CN107451832B - Method and device for pushing information - Google Patents
Method and device for pushing information Download PDFInfo
- Publication number
- CN107451832B CN107451832B CN201610371042.5A CN201610371042A CN107451832B CN 107451832 B CN107451832 B CN 107451832B CN 201610371042 A CN201610371042 A CN 201610371042A CN 107451832 B CN107451832 B CN 107451832B
- Authority
- CN
- China
- Prior art keywords
- data
- user
- period
- pushing information
- feature data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0253—During e-commerce, i.e. online transactions
-
- 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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a method and a device for pushing information. One embodiment of the method comprises the following steps: acquiring multi-dimensional characteristic data of a user in a preset time period based on the priority dimension in the priority dimension database; dividing the multi-dimensional feature data into a plurality of periods; acquiring a user liveness value of each period; in a preset period, calculating the Euclidean distance between the user liveness values of every two periods; clustering user group data according to the Euclidean distance; and pushing information to the user side according to the user group data. The embodiment improves the utilization rate of the user data and the accuracy of clustering the user groups, so that the information pushed to the users is more targeted.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to the field of internet technologies, and in particular, to a method and an apparatus for generating push information.
Background
The information pushing method refers to pushing information to a user based on objective data. The current common information pushing method is based on user portrait to push information to users. The user representation here is a virtual representation of a real user, and is a target user model built on top of a series of real data (order data, useful data, etc.). The user representation includes the user's basic data (e.g., age, gender, etc.), interests (e.g., books, apparel, etc.), and consumption habits (e.g., time, quantity, and amount), etc., so that merchants can provide more targeted services based on the user representation.
The existing information pushing method comprises the steps of firstly, manually analyzing the existing user data to determine rules of user groups, further constructing rules of a user portrait model, manually modeling the user portrait, generating the model, then generating an execution statement, and finally executing and acquiring the user group data on a big data platform.
However, the current method of pushing information needs to determine the rule of the user group through manual analysis and the utilization rate of the user basic data is low, so that the efficiency of acquiring the user group data is low and the accuracy of pushing information to the user is low.
Disclosure of Invention
The application aims to provide an improved method and device for pushing information, which solve the technical problems mentioned in the background art section.
In a first aspect, the present application provides a method for pushing information, the method comprising: acquiring multi-dimensional characteristic data of a user in a preset time period based on the priority dimension in the priority dimension database; dividing the multi-dimensional feature data into a plurality of periods; acquiring a user liveness value of each period; in a preset period, calculating the Euclidean distance between the user liveness values of every two periods; clustering user group data according to the Euclidean distance; and pushing information to a user terminal according to the user group data.
In a second aspect, the present application provides an apparatus for pushing information, the apparatus comprising: the device comprises: the first acquisition unit is used for acquiring multi-dimensional characteristic data of the user in a preset time period based on the priority dimension in the priority dimension database; a dividing unit for dividing the multi-dimensional feature data into a plurality of periods; a second obtaining unit, configured to obtain a user activity value of each period; a calculating unit, configured to calculate, in a predetermined period, a euclidean distance between user activity values in two periods; the clustering unit is used for clustering user group data according to the Euclidean distance; and the pushing unit is used for pushing information to the user side according to the user group data.
According to the method and device for pushing information, the multi-dimensional characteristic data of the user in the preset time period are obtained based on the priority dimension in the priority dimension database, the multi-dimensional characteristic data are divided into a plurality of periods, the user liveness value of each period is obtained, the Euclidean distance between the user liveness values of every two periods is calculated in the preset period, the user group data are clustered according to the Euclidean distance, and the information is pushed to the user side according to the user group data, so that the rule of the user group is determined through a computer, the efficiency of determining the user group is improved, the utilization rate of user basic data is improved, and the information pushed to the user is more targeted.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the detailed description of non-limiting embodiments, made with reference to the accompanying drawings in which:
FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 is a flow chart of one embodiment of a method of pushing information in accordance with the present application;
FIG. 3 is a flow chart of yet another embodiment of a method of pushing information in accordance with the present application;
FIG. 4 is a schematic diagram of an application scenario of a method of pushing information according to the present application;
FIG. 5 is a schematic diagram of an embodiment of an apparatus for pushing information in accordance with the present application;
fig. 6 is a schematic structural view of still another embodiment of an apparatus for pushing information according to the present application;
fig. 7 is a schematic diagram of a computer system suitable for use in implementing an embodiment of the application.
Detailed Description
The application is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be noted that, for convenience of description, only the portions related to the present application are shown in the drawings.
It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.
Fig. 1 illustrates an exemplary system architecture 100 of an embodiment of a method of pushing information or an apparatus of pushing information to which the present application may be applied.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and servers 105, 106. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the servers 105, 106. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
The user 110 may interact with the servers 105, 106 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication client applications, such as a web browser application, a shopping class application, a search class application, an instant messaging tool, a mailbox client, social platform software, etc., may be installed on the terminal devices 101, 102, 103.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting man-machine interaction, including but not limited to smartphones, tablet computers, MP3 players (Moving Picture Experts Group Audio Layer III, dynamic video expert compression standard audio plane 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic video expert compression standard audio plane 4) players, laptop and desktop computers, and the like.
The servers 105, 106 may be servers providing various services, such as a background server providing support for information displayed on the terminal devices 101, 102, 103. The background server may analyze the received multi-dimensional feature data of the user, and feedback the processing result (e.g. push information) to the terminal device.
It should be noted that, the method for pushing information provided in the embodiment of the present application is generally executed by the servers 105 and 106, and accordingly, the device for pushing information is generally disposed in the servers 105 and 106.
It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow 200 of one embodiment of a method of pushing information in accordance with the present application is shown. The method for pushing information comprises the following steps:
step 201, acquiring multi-dimensional feature data of a user in a preset time period based on a priority dimension in a priority dimension database.
In this embodiment, the electronic device (e.g., the server shown in fig. 1) on which the information pushing method operates may push information to the user terminal through a wired connection manner or a wireless connection manner. It should be noted that the wireless connection may include, but is not limited to, 3G/4G connections, wiFi connections, bluetooth connections, wiMAX connections, zigbee connections, UWB (ultra wideband) connections, and other now known or later developed wireless connection means. Generally, a user browses web pages or purchases using a web browser application, a shopping class application, a search class application, an instant messaging tool, etc. installed on a terminal.
It should be understood that, in the foregoing priority dimension database, the priority dimension preset by the technical developer and the number of priority dimensions may be included. For example, the technical developer may preset the priority dimension to be two dimensions of order data and shopping cart data, and when acquiring the multi-dimensional feature data of the user in the predetermined period based on the priority dimension in the priority dimension database, the order data and shopping cart data of the user may be acquired preferentially.
The multi-dimensional feature data herein may include a plurality of the following dimensions: order data, shopping cart data, collection data, consultation data, comment data, attention data, forwarding data, browsing record data, search record data, posting data, gender data, age data, income data, occupation data, psychological characteristic data, value view data, consumption behavior preference data, attitude data, and habit data. For example, two dimensions of order data and browsing data may be selected as the dimensions to be acquired, and then feature data of the two dimensions of each user may be acquired.
The predetermined time period refers to a time dimension preset according to actual needs. For example, data within 1 year before pushing information can be set as multi-dimensional feature data of a user within a predetermined period of time according to requirements.
Step 202, dividing the multi-dimensional feature data into a plurality of periods.
In this embodiment, based on the multi-dimensional feature data acquired in step 201, the multi-dimensional feature data may be divided into a plurality of periods as needed. For example, if it is necessary to acquire the feature data of the user within 10 days, each period may be set to 10 days, so that the acquired feature data of multiple dimensions within 1 year is divided into 37 periods.
Step 203, obtaining the user activity value of each period.
In this embodiment, when the user activity value of each period is obtained, the multidimensional feature data of each period may be analyzed and processed, and the multidimensional feature data of each period is converted into the user activity value according to a preset user activity calculation rule. The user activity rule herein may be a user activity calculation rule in the prior art or in a future developed technology, which the present application is not limited to.
In an alternative implementation manner of this embodiment, acquiring the user activity value of each period may include: acquiring a weighted average of the multi-dimensional feature data in each period; normalizing the weighted average value to obtain normalized characteristic data; fitting the normalized characteristic data to obtain a user liveness curve; and acquiring the user activity value of each period according to the user activity curve.
In the implementation manner, weights are preset corresponding to the feature data of different dimensions, wherein the weights refer to the relative importance degree of the feature data of the dimension in the feature data of the multiple dimensions, so that a weighted average value of the feature data of the multiple dimensions can be obtained according to the weights in each period; then, carrying out normalization processing on the weighted average value to convert the absolute value of the weighted average value into a relative value relation in the same interval, thereby obtaining normalized characteristic data; fitting the normalized characteristic data to obtain a user liveness curve, wherein the fitting refers to a plurality of discrete function values { f1, f2, …, fn } of a known function, and the difference (such as the difference in least squares meaning) between the function and a known point set is minimized by adjusting a plurality of coefficient f (lambda 1, lambda 2, …, lambda n) to be determined in the function; finally, according to the user activity curve, the user activity value of each period is obtained, and it is understood that the user activity value at this time is a value on the user activity curve corresponding to each period.
It should be understood that the fitting method herein may be a fitting method in the prior art or in future developed technologies, and the present application is not limited in this regard. Illustratively, fitting the normalized feature data to obtain a user liveness curve may include: and inputting the normalized characteristic data into a Support Vector Regression (SVR) model for fitting, so as to obtain a user liveness curve. When the normalized feature data is fitted by using a support vector regression model, the method for pushing information may further include: and training a support vector regression model by using the normalized characteristic data. The method for training the support vector regression model may be a training method existing in the prior art or in a future developed technology, and will not be described herein.
Step 204, calculating the Euclidean distance between the user liveness values of every two periods within the preset period.
In this embodiment, the euclidean distance, i.e., euclidean metric, is a commonly used distance definition, which refers to the true distance between two points in m-dimensional space, or the natural length of a vector (i.e., the distance from the point to the origin). The euclidean distance in the two-dimensional space of the present application is the actual distance between two points, and therefore, the euclidean distance between the user activity values of two periods, that is, the actual distance between the user activity values of two periods, is calculated within a predetermined period, that is, within a period according to a preset focus.
Step 205, clustering user population data according to Euclidean distance.
In this embodiment, based on the euclidean distance obtained in step 204, user group data with similar euclidean distances may be clustered according to the euclidean distance, that is, a user group with similar variation trend of the user activity value in the period of important attention is obtained. Here, clustering refers to a process of dividing user population data into a plurality of classes composed of similar euclidean distances.
Step 206, pushing information to the user terminal according to the user group data.
In this embodiment, based on the user group data obtained in step 205, information may be pushed to a user group whose trend of change of the activity value is similar in a period of important attention.
The information pushing method provided by the embodiment of the application can push information to the users with the determined user group rule, and improves the utilization rate of user data and the accuracy of clustering user groups, so that the information pushed to the users is more targeted.
With further reference to fig. 3, a flow 300 of yet another embodiment of a method of pushing information in accordance with the present application is shown. The method for pushing information comprises the following steps:
in step 301, based on the priority dimension in the priority dimension database, acquiring multi-dimensional feature data of the user in a predetermined period of time, and then executing step 302;
in step 302, the multi-dimensional feature data is divided into a plurality of periods, and then step 303 is performed;
in step 303, a user activity value of each period is acquired, and then step 304 is executed;
in step 304, the euclidean distance between the user activity level values of every two periods is calculated in a predetermined period, and then step 305 is executed;
in step 305, the user population data is clustered according to the Euclidean distance, and then step 306 is performed;
in step 306, user individual data corresponding to the historical user order data in the user group data is detected, and then step 307 is executed;
in step 307, the dimensions of the feature data acquired by the user individual data and the number of dimensions of each acquired feature data are acquired, after which step 308 is performed;
in step 308, according to the number from large to small, the dimensions of the feature data acquired in the preset number are acquired, and then step 309 is executed;
in step 309, the dimensions of the feature data acquired in the preset number are taken as priority dimensions, and the priority dimension database is updated, and then step 301 is performed.
It should be understood that the steps 301 to 305 correspond to the steps 201 to 205 in fig. 2, and thus the operations and steps described in the steps 201 to 205 are equally applicable to the steps 301 to 305, and are not repeated herein.
In steps 306 to 309, the user group data is cluster data obtained after analysis and processing according to the multidimensional feature data, and the historical user order data is data of orders that have actually occurred, and according to the order data that have actually occurred, feature data of users that have correctly purchased in the user group data can be detected, and dimensions of the feature data of the users that have correctly purchased (that is, dimensions of feature data obtained by the above-mentioned individual data of the users) are obtained. Specifically, the category of the user group data corresponding to the historical user order data may be found by a recursive search method, after the search is completed, the dimensions of the feature data included in the user are counted and ordered, the dimensions of the preset number of feature data are found, the dimensions of the preset number of feature data are updated as priority dimensions to a priority dimension database, if the priority dimension database already includes the dimensions, the updating step is skipped, and if the priority dimension database does not include the dimensions, the dimensions are updated to the priority dimension database, and then step 301 is executed.
According to the information pushing method provided by the embodiment of the application, the characteristic data of the priority dimension of the user in the preset time period can be obtained and used as the user basic data for analysis, the utilization rate of the user basic data is improved, and the efficiency and the accuracy of clustering user groups are improved, so that the information pushed to the user is more targeted.
With continued reference to fig. 4, fig. 4 is a schematic flowchart of an application scenario of the method of pushing information according to the present embodiment.
As shown in fig. 4, in an application scenario of the method for pushing information, the following four modules are designed to implement the method for pushing information: a data extraction module 410, a model classification module 420, a reinforcement learning module 430, and a push information module 440.
The main function of the data extraction module 410 is to extract all data in a time dimension from a large data platform, and after time period transformation and normalization change of data magnitude, the data in which the user is cluttered becomes a data format which can be calculated uniformly by using a model.
The data extraction module can obtain a unified data format through the following steps:
first, in step 411, feature data of multiple dimensions is extracted.
Before building a model, basic information of a user needs to be extracted, firstly, multi-dimensional feature data such as historical order data, historical browsing data and the like of the user in a preset time period are extracted on a big data platform according to a time format (note that the dimension of the feature data is selected empirically (for example, order, browsing and the like) at first, when the priority dimension of a priority dimension database in the reinforcement learning module 430 is continuously increased, the feature extraction module automatically calls the feature data, and the priority dimension is guaranteed to be preferentially selected), and the multi-dimensional feature data within 1 year is assumed to be extracted according to the following format data:
thereafter, in step 412, the time period of the multi-dimensional feature data is transformed.
After the specified multi-dimensional feature data arranged in time is selected, time-period transformation is required according to different periods, and the feature data of different dimensions (order data and browsing data) of each user are required to be put into a unified time life period (taking 10 days as one period as an example). The format after the change is:
testname 0.0 0.0 4 6 6 0.0 0.0 4 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
description: the testname is a user name used for testing, wherein 4= (4×0.9+0.1×4) refers to that the total number of orders in one period is 4, the total number of browses is 4, the weight of orders is 0.9, the weight of browses is 0.1, so that the weighted average value of feature data in two dimensions of order data and browsed data is 4, and similarly, the numerical value in other periods is also the weighted average value of feature data in two dimensions of order data and browsed data.
Thereafter, in step 413, the feature data after the transformation time period is normalized.
After obtaining the feature data after the transformation time period, there may be an order of magnitude difference between different users, and it is assumed that the user a has 10 valid orders in one month, the number of browsing times is 1, the user B has 100 valid orders in one month, the number of browsing times is 10, if the period transformation is directly performed at this time, the activity value calculated by the user B is definitely higher than that of the user a, but in this case, the activity value is inaccurate, mathematical changes need to be performed, the data of the user a and the data of the user B are both divided into the same interval, for example, between [0,4], and it is assumed that one data is randomly taken from the data pool:
testname 0.0 0.0 0.5 1.0 1.0 0.0 0.0 0.5 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
the user representation of a time period is thus characterized as a set of data representations in a uniform format.
The main function of the model classification module 420 is to build a model through the data input by the data extraction module and through the SVR algorithm, calculate the user liveness based on the time life cycle, and cluster the user population according to the user liveness.
Model classification module 420 clusters the user population by:
after the normalized data input from the data extraction module is obtained, in step 421, the SVR model is started to be built and a fitting curve is generated according to the built SVR model, then in step 422, the activity value of each user in each period is calculated, and then in step 423, the user population is clustered according to the activity value of each user in each period.
The currently adopted method is as follows: the acquired cycle data is trained to calculate the cycle value of the SVR regression (versus existing value) and the SVR prediction (versus unknown data), e.g., the testname user now has 37 cycle values for 15 days as follows:
Testname 0.00.0 0.5 1.0 1.0 0.0 0.0 0.5 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
the earliest extraction time is 2014-1-1 and the latest time is 2015-1-1, so we want to know the values of the 1 st month 1 day to 1 month 14 day period in 2015, and the corresponding values after calculation by SVR are:
where 0.0996304954031 is the state the current user is in, 0.156469039467 is the state the next cycle may be in.
At present, after all data are counted, the frequencies of the data are ordered, and the 5 intervals with the highest frequency are taken, so that the active period is divided as follows:
less than 0.11: inactive state
0.11 to 0.5: low activity
0.5 to 1.5: normally active
1.5 to 2.5: high activity
Greater than 2.5: ultrahigh activity
Thus, activity values for all users are obtained.
Next, the user population classification sub-module starts to be counted, and the inputs of this module are as follows:
examples:
then, according to the defined period, a corresponding time sequence is found, for example, the last 4 periods of 15 days:
0.0999411429443 0.100038003852 0.0996304954031 0.156469039467, calculating the difference between every two to obtain three differences, and similarly, calculating the values of the last 4 periods of all users, and finally calculating the Euclidean distance between every two users until the calculation is stopped, and outputting the user group.
The reinforcement learning module 430 has the main functions of comparing and evaluating the classified user group data by the input model classification module with the real user shopping order data in the real marketing period, finding out the dimension of the feature data of the user who purchases correctly, counting the dimension of the feature data of all the correct users, transmitting the feature data into an independent priority dimension database, and providing the priority dimension for the feature extraction module to use when the data extraction module uses the feature data with multiple dimensions.
Reinforcement learning module 430 generates a priority dimension database by:
in step S431, the effect of the clustered user group is evaluated, the category of the user group corresponding to the real user shopping order data is found by using a recursive search method, then in step S432 after the search is completed, the dimensions of the feature data included in the user are counted and sorted to find the dimensions of the first three data features, then in step S433, the three dimensions are updated to the priority dimension database, and if the dimension is already in the priority dimension database, the updating is skipped and not updated. So that the next modeling can be automatically completed instead of manually analyzing and modeling the data.
The main function of the push information module 440 is to push information to users according to the clustered user population output by the model classification module 420.
The push information module 440 pushes user information through step S441. In step S441, information conforming to the category of the clustered user group is queried in the information pushed to the user by using the query method, and then information conforming to the category of the clustered user group is pushed to the user.
In the application scenario of the embodiment of the application, the method for pushing information pushes information to the clustered user groups, and obtains the characteristic data of the priority dimension of the user in a preset time period as the user basic data for analysis, thereby improving the utilization rate of the user data and the accuracy of the clustered user groups, and further enabling the information pushed to the user to be more targeted.
With further reference to fig. 5, as an implementation of the method shown in the foregoing figures, the present application provides an embodiment of an apparatus for pushing information, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be specifically applied to various electronic devices.
As shown in fig. 5, the information pushing apparatus 500 in this embodiment includes: a first acquisition unit 510, a partitioning unit 520, a second acquisition unit 530, a calculation unit 540, a clustering unit 550, and a pushing unit 560.
The first obtaining unit 510 is configured to obtain multi-dimensional feature data of the user in a predetermined period of time based on the priority dimension in the priority dimension database.
The dividing unit 520 is configured to divide the multi-dimensional feature data into a plurality of periods.
A second obtaining unit 530, configured to obtain a user activity value of each period.
The calculating unit 540 is configured to calculate, in a predetermined period, a euclidean distance between user activity level values of two periods.
And a clustering unit 550 for clustering user group data according to the Euclidean distance.
And the pushing unit 560 is configured to push information to the user terminal according to the user group data.
Those skilled in the art will appreciate that the above-described information pushing device 500 further includes some other well-known structures, such as a processor, a memory, etc., which are not shown in fig. 5 in order to unnecessarily obscure the embodiments of the present disclosure.
It should be understood that the elements recited in apparatus 500 correspond to the various steps in the method described with reference to fig. 2. Thus, the operations and features described above for the method of pushing information are equally applicable to the apparatus 500 and the units contained therein, and are not described herein. The corresponding units in the apparatus 500 may cooperate with units in a terminal device and/or a server to implement the solution of the embodiments of the present application.
With further reference to fig. 6, as an implementation of the method shown in the foregoing figures, the present application provides an embodiment of an apparatus for pushing information, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be specifically applied to various electronic devices.
As shown in fig. 6, an apparatus 600 for pushing information according to the present embodiment includes: the first acquisition unit 610, the division unit 620, the second acquisition unit 630, the calculation unit 640, the clustering unit 660, and the pushing unit 660.
The first obtaining unit 610 is configured to obtain multi-dimensional feature data of a user in a predetermined period of time based on a priority dimension in the priority dimension database.
And a dividing unit 620 for dividing the multi-dimensional feature data into a plurality of periods.
A second obtaining unit 630, configured to obtain a user activity value of each period.
And a calculating unit 640 for calculating the euclidean distance between the user liveness values of two cycles within a predetermined cycle.
And a clustering unit 650 for clustering user group data according to the euclidean distance.
And a detection unit 660 for detecting individual data of the user, which matches with the historical order data of the user, in the user group data.
A third acquiring unit 670 configured to acquire dimensions of feature data acquired by the user individual data and the number of dimensions of each acquired feature data.
A fourth acquiring unit 680, configured to acquire dimensions of the feature data acquired by the preset number according to the number from large to small.
And a setting unit 690, configured to update the priority dimension database with the dimension of the feature data obtained in the preset amount as the priority dimension.
Those skilled in the art will appreciate that the above-described information pushing apparatus 600 also includes some other well-known structures, such as a processor, a memory, etc., which are not shown in fig. 6 in order to unnecessarily obscure the embodiments of the present disclosure.
It should be understood that the elements recited in apparatus 600 correspond to the various steps in the method described with reference to fig. 3. Thus, the operations and features described above for the method of pushing information are equally applicable to the apparatus 600 and the units contained therein, and are not described herein. The corresponding elements in the apparatus 600 may cooperate with elements in a terminal device and/or a server to implement aspects of embodiments of the present application.
In the above-described embodiment of the present application, the first acquisition unit, the second acquisition unit, the third acquisition unit, and the fourth acquisition unit represent only four units whose acquisition objects are different from each other. It will be appreciated by those skilled in the art that the first, second, third or fourth thereof do not constitute a particular limitation of the acquisition unit.
Similarly, the first acquisition subunit and the second acquisition subunit represent only two subunits with different acquisition objects. It will be appreciated by those skilled in the art that the first or second thereof does not constitute a particular limitation of the acquisition subunit.
Referring now to FIG. 7, there is illustrated a schematic diagram of a computer system 700 suitable for use in implementing a terminal device or server in accordance with an embodiment of the present application.
As shown in fig. 7, the computer system 700 includes a Central Processing Unit (CPU) 701, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 702 or a program loaded from a storage section 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the system 700 are also stored. The CPU 701, ROM 702, and RAM 703 are connected to each other through a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
The following components are connected to the I/O interface 705: an input section 706 including a keyboard, a mouse, and the like; an output portion 707 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage section 708 including a hard disk or the like; and a communication section 709 including a network interface card such as a LAN card, a modem, or the like. The communication section 709 performs communication processing via a network such as the internet. The drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 710 as necessary, so that a computer program read therefrom is mounted into the storage section 708 as necessary.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program tangibly embodied on a machine-readable medium, the computer program comprising program code for performing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 709, and/or installed from the removable medium 711.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a unit, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units involved in the embodiments of the present application may be implemented in software or in hardware. The described units may also be provided in a processor, for example, described as: the processor comprises a first acquisition unit, a division unit, a second acquisition unit, a calculation unit, a clustering unit and a pushing unit. The names of these units do not constitute a limitation on the unit itself in some cases, and for example, the semantic receiving unit may also be described as "a unit that acquires multi-dimensional feature data of a user within a predetermined period of time based on a priority dimension in a priority dimension database".
As another aspect, the present application also provides a nonvolatile computer storage medium, which may be a nonvolatile computer storage medium included in the apparatus described in the above embodiment; or may be a non-volatile computer storage medium, alone, that is not incorporated into the terminal. The above-described nonvolatile computer storage medium stores one or more programs that, when executed by an apparatus, cause the apparatus to: acquiring multi-dimensional characteristic data of a user in a preset time period based on the priority dimension in the priority dimension database; dividing the multi-dimensional feature data into a plurality of periods; acquiring a user liveness value of each period; in a preset period, calculating the Euclidean distance between the user liveness values of every two periods; clustering user group data according to the Euclidean distance; and pushing information to the user side according to the user group data.
The above description is only illustrative of the preferred embodiments of the present application and of the principles of the technology employed. It will be appreciated by persons skilled in the art that the scope of the application referred to in the present application is not limited to the specific combinations of the technical features described above, but also covers other technical features formed by any combination of the technical features described above or their equivalents without departing from the inventive concept. Such as the above-mentioned features and the technical features disclosed in the present application (but not limited to) having similar functions are replaced with each other.
Claims (11)
1. A method of pushing information, the method comprising:
acquiring multi-dimensional characteristic data of each user in a preset time period based on the priority dimension in the priority dimension database;
dividing the multi-dimensional characteristic data of each user into a plurality of periods, wherein the periods are obtained by dividing the preset time period;
acquiring a user activity value of each user in each period;
in a preset period, calculating the Euclidean distance between the user activity values of every two periods of each user;
clustering user group data according to the Euclidean distance to form users with similar change trend of the liveness value in the preset period into a user group;
pushing information to a user side according to the user group data;
the obtaining the user activity value of each user in each period comprises the following steps: converting the multi-dimensional characteristic data of each period in the plurality of periods into a user liveness value according to a preset user liveness calculation rule; the method specifically comprises the following steps:
acquiring a weighted average of the multi-dimensional feature data in each period; normalizing the weighted average value to obtain normalized characteristic data; fitting the normalized characteristic data to obtain a user liveness curve; and acquiring a user activity value of each period according to the user activity curve.
2. The method for pushing information according to claim 1, wherein said fitting the normalized feature data to obtain a user liveness curve comprises:
and inputting the normalized characteristic data into a support vector regression model for fitting to obtain a user liveness curve.
3. The method for pushing information according to claim 2, wherein the obtaining the user activity value of each user in each period further comprises:
and training the support vector regression model by adopting the normalized characteristic data.
4. The method of pushing information according to claim 1, further comprising:
detecting user individual data which accords with the historical order data of the user in the user group data;
acquiring dimensions of the feature data acquired by the user individual data and the number of dimensions of each acquired feature data;
according to the number from large to small, acquiring the dimension of the feature data acquired by the preset number;
and taking the dimension of the feature data acquired by the preset quantity as a priority dimension, and updating the priority dimension database.
5. The method of pushing information according to claim 1, wherein the characteristic data comprises a plurality of the following dimensions: order data, shopping cart data, collection data, consultation data, comment data, attention data, forwarding data, browsing record data, search record data, posting data, gender data, age data, income data, occupation data, psychological characteristic data, value view data, consumption behavior preference data, attitude data, and habit data.
6. An apparatus for pushing information, the apparatus comprising:
the first acquisition unit is used for acquiring multi-dimensional characteristic data of each user in a preset time period based on the priority dimension in the priority dimension database;
a dividing unit, configured to divide the multi-dimensional feature data of each user into a plurality of periods, where the plurality of periods are obtained by dividing the predetermined time period;
the second acquisition unit is used for acquiring the user activity value of each user in each period;
a calculating unit, configured to calculate, in a predetermined period, a euclidean distance between user activity values of each user in two periods;
a clustering unit for clustering user group data according to the Euclidean distance to form users with similar change trend of the liveness value in the preset period into a user group;
the pushing unit is used for pushing information to the user side according to the user group data;
the second acquisition unit is further configured to: converting the multi-dimensional characteristic data of each period in the plurality of periods into a user liveness value according to a preset user liveness calculation rule;
wherein the second acquisition unit includes: a first acquisition subunit configured to acquire a weighted average of the multi-dimensional feature data in each period; a normalization subunit, configured to normalize the weighted average value to obtain normalized feature data; a fitting subunit, configured to fit the normalized feature data to obtain a user liveness curve; and the second acquisition subunit is used for acquiring the user activity value of each period according to the user activity curve.
7. The apparatus for pushing information of claim 6, wherein the fitting subunit is further configured to: and inputting the normalized characteristic data into a support vector regression model for fitting to obtain a user liveness curve.
8. The apparatus for pushing information according to claim 7, wherein the second obtaining unit further includes:
and the training subunit is used for training the support vector regression model by adopting the normalized characteristic data.
9. The apparatus for pushing information according to claim 6, further comprising:
the detection unit is used for detecting user individual data which is consistent with the historical order data of the user in the user group data;
a third acquisition unit configured to acquire dimensions of the feature data acquired by the user individual data and the number of dimensions of each acquired feature data;
a fourth obtaining unit, configured to obtain, according to the number from large to small, a dimension of the feature data obtained by a preset number; and
the setting unit is used for taking the dimension of the feature data acquired by the preset quantity as a priority dimension and updating the priority dimension database.
10. An apparatus for pushing information, comprising:
a memory; and a processor coupled to the memory, the processor configured to perform the method of pushing information of any of claims 1-5 based on instructions stored in the memory.
11. A computer readable storage medium storing computer instructions which, when executed by a processor, implement a method of pushing information according to any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610371042.5A CN107451832B (en) | 2016-05-30 | 2016-05-30 | Method and device for pushing information |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610371042.5A CN107451832B (en) | 2016-05-30 | 2016-05-30 | Method and device for pushing information |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107451832A CN107451832A (en) | 2017-12-08 |
CN107451832B true CN107451832B (en) | 2023-09-05 |
Family
ID=60485643
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610371042.5A Active CN107451832B (en) | 2016-05-30 | 2016-05-30 | Method and device for pushing information |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107451832B (en) |
Families Citing this family (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108492194A (en) * | 2018-03-06 | 2018-09-04 | 平安科技(深圳)有限公司 | Products Show method, apparatus and storage medium |
CN108648000B (en) * | 2018-04-24 | 2022-10-28 | 腾讯科技(深圳)有限公司 | Method and device for evaluating user retention life cycle and electronic equipment |
CN109241133A (en) * | 2018-08-14 | 2019-01-18 | 北京粉笔未来科技有限公司 | Data monitoring method, calculates equipment and storage medium at device |
CN109711871B (en) * | 2018-12-13 | 2021-03-12 | 北京达佳互联信息技术有限公司 | Potential customer determination method, device, server and readable storage medium |
CN111797848B (en) * | 2019-04-09 | 2023-10-24 | 成都鼎桥通信技术有限公司 | User classification method, device, equipment and storage medium |
CN112150179B (en) * | 2019-06-28 | 2024-04-09 | 京东科技控股股份有限公司 | Information pushing method and device |
CN111062824B (en) * | 2019-12-04 | 2023-08-18 | 腾讯科技(深圳)有限公司 | Group member processing method, device, computer equipment and storage medium |
CN111400764B (en) * | 2020-03-25 | 2021-05-07 | 支付宝(杭州)信息技术有限公司 | Personal information protection wind control model training method, risk identification method and hardware |
CN111612499B (en) * | 2020-04-03 | 2023-07-28 | 浙江口碑网络技术有限公司 | Information pushing method and device, storage medium and terminal |
CN112053212A (en) * | 2020-09-30 | 2020-12-08 | 杭州拼便宜网络科技有限公司 | Commodity group purchase method, commodity group purchase system and electronic equipment |
CN117808473B (en) * | 2024-03-01 | 2024-05-31 | 深圳迅策科技股份有限公司 | Privacy calculation method and system for transaction data |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102339296A (en) * | 2010-07-26 | 2012-02-01 | 阿里巴巴集团控股有限公司 | Method and device for sorting query results |
CN102346894A (en) * | 2010-08-03 | 2012-02-08 | 阿里巴巴集团控股有限公司 | Output method, system and server of recommendation information |
CN102411596A (en) * | 2010-09-21 | 2012-04-11 | 阿里巴巴集团控股有限公司 | Information recommendation method and system |
US8533144B1 (en) * | 2012-11-12 | 2013-09-10 | State Farm Mutual Automobile Insurance Company | Automation and security application store suggestions based on usage data |
CN103377242A (en) * | 2012-04-25 | 2013-10-30 | Tcl集团股份有限公司 | User behavior analysis method, user behavior analytical prediction method and television program push system |
CN104077332A (en) * | 2013-03-29 | 2014-10-01 | 上海城际互通通信有限公司 | User behavior analysis method based on charging information |
CN104111946A (en) * | 2013-04-19 | 2014-10-22 | 腾讯科技(深圳)有限公司 | Clustering method and device based on user interests |
CN104866540A (en) * | 2015-05-04 | 2015-08-26 | 华中科技大学 | Personalized recommendation method based on group user behavior analysis |
-
2016
- 2016-05-30 CN CN201610371042.5A patent/CN107451832B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102339296A (en) * | 2010-07-26 | 2012-02-01 | 阿里巴巴集团控股有限公司 | Method and device for sorting query results |
CN102346894A (en) * | 2010-08-03 | 2012-02-08 | 阿里巴巴集团控股有限公司 | Output method, system and server of recommendation information |
CN102411596A (en) * | 2010-09-21 | 2012-04-11 | 阿里巴巴集团控股有限公司 | Information recommendation method and system |
CN103377242A (en) * | 2012-04-25 | 2013-10-30 | Tcl集团股份有限公司 | User behavior analysis method, user behavior analytical prediction method and television program push system |
US8533144B1 (en) * | 2012-11-12 | 2013-09-10 | State Farm Mutual Automobile Insurance Company | Automation and security application store suggestions based on usage data |
CN104077332A (en) * | 2013-03-29 | 2014-10-01 | 上海城际互通通信有限公司 | User behavior analysis method based on charging information |
CN104111946A (en) * | 2013-04-19 | 2014-10-22 | 腾讯科技(深圳)有限公司 | Clustering method and device based on user interests |
CN104866540A (en) * | 2015-05-04 | 2015-08-26 | 华中科技大学 | Personalized recommendation method based on group user behavior analysis |
Also Published As
Publication number | Publication date |
---|---|
CN107451832A (en) | 2017-12-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107451832B (en) | Method and device for pushing information | |
CN109460514B (en) | Method and device for pushing information | |
Nguyen et al. | Real-time event detection for online behavioral analysis of big social data | |
WO2018103718A1 (en) | Application recommendation method and apparatus, and server | |
JP6404106B2 (en) | Computing device and method for connecting people based on content and relationship distance | |
CN106951527B (en) | Song recommendation method and device | |
CN113688310B (en) | Content recommendation method, device, equipment and storage medium | |
US20170235726A1 (en) | Information identification and extraction | |
CN112100396B (en) | Data processing method and device | |
US10262041B2 (en) | Scoring mechanism for discovery of extremist content | |
US20150278907A1 (en) | User Inactivity Aware Recommendation System | |
CN108512674B (en) | Method, device and equipment for outputting information | |
WO2017201905A1 (en) | Data distribution method and device, and storage medium | |
CN110968802A (en) | User characteristic analysis method, analysis device and readable storage medium | |
TW201508509A (en) | System and method for recommending files | |
Mollgaard et al. | Emergent user behavior on Twitter modelled by a stochastic differential equation | |
CN108959289B (en) | Website category acquisition method and device | |
CN113792952A (en) | Method and apparatus for generating a model | |
CN109299351B (en) | Content recommendation method and device, electronic equipment and computer readable medium | |
CN110852078A (en) | Method and device for generating title | |
CN113076450B (en) | Determination method and device for target recommendation list | |
CN113516524B (en) | Method and device for pushing information | |
CN112487276B (en) | Object acquisition method, device, equipment and storage medium | |
CN113704617A (en) | Article recommendation method, system, electronic device and storage medium | |
JP2017004493A (en) | Data analysis method, data analysis device and program |
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 | ||
GR01 | Patent grant |