[go: up one dir, main page]

CN114861061B - Method, device, equipment, storage medium and program product for sending display information - Google Patents

Method, device, equipment, storage medium and program product for sending display information

Info

Publication number
CN114861061B
CN114861061B CN202210572451.7A CN202210572451A CN114861061B CN 114861061 B CN114861061 B CN 114861061B CN 202210572451 A CN202210572451 A CN 202210572451A CN 114861061 B CN114861061 B CN 114861061B
Authority
CN
China
Prior art keywords
label
click
collection
labels
historical
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
Application number
CN202210572451.7A
Other languages
Chinese (zh)
Other versions
CN114861061A (en
Inventor
张众一
何丽
李忆纯
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Sankuai Online Technology Co Ltd
Original Assignee
Beijing Sankuai Online Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Sankuai Online Technology Co Ltd filed Critical Beijing Sankuai Online Technology Co Ltd
Priority to CN202210572451.7A priority Critical patent/CN114861061B/en
Publication of CN114861061A publication Critical patent/CN114861061A/en
Application granted granted Critical
Publication of CN114861061B publication Critical patent/CN114861061B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06F16/9538—Presentation of query results
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
    • G06F16/9562—Bookmark management

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

本申请公开了一种发送展示信息的方法、装置、设备、存储介质和程序产品，属于计算机技术领域。所述方法包括：基于多个标签分别对应的统计数据，对多个标签进行筛选，得到多个可推荐标签；基于目标账户的历史行为数据，确定目标账户对应的多个参考标签；将多个可推荐标签和多个参考标签之间的交集，确定为目标账户对应的目标推荐标签；获取每个目标推荐标签对应的目标展示信息，向目标账户所属的目标终端发送目标展示信息。采用本申请，可以确定出既有质量、具有可推荐性，用户又感兴趣的目标推荐标签，从而提高推荐效果。

The present application discloses a method, apparatus, device, storage medium and program product for sending display information, and belongs to the field of computer technology. The method comprises: screening multiple tags based on statistical data corresponding to multiple tags to obtain multiple recommendable tags; determining multiple reference tags corresponding to the target account based on the historical behavior data of the target account; determining the intersection between the multiple recommendable tags and the multiple reference tags as the target recommendation tag corresponding to the target account; obtaining the target display information corresponding to each target recommendation tag, and sending the target display information to the target terminal to which the target account belongs. By adopting the present application, it is possible to determine target recommendation tags that are of both quality and recommendability and that the user is interested in, thereby improving the recommendation effect.

Description

Method, apparatus, device, storage medium and program product for transmitting presentation information
Technical Field
The present application relates to the field of computer technology, and in particular, to a method, an apparatus, a device, a storage medium, and a program product for transmitting presentation information.
Background
Many current application programs have a recommendation function, and the viscosity of a user is improved and the use experience of the user is improved by recommending display information possibly interested in the application programs to the user.
In a typical recommendation method, display information with a high click rate or collection rate is directly recommended to a user.
However, the recommendation method is rough, the display information which is not interested by the user may be recommended to the user, and the final recommendation effect is poor.
Disclosure of Invention
The embodiment of the application provides a method for sending display information, which can solve the problem of poor recommendation effect caused by rough recommendation method in the prior art.
In a first aspect, there is provided a method of transmitting presentation information, the method comprising:
screening the plurality of labels based on the statistical data corresponding to the plurality of labels respectively to obtain a plurality of recommended labels, wherein the labels are information for indicating the content characteristics of the display information;
determining a plurality of reference labels corresponding to a target account based on historical behavior data of the target account;
Determining an intersection set between the plurality of recommendable labels and the plurality of reference labels as a target recommendation label corresponding to the target account;
And acquiring target display information corresponding to each target recommendation label, and sending the target display information to a target terminal to which the target account belongs.
In one possible implementation, the method further includes:
and for each piece of display information, determining a label corresponding to the display information based on the display information and a keyword extraction model.
In one possible implementation manner, the filtering the plurality of tags based on the statistics data corresponding to the plurality of tags respectively to obtain a plurality of recommended tags includes:
determining the user interest intensity corresponding to each label based on the statistical data corresponding to each label;
And screening the plurality of labels based on the user interest intensity corresponding to each label and a preset intensity threshold value to obtain a plurality of recommended labels.
In one possible implementation, the statistics include click statistics and collection statistics.
In a possible implementation manner, the click statistics data includes a first click rate corresponding to all users in a first preset period and a second click rate corresponding to a historical click user in the first preset period, where the historical click user is a user who performs a click operation on any display information corresponding to the tag in a second preset period before the first preset period and performs an exposure operation on the display information corresponding to the tag in the first preset period;
The collection statistics data comprise first collection rates corresponding to all users in the first preset period and second collection rates corresponding to historical collection users in the first preset period, wherein the historical collection users are users who perform collection operation on any display information corresponding to the tag in the second preset period and perform overexposure operation on the display information corresponding to the tag in the first preset period;
the determining the user interest intensity corresponding to each tag based on the statistical data corresponding to the plurality of tags respectively includes:
For each tag, determining the click interest intensity of the user corresponding to the tag based on the first click rate and the second click rate corresponding to the tag;
Determining the user collection interest intensity corresponding to the label based on the first collection rate and the second collection rate corresponding to the label;
And determining the user interest intensity corresponding to the tag based on the user click interest intensity and the user collection interest intensity corresponding to the tag.
In one possible implementation manner, the determining, based on the historical behavior data of the target account, a plurality of reference tags corresponding to the target account includes:
Determining a short-term label corresponding to the target account based on historical behavior data in a third preset time period of the target account, wherein the third preset time period is a time period in which a plurality of pieces of user behavior information exist recently, and the time difference between every two pieces of adjacent user behavior information is smaller than a preset time length;
determining a long-term label corresponding to the target account based on historical behavior data in a fourth preset period of the target account;
and determining a reference label corresponding to the target account based on the short-term label corresponding to the target account and the long-term label corresponding to the target account.
In one possible implementation, the historical behavior data includes historical click data and historical collection data, the historical click data includes one or more historical click display information and click time points corresponding to each historical click display information, and the historical collection data includes one or more historical collection display information and collection time points corresponding to each historical collection display information.
In one possible implementation manner, the determining, based on the historical behavior data in the third preset period of time of the target account, the short-term label corresponding to the target account includes:
acquiring a short-term click tag corresponding to the historical click data in a third preset period of the target account and a short-term collection tag corresponding to the historical collection data in the third preset period of the target account;
Respectively determining the latest click time point corresponding to each short-term click label in the click time points corresponding to one or more pieces of historical click display information corresponding to each short-term click label;
Selecting a first preset number of short-term click labels according to the sequence from near to far of the latest click time points, and obtaining target short-term click labels corresponding to the target account;
respectively determining the latest collection time point corresponding to each short-term collection label in the collection time points corresponding to one or more pieces of historical collection display information corresponding to each short-term collection label;
Selecting a second preset number of short-term collection labels according to the sequence from near to far of the latest collection time point to obtain target short-term collection labels corresponding to the target account;
And performing de-duplication treatment on the target short-term click label and the target short-term collection label to obtain a short-term label corresponding to the target account.
In one possible implementation manner, the determining, based on the historical behavior data in the fourth preset period of the target account, the long-term label corresponding to the target account includes:
Acquiring a long-term click tag corresponding to the historical click data in a fourth preset period of the target account and a long-term collection tag corresponding to the historical collection data in the fourth preset period of the target account;
performing de-duplication treatment on the long-term click label and the long-term collection label to obtain a reference long-term label corresponding to the target account;
Determining the correlation degree between each reference long-term label and the target account respectively based on historical behavior data in a fourth preset period corresponding to each reference long-term label;
And selecting a third preset number of reference long-term labels according to the sequence of the correlation from high to low to obtain the long-term labels corresponding to the target account.
In one possible implementation manner, after the determining the long-term label corresponding to the target account, the method further includes:
Acquiring a feature vector corresponding to each tag;
for each long-term label, calculating the similarity between each label and the long-term label;
determining expansion labels corresponding to each long-term label based on the similarity between each label and the long-term label;
The determining the reference label corresponding to the target account based on the short-term label corresponding to the target account and the long-term label corresponding to the target account includes:
And determining a reference label corresponding to the target account based on the short-term label corresponding to the target account, the long-term label corresponding to the target account and the expansion label corresponding to each long-term label.
In one possible implementation manner, the obtaining the target display information corresponding to each target recommendation tag includes:
For each target recommendation label, determining a score of each piece of display information corresponding to the target recommendation label based on the statistical data of each piece of display information corresponding to the target recommendation label;
and selecting a fourth preset number of display information according to the order of the scores from high to low to obtain target display information corresponding to the target recommendation label.
In a second aspect, there is provided an apparatus for transmitting presentation information, the apparatus comprising:
The screening module is used for screening the plurality of labels based on the statistical data corresponding to the labels respectively to obtain a plurality of recommended labels, wherein the labels are information for indicating the content characteristics of the display information;
The first determining module is used for determining a plurality of reference labels corresponding to the target account based on historical behavior data of the target account;
The second determining module is used for determining the intersection set between the plurality of recommendable labels and the plurality of reference labels as a target recommendation label corresponding to the target account;
the sending module is used for obtaining the target display information corresponding to each target recommendation label and sending the target display information to the target terminal to which the target account belongs.
In one possible implementation manner, the apparatus further includes a tag determination module configured to:
and for each piece of display information, determining a label corresponding to the display information based on the display information and a keyword extraction model.
In one possible implementation manner, the screening module is configured to:
determining the user interest intensity corresponding to each label based on the statistical data corresponding to each label;
And screening the plurality of labels based on the user interest intensity corresponding to each label and a preset intensity threshold value to obtain a plurality of recommended labels.
In one possible implementation, the statistics include click statistics and collection statistics.
In a possible implementation manner, the click statistics data includes a first click rate corresponding to all users in a first preset period and a second click rate corresponding to a historical click user in the first preset period, where the historical click user is a user who performs a click operation on any display information corresponding to the tag in a second preset period before the first preset period and performs an exposure operation on the display information corresponding to the tag in the first preset period;
The collection statistics data comprise first collection rates corresponding to all users in the first preset period and second collection rates corresponding to historical collection users in the first preset period, wherein the historical collection users are users who perform collection operation on any display information corresponding to the tag in the second preset period and perform overexposure operation on the display information corresponding to the tag in the first preset period;
The screening module is used for:
For each tag, determining the click interest intensity of the user corresponding to the tag based on the first click rate and the second click rate corresponding to the tag;
Determining the user collection interest intensity corresponding to the label based on the first collection rate and the second collection rate corresponding to the label;
And determining the user interest intensity corresponding to the tag based on the user click interest intensity and the user collection interest intensity corresponding to the tag.
In one possible implementation manner, the first determining module is configured to:
Determining a short-term label corresponding to the target account based on historical behavior data in a third preset time period of the target account, wherein the third preset time period is a time period in which a plurality of pieces of user behavior information exist recently, and the time difference between every two pieces of adjacent user behavior information is smaller than a preset time length;
determining a long-term label corresponding to the target account based on historical behavior data in a fourth preset period of the target account;
and determining a reference label corresponding to the target account based on the short-term label corresponding to the target account and the long-term label corresponding to the target account.
In one possible implementation, the historical behavior data includes historical click data and historical collection data, the historical click data includes one or more historical click display information and click time points corresponding to each historical click display information, and the historical collection data includes one or more historical collection display information and collection time points corresponding to each historical collection display information.
In one possible implementation manner, the first determining module is configured to:
acquiring a short-term click tag corresponding to the historical click data in a third preset period of the target account and a short-term collection tag corresponding to the historical collection data in the third preset period of the target account;
Respectively determining the latest click time point corresponding to each short-term click label in the click time points corresponding to one or more pieces of historical click display information corresponding to each short-term click label;
Selecting a first preset number of short-term click labels according to the sequence from near to far of the latest click time points, and obtaining target short-term click labels corresponding to the target account;
respectively determining the latest collection time point corresponding to each short-term collection label in the collection time points corresponding to one or more pieces of historical collection display information corresponding to each short-term collection label;
Selecting a second preset number of short-term collection labels according to the sequence from near to far of the latest collection time point to obtain target short-term collection labels corresponding to the target account;
And performing de-duplication treatment on the target short-term click label and the target short-term collection label to obtain a short-term label corresponding to the target account.
In one possible implementation manner, the first determining module is configured to:
Acquiring a long-term click tag corresponding to the historical click data in a fourth preset period of the target account and a long-term collection tag corresponding to the historical collection data in the fourth preset period of the target account;
performing de-duplication treatment on the long-term click label and the long-term collection label to obtain a reference long-term label corresponding to the target account;
Determining the correlation degree between each reference long-term label and the target account respectively based on historical behavior data in a fourth preset period corresponding to each reference long-term label;
And selecting a third preset number of reference long-term labels according to the sequence of the correlation from high to low to obtain the long-term labels corresponding to the target account.
In one possible implementation manner, after the determining the long-term label corresponding to the target account, the first determining module is further configured to:
Acquiring a feature vector corresponding to each tag;
for each long-term label, calculating the similarity between each label and the long-term label;
determining expansion labels corresponding to each long-term label based on the similarity between each label and the long-term label;
The determining the reference label corresponding to the target account based on the short-term label corresponding to the target account and the long-term label corresponding to the target account includes:
And determining a reference label corresponding to the target account based on the short-term label corresponding to the target account, the long-term label corresponding to the target account and the expansion label corresponding to each long-term label.
In one possible implementation manner, the sending module is configured to:
For each target recommendation label, determining a score of each piece of display information corresponding to the target recommendation label based on the statistical data of each piece of display information corresponding to the target recommendation label;
and selecting a fourth preset number of display information according to the order of the scores from high to low to obtain target display information corresponding to the target recommendation label.
In a third aspect, a computer device is provided that includes a processor and a memory having at least one instruction stored therein that is loaded and executed by the processor to perform operations performed by a method of transmitting presentation information.
In a fourth aspect, a computer-readable storage medium having stored therein at least one instruction for loading and execution by a processor to perform operations performed by a method of transmitting presentation information is provided.
In a fifth aspect, a computer program product is provided, comprising at least one instruction therein, the at least one instruction being loaded and executed by a processor to implement operations performed by a method of transmitting presentation information.
The technical scheme provided by the embodiment of the application has the beneficial effects that the scheme can be used for screening the plurality of labels based on the statistical data corresponding to the labels respectively, so that a plurality of recommendable labels with good quality and recommendability are obtained, then, based on the historical behavior data of the target account, the reference labels which are interested by a plurality of users and correspond to the target account are determined, then, the intersection between the recommendable labels and the reference labels is determined as the target recommendation labels corresponding to the target account, finally, the target display information corresponding to each target recommendation label is obtained, and the target display information is sent to the target terminal which the target account belongs to. By adopting the method and the device, the target recommendation label which has the quality and the recommendability and is interested by the user can be determined, so that the recommendation effect is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for sending presentation information according to an embodiment of the present application;
FIG. 2 is a flow chart of a method for determining a short term tag according to an embodiment of the present application;
FIG. 3 is a flow chart of a method for determining long-term tags provided by an embodiment of the present application;
Fig. 4 is a schematic structural diagram of a device for sending display information according to an embodiment of the present application;
fig. 5 is a block diagram of a server according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings.
The embodiment of the application provides a method for sending display information, which can be realized by a server. The server may be a single server or may be a server cluster formed by a plurality of servers.
The server may comprise a processor, a memory, a communication means, etc., to which the processor is connected, respectively.
The processor may be a CPU (Central Processing Unit ). The processor may be configured to read the instructions and process the data, for example, filter the plurality of tags to obtain a plurality of recommendable tags, determine a plurality of reference tags corresponding to the target account, determine a target recommendation tag corresponding to the target account, obtain target presentation information corresponding to each target recommendation tag, and so on.
The Memory may include ROM (Read-Only Memory), RAM (Random Access Memory ), CD-ROM (Compact Disc Read-Only Memory), magnetic disk, optical data storage device, and the like. The memory may be used for data storage, for example, storage of data for a plurality of tags, storage of data for a plurality of recommendable tags, storage of historical behavioral data for a target account, storage of data for a plurality of reference tags corresponding to a determined target account, storage of data for a target recommended tag corresponding to a determined target account, storage of data for target presentation information corresponding to each tag, and so forth.
The communication means may be a wired network connector, a wireless fidelity module, a bluetooth module, a cellular network communication module, etc. The communication means may be used to receive and transmit signals, for example, to transmit target presentation information to a target terminal to which a target account belongs, and so on.
Fig. 1 is a flowchart of a method for sending presentation information according to an embodiment of the present application. Referring to fig. 1, this embodiment includes:
101. And screening the plurality of labels based on the statistical data corresponding to the plurality of labels respectively to obtain a plurality of recommended labels.
Wherein the tag is information for indicating a content characteristic of the presentation information.
In implementations, each presentation information corresponds to one or more tags. When the display information is required to be recommended to the target account, the statistical data corresponding to each label can be acquired first, and then the labels with better quality and recommendation performance can be screened out according to the statistical data.
Optionally, the method for screening the plurality of tags through the statistical data may be that the user interest intensity corresponding to each tag is determined based on the statistical data corresponding to each of the plurality of tags. And screening the plurality of labels based on the user interest intensity corresponding to each label and a preset intensity threshold value to obtain a plurality of recommended labels.
In practice, the worker may preset a preset intensity threshold. When a plurality of labels need to be screened, the user interest intensity corresponding to each label can be calculated based on the statistical data corresponding to each label, and the user interest intensity is used for representing the interest degree of the user on the label. Then, a tag whose user interest intensity is greater than or equal to a preset intensity threshold may be determined as a recommended tag.
102. And determining a plurality of reference labels corresponding to the target account based on the historical behavior data of the target account.
In implementation, when the information is required to be recommended and displayed to the target account, a plurality of reference tags corresponding to the target account are also required to be determined according to the historical behavior data of the target account, wherein the reference tags are tags which are interested by the user to which the target account belongs.
Optionally, the method for determining the reference tag through the historical behavior data of the target account may be that a short-term tag corresponding to the target account is determined based on the historical behavior data of the target account in a third preset period, wherein the third preset period is a period in which a plurality of pieces of user behavior information exist recently, and a time difference between every two adjacent pieces of user behavior information is smaller than a preset duration. And determining the long-term label corresponding to the target account based on the historical behavior data in the fourth preset period of the target account. And determining a reference label corresponding to the target account based on the short-term label corresponding to the target account and the long-term label corresponding to the target account.
In implementation, the short-term label is a label that the user to which the target account belongs is interested in the last period of time, and the long-term label is a label that the user to which the target account belongs is interested in a long period of time.
When the short-term label corresponding to the target account is determined, historical behavior data in a relatively short period of time, namely, the historical behavior data in the third preset period of time, can be obtained, wherein the third preset period of time is a period of time in which a plurality of pieces of user behavior information exist recently, and the time difference between every two pieces of adjacent user behavior information in the period of time is smaller than a preset duration, and in general, the third preset period of time can be called session. The preset duration may be set to any reasonable duration, for example, the preset duration may be set to half an hour, etc., which is not limited in the embodiment of the present application.
When the long-term label corresponding to the target account is determined, historical behavior data in a longer period of time, namely the fourth preset period, can be obtained. The fourth preset period may be longer than the third preset period, for example, the fourth preset period may be set to half a year, or the like, or may be another reasonable period, which is not limited in the embodiment of the present application.
After the short-term label and the long-term label corresponding to the target account are determined, the short-term label and the long-term label can be directly determined as the reference label corresponding to the target account, the short-term label and the long-term label can be screened in other modes, and the label obtained after screening is determined as the reference label corresponding to the target account.
103. And determining an intersection set between the plurality of recommendable labels and the plurality of reference labels as a target recommendation label corresponding to the target account.
In implementation, after determining a plurality of recommendable labels and a plurality of reference labels corresponding to the target account, an intersection between the recommendable labels and the target account can be obtained, and then the target recommended label which has recommendation quality and meets the interest requirements of the user to which the target account belongs can be obtained.
104. And acquiring target display information corresponding to each target recommendation label, and sending the target display information to a target terminal to which the target account belongs.
In implementation, all the display information corresponding to each target recommendation label can be directly used as target display information to be pushed to the target terminal. The display information corresponding to the target recommendation label can be screened to obtain target display information, and then the target display information is pushed to the target terminal.
Optionally, the method for screening the display information corresponding to the target recommendation label may include determining, for each target recommendation label, a score of each display information corresponding to the target recommendation label based on the statistical data of each display information corresponding to the target recommendation label. And selecting a fourth preset number of display information according to the order of the scores from high to low to obtain target display information corresponding to the target recommendation label.
The statistical data of the display information may include the click rate and the collection rate of the fifth preset period, and the score of the display information may be determined by the sum of the click rate and the collection rate of the display information in the fifth preset period, which may, of course, be other calculation manners.
Before step 101, a label corresponding to each presentation information may be determined, and the method for determining the label may be various, which is listed as follows:
For each presentation information, determining a label corresponding to the presentation information based on the presentation information and the keyword extraction model.
In implementation, attribute information of the display information or information such as content of the display information may be input into a trained keyword extraction model, so as to obtain one or more keywords corresponding to the display information. The keywords can be directly used as labels corresponding to the display information, or one or more obtained keywords can be combined by using a preset template, so that one or more labels corresponding to the display information are obtained, for example, the keywords of the display information output by a keyword extraction model can be divided into time, cuisine, taste, quality, place, activity, place and the like, and the preset template can comprise time+cuisine, taste+cuisine, category+cuisine, place+cuisine, place+activity, time+place, taste+place, quality+place, place+place and the like.
In step 101, a plurality of labels may also be screened based on a preset rule, where the preset rule may be set according to requirements, and the following two preset rules are used:
First kind
The first display information number threshold may be preset by the staff. During screening, the number of the display information corresponding to each label can be obtained, and the labels with the number of the corresponding display information smaller than the threshold value of the number of the first display information are removed.
Second kind
Each presentation information corresponds to one or more categories. Categories are more coarsely grained divisions than labels. The staff may preset a second presented information number threshold.
During screening, for each tag, acquiring one or more categories of display information corresponding to the tag, determining the target category with the largest number of the corresponding display information, and removing the tag if the number of the display information corresponding to the target category is smaller than a second display information number threshold.
The preset rule may be any reasonable setting, which is not limited in the embodiment of the present application.
The statistics in step 101 may be possible, and the statistics including click statistics and collection statistics will be described in more detail, but of course, other statistics may be included, which is not limited by the embodiment of the present application.
In more detail, the click statistics data may include a first click rate corresponding to all users in a first preset period and a second click rate corresponding to a history click user in the first preset period, where the history click user is a user who performs a click operation on any display information corresponding to the tag in a second preset period before the first preset period and performs an overexposure operation on the display information corresponding to the tag in the first preset period.
The first click rate corresponding to the label is the ratio of the click rate to the exposure of all the users to the display information corresponding to the label in a first preset period. The second click rate corresponding to the label is the ratio of the click rate of the history click user on the display information corresponding to the label to the exposure in the first preset time period.
The second preset time period is adjacent to the first preset time period, and the second preset time period is located before the first preset time period. For example, the duration of the first preset period is set to be one day, the duration of the second preset period is set to be one week, and when the second click rate corresponding to the a label in the 3 month number 10 is to be determined, a user who performs the click operation on any display information corresponding to the a label in the 3 month number 3 to the 3 month number 9 and performs the exposure operation in the 3 month number 10 may be obtained first as the historical click user.
The first click rate may be used to characterize the level of interest of all users in the tag, and the second click rate may be used to characterize the level of interest of users in the tag when they recommends the presentation information corresponding to the tag again.
And the collection statistics data can comprise first collection rates corresponding to all users in a first preset period and second collection rates corresponding to historical collection users in the first preset period, wherein the historical collection users are users who perform collection operation on any display information corresponding to the tag in the second preset period and perform exposure operation on the display information corresponding to the tag in the first preset period.
Based on the click statistics and the collection statistics, the method for determining the user interest intensity corresponding to each tag may be as follows:
And for each label, determining the click interest intensity of the user corresponding to the label based on the first click rate and the second click rate corresponding to the label. And determining the user collection interest intensity corresponding to the label based on the first collection rate and the second collection rate corresponding to the label. And determining the user interest intensity corresponding to the tag based on the user click interest intensity and the user collection interest intensity corresponding to the tag.
In practice, the user interest intensity corresponding to a tag may be determined based on the following equations 1-3.
Where gamma is the intensity of the user's interest,Is the intensity of the user's click interest,Is the collection interest intensity of the user,Is the first click-through rate and,Is the second click rate, a and B are weights,Is the first collection rate of the utility model,Is the second collection rate.
Alternatively, for a case where a tag has multiple corresponding presentation information, the user interest intensity corresponding to the tag may be determined based on statistics corresponding to each presentation information. For example, in an application program with a consumption function, it is necessary to recommend the comment content for the target account, and in the application program, each tag may correspond to at least one comment content and at least one POI (Point OfInterest, interest point), when determining the user interest intensity corresponding to each tag, the user interest intensity corresponding to the comment content may be calculated based on the statistics of the comment content corresponding to the tag, the user interest intensity corresponding to the POI may be calculated based on the statistics of the POI corresponding to the tag, and then the two may be added to obtain the user interest intensity corresponding to the tag.
The historical behavior data in step 102 may be a plurality of possible types, and the historical behavior data including the historical click data and the historical collection data will be described in more detail below, but of course, other statistical data may be included, which is not limited by the embodiment of the present application.
In more detail, the historical click data may include one or more historical click display information and a click time point corresponding to each historical click display information, where the historical click display information is the display information clicked by the target account in the third preset period or the fourth preset period, and the click time point corresponding to the historical click display information is a time point when the user to which the target account belongs clicks the historical click display information.
The historical collection data may include one or more historical collection display information and a collection time point corresponding to each of the historical collection display information, where the historical collection display information is display information collected by the target account in a third preset period or a fourth preset period, and the collection time point corresponding to the historical collection display information is a time point when the user to which the target account belongs collects the historical collection display information.
Optionally, the history click display information and the history collection display information may include various display information, for example, may include comment content, POI, and the like, which is not limited in the embodiment of the present application.
Based on the above settings of the historical click data and the historical collection data, the method for determining the short-term label corresponding to the target account may refer to fig. 2, which corresponds to the following:
201. And acquiring a short-term click label corresponding to the historical click data in a third preset period of the target account and a short-term collection label corresponding to the historical collection data in the third preset period of the target account.
In implementation, one or more labels corresponding to a plurality of pieces of historical click display information included in the historical click data in the third preset period of time can be obtained, and then the labels are subjected to de-duplication processing, so that short-term click labels are obtained. Similarly, one or more labels corresponding to a plurality of pieces of history collection display information included in the history collection data in the third preset period of time may be obtained, and then the labels are subjected to deduplication processing, so as to obtain short-term collection labels.
202. And respectively determining the latest click time point corresponding to each short-term click label in the click time points corresponding to one or more pieces of historical click display information corresponding to each short-term click label.
In implementation, for each short-term click tag, one or more click time points corresponding to the historical click display information corresponding to the short-term click tag are obtained, and then the click time point nearest to the current time is determined as the nearest click time point corresponding to the short-term click tag.
203. And selecting a first preset number of short-term click labels according to the sequence from near to far of the latest click time points, and obtaining target short-term click labels corresponding to the target account.
In implementation, the short-term click labels are arranged according to the sequence from the near to the far of the corresponding latest click time points, and the first preset number of short-term click labels are determined to be the target short-term click labels corresponding to the target account. The first preset number may be any reasonable number, for example, may be 50, etc., which is not limited by the embodiment of the present application.
204. And respectively determining the latest collection time point corresponding to each short-term collection label in the collection time points corresponding to one or more pieces of historical collection display information corresponding to each short-term collection label.
In implementation, for each short-term collection tag, a collection time point corresponding to one or more historical collection display information corresponding to the short-term collection tag is obtained, and then the collection time point nearest to the current time is determined as the nearest collection time point corresponding to the short-term collection tag.
205. And selecting a second preset number of short-term collection labels according to the sequence from near to far of the latest collection time point, and obtaining a target short-term collection label corresponding to the target account.
In the implementation, the short-term collection labels are arranged according to the sequence from the near to the far of the corresponding nearest collection time points, and the second preset number of short-term collection labels are determined to be the target short-term collection labels corresponding to the target accounts. The second preset number may be any reasonable number, for example, may be 30, etc., and may be the same as or different from the first preset number, which is not limited in the embodiment of the present application.
It will be appreciated that steps 202-203 and steps 204-205 are not in chronological order.
206. And performing de-duplication treatment on the target short-term click label and the target short-term collection label to obtain a short-term label corresponding to the target account.
Based on the above settings of the historical click data and the historical collection data, the method for determining the long-term label corresponding to the target account may refer to fig. 3, which corresponds to the following:
301. and acquiring a long-term click label corresponding to the historical click data in the fourth preset period of the target account and a long-term collection label corresponding to the historical collection data in the fourth preset period of the target account.
In implementation, one or more labels corresponding to a plurality of pieces of historical click display information included in the historical click data in the fourth preset period of time can be obtained, and then the labels are subjected to de-duplication processing, so that long-term click labels are obtained. Similarly, one or more labels corresponding to the plurality of pieces of history collection display information included in the history collection data in the fourth preset period of time may be obtained, and then the labels may be subjected to deduplication processing, so as to obtain long-term collection labels.
302. And performing de-duplication treatment on the long-term click label and the long-term collection label to obtain a reference long-term label corresponding to the target account.
303. And respectively determining the correlation degree between each reference long-term label and the target account based on the historical behavior data in the fourth preset period corresponding to each reference long-term label.
In implementation, there may be various methods for calculating the correlation between the reference long-Term tag and the target account, and the embodiments of the present application calculate by TF-IDF (Term Frequency-inverse document Frequency) method:
And acquiring one or more historical click display information corresponding to the reference long-term label and a click time point corresponding to the historical click display information from the historical behavior data in a fourth preset period. Then, a corresponding score may be assigned based on a distance between a click time point corresponding to each of the history click presentation information and an end time point of the fourth preset period, the score corresponding to the click time point being higher the closer to the end time point of the fourth preset period. Specifically, the score corresponding to each click time point is:
Wherein D 1 is a duration of the click time point from the start time point of the fourth preset period, and D 2 is a total duration of the fourth preset period.
By the above method, the score corresponding to the click time point of the one or more historical click display information corresponding to each reference long-term label can be determined, and the TF Clicking corresponding to the reference long-term label is the sum of the scores corresponding to the one or more click time points corresponding to the reference long-term label.
Then, an IDF Clicking corresponding to each reference long-term label may be calculated, where the corresponding calculation formula is:
Wherein ω 1 is the total number of users of the application program, and ω 2 is the number of users including the history click presentation information corresponding to the long-term click tag in the history click data within the fourth preset period.
After the TF Clicking and the IDF Clicking corresponding to each reference long-term label are calculated in the above manner, the TF Clicking and the IDF Clicking may be multiplied, so as to obtain the click correlation degree between each reference long-term label and the target account. Or the TF Clicking and the IDF Clicking corresponding to the reference long-term label can be multiplied and then the multiplied reference long-term label can be used for the reference long-term labelMultiplied by, or can be withTo a first preset power of (a) to obtain a click correlation between the reference long-term label and the target account.
Similarly, the TFIDF method described above may also be used to calculate the collection correlation between each reference long-term label and the target account.
And acquiring one or more historical collection display information corresponding to the reference long-term label and collection time points corresponding to the historical collection display information from the historical behavior data in a fourth preset period. Then, the corresponding score may be assigned based on the distance between the collection time point corresponding to each of the historical collection presentation information and the end time point of the fourth preset period, the score corresponding to the collection time point closer to the end time point of the fourth preset period being higher. Specifically, the score corresponding to each collection time point is:
wherein D 3 is a duration of the collection time point from the start time point of the fourth preset period, and D 4 is a total duration of the fourth preset period.
By the method, the scores corresponding to the collection time points of one or more pieces of historical collection display information corresponding to each reference long-term label can be determined, and the TF Collecting and storing corresponding to the reference long-term label is the sum of the scores corresponding to the one or more collection time points corresponding to the reference long-term label.
Then, an IDF Collecting and storing corresponding to each reference long-term label may be calculated, where the corresponding calculation formula is:
Wherein ω 3 is the total number of users of the application program, ω 4 is the number of users including the history collection presentation information corresponding to the reference long-term tag in the history collection data within the fourth preset period.
After the TF Collecting and storing and the IDF Collecting and storing corresponding to each reference long-term label are calculated in the above manner, the TF Collecting and storing and the IDF Collecting and storing may be multiplied, so as to obtain a collection correlation between each reference long-term label and the target account. Or the TF Collecting and storing and the IDF Collecting and storing corresponding to the reference long-term label can be multiplied and then the multiplied reference long-term label can be used for the reference long-term labelMultiplied by, or can be withTo a second preset power of (a) to obtain a collection correlation between the reference long-term tag and the target account.
Then, for each reference long-term label, the click relevance and the collection relevance corresponding to the reference long-term label can be added, so that the relevance between the reference long-term label and the target account is obtained. Or weights can be respectively allocated to the click relevance and the collection relevance according to the emphasis point, and the value obtained by multiplying the corresponding weights and adding the multiplied weights is determined as the relevance between the reference long-term label and the target account.
304. And selecting a third preset number of reference long-term labels according to the sequence of the correlation from high to low to obtain the long-term labels corresponding to the target account.
In implementation, the plurality of reference long-term labels are arranged according to the sequence of the corresponding relevance from high to low, and the first third preset number of reference long-term labels are determined to be the long-term labels corresponding to the target account.
The third preset number may be any reasonable number, which is not limited in the embodiment of the present application.
Optionally, in addition to obtaining the short-term label and the long-term label corresponding to the target account, a label similar to the long-term label may be obtained, and the corresponding processing is as follows:
For each long-term tag, the similarity between each tag and the long-term tag is calculated separately. And determining the expansion label corresponding to each long-term label based on the similarity between each label and the long-term label.
In practice, for each long-term tag, a process of calculating the similarity between the long-term tag and each tag may be performed separately. Then, each label can be arranged according to the sequence of the similarity from large to small, and then the fifth preset number of labels are determined to be the expansion labels corresponding to the long-term labels, or the labels with the similarity larger than the preset similarity threshold value can be determined to be the expansion labels corresponding to the long-term labels.
The method for determining the similarity between the long-term label and each label can be that the characteristic extraction model is used for carrying out characteristic extraction on each label so as to obtain a characteristic vector corresponding to each label, and the similarity is calculated through the characteristic vector corresponding to the long-term label and the characteristic vector corresponding to each other label.
The feature extraction model may be a word2vec (word to vector) model, for example, a CBOW (Continuous Bag Of Words model) model, which is not limited in the embodiment Of the present application.
After the short-term label, the long-term label and the expansion label corresponding to the target account are determined, the reference label corresponding to the target account can be determined based on the three types of labels. In implementation, the short-term label, the long-term label and the expansion label corresponding to the target account can be subjected to duplication removal processing, so that the reference label corresponding to the target account is obtained.
Any combination of the above optional solutions may be adopted to form an optional embodiment of the present application, which is not described herein.
According to the scheme, the plurality of labels can be screened based on the statistical data corresponding to the plurality of labels respectively, so that a plurality of recommendable labels with good quality and recommendability are obtained, then, based on the historical behavior data of the target account, a plurality of reference labels which are interested by a user and correspond to the target account are determined, then, the intersection between the plurality of recommendable labels and the plurality of reference labels is determined to be the target recommendation label corresponding to the target account, finally, the target display information corresponding to each target recommendation label is obtained, and the target display information is sent to a target terminal to which the target account belongs. By adopting the method and the device, the target recommendation label which has the quality and the recommendability and is interested by the user can be determined, so that the recommendation effect is improved.
An embodiment of the present application provides an apparatus for sending presentation information, where the apparatus may be a computer device in the foregoing embodiment, as shown in fig. 4, and the apparatus includes:
A screening module 410, configured to screen the plurality of tags based on statistical data corresponding to the plurality of tags, to obtain a plurality of recommended tags, where the tags are information for indicating content characteristics of the display information;
a first determining module 420, configured to determine a plurality of reference tags corresponding to a target account based on historical behavior data of the target account;
A second determining module 430, configured to determine an intersection between the plurality of recommendable labels and the plurality of reference labels as a target recommendation label corresponding to the target account;
and the sending module 440 is configured to obtain target display information corresponding to each target recommendation tag, and send the target display information to a target terminal to which the target account belongs.
In one possible implementation manner, the apparatus further includes a tag determination module configured to:
and for each piece of display information, determining a label corresponding to the display information based on the display information and a keyword extraction model.
In one possible implementation, the screening module 410 is configured to:
determining the user interest intensity corresponding to each label based on the statistical data corresponding to each label;
And screening the plurality of labels based on the user interest intensity corresponding to each label and a preset intensity threshold value to obtain a plurality of recommended labels.
In one possible implementation, the statistics include click statistics and collection statistics.
In a possible implementation manner, the click statistics data includes a first click rate corresponding to all users in a first preset period and a second click rate corresponding to a historical click user in the first preset period, where the historical click user is a user who performs a click operation on any display information corresponding to the tag in a second preset period before the first preset period and performs an exposure operation on the display information corresponding to the tag in the first preset period;
The collection statistics data comprise first collection rates corresponding to all users in the first preset period and second collection rates corresponding to historical collection users in the first preset period, wherein the historical collection users are users who perform collection operation on any display information corresponding to the tag in the second preset period and perform overexposure operation on the display information corresponding to the tag in the first preset period;
The screening module 410 is configured to:
For each tag, determining the click interest intensity of the user corresponding to the tag based on the first click rate and the second click rate corresponding to the tag;
Determining the user collection interest intensity corresponding to the label based on the first collection rate and the second collection rate corresponding to the label;
And determining the user interest intensity corresponding to the tag based on the user click interest intensity and the user collection interest intensity corresponding to the tag.
In one possible implementation manner, the first determining module 420 is configured to:
Determining a short-term label corresponding to the target account based on historical behavior data in a third preset time period of the target account, wherein the third preset time period is a time period in which a plurality of pieces of user behavior information exist recently, and the time difference between every two pieces of adjacent user behavior information is smaller than a preset time length;
determining a long-term label corresponding to the target account based on historical behavior data in a fourth preset period of the target account;
and determining a reference label corresponding to the target account based on the short-term label corresponding to the target account and the long-term label corresponding to the target account.
In one possible implementation, the historical behavior data includes historical click data and historical collection data, the historical click data includes one or more historical click display information and click time points corresponding to each historical click display information, and the historical collection data includes one or more historical collection display information and collection time points corresponding to each historical collection display information.
In one possible implementation manner, the first determining module 420 is configured to:
acquiring a short-term click tag corresponding to the historical click data in a third preset period of the target account and a short-term collection tag corresponding to the historical collection data in the third preset period of the target account;
Respectively determining the latest click time point corresponding to each short-term click label in the click time points corresponding to one or more pieces of historical click display information corresponding to each short-term click label;
Selecting a first preset number of short-term click labels according to the sequence from near to far of the latest click time points, and obtaining target short-term click labels corresponding to the target account;
respectively determining the latest collection time point corresponding to each short-term collection label in the collection time points corresponding to one or more pieces of historical collection display information corresponding to each short-term collection label;
Selecting a second preset number of short-term collection labels according to the sequence from near to far of the latest collection time point to obtain target short-term collection labels corresponding to the target account;
And performing de-duplication treatment on the target short-term click label and the target short-term collection label to obtain a short-term label corresponding to the target account.
In one possible implementation manner, the first determining module 420 is configured to:
Acquiring a long-term click tag corresponding to the historical click data in a fourth preset period of the target account and a long-term collection tag corresponding to the historical collection data in the fourth preset period of the target account;
performing de-duplication treatment on the long-term click label and the long-term collection label to obtain a reference long-term label corresponding to the target account;
Determining the correlation degree between each reference long-term label and the target account respectively based on historical behavior data in a fourth preset period corresponding to each reference long-term label;
And selecting a third preset number of reference long-term labels according to the sequence of the correlation from high to low to obtain the long-term labels corresponding to the target account.
In one possible implementation manner, after the determining the long-term label corresponding to the target account, the first determining module 420 is further configured to:
Acquiring a feature vector corresponding to each tag;
for each long-term label, calculating the similarity between each label and the long-term label;
determining expansion labels corresponding to each long-term label based on the similarity between each label and the long-term label;
The determining the reference label corresponding to the target account based on the short-term label corresponding to the target account and the long-term label corresponding to the target account includes:
And determining a reference label corresponding to the target account based on the short-term label corresponding to the target account, the long-term label corresponding to the target account and the expansion label corresponding to each long-term label.
In one possible implementation, the sending module 440 is configured to:
For each target recommendation label, determining a score of each piece of display information corresponding to the target recommendation label based on the statistical data of each piece of display information corresponding to the target recommendation label;
and selecting a fourth preset number of display information according to the order of the scores from high to low to obtain target display information corresponding to the target recommendation label.
It should be noted that, when the device for sending display information provided in the above embodiment sends display information, only the division of the above functional modules is used for illustration, in practical application, the above functional allocation may be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device for sending the display information provided in the above embodiment belongs to the same concept as the method embodiment for sending the display information, and the specific implementation process is detailed in the method embodiment, which is not repeated here.
Fig. 5 is a schematic structural diagram of a server according to an embodiment of the present application, where the server 500 may have a relatively large difference due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) 501 and one or more memories 502, where at least one instruction is stored in the memories 502, and the at least one instruction is loaded and executed by the processors 501 to implement the methods provided in the foregoing method embodiments. Of course, the server may also have a wired or wireless network interface, a keyboard, an input/output interface, and other components for implementing the functions of the device, which are not described herein.
In an exemplary embodiment, a computer readable storage medium, such as a memory including instructions executable by a processor in a terminal to perform the method of transmitting presentation information in the above embodiment is also provided. The computer readable storage medium may be non-transitory. For example, the computer readable storage medium may be ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program for instructing relevant hardware, where the program may be stored in a computer readable storage medium, and the storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
It should be noted that, the information (including but not limited to user equipment information, user personal information, etc.), data (including but not limited to data for analysis, stored data, presented data, etc.), and signals (including but not limited to signals transmitted between the user terminal and other devices, etc.) related to the present application are all authorized by the user or are fully authorized by the parties, and the collection, use, and processing of the related data is required to comply with the relevant laws and regulations and standards of the relevant country and region. For example, the "statistics" referred to in this application are all obtained with sufficient authorization.
The foregoing description of the preferred embodiments of the present application is not intended to limit the application, but rather, the application is to be construed as limited to the appended claims.

Claims (7)

1. A method of transmitting presentation information, the method comprising:
screening the plurality of labels based on the statistical data corresponding to the plurality of labels respectively to obtain a plurality of recommended labels, wherein the labels are information for indicating the content characteristics of the display information;
determining a plurality of reference labels corresponding to a target account based on historical behavior data of the target account;
Determining an intersection set between the plurality of recommendable labels and the plurality of reference labels as a target recommendation label corresponding to the target account;
The method comprises the steps of obtaining target display information corresponding to each target recommendation label, sending the target display information to a target terminal to which the target account belongs, screening the labels based on statistical data corresponding to the labels respectively to obtain a plurality of recommendable labels, and comprising the following steps:
determining the user interest intensity corresponding to each label based on the statistical data corresponding to each label;
Screening the labels based on the user interest intensity corresponding to each label and a preset intensity threshold value to obtain a plurality of recommended labels, wherein the statistical data comprise click statistical data and collection statistical data;
The click statistics data comprise first click rates corresponding to all users in a first preset period and second click rates corresponding to historical click users in the first preset period, wherein the historical click users are users who perform click operation on any display information corresponding to the tag in a second preset period before the first preset period and perform overexposure operation on the display information corresponding to the tag in the first preset period;
The collection statistics data comprise first collection rates corresponding to all users in the first preset period and second collection rates corresponding to historical collection users in the first preset period, wherein the historical collection users are users who perform collection operation on any display information corresponding to the tag in the second preset period and perform overexposure operation on the display information corresponding to the tag in the first preset period;
Determining the user interest intensity corresponding to each tag based on the statistical data corresponding to the plurality of tags respectively, wherein the determining the user interest intensity corresponding to each tag comprises determining the user interest intensity corresponding to the tag based on a first click rate and a second click rate corresponding to the tag for each tag;
And determining the user interest intensity corresponding to the label based on the user click interest intensity and the user collection interest intensity corresponding to the label.
2. The method of claim 1, wherein the determining a plurality of reference tags corresponding to the target account based on historical behavioral data of the target account comprises:
Determining a short-term label corresponding to the target account based on historical behavior data in a third preset time period of the target account, wherein the third preset time period is a time period in which a plurality of pieces of user behavior information exist recently, and the time difference between every two pieces of adjacent user behavior information is smaller than a preset time length;
and determining a reference label corresponding to the target account based on the short-term label corresponding to the target account and the long-term label corresponding to the target account.
3. The method of claim 2, wherein the historical behavior data comprises historical click data and historical collection data, the historical click data comprising one or more historical click presentation information and click time points corresponding to each historical click presentation information, the historical collection data comprising one or more historical collection presentation information and collection time points corresponding to each historical collection presentation information.
4. An apparatus for transmitting presentation information, the apparatus comprising:
The screening module is configured to screen the plurality of tags based on statistical data corresponding to the plurality of tags, to obtain a plurality of recommended tags, and includes:
determining the user interest intensity corresponding to each label based on the statistical data corresponding to each label;
Screening the plurality of labels based on the user interest intensity corresponding to each label and a preset intensity threshold value to obtain a plurality of recommended labels, wherein the statistics data comprise click statistics data and collection statistics data, the labels are information for indicating the content characteristics of display information, the click statistics data comprise first click rates corresponding to all users in a first preset period and second click rates corresponding to historical click users in the first preset period, the historical click users are users who perform click operation on any display information corresponding to the labels in a second preset period before the first preset period and perform overexposure operation on the display information corresponding to the labels in the first preset period, and the collection statistics data comprise first collection rates corresponding to all users in the first preset period and second collection rates corresponding to historical collection users in the first preset period, wherein the historical users are users who perform overexposure operation on any display information corresponding to the labels in the second preset period and perform overexposure operation on the display information corresponding to the labels in the first preset period;
Determining the user interest intensity corresponding to each tag based on the statistical data corresponding to the plurality of tags respectively, wherein the determining the user interest intensity corresponding to each tag comprises determining the user interest intensity corresponding to the tag based on a first click rate and a second click rate corresponding to the tag for each tag;
Determining the user collection interest intensity corresponding to the label based on the first collection rate and the second collection rate corresponding to the label; determining the user interest intensity corresponding to the tag based on the user click interest intensity and the user collection interest intensity corresponding to the tag;
The first determining module is used for determining a plurality of reference labels corresponding to the target account based on historical behavior data of the target account;
The second determining module is used for determining the intersection set between the plurality of recommendable labels and the plurality of reference labels as a target recommendation label corresponding to the target account;
the sending module is used for obtaining the target display information corresponding to each target recommendation label and sending the target display information to the target terminal to which the target account belongs.
5. A computer device comprising a processor and a memory having stored therein at least one instruction that is loaded and executed by the processor to implement the operations performed by the method of transmitting presentation information as claimed in any one of claims 1 to 3.
6. A computer-readable storage medium having stored therein at least one instruction that is loaded and executed by a processor to implement the operations performed by the method of transmitting presentation information of any one of claims 1 to 3.
7. A computer program product comprising at least one instruction for loading and executing by a processor to perform the operations performed by the method for sending presentation information according to any one of claims 1 to 3.
CN202210572451.7A 2022-05-24 2022-05-24 Method, device, equipment, storage medium and program product for sending display information Active CN114861061B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210572451.7A CN114861061B (en) 2022-05-24 2022-05-24 Method, device, equipment, storage medium and program product for sending display information

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210572451.7A CN114861061B (en) 2022-05-24 2022-05-24 Method, device, equipment, storage medium and program product for sending display information

Publications (2)

Publication Number Publication Date
CN114861061A CN114861061A (en) 2022-08-05
CN114861061B true CN114861061B (en) 2025-08-29

Family

ID=82639034

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210572451.7A Active CN114861061B (en) 2022-05-24 2022-05-24 Method, device, equipment, storage medium and program product for sending display information

Country Status (1)

Country Link
CN (1) CN114861061B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109446412A (en) * 2018-09-25 2019-03-08 中国平安人寿保险股份有限公司 Product data method for pushing, device, equipment and medium based on web page tag
CN113032668A (en) * 2021-03-03 2021-06-25 深圳市七号网络科技有限公司 Product recommendation method, device and equipment based on user portrait and storage medium

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8708841B2 (en) * 2007-02-07 2014-04-29 Skyhawke Technologies, Llc Systems and methods for golf performance analytics
CN104615655B (en) * 2014-12-31 2019-04-23 小米科技有限责任公司 Information recommendation method and device
CN108776907B (en) * 2018-05-31 2023-07-25 康键信息技术（深圳）有限公司 Intelligent advertisement recommendation method, server and storage medium
CN114282054A (en) * 2020-09-28 2022-04-05 苏宁云计算有限公司 Video recommendation method and device, computer equipment and storage medium
CN113868528A (en) * 2021-09-29 2021-12-31 平安银行股份有限公司 Information recommendation method, device, electronic device and readable storage medium

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109446412A (en) * 2018-09-25 2019-03-08 中国平安人寿保险股份有限公司 Product data method for pushing, device, equipment and medium based on web page tag
CN113032668A (en) * 2021-03-03 2021-06-25 深圳市七号网络科技有限公司 Product recommendation method, device and equipment based on user portrait and storage medium

Also Published As

Publication number Publication date
CN114861061A (en) 2022-08-05

Similar Documents

Publication Publication Date Title
TWI743428B (en) Method and device for determining target user group
CN106528813B (en) A kind of multimedia recommendation method and device
CN104991899B (en) The recognition methods of user property and device
CN103116582B (en) A kind of information retrieval method and related system and device
CN108833458A (en) A kind of application recommended method, device, medium and equipment
CN110334356A (en) Article matter method for determination of amount, article screening technique and corresponding device
CN104636407B (en) Parameter value training and searching request treating method and apparatus
CN115017200B (en) Search result sorting method, device, electronic device and storage medium
CN113365095B (en) Live resource recommendation method, device, electronic device, and storage medium
CN115470401A (en) Resource recommendation method and device, electronic equipment and storage medium
CN113407816A (en) Object recommendation method and device, electronic equipment and storage medium
CN109543940B (en) Activity evaluation method, activity evaluation device, electronic equipment and storage medium
CN114201696A (en) A message push method and device, storage medium, and computer equipment
CN101464883A (en) Contents-retrieving apparatus and method
CN114861061B (en) Method, device, equipment, storage medium and program product for sending display information
CN113869926A (en) Advertisement identification method, device, electronic device and storage medium
CN113742571B (en) Message pushing method and device based on big data and storage medium
CN114691837B (en) Insurance business data processing method and processing system based on big data
CN117009660A (en) Method, device, equipment and medium for determining recommended game
CN115408606A (en) Insurance information pushing method and device, storage medium and computer equipment
CN116910304A (en) Method, device, electronic equipment and storage medium for replacing video recommendation reason
CN116932857A (en) User portrait construction method, system, medium and equipment based on search engine
CN115757546A (en) Data searching method and device
CN114861107A (en) Landing page display method and device and electronic equipment
CN114048390A (en) Content recommendation method and device, electronic equipment 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
GR01 Patent grant