CN114638649A - Window pushing method, system and related device - Google Patents
Window pushing method, system and related device Download PDFInfo
- Publication number
- CN114638649A CN114638649A CN202210320225.XA CN202210320225A CN114638649A CN 114638649 A CN114638649 A CN 114638649A CN 202210320225 A CN202210320225 A CN 202210320225A CN 114638649 A CN114638649 A CN 114638649A
- Authority
- CN
- China
- Prior art keywords
- window
- pushing
- pushed
- push
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000012545 processing Methods 0.000 claims description 26
- 230000002159 abnormal effect Effects 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000002085 persistent effect Effects 0.000 claims description 3
- 230000001052 transient effect Effects 0.000 claims description 2
- 238000011156 evaluation Methods 0.000 abstract description 2
- 230000014509 gene expression Effects 0.000 description 5
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000001771 impaired effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
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
- G06Q30/0203—Market surveys; Market polls
-
- 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
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0224—Discounts or incentives, e.g. coupons or rebates based on user history
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Technology Law (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The embodiment of the application discloses a window pushing method, a window pushing system and a related device. Therefore, the comprehensively-selected target push window can be the best product information window which is most suitable for the user requirements through three evaluation conditions of push time, user labels and total push selection, and the products displayed on the window are also the products which are most suitable for the user in comparison. Therefore, the product information window meeting the self requirements can be pushed to the user in a targeted manner, so that more convenient and effective consumption selection is provided for the user, and the user experience is improved.
Description
Technical Field
The embodiment of the application relates to the technical field of internet, in particular to a window pushing method, a window pushing system and a related device.
Background
With the continuous development of the information age, various product information layers are endless, so people usually only pay attention to or browse product information meeting their own needs.
For example, in the aspect of investment and financial management, people are more and more interested in purchasing credit products, however, most of the credit product windows displayed on the existing user side are not favored by users, mainly because the credit products displayed on the windows are not products really required by the users, namely, the pushing accuracy is low, which easily results in the impaired user experience.
Disclosure of Invention
The embodiment of the application provides a window pushing method, a window pushing system and a related device, which are used for pertinently pushing a product information window meeting the self requirement to a user.
A first aspect of an embodiment of the present application provides a window pushing method, including:
after receiving a window display request which is sent by a user side and carries user attribute information, acquiring preset push time of each window to be pushed and user label information related to each window to be pushed, wherein the window to be pushed is used for displaying product information;
selecting at least one alternative push window with preset push time meeting the push time condition and user label information meeting the user attribute information condition from the windows to be pushed;
calculating the total pushing and selecting points of each alternative pushing window in the at least one alternative pushing window, and determining a target pushing window from the at least one alternative pushing window according to the sequence of the total pushing and selecting points;
and pushing the target pushing window to the user side.
Optionally, the calculating a total score of the push selection of each alternative push window in the at least one alternative push window includes:
calculating a total pushed and selected score of each alternative pushed window according to at least one of the product score and the user score of each alternative pushed window in the at least one alternative pushed window;
the product score is obtained by calculation according to a weight score of a first product label, wherein the first product label comprises one or more of promotion rate, product attribute, shelf life and product standard reaching rate of a product corresponding to the alternative pushing window;
the user score is calculated according to the number of abnormal operations and the number of normal operations, the number of abnormal operations is the number of times that the abnormal operations are executed in the alternative push window within a history period of time, and the number of normal operations is the number of times that the normal operations are executed in the alternative push window within the history period of time.
Optionally, after calculating the total score of push selection of each alternative push window in the at least one alternative push window, before determining the target push window from the at least one alternative push window according to the ranking of the total score of push selection, the method further includes:
if more than two identical values exist in each total pushing score, acquiring a second product label of an alternative pushing window with the identical values, wherein the second product label is a difference label different from the first product label;
obtaining a weight score of a second product label associated with the alternative push window with the same score;
updating the total pushed and selected scores of the alternative pushed windows with the same score according to the weight scores corresponding to all product labels associated with the alternative pushed windows with the same score; wherein the all product tags include the first product tag and the second product tag.
Optionally, before obtaining the preset pushing time of each window to be pushed, the method further includes:
counting heat index values of the windows to be pushed at different historical time points;
and generating preset pushing time of each window to be pushed according to the historical time point corresponding to the heat index value meeting the heat index condition of each window to be pushed.
Optionally, before obtaining user tag information associated with each window to be pushed, the method further includes:
counting a plurality of normal history user terminals to which each window to be pushed is pushed within a history period of time; the normal history user side is used for representing the history user side which executes normal operation on the pushed window to be pushed;
and carrying out user label analysis processing on the user attribute information of a plurality of normal historical user ends corresponding to each window to be pushed so as to generate user label information associated with each window to be pushed.
Optionally, the pushing the target push window to the user side includes:
any one of the following processes is performed:
if the current time point reaches the preset pushing time corresponding to the target pushing window, pushing the target pushing window to the user side so that the user side can display the target pushing window at the current time point;
if the current time point is earlier than the preset pushing time corresponding to the target pushing window, pushing the target pushing window to the user side so that the user side stores the target pushing window, and displaying the target pushing window when the current time point reaches the preset pushing time corresponding to the target pushing window.
Optionally, if the current time point is earlier than a preset pushing time corresponding to the target pushing window, the method further includes, after pushing the target pushing window to the user side:
and stopping responding to the window display request newly sent by the user side before the current time point reaches the preset push time corresponding to the target push window.
Optionally, selecting at least one alternative push window whose preset push time satisfies the push time condition includes:
and selecting the window to be pushed within the target pushing time period of the preset pushing time as an alternative pushing window according to the preset pushing time of each window to be pushed.
A second aspect of the embodiments of the present application provides a window pushing system, including:
the system comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is used for acquiring preset pushing time of each window to be pushed and user label information related to each window to be pushed after receiving a window display request which is sent by a user side and carries user attribute information, and the window to be pushed is used for displaying product information;
the processing unit is used for selecting at least one alternative pushing window of which the preset pushing time meets the pushing time condition and the user label information meets the user attribute information condition from all the windows to be pushed;
the processing unit is further configured to calculate a total push score of each alternative push window in the at least one alternative push window, and determine a target push window from the at least one alternative push window according to a ranking of the total push scores;
and the sending unit is used for pushing the target pushing window to the user side.
Optionally, the processing unit is specifically configured to:
calculating a total pushed score of each alternative pushed window according to at least one of the product score and the user score of each alternative pushed window in the at least one alternative pushed window;
the product score is obtained by calculating according to the weight score of a first product label, wherein the first product label comprises one or more of promotion rate, product attribute, shelf life and product standard reaching rate of a product corresponding to the alternative pushing window;
the user score is calculated according to the number of abnormal operations and the number of normal operations, the number of abnormal operations is the number of times that the abnormal operations are executed in the alternative push window within a history period of time, and the number of normal operations is the number of times that the normal operations are executed in the alternative push window within the history period of time.
Optionally, the processing unit is further configured to:
if more than two identical values exist in each total pushing score, acquiring a second product label of an alternative pushing window with the identical values, wherein the second product label is a difference label different from the first product label;
obtaining a weight score of a second product label associated with the alternative push window with the same score;
updating the total pushed and selected scores of the alternative pushed windows with the same score according to the weight scores corresponding to all product labels associated with the alternative pushed windows with the same score; wherein the all product tags include the first product tag and the second product tag.
Optionally, the processing unit is further configured to:
counting heat index values of the windows to be pushed at different historical time points;
and generating preset pushing time of each window to be pushed according to the historical time point corresponding to the heat index value meeting the heat index condition of each window to be pushed.
Optionally, the processing unit is further configured to:
counting a plurality of normal history user terminals to which each window to be pushed is pushed within a history period of time; the normal history user side is used for representing the history user side which executes normal operation on the pushed window to be pushed;
and carrying out user label analysis processing on the user attribute information of a plurality of normal historical user ends corresponding to each window to be pushed so as to generate user label information associated with each window to be pushed.
Optionally, the processing unit is specifically configured to execute any one of the following processes:
if the current time point reaches the preset pushing time corresponding to the target pushing window, pushing the target pushing window to the user side so that the user side can display the target pushing window at the current time point;
if the current time point is earlier than the preset pushing time corresponding to the target pushing window, pushing the target pushing window to the user side so that the user side stores the target pushing window, and displaying the target pushing window when the current time point reaches the preset pushing time corresponding to the target pushing window.
Optionally, the processing unit is further configured to: and stopping responding to the window display request newly sent by the user side before the current time point reaches the preset push time corresponding to the target push window.
Optionally, the processing unit is specifically configured to: and selecting the window to be pushed with the preset pushing time belonging to the target pushing time period as the alternative pushing window according to the preset pushing time of each window to be pushed.
A third aspect of the embodiments of the present application provides a window pushing apparatus, including:
the system comprises a central processing unit, a memory and an input/output interface;
the memory is a transient memory or a persistent memory;
the central processing unit is configured to communicate with the memory and execute the instructions in the memory to perform the method described in the first aspect of the embodiments of the present application or any specific implementation manner of the first aspect.
A fourth aspect of embodiments of the present application provides a computer-readable storage medium, including instructions that, when executed on a computer, cause the computer to perform a method as described in the first aspect of embodiments of the present application or any specific implementation manner of the first aspect.
A fifth aspect of embodiments of the present application provides a computer program product comprising instructions that, when run on a computer, cause the computer to perform a method as described in the first aspect of embodiments of the present application or any implementation manner of the first aspect.
According to the technical scheme, the embodiment of the application has the following advantages:
according to the embodiment of the application, after at least one window to be pushed which meets the pushing time condition and the user attribute information condition at the same time is used as the alternative pushing window, the total pushing points of all the alternative pushing windows are compared, and then the target pushing window which is finally pushed to the user side can be determined. Therefore, the comprehensively selected target pushing window is the best product information window which is most suitable for the user requirements through three evaluation conditions of pushing time, user labels and total selection score, and the products displayed by the window are also the products which are most suitable for the user in comparison. Therefore, the product information window meeting the self requirements can be pushed to the user in a targeted manner, so that more convenient and effective consumption selection is provided for the user, and the user experience is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art according to the drawings.
Fig. 1 is a schematic flowchart of a window pushing method according to an embodiment of the present application;
fig. 2 is another schematic flow chart illustrating a window pushing method according to an embodiment of the present application;
fig. 3 is another schematic flow chart illustrating a window pushing method according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a window pushing system according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a window pushing device according to an embodiment of the present application.
Detailed Description
For convenience of explanation and understanding, the terms and expressions referred to in the embodiments of the present application are used in the following explanations.
(1) cron: a string with a temporal meaning, often separated by 5 spaces, divided into 6 fields, in the format X. Wherein X is a placeholder of a field, and when a single field has a plurality of values, the values are separated by using a half-angle comma; each field may be a definite value or a special character with logical meaning.
The following table shows the values that the six fields in the cron expression can take and the special characters supported.
(2) User tags (crowd tags): the label is a keyword for describing information, and the label can be used for describing the preference of the user to the article or the behavior habit information of the user.
The following provides a more detailed description of the embodiments of the present application. Referring to fig. 1 to 3, a first aspect of the present application provides an embodiment of a window pushing method, including:
100. and generating preset pushing time of each window to be pushed and user label information related to each window to be pushed.
Here, for each window to be pushed, the preset pushing time and the user tag information may be artificially defined, or may be automatically generated in combination with historical experience.
In a specific embodiment, the process of generating the preset push time of each window to be pushed includes:
counting heat index values of the windows to be pushed at different historical time points;
and generating preset pushing time of each window to be pushed according to the historical time point corresponding to the heat index value meeting the heat index condition of each window to be pushed. The heat index condition may specifically be a highest heat index value in a history period of the window to be pushed, or may also be a heat index value of top K in the history period, where K is a preset integer greater than or equal to 2. In an actual situation, the popularity index value may specifically be the number of times (or called a click rate) that a user clicks to enter browsing or collecting attention in a history experience that a certain window to be pushed has been pushed and displayed before. It should be noted that the historical time point may be a time point within a certain time period, and taking the time period as a day as an example, the historical time point may be eight am, three pm, and the like. By means of the method, the generated preset pushing time can be guaranteed to correspond to higher heat in historical experience, and therefore the accuracy of window pushing is improved.
In a specific embodiment, the process of generating the user tag information associated with each window to be pushed includes:
counting a plurality of normal history user terminals to which each window to be pushed is pushed within a history period of time; the normal history user side is used for representing the history user side which executes normal operation on the pushed window to be pushed;
and carrying out user label analysis processing on the user attribute information of a plurality of normal historical user ends corresponding to each window to be pushed so as to generate user label information associated with each window to be pushed. For example, user tags include, but are not limited to, user gender, user scholarness, user age, user occupation, address of residency, hobbies, cost budget rating of the user for products to be purchased, and yearly total of purchased products.
Here, the normal operation is also called a forward operation, for example, the normal operation may be an operation in which a window is clicked in or collected by a user side. For each window to be pushed, after counting a plurality of corresponding normal history user sides, performing user label analysis processing on the user attribute information of the normal history user sides to obtain user label information associated with the window to be pushed. The user attribute information includes a plurality of "user tag-tag value" (e.g., "user sex-male") combinations, and the user tag analysis processing described above may be the "user tag-tag value" combination with the highest statistical occurrence frequency or top K, and is added to the user tag information associated with the window to be pushed. By the method, the target audiences of the windows to be pushed can be determined, and the characteristics which are embodied in a centralized manner by the target audiences are added into the user label information.
101. And acquiring preset pushing time of each window to be pushed and user label information associated with each window to be pushed.
Because different users have differences in basic information (such as academic history, age and occupation) or user behaviors (interests, hobbies, cost budget and expectation of products to be purchased and annual total amount of purchased products), in order to select a product information window meeting the needs of the user, after receiving a window display request which is sent by a user side and carries user attribute information, the preset push time of each window to be pushed and user label information related to each window to be pushed need to be acquired. The window to be pushed is used for displaying product information (such as credit product information), and specifically can be a pop-up window with a luxuriant drawing and text; the preset pushing time of each window to be pushed can be specifically set and recorded in the form of a character string cron expression, and the later period of the preset pushing time in the cron form can be analyzed into the style (for example, 11:00:00) of the current time of the system for time comparison; the user label information of the window to be pushed can be specifically used for describing the characteristics of consumer groups suitable for the products in the window; the client may specifically be H5, APP or WEB.
102. Selecting at least one alternative push window satisfying the push time condition and the user attribute information condition.
Based on the pushing time of the windows to be pushed and the consideration of the user label information, after acquiring the preset pushing time of each window to be pushed and the user label information associated with each window to be pushed, selecting at least one alternative pushing window of which the preset pushing time meets the pushing time condition and the user label information meets the user attribute information condition from each window to be pushed; in other words, time comparison (or called time check) and user information comparison (or called crowd tag screening) are required to determine the alternative push window. For example, when the gender of the user in the user attribute information is identified as female, the alternative push window for selection may be a product information window more suitable for female. In practical application, the specific sequence of executing the time comparison process and the user information comparison process is not limited, as long as the alternative push window meeting the push time condition and the user attribute information condition can be determined.
In a specific embodiment, the push time condition may be a target push time period, and the target push time period may be preset, for example, if the target push time period is a time period starting from the current time and having a duration of a preset duration, the preset push time meeting the push time condition means that the preset push time is within the target push time period.
In a specific embodiment, the condition that the user tag information satisfies the user attribute information condition may be: and the matching degree between the user label information and the user attribute information meets the matching degree condition. The matching degree between the user tag information and the user attribute information is equal to the number of the same "user tag-tag value" combinations in the user tag information and the user attribute information, or the total number of the "user tag-tag value" combinations in the user tag information and the user attribute information (on the premise of not repeating), and the matching degree condition may be that the matching degree is the highest, the matching degree is greater than the matching degree threshold, or the matching degree is located at top K.
103. And calculating the total pushed points of each alternative pushed window in the at least one alternative pushed window.
In a specific embodiment, the specific implementation process of step 103 includes:
calculating a total pushed and selected score of each alternative pushed window according to at least one of a product score (or called a weight ratio) of each alternative pushed window in at least one alternative pushed window and a user score; the product score is calculated according to a weight score of a first product label, the first product label comprises one or more of a promotion rate, a product attribute, a shelf life and a product reaching standard rate of a product corresponding to the alternative push window, and the product attribute specifically comprises one or more of a money drawing speed, an interest rate and a term of the credit product.
The user score is calculated according to the number of abnormal operations and the number of normal operations, the number of abnormal operations is the number of times that the abnormal operations are executed in the alternative push window within a history period of time, and the number of normal operations is the number of times that the normal operations are executed in the alternative push window within the history period of time.
Illustratively, the total pushed score (product score) of a certain candidate push window under each first product label is (the weight ratio of the first product label a × a + the weight ratio of the first product label B × B + the weight ratio of the first product label C × C)/the number of first product labels participating in the weight calculation.
Illustratively, the total pushed score is calculated from the product score and the user score of a certain candidate pushing window, namely product score × product score weight + user score × user score weight.
In a specific embodiment, the type of the abnormal operation is that the alternative push window is clicked by the user end to close or complain; the normal operation type is that the alternative push window is clicked by the user side to enter or be collected.
1031. And updating the total pushed points of the alternative pushing windows with the same values.
In a specific embodiment, the multiple candidate push windows with the same score in the total score pushed in step 103 may be subjected to window filtering processing by the added second product label, specifically, only the same score appearing in the highest pushed total score (referred to as the highest common score for short, and refers to multiple parallel highest scores appearing in the pushed total score list) may be processed, or all the same scores may be processed, and the specific process includes:
acquiring a second product label of the alternative push window with the same score, wherein the second product label is a difference label different from the first product label (such as good product score);
obtaining a weight score of a second product label associated with the alternative push window with the same score;
updating the total pushed and selected scores of the alternative pushing windows with the same score according to the weight scores corresponding to all product labels associated with the alternative pushing windows with the same score; wherein all of the product labels include a first product label and a second product label.
It can be seen that the purpose of step 1031 is to eliminate the influence of the equivalence value in step 103 on the subsequent selection of the target push window, in short, to ensure that a limited number of target push windows can be determined finally.
104. And determining a target push window from at least one alternative push window according to the ordering of the push total scores.
For example, according to the ranking of the total push points from high to low, a target push window is determined from at least one candidate push window, for example, the candidate push window corresponding to the highest total push point is selected as the target push window, and the candidate push window corresponding to the total push point of top K is selected as the target push window.
Taking the case that the alternative push window corresponding to the highest total push score is selected to serve as the target push window as an example, as for step 103, if there are more than two (parallel highest scores) highest scores, any alternative push window corresponding to the highest same score can be directly determined to serve as the target push window; or, in step 1031, after updating the total election score with the same score, correspondingly substituting the updated score into the original ranking position of the initial total election score ranking table formed in step 103, checking whether the original maximum ranking position includes multiple update scores, if so, determining an alternative push window corresponding to the maximum value (if the maximum score still exists, step 1031 may be repeated until the only maximum value appears) in the multiple update scores as the target push window, and if not, directly determining that the alternative push window corresponding to the original maximum ranking position is the target push window. Of course, for the only highest score in the initial pushed total sorting table, it can be directly determined that the alternative push window corresponding to the highest score is the target push window.
105. And pushing the target push window to the user side.
Here, the screened target pushing window can be immediately pushed to the user side, and can also be pushed according to the preset pushing time corresponding to the target pushing window.
For example, if the current time point reaches the preset pushing time corresponding to the target pushing window, the target pushing window is pushed to the user side, so that the user side displays the target pushing window at the current time point.
Or if the current time point is earlier than the preset pushing time corresponding to the target pushing window, pushing the target pushing window to the user side so that the user side stores the target pushing window, and displaying the target pushing window when the current time point reaches the preset pushing time corresponding to the target pushing window, so that the success rate and the response speed of window pushing can be improved; under the condition, the response of the window display request newly sent by the user side is stopped before the current time point reaches the preset push time corresponding to the target push window, so that repeated occupation and time consumption of system resources are avoided.
It should be noted that, if a user only supports displaying one window at a future time, in order to avoid bad experience caused by multi-window conflict display, the highest score herein specifically refers to the maximum score (including the situation of updating the pushed total score) that is finally and uniquely determined in each pushed total score, so that the user displays a unique product information window at a future time point; of course, if the ue supports displaying multiple windows at a future time, multiple candidate push windows with the highest common score all have a chance to be pushed and displayed.
In practical applications, the main body for executing the above operations may be the user end indicated in steps 100 to 105, or all history user ends that are pushed. Therefore, according to the method and the device for selecting the credit product, the optimal product information window (target pushing window) which is most suitable for the user requirements can be comprehensively selected through three selecting conditions of pushing time, the user label and the total selecting points, and the credit product displayed by the window is also the product which is most suitable for the user in comparison, so that more convenient, effective and targeted consumption selection is provided for the user, and the user experience is improved.
In summary, the embodiment of the application can use the characteristics of flexible horizontal and vertical combination and simple grammar of the cron expression to write any time point needing to trigger window pushing by the cron expression, thereby realizing finer granularity and more convenient time management of the operation window and simplifying the workload of managers. In addition, through a plurality of selection conditions such as the pushing time, the user label and the total selection score, the comprehensively selected target pushing window and the displayed product can efficiently fit with the user requirements, and the user experience is improved.
Referring to fig. 4, a second aspect of the present application provides an embodiment of a window pushing system, including:
an obtaining unit 401, configured to obtain preset pushing time of each window to be pushed and user tag information associated with each window to be pushed after receiving a window display request carrying user attribute information sent by a user side, where the window to be pushed is used for displaying product information;
a processing unit 402, configured to select, in each to-be-pushed window, at least one alternative pushing window in which preset pushing time meets a pushing time condition and user tag information meets a user attribute information condition;
the processing unit 402 is further configured to calculate a total pushing score of each alternative pushing window in the at least one alternative pushing window, and determine a target pushing window from the at least one alternative pushing window according to a ranking of the total pushing scores;
a sending unit 403, configured to push the target push window to the user side.
In this embodiment of the application, operations executed by each unit of the window pushing system are similar to the operations described in the foregoing first aspect or any specific method embodiment of the first aspect, and details are not repeated here.
Referring to fig. 5, a window pushing apparatus 500 according to an embodiment of the present disclosure may include one or more Central Processing Units (CPUs) 501 and a memory 505, where the memory 505 stores one or more applications or data.
The central processing unit 501 may perform the operations performed by the foregoing first aspect or any specific method embodiment of the first aspect, which are not described in detail herein.
It should be understood that, in the various embodiments of the present application, the size of the serial number of each step does not mean the execution sequence, and the execution sequence of each step should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and there may be other divisions when actually implementing, for example, a plurality of units or components may be combined or integrated into another system or apparatus, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in the form of a software product (computer program product) stored in a storage medium, and includes several instructions for causing a computer device (which may be a personal computer, a service server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and the like.
Claims (10)
1. A window pushing method is characterized by comprising the following steps:
after receiving a window display request which is sent by a user side and carries user attribute information, acquiring preset push time of each window to be pushed and user label information related to each window to be pushed, wherein the window to be pushed is used for displaying product information;
selecting at least one alternative push window with preset push time meeting the push time condition and user label information meeting the user attribute information condition from the windows to be pushed;
calculating the total push-select score of each alternative push window in the at least one alternative push window, and determining a target push window from the at least one alternative push window according to the sequence of the total push scores;
and pushing the target pushing window to the user side.
2. The window pushing method according to claim 1, wherein the calculating a total score of the push of each of the at least one alternative push window comprises:
calculating a total pushed score of each alternative pushed window according to at least one of the product score and the user score of each alternative pushed window in the at least one alternative pushed window;
the product score is obtained by calculation according to a weight score of a first product label, wherein the first product label comprises one or more of promotion rate, product attribute, shelf life and product standard reaching rate of a product corresponding to the alternative pushing window;
the user score is calculated according to the number of abnormal operations and the number of normal operations, the number of abnormal operations is the number of times that the abnormal operations are executed in the alternative push window within a history period of time, and the number of normal operations is the number of times that the normal operations are executed in the alternative push window within the history period of time.
3. The window pushing method according to claim 2, wherein after the calculating of the total push score of each of the at least one alternative push window, and before the determining of the target push window from the at least one alternative push window according to the ranking of the total push scores, the method further comprises:
if more than two identical values exist in each total pushing score, acquiring a second product label of an alternative pushing window with the identical values, wherein the second product label is a difference label different from the first product label;
obtaining a weight score of a second product label associated with the alternative push window with the same score;
updating the total pushed and selected scores of the alternative pushed windows with the same score according to the weight scores corresponding to all product labels associated with the alternative pushed windows with the same score; wherein the all product tags include the first product tag and the second product tag.
4. The window pushing method according to claim 1, wherein before obtaining the preset pushing time of each window to be pushed, the method further comprises:
counting heat index values of the windows to be pushed at different historical time points;
and generating preset pushing time of each window to be pushed according to the historical time point corresponding to the heat index value meeting the heat index condition of each window to be pushed.
5. The window pushing method according to claim 1, wherein before obtaining the user tag information associated with each window to be pushed, the method further comprises:
counting a plurality of normal history user terminals to which each window to be pushed is pushed within a history period of time; the normal history user side is used for representing the history user side which executes normal operation on the pushed window to be pushed;
and carrying out user label analysis processing on the user attribute information of a plurality of normal historical user ends corresponding to each window to be pushed so as to generate user label information associated with each window to be pushed.
6. The window pushing method according to any one of claims 1 to 5, wherein the pushing the target push window to the user side includes:
any one of the following processes is performed:
if the current time point reaches the preset pushing time corresponding to the target pushing window, pushing the target pushing window to the user side so that the user side can display the target pushing window at the current time point;
if the current time point is earlier than the preset pushing time corresponding to the target pushing window, pushing the target pushing window to the user side so that the user side stores the target pushing window, and displaying the target pushing window when the current time point reaches the preset pushing time corresponding to the target pushing window.
7. The window pushing method of claim 6, wherein if the current time point is earlier than a preset pushing time corresponding to the target pushing window, the method further comprises, after pushing the target pushing window to the user side:
and stopping responding to the window display request newly sent by the user side before the current time point reaches the preset push time corresponding to the target push window.
8. A window pushing system, comprising:
the system comprises an acquisition unit, a display unit and a display unit, wherein the acquisition unit is used for acquiring preset pushing time of each window to be pushed and user label information related to each window to be pushed after receiving a window display request which is sent by a user side and carries user attribute information, and the window to be pushed is used for displaying product information;
the processing unit is used for selecting at least one alternative push window of which the preset push time meets the push time condition and the user label information meets the user attribute information condition from the windows to be pushed;
the processing unit is further configured to calculate a total push score of each alternative push window in the at least one alternative push window, and determine a target push window from the at least one alternative push window according to a ranking of the total push scores;
and the sending unit is used for pushing the target pushing window to the user side.
9. A window pushing device, comprising:
the system comprises a central processing unit, a memory and an input/output interface;
the memory is a transient memory or a persistent memory;
the central processor is configured to communicate with the memory and execute the operations of the instructions in the memory to perform the method of any of claims 1 to 7.
10. A computer-readable storage medium comprising instructions which, when executed on a computer, cause the computer to perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210320225.XA CN114638649A (en) | 2022-03-29 | 2022-03-29 | Window pushing method, system and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210320225.XA CN114638649A (en) | 2022-03-29 | 2022-03-29 | Window pushing method, system and related device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114638649A true CN114638649A (en) | 2022-06-17 |
Family
ID=81952700
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210320225.XA Pending CN114638649A (en) | 2022-03-29 | 2022-03-29 | Window pushing method, system and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114638649A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107360222A (en) * | 2017-06-30 | 2017-11-17 | 广东欧珀移动通信有限公司 | Commodity information push method, device, storage medium and server |
| CN107767227A (en) * | 2017-10-31 | 2018-03-06 | 深圳春沐源控股有限公司 | Method of Commodity Recommendation, the commercial product recommending system of online shopping mall |
| CN107862553A (en) * | 2017-11-15 | 2018-03-30 | 平安科技（深圳）有限公司 | Advertisement real-time recommendation method, device, terminal device and storage medium |
| CN108920596A (en) * | 2018-06-27 | 2018-11-30 | 广东亿迅科技有限公司 | A kind of personalized recommendation algorithm and terminal |
| CN110458637A (en) * | 2019-06-19 | 2019-11-15 | 中国平安财产保险股份有限公司 | Product method for pushing and its relevant device neural network based |
| CN111026969A (en) * | 2019-12-18 | 2020-04-17 | 腾讯科技（深圳）有限公司 | Content recommendation method and device, storage medium and server |
| CN112381627A (en) * | 2021-01-14 | 2021-02-19 | 北京崔玉涛儿童健康管理中心有限公司 | Commodity scoring processing recommendation method and device under child-care knowledge |
| CN112839063A (en) * | 2019-11-04 | 2021-05-25 | 腾讯科技（深圳）有限公司 | Message pushing method, message display method, storage medium and computer equipment |
-
2022
- 2022-03-29 CN CN202210320225.XA patent/CN114638649A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107360222A (en) * | 2017-06-30 | 2017-11-17 | 广东欧珀移动通信有限公司 | Commodity information push method, device, storage medium and server |
| CN107767227A (en) * | 2017-10-31 | 2018-03-06 | 深圳春沐源控股有限公司 | Method of Commodity Recommendation, the commercial product recommending system of online shopping mall |
| CN107862553A (en) * | 2017-11-15 | 2018-03-30 | 平安科技（深圳）有限公司 | Advertisement real-time recommendation method, device, terminal device and storage medium |
| CN108920596A (en) * | 2018-06-27 | 2018-11-30 | 广东亿迅科技有限公司 | A kind of personalized recommendation algorithm and terminal |
| CN110458637A (en) * | 2019-06-19 | 2019-11-15 | 中国平安财产保险股份有限公司 | Product method for pushing and its relevant device neural network based |
| CN112839063A (en) * | 2019-11-04 | 2021-05-25 | 腾讯科技（深圳）有限公司 | Message pushing method, message display method, storage medium and computer equipment |
| CN111026969A (en) * | 2019-12-18 | 2020-04-17 | 腾讯科技（深圳）有限公司 | Content recommendation method and device, storage medium and server |
| CN112381627A (en) * | 2021-01-14 | 2021-02-19 | 北京崔玉涛儿童健康管理中心有限公司 | Commodity scoring processing recommendation method and device under child-care knowledge |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8156138B2 (en) | System and method for providing targeted content | |
| US8543518B2 (en) | Deducing shadow user profiles for ad campaigns | |
| US8341101B1 (en) | Determining relationships between data items and individuals, and dynamically calculating a metric score based on groups of characteristics | |
| US9639846B2 (en) | System and method for providing targeted content | |
| US20160189201A1 (en) | Enhanced targeted advertising system | |
| US20160189207A1 (en) | Enhanced online content delivery system using action rate lift | |
| CN112733042A (en) | Recommendation information generation method, related device and computer program product | |
| US10559004B2 (en) | Systems and methods for establishing and utilizing a hierarchical Bayesian framework for ad click through rate prediction | |
| US11887156B2 (en) | Dynamically varying remarketing based on evolving user interests | |
| CN113312512B (en) | Training method, recommending device, electronic equipment and storage medium | |
| CN111104590A (en) | Information recommendation method, device, medium and electronic equipment | |
| CN112839063A (en) | Message pushing method, message display method, storage medium and computer equipment | |
| CN111552835A (en) | File recommendation method and device and server | |
| US20110251889A1 (en) | Inventory clustering | |
| US8478702B1 (en) | Tools and methods for determining semantic relationship indexes | |
| US20190087852A1 (en) | Re-messaging with alternative content items in an online remarketing campaign | |
| CN112818230A (en) | Content recommendation method and device, electronic equipment and storage medium | |
| US9928523B2 (en) | System and method for booking an advertisement to an impression using a targeting dimension dictionary | |
| JP5603678B2 (en) | Demand forecasting apparatus and demand forecasting method | |
| CN113032671A (en) | Content processing method, content processing device, electronic equipment and storage medium | |
| CN112200602A (en) | Neural network model training method and device for advertisement recommendation | |
| CN108241699B (en) | Method and device for pushing information | |
| CN116627564A (en) | Information display method, device, equipment and storage medium | |
| US20190114673A1 (en) | Digital experience targeting using bayesian approach | |
| CN114638649A (en) | Window pushing method, system and related 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 |