CN114840779A - Object display method and display device - Google Patents
Object display method and display device Download PDFInfo
- Publication number
- CN114840779A CN114840779A CN202110139008.6A CN202110139008A CN114840779A CN 114840779 A CN114840779 A CN 114840779A CN 202110139008 A CN202110139008 A CN 202110139008A CN 114840779 A CN114840779 A CN 114840779A
- Authority
- CN
- China
- Prior art keywords
- click
- objects
- click rate
- rate difference
- candidate
- 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 55
- 230000002452 interceptive effect Effects 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 230000010365 information processing Effects 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 7
- 230000003993 interaction Effects 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000009499 grossing Methods 0.000 description 3
- 238000005034 decoration Methods 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9538—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G06F3/04842—Selection of displayed objects or displayed text elements
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Human Computer Interaction (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a display method and a display device of an object, and belongs to the technical field of information processing. The method comprises the following steps: acquiring a plurality of candidate first objects, wherein each first object is an object appearing in one or more user interfaces corresponding to specified users; acquiring a first click number of a first object in a first preset time period and a second click number of a specified user on a second object; determining the click rate difference ratio of the first object according to the first click number and the second click number, wherein the click rate difference ratio is used for representing the difference between the click heat of the first object and the click heat of the second object; and selecting a target first object from the candidate plurality of first objects according to the click rate difference ratio of the first object for displaying. The method and the device solve the technical problem that the object is inaccurately recommended due to the fact that the actual popularity of the object is difficultly reflected by the click rate of the object due to long tail distribution in the prior art, and improve the rationality of the result of recommending according to the object click rate sequence.
Description
Technical Field
The invention relates to the technical field of information processing, in particular to a display method and a display device of an object.
Background
In the APP, which recommended objects are popular and which are unpopular are usually judged according to the statistical historical click rate of each recommended object, and then an object recommendation or operation strategy of the APP is adjusted, for example, objects in the APP include files, products and the like. For example, the recommendation system includes an object a and an object B, where the object a is exposed 100 times, clicked 10 times, the object B is exposed 100w times, and clicked 5w times, and according to a calculation formula of "click rate ═ click/exposure", the click rate of a is 0.1, the click rate of B is 0.05, and the click rate of a is much higher than that of B, but obviously, the object a is exposed to fewer objects, and the calculation result has a large error. The natural gap of data exposure caused by the long tail problem of the recommendation system data cannot be made up by the data side, so that the direct calculation by using the exposure click data is not practical.
In the prior art, the calculation of the click rate is optimized by using a Bayesian smoothing scheme, and the algorithm mainly approximates the posterior distribution by using the integral prior distribution and likelihood distribution of data, so that the click rate error is repaired to a certain extent in terms of implementation effect. However, the core of the bayesian smoothing scheme is that data distribution is assumed to be consistent, in an actual situation, because natural deviation exists in a recommended system algorithm, natural inconsistency exists in exposure of each object, so that the bayesian smoothing scheme is difficult to achieve an ideal effect, and no obvious effect exists in the case of large data deviation.
Aiming at the problem that the actual popularity of an object is difficult to reflect due to the long tail distribution in the prior art, so that the recommendation of the object is inaccurate, an effective solution is not provided at present.
Disclosure of Invention
The embodiment of the invention provides an object display method and device, and aims to at least solve the technical problem that in the prior art, due to long tail distribution, the actual heat of an object is difficult to reflect by the click rate of the object, so that the object is not recommended accurately.
According to an aspect of an embodiment of the present invention, there is provided an object display method including: acquiring a plurality of candidate first objects, wherein each first object is an object appearing in one or more user interfaces corresponding to specified users; acquiring a first click number of a first object in a first preset time period and a second click number of a second object by a designated user, wherein the second object is an object appearing in all user interfaces; determining a click rate difference ratio of the first object according to the first click number and the second click number, wherein the click rate difference ratio is used for representing the difference between the click heat of the first object and the click heat of the second object; and selecting a target first object from the candidate plurality of first objects according to the click rate difference ratio of the first object for displaying.
According to another aspect of the embodiments of the present invention, there is also provided a display apparatus of an object, including: the object acquisition module is used for acquiring a plurality of candidate first objects, wherein each first object is an object appearing in one or more user interfaces corresponding to the specified users; the number acquisition module is used for acquiring a first click number of the first object in a first preset time period and a second click number of a designated user on a second object, wherein the second object is an object appearing in all user interfaces; the determining module is used for determining the click rate difference ratio of the first object according to the first click number and the second click number, wherein the click rate difference ratio is used for representing the difference between the click heat of the first object and the click heat of the second object; and the selection module is used for selecting a target first object from the candidate first objects according to the click rate difference ratio of the first object for displaying.
According to another aspect of embodiments of the present invention, there is also provided a computer storage medium having stored thereon a plurality of instructions adapted to be loaded by a processor and to perform the method steps of any one of the above.
According to another aspect of the embodiments of the present invention, there is also provided an intelligent interactive tablet, including: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform any of the method steps described above.
In the embodiment of the invention, the number of the overlapped users is determined by taking the second objects which can be seen by all the users as reference, the click rate difference ratio of the first object is calculated according to the click number of the overlapped users to the first object and the second object, and the recommended objects are determined according to the click rate difference ratio sequence of different first objects. Because the click rate difference is the relative click rate of the first object to the second object in the common user group, compared with the recommendation method based on object click rate sorting, the method has smaller errors and higher stability, and the situation that some prediction deviations and sorting relations are different greatly can be positioned through the difference relation between the click heat degrees of the first object and the second object, so that the result of sorting and recommending the objects is more reasonable, and the problem that the actual heat degrees of the objects are difficult to reflect due to long tail distribution in the prior art, and the object recommendation is inaccurate is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention and do not constitute a limitation of the invention. In the drawings:
FIG. 1 is a flowchart of a method of displaying an object according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a display device for an object according to an embodiment of the present invention;
fig. 3 is a schematic diagram of an alternative smart interactive tablet in accordance with embodiments of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
At present, in the APP, a display method for objects predicts which objects are liked by a user to the end according to the click rate prediction ordering of the objects, and the predicted objects are used as a recommendation strategy of the objects. For example, the object in the APP can be a file object, and a file theme which is interested by the user is estimated according to the click rate of the file object; the object in the APP can also be an article, and the type of the object liked by the user is estimated according to the click rate of the object. The existing calculation formula of the click rate of the object is as follows: the click rate is click/exposure, and the click rate of different objects can be calculated according to the formula, so that the popularity of the objects can be estimated. For example, table 1 provides exposure and click data of the object A, B, C, D, E in a group of APPs, and table 1 counts exposure data of each object, the number of times each object is clicked, and the click rate obtained by calculation according to the above calculation formula of the click rate (click rate ═ click/exposure).
TABLE 1
| Object | Exposure method | Click on | Click rate |
| A | 400000 | 50000 | 0.125 |
| B | 120000 | 10000 | 0.083 |
| C | 40000 | 3000 | 0.075 |
| D | 60000 | 8000 | 0.133 |
| E | 5000 | 800 | 0.16 |
The click rates of the objects A-E are sorted, and the objects with the click rates from top to bottom are sequentially as follows: e > D > A > B > C, objects E and D are objects with high click rate, however, the exposure data of the objects C, D and E are less, the click rate calculation error is large, the sorting credibility is low, the sorting fluctuation of cold objects with small partial exposure and large click is large, and the actual heat of the objects is difficult to reflect by the click rate of the objects. For example, the objects a to E are item recommendation objects, and although the click rate of the object E is ranked first, if the item represented by the object E is taken as a key recommendation product, the quality and popularity of the product E are difficult to guarantee. The invention provides the following embodiments to solve the problem that in the prior art, due to long tail distribution, the actual popularity of an object is difficult to reflect by the click rate of the object, so that the recommendation of the object is inaccurate.
Example 1
In accordance with an embodiment of the present invention, there is provided an embodiment of a method for displaying an object, it should be noted that the steps illustrated in the flowchart of the accompanying drawings may be performed in a computer system such as a set of computer-executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than here.
Fig. 1 is a flowchart of a display method of an object according to an embodiment of the present invention, as shown in fig. 1, the method including the steps of:
step S101, a plurality of candidate first objects are obtained, where each first object is an object appearing in one or more user interfaces corresponding to a designated user.
The first object is understood as an object exposed to a specified user according to a preset recommendation strategy, for example, if the preset recommendation strategy is to recommend according to a user attention topic, the first object is an object related to the user attention topic, and because the user attention topics are different, the first object is exposed only on user interfaces of some users, for example, among 10 users, only 3 users pay attention to a topic corresponding to the first object, the 3 users are specified users, and the first object is exposed only on user interfaces of 3 specified users. The user interface of the appointed user can be an intelligent terminal APP interface of the appointed user, and the appointed user can browse the exposed object through the APP interface.
Step S102, acquiring a first click number of the first object in a first preset time period and a second click number of a second object by a designated user, wherein the second object is an object appearing in all user interfaces.
The first preset time is a time interval in which the number of clicks needs to be counted, for example, the number of clicks in a certain day is counted.
The second object is understood to be an object that is shown positioned on top in the user interface and can be seen by all users, thus designating a user as an overlapping user who can see not only the second object but also the first object. For example, if the object a counted in table 1 is the second object, the total number of users is 400000, the object a can be seen by all the exposed users, the exposure amount of the object E is 5000, that is, 5000 users can see the object E, and the 5000 users can certainly see the object a, so that the 5000 users are the designated users, the number of clicks 800 of the 5000 users on the object E is the first number of clicks, and the number of clicks of the 5000 users on the object a is the second number of clicks.
It should be noted that there may be a plurality of objects that can be seen by all users, and any one of them may be selected as the second object in this implementation.
And S103, determining a click rate difference ratio of the first object according to the first click number and the second click number, wherein the click rate difference ratio is used for representing the difference between the click heat of the first object and the click heat of the second object.
Due to the long tail effect, the objects are not accurately recommended only according to the click rate sorting, so that the click rate difference ratio is provided in the scheme, the click rate of the second objects which can be seen by only part of users is corrected by using the click rate difference ratio, and the more accurate object heat condition can be obtained according to the sorting of the click rate difference ratio.
In an alternative embodiment, the click rate difference ratio may be calculated by: (first number of clicks-second number of clicks)/number of overlapped users, by which the click rate difference ratio of the first object can be obtained.
Step S104, selecting and displaying a target first object from a plurality of candidate first objects according to the click rate difference ratio of the first object.
Specifically, for the plurality of first objects, the click rate difference ratio of each first object is obtained according to the steps, and the target first object is selected as the recommendation object according to the ranking of the click rate difference ratios of the plurality of first objects. The display indicates that the target first object is displayed at the specified position of the APP and is used as the recommendation object, for example, the recommendation object is displayed at the top position of the front page of the APP.
The number of target first objects may be set by the user, for example, the target first object may be a first object having the highest click rate difference ratio, or may be a plurality of first objects ranked first after ranking according to the click rate difference ratio.
In an optional implementation, table 2 provides statistical results of exposure and click data of objects a to E in a certain day by a certain application program, in table 2, the object a is set as a second object, that is, an object that can be seen by all users, the objects B to E are the first objects, the click rate in table 2 is obtained according to click/exposure calculation of each object, overlapping exposure clicks are the number of clicks of the object a set by a designated user of each object, for example, overlapping exposure clicks of the object B are the number of clicks of the exposure user of the object B on the object a, and the click rate difference ratio of each object is calculated by:
click rate difference ratio (click-overlap exposure click)/number of overlapping users.
The number of the overlapping users is the above-mentioned designated user, that is, the user can see the object a and the object to be calculated at the same time, for example, the number of the overlapping users of the object B is 120000, the click rate difference ratio of the object B is (click of B-overlap exposure click of B)/the number of the overlapping users of B is (10000-.
TABLE 2
According to the click rate difference ratio of each object in the table 2, the click rate difference ratio of each object is subjected to descending order arrangement to obtain: d > C > A > B > E, and under the condition that one object is selected as a recommended object, the object D is determined to be the target first object, namely the object D is used as the recommended object; in the case where three objects are selected as the recommendation objects, the objects D, C and a are determined to be the above-described target first objects, that is, the objects D, C and a are the recommendation objects.
In this embodiment, the number of overlapping users is determined by using the second objects visible to all users as a reference, the click rate difference ratio of the first object is calculated according to the number of clicks of the overlapping users on the first object and the second object, and the recommended objects are determined according to the click rate difference ratio sequences of different first objects. Because the click rate difference is the relative click rate of the first object to the second object in the common user group, compared with the recommendation method based on single-object click rate sorting, the method has smaller error and higher stability, and the situation that some prediction deviation and the sorting relation have larger difference can be positioned through the difference relation between the click heat degrees of the first object and the second object, so that the result of sorting and recommending the objects is more reasonable, and the problem that the actual heat degree of the objects is difficult to reflect due to long tail distribution in the prior art, and the recommendation of the objects is inaccurate is solved.
As an alternative embodiment, determining the click rate difference ratio of the first object according to the first click number and the second click number includes: acquiring a difference value between the first click number and the second click number; determining a ratio of the difference value to the number of the specified users as a click rate difference ratio of the first object.
Specifically, the click rate difference ratio of the first object may be calculated by: (the first number of clicks-the second number of clicks)/the number of overlapping users, the click rate difference ratio of the first object can be obtained by the calculation method, wherein the overlapping users are the designated users.
As an alternative embodiment, before obtaining the candidate plurality of first objects, the method further includes: the method comprises the steps of obtaining a recall strategy of a first object, wherein the recall strategy is used for indicating a plurality of dimensions for recalling the first object, and the plurality of dimensions at least comprise click popularity.
The multiple dimensions may include click popularity, user preferences, historical collections, and the like. The recall strategy is used for screening out a set of objects to be recommended for a user, and can comprise multiple dimensions, and the recall strategy of the multiple dimensions is adopted to determine the first object, so that the recall accuracy can be improved. For example, after the objects to be recommended are screened out from the user according to the preference of the user, secondary screening is performed on the screened preference objects according to the click popularity to obtain a recall object set.
As an alternative embodiment, obtaining a candidate plurality of first objects includes: recalling the candidate first objects according to the click popularity, wherein the step of recalling the candidate first objects according to the click popularity comprises the following steps: acquiring click heat parameters of a plurality of first objects in a second preset time period, wherein the click heat parameters are click rates of the first objects in the second preset time period; and sequencing the plurality of first objects from high to low according to the click heat parameter to obtain a plurality of first objects with the first n first objects as candidates.
In an actual recall strategy, a click rate estimation and click rate difference ratio combined method is usually adopted to screen out a set of objects to be recommended so as to improve the recall accuracy. For example, as table 2 provides the click rate of objects a-E within a certain day, E > D > a > B > C are ranked according to their click rate from high to low, and in the case where n is 3, E, D, A of top 3 is taken as the first object candidate.
The value of n is determined according to the actual recall strategy and the number of the objects to be recommended, and can be different values in different application scenes, which is not limited here.
As an alternative embodiment, selecting a target first object from a plurality of candidate first objects for display according to the click rate difference ratio of the first object, includes: acquiring the number m of preset target first objects; sorting the candidate first objects from high to low according to the click rate difference ratio, and acquiring the first m first objects as target first objects; the target first object is displayed.
For example, the click rate difference ratios of the objects are sorted in descending order according to the click rate difference ratio of the objects in table 2 to obtain: d > C > a > B > E, in the case where m is 3, it is determined that the objects D, C and a are the above-described target first objects, that is, the objects D, C and a are objects to be recommended.
In another alternative embodiment, as shown in table 2, E > D > a > B > C may be obtained according to the click rate of each object in descending order, E, D, A of the top 3 is used as a candidate first object, then D > a > E is obtained according to the click rate difference ratio of E, D, A in descending order, and in case that m is 2, it is determined that D and a in the top order are the target first object.
The value of m is determined according to the number of objects to be recommended, and may be different values in different application scenarios, which is not limited here.
As an alternative embodiment, the method further includes: acquiring a recall strategy of the first object, wherein the recall strategy comprises the number of recalls of the first object through each dimension, and acquiring the preset number m of target first objects, and the method comprises the following steps: acquiring the number of first objects recalled according to click popularity in a recall strategy; and determining the number of the first objects recalled according to the click popularity as the preset number m of the target first objects.
For example, if the number of recalls made for 20 first objects according to the click popularity dimension is 5, the number m of preset target first objects is determined to be 5. In the objects a-E shown in table 2, if the recall policy includes that the number of recalls according to the click popularity is 2, the click rate difference ratios of the objects are sorted in descending order to obtain: d > C > A > B > E, and determining the objects D and C ranked in the top 2 as the target first object.
In the application scene of the teaching application program, the display method of the object can be used for recalling and recommending courses. For example, course recommendation requires recall in multiple dimensions, hot recall is one of recall algorithms in multiple dimensions, exposure of part of courses is more and exposure of a large number of courses is less due to extremely uneven exposure number of courses, and it is inaccurate to recall courses by simply using click popularity as a recall strategy. According to the object recommending method of the embodiment of the invention, firstly, a hot course with larger click purchase amount is locked at the first position of a light course field for fixing, other courses carry out recommendation exposure by using the click rate difference sorting method, and a data platform counts exposure click purchase data every day. After the user slides to the light course column, the hot course fixed at the first position is exposed, the click rate of the hot course is compared with the click rates of all other courses to obtain the click rate difference ratio of each course, the ordering relation of the exposed courses is obtained according to the click rate difference ratio, and the ordering result based on the hot recall can be obtained by utilizing the whole ordering relation. For example, the course 2 exposes part of the users, and the part of the users certainly exposes the course 1, so that the corresponding click rate and conversion rate indexes of the two courses can be calculated by using the overlapped part of the users, and the ordering relation of the two courses is obtained.
Under the condition that a new course is on line in the APP, the relative click rate relationship of the course (namely the click rate difference ratio of the new course to the top-placed hot course) is updated every day, the click rate of a user to a recalled course is estimated by using a click rate estimation model, and then the click rate is corrected by using the calculated click rate difference ratio, so that the deviation of low-frequency course click rate estimation is avoided, and the on-line course recommendation service is biased to recommend the hot course. The situation that the difference between the prediction deviation of the click rate and the sorting relation is large can be positioned through the relation of the click rate difference ratio of the courses, the sorting positions are corrected to enable the courses to be sorted more reasonably, the risk of misarrangement caused by sorting according to the click rate is reduced, and the problem that the error of the click rate of the existing sorting model based on the click rate is large in low-frequency course estimation is solved.
According to the object recommendation method provided by the embodiment, the large exposure of the hot object and the small exposure of the cold object are utilized, the hot object and the cold object exist in a common overlapped user group, the difference of the click rate is calculated by utilizing the difference of the overlapped user group to obtain the click rate difference ratio, and as the recommendations of all the objects are from the same set of recommendation algorithm, the occurring people of each object are integrally distributed according with the algorithm, so that the difference of the click rate can be compared with the people of each object; and the click rate difference ratio is provided and combined with the click rate estimation recall strategy to correct the hot recall strategy, so that the accuracy of user personalized click rate estimation is improved.
Example 2
According to an embodiment of the present invention, there is provided an embodiment of a display apparatus for an object, and fig. 2 is a schematic diagram of the display apparatus for an object according to the embodiment of the present invention, as shown in fig. 2, the apparatus including: an object obtaining module 21, configured to obtain a plurality of candidate first objects, where each first object is an object appearing in one or more user interfaces corresponding to a specified user; the number obtaining module 22 is configured to obtain a first number of clicks of the first object in a first preset time period and a second number of clicks of a second object by a specified user, where the second object is an object appearing in all user interfaces; the determining module 23 is configured to determine a click rate difference ratio of the first object according to the first click number and the second click number, where the click rate difference ratio is used to represent a difference between a click heat of the first object and a click heat of the second object; and the selecting module 24 is used for selecting a target first object from the candidate multiple first objects to display according to the click rate difference ratio of the first object.
As an alternative embodiment, the determining module includes: the difference value obtaining submodule is used for obtaining the difference value between the first click number and the second click number; and the click rate difference ratio determining submodule is used for determining the ratio of the difference value to the number of the specified users as the click rate difference ratio of the first object.
As an alternative embodiment, the apparatus further comprises: the first recall strategy acquisition module is used for acquiring a recall strategy of the first object, wherein the recall strategy is used for indicating a plurality of dimensions for recalling the first object, and the plurality of dimensions at least comprise click popularity.
As an alternative embodiment, the object obtaining module includes: the recalling module is used for recalling the candidate first objects according to the click popularity, and comprises: the parameter obtaining sub-module is used for obtaining click heat parameters of a plurality of first objects in a second preset time period, wherein the click heat parameters are click rates of the first objects in the second preset time period; and the sorting submodule is used for sorting the first objects from high to low according to the click heat parameter and acquiring the first n first objects as candidate first objects.
As an alternative embodiment, the selecting module includes: the number obtaining submodule is used for obtaining the number m of preset target first objects; the target first object obtaining sub-module is used for sorting the candidate first objects from high to low according to the click rate difference ratio and obtaining the first m first objects as target first objects; and the display submodule is used for displaying the target first object.
As an alternative embodiment, the apparatus further comprises: a second recall policy obtaining module, configured to obtain a recall policy of the first object, where the recall policy includes a number of recalls performed on the first object by each dimension, and the number obtaining sub-module includes: the click popularity number obtaining submodule is used for obtaining the number of first objects recalled according to the click popularity in the recall strategy; and the preset number determining submodule is used for determining the number of the recalled first objects according to the click popularity as the preset number m of the target first objects.
In the embodiment, the number of the overlapping users is determined by taking the second objects which can be seen by all the exposure users as reference, the click rate difference ratio of the first object is calculated according to the number of clicks of the overlapping users on the first object and the second object, and the recommended objects are determined according to the click rate difference ratio sequence of different first objects. Because the click rate difference is the relative click rate of the first object to the second object in the common user group, compared with the recommendation method based on single-object click rate sorting, the method has smaller error and higher stability, and the situation that some prediction deviation and the sorting relation have larger difference can be positioned through the difference relation between the click heat degrees of the first object and the second object, so that the result of sorting and recommending the objects is more reasonable, and the problem that the actual heat degree of the objects is difficult to reflect due to long tail distribution in the prior art, and the recommendation of the objects is inaccurate is solved.
Example 3
According to an embodiment of the application, an embodiment of a computer storage medium is provided, the computer storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform the method steps of any of embodiment 1. In the embodiment, the number of the overlapping users is determined by taking the second objects which can be seen by all the exposure users as reference, the click rate difference ratio of the first object is calculated according to the number of clicks of the overlapping users on the first object and the second object, and the recommended objects are determined according to the click rate difference ratio sequence of different first objects. Because the click rate difference is the relative click rate of the first object to the second object in the common user group, compared with the recommendation method based on single-object click rate sorting, the method has smaller error and higher stability, and the situation that some prediction deviation and the sorting relation have larger difference can be positioned through the difference relation between the click heat degrees of the first object and the second object, so that the result of sorting and recommending the objects is more reasonable, and the problem that the actual heat degree of the objects is difficult to reflect due to long tail distribution in the prior art, and the recommendation of the objects is inaccurate is solved.
Example 4
According to an embodiment of the present application, there is provided an intelligent interactive tablet, including: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the method steps of any of the embodiment 1.
Fig. 3 is a schematic diagram of an intelligent interaction tablet according to an embodiment of the present application, where the intelligent interaction tablet includes the interaction device main body and the touch frame, and as shown in fig. 3, the intelligent interaction tablet 1000 may include: at least one processor 1001, at least one network interface 1004, a user interface 1003, memory 1005, at least one communication bus 1002.
Wherein a communication bus 1002 is used to enable connective communication between these components.
The user interface 1003 may include a Display screen (Display) and a Camera (Camera), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.
The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), among others.
The Memory 1005 may include a Random Access Memory (RAM) or a Read-Only Memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable medium. The memory 1005 may be used to store an instruction, a program, code, a set of codes, or a set of instructions. The memory 1005 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the various method embodiments described above, and the like; the storage data area may store data and the like referred to in the above respective method embodiments. The memory 1005 may optionally be at least one memory device located remotely from the processor 1001. As shown in fig. 3, the memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and an operating application of the smart interactive tablet.
In the intelligent interactive tablet 1000 shown in fig. 3, the user interface 1003 is mainly used to provide an input interface for a user to obtain data input by the user; and the processor 1001 may be configured to call an operation application of the smart interactive tablet stored in the memory 1005, and specifically perform any one of the operations in embodiment 1.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. 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, units or modules, and may be in an electrical 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 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 invention 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 invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A method of displaying an object, comprising:
acquiring a plurality of candidate first objects, wherein each first object is an object appearing in one or more user interfaces corresponding to a designated user;
acquiring a first click number of the first object in a first preset time period and a second click number of the second object by the designated user, wherein the second object is an object appearing in all user interfaces;
determining a click rate difference ratio of the first object according to the first click number and the second click number, wherein the click rate difference ratio is used for representing the difference between the click heat of the first object and the click heat of the second object;
and selecting a target first object from the candidate plurality of first objects for display according to the click rate difference ratio of the first object.
2. The method of claim 1, wherein determining the click rate difference ratio for the first object based on the first number of clicks and the second number of clicks comprises:
acquiring a difference value between the first click number and the second click number;
and determining the ratio of the difference value to the number of the specified users as the click rate difference ratio of the first object.
3. The method of claim 1, wherein prior to obtaining the candidate plurality of first objects, the method further comprises: the method comprises the steps of obtaining a recall strategy of a first object, wherein the recall strategy is used for indicating a plurality of dimensions for recalling the first object, and the dimensions at least comprise click popularity.
4. The method of claim 3, wherein obtaining a candidate plurality of first objects comprises: recalling the candidate first objects according to the click popularity, wherein the step of recalling the candidate first objects according to the click popularity comprises the following steps:
acquiring click heat parameters of a plurality of first objects in a second preset time period, wherein the click heat parameters are click rates of the first objects in the second preset time period;
and sequencing the plurality of first objects from high to low according to the click heat parameter to obtain the first n first objects as the candidate plurality of first objects.
5. The method of claim 1, wherein selecting a target first object from the candidate plurality of first objects for display based on the click-through rate difference ratios of the first object comprises:
acquiring the number m of preset target first objects;
sorting the candidate first objects from high to low according to the click rate difference ratio, and acquiring the first m first objects as the target first objects;
and displaying the target first object.
6. The method of claim 5, further comprising: acquiring a recall strategy of a first object, wherein the recall strategy comprises the number of recalls of the first object through each dimension, and acquiring a preset target number m of the first object, and the method comprises the following steps:
acquiring the number of the first objects recalled in the recall strategy according to the click popularity;
and determining the number of the first objects recalled according to the click popularity as the preset number m of the target first objects.
7. A display device for an object, comprising:
the system comprises an object acquisition module, a display module and a display module, wherein the object acquisition module is used for acquiring a plurality of candidate first objects, and each first object is an object appearing in one or more user interfaces corresponding to specified users;
the quantity acquisition module is used for acquiring a first click quantity of the first object in a first preset time period and a second click quantity of the specified user on a second object, wherein the second object is an object appearing in all user interfaces;
the determining module is used for determining a click rate difference ratio of the first object according to the first click number and the second click number, wherein the click rate difference ratio is used for representing the difference between the click heat of the first object and the click heat of the second object;
and the selection module is used for selecting a target first object from the candidate first objects to display according to the click rate difference ratio of the first object.
8. The apparatus of claim 7, wherein the determining module comprises:
a difference value obtaining submodule, configured to obtain a difference value between the first click number and the second click number;
and the click rate difference ratio determining submodule is used for determining that the ratio of the difference value to the number of the specified users is the click rate difference ratio of the first object.
9. A computer storage medium, characterized in that it stores a plurality of instructions adapted to be loaded by a processor and to perform the method steps of any of claims 1 to 6.
10. An intelligent interactive tablet, comprising: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the method steps of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110139008.6A CN114840779A (en) | 2021-02-01 | 2021-02-01 | Object display method and display device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110139008.6A CN114840779A (en) | 2021-02-01 | 2021-02-01 | Object display method and display device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114840779A true CN114840779A (en) | 2022-08-02 |
Family
ID=82561341
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110139008.6A Pending CN114840779A (en) | 2021-02-01 | 2021-02-01 | Object display method and display device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114840779A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117312689A (en) * | 2023-11-29 | 2023-12-29 | 山东阳光普众信息科技有限公司 | Information management platform management analysis method and system, storage medium and intelligent terminal |
-
2021
- 2021-02-01 CN CN202110139008.6A patent/CN114840779A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117312689A (en) * | 2023-11-29 | 2023-12-29 | 山东阳光普众信息科技有限公司 | Information management platform management analysis method and system, storage medium and intelligent terminal |
| CN117312689B (en) * | 2023-11-29 | 2024-02-02 | 山东阳光普众信息科技有限公司 | Information management platform management analysis method and system, storage medium and intelligent terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020048084A1 (en) | Resource recommendation method and apparatus, computer device, and computer-readable storage medium | |
| CN110580649B (en) | Method and device for determining commodity potential value | |
| CN103823908B (en) | Content recommendation method and server based on user preference | |
| US20170098314A1 (en) | Automatic image-based recommendations using a color palette | |
| EP3139288A1 (en) | Item recommendation method and device | |
| US20150379001A1 (en) | Automatic color validation of image metadata | |
| US20150379733A1 (en) | Automatic image-based recommendations using a color palette | |
| EP3161770A1 (en) | Automatic image-based recommendations using a color palette | |
| CN108205768A (en) | Database building method and data recommendation method and device, equipment and storage medium | |
| CN108073578B (en) | Method and system for object recommendation | |
| CN106168980A (en) | Multimedia resource recommends sort method and device | |
| CN110489574B (en) | Multimedia information recommendation method and device and related equipment | |
| CN109902713A (en) | Building recommended method, equipment, storage medium and device based on data analysis | |
| CN105913301A (en) | Bill sharing information processing method and system | |
| CN110874787A (en) | Recommendation model effect evaluation method and related device | |
| KR101567684B1 (en) | Method for selecting recommendation type in product recommeding system | |
| CN109274987A (en) | A kind of video collection sort method, server and readable storage medium storing program for executing | |
| CN111310037A (en) | Household material recommendation method and device and electronic equipment | |
| CN108038758B (en) | Application recommendation method and system and terminal equipment | |
| CN116308657A (en) | Commodity recommendation method and system for digital marketing platform | |
| CN111078997B (en) | Information recommendation method and device | |
| CN110515929B (en) | Book display method, computing device and storage medium | |
| CN114840779A (en) | Object display method and display device | |
| CN114581174A (en) | Recommendation method and device, electronic equipment and storage medium | |
| CN110472143A (en) | A kind of information-pushing method, device, readable storage medium storing program for executing and terminal 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 |