the crowd label and the click rate of each piece of information in the crowd with the crowd label.
In one embodiment, the click rate of each piece of information in the crowd having the crowd label is added to be used as the click index corresponding to each piece of information corresponding to the user having the new user label.
The implementation of steps S610 to S620 is similar to the implementation of steps S312 to S313 in the previous embodiment, and is not repeated here.
Step S630, according to each click index, recommending information to the user with the new user label.
As an embodiment, referring to fig. 9, step S530 includes:
step S631, sorting the information according to the click indexes;
step S632 is performed to select and recommend a predetermined number of recommendation information to the user with the new user tag according to the sorting result.
The implementation of step S631 to step S632 is similar to the implementation of step S321 to step S322 in the previous embodiment, and is not repeated here.
According to the information recommendation method provided by the embodiment of the invention, historical user records corresponding to all information in an information set are inquired according to the crowd labels corresponding to users with new user labels, and the click rate of all information in crowds with the crowd labels is obtained; calculating a click index corresponding to each piece of information according to the crowd label and the click rate of each piece of information in the crowd with the crowd label; according to the click indexes, information is recommended to the user with the new user label, according to the scheme, the information which is verified to be high-quality information is recommended to the new user according to other historical user records corresponding to the information in the information set, the accuracy rate of recommending to the new user is improved, and the experience of the new user is further improved.
Please refer to fig. 10, which is a functional module diagram of an information recommendation device 700 according to a third embodiment of the present invention. The information recommendation device 700 includes a first recommendation module 710 and a second recommendation module 720.
The first recommending module 710 is configured to recommend information to each user in the first group according to the historical user record corresponding to each information in the information set.
In one embodiment, the information is a short video with a playing time length less than a preset time length.
As an implementation manner, the first recommending module 710 is further configured to calculate, according to the historical user records corresponding to the pieces of information in the information set, click indexes of the pieces of information respectively corresponding to each user in the first group; and recommending information to each user in the first group according to each click index.
As an embodiment, the first recommending module 710 is further configured to obtain a crowd label of each user in the first group; inquiring historical user records corresponding to all information in the information set according to the crowd label of each user respectively to obtain the click rate of all information corresponding to each user; and respectively calculating the click indexes of the information corresponding to each user according to the crowd label of each user and the click rate of the information corresponding to each user.
As an implementation manner, the first recommending module 710 is further configured to add click rates of the information in the crowd having the crowd tag of the user to obtain a click index corresponding to the information corresponding to the user.
As an implementation manner, the first recommending module 710 is further configured to sort the information corresponding to each user according to the click indexes corresponding to each user in the first group; and selecting and recommending a preset number of pieces of recommendation information for each user according to the corresponding sorting result of each user.
In one embodiment, the apparatus further includes a dividing module 730, configured to obtain a plurality of users with new user tags from the user list; and dividing the users with the new user labels into a first group and a second group according to the proportion.
A second recommending module 720, configured to select information with exposure times lower than a preset threshold from the information set as recommendation information, recommend the recommendation information to each user in a second group respectively, and update a historical user record corresponding to each information in the information set and update a user record in a user list according to a feedback result of each user in the second group on the recommendation information respectively, where the users in the first group and the users in the second group are both users in the user list who have a new user tag, and the number of users in the second group is less than the number of users in the first group.
As an embodiment, the feedback result includes information of each user in the second group and information of whether each user clicks the recommendation information; the historical user record corresponding to each piece of information comprises an information identification number, a crowd label, and the exposure times, click times and click rates of the information corresponding to the information identification number in the crowd with the crowd label; the second recommending module 720 is further configured to update the exposure times, the click times, and the click rate of the information corresponding to the feedback result in the information set in the crowd having the crowd labels of the users in the second crowd.
As an embodiment, each user record in the user list includes a user identification number, a crowd tag, and a new user tag; the second recommending module 720 is further configured to update a new user tag of the user corresponding to the feedback result in the user list.
The above modules may be implemented by software codes, and in this case, the modules may be stored in the memory 201 of the server 200. The above modules may also be implemented by hardware, such as an integrated circuit chip.
Please refer to fig. 11, which is a schematic diagram illustrating functional modules of an information recommendation apparatus 800 according to a fourth embodiment of the present invention. The information recommendation device 800 includes a query module 810, a calculation module 820, and a third recommendation module 830.
The query module 810 is configured to query, according to the crowd tag corresponding to the user having the new user tag, the historical user record corresponding to each piece of information in the information set, and obtain the click rate of each piece of information in the crowd having the crowd tag.
In one embodiment, the information is a short video with a playing time length less than a preset time length.
The calculating module 820 is configured to calculate a click index corresponding to each piece of information according to the crowd label and the click rate of each piece of information in the crowd having the crowd label.
As an embodiment, the calculating module 820 is further configured to add the click rate of each piece of information in the crowd having the crowd label to obtain the click index corresponding to each piece of information corresponding to the user having the new user label.
And a third recommending module 830, configured to recommend information to the user with the new user tag according to each click index.
As an implementation manner, the third recommending module 830 is further configured to sort the information according to the click indexes; and selecting and recommending a preset number of pieces of recommendation information to the user with the new user label according to the sorting result.
The above modules may be implemented by software codes, and in this case, the modules may be stored in the memory 201 of the server 200. The above modules may also be implemented by hardware, such as an integrated circuit chip.
A fifth embodiment of the invention provides a server comprising a memory and a processor, the memory coupled to the processor, the memory storing instructions that, when executed by the processor, cause the processor to:
recommending information to each user in the first group according to the historical user record corresponding to each information in the information set;
selecting information with exposure times lower than a preset threshold value from the information set as recommendation information, recommending the recommendation information to each user in a second group respectively, and updating historical user records corresponding to each information in the information set and user records in an updated user list respectively according to feedback results of each user in the second group on the recommendation information, wherein the users in the first group and the users in the second group are users with new user labels in the user list, and the number of the users in the second group is less than that of the users in the first group.
A sixth embodiment of the invention provides a server comprising a memory and a processor, the memory coupled to the processor, the memory storing instructions that, when executed by the processor, cause the processor to:
according to the crowd label corresponding to the user with the new user label, querying a historical user record corresponding to each piece of information in an information set, and obtaining the click rate of each piece of information in the crowd with the crowd label;
calculating a click index corresponding to each piece of information according to the crowd label and the click rate of each piece of information in the crowd with the crowd label;
and recommending information to the user with the new user label according to each click index.
It should be noted that, in the present specification, the embodiments are all described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments may be referred to each other.
The information recommendation device provided by the embodiment of the invention has the same implementation principle and technical effect as the method embodiments, and for the sake of brief description, the corresponding contents in the method embodiments can be referred to where the device embodiments are not mentioned.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, 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, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block 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 will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes. It is noted that, herein, relational terms such as first and third, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention. It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (19)
1. An information recommendation method, the method comprising:
recommending information to each user in the first group according to the historical user record corresponding to each information in the information set;
selecting information with exposure times lower than a preset threshold value from the information set as recommendation information, recommending the recommendation information to each user in the second group respectively,
and respectively updating the historical user records corresponding to each information in the information set and the user records in the updated user list according to the feedback result of each user in the second group to the recommended information,
wherein, the users in the first group and the users in the second group are all the users with new user labels in the user list, and the number of users in the second group is less than that in the first group.
2. The method of claim 1, wherein the recommending information to each user in the first group according to the historical user record corresponding to each information in the information set comprises:
calculating the click indexes of the information respectively corresponding to each user in the first group according to the historical user records corresponding to the information in the information set;
and recommending information to each user in the first group according to each click index.
3. The method of claim 2, wherein calculating the click index of each piece of information corresponding to each user in the first group according to the historical user records corresponding to each piece of information in the information set comprises:
respectively acquiring a crowd label of each user in the first group;
inquiring historical user records corresponding to all information in the information set according to the crowd label of each user respectively to obtain the click rate of all information corresponding to each user;
and respectively calculating the click indexes of the information corresponding to each user according to the crowd label of each user and the click rate of the information corresponding to each user.
4. The method of claim 3, wherein said calculating the click through index of each information corresponding to each user according to the crowd label of each user and the click through rate of each information corresponding to each user comprises:
and adding the click rate of each piece of information in the crowd with the crowd label of the user to be used as the click index corresponding to each piece of information corresponding to the user.
5. The method of claim 2, wherein the recommending information to each user in the first group according to each click index comprises:
sorting the information corresponding to each user according to the click indexes corresponding to each user in the first group;
and selecting and recommending a preset number of pieces of recommendation information for each user according to the corresponding sorting result of each user.
6. The method of claim 1, further comprising:
acquiring a plurality of users with new user tags from the user list;
and dividing the users with the new user labels into a first group and a second group according to the proportion.
7. The method of claim 1, wherein the feedback result comprises information of each user in the second group and information of whether each user clicks on the recommendation information; the historical user record corresponding to each piece of information comprises an information identification number, a crowd label, the exposure times, the click times and the click rate of the information corresponding to the information identification number in the crowd with the crowd label,
the updating of the historical user record corresponding to each information in the information set includes:
and updating the exposure times, click times and click rates of the information corresponding to the feedback result in the information set in the crowd having the crowd labels of the users in the second crowd.
8. The method of claim 1, wherein each user record in the user list includes a user identification number, a crowd tag, and a new user tag;
the updating the user record in the user list comprises:
and updating the new user label of the user corresponding to the feedback result in the user list.
9. The method according to any one of claims 1 to 8, wherein the information is a short video having a playing time duration less than a predetermined time duration.
10. An information recommendation apparatus, comprising:
the first recommending module is used for recommending information to each user in the first group according to the historical user record corresponding to each information in the information set;
and the second recommending module is used for selecting information with the exposure times lower than a preset threshold value from the information set as recommending information, recommending the recommending information to each user in a second group respectively, and updating the historical user record corresponding to each information in the information set and the user record in the user list respectively according to the feedback result of each user in the second group on the recommending information, wherein the users in the first group and the users in the second group are both users in the user list with new user labels, and the number of the users in the second group is less than that of the users in the first group.
11. The apparatus of claim 10, wherein the first recommending module is further configured to calculate a click index of each piece of information corresponding to each user in the first group according to a historical user record corresponding to each piece of information in the information set; and recommending information to each user in the first group according to each click index.
12. The apparatus of claim 11, wherein the first recommending module is further configured to obtain a crowd label for each user in the first group; inquiring historical user records corresponding to all information in the information set according to the crowd label of each user respectively to obtain the click rate of all information corresponding to each user; and respectively calculating the click indexes of the information corresponding to each user according to the crowd label of each user and the click rate of the information corresponding to each user.
13. The apparatus of claim 12, wherein the first recommending module is further configured to add click rates of the information in the crowd having the crowd tag of the user to obtain the click index corresponding to the information corresponding to the user.
14. The apparatus of claim 11, wherein the first recommending module is further configured to sort the information corresponding to each user according to the click indexes corresponding to the users in the first group; and selecting and recommending a preset number of pieces of recommendation information for each user according to the corresponding sorting result of each user.
15. The apparatus of claim 10, further comprising a partitioning module configured to obtain a plurality of users with new user tags from the user list; and dividing the users with the new user labels into a first group and a second group according to the proportion.
16. The apparatus of claim 10, wherein the feedback result comprises information of each user in the second group and information of whether each user clicks on the recommendation information; the historical user record corresponding to each piece of information comprises an information identification number, a crowd label, and the exposure times, click times and click rates of the information corresponding to the information identification number in the crowd with the crowd label; the second recommending module is further configured to update the exposure times, click times and click rates of the information corresponding to the feedback result in the information set in the crowd having the crowd labels of the users in the second crowd.
17. The apparatus of claim 10, wherein each user record in the user list comprises a user identification number, a crowd tag, and a new user tag; the second recommending module is further configured to update a new user tag of the user corresponding to the feedback result in the user list.
18. The apparatus according to any one of claims 10 to 17, wherein the information is a short video having a playing time duration less than a predetermined time duration.
19. A server, comprising a memory and a processor, the memory coupled to the processor, the memory storing instructions that, when executed by the processor, cause the processor to:
recommending information to each user in the first group according to the historical user record corresponding to each information in the information set;
selecting information with exposure times lower than a preset threshold value from the information set as recommendation information, recommending the recommendation information to each user in a second group respectively, and updating historical user records corresponding to each information in the information set and user records in an updated user list respectively according to feedback results of each user in the second group on the recommendation information, wherein the users in the first group and the users in the second group are users with new user labels in the user list, and the number of the users in the second group is less than that of the users in the first group.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710530877.5A CN107273538B (en) | 2017-06-29 | 2017-06-29 | Information recommendation method, device and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710530877.5A CN107273538B (en) | 2017-06-29 | 2017-06-29 | Information recommendation method, device and server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107273538A CN107273538A (en) | 2017-10-20 |
| CN107273538B true CN107273538B (en) | 2020-07-07 |
Family
ID=60070468
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710530877.5A Active CN107273538B (en) | 2017-06-29 | 2017-06-29 | Information recommendation method, device and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107273538B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108804577B (en) * | 2018-05-24 | 2022-11-01 | 联通在线信息科技有限公司 | Method for estimating interest degree of information tag |
| CN111523050B (en) * | 2020-04-16 | 2023-09-19 | 咪咕文化科技有限公司 | Content recommendation method, server and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101556622A (en) * | 2008-04-11 | 2009-10-14 | 纳珀企业有限责任公司 | Providing expected desirability information prior to sending a recommendation |
| CN103425703A (en) * | 2012-05-25 | 2013-12-04 | 深圳市腾讯计算机系统有限公司 | Method and device for processing network information |
| CN104504098A (en) * | 2014-12-29 | 2015-04-08 | 北京奇虎科技有限公司 | Information recommending method and device |
| CN105335509A (en) * | 2015-10-29 | 2016-02-17 | 广州神马移动信息科技有限公司 | Method and device for recommending activity information and server |
| CN106446189A (en) * | 2016-09-29 | 2017-02-22 | 广州艾媒数聚信息咨询股份有限公司 | Message-recommending method and system |
-
2017
- 2017-06-29 CN CN201710530877.5A patent/CN107273538B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101556622A (en) * | 2008-04-11 | 2009-10-14 | 纳珀企业有限责任公司 | Providing expected desirability information prior to sending a recommendation |
| CN103425703A (en) * | 2012-05-25 | 2013-12-04 | 深圳市腾讯计算机系统有限公司 | Method and device for processing network information |
| CN104504098A (en) * | 2014-12-29 | 2015-04-08 | 北京奇虎科技有限公司 | Information recommending method and device |
| CN105335509A (en) * | 2015-10-29 | 2016-02-17 | 广州神马移动信息科技有限公司 | Method and device for recommending activity information and server |
| CN106446189A (en) * | 2016-09-29 | 2017-02-22 | 广州艾媒数聚信息咨询股份有限公司 | Message-recommending method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107273538A (en) | 2017-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107222566B (en) | Information pushing method and device and server | |
| CN108521439B (en) | Message pushing method and device | |
| US10943267B2 (en) | Machine learning assisted target segment audience generation | |
| US11580447B1 (en) | Shared per content provider prediction models | |
| CN105550903B (en) | Target user determination method and device | |
| US8204878B2 (en) | System and method for finding unexpected, but relevant content in an information retrieval system | |
| US8631122B2 (en) | Determining demographics based on user interaction | |
| US10719854B2 (en) | Method and system for predicting future activities of user on social media platforms | |
| US20160364736A1 (en) | Method and system for providing business intelligence based on user behavior | |
| CN108563670B (en) | Video recommendation method and device, server and computer-readable storage medium | |
| US20160034948A1 (en) | System and method for fractional attribution utilizing user-level data and aggregate level data | |
| US20180307733A1 (en) | User characteristic extraction method and apparatus, and storage medium | |
| US20180068028A1 (en) | Methods and systems for identifying same users across multiple social networks | |
| CN109120719B (en) | Information pushing method, information display method, computer equipment and storage medium | |
| CN111178970A (en) | Advertisement delivery method and device, electronic equipment and computer readable storage medium | |
| CN108959323B (en) | Video classification method and device | |
| KR102422410B1 (en) | System and method for matching client and influencer | |
| WO2018133566A1 (en) | Method and device for determining freshness of promotional information, electronic device, and storage medium | |
| CN112100489A (en) | Object recommendation method, device and computer storage medium | |
| CN111242709A (en) | Message pushing method and device, equipment and storage medium thereof | |
| CN112015986B (en) | Data pushing method, device, electronic equipment and computer readable storage medium | |
| CN107273538B (en) | Information recommendation method, device and server | |
| CN106919692B (en) | Method and device for pushing message | |
| US20230316106A1 (en) | Method and apparatus for training content recommendation model, device, and storage medium | |
| CN113434762A (en) | Association pushing method, device and equipment based on user information and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200529 Address after: 310051 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: Alibaba (China) Co.,Ltd. Address before: 510627 Guangdong city of Guangzhou province Whampoa Tianhe District Road No. 163 Xiping Yun Lu Yun Ping square B radio tower 15 layer self unit 02 (only for office use) Applicant before: GUANGZHOU UC NETWORK TECHNOLOGY Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |