Object display method and display device

Abstract

The present invention discloses a method and device for displaying an object, and belongs to the field of information processing technology. The method comprises: obtaining multiple candidate first objects, each first object being an object that appears in one or more user interfaces corresponding to a specified user; obtaining the first number of clicks on the first object in a first preset time period and the second number of clicks on the second object by the specified user; determining the click rate difference ratio of the first object according to the first number of clicks and the second number of clicks, the click rate difference ratio being used to characterize the difference between the click heat of the first object and the click heat of the second object; selecting a target first object from the multiple candidate first objects for display according to the click rate difference ratio of the first object. The present invention solves the technical problem in the prior art that the object click rate is difficult to reflect the actual heat of the object due to the long-tail distribution, thereby resulting in inaccurate recommendations for the object, and improves the rationality of the results of recommendations based on the sorting of the object click rates.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to a method and a device for displaying an object. Background Art

[0002] In APP, it is usually based on the historical click-through rate of each recommended object to determine which recommended objects are popular and which are unpopular, and then adjust the object recommendation or operation strategy of APP. For example, objects in APP include files, products, etc. However, in the existing object recommendation system, the object exposure and click data are both long-tail distribution. The long-tail distribution data will lead to insufficient exposure of the object. According to the central limit theorem, the calculated object click-through rate has a large error. For example, the recommendation system includes objects A and B, where object A is exposed 100 times and clicked 10 times, and object B is exposed 1 million times and clicked 50,000 times. According to the calculation formula of "click-through rate = click / exposure", the click-through rate of A is 0.1 and the click-through rate of B is 0.05. The click-through rate of A is much higher than that of B, but it is obvious that object A has fewer exposed objects, and this calculation result has a large error. This natural gap in data exposure caused by the long-tail problem of recommendation system data cannot be made up by simply relying on the data side, so it is not practical to directly calculate using exposure click data.

[0003] In the prior art, the Bayesian smoothing scheme is used to optimize the calculation of click-through rate. This algorithm mainly uses the overall prior distribution and likelihood distribution of the data to approximate its posterior distribution. From the implementation effect, it has a certain repair effect on the click-through rate error. However, the core of the Bayesian smoothing scheme is to assume that the data distribution is consistent. In actual situations, due to the natural deviation of the recommendation system algorithm, the exposure of each object is naturally inconsistent, which makes it difficult for the Bayesian smoothing scheme to achieve its ideal effect. In the case of large data deviation, there is no obvious effect.

[0004] With respect to the problem in the prior art that the long-tail distribution makes it difficult for the click rate of an object to reflect its actual popularity, thus leading to inaccurate recommendations for the object, no effective solution has been proposed so far. Summary of the invention

[0005] The embodiments of the present invention provide a method and device for displaying an object, so as to at least solve the technical problem in the prior art that the object click rate cannot reflect the actual popularity of the object due to long-tail distribution, thereby causing inaccurate recommendation of the object.

[0006] According to one aspect of an embodiment of the present invention, a method for displaying an object is provided, comprising: obtaining a plurality of candidate first objects, wherein each first object is an object that appears in one or more user interfaces corresponding to a specified user; obtaining a first number of clicks on the first object in a first preset time period and a second number of clicks on a second object by the specified user, wherein the second object is an object that appears in all user interfaces; determining a click rate difference ratio of the first object based on the first number of clicks and the second number of clicks, wherein the click rate difference ratio is used to characterize 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 plurality of candidate first objects for display based on the click rate difference ratio of the first object.

[0007] According to another aspect of an embodiment of the present invention, there is also provided an object display device, comprising: an object acquisition module, used to acquire a plurality of candidate first objects, wherein each first object is an object appearing in one or more user interfaces corresponding to a specified user; a quantity acquisition module, used to acquire a first number of clicks on the first object in a first preset time period and a second number of clicks on the second object by the specified user, wherein the second object is an object appearing in all user interfaces; a determination module, used to determine a click rate difference ratio of the first object based on the first number of clicks and the second number of clicks, wherein the click rate difference ratio is used to characterize the difference between the click heat of the first object and the click heat of the second object; and a selection module, used to select a target first object from the plurality of candidate first objects for display based on the click rate difference ratio of the first object.

[0008] According to another aspect of an embodiment of the present invention, a computer storage medium is provided, wherein the computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing any one of the method steps described above.

[0009] According to another aspect of an embodiment of the present invention, there is also provided a smart interactive tablet, comprising: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing any one of the above method steps.

[0010] In an embodiment of the present invention, the number of overlapping users is determined by taking the second object that can be seen by all users as a reference, the click rate difference ratio of the first object is calculated based on the number of clicks on the first object and the second object by overlapping users, and the recommended object is determined based on the click rate difference ratios of different first objects. Since the click rate difference ratio is the relative click rate of the first object to the second object in a common user group, this embodiment has a smaller error and higher stability than the recommendation method based on object click rate sorting. The difference relationship between the click heat between the first object and the second object can be used to locate some situations where the prediction deviation and the sorting relationship are greatly different, making the result of sorting and recommending the objects more reasonable, and solving the problem in the prior art that the object click rate is difficult to reflect the actual heat of the object due to the long-tail distribution, thereby leading to inaccurate recommendations of the object. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0012] Figure 1 is a flow chart of a method for displaying an object according to an embodiment of the present invention;

[0013] Figure 2 is a schematic diagram of a display device of an object according to an embodiment of the present invention;

[0014] Figure 3 It is a schematic diagram of an optional intelligent interactive tablet according to an embodiment of the present invention. DETAILED DESCRIPTION

[0015] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0016] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0017] At present, the display method of objects in APP estimates which objects users like according to the estimated click-through rate of the objects as a recommendation strategy for objects. For example, the objects in APP can be file objects, and the file topics that users are interested in can be estimated according to the click-through rate of the file objects; the objects in APP can also be items, and the types of objects that users like can be estimated according to the click-through rate of the objects. The existing object click-through rate calculation formula is: click-through rate = click / exposure. According to this formula, the click-through rate of different objects can be calculated, and then the popularity of the objects can be estimated. For example, Table 1 provides a set of exposure and click data of objects A, B, C, D, and E in APP. Table 1 respectively counts the exposure data of each object, the number of times each object is clicked, and the click-through rate calculated according to the above click-through rate calculation formula (click-through rate = click / exposure).

[0018] Table 1

[0019] Object exposure Click Click-through 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

[0020] By sorting the click-through rates of objects AE, we can obtain the objects with the click-through rates from high to low: E>D>A>B>C. Objects E and D are objects with higher click-through rates. However, objects C, D, and E have less exposure data, and their click-through rate calculation errors are large, resulting in low credibility of the above-mentioned sorting, which will cause the ranking of some unpopular objects with less exposure but more clicks to fluctuate greatly, making it difficult for the object click-through rate to reflect the actual popularity of the object. For example, the above-mentioned objects AE are recommended items. Although the click-through rate of object E ranks first, if the item represented by object E is used as a key recommended product, the quality and popularity of product E are difficult to guarantee. The present invention provides the following embodiments to solve the problem in the prior art that the object click-through rate is difficult to reflect the actual popularity of the object due to the long-tail distribution, resulting in inaccurate recommendations of the object.

[0021] Example 1

[0022] According to an embodiment of the present invention, an embodiment of a method for displaying an object is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0023] Figure 1 is a flow chart of a method for displaying an object according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0024] Step S101 : obtaining a plurality of candidate first objects, wherein each first object is an object appearing in one or more user interfaces corresponding to a specified user.

[0025] The first object is understood to be an object exposed to a designated user according to a preset recommendation strategy. For example, if the preset recommendation strategy is to recommend based on the user's focus topic, the first object is an object related to the user's focus topic. Since the user focuses on different topics, the first object is only exposed in the user interfaces of some users. For example, among 10 users, only 3 users focus on the topic corresponding to the first object. The above 3 users are designated users, and the first object is only exposed in the user interfaces of the 3 designated users. The user interface of the designated user can be the designated user's smart terminal APP interface, and the designated user can browse the exposed objects through the APP interface.

[0026] Step S102, obtaining a first click count of a first object in a first preset time period and a second click count of a second object by a specified user, wherein the second object is an object that appears in all user interfaces.

[0027] The first preset time is a time interval in which click counts need to be performed, for example, the click counts within a certain day.

[0028] The second object is understood to be an object that is displayed at the top of the user interface and can be seen by all users. Therefore, the designated user is an overlapping user who can not only see 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 400,000, and object A can be seen by all exposed users, and the exposure of object E is 5,000, that is, 5,000 users can see object E, and these 5,000 users must also see object A. Therefore, these 5,000 users are the above-mentioned designated users, and the number of clicks on object E by 5,000 users, 800, is the above-mentioned first click number, and the number of clicks on object A by 5,000 users is the above-mentioned second click number.

[0029] It should be noted that there may be multiple objects that can be seen by all users, and in this implementation, any one of them can be selected as the second object.

[0030] Step 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 to characterize the difference between the click heat of the first object and the click heat of the second object.

[0031] Due to the long-tail effect, it is not accurate to recommend objects based solely on click-through rate ranking. Therefore, the above solution proposes a click-through rate difference ratio, which is used to correct the click-through rate of the second object that can only be seen by some users. Sorting based on the click-through rate difference ratio can obtain a more accurate object popularity situation.

[0032] In an optional embodiment, the click rate difference ratio may be calculated by: (first click number-second click number) / number of overlapping users, and the click rate difference ratio of the first object may be obtained through this calculation method.

[0033] Step S104: selecting a target first object from a plurality of candidate first objects for display according to the click rate difference ratio of the first objects.

[0034] Specifically, the click rate difference ratio of each first object is obtained according to the above steps for multiple first objects, and the target first object is selected as the recommended object according to the order of the click rate difference ratios of the multiple first objects. The above display refers to displaying the target first object at a specified position of the APP as a recommended object, for example, displaying the recommended object at the top position of the APP homepage.

[0035] It should be noted that the number of target first objects can be set by the user. For example, the target first object can be the first object with the highest click rate difference ratio, or can be a plurality of first objects ranked at the top after being sorted by click rate difference ratio.

[0036] In an optional implementation, Table 2 provides the statistical results of the exposure and click data of objects AE by a certain application in a certain day. In Table 2, object A is placed at the top as the second object, that is, the object that can be seen by all users, and object BE is the first object. The click rate in Table 2 is calculated based on the click / exposure of each object, and the overlapping exposure click is the number of clicks on the top object A by the specified user of each object. For example, the overlapping exposure click of object B is the number of clicks on object A by the exposed users of object B. The calculation method of the click rate difference ratio of each object is:

[0037] Click-through rate difference ratio = (click-overlapping exposure click) / number of overlapping users.

[0038] Among them, the number of overlapping users is the above-mentioned specified users, that is, users who can see object A and the object to be calculated at the same time. For example, the number of overlapping users of object B is the exposure number of object B itself, 120,000. The click rate difference ratio of object B = (B's clicks - B's overlapping exposure clicks) / the number of overlapping users of B = (10,000-12,000) / 120,000 = -0.0167. The click rate difference ratios of objects C, D, and E are calculated in turn through this method, as shown in the click rate difference ratio data in Table 2.

[0039] Table 2

[0040]

[0041]

[0042] According to the click rate difference ratio of each object in Table 2, the click rate difference ratio of each object is arranged in descending order to obtain: D>C>A>B>E. When one object is selected as the recommended object, object D is determined as the first target object, that is, object D is recommended; when three objects are selected as recommended objects, objects D, C and A are determined as the first target objects, that is, objects D, C and A are recommended.

[0043] In this embodiment, the number of overlapping users is determined by taking the second object that can be seen by all users as a reference, the click rate difference ratio of the first object is calculated according to the number of clicks on the first object and the second object by overlapping users, and the recommended object is determined according to the click rate difference ratio ranking of different first objects. Since the click rate difference ratio is the relative click rate of the first object to the second object in the common user group, this embodiment has smaller errors and higher stability than the recommendation method based on single object click rate ranking. The difference relationship between the click heat between the first object and the second object can locate some situations where the prediction deviation and the ranking relationship are greatly different, making the result of ranking and recommending objects more reasonable, and solving the problem in the prior art that the object click rate is difficult to reflect the actual heat of the object due to the long-tail distribution, thereby leading to inaccurate recommendation of the object.

[0044] As an optional embodiment, determining the click rate difference ratio of the first object based on the first click number and the second click number includes: obtaining the difference between the first click number and the second click number; and determining the ratio of the difference to the number of specified users as the click rate difference ratio of the first object.

[0045] Specifically, the click rate difference ratio of the first object may be calculated as: (first click number-second click number) / number of overlapping users. The click rate difference ratio of the first object may be obtained by this calculation method, wherein the overlapping users are the above-mentioned designated users.

[0046] As an optional embodiment, before obtaining multiple candidate first objects, the method further includes: obtaining a recall strategy for the first object, wherein the recall strategy is used to indicate multiple dimensions for recalling the first object, and the multiple dimensions include at least click heat.

[0047] The above multiple dimensions may include click heat, user preferences, historical collections, etc. The recall strategy is used to filter out a set of objects to be recommended to the user, which may include multiple dimensions. By adopting a recall strategy of multiple dimensions to determine the first object, the accuracy of the recall can be improved. For example, after filtering out the objects to be recommended to the user, the objects are first filtered according to the user's preferences, and then the filtered favorite objects are secondary filtered according to the click heat to obtain a set of recalled objects.

[0048] As an optional embodiment, obtaining multiple candidate first objects includes: recalling multiple candidate first objects according to click heat, wherein the step of recalling multiple candidate first objects according to click heat includes: obtaining click heat parameters of multiple first objects within a second preset time period, wherein the click heat parameter is the click rate of the first object within the second preset time period; sorting the multiple first objects from high to low according to the click heat parameter, and obtaining the first n first objects as multiple candidate first objects.

[0049] In actual recall strategies, a combination of click rate estimation and click rate difference ratio is usually used to screen out the set of recommended objects to improve the accuracy of recall. For example, Table 2 provides the click rates of objects AE in a certain day. According to their click rates, they are sorted from high to low to obtain E>D>A>B>C. When n=3, the top 3 E, D, and A are selected as the first candidate objects.

[0050] The value of n is determined according to the actual recall strategy and the number of objects to be recommended, and may be different in different application scenarios, and is not limited here.

[0051] As an optional embodiment, a target first object is selected from multiple candidate first objects for display based on the click rate difference ratio of the first object, including: obtaining the preset number m of target first objects; sorting the multiple candidate first objects from high to low based on the click rate difference ratio, and obtaining the first m first objects as the target first objects; and displaying the target first object.

[0052] For example, according to the click rate difference ratio of each object in Table 2, the click rate difference ratio of each object is arranged in descending order to obtain: D>C>A>B>E. When m=3, objects D, C and A are determined to be the above-mentioned first target objects, that is, objects D, C and A are taken as objects to be recommended.

[0053] In another optional embodiment, as shown in Table 2, the objects can be first sorted from high to low according to their click rate to obtain E>D>A>B>C, and the top 3 E, D, and A can be used as candidate first objects. Then, E, D, and A can be sorted in descending order according to their click rate difference ratio to obtain D>A>E. When m=2, D and A, which are ranked at the top, are determined as the target first objects. This implementation uses the click rate difference ratio as a correction to the click rate sorting model, reduces the deviation of the click rate model of objects with low exposure, and improves the recall accuracy.

[0054] The value of m is determined according to the number of objects to be recommended, and may be different in different application scenarios, which is not limited here.

[0055] As an optional embodiment, the above method also includes: obtaining a recall strategy for the first object, the recall strategy includes the number of first objects recalled through each dimension, and obtaining the preset number m of target first objects, including: obtaining the number of first objects recalled according to click heat in the recall strategy; determining that the number of first objects recalled according to click heat is the preset number m of target first objects.

[0056] For example, if the number of 20 first objects recalled according to the click heat dimension is 5, then the number of preset target first objects m is determined to be 5. In the objects AE shown in Table 2, if its recall strategy includes the number of objects recalled according to click heat being 2, the click rate difference ratios of each object are arranged in descending order to obtain: D>C>A>B>E, and the objects D and C ranked in the top 2 are determined to be the above-mentioned target first objects.

[0057] In the application scenario of teaching applications, the display method of the above-mentioned objects can be used for recalling and recommending courses. For example, course recommendation requires recalling in multiple dimensions, and popular recall is one of the recall algorithms in multiple dimensions. Due to the extremely uneven exposure of courses, some courses are exposed more, while a large number of courses are exposed less. Simply using click heat as a recall strategy will lead to inaccurate recall of courses. According to the object recommendation method of an embodiment of the present invention, here, first a popular course with a large number of click purchases is locked in the first position of the light course column for fixing, and other courses are recommended for exposure using the above-mentioned click rate difference ratio sorting method, and the data platform counts the exposure click purchase data every day. When the user slides to the light course column, the popular course fixed in the first position must be exposed, and the click rate of the popular course is compared with the click rate of all other courses to calculate the click rate difference ratio of each course, and the sorting relationship of the exposed courses is obtained according to the click rate difference ratio. The sorting result based on popular recall can be obtained by using the overall sorting relationship. For example, if Course 2 has exposed some users, and these users must have also been exposed to Course 1, we can use the overlapping users to calculate the corresponding click-through rate and conversion rate indicators of the two courses and obtain the ranking relationship of the two courses.

[0058] When new courses are launched on the APP, the relative click-through rate relationship of the courses is updated every day (i.e., the difference in click-through rate between the new courses and the top popular courses). The click-through rate estimation model is used to estimate the click-through rate of users on the recalled courses, and then the click-through rate difference ratio calculated above is used to correct the click-through rate to avoid the deviation in the click-through rate estimation of low-frequency courses, which causes the online course recommendation service to recommend popular courses. The relationship between the click-through rate difference ratio of courses can be used to locate the situation where the click-through rate prediction deviation is greatly different from the ranking relationship. The ranking position can be corrected to make the course ranking more reasonable, reduce the risk of misranking caused by sorting based on click-through rate, and solve the problem that the existing sorting model based on click-through rate has large errors in estimating the click-through rate of low-frequency courses.

[0059] The object recommendation method proposed in this embodiment takes advantage of the fact that popular objects have a large exposure volume, while unpopular objects have a small exposure volume, and the two exist in a common overlapping user group. The difference in overlapping user groups is used to calculate the difference in click-through rate to obtain the click-through rate difference ratio. Since the recommendation of all objects comes from the same set of recommendation algorithms, for each object, the population in which it appears is consistent with the overall distribution of the algorithm, then for the population of each object, the difference in click-through rate can be compared; and a click-through rate difference ratio combined with a recall strategy for click-through rate estimation is proposed to correct the popular recall strategy, thereby improving the accuracy of user personalized click-through rate estimation.

[0060] Example 2

[0061] According to an embodiment of the present invention, a display device embodiment of an object is provided. Figure 2 is a schematic diagram of a display device of an object according to an embodiment of the present invention, such as Figure 2 As shown, the device includes: an object acquisition module 21, used to acquire multiple candidate first objects, wherein each first object is an object that appears in one or more user interfaces corresponding to a specified user; a quantity acquisition module 22, used to acquire a first click quantity of the first object in a first preset time period and a second click quantity of the specified user on the second object, wherein the second object is an object that appears in all user interfaces; a determination module 23, used to determine a click rate difference ratio of the first object based on the first click quantity and the second click quantity, wherein the click rate difference ratio is used to characterize the difference between the click heat of the first object and the click heat of the second object; and a selection module 24, used to select a target first object from the multiple candidate first objects for display based on the click rate difference ratio of the first object.

[0062] As an optional embodiment, the above-mentioned determination module includes: a difference acquisition submodule, used to obtain the difference between the first number of clicks and the second number of clicks; a click rate difference ratio determination submodule, used to determine the ratio of the difference to the number of specified users as the click rate difference ratio of the first object.

[0063] As an optional embodiment, the above-mentioned device also includes: a first recall strategy acquisition module, used to obtain a recall strategy for the first object, wherein the recall strategy is used to indicate multiple dimensions for recalling the first object, and the multiple dimensions at least include click heat.

[0064] As an optional embodiment, the object acquisition module includes: a recall module, used to recall multiple candidate first objects according to click heat, wherein the recall module includes: a parameter acquisition sub-module, used to obtain click heat parameters of multiple first objects within a second preset time period, wherein the click heat parameter is the click rate of the first object within the second preset time period; a sorting sub-module, used to sort the multiple first objects from high to low according to the click heat parameter, and obtain the first n first objects as multiple candidate first objects.

[0065] As an optional embodiment, the above-mentioned selection module includes: a quantity acquisition submodule, used to obtain the preset number m of target first objects; a target first object acquisition submodule, used to sort multiple candidate first objects from high to low according to the click rate difference ratio, and obtain the first m first objects as target first objects; a display submodule, used to display the target first objects.

[0066] As an optional embodiment, the above-mentioned device also includes: a second recall strategy acquisition module, used to obtain the recall strategy of the first object, the recall strategy includes the number of first objects recalled through each dimension, and the number acquisition submodule includes: a click heat quantity acquisition submodule, used to obtain the number of first objects recalled according to click heat in the recall strategy; a preset quantity determination submodule, used to determine the number of first objects recalled according to click heat as the preset target first object number m.

[0067] This embodiment uses the second object that can be seen by all exposed users as a reference to determine the number of overlapping users, calculates the click rate difference ratio of the first object based on the number of clicks on the first object and the second object by overlapping users, and determines the recommended object based on the click rate difference ratios of different first objects. Since the click rate difference ratio is the relative click rate of the first object to the second object in the common user group, this embodiment has a smaller error and higher stability than the recommendation method based on single object click rate sorting. The difference relationship between the click heat between the first object and the second object can locate some situations where the prediction deviation and the sorting relationship are greatly different, making the result of sorting and recommending the objects more reasonable, and solving the problem in the prior art that the object click rate is difficult to reflect the actual heat of the object due to the long-tail distribution, thereby leading to inaccurate recommendations for the object.

[0068] Example 3

[0069] According to an embodiment of the present application, an embodiment of a computer storage medium is provided, wherein the computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing any one of the method steps in Embodiment 1. In this embodiment, the number of overlapping users is determined by taking the second object that can be seen by all exposed users as a reference, and 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 object is determined according to the click rate difference ratio sorting of different first objects. Since the click rate difference ratio is the relative click rate of the first object to the second object in a common user group, this embodiment has a smaller error and higher stability than the recommendation method based on the click rate sorting of a single object. Through the difference relationship between the click heat between the first object and the second object, some situations where the prediction deviation and the sorting relationship are greatly different can be located, so that the result of sorting and recommending the object is more reasonable, which solves the problem in the prior art that the object click rate is difficult to reflect the actual heat of the object due to the long-tail distribution, thereby leading to inaccurate recommendation of the object.

[0070] Example 4

[0071] According to an embodiment of the present application, a smart interactive tablet is provided, comprising: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing any one of the method steps in Example 1.

[0072] Figure 3 is a schematic diagram of a smart interactive tablet provided in an embodiment of the present application, the smart interactive tablet comprises the above-mentioned interactive device body and touch frame, combined with Figure 3 As shown, the smart interactive tablet 1000 may include: at least one processor 1001 , at least one network interface 1004 , a user interface 1003 , a memory 1005 , and at least one communication bus 1002 .

[0073] The communication bus 1002 is used to realize the connection and communication between these components.

[0074] 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.

[0075] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0076] Among them, the processor 1001 may include one or more processing cores. The processor 1001 uses various interfaces and lines to connect the various parts of the entire intelligent interactive tablet 1000, and executes various functions and processes data of the intelligent interactive tablet 1000 by running or executing instructions, programs, code sets or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Optionally, the processor 1001 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 1001 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processor (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 1001, and it can be implemented separately through a chip.

[0077] Among them, the memory 1005 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 1005 may optionally be at least one storage device located away from the aforementioned processor 1001. As Figure 3 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an operating application of the smart interactive tablet.

[0078] exist Figure 3 In the smart interactive tablet 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 1001 can be used to call the operating application of the smart interactive tablet stored in the memory 1005, and specifically perform any one of the operations in Example 1.

[0079] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0080] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0081] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0082] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0083] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0084] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0085] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for displaying an object, characterized in that: include: Acquire multiple candidate first objects, wherein each of the first objects is an object that appears in one or more user interfaces corresponding to a specified user; Obtaining a first number of clicks on the first object in a first preset time period and a second number of clicks on a second object by the specified user, wherein the second object is an object that appears in all user interfaces; Determine a click rate difference ratio of the first object according to the first number of clicks and the second number of clicks, wherein the click rate difference ratio is used to represent the difference between the click heat of the first object and the click heat of the second object; A target first object is selected from the plurality of candidate first objects for display according to the click rate difference ratio of the first objects.

2. The method according to claim 1, characterized in that Determining a click rate difference ratio of the first object according to the first number of clicks and the second number of clicks includes: Obtaining a difference between the first number of clicks and the second number of clicks; The ratio of the difference value to the number of the designated users is determined as the click rate difference ratio of the first object.

3. The method according to claim 1, characterized in that Before obtaining multiple candidate first objects, the method further includes: obtaining a recall strategy for the first object, wherein the recall strategy is used to indicate multiple dimensions for recalling the first object, and the multiple dimensions at least include click heat.

4. The method according to claim 3, characterized in that: Acquiring multiple candidate first objects includes: recalling multiple candidate first objects according to the click heat, wherein the step of recalling multiple candidate first objects according to the click heat includes: Acquire click heat parameters of a plurality of first objects within a second preset time period, wherein the click heat parameters are click rates of the first objects within the second preset time period; The multiple first objects are sorted from high to low according to the click heat parameter, and the first n first objects are obtained as the candidate multiple first objects.

5. The method according to claim 1, characterized in that Selecting a target first object from the plurality of candidate first objects for display according to the click rate difference ratio of the first objects includes: Obtaining the number m of preset target first objects; Sort the candidate multiple first objects from high to low according to the click rate difference ratio, and obtain the first m first objects as the target first object; The target first object is displayed.

6. The method according to claim 5, characterized in that The method further includes: obtaining a recall strategy for the first object, the recall strategy including the number of first objects recalled through each dimension, and obtaining a preset number m of target first objects, including: Obtain the number of the first objects recalled according to the click heat in the recall strategy; The number of first objects recalled according to the click heat is determined to be the preset number m of target first objects.

7. A display device for an object, characterized in that: include: An object acquisition module, used to acquire multiple candidate first objects, wherein each of the first objects is an object appearing in one or more user interfaces corresponding to a specified user; A quantity acquisition module, used to acquire a first click quantity of the first object in a first preset time period and a second click quantity of the second object by the specified user, wherein the second object is an object that appears in all user interfaces; a determination module, configured to determine a click rate difference ratio of the first object according to the first number of clicks and the second number of clicks, wherein the click rate difference ratio is used to represent a difference between click heat of the first object and click heat of the second object; A selection module is used to select a target first object from the plurality of candidate first objects for display according to the click rate difference ratio of the first objects.

8. The device according to claim 7, characterized in that The determining module comprises: A difference acquisition submodule, used for acquiring a difference between the first number of clicks and the second number of clicks; The click rate difference ratio determination submodule is used to determine the ratio of the difference value to the number of the specified users as the click rate difference ratio of the first object.

9. A computer storage medium, characterized in that The computer storage medium stores a plurality of instructions, which are suitable for being loaded by a processor and executing the method steps according to any one of claims 1 to 6.

10. A smart interactive tablet, characterized in that: include: A processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the method steps as claimed in any one of claims 1 to 6.

Images