CN117194787A - Application pushing method based on user behavior analysis - Google Patents
Application pushing method based on user behavior analysis Download PDFInfo
- Publication number
- CN117194787A CN117194787A CN202311166254.6A CN202311166254A CN117194787A CN 117194787 A CN117194787 A CN 117194787A CN 202311166254 A CN202311166254 A CN 202311166254A CN 117194787 A CN117194787 A CN 117194787A
- Authority
- CN
- China
- Prior art keywords
- user
- user behavior
- application
- seat
- information
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 230000006399 behavior Effects 0.000 claims description 94
- 230000006870 function Effects 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000014759 maintenance of location Effects 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Abstract
The application discloses an application pushing method based on user behavior analysis, which relates to an information recommendation technology and comprises the steps of obtaining user behavior data, adding source information to the user behavior data, classifying the user behavior data according to user and seat information, updating the user behavior data into a corresponding user behavior historical database according to the category of the user behavior data, calculating keywords and weights of each category according to the user behavior historical database, obtaining a user-seat-keyword ranking library of each category according to the keywords and weights, and recommending an application list to a user according to the ranking library. According to the application, the user behavior data is divided through the user seat information, the keyword ranking libraries with different weights are calculated through the user history behavior database, and hot and favorite applications of the user are recommended to the user according to the keyword ranking libraries, so that the recommendation result can more accord with the requirements of the user.
Description
Technical Field
The application relates to the technical field of information recommendation, in particular to an application pushing method based on user behavior analysis.
Background
At present, when the Internet data is in the age of large explosion, a lot of information is received every day, but not every kind of information is interested, and the information overload causes various information dazzling presented to the user, so that the user is difficult to select. Based on this background, recommendation systems have been developed which address the problem of overload of information across industries. For the user, the recommendation system can find something more interesting, and can help the user to make decisions, and can also find fresh things; for merchants and service providers, the recommendation system can provide personalized services, so that the trust and viscosity are improved, and the recommendation system is beneficial to increasing the revenue. The recommendation system is also adapted for various industries such as e-commerce, movie video, music stations, social networks, reading, location-based takeaway/network booking, personalized mail, personalized advertising, application stores/warehouses, etc.
In the prior art, application stores/warehouses usually recommend the application by matching user portraits (such as information of age groups, gender, interest tags and the like) with the applied tags, and the defect of the mode is that the granularity of recommendation results is relatively coarse, on one hand, the judgment of the users of the same type can be classified according to the portraits attribute acquired by the Internet, such as age, gender and the like, and the information can be classified for the users but is not accurate enough; on the other hand, the preference of the user for the application (such as the frequency of using the application and the duration of using the user) cannot be well reflected in the weight of the recommendation, and important information such as content tags browsed by the user, search keywords used by the user and the like cannot be used in the application recommendation. In addition, in the existing products, the application list which is not installed in the current device but is installed in other devices by the current user and the seat cannot be actively displayed for the user to click and install as required.
Disclosure of Invention
Therefore, the application provides an application pushing method based on user behavior analysis, which aims to solve the problem that a recommendation system of an application store/warehouse is not accurate enough in the prior art.
In order to achieve the above object, the present application provides the following technical solutions:
in a first aspect, an application pushing method based on user behavior analysis includes:
step 1: acquiring user behavior data;
step 2: adding source information of the user behavior data;
step 3: classifying the user behavior data according to the user and seat information;
step 4: updating the user behavior data to a corresponding user behavior history database according to the category of the user behavior data;
step 5: calculating keywords and weights of all the categories according to the user behavior history database, and obtaining a user-seat-keyword ranking library of all the categories according to the keywords and weights;
step 6: and recommending an application list to the user according to the user-seat-keyword ranking library of each category.
Preferably, in the step 1, the user behavior data includes user login information, application opening and closing information, in-application function usage information, in-application content click information, and unified search behavior information.
Preferably, in the step 2, the source information is an IP address of the device node.
Preferably, in the step 5, the weight is calculated according to the historical click times and the residence time.
Preferably, in the step 5, the user-seat-keyword ranking library includes a user-seat-content keyword ranking library and a user-seat-application keyword ranking library.
Preferably, in the step 6, the recommending application list to the user includes guessing that you like the application recommending list, guessing that you like the content recommending list, the hottest application list in the same seat, the most interesting content list in the same seat, and other application lists installed on the device but not installed on the device.
In a second aspect, an application push system based on user behavior analysis includes:
the data acquisition module is used for acquiring user behavior data;
the data preprocessing module is used for adding source information of the user behavior data;
the data classification module is used for classifying the user behavior data according to the user and seat information;
the database updating module is used for updating the user behavior data into a corresponding user behavior history database according to the category of the user behavior data;
the keyword ranking library module is used for calculating keywords and weights of all categories according to the user behavior history database to obtain user-seat-keyword ranking libraries of all categories;
and the application recommendation module is used for recommending an application list to the user according to the user-seat-keyword ranking library of each category.
In a third aspect, a computer device comprises a memory storing a computer program and a processor implementing the steps of an application push method based on user behavior analysis when the computer program is executed.
In a fourth aspect, a computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of an application push method based on user behavior analysis.
Compared with the prior art, the application has at least the following beneficial effects:
the application provides an application pushing method based on user behavior analysis, which comprises the steps of obtaining user behavior data; adding source information of user behavior data; classifying the user behavior data according to the user and seat information; updating the user behavior data into a corresponding user behavior history database according to the category of the user behavior data; calculating keywords and weights of all the categories according to the user behavior history database, and obtaining a user-seat-keyword ranking library of all the categories according to the keywords and weights; and recommending an application list to the user according to the user-seat-keyword ranking library of each category. According to the application, the user behavior data is divided through the user seat information, and the preference of the user to the application is added into the recommended weight, so that the recommendation result can better meet the requirements of the user, and the recommended object is more accurate.
Drawings
In order to more intuitively illustrate the prior art and the application, several exemplary drawings are presented below. It should be understood that the specific shape and configuration shown in the drawings are not generally considered limiting conditions in carrying out the application; for example, those skilled in the art will be able to make routine adjustments or further optimizations for the addition/subtraction/attribution division, specific shapes, positional relationships, connection modes, dimensional proportion relationships, and the like of certain units (components) based on the technical concepts and the exemplary drawings disclosed in the present application.
Fig. 1 is a flowchart of an application pushing method based on user behavior analysis according to a first embodiment of the present application;
fig. 2 is a schematic structural diagram of an application pushing method based on user behavior analysis according to a first embodiment of the present application;
FIG. 3 is a flowchart of a first embodiment of the present application for obtaining user behavior data;
FIG. 4 is a flowchart of a recommendation keyword and weight analysis according to an embodiment of the present application;
fig. 5 is a flowchart of application and content recommendation provided in an embodiment of the present application.
Detailed Description
The application will be further described in detail by means of specific embodiments with reference to the accompanying drawings.
In the description of the present application: unless otherwise indicated, the meaning of "a plurality" is two or more. The terms "first," "second," "third," and the like in this disclosure are intended to distinguish between the referenced objects without a special meaning in terms of technical connotation (e.g., should not be construed as emphasis on the degree of importance or order, etc.). The expressions "comprising", "including", "having", etc. also mean "not limited to" (certain units, components, materials, steps, etc.).
The terms such as "upper", "lower", "left", "right", "middle", etc. are generally used herein for convenience of visual understanding with reference to the drawings and are not to be construed as absolute limitations on the positional relationship of the actual product. Such changes in the relative positional relationship without departing from the technical idea of the present application are also considered as the scope of the present application.
Example 1
The embodiment provides an application pushing method based on user behavior analysis, which divides user behavior data through seat information instead of common image attributes of the Internet, wherein the analyzed user behavior information comprises the times and duration of using application and application function channels by a user, the label and stay duration information of content browsed by the user and the keyword information of searching the application or the content by the user. In the process of analyzing and processing the user behavior information, the weight information is determined by combining with the user behavior history library, and finally a keyword ranking library is formed for application recommendation of the current user (hot application, guessing that you like to quote, application of which the device is not installed but other devices are installed).
Referring to fig. 1 and 2, the method includes:
s1: acquiring user behavior data;
referring to fig. 3, specifically, the user behavior data includes user login information, application opening and closing information, in-application function usage information, in-application content click information, and unified search behavior information.
Specific information of each user behavior data is as follows:
user login information: user name/seat name, login time;
application open and close information: application name, opening or closing action, tag list of application, time of occurrence;
application function usage information: application name, function name, tag list of functions, enter function or exit action, time of occurrence;
in-application content click information: application name, content tag, entering content or exiting action, time of occurrence;
unifying search behavior information: search type (application/content), search keyword, search time.
S2: adding source information of user behavior data;
specifically, the user behavior data acquired from each equipment terminal node is preprocessed. The preprocessing is mainly to add source information of user behavior data (i.e., IP address of device node).
S3: classifying the user behavior data according to the user and seat information;
s4: updating the user behavior data into a corresponding user behavior history database according to the category of the user behavior data;
s5: calculating keywords and weights of all the categories according to the user behavior history database, and obtaining a user-seat-keyword ranking library of all the categories according to the keywords and weights;
referring to fig. 4, the following descriptions are specifically provided with reference to S3 to S5.
When the classification is performed:
(1) If the user behavior is app (switch of application), calculating the stay time of the application, reading the label list of the application, and adding and updating to the user seat-application click history library.
If the user behavior is func (function use of application), calculating the stay time of the application function, reading the label list of the function, and adding and updating the label list to the user seat-application-function click history library.
Respectively inquiring the data of the two types of data in the history base according to the labels, and determining a click factor m and a duration factor t:
determining a clicking factor m according to the historical clicking times n, if the first clicking or the clicking times are less, determining that the clicking factor m adopts a low factor value, otherwise, adopting a high factor value;
and determining a duration factor t according to the stay duration time, wherein if the stay time is long, the t adopts a high factor value, otherwise, the t adopts a low factor value.
After m and t are determined, weight is calculated according to a calculation formula of weight=m+0.5+t+0.5, and an application keyword-weight list of the current user behavior is output.
(2) If the user behavior is content, recording the label of the content page, calculating the stay time in each content page, performing word segmentation statistics on the title and the content (the word segmentation result is low weight, the link configuration is optional), storing the content in a user seat-content click history library, and then combining the content click history library to output a content keyword-weight list of the user behavior.
(3) If the user behavior is search, a determination is made as to the search type:
1) When the search result is app (application), and if the application is installed later, recording keywords, and combining an application label into the app for processing;
2) When the search result is func (application function), and the subsequent click result directly enters a specific function of the app, recording keywords, and combining the function labels into a 'user behavior is func' for processing;
3) Updating the search keywords formed in the steps 1) and 2) into a user-seat-search keyword historic base, and forming an application keyword-weight list according to accumulated data in the historic base.
4) When the search result is content, and the content is clicked for browsing, keyword is recorded, and the content label is combined into the content for processing;
and (3) updating the search keywords formed in the whole link (3) into a user seat-search history library, and forming a content keyword-weight list according to accumulated data in the history library.
(4) And (3) combining the results output by the links (1) and (3) to form an application keyword-weight list, updating the application keyword-weight list to a user-seat-application keyword historic library to form a ranking, and obtaining the user-seat-application keyword ranking library.
(5) And (3) combining the results output by the step (2) and the step (3) to form a content keyword-weight list, updating the content keyword-weight list to a user-seat-content keyword historical library to form a ranking, and obtaining a user-seat-content keyword ranking library.
S6: and recommending an application list to the user according to the user-seat-keyword ranking library of each category.
Referring to fig. 5, specifically, after a user logs in, the system invokes a recommendation engine to make the following recommendations in combination with the current user-seat-device information, user-seat-application keyword ranking library, user-seat-content keyword ranking library, application-tag library, content-tag library, and other information:
(1) Guessing that you like the application recommendation list;
(2) Guessing that you like the content recommendation list;
(3) The hottest application list of the same seat;
(4) The content list with the most attention of the seat;
(5) List of applications installed on other devices but not installed on the device.
Compared with the prior art, the application pushing method based on the user behavior analysis aims at the determined user seat instead of the big data user portrait commonly used by the Internet, so that the recommended object is more accurate, and the preference of the user to the application is added into the recommended weight through the analysis of the frequency and the stay time of the user in the application and the functional channel and the keyword frequency of the search application, so that the weight in the recommendation strategy is more in line with the interest point of the user, and the recommendation result is more in line with the requirement of the user.
In addition, through actively displaying an application list which is not installed at the terminal but installed at other terminals at the current user seat, a user can conveniently install a required application by one key after changing equipment.
Example two
The embodiment provides an application pushing system based on user behavior analysis, which comprises:
the data acquisition module is used for acquiring user behavior data;
the data preprocessing module is used for adding source information of the user behavior data;
the data classification module is used for classifying the user behavior data according to the user and seat information;
the database updating module is used for updating the user behavior data into a corresponding user behavior history database according to the category of the user behavior data;
the keyword ranking library module is used for calculating keywords and weights of all categories according to the user behavior history database to obtain user-seat-keyword ranking libraries of all categories;
and the application recommendation module is used for recommending an application list to the user according to the user-seat-keyword ranking library of each category.
For specific limitations regarding the application push system based on user behavior analysis, reference may be made to the above limitation regarding the application push method based on user behavior analysis, and no further description is given here.
Example III
The embodiment provides a computer device, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of an application pushing method based on user behavior analysis when executing the computer program.
Example IV
The present embodiment provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of an application push method based on user behavior analysis.
Any combination of the technical features of the above embodiments may be performed (as long as there is no contradiction between the combination of the technical features), and for brevity of description, all of the possible combinations of the technical features of the above embodiments are not described; these examples, which are not explicitly written, should also be considered as being within the scope of the present description.
The application has been described above with particularity and detail in connection with general description and specific embodiments. It should be understood that numerous conventional modifications and further innovations may be made to these specific embodiments, based on the technical concepts of the present application; but these conventional modifications and further innovations may also fall within the scope of the claims of the present application as long as they do not depart from the technical spirit of the present application.
Claims (9)
1. An application pushing method based on user behavior analysis is characterized by comprising the following steps:
step 1: acquiring user behavior data;
step 2: adding source information of the user behavior data;
step 3: classifying the user behavior data according to the user and seat information;
step 4: updating the user behavior data to a corresponding user behavior history database according to the category of the user behavior data;
step 5: calculating keywords and weights of all the categories according to the user behavior history database, and obtaining a user-seat-keyword ranking library of all the categories according to the keywords and weights;
step 6: and recommending an application list to the user according to the user-seat-keyword ranking library of each category.
2. The application pushing method based on user behavior analysis according to claim 1, wherein in the step 1, the user behavior data includes user login information, application opening and closing information, in-application function usage information, in-application content click information, and unified search behavior information.
3. The method for pushing applications based on user behavior analysis according to claim 1, wherein in the step 2, the source information is an IP address of a device node.
4. The method according to claim 1, wherein in the step 5, the weight is calculated according to the number of historical clicks and the retention time.
5. The method for pushing applications based on user behavior analysis according to claim 1, wherein in the step 5, the user-seat-keyword ranking library includes a user-seat-content keyword ranking library and a user-seat-application keyword ranking library.
6. The method of claim 1, wherein in step 6, recommending an application list to the user includes guessing that you like the application recommendation list, guessing that you like the content recommendation list, the hottest application list on the same seat, the most interesting content list on the same seat, and other application lists installed on the device but not installed on the device.
7. An application push system based on user behavior analysis, comprising:
the data acquisition module is used for acquiring user behavior data;
the data preprocessing module is used for adding source information of the user behavior data;
the data classification module is used for classifying the user behavior data according to the user and seat information;
the database updating module is used for updating the user behavior data into a corresponding user behavior history database according to the category of the user behavior data;
the keyword ranking library module is used for calculating keywords and weights of all categories according to the user behavior history database to obtain user-seat-keyword ranking libraries of all categories;
and the application recommendation module is used for recommending an application list to the user according to the user-seat-keyword ranking library of each category.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311166254.6A CN117194787A (en) | 2023-09-11 | 2023-09-11 | Application pushing method based on user behavior analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311166254.6A CN117194787A (en) | 2023-09-11 | 2023-09-11 | Application pushing method based on user behavior analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117194787A true CN117194787A (en) | 2023-12-08 |
Family
ID=88984486
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311166254.6A Pending CN117194787A (en) | 2023-09-11 | 2023-09-11 | Application pushing method based on user behavior analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117194787A (en) |
-
2023
- 2023-09-11 CN CN202311166254.6A patent/CN117194787A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20180322201A1 (en) | Interest Keyword Identification | |
| US9760640B2 (en) | Relevancy-based domain classification | |
| US8380721B2 (en) | System and method for context-based knowledge search, tagging, collaboration, management, and advertisement | |
| TWI636416B (en) | Method and system for multi-phase ranking for content personalization | |
| US9270767B2 (en) | Method and system for discovery of user unknown interests based on supplemental content | |
| US8959091B2 (en) | Keyword assignment to a web page | |
| US20140278308A1 (en) | Method and system for measuring user engagement using click/skip in content stream | |
| US11127063B2 (en) | Product and content association | |
| US20080147635A1 (en) | System, apparatus and method for providing weight to information gathering engine according to situation of user and computer readable medium processing the method | |
| US20140280554A1 (en) | Method and system for dynamic discovery and adaptive crawling of content from the internet | |
| US20110246277A1 (en) | Multi-factor promotional offer suggestion | |
| US11048764B2 (en) | Managing under—and over-represented content topics in content pools | |
| US20160048575A1 (en) | System and method for topics extraction and filtering | |
| CN111310046A (en) | Object recommendation method and device | |
| Singh et al. | Classification and Comparison of Web Recommendation Systems used in Online Business | |
| Li et al. | Review of Recommender Systems and Their Applications | |
| CN117194787A (en) | Application pushing method based on user behavior analysis | |
| CN112182376B (en) | Recommendation engine method of internet advertisement platform capable of real-time and efficient analysis | |
| Arour et al. | Contextual Recommender Systems in Business from Models to Experiments | |
| Adde et al. | A Comprehensive Study on Recommender Systems For E-Commerce Applications | |
| Sivanaiah et al. | Content boosted hybrid filtering for solving pessimistic user problem in recommendation systems | |
| CN116502007A (en) | Big data-based policy configuration generation display method | |
| Lu | Click Behavior in Search Engine Marketing | |
| Konow et al. | A Visited Item Frequency Based Recommender System: Experimental Evaluation and Scenario Description. | |
| Harshika et al. | An Approach for Extracting and Predicting Instance–specific Attribute Values from E–commerce Sitesfor Used Products |
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 |