CN112561565A - User demand identification method based on behavior log - Google Patents
User demand identification method based on behavior log Download PDFInfo
- Publication number
- CN112561565A CN112561565A CN202011363261.1A CN202011363261A CN112561565A CN 112561565 A CN112561565 A CN 112561565A CN 202011363261 A CN202011363261 A CN 202011363261A CN 112561565 A CN112561565 A CN 112561565A
- Authority
- CN
- China
- Prior art keywords
- user
- behavior log
- behavior
- data
- page
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a user demand identification method based on a behavior log, belongs to the field of Internet technology application, and solves the problems that actual demand clients and popularization clients are not matched due to lack of user financial business transaction demand data in a database, and harassment is caused to the clients. Collecting a user behavior log in a low-frequency scene; dividing users into registered users and guest users; recording and uploading the equipment address information of the tourist user to a server; generating user Identification (ID) from the equipment address information of the tourist user; matching the demand data of the tourist user with the user identification ID; preprocessing a user behavior log in a server; the processor counts and analyzes the behavior characteristics of the user in a period; establishing a user demand identification model; target customer demand data is generated. The invention aims to obtain more reliable user financial business transaction requirement data and provide more appropriate service for customers. The invention is suitable for bank financial business transaction.
Description
Technical Field
The invention belongs to the field of Internet technology application, and particularly relates to a user demand identification method based on a behavior log.
Background
The user image is specifically depicted in a label form, so that personalized service can be provided for the characteristics of the user and value is generated, the method is widely applied in many scenes, typical commodity recommendation in e-commerce scenes is carried out, and the business value transformation is effectively promoted by utilizing the user portrait for marketing of thousands of people. However, most portrait labels describe static characteristics of users, descriptions of user behavior characteristics are related to specific application scenarios, and consumption-related behaviors of the users in the consumption scenarios are more frequent, so that purchasing habits, commodity preferences, service preferences and the like of the users are more easily captured, and further consumption requirements of the users are mined and conversion is guided.
Under the financial business transaction scene, because the demand of a user on funds is lower than the commodity purchasing behavior, the current fund demand of the user is difficult to be accurately grasped simply according to the past record information of the borrowing and repaying behavior of the user, but only the records of historical borrowing and lending, returning and the like of the user are stored in a database, the conversion effect cannot reach expectation, and the marketing of financial business transaction products is usually recommended to a target user group through ways of calling out, sending short messages and the like, and the direct marketing is also a disturbance to the user under the condition that the user demand is not known.
Disclosure of Invention
The method aims to solve the problems that under the low-frequency scene of the existing financial business transaction scene, data of user financial business transaction demands in a database are lacked, actual demand customers and popularization customers are not matched, and harassment is caused to customers. The invention provides a user demand identification method based on a behavior log, which aims to realize the following steps: more reliable user financial business transaction requirement data is obtained, and more appropriate service is provided for the client.
The technical scheme adopted by the invention is as follows:
a user demand identification method based on a behavior log is characterized by comprising the following steps:
collecting a user behavior log in a low-frequency scene;
dividing users into registered users and guest users;
recording and uploading the equipment address information of the tourist user to a server;
generating a user Identification (ID) from the equipment address information of the tourist user;
matching the demand data of the tourist user with the user identification ID;
preprocessing the user behavior log in a server;
the processor counts and analyzes the behavior characteristics of the user in a period;
establishing a user demand identification model;
target customer demand data is generated.
Under the low-frequency scene of the financial business transaction scene, because the using client quantity of the WeChat public number of the financial business transaction product is less, when the general client does not have the financial business transaction requirement, the WeChat public number of the financial business transaction product can not be easily used for searching and obtaining the related information, and when the user generally has the financial business transaction requirement, the WeChat public number of the financial business transaction product can be used for searching and obtaining the information related to the financial business transaction.
As many newly-used users log in on the WeChat public number, the users are classified as tourist users, and as the tourist users, part of the users use the device address information collected in the log data to complement the user information, but the users cannot complement the user information, as the users are users with potential financial business transaction requirements on the platform, the terminal device for access can be regarded as a virtual user, in the process that the tourist users register to use the WeChat public number to search the related information of financial business transaction products, the device address information of the tourist users is generated into user identification IDs which are easy to distinguish, the demand data of the tourist users using the WeChat public number is matched with the user identification IDs, when the users register, the demand data recorded on the user identification IDs are matched with accounts of the tourist users after registering, in order to provide better service to the user.
And acquiring a user behavior log under a period, and conjointly with the historical label information of the user, and conjecturing the financial service transaction requirement of the current user through a financial service transaction requirement identification model of the user. Under a low-frequency scene, the behavior characteristics of the user in a period can better feed back the financial business transaction requirements of the current user, and the method is favorable for providing more appropriate service meeting the financial business transaction requirements for the client.
Further, the collecting the user behavior log in the low-frequency scene includes:
embedding points on a user access page or an access module;
the data acquisition equipment acquires the user behavior log in a WeChat public number;
and reporting the user behavior log to a server.
The method comprises the steps of obtaining behavior log data of a user, collecting user logs reported by a WeChat public number in real time through a data collection device, and burying points of all pages and behavior events of a financial business transaction business process in advance, wherein the pages and the behavior events comprise pages such as registration, login, real-name authentication, application of credit, credit result, borrowing, repayment, card coupon discount and the like, the behavior events comprise access browsing of the user to the pages, clicking of modules on the pages and the like, and the data are stored in a distributed file system to facilitate subsequent processing of the data due to the fact that the data volume of the behavior logs of the user is large generally.
To know which pages a user accesses, the url is generally determined, and the url usually has many parameter information, so that the url is regularly matched according to the buried point event table to identify the access behavior of the user, for example, the name of a specific page or module is accessed after a certain url is accessed.
Further, the preprocessing the user behavior log in the server specifically includes:
and filtering irrelevant data and dirty data in the user behavior log.
The collected user behavior log data usually contains a large amount of irrelevant data and dirty data related to the financial transaction of the client, and the irrelevant data needs to be filtered first.
Further, the processor counts and analyzes the performance characteristics of the user in a period, and comprises:
counting behavior conditions of each embedded point of a user in a period;
and generating a user periodic behavior log label.
The access page or the module is coded in a point burying mode to realize user behavior tracking, namely, the access behavior of a specific service user can be identified through coding, data meeting the current financial service transaction requirements of the user can be conveniently and quickly acquired, the behavior condition of each buried point of the user in a period is counted, and a user periodic behavior log label is generated.
Further, the establishing of the user requirement identification model includes:
acquiring static image data to form a static image characteristic label;
writing the static portrait feature tag and the periodic behavior log tag into a mathematical model;
and training historical data of the mathematical model, and establishing a user demand recognition model.
And training historical data of the user by adopting some basic data models in combination with the static portrait characteristics and the periodic behavior log labels of the user to obtain parameters required to be used by the final model, wherein the basic models can be common regression algorithm models, random forest models and the like.
The model training mainly depends on feature labels generated by a user behavior log, and the recent access behavior of the user can reflect the current fund demand of the user to some extent. And identifying and judging the financial business transaction requirement willingness of the user by using the final model obtained by training, and taking the access behavior data and the static characteristic label of the user as the input of the model to obtain the financial business transaction requirement result of the user in a future period of time.
Further, the user periodic behavior log tag includes: the number of times of accessing the registration page or module, the number of times and the number of days of accessing the login page or module, the number of times and the number of days of accessing the credit page or module, the number of times and the number of days of accessing the debit page or module, the number of times and the number of days of accessing the repayment page or module, the dwell time of accessing the page, the number of days of accessing the page or module at the last time, the number of login days in the period and the number of login times in one day.
In summary, due to the adoption of the technical scheme, the invention has the beneficial effects that:
1. aiming at a low-frequency financial business transaction service scene, the collected user behavior logs are fully analyzed and mined, information capable of representing user behaviors is extracted from the user behavior logs, a model capable of identifying the financial business transaction requirement willingness of the user is obtained through training historical data by combining with static portrait data of the user, and users with different requirement levels are respectively marketed according to model results; in addition, the data of the user behavior log makes up the problem of insufficient user behavior characteristic information in a financial business transaction scene, meanwhile, a part of information of potential tourist users which are not registered is only browsed, user identification IDs are distributed to the part of the tourist users, and interest tags on the user identification IDs are directly matched when the part of the tourist users are registered, so that the problem that data required by financial business transactions in a database are lacked is effectively solved, and a platform user group is expanded to a certain extent.
2. In the invention, because a mathematical model is introduced, the financial business transaction requirement willingness degree of a user is identified, and the input characteristics mainly depend on the offline behavior log statistical performance of the user, the problem that the actual requirement client is not matched with the promotion client is effectively solved, the current financial business transaction requirement of the user is favorably controlled, the marketing conversion rate of the user is further improved, in addition, the disturbance of the marketing link to the user can be reduced, and the better service is provided for the user.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a flowchart of a method for identifying financial transaction requirements in a low-frequency scenario according to an embodiment of the present application;
FIG. 2 is a flow chart of a financial transaction process;
fig. 3 is a diagram of a user behavior log preprocessing result.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments, but not all embodiments, of the technical solutions of the present application. All other embodiments obtained by a person skilled in the art without any inventive step based on the embodiments described in the present application are within the scope of the protection of the present application.
Some concepts related to the embodiments of the present application are described below.
User behavior log: track information such as access, browsing, clicking and the like of each time the user accesses a website, an app, an applet and the like is recorded, and based on the record of each access of the user, data such as an IP address, equipment information, an account number, access time, residence time, a region, an access page and the like of a visitor can be generally obtained.
Embedding points: the embedded point is that certain information is collected in a specific process in the application, and is used for tracking the use condition of the application, and then is used for further optimizing products or providing data support of operation, wherein the data support comprises access times, visitor number, page dwell time, page browsing number, page jump rate and the like. Such information gathering can be broadly divided into page statistics and statistical operational behavior.
url: a Uniform Resource Locator (url), a network address, used to locate a Resource on the network.
Static portrait characteristics: the characteristics refer to the gender and age of the user, and the like, and do not change in a short period. Such features are obtained by the material filled in by the user at registration. And feature correctness checking and outlier processing are required. The static features of the present invention mainly include: whether the user registers, whether the user gives credit, the range of credit line, whether the user gives credit but not borrowing, whether the user borrows money for many times, whether the user borrows money clearly, the number of days of the last borrowing money from the current day and the like.
The preferred embodiments of the present application will be described below with reference to the accompanying drawings of the specification, it should be understood that the preferred embodiments described herein are merely for illustrating and explaining the present application, and are not intended to limit the present application, and that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
Example (b):
fig. 1 is a flowchart illustrating a method for identifying financial transaction requirements in a low frequency scenario.
Fig. 2 is a flow chart of financial transaction.
In this embodiment, a user requirement identification method based on a behavior log includes the following steps:
s10: and collecting a user behavior log in a low-frequency scene.
In this embodiment, the general flow of financial transaction is as follows: registering and logging in, performing real-name authentication on a logged-in user, applying for credit through history information of the real-name authentication, and if the credit is successful, performing financial business transaction loan on the user and supervising and urging the user to repay in a specified time; if the credit granting fails, the user can not borrow, and the user can be in the credit application stage all the time, and the credit granting is successful until the credit of the user is qualified, so that the borrowing and lending service can not be developed.
In this embodiment, the user behavior log records the operation behavior of the user, the data of the user is reported at intervals, and after the data is reported to the server, the log data is stored to the distributed file system at regular time. Besides the basic content capable of identifying the user identity information and the operation time, the reported content also needs to contain other key information capable of representing the user operation behavior, so that the core service link flow of the financial service transaction and the key behavior nodes of the user need to be embedded in advance.
Under the low-frequency scene of the financial business transaction scene, because the using client quantity of the WeChat public number of the financial business transaction product is less, when the general client does not have the financial business transaction requirement, the WeChat public number of the financial business transaction product can not be easily used for searching and obtaining the related information, and when the user generally has the financial business transaction requirement, the WeChat public number of the financial business transaction product can be used for searching and obtaining the information related to the financial business transaction.
S20: the users are classified into registered users and guest users.
S30: and recording and uploading the equipment address information of the tourist user to a server.
S40: and generating the device address information of the tourist user into a user Identification (ID).
S50: and matching the requirement data of the tourist user with the user identification ID.
In this embodiment, for a registered user, a user number is used as a user identifier, and for an unregistered user, an identifier is generated for an access device according to a certain rule method in combination with some identifiers (for example, IMEI, IDFA, and the like) of related devices that can be acquired in step one, the device identifier is used as a potential user identifier, when such a user visits again, the user can be guided to perform registration conversion, and after registration, the historical user behavior of the device can be associated with a corresponding user identifier ID.
S60: and preprocessing the user behavior log in the server.
In this embodiment, information that can describe the behavior characteristics of the user is extracted from the log data. Log data usually contains various contents related to application programs, some are related to user behaviors, some are simply used for dotting performance monitoring logs, irrelevant data parts need to be filtered out first, and only parts needing to be analyzed are reserved. In addition, a small amount of dirty data in the reported log data influences subsequent data analysis and needs to be filtered. Depending on the embedded point event table, we can know which page a user specifically visits and which operations are performed on the page, for example, a b module of a page is clicked, the embedded point event table can be managed in a coding mode, that is, the access behavior of a specific service user can be identified through coding, in most cases, it is required to know which pages the user visits and which operations are performed, and generally, the judgment is also performed in a url matching mode, the mode is simpler and more direct, the embedded point event table can maintain information related to urls, and the access behavior of the user is identified by performing regular matching on the urls in log data according to the embedded point event table.
As shown in fig. 3, it is a user behavior log preprocessing result diagram, and data such as user id (user identifier), device id (device identifier), tile num (user phone number), log time (log time), page name (access page), page url (web address), orig page url (original web address), event (event) and the like are recorded therein, where view (visit) and click (click) are recorded.
S70: the processor counts and analyzes the performance characteristics of the user in the period.
In this embodiment, the user periodic behavior log tag includes: the number of times of accessing the registration page or module, the number of times and the number of days of accessing the login page or module, the number of times and the number of days of accessing the credit page or module, the number of times and the number of days of accessing the debit page or module, the number of times and the number of days of accessing the repayment page or module, the dwell time of accessing the page, the number of days of accessing the page or module at the last time, the number of login days in the period, the number of login times in one day, the track path left when the user accesses, and the like.
The log behaviors of the user are subjected to statistical analysis, the behavior conditions of each embedded point page or module of the user in a period are counted, the period is set according to specific conditions, 1/7/30 days are taken as a statistical period in the embodiment, specific statistical user behavior indexes comprise the number of times that the user accesses the pages and modules such as registration, login, credit granting, borrowing, repayment and the like in the last 1/7/30 days, the number of days that the pages and modules are accessed in the last 1/7/30 days, the total length of stay of the pages in the last 1/7/30-day access process, the number of days that the last access dates are away from the current days, the number of days that the same-day discontinuous time login appears in the last 1/7/30 days, the number of times of login in the last 1/7/30 days and the like, also included are trace path conditions left by the user when visiting, such as the number of jump steps from user login to the shortest/longest/average needed to reach the target page in the last 1/7/30 days. The non-continuous time login specifically means that a certain interval exists between the second login time and the last logout time in the same day of the user, for example, the user logs in the first login time in 13 pm: 00-13: exit after 30 hours of access, 14: 00-14: the login behavior is again assumed to be 2 times the user logs in the day 30, but once again if the user logs in and logs out again in a very short time, since this may be the result of the user's operating habits, the user does not really want to log out.
S80: and establishing a user demand identification model.
In the embodiment, the static portrait characteristics of the user and the log behavior in the period are combined, some basic data models are adopted to train the historical data of the user, and a model for identifying the financial business transaction requirement willingness of the user is obtained. In the embodiment, a random forest model is taken as an example, a training set is formed by using historical behavior data of a user and static portrait characteristics to generate a corresponding random forest model, the static portrait characteristics of the user include whether the user is a registered user, whether the user is credited, the credit line range is credited, whether the user is not credited, whether the user is debited, whether multiple debits are made, whether the debit is settled, the number of days since the last debit is present and the like, and the stage of the user in the whole financial business transaction flow is mainly represented.
S90: target customer demand data is generated.
In this embodiment, the model obtained by the training is used to identify and judge the recent financial transaction requirements of the user, the access behavior data and the static feature tag of the user are used as the input of the model to judge the financial transaction willingness of the user in a period of time in the future, such as the financial transaction willingness of 7 days in the future, the financial transaction willingness of 30 days in the future, and the like, and the result is output to the marketing platform, so that a coupon is issued to the user in a key operation mode for the user with strong financial transaction willingness and tendency, and the like, so as to achieve a better marketing conversion effect and promote the financial transaction of the user. The statistics of the user access behaviors mainly depends on processing log data acquired in the T +1 day, so that the evaluation result of the financial business transaction requirement willingness of the user can be dynamically adjusted every day, and the current fund requirement of the user can be timely sensed.
While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (6)
1. A user demand identification method based on a behavior log is characterized by comprising the following steps:
collecting a user behavior log in a low-frequency scene;
dividing users into registered users and guest users;
recording and uploading the equipment address information of the tourist user to a server;
generating a user Identification (ID) from the equipment address information of the tourist user;
matching the demand data of the tourist user with the user identification ID;
preprocessing the user behavior log in a server;
the processor counts and analyzes the behavior characteristics of the user in a period;
establishing a user demand identification model;
target customer demand data is generated.
2. The method for identifying user requirements based on the behavior log according to claim 1, wherein the collecting the user behavior log in the low-frequency scene comprises:
embedding points on a user access page or an access module;
the data acquisition equipment acquires the user behavior log in a WeChat public number;
and reporting the user behavior log to a server.
3. The method for identifying user demand based on behavior log according to claim 1, wherein the preprocessing the user behavior log in the server specifically comprises:
and filtering irrelevant data and dirty data in the user behavior log.
4. The method for identifying user requirements based on the behavior log as claimed in claim 1, wherein the processor counts and analyzes the behavior characteristics of the user in a period, comprising:
counting behavior conditions of each embedded point of a user in a period;
and generating a user periodic behavior log label.
5. The method for identifying user requirements based on the behavior log according to claim 4, wherein the establishing of the user requirement identification model comprises:
acquiring static image data to form a static image characteristic label;
writing the static portrait feature tag and the periodic behavior log tag into a mathematical model;
and training historical data of the mathematical model, and establishing a user demand recognition model.
6. The method for identifying user requirements based on the behavior log as claimed in claim 5, wherein the user periodic behavior log label is specifically: the number of times of accessing the registration page or module, the number of times and the number of days of accessing the login page or module, the number of times and the number of days of accessing the credit page or module, the number of times and the number of days of accessing the debit page or module, the number of times and the number of days of accessing the repayment page or module, the dwell time of accessing the page, the number of days of accessing the page or module at the last time, the number of login days in the period, the number of login times in one day and the track path left by the user during access.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011363261.1A CN112561565A (en) | 2020-11-27 | 2020-11-27 | User demand identification method based on behavior log |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011363261.1A CN112561565A (en) | 2020-11-27 | 2020-11-27 | User demand identification method based on behavior log |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112561565A true CN112561565A (en) | 2021-03-26 |
Family
ID=75046535
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011363261.1A Withdrawn CN112561565A (en) | 2020-11-27 | 2020-11-27 | User demand identification method based on behavior log |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112561565A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113468240A (en) * | 2021-06-25 | 2021-10-01 | 和元达信息科技有限公司 | Method for analyzing big data based on internet surfing behavior of mobile terminal |
| CN114817225A (en) * | 2022-05-25 | 2022-07-29 | 广西润嘉互联网科技有限公司 | User behavior data processing method and system based on big data e-commerce optimization |
| CN115017201A (en) * | 2022-08-09 | 2022-09-06 | 中企云链（北京）金融信息服务有限公司 | FLINK processing engine-based user behavior analysis method and system |
| CN116523572A (en) * | 2023-06-28 | 2023-08-01 | 悦享星光(北京)科技有限公司 | Client mining method and system based on client behavior characteristics |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111209170A (en) * | 2019-10-21 | 2020-05-29 | 江苏卓易信息科技股份有限公司 | Rule-based user behavior log acquisition and analysis method and system |
| CN111488261A (en) * | 2020-03-11 | 2020-08-04 | 北京健康之家科技有限公司 | User behavior analysis system, method, storage medium and computing device |
| CN111538910A (en) * | 2020-06-23 | 2020-08-14 | 上海摩莱信息科技有限公司 | Intelligent recommendation method and device and computer storage medium |
| CN111953763A (en) * | 2020-08-06 | 2020-11-17 | 腾讯科技（深圳）有限公司 | Business data pushing method and device and storage medium |
-
2020
- 2020-11-27 CN CN202011363261.1A patent/CN112561565A/en not_active Withdrawn
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111209170A (en) * | 2019-10-21 | 2020-05-29 | 江苏卓易信息科技股份有限公司 | Rule-based user behavior log acquisition and analysis method and system |
| CN111488261A (en) * | 2020-03-11 | 2020-08-04 | 北京健康之家科技有限公司 | User behavior analysis system, method, storage medium and computing device |
| CN111538910A (en) * | 2020-06-23 | 2020-08-14 | 上海摩莱信息科技有限公司 | Intelligent recommendation method and device and computer storage medium |
| CN111953763A (en) * | 2020-08-06 | 2020-11-17 | 腾讯科技（深圳）有限公司 | Business data pushing method and device and storage medium |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113468240A (en) * | 2021-06-25 | 2021-10-01 | 和元达信息科技有限公司 | Method for analyzing big data based on internet surfing behavior of mobile terminal |
| CN114817225A (en) * | 2022-05-25 | 2022-07-29 | 广西润嘉互联网科技有限公司 | User behavior data processing method and system based on big data e-commerce optimization |
| CN114817225B (en) * | 2022-05-25 | 2023-03-28 | 深圳市晟晟科技有限公司 | User behavior data processing method and system based on big data e-commerce optimization |
| CN115017201A (en) * | 2022-08-09 | 2022-09-06 | 中企云链（北京）金融信息服务有限公司 | FLINK processing engine-based user behavior analysis method and system |
| CN116523572A (en) * | 2023-06-28 | 2023-08-01 | 悦享星光(北京)科技有限公司 | Client mining method and system based on client behavior characteristics |
| CN116523572B (en) * | 2023-06-28 | 2023-09-08 | 悦享星光(北京)科技有限公司 | Client mining method and system based on client behavior characteristics |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US5918014A (en) | Automated collaborative filtering in world wide web advertising | |
| CN112561565A (en) | User demand identification method based on behavior log | |
| CN103473721B (en) | Methods and apparatus to determine media impressions using distributed demographic information | |
| WO2021025926A1 (en) | Digital content prioritization to accelerate hyper-targeting | |
| CN112035742A (en) | User portrait generation method, device, equipment and storage medium | |
| US7890511B2 (en) | System and method for conducting network analytics | |
| CN109741146A (en) | Products Show method, apparatus, equipment and storage medium based on user behavior | |
| US9256692B2 (en) | Clickstreams and website classification | |
| US20150006294A1 (en) | Targeting rules based on previous recommendations | |
| CN106504099A (en) | A kind of system for building user's portrait | |
| CN112330412B (en) | Product recommendation method and device, computer equipment and storage medium | |
| JP2003523578A (en) | System and method for determining the validity of an interaction on a network | |
| EP2577584A1 (en) | Method of identifying remote users of websites | |
| CN109284369A (en) | Determination method, system, device and the medium of security news information importance | |
| CN106779946A (en) | A kind of film recommends method and device | |
| CN111429214B (en) | Transaction data-based buyer and seller matching method and device | |
| CN111723083A (en) | User identity identification method and device, electronic equipment and storage medium | |
| JP2019185595A (en) | Information processor, method for processing information, information processing program, determination device, method for determination, and determination program | |
| CN117668361B (en) | Big data-based pushing method and system | |
| CN112347457A (en) | Abnormal account detection method and device, computer equipment and storage medium | |
| US20160307223A1 (en) | Method for determining a user profile in relation to certain web content | |
| CN114693409A (en) | Product matching method, device, computer equipment, storage medium and program product | |
| US11538116B2 (en) | Life event bank ledger | |
| CN111373395A (en) | Artificial intelligence system and method based on hierarchical clustering | |
| CN103034674A (en) | Information providing system, list builder and user management device |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210326 |