CN112925976A

CN112925976A - Rating data distribution method, device, server and storage medium

Info

Publication number: CN112925976A
Application number: CN202110125642.4A
Authority: CN
Inventors: 程波波
Original assignee: Beijing Dajia Internet Information Technology Co Ltd
Current assignee: Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2021-01-29
Filing date: 2021-01-29
Publication date: 2021-06-08
Anticipated expiration: 2041-01-29
Also published as: CN112925976B

Abstract

The disclosure relates to a method, a device, a server and a storage medium for allocating name data, belonging to the technical field of internet, wherein the method comprises the following steps: and acquiring a first display quality parameter of the first object and a second display quality parameter of the second object, and determining a quota allocation result of the second object based on a difference value between the first display quality parameter and the second display quality parameter. The embodiment of the disclosure provides a method for dynamically allocating denomination data, which judges whether the object is allowed to obtain the denomination data or not according to a difference value between a display quality parameter of each object and a display quality parameter of the object of which the in-queue parameter is smaller than a target threshold value, and considers the display quality parameter of the object, so that the object with better display quality can obtain the denomination data, the object with poorer display quality is prevented from obtaining the denomination data, and the display quality of the object can be ensured while allocating the denomination data to the object.

Description

Rating data distribution method, device, server and storage medium

Technical Field

The present disclosure relates to the field of internet technologies, and in particular, to a method, an apparatus, a server, and a storage medium for allocating name data.

Background

With the rapid development of internet technology and the gradual expansion of network user scale, services such as internet advertisement and internet publicity have penetrated the aspects of people's life, and service objects are generally required to be recommended for users in the internet. When recommending a business object, an object queue is usually created first, and objects stored in the object queue are recommended.

Generally, when a plurality of objects exist, the objects are sorted, and the objects in the top of the sorting are selected and added into an object queue. However, in order to recommend some target objects preferentially, a certain number of denominations are allocated to the target objects, so that the target objects with the denominations are also added to the object queue to improve the opportunity of recommending the target objects.

However, if the number of target objects is large, how to allocate limited denominations to the plurality of target objects becomes a problem to be solved urgently.

Disclosure of Invention

The present disclosure provides a method, an apparatus, a server, and a storage medium for dynamically allocating denomination data, which can allocate the denomination data to an object and ensure the display quality of the object. The technical scheme of the disclosure is as follows:

according to a first aspect of embodiments of the present disclosure, there is provided a method for allocating name data, the method including:

acquiring a first display quality parameter of a first object, wherein the first object is determined based on an object of which the current display quality parameter in an object queue to be recommended is smaller than a target threshold value;

acquiring a second display quality parameter of a second object, wherein the second object is any one object in a target object set, and the target object set comprises a plurality of objects;

determining a denomination assignment result of the second object based on a difference value between the first presentation quality parameter and the second presentation quality parameter, the denomination assignment result being used for indicating whether the second object is allowed to obtain denomination data, the denomination data representing the denominations added to the queue of objects to be recommended.

The utility model provides a method for dynamic allocation of denomination data, for each object to be allocated with the denomination data, whether the object is allowed to obtain the denomination data is judged according to the difference value between the display quality parameter of the object and the display quality parameter of the object of which the in-queue parameter is smaller than the target threshold value, the display quality parameter of the object is considered, so that the object with better display quality can obtain the denomination data, the object with poorer display quality is prevented from obtaining the denomination data, and the display quality of the object can be ensured while allocating the denomination data to the object.

In some embodiments, the determining the denomination assignment for the second object based on the difference between the first presentation quality parameter and the second presentation quality parameter comprises:

determining a target distribution parameter of the second object based on a difference between the first presentation quality parameter and the second presentation quality parameter, the target distribution parameter representing a probability of the second object being added to the object queue;

and determining the quota allocation result of the second object based on the target allocation parameter.

The probability of adding the object into the object queue is determined according to the difference value between the display quality parameter of the object to be allocated with the denomination and the display quality parameter of the object with the score smaller than the target threshold value in the queue.

In some embodiments, the determining a target distribution parameter for the second object based on the difference between the first presentation quality parameter and the second presentation quality parameter comprises:

determining a difference parameter based on the difference between the first display quality parameter and the second display quality parameter and the first display quality parameter, the difference parameter being positively correlated with the difference and negatively correlated with the first display quality parameter;

based on the difference parameter, a target dispensing parameter of the second object is determined, the target dispensing parameter being inversely related to the difference parameter.

According to the difference value between the display quality parameter of the object to be allocated with the denomination and the display quality parameter of the object with the in-queue score smaller than the target threshold, the difference parameter which is in positive correlation with the difference value is determined, and then the target allocation parameter which is in negative correlation with the difference parameter is determined based on the difference parameter, namely, the larger the difference value between the display quality parameter of the object to be allocated with the display quality parameter of the object with the in-queue score smaller than the target threshold is, the smaller the probability that the object is added into the object queue is, so that the opportunity that the object with the better display quality is added into the object queue can be improved, the object with the better display quality obtains the denomination data, and the accuracy of allocating the denomination data is improved while the display quality is ensured.

In some embodiments, the determining a target allocation parameter for the second object based on the difference parameter comprises:

determining the probability that the independent variable of the Gaussian function is positioned in a first interval based on the Gaussian function, wherein the first interval is an interval larger than the difference parameter;

and determining a target distribution parameter of the second object based on the probability that the independent variable is positioned in the first interval, wherein the target distribution parameter is determined based on the characteristic that the Gaussian function is symmetrical to the longitudinal axis of the coordinate.

The Gaussian function is skillfully adopted to represent the negative correlation between the difference parameter and the target distribution parameter, on one hand, the probability that the object is added into the object queue can be represented by adopting the probability that the independent variable is positioned in the interval larger than the difference parameter, on the other hand, the probability that the object is added into the object queue can be more accurately determined by considering the forward difference degree and the symmetric characteristic of the Gaussian function, and the accuracy of determining the target distribution parameter is improved.

In some embodiments, the determining the quota allocation result for the second object based on the target allocation parameter comprises:

issuing a random number in a second interval for the second object;

dividing the second interval into a first sub-interval and a second sub-interval according to the target distribution parameter, wherein the ratio of the length of the first sub-interval to the length of the second interval is equal to the target distribution parameter;

if the random number is in the first sub-interval, the second object is allowed to occupy the nominal data, and if the random number is in the second sub-interval, the second object is not allowed to occupy the nominal data.

The method for dynamically distributing the name data is provided, the exploration effect is increased, the object with better display quality can obtain the name data, the object with poorer display quality is prevented from obtaining the name data, and the display quality of the object can be ensured while the name data is distributed to the object.

In some embodiments, after the determining the denomination assignment of the second object based on the difference between the first presentation quality parameter and the second presentation quality parameter, the method further comprises:

and stopping allocating the denomination data if the number of the objects added into the object queue in the target object set reaches the total number of the denomination data.

By setting the total amount of the denomination data for the target object set, the number of objects needing to be allocated with the denomination data in the object set is limited within a certain number, and the excessive denomination data allocated to the objects is avoided.

In some embodiments, the set of target objects is a subset of the original set of objects, and before the obtaining the first display quality parameter of the first object, the method further comprises:

sequencing the objects in the original object set according to the sequence of the display quality parameters of the objects from high to low;

and adding the object with the target number which shows the quality parameter at the front in the plurality of objects in the original object set into the object queue.

In the above embodiment, when the object queue is determined, the object with the higher display quality parameter is selected, so that the subsequent display quality can be ensured, and the subsequent process of adding into the object queue and the determination process of the target object set are facilitated by the process of sequencing first.

In some embodiments, after adding the number of objects showing the top quality parameter in the plurality of objects in the original object set to the object queue, the method further comprises:

and selecting the objects which are not added into the object queue but meet the recommendation condition from the original object set to form the target object set.

In the embodiment, the objects meeting the recommendation condition are selected from the objects which do not enter the object queue, so that the target object set can be quickly determined, the subsequent process of judging whether to allocate the denomination data to the objects is facilitated, and the efficiency of allocating the denomination data to the objects is improved.

According to a second aspect of the embodiments of the present disclosure, there is provided a title data distribution apparatus including:

a first obtaining unit configured to perform obtaining a first presentation quality parameter of a first object, the first object being determined based on an object whose current presentation quality parameter in an object queue to be recommended is smaller than a target threshold;

the second acquisition unit is configured to execute acquisition of a second display quality parameter of a second object, wherein the second object is any one object in a target object set, and the target object set comprises a plurality of objects;

a determination unit configured to perform determining a denomination assignment result of the second object based on a difference between the first presentation quality parameter and the second presentation quality parameter, the denomination assignment result indicating whether or not to allow the second object to obtain denomination data representing the denominations added to the queue of objects to be recommended.

In some embodiments, the determining unit includes:

an allocation parameter determination unit configured to perform determining a target allocation parameter of the second object based on a difference between the first presentation quality parameter and the second presentation quality parameter, the target allocation parameter representing a probability of the second object being added to the object queue;

an allocation result determination unit configured to perform a determination of a quota allocation result of the second object based on the target allocation parameter.

In some embodiments, the allocation parameter determining unit includes:

a difference parameter determination subunit configured to perform a determination of a difference parameter, based on a difference between the first presentation quality parameter and the second presentation quality parameter and the first presentation quality parameter, the difference parameter being positively correlated with the difference and negatively correlated with the first presentation quality parameter;

an allocation parameter determination subunit configured to perform determining a target allocation parameter of the second object based on the difference parameter, the target allocation parameter being inversely related to the difference parameter.

In some embodiments, the allocation parameter determining subunit is configured to perform:

In some embodiments, the assignment result determination unit is configured to perform:

issuing a random number in a second interval for the second object;

In some embodiments, the apparatus further comprises:

and the allocation unit is configured to stop allocating the quota data if the number of the objects added into the object queue in the target object set reaches the total number of the quota data.

In some embodiments, the set of target objects is a subset of the set of original objects, the apparatus further comprising:

the sorting unit is configured to perform sorting according to the sequence of the display quality parameters of the objects in the original object set from high to low;

and the adding unit is configured to add the objects which show the number of the objects with the top quality parameters in the plurality of objects in the original object set into the object queue.

In some embodiments, the apparatus further comprises:

and the selecting unit is configured to select objects which are not added into the object queue but meet recommendation conditions from the original object set to form the target object set.

According to a third aspect of embodiments of the present disclosure, there is provided a server, including:

one or more processors;

a memory for storing the processor executable program code;

wherein the processor is configured to execute the program code to implement the rating data allocation method described above.

According to a fourth aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium including: the program code in the computer readable storage medium, when executed by a processor of a server, enables the server to perform the denomination data allocation method described above.

According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product comprising a computer program that, when executed by a processor, implements the denomination-data allocation method described above.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.

FIG. 1 is a schematic diagram of an implementation environment for a method of allocating data for a title, according to an example embodiment;

FIG. 2 is a flow diagram illustrating a method of allocating title data in accordance with an exemplary embodiment;

FIG. 3 is a flow diagram illustrating a method of allocating title data in accordance with an exemplary embodiment;

FIG. 4 is a flow diagram illustrating a method of allocating title data in accordance with an exemplary embodiment;

FIG. 5 is a block diagram illustrating a rating data distribution apparatus according to an exemplary embodiment;

FIG. 6 is a block diagram illustrating a server in accordance with an example embodiment.

Detailed Description

In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings 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 disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

The data to which the present disclosure relates may be data that is authorized by a user or sufficiently authorized by parties.

Fig. 1 is a schematic diagram of an implementation environment of a method for allocating name data according to an embodiment of the present disclosure, and referring to fig. 1, the implementation environment includes: a terminal 101 and a server 102.

The terminal 101 may be at least one of a smart phone, a smart watch, a desktop computer, a laptop computer, a virtual reality terminal, an augmented reality terminal, a wireless terminal, a laptop computer, and the like, the terminal 101 has a communication function and can access the internet, and the terminal 101 may be generally referred to as one of a plurality of terminals, which is only exemplified by the terminal 101 in this embodiment. Those skilled in the art will appreciate that the number of terminals described above may be greater or fewer.

In some embodiments, the terminal 101 may be running a video application, a live application, a social application, and the like. During use of a video application, live application, or social application by a user, server 102 may push business objects such as advertising videos, promotional videos, and the like to these applications.

The server 102 may be an independent physical server, a server cluster or a distributed file system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), a big data and artificial intelligence platform, and the like. Server 102 may be a backend server for the applications referred to above. The server 102 and the terminal 101 may be directly or indirectly connected through wired or wireless communication, which is not limited in the embodiment of the present disclosure. In some embodiments, the number of the servers 102 may be more or less, and the embodiments of the disclosure do not limit this. Of course, the server 102 may also include other functional servers to provide more comprehensive and diverse services.

In the embodiment of the present disclosure, the server 102 is configured to determine a quota allocation result of the second object based on a difference value between a first presentation quality parameter of the first object and a second presentation quality parameter of the second object, and further perform quota data allocation based on content indicated by the quota allocation result. Wherein the denomination data represents the denominations added to the queue of objects to be recommended. The first object is determined based on objects in the object queue for which the current presentation quality parameter is less than the target threshold. The second object is any object in the target object set. The denomination assignment result is used to indicate whether the second object is allowed to obtain the denomination data.

The quota data allocation method provided by the embodiment of the disclosure can be applied to business scenes such as internet advertisements and internet propaganda, for example, can be applied to recommendation scenes of business objects such as advertisement videos and propaganda videos. It should be noted that, when recommending a business object, the server 102 generally needs to go through three stages, i.e., recall, rough ranking, and fine ranking. The recall stage is a first stage of recommendation, and is to quickly retrieve a part of objects potentially interested by a user from a massive object library according to user characteristics and object characteristics and add the part of objects into a recall queue. The rough-ranking stage is a recommended second stage, and is to sort the objects in the recall queue according to some rough-ranking service indexes (such as click rate), screen out the objects in the front of the ranking, and add the screened objects into the rough-ranking queue, so as to reduce the number of recalled objects and reduce the ranking pressure in the fine-ranking stage. The fine ranking stage is a third stage of recommendation, and is to further rank the objects in the rough ranking queue according to some fine ranking service indexes (such as expected income and bid information) and screen out the objects ranked most forward to obtain the objects to be recommended.

The quota data allocation method provided by the embodiment of the disclosure can be applied to a recall stage or a rough ranking stage to preferentially recommend a target object. The target object refers to an object of a specific industry or an innovative industry, that is, an object containing specific content or innovative content, such as a public service advertisement video, an innovative advertisement video, and the like. It should be noted that, in the scenario of advertisement service or propaganda service, there is a need to preferentially display objects in some specific industries or innovative industries, so as to achieve the purpose of propaganda of the industries. That is, in the recall stage or the rough queue stage, a certain number of denominations are allocated to the target objects which do not enter the recall queue or the rough queue, so that the target objects with the acquired denominations are added into the corresponding queues, the chance of the target objects entering the next stage is improved, and the purpose of supporting the specific service and the innovative service is achieved.

Fig. 2 is a flowchart illustrating a method for allocating name data according to an exemplary embodiment, where, as shown in fig. 2, the embodiment takes a server as an execution subject and includes the following steps:

in step 201, the server obtains a first presentation quality parameter of a first object, where the first object is determined based on an object whose current presentation quality parameter in the object queue to be recommended is smaller than a target threshold.

In step 202, the server obtains a second display quality parameter of a second object, where the second object is any object in a target object set, and the target object set includes a plurality of objects.

In step 203, the server determines a quota allocation result of the second object based on a difference value between the first presentation quality parameter and the second presentation quality parameter, the quota allocation result being used for indicating whether to allow the second object to obtain quota data, the quota data representing the quota added to the queue of the objects to be recommended.

The embodiment of the disclosure provides a method for dynamically allocating denomination data, which judges whether the object is allowed to obtain the denomination data or not according to a difference value between a display quality parameter of each object and a display quality parameter of the object of which the in-queue parameter is smaller than a target threshold value, and considers the display quality parameter of the object, so that the object with better display quality can obtain the denomination data, the object with poorer display quality is prevented from obtaining the denomination data, and the display quality of the object can be ensured while allocating the denomination data to the object.

Fig. 2 is a basic flow chart of the present disclosure, and the scheme provided by the present disclosure is further explained below based on a specific implementation, and fig. 3 is a flow chart of a method for allocating the title data according to an exemplary embodiment, and referring to fig. 3, the method includes:

in step 301, in response to the display request of the terminal, the server sorts the display quality parameters of the objects in the original object set in order from high to low.

The display request is used for triggering display of one or more objects. In some embodiments, if the present embodiment is applied to the recall stage, the original object set refers to a set of massive objects, for example, the original object set may be an object library. In other embodiments, if the present embodiment is applied to the rough queue stage, the original object set refers to a set of a plurality of objects determined in the recall stage, for example, the original object set may be a recall queue. The display quality parameter of the object is used for representing the display quality of the object. In some embodiments, the display quality parameter is one of a thousand display gains (eCPM), which is a gain that can be obtained every one thousand displays, or a delivery rate, which is a ratio of the number of times that objects are delivered to the user side. It should be understood that the higher the presentation quality parameter of an object, the better the presentation quality of the object, and the greater the revenue generated by the object.

In some embodiments, the terminal sends a presentation request to the server based on a trigger operation of the user. Taking a video application program as an example, a user operates on a terminal to start the video application program, a plurality of control controls, such as a viewing control or a playing control, are displayed in an interface of the video application program, if the terminal detects that the user clicks the viewing control or the playing control, a display request is sent to a server, and the server performs subsequent operations after receiving the display request.

In some embodiments, the server responds to the display request of the terminal, obtains thousands of display yields of the plurality of objects in the original object set, and sorts the display yields of the plurality of objects in the order from high to low to obtain the arrangement order of the plurality of objects. Optionally, the process of acquiring the thousands of display profits by the server is as follows: and predicting the click rate of the object for any object in the original object set to obtain the predicted click rate of the object, and determining the product of the predicted click rate of the object, the single click income of the object and a constant 1000 as the thousands of display incomes of the object. In the embodiment, the display quality parameters are adopted for sequencing, so that the display quality of the objects can be well represented, and the subsequent process of allocating the denomination data to the objects is facilitated.

In still other embodiments, the server responds to the display request of the terminal, obtains the delivery rates of the plurality of objects in the original object set, and sorts the plurality of objects according to the sequence of the delivery rates of the plurality of objects from high to low to obtain the arrangement sequence of the plurality of objects. Optionally, the process of acquiring the delivery rate by the server is as follows: in the embodiment, the object sending rates are adopted for sequencing, the display quality of the objects can be well represented, and the subsequent process of allocating the denomination data to the objects is facilitated.

In other embodiments, the server may further perform weighted summation on the thousands of display proceeds, the first weight of the thousands of display proceeds, the delivery rate, and the second weight of the delivery rate based on the thousands of display proceeds of the plurality of objects in the original object set to obtain display quality parameters of the plurality of objects in the original object set, and then perform ranking according to the order of the display quality parameters of the plurality of objects from high to low to obtain the ranking order of the plurality of objects. In the embodiment, the display quality parameters are adopted for sequencing, the display quality of the objects can be well represented, the sequencing is carried out in a weighted summation mode, two sequencing parameters are considered, the sequencing can be carried out more accurately, and the subsequent process of allocating the denomination data to the objects is facilitated.

The above process illustrates the sequencing process by taking thousands of revenues and delivery rates for display as an example. In other embodiments, parameters of other dimensions can be selected for sorting, for example, a thousand-display click rate, a user click frequency, a user interaction frequency, a user interest score, and the like, or a comprehensive dimension score of the above-mentioned multiple dimension parameters can be used for sorting. It should be understood that the presentation quality parameter is a parameter that can represent a positive effect when presenting an object. The selected display quality parameter is not limited in the embodiments of the present disclosure.

In step 302, the server adds the number of objects showing the top quality parameters among the plurality of objects in the original object set to an object queue.

Wherein the target number is a predetermined fixed number, such as 20. The target number of objects refers to a plurality of objects to be recommended that are preliminarily determined. Optionally, the object queue is an object queue of a recall phase or a shuffle phase. The object queue is used for storing a plurality of objects to be recommended determined in the one-time display request.

In some embodiments, the server selects, based on the ranking order of the plurality of objects in the original object set, an object showing the number of objects with the highest quality parameter among the plurality of objects in the original object set, and adds the selected object to the object queue. In this embodiment, when the object queue is determined, an object with a higher display quality parameter is selected, so that the subsequent display quality can be ensured.

In step 303, the server selects, from the original object set, objects that are not added to the object queue but satisfy the recommendation condition, to form a target object set, where the target object set includes a plurality of objects.

Wherein the set of target objects is a subset of the set of original objects. The target object set refers to a set of objects meeting recommendation conditions in the original object set, that is, a set of objects needing to be preferentially recommended. The object satisfying the recommendation condition refers to an object containing specific content or innovative content, such as a public service advertisement video, an innovative advertisement video, and the like, that is, the above-mentioned target object.

In some embodiments, after adding the selected object to the object queue, the server selects, from the original object set, objects that are not added to the object queue but satisfy the recommendation condition, and constructs the target object set according to the objects that satisfy the recommendation condition. In the embodiment, the objects meeting the recommendation condition are selected from the objects which do not enter the object queue, so that the target object set can be quickly determined, the subsequent process of judging whether to allocate the denomination data to the objects is facilitated, and the efficiency of allocating the denomination data to the objects is improved.

In step 304, the server obtains a first presentation quality parameter of a first object, where the first object is determined based on objects in the queue of objects to be recommended, where the current presentation quality parameter is smaller than a target threshold.

The target threshold is a preset fixed threshold.

In some embodiments, the process of the server determining the first object comprises any one of:

(1) and if the display quality parameter of one object in the object queue is smaller than the target threshold, the server takes the object as the first object.

(2) If the display quality parameters of a plurality of objects in the object queue are smaller than the target threshold, the server randomly selects one object from the plurality of objects as a first object, or the server takes the object with the lowest display quality parameter from the plurality of objects as the first object. In the process, if a plurality of objects with the display quality parameters smaller than the target threshold exist, one of the objects or the object with the lowest display quality parameter can be selected as the first object, so that the first object can be quickly determined, and subsequent operations can be conveniently executed.

(3) And the server selects the object with the lowest current display quality parameter in the object queue as a first object from the object queue to be recommended. That is, the server obtains the object after the arrangement from the object queue as the first object. Therefore, the first object can be determined more quickly by directly selecting the objects which are arranged in the queue in the later sequence, the efficiency of determining the first object is improved, and the efficiency of allocating the nominal data is further improved. The embodiment of the present disclosure subsequently takes as an example the selection of the object with the lowest display quality parameter as the first object.

For example, if the object queue includes N objects, since the objects in the object queue are arranged according to the presentation quality parameters from high to low, the object with the arrangement order of N in the object queue is taken as a first object, and the first presentation quality parameter of the first object may be denoted as rank _ score _ N.

In the above steps (1) to (3), after the first object is determined, the display quality parameter of the first object is obtained, so that the first display quality parameter can be obtained. In other embodiments, if the display quality parameters of a plurality of objects in the object queue are smaller than the target threshold, the server obtains the display quality parameters of the plurality of objects, and determines an average value of the display quality parameters of the plurality of objects as the first display quality parameter. In the process, the server adopts the average value of the plurality of display quality parameters as the first display quality parameter, the first display quality parameter can be rapidly determined, the display quality parameters of the plurality of objects are comprehensively considered, and the accuracy of subsequent denomination data distribution is improved.

In step 305, the server obtains a second display quality parameter of a second object, where the second object is any object in the target object set.

In some embodiments, the server selects the presentation quality parameter of one object from the target object set as the second presentation quality parameter of the second object.

In some embodiments, the process of the server selecting the second object includes any one of:

(1) and the server randomly selects an object from the target object set as the second object. In the embodiment, the second object is selected in a random selection mode, so that the second object can be quickly determined, and the efficiency of allocating the nominal data is improved.

(2) And the server selects the object with the highest display quality parameter from the target object set as the second object. In the embodiment, the second object can be quickly determined by selecting the object with the highest display quality parameter, and the possibility of allocating the denomination data to the second object can be improved, so that the speed of allocating the denomination data to the object can be increased, and the efficiency of allocating the denomination data is further improved.

Exemplarily, in the target object set, one object is selected as a second object, and a second presentation quality parameter of the second object may be denoted as rank _ score _ H.

In step 306, the server determines a target allocation parameter of the second object based on a difference between the first presentation quality parameter and the second presentation quality parameter, the target allocation parameter indicating a probability of the second object being added to the object queue, and the denomination data indicating the denomination to be added to the object queue to be recommended.

The quota data is a queue quota (quota) of the object queue, that is, a queue quota occupied by the object when the object is added to the object queue.

In the process, the probability of adding the object into the object queue is determined according to the difference value between the display quality parameter of the object to be allocated with the denomination and the display quality parameter of the object with the lowest score in the queue, and the probability can represent the possibility of adding the object into the queue, so that whether the denomination data is allocated to the object can be rapidly known according to the probability, and the allocation efficiency of the denomination data is improved.

In some embodiments, after obtaining a first display quality parameter of a first object and a second display quality parameter of a second object, a server determines a difference parameter based on a difference between the first display quality parameter and the second display quality parameter and the first display quality parameter, where the difference parameter is positively correlated with the difference and negatively correlated with the first display quality parameter. And determining a target distribution parameter of the second object based on the difference parameter, wherein the target distribution parameter is inversely related to the difference parameter.

In this embodiment, according to the difference between the display quality parameter of the object to be assigned with the denomination and the display quality parameter of the object with the lowest score in the queue, the difference parameter positively correlated with the difference is determined, and then the target assignment parameter negatively correlated with the difference parameter is determined based on the difference parameter, that is, the larger the difference between the display quality parameter of the object to be assigned with the display quality parameter of the object with the lowest score in the queue, the smaller the probability that the object is added to the object queue is, so that the chance that the object with the better display quality is added to the object queue can be improved, the object with the better display quality obtains the denomination data, and the accuracy of assigning the denomination data is improved while the display quality is ensured.

The following describes in detail a process of determining a target allocation parameter of the second object based on the first display quality parameter and the second display quality parameter:

the server determines a difference between the first presentation quality parameter and the second presentation quality parameter based on the first presentation quality parameter, the second presentation quality parameter and formula (1).

Δ_{rank_score}＝rank_score_N-rank_score_H (1)

In the formula,. DELTA._{rank_score}For the difference between the first presentation quality parameter and the second presentation quality parameter, rank score_NFor the first presentation quality parameter, rank score_HAnd displaying the quality parameter for the second display.

The server determines a difference parameter based on the difference between the first presentation quality parameter and the second presentation quality parameter, the first presentation quality parameter, and equation (2).

Wherein, rank _ score_normAs a difference parameter, Δ_{rank_score}For the difference between the first presentation quality parameter and the second presentation quality parameter, rank score_NIs a first display quality parameter.

In some embodiments, the process of the server determining the target allocation parameter is: the server determines the probability that the argument of the Gaussian function is located in a first interval based on the Gaussian function, wherein the first interval is an interval larger than the difference parameter, and determines the target distribution parameter of the second object based on the probability that the argument is located in the first interval, wherein the target distribution parameter is determined based on the characteristic that the Gaussian function is symmetrical to the longitudinal axis of the coordinate. Specifically, the server determines a target allocation parameter for the second object based on the difference parameter and equation (3).

P₂＝2×P₁(v>rank_score_norm/v～Gauss(μ,δ))(μ＝0，δ＝1) (3)

In the formula, P₂Assigning a parameter, P, to a target of a second object₁v-Gauss (μ, δ)) (μ ═ 0, δ ═ 1) is a gaussian function whose mean is 0, variance is 1, v is an argument of the gaussian function, rank _ score is the probability that the argument of the gaussian function lies in the first interval_normIs a difference parameter.

It should be noted that, all the objects in the target object set are the objects that are not added to the object queue during the sorting in step 302, that is, the objects with lower display quality parameters during the sorting, and therefore, the display quality parameters of the objects in the target object set are lower than the display quality parameters of the objects in the object queue, so that the difference degree between any object in the target object set and the object with the lowest current display quality parameter in the object queue is the degree of how much the object is lower than the object with the lowest parameter in the object queue.

It should be noted that, if the degree of difference (difference parameter) between an object and the object with the lowest current presentation quality parameter in the object queue is larger, the benefit brought by the object is smaller, and the probability (that is, the target distribution parameter) of finally allocating the denomination data to the object is smaller, and if the degree of difference between the object and the object with the lowest current presentation quality parameter in the object queue is smaller, the benefit brought by the object is larger, and the probability of allocating the denomination data to the object is larger, it can be found that the probability of whether to allocate the denomination data to the object is inversely related to the degree of difference between the object and the object with the lowest current presentation quality parameter in the object queue. Therefore, in the embodiment of the present disclosure, a gaussian function is skillfully used to represent a negative correlation between a difference parameter and a target distribution parameter, on one hand, a probability that an argument is located in an interval greater than the difference parameter is used to represent a probability that the object is added to an object queue, and on the other hand, considering that a difference degree is a positive direction and a symmetric characteristic of the gaussian function, a gaussian distribution is converted into an abs (x) (function for solving an absolute value), that is, a preliminarily determined probability is multiplied by 2, so that the probability that the object is added to the object queue can be more accurately determined, and accuracy of determining the target distribution parameter is improved.

In step 307, the server determines a quota allocation result of the second object based on the target allocation parameter, the quota allocation result indicating whether the second object is allowed to obtain quota data.

In some embodiments, the server performs random probability value sampling based on the determined target assignment parameter (i.e., probability) to determine whether to allow the second object to obtain a denomination data. The corresponding process comprises the following steps: the server sends a random number in a second interval to the second object, the second interval is divided into a first sub-interval and a second sub-interval according to the target distribution parameter, wherein the ratio of the length of the first sub-interval to the length of the second interval is equal to the target distribution parameter, if the random number is located in the first sub-interval, the second object is allowed to occupy the quota data, and if the random number is located in the second sub-interval, the second object is not allowed to occupy the quota data.

Illustratively, taking the second interval as 0-100 as an example, if the target allocation parameter of the second object is 9/10, the second interval is divided into 0-10 and 10-100 or 0-90 and 90-100 according to 9/10. Understandably, in the first division, 10-100 are the first subintervals, i.e., the subintervals occupying 0-100 of the total length 9/10, and in the second division, 90-100 are the first subintervals, i.e., the subintervals occupying 0-100 of the total length 9/10. For any of the above dividing cases, if the random number issued for the second object falls within the sub-interval (first sub-interval) occupying the total length of 0 to 100 9/10, indicating that the probability of displaying the name data by the second object under the random condition is high, the second object is added to the object queue, and if the random number issued for the second object falls within the sub-interval (second sub-interval) occupying the total length of 0 to 100 1/10, indicating that the probability of displaying the name data by the second object under the random condition is low, the second object is not added to the object queue.

In the embodiment, sampling of the random probability value is adopted to judge whether to allocate one denomination data to the second object, so that the method for dynamically allocating the denomination data is provided, the exploration effect is increased, the object with better display quality can obtain the denomination data, the object with poorer display quality is prevented from obtaining the denomination data, and the display quality of the object can be ensured while allocating the denomination data to the object.

In step 308, if the result of the allocation of the quota for the second object indicates that the second object is allowed to obtain the quota data, the server allocates the quota data for the second object and adds the second object to the object queue.

In some embodiments, if the result of the allocation of the quota of the second object indicates that the second object is allowed to obtain a quota data, the server obtains an object identifier of the second object, selects a tag of the quota data, and generates a corresponding relationship between the object identifier and the tag of the quota data, so as to add the second object to the object queue.

Alternatively, the tag of the denomination data selected by the server may be a tag of the denomination data of the first object, that is, the object with the lowest presentation quality parameter in the object queue is deleted, and the second object is added to the object queue. In the process, the object with the lowest quality parameter shown in the object queue is replaced by the second object, so that the priority recommendation of the second object is realized.

In other embodiments, if the result of the allocation of the quota of the second object indicates that the second object is not allowed to obtain the quota data, the server does not allocate the quota data to the second object, continues to traverse the remaining objects in the target object set, and sequentially performs the quota data allocation process on the remaining objects.

The above-described steps 301 to 308 describe the determination process of assigning denomination data to any object in the target object set based on the second object. For the whole target object set, the server also presets the total amount of the denomination data allocated to the target object set, namely the upper limit of the amount of the denomination data, and further judges whether to allocate the denomination data to a plurality of objects in the target object set based on the total amount of the denomination data, if the number of the objects added into the object queue in the target object set reaches the total amount of the denomination data, the server stops allocating the denomination data, and if the number of the objects added into the object queue in the target object set does not reach the total amount of the denomination data, the server continues allocating the denomination data.

It should be noted that, the determining, by the server, whether to allocate the reputation data to the plurality of objects in the target object set based on the total amount of the reputation data may include any one of the following:

in some embodiments, the server determines whether to allocate the denomination data to the plurality of objects in the target object set based on the total amount of the denomination data, and the determination is performed before obtaining the presentation quality parameter of any object in the target object set, that is, before step 305. The corresponding process is as follows: when the server acquires the display quality parameter of any object in the target object set each time, whether the number of the objects added into the object queue in the target object set reaches the total number of the nominal data is judged, if so, the step of acquiring the display quality parameter of any object in the target object set is not executed, and if not, the step of acquiring the display quality parameter of any object in the target object set is continuously executed. Therefore, before judging whether the denomination data is distributed to the object, whether the total amount of the denomination data is reached or not can be known in advance, the server continues to distribute the denomination data under the condition that the surplus number of the denomination data exists, and does not continue to distribute the denomination data under the condition that the surplus number of the denomination data does not exist, so that the processing content of the server is greatly reduced.

In other embodiments, the server determines whether to assign the denomination data to the plurality of objects in the target object set based on the total amount of the denomination data, and the determining is performed when the second object occupies one of the denomination data. The corresponding process is as follows: if the result of the allocation of the name of the second object indicates that the second object is allowed to obtain a name data, the server judges whether the number of the objects added into the object queue in the target object set reaches the total number of the name data, if so, the name data is not allocated to the second object, and if not, a name data is allocated to the second object. In the process, when determining that the denomination data is distributed to the second object, the total amount of the denomination data is judged, so that the excess objects are prevented from occupying the denomination data.

In the above embodiment, by setting the total amount of the denomination data for the target object set, the number of objects in the object set to which the denomination data needs to be allocated is limited to a certain number, and the excess of the denomination data allocated to the objects is avoided.

The above process is a process of setting the total amount of the denomination data for the target object set, and in other embodiments, the server is preset with an upper limit (Num _ max) and a lower limit (Num _ min) of the number of the denomination data, and when allocating the denomination data to any object in the target object set, it is determined whether to allocate the denomination data to the object based on the upper limit and the lower limit of the number.

Similarly, the server may determine, based on the upper limit and the lower limit of the number of the reputation data, whether to allocate the reputation data to the plurality of objects in the target object set at the execution timing, including any one of:

in some embodiments, each time the server obtains the display quality parameter of any object in the target object set, the server first determines the relationship between the number of the objects added into the object queue in the target object set and the upper limit and the lower limit of the number, and if the number of the objects added into the object queue in the target object set is less than the lower limit of the number of the denomination data, the server performs the step of obtaining the display quality parameter of any object in the target object set; if the number of the objects added into the object queue in the target object set is larger than the lower limit of the number of the nominal data and smaller than the upper limit of the number of the nominal data, the server executes the step of acquiring the display quality parameter of any object in the target object set; and if the number of the objects added into the object queue in the target object set is greater than the upper limit of the number of the nominal data, the step of obtaining the display quality parameter of any object in the target object set is not executed.

In other embodiments, when determining that a second object occupies a piece of quota data, the server determines a relationship between the number of objects added to the object queue in the target object set and an upper limit and a lower limit of the number of the objects, and if the number of the objects added to the object queue in the target object set is smaller than the lower limit of the number of the quota data, the server allocates a piece of quota data to the second object; if the number of the objects added into the object queue in the target object set is larger than the lower limit of the number of the nominal data and smaller than the upper limit of the number of the nominal data, the server distributes nominal data to the second object; and if the number of the objects added into the object queue in the target object set is greater than the upper limit of the number of the quota data, not allocating the quota data to the second object.

The upper limit and the lower limit of the number of denomination data may be in the form of a number interval. The embodiment adopts the upper limit and the lower limit of the quantity of the nominal data to limit the quantity of the nominal data in one display request, and can avoid the condition that the number of the objects of the nominal data to be distributed determined in each display request is too much or too few, so that the number of the objects of the nominal data to be distributed is limited in a range.

It should be further noted that, in the process of allocating the denomination data to the multiple objects, an object with a higher presentation quality parameter is selected from the multiple objects based on the presentation quality parameter of the object, and the denomination data is allocated to the selected object, because the higher the presentation quality parameter is, the better the presentation quality of the object is, and further the larger the revenue generated by the object is, higher revenue can be ensured.

FIG. 3 illustrates how a denomination can be assigned to an object in the target set of objects. Fig. 4 is a flowchart illustrating a method of allocating title data according to an exemplary embodiment, referring to fig. 4, the method including:

in step 401, in response to the display request from the terminal, the server sorts the display quality parameters of the objects in the original object set in order from high to low.

In step 402, the server adds the number of objects showing the top quality parameters among the objects in the original object set to the object queue.

In step 403, the server selects, from the original object set, objects that are not added to the object queue but satisfy the recommendation condition, to form the target object set, where the target object set includes a plurality of objects.

In step 404, the server obtains a first presentation quality parameter of a first object, where the first object is determined based on an object whose current presentation quality parameter in the queue of objects to be recommended is smaller than a target threshold.

In step 405, the server obtains a second display quality parameter of a second object, where the second object is any object in the target object set.

In step 406, the server determines a target allocation parameter of the second object based on a difference between the first presentation quality parameter and the second presentation quality parameter, the target allocation parameter indicating a probability of the second object being added to the object queue, and the denomination data indicating the denomination to be added to the object queue to be recommended.

In step 407, the server determines a quota allocation result of the second object based on the target allocation parameter, the quota allocation result indicating whether the second object is allowed to obtain quota data.

In step 408, if the result of the allocation of the quota for the second object indicates that the second object is allowed to obtain the quota data, the server allocates the quota data for the second object and adds the second object to the object queue.

The contents of steps 401 to 408 are referred to in steps 301 to 308, and are not described again.

In step 409, the server obtains the display quality parameter of the object whose current display quality parameter is less than the target threshold value from the objects in the object queue except the newly added object.

In step 410, the server obtains the display quality parameter of the next object in the target object set, and determines the target distribution parameter of the next object based on the difference between the display quality parameter of the object whose display quality parameter is smaller than the target threshold and the display quality parameter of the next object.

In some embodiments, the server selects, in the target object set, the presentation quality parameter of the object with the highest presentation quality parameter except the second object as the presentation quality parameter of the next object. Therefore, the speed of allocating the denomination data to the object can be increased, and the efficiency of allocating the denomination data is improved. Of course, in other embodiments, the server may also select the next object by randomly selecting. Optionally, the plurality of objects in the target object set are sorted in order from high to low. Therefore, the object with the highest quality parameter can be conveniently determined, and the efficiency of allocating the denomination data is improved.

It should be noted that, the process of determining the target allocation parameter by the server is referred to as step 306, and is not described in detail.

In step 411, the server determines the quota allocation result of the next object based on the target allocation parameter of the next object, and if the quota allocation result of the next object indicates that the next object is allowed to obtain quota data, the server allocates quota data to the next object and adds the next object to the object queue.

In other embodiments, if the result of allocating the quota of the next object indicates that the object is not allowed to obtain a quota data, the server does not allocate a quota data for the next object, and continues to traverse the remaining objects in the target object set, and sequentially performs the quota data allocation process on the remaining objects.

In step 412, the above-mentioned step of allocating the quota to the object in the target object set is repeatedly executed until the number of the objects added to the object queue in the target object set reaches the total number of the quota data, and then the server stops allocating the quota data.

In some embodiments, when the server allocates the quota for the object in the target object set, for any object in the target object set, if the quota allocation result of the object indicates that the object is allowed to obtain a quota data, it is determined whether the number of the objects added to the object queue in the target object set reaches the total number of the quota data, if so, the allocation of the quota data is stopped, and if not, the quota data is allocated for the object, and the traversal of other objects in the target object set is continued.

It should be appreciated that in some embodiments, when the server has traversed all objects in the target set of objects, the number of objects in the target set of objects that are added to the object queue may not yet reach the total amount of the quota data, at which point the server stops allocating the quota data.

The embodiment of the disclosure provides a method for dynamically allocating denomination data, which judges whether the object is allowed to obtain the denomination data or not according to a difference value between a display quality parameter of each object and a display quality parameter of an object with a parameter in a queue smaller than a target threshold value, and considers the display quality parameter of each object, so that the object with better display quality can obtain the denomination data, the object with poorer display quality is prevented from obtaining the denomination data, and the display quality of the object can be ensured while allocating the denomination data to the object.

Fig. 5 is a block diagram illustrating a title data distribution apparatus according to an example embodiment. Referring to fig. 5, the apparatus includes a first acquisition unit 501, a second acquisition unit 502, and a determination unit 503.

A first obtaining unit 501 configured to perform obtaining a first presentation quality parameter of a first object, where the first object is determined based on an object whose current presentation quality parameter in the object queue to be recommended is smaller than a target threshold;

a second obtaining unit 502 configured to perform obtaining a second display quality parameter of a second object, where the second object is any one object in a target object set, and the target object set includes a plurality of objects;

a determining unit 503 configured to perform determining a denomination assignment result of the second object based on a difference between the first presentation quality parameter and the second presentation quality parameter, the denomination assignment result being used for indicating whether or not to allow the second object to obtain denomination data, the denomination data representing the denominations added to the queue of objects to be recommended.

In some embodiments, the determining unit 503 includes:

In some embodiments, the allocation parameter determining unit includes:

issuing a random number in a second interval for the second object;

In some embodiments, the apparatus further comprises:

It should be noted that: the denomination data allocation device provided in the above embodiment is only exemplified by the division of each functional module when allocating the denomination data, and in practical applications, the function allocation may be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus for allocating nomial data provided by the above embodiment and the method for allocating nomial data belong to the same concept, and the specific implementation process thereof is described in the method embodiment and is not described herein again.

Fig. 6 is a block diagram of a server according to an exemplary embodiment, where the server 600 may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 601 and one or more memories 602, where at least one program code is stored in the one or more memories 602, and the at least one program code is loaded and executed by the one or more processors 601 to implement the denomination data allocation method provided by the various method embodiments. Of course, the server 600 may also have components such as a wired or wireless network interface, a keyboard, and an input/output interface, so as to perform input and output, and the server 600 may also include other components for implementing the functions of the device, which is not described herein again.

In an exemplary embodiment, there is also provided a computer readable storage medium, such as the memory 602, comprising program code executable by the processor 601 of the server 600 to perform the above-described denomination data allocation method. Alternatively, the computer-readable storage medium may be a read-only memory (ROM), a Random Access Memory (RAM), a compact-disc read-only memory (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.

In an exemplary embodiment, a computer program product is also provided, comprising a computer program which, when executed by a processor, implements the rating data allocation method described above.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method of allocating denomination data, the method comprising:

2. The title data allocation method according to claim 1, wherein said determining the title allocation result of the second object based on the difference between the first presentation quality parameter and the second presentation quality parameter comprises:

determining a target distribution parameter of the second object based on a difference between the first presentation quality parameter and the second presentation quality parameter, the target distribution parameter representing a probability that the second object is added to the object queue;

3. The rating data allocating method according to claim 2, wherein the determining a target allocation parameter of the second object based on the difference between the first presentation quality parameter and the second presentation quality parameter comprises:

4. The reputation data allocation method according to claim 3, wherein the determining a target allocation parameter of the second object based on the difference parameter comprises:

determining the probability that the independent variable of the Gaussian function is located in a first interval based on the Gaussian function, wherein the first interval is an interval larger than the difference parameter;

5. The quota data allocation method according to claim 2, wherein said determining a quota allocation result of the second object based on the target allocation parameter comprises:

issuing a random number in a second interval for the second object;

and if the random number is located in the first sub-interval, allowing the second object to occupy the nominal data, and if the random number is located in the second sub-interval, not allowing the second object to occupy the nominal data.

6. The title data allocation method according to claim 1, wherein after determining the title allocation result of the second object based on the difference between the first presentation quality parameter and the second presentation quality parameter, the method further comprises:

and if the number of the objects added into the object queue in the target object set reaches the total number of the quota data, stopping allocating the quota data.

7. A title data distribution apparatus, characterized in that the apparatus comprises:

the first obtaining unit is configured to obtain a first display quality parameter of a first object, and the first object is determined based on objects of which the current display quality parameter in the object queue to be recommended is smaller than a target threshold value;

a determination unit configured to perform determination of a denomination assignment result of the second object based on a difference between the first presentation quality parameter and the second presentation quality parameter, the denomination assignment result indicating whether or not the second object is allowed to obtain denomination data representing the denominations added to the queue of objects to be recommended.

8. A server, characterized in that the server comprises:

one or more processors;

a memory for storing the processor executable program code;

wherein the processor is configured to execute the program code to implement the reputation data allocation method according to any of claims 1 to 6.

9. A computer-readable storage medium, characterized in that when program code in the computer-readable storage medium is executed by a processor of a server, the server is enabled to execute the reputation data allocation method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the rating data allocation method of any of claims 1 to 6.