CN113038168A

CN113038168A - Data processing method and device

Info

Publication number: CN113038168A
Application number: CN202110382089.2A
Authority: CN
Inventors: 孙袁袁
Original assignee: Shanghai Bilibili Technology Co Ltd
Current assignee: Shanghai Bilibili Technology Co Ltd
Priority date: 2021-04-09
Filing date: 2021-04-09
Publication date: 2021-06-25

Abstract

The application provides a data processing method and a device, wherein the data processing method comprises the following steps: acquiring at least one heat value of a target live broadcast room and the jitter rate of each heat value; determining a first abnormal heat value of the at least one heat value, wherein the first abnormal heat value is a heat value with a jitter rate greater than or equal to a safety threshold; acquiring a first historical heat value corresponding to the first abnormal heat value, and replacing the first abnormal heat value with the first historical heat value; and determining the popularity value of the target live broadcast room according to the replaced first abnormal heat value. The problem of unstable people's qi value of final calculation under the condition that the acquired heat value appears unusually is solved, reliability and validity that the people's qi value is confirmed have been improved.

Description

Data processing method and device

Technical Field

The present application relates to the field of computer technologies, and in particular, to a data processing method. The application also relates to a data processing apparatus, a computing device, and a computer-readable storage medium.

Background

With the rapid development of computer technology and internet technology, user demand is also increasing explosively, and video live broadcast service is an effective way for users to communicate in real time, and is popular with a large number of users due to the characteristics of rich and colorful live broadcast types and real-time and rapid communication.

In the existing live broadcast system, popularity value is an important index for live broadcast platform room ranking. The popularity value can be comprehensively calculated according to certain weight by watching the number of people, the number of bullet screens and other factors in real time. However, in the above method, because there are many factors that depend on each other and each factor comes from a separate service, once any one of the factors has a service problem, the information cannot be acquired or dirty data or inaccurate information occurs, which may affect the stability of the popularity value. There is therefore a need for an effective solution to the above problems.

Disclosure of Invention

In view of this, the present application provides a data processing method. The application also relates to a data processing device, a computing device and a computer readable storage medium, which are used for solving the problem of unstable human qi value caused by abnormal data in the prior art.

According to a first aspect of embodiments of the present application, there is provided a data processing method, including:

acquiring at least one heat value of a target live broadcast room and the jitter rate of each heat value;

determining a first abnormal heat value of the at least one heat value, wherein the first abnormal heat value is a heat value with a jitter rate greater than or equal to a safety threshold;

acquiring a first historical heat value corresponding to the first abnormal heat value, and replacing the first abnormal heat value with the first historical heat value;

and determining the popularity value of the target live broadcast room according to the replaced first abnormal heat value.

According to a second aspect of embodiments of the present application, there is provided a data processing apparatus including:

a first acquisition module configured to acquire at least one heat value of a target live broadcast room and a jitter rate of each heat value;

a first determination module configured to determine a first abnormal heat value of the at least one heat value, wherein the first abnormal heat value is a heat value with a jitter rate greater than or equal to a safety threshold;

a replacing module configured to acquire a first historical heat value corresponding to the first abnormal heat value, and replace the first abnormal heat value with the first historical heat value;

a processing module configured to determine a popularity value of the target live broadcast room according to the replaced first abnormal heat value.

According to a third aspect of embodiments herein, there is provided a computing device comprising a memory, a processor and computer instructions stored on the memory and executable on the processor, the processor implementing the steps of the data processing method when executing the computer instructions.

According to a fourth aspect of embodiments of the present application, there is provided a computer-readable storage medium storing computer instructions which, when executed by a processor, implement the steps of the data processing method.

According to the data processing method, at least one heat value and a corresponding jitter rate of a target live broadcast room are obtained, a first abnormal heat value in the at least one heat value is determined, the first abnormal heat value is replaced by a first historical heat value, and a human atmosphere value of the target live broadcast room is further determined. The problem of unstable people's qi value of final calculation under the condition that the acquired heat value appears unusually is solved, reliability and validity that the people's qi value is confirmed have been improved. In addition, the method starts from the jitter rate of each heat value, automatically degrades according to the jitter condition, can dynamically adjust the weight of each heat value, improves the stability of the popularity value, and improves the experience of the user.

Drawings

Fig. 1 is a flowchart of a data processing method according to an embodiment of the present application;

FIG. 2A is a flow chart of a jitter rate method for determining a heat value according to an embodiment of the present application;

FIG. 2B is a flow chart of a jitter rate method for determining various heat values according to an embodiment of the present disclosure;

fig. 3 is a flowchart of a method for determining jitter of a hot value of a live broadcast room according to an embodiment of the present application;

fig. 4 is a flowchart of a jitter rate determination method according to an embodiment of the present application;

fig. 5A and 5B are process flow diagrams of a data processing method applied to a singing live broadcast according to an embodiment of the present application;

fig. 6 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present application;

fig. 7 is a block diagram of a computing device according to an embodiment of the present application.

Detailed Description

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application is capable of implementation in many different ways than those herein set forth and of similar import by those skilled in the art without departing from the spirit of this application and is therefore not limited to the specific implementations disclosed below.

The terminology used in the one or more embodiments of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the one or more embodiments of the present application. As used in one or more embodiments of the present application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present application refers to and encompasses any and all possible combinations of one or more of the associated listed items.

It will be understood that, although the terms first, second, etc. may be used herein in one or more embodiments of the present application to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first aspect may be termed a second aspect, and, similarly, a second aspect may be termed a first aspect, without departing from the scope of one or more embodiments of the present application. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.

First, the noun terms to which one or more embodiments of the present application relate are explained.

Live broadcasting, which is now often referred to as web-interactive live broadcasting, is a social and business approach. The computer or the mobile phone is used by the anchor to synchronously broadcast the things which are done by the anchor, audiences can watch the things through the website or the APP, money can be enjoyed for the favorite anchor or the favorite content, and the purpose of entertainment or teaching is achieved.

Popularity value of the live room: the real-time online number of people, the number of the bullet screens, the number of gifts and other numerical values calculated according to a certain proportion are substantially integrated, and the numerical values are used for ranking according to the popularity on the live broadcast platform.

In the present application, a data processing method is provided, and the present application relates to a data processing apparatus, a computing device, and a computer-readable storage medium, which are described in detail in the following embodiments one by one.

Fig. 1 shows a flowchart of a data processing method according to an embodiment of the present application, which specifically includes the following steps:

step 102: at least one heat value of a target live broadcast room and a jitter rate of each heat value are obtained.

Specifically, the live broadcast room refers to a live network program opened by a certain person or an organization in the internet era; the target live broadcast room is a live broadcast room needing to determine the popularity value; the popularity value is a popularity representing the popularity of the live broadcast room, and includes but is not limited to at least any one of the number of watching people, the number of barrage, the number of sending virtual gifts or the number of attention of the live broadcast room, or a value obtained by performing combined calculation based on any one of the number of watching people, the number of barrage, the number of sending virtual gifts or the number of attention of the live broadcast room; the watching number refers to the real number of people who watch the target live broadcast room in real time; the number of the barrages is the number of barrages sent by a live broadcast room in real time; the number of sent virtual gifts refers to the number and the total value number of the virtual gifts sent by the target live broadcast room; the attention number refers to the number of people in an attention target live broadcast room; the at least one popularity value comprises at least one of the number of people watching, the number of barracks, the number of sending virtual gifts and the number of concerns; the jitter rate refers to a short-term deviation degree between the acquired heat value and the actual heat value.

In practical application, in order to more accurately and effectively measure the popularity of the live broadcast room, the live broadcast room of the popularity to be determined, namely at least one heat value of the target live broadcast room and the jitter rate of the corresponding heat value can be obtained in real time, so that whether the obtained heat value is credible or not can be determined according to the jitter rate, corresponding adjustment can be made, and the accuracy of determining the popularity of the live broadcast room is improved to a certain extent.

For example, the popularity of a particular singing live broadcast room may be determined, and the judder rates of the number of viewers and the number of viewers, the judder rates of the number of barrages and the number of barrages, the judder rates of the number of virtual gifts delivered and the number of virtual gifts delivered, and the judder rates of the number of concerns and the number of concerns in the live broadcast room may be obtained.

In one or more embodiments of this embodiment, before the obtaining of the at least one thermal value and the jitter rate of the target live broadcast room, it is further required to determine the jitter rate of the at least one thermal value. The jitter rate of the heat value cannot be directly obtained through the system, and the jitter rate is determined according to the heat values of all the live broadcast rooms, so that the reliability of the jitter rate is improved. Alternatively, referring to fig. 2A, a specific implementation process for determining the jitter rate of the at least one thermal value may be as follows:

step 202: determining the number of live broadcast rooms in live broadcast in first preset time, and acquiring an ith heat value of each live broadcast room in the live broadcast rooms, wherein i is a positive integer.

Step 204: and acquiring the jitter condition of the ith heat value of each live broadcast room in the live broadcast rooms, and determining the number of live broadcast rooms with jittered ith heat values.

Step 206: and determining the change rate of the number of live broadcast rooms according to the number of live broadcast rooms which are live broadcast in the first preset time.

Step 208: and determining the jitter rate of the ith heat value according to the change rate of the number of the live broadcasting rooms, the number of live broadcasting rooms which are live broadcasting in the first preset time and the number of live broadcasting rooms in which the ith heat value is jittered.

Specifically, the first preset time is a time set for determining the jitter rate, and the setting mode may be set according to requirements, and may be five minutes, ten minutes, and the like; the ith heat value is the ith heat value in the at least one heat value, for example, if the at least one heat value is the number of people watching, the number of barrage, the number of sending virtual gifts and the number of attention, the 1 st heat value is the number of people watching, the 2 nd heat value is the number of barrage, the 3 rd heat value is the number of sending virtual gifts, and the 4 th heat value is the number of attention; the live broadcast room quantity change rate refers to the change condition of the data volume of the live broadcast room in the first preset time.

In practical application, the 1 st heat value is explained first, the number of live broadcast rooms in the first preset time is obtained from system service, and simultaneously the 1 st heat value of each live broadcast room needs to be read. And determining the jitter condition of each live broadcast room relative to the 1 st heat value according to the 1 st heat value of each live broadcast room, and further determining how many 1 st heat values of the live broadcast rooms have jitter. And then, determining the change rate of the number of the live broadcast rooms according to the obtained number of the live broadcast rooms in the first preset time, and further determining the jitter rate of the 1 st heat value according to the change rate of the number of the live broadcast rooms, the number of the live broadcast rooms in the first preset time and the number of the live broadcast rooms with jitter of the 1 st heat value.

Taking the popularity value of the number of watching people as an example, the number of all live broadcast rooms in nearly five minutes can be read from the people number service, and the watching number of people in each live broadcast room can be obtained. And respectively determining whether the number of the watching persons in each live broadcast room is jittered or not according to the number of the watching persons in each live broadcast room, and counting the number of the live broadcast rooms with jittered watching persons. And determining the change rate of the number of the live broadcast rooms according to the number of all live broadcast rooms in nearly five minutes, and determining the shaking rate of the number of the watching people according to the change rate of the number of the live broadcast rooms, the number of all live broadcast rooms in nearly five minutes and the number of live broadcast rooms in which the number of the watching people shakes.

Preferably, when determining the jitter rate of the at least one thermal value, the jitter rate of each of the at least one thermal value may be determined, that is, for each thermal value, the jitter rate of each thermal value may be determined by using the above-mentioned step of determining the jitter rate of the at least one thermal value. Specifically, referring to fig. 2B, a specific implementation process for determining the jitter rate of each of the at least one thermal value may be as follows:

Step 210: and judging whether the jitter rate of each of the at least one heat value is determined, if not, increasing the jitter rate by 1, executing step 202, namely, continuously executing the step of acquiring the ith heat value of each live broadcast room in the live broadcast room, and if so, ending the determination of the jitter rate of each of the at least one heat value.

In practical applications, in order to ensure that the jitter rate of each thermal value can be obtained, in the present embodiment, the jitter rate of each thermal value is determined by a cyclic method, so that it is necessary to make i equal to 1, that is, in the present embodiment, the jitter rate of the 1 st thermal value in at least one thermal value is determined first. After determining the jitter rate of the 1 st heat value of the at least one heat value, it is necessary to determine whether there is any more of the 2 nd heat value, the 3 rd heat value, and so on. If so, each thermal value is referenced to the above method to determine a corresponding jitter rate until a jitter rate for each thermal value is determined. If not, the process ends.

Following the above example, after the jitter rate of the number of viewers is determined, it is determined that at least one of the heat values further includes the heat value of the number of live broadcast, at this time, the number of all live broadcast rooms in the last five minutes can be read from the live broadcast service, and the number of live broadcast rooms can be obtained. And respectively determining whether the live broadcast rooms have the condition of bullet screen number jitter according to the bullet screen number of each live broadcast room, and counting the number of the live broadcast rooms with the bullet screen number jitter. And determining the change rate of the number of the live broadcast rooms according to the number of all live broadcast rooms in nearly five minutes, and determining the shaking rate of the bullet screen number according to the change rate of the number of the live broadcast rooms, the number of all live broadcast rooms in nearly five minutes and the shaking number of the bullet screen number. Then, continuing to judge, and if the jitter rate of each of the at least one heat value is found to be determined completely, ending the determination of the jitter rate of each of the at least one heat value.

In the application, through the acquisition of the ith heat value of the live broadcast room in the first preset time and the determination of the jitter condition, the jitter rate of the ith heat value is further determined, so that the ith heat value of all the live broadcast rooms in the first preset time is integrated, the jitter rate of the ith heat value is determined, the problem that the jitter rate is influenced due to the acquisition failure of the ith heat value of a single live broadcast room is avoided, and the robustness and the effectiveness of the jitter rate of the ith heat value are improved.

In one or more embodiments of this embodiment, referring to fig. 3, a specific implementation process of obtaining a jitter condition of an ith heat value of each live broadcast room in the live broadcast rooms may be as follows:

step 302: selecting a jth live broadcast room in the live broadcast rooms, and acquiring at least two ith heat values of the jth live broadcast room in the first preset time, wherein j is a positive integer.

Step 304: and carrying out differential calculation on the at least two ith heat values to obtain at least one differential value.

Step 306: and determining that the ith heat value of the jth live broadcast room is jittered when the difference value larger than the jitter threshold value exists in the at least one difference value, and determining that the ith heat value of the jth live broadcast room is not jittered when the difference value larger than the jitter threshold value does not exist in the at least one difference value.

Step 308: judging whether the jitter condition of the ith heat value of each live broadcast room in the live broadcast room is determined to be finished, if not, increasing j by 1, jumping to step 302, continuing to execute the step of acquiring at least two ith heat values in the preset time of the jth live broadcast room, and if so, finishing acquiring the jitter condition of the ith heat value of each live broadcast room in the live broadcast room.

Specifically, the jth live broadcast room refers to the jth live broadcast room in live broadcast rooms, and if three live broadcast rooms exist, the jth live broadcast room can be a 1 st live broadcast room, a 2 nd live broadcast room and a 3 rd live broadcast room respectively; the difference calculation refers to first-order difference calculation, namely, the difference value of adjacent values is judged, and the difference calculation can be used for detecting the stationarity of a time sequence; the differential value refers to a difference value between adjacent 2 values; the jitter threshold is a value used for judging whether the ith heat value jitters, the jitter is determined when the difference value of the ith heat value is larger than the jitter threshold, and the jitter is determined not when all the difference values of the ith heat value are smaller than or equal to the jitter threshold.

In practical applications, in order to ensure that each live broadcast room can be traversed to determine the jitter of the ith heat value of each live broadcast room, it is necessary to make j equal to 1, that is, determine the jitter of the ith heat value from the first live broadcast room. When the jitter of the ith heat value of each live broadcast room in the live broadcast rooms is acquired, the number of viewers in the 1 st live broadcast room (ith heat value) will be described as an example. The number of viewers at all time points in 5 minutes in the 1 st live broadcast room is read, and if 30 seconds is one time point, 5 × 2-10 pieces of data are obtained: x1, x2, x3, x4, x5, x6, x7, x8, x9 and x10, and carrying out differential calculation on the 10 data to obtain nine differential values, namely x2-x1, x3-x2, x4-x3, x5-x4, x6-x5, x7-x6, x8-x7, x9-x8 and x10-x 9. Judging whether the nine differential values have differential values larger than a shaking threshold value, if so, determining the 1 st live broadcast room as a live broadcast room with shaking watching people number; if not, the 1 st live broadcast room is determined as a live broadcast room with no jittering watching people. And then, determining the shaking conditions of the watching people in the 2 nd live broadcast room and the 3 rd live broadcast room according to the method until the shaking conditions of the watching people in all the live broadcast rooms are determined. Similarly, the jitter of the number of delivered virtual gifts, the number of barrage and the number of attention in the live broadcast room can be determined according to the method.

According to the method and the device, the jitter condition of the ith heat value of the live broadcast room is determined through differential calculation and the jitter threshold, the process of determining the jitter condition is simplified, and the data processing speed and the efficiency of determining the jitter condition are improved.

In one or more implementation manners of this embodiment, the determining a live broadcast time change rate according to the number of live broadcast times in the first preset time may be implemented by the following processes:

acquiring the number of live broadcasting rooms which are live broadcasting within a second preset time;

and determining the change rate of the number of live broadcast rooms according to the number of live broadcast rooms which are live broadcast in the first preset time and the number of live broadcast rooms which are live broadcast in the second preset time.

Specifically, the second preset time is similar to the first preset time, and a setting mode of the second preset time may be set according to a requirement, which is not limited herein, where the second preset time is the same as the first preset time in length and is adjacent to the first preset time, for example, the first preset time is a time period from this time to the first five minutes, the second preset time is a time period from the first five minutes to the tenth minutes, or for example, the current time is 10:00, the first preset time is a time period from 9:50 to 10:00, and the second preset time is a time period from 9:40 to 9: 50.

In practical application, on the basis of acquiring the number of live broadcast rooms which are live broadcast within first preset time, the number of live broadcast rooms which are live broadcast within second preset time can be acquired, so that the live broadcast room number change rate is determined according to the number of live broadcast rooms which are live broadcast within first preset time and the number of live broadcast rooms which are live broadcast within second preset time, and whether the number of live broadcast rooms which are live broadcast within first preset time is jittered or not can be determined. Determining the live broadcast room quantity change rate in a mode of formula 1 according to the live broadcast room quantity in live broadcast in the first preset time and the live broadcast room quantity in live broadcast in the second preset time, namely calculating the ratio of the absolute value of the difference between the live broadcast room quantity in live broadcast in the first preset time and the live broadcast room quantity in live broadcast in the second preset time to obtain the live broadcast room quantity change rate.

Q ═ N-M |/M (formula 1)

In formula 1, Q is the live broadcast room number change rate, N is the live broadcast room number that is live broadcast within a first preset time, and M is the live broadcast room number that is live broadcast within a second preset time.

For example, the number of live broadcast rooms live broadcast within the first preset time (within the first five minutes) is 1000, the number of live broadcast rooms live broadcast within the second preset time (within the first five minutes to the first ten minutes) is 2000, and the change rate of the number of live broadcast rooms is | 1000-.

It should be noted that, a change rate threshold may be preset: when the change rate of the number of live broadcast rooms is larger than the change rate threshold value, the number of live broadcast rooms is greatly reduced or increased in a short time, and the number of live broadcast rooms is basically steadily increased or unchanged in the short time, so that the problem of acquiring the number of live broadcast rooms at a high rate is solved; and when the variation rate of the number of live broadcasting rooms is smaller than or equal to the variation rate threshold value, the number of live broadcasting rooms in the live broadcasting is jittered within a normal range.

In the method and the device, the interfaces of the number of live broadcast rooms can be determined by determining the number change rate of the live broadcast rooms, parameters are provided for the subsequent jitter rate of the heat value determination, and the data processing speed is improved.

In one or more embodiments of this embodiment, referring to fig. 4, a specific implementation process of determining the jitter rate of the ith heat value according to the live broadcast time number change rate, the live broadcast time number being live broadcast within the first preset time, and the live broadcast time number of the ith heat value jitter may be as follows:

step 402: calculating the sum of the change rate of the number of the live broadcast rooms, the number of live broadcast rooms with jittering ith heat value and the ratio of the number of live broadcast rooms with live broadcast in the first preset time to obtain a jitter rate parameter of the ith heat value;

step 404: under the condition that the jitter rate parameter of the ith heat value is smaller than or equal to a jitter rate threshold value, storing the ith heat value of each live broadcast room in the live broadcast rooms at the current moment, and setting the jitter rate of the ith heat value to be zero;

step 406: and under the condition that the jitter rate parameter of the ith heat value is larger than the jitter rate threshold, calculating the difference value between the jitter rate parameter of the ith heat value and the jitter rate threshold to obtain the jitter rate of the ith heat value.

Specifically, the jitter rate parameter is a parameter for determining the jitter rate of the heat value; the jitter rate threshold is a value set for whether the hot value interface is normal or not. In practical application, when the jitter rate parameter of the ith heat value is determined according to the number of live broadcast rooms in live broadcast in the first preset time, the number of live broadcast rooms with jittered ith heat value and the change rate of the number of live broadcast rooms, the jitter rate parameter of the ith heat value can be calculated according to the method shown in formula 2. On the basis, the jitter rate parameter of the ith heat value is compared with the preset jitter rate parameter: when the jitter rate parameter of the ith heat value is smaller than or equal to the jitter rate threshold, indicating that the interface corresponding to the ith heat value is normal, storing the current time and the ith heat value of each live broadcast room at the current time, wherein the ith heat value can be stored in a cache, and setting the jitter rate of the ith heat value to be zero; and when the jitter rate parameter of the ith heat value is larger than the jitter rate threshold, indicating that the interface corresponding to the ith heat value has a problem, and setting the difference value between the jitter rate parameter of the ith heat value and the jitter rate threshold as the jitter rate of the ith heat value. Thus, the reliability of the jitter rate of the thermal value can be effectively improved.

t is Q + P/N (formula 2)

In formula 2, t is a jitter rate parameter of the ith heat value, Q is a live broadcast room number variation rate, P is a live broadcast room number of jitter of the ith heat value, and N is a live broadcast room number in the live broadcast in the first preset time.

For example, taking the number of viewers as an example, table 1 shows specific values of the number of live broadcast rooms in which the number of viewers is jittered, the live broadcast room change rate, the number of live broadcast rooms in which live broadcast is performed in nearly five minutes, and the jitter rate threshold, and the jitter rate parameter of the number of viewers is calculated according to equation 2 as: 1000/5000+0.1 is 0.3, 0.3 is more than 0.2, namely the corresponding interface of the number of viewers has problems, and the shaking rate of the number of viewers is set to 0.3-0.2 is 0.1.

TABLE 1 four parameters

Number of live broadcast rooms with jittering watching number	1000
		Live broadcast room number change rate	0.1
Number of live broadcast rooms being live broadcast in nearly five minutes	5000
		Jitter rate threshold	0.2

In the application, at least one heat value of the target live broadcast room and the jitter rate of each heat value are obtained, preparation work can be made for follow-up determination of the human value of the target live broadcast room, and the data processing speed and the reliability of determining the human value of the target live broadcast room are improved to a certain extent.

Step 104: determining a first abnormal heat value of the at least one heat value, wherein the first abnormal heat value is a heat value with a jitter rate greater than or equal to a safety threshold.

On the basis of obtaining at least one heat value of a target live broadcast room and the jitter rate of each heat value, further determining a first abnormal heat value of the at least one heat value, wherein the jitter rate is greater than or equal to a safety threshold value.

Specifically, the safety threshold may be a criterion for determining whether the heat value is available; the first abnormal heat value refers to an abnormal heat value of the at least one heat value, wherein the jitter rate is greater than or equal to a safety threshold value.

In practical application, the jitter rate of each of the at least one heat value needs to be compared with a safety threshold, and a heat value of the at least one heat value, of which the jitter rate is greater than or equal to the safety threshold, is determined as a first abnormal heat value.

For example, the at least one heat value includes four heat values of the number of viewers, the number of barrages, the number of virtual gifts, and the number of concerns, as shown in table 2. Setting a safety threshold value to be 30, wherein the jitter rates of the number of watching persons, the number of bullet screens and the number of attention are all smaller than the safety threshold value, and only the jitter rate of the number of sending virtual gifts is larger than 30. Therefore, the number of delivered virtual gifts is determined as the first abnormality threshold.

TABLE 2 jitter Rate for various Heat values

Heat value	Number of people watching	Number of bullet screens	Number of virtual gifts sent	Number of concerns
					Jitter rate	20	15	32	0

In the application, the safety threshold value is compared with the jitter rates of all the heat values, so that the first abnormal heat value is determined, preparation is made for subsequently processing the first abnormal heat value, and the data processing efficiency is improved.

Step 106: and acquiring a first historical heat value corresponding to the first abnormal heat value, and replacing the first abnormal heat value with the first historical heat value.

On the basis of determining a first abnormal heat value in at least one heat value, further acquiring a first historical heat value corresponding to the first abnormal heat value, and replacing the first abnormal heat value with the first historical heat value.

Specifically, the historical heat value refers to a heat value with reliability stored in a cache; the first historical heat value is a historical heat value corresponding to the first abnormal heat value, and the first historical heat value may be a historical heat value closest to the current time or a historical heat value with the highest reliability.

In practical application, when the jitter rate is greater than or equal to the safety threshold, it is indicated that most of the live broadcast rooms jitter relative to the first abnormal heat value, and the first abnormal heat value acquired this time may be considered to be unreliable and discarded. In general, the heat value does not fluctuate widely. When the interface corresponding to the first abnormal heat value has a problem, the first historical heat value is generally considered to be credible, and the latest or optimal first historical heat value stored in the cache is used for replacing the first abnormal heat value, so that the conditions that the first abnormal heat value is not credible and the first abnormal heat value in a large range shakes can be avoided, and the improvement of the user experience is facilitated.

In the above example, if the first abnormal heat value is the number of sent virtual gifts, the historical number of sent virtual gifts stored in the cache is obtained, the historical number of sent virtual gifts closest to the current time in the historical number of sent virtual gifts may be selected to replace the current number of sent virtual gifts, or the historical number of sent virtual gifts with the highest data in the historical number of sent virtual gifts may be selected to replace the current number of sent virtual gifts.

In the application, the first historical heat value corresponding to the first abnormal heat value is obtained, and the first historical heat value is used for replacing the first abnormal heat value, so that the data are more reliable and effective, the credibility of the popularity value of the follow-up calculation is improved, and the experience of the user is further improved.

Step 108: and determining the popularity value of the target live broadcast room according to the replaced first abnormal heat value.

On the basis of acquiring a first historical heat value corresponding to the first abnormal heat value and replacing the first abnormal heat value with the first historical heat value, further, the popularity value of the target live broadcast room can be determined according to the replaced first abnormal heat value.

In practical application, the replaced first abnormal heat value is processed, the first abnormal heat value can be directly used as the popularity value of the target live broadcast room, if the replaced first abnormal heat value is 4890, 4890 can be directly used as the popularity value of the target live broadcast room, that is, the popularity value of the target live broadcast room is 4890; the first abnormal heat value can also be subjected to weighting processing and the like to obtain the human value of the target live broadcast room, and the process is not limited in the application.

In one or more embodiments of this embodiment, before determining the popularity value of the target live broadcast room according to the replaced first abnormal heat value, an initial heat weight of each heat value needs to be obtained, and the initial heat weight of the first abnormal heat value is determined as the target heat weight of the replaced first abnormal heat value.

Specifically, the initial heat value weight refers to the weight of each heat value before the heat value is not processed; the target heat weight refers to the weight corresponding to the heat value after being processed.

In practical application, an initial heat weight can be obtained for each heat value of a target live broadcast room. For the first abnormal-heat-value, since the first abnormal-heat-value is replaced with the first historical heat-value, the initial heat-weight of the first abnormal-heat-value may be used as the target heat-weight of the first historical heat-value, i.e., the replaced first abnormal-heat-value.

Optionally, after determining the target heat weight of the replaced first abnormal heat value, a second abnormal heat value in the at least one heat value may be further determined, wherein the second abnormal heat value is a heat value with a jitter rate greater than zero and less than a safety threshold; and determining the target heat weight of the second abnormal heat value according to the jitter rate and the initial heat weight of the second abnormal heat value.

The jitter rate of the second abnormal heat value is larger than zero and smaller than the safety threshold, which indicates that only part of the second abnormal heat values of the live broadcast room are not credible but do not influence the whole second abnormal heat value, so that the weight of the second abnormal heat value can be reduced, and the influence of the second abnormal heat value on the subsequent calculation of the human atmosphere value is reduced. Compared with the first abnormal heat value, the second abnormal heat value is slightly abnormal, the second abnormal heat value does not need to be replaced, the initial heat weight can be adaptively adjusted according to the jitter rate of the second abnormal heat value and the equation 3, and the target heat weight of the second abnormal heat value can be obtained.

H ═ 1-w) H (formula 3)

In equation 3, H is the target heat weight of the second abnormal heat value, H is the initial heat weight of the second abnormal heat value, and w is the jitter rate of the second abnormal heat value.

For example, the at least one heat value includes four heat values of the number of viewers, the number of barrages, the number of virtual gifts, and the number of concerns, and the jitter rate and the initial heat weight are shown in table 3. Setting a safety threshold value to be 30, and if the jitter rate of the virtual gift number is greater than the safety threshold value, sending the virtual gift number to be a first abnormal heat value, wherein the initial heat weight of the virtual gift number is 0.25, namely the weight of the replaced first abnormal heat value; and if the jitter rates of the number of the watching people and the number of the barrage are both larger than zero and smaller than the safety threshold, the number of the watching people and the number of the barrage are second historical abnormal heat values, the target heat weights of the number of the watching people and the number of the barrage are respectively calculated according to the formula 3, and the target heat weight of the number of the watching people is (1-0.5) × 0.25 ═ 0.125, and the target heat weight of the number of the barrage is (1-11) × 0.35 ═ 3.5.

TABLE 3 jitter Rate and initial Heat weight for each Heat value

Heat value	Number of people watching	Number of bullet screens	Number of virtual gifts sent	Number of concerns
					Jitter rate	0.5	11	32	0
Initial heat weight	0.25	0.35	0.25	0.15

In the method and the device, the target heat weight of the first abnormal heat value and the second abnormal heat value after replacement is determined, a foundation is laid for determining the human value of the target live broadcast room based on the heat value and the weight in the follow-up process, and the efficiency of follow-up data processing is improved.

In one or more embodiments of this embodiment, a historical popularity value of the target live broadcast room and an initial historical popularity weight of the historical popularity value may also be obtained; and determining the target historical popularity weight of the historical popularity value according to the target popularity weight of the second abnormal popularity value and the initial historical popularity weight of the historical popularity value.

Specifically, the historical popularity value refers to the popularity value of the same live broadcast room at the same time within the past several days; the initial historical popularity weight is the weight corresponding to the historical popularity value before the adjustment; the target historical popularity weight refers to the weight corresponding to the adjusted historical popularity value.

In practical application, because the weight of the second abnormal heat value is reduced, the influence of the second abnormal heat value on the subsequent calculation popularity value is reduced, at the moment, a part of historical popularity values can be used as a substitute, namely, the weight of the historical popularity values is improved to ensure balance. Under the condition that a historical popularity value exists in a target live broadcast room, a historical popularity value and an initial historical popularity weight of the target live broadcast room are further obtained, then the target historical popularity weight is determined according to a second abnormal popularity value weight variation and the initial historical popularity weight, the initial historical popularity weight of the historical popularity value and the difference value between the target popularity weight and the initial popularity weight of the second abnormal popularity value can be summed, and the target historical popularity weight corresponding to the historical popularity value is obtained. Namely, the target popularity weight of the second abnormal popularity value is decreased or increased relative to the initial popularity weight, namely, the initial popularity weight of the historical popularity value is correspondingly increased or decreased, so as to obtain the target historical popularity weight. As can be seen from equation 3, if the target popularity weight of the second abnormal popularity value is decreased wh relative to the initial popularity weight, the initial historical popularity weight of the historical popularity value is correspondingly increased wh, and then the target historical popularity weight is obtained.

For example, a historical popularity value and an initial historical popularity weight of a certain live broadcast room are obtained, where the initial historical popularity weight is 0.3, and the target popularity weight and the initial popularity weight of the second abnormal popularity value are 0.2 and 0.5, respectively, and it is seen that the weight of the second abnormal popularity value is reduced by 0.3, and the target historical popularity weight 0.3+0.3 is 0.6 by adding 0.3 to the initial historical popularity weight.

In the application, the weight of the historical popularity value is adjusted according to the weight of the second abnormal popularity value, so that the phenomenon that the popularity value is unreliable in subsequent calculation due to the fact that the popularity value of part of live broadcast rooms is unavailable is avoided to a certain extent, and the reliability of the popularity value in subsequent calculation is improved.

Optionally, when determining the popularity value of the target live broadcast room, the popularity value of the target live broadcast room may be further determined according to the historical popularity value and the target historical popularity weight, the target popularity weight of the first abnormal popularity value and the first abnormal popularity value, the target popularity weight of the second abnormal popularity value and the second abnormal popularity value, and/or the target popularity weights of other popularity values and the other popularity values, wherein the other popularity values are popularity values other than the first abnormal popularity value and the second abnormal popularity value in the at least one popularity value.

Specifically, the other heat value may be a normal heat value in the at least one heat value, where the normal heat value is a heat value with a jitter rate of zero, and for the normal heat value, the heat value and the weight thereof may be kept unchanged, that is, the target heat weight of the other heat value is equal to the initial heat weight.

In practical application, the method for determining the popularity value of the target live broadcast room can be various, the popularity value can be determined independently according to the historical popularity value and the target historical popularity weight, can be determined independently according to each popularity value and the target popularity weight corresponding to the popularity value, and can also be determined by integrating the historical popularity value, several of the popularity values and the corresponding weights. When the popularity value of the target live broadcast room is determined by integrating the historical popularity value and each popularity value, the popularity value can be calculated by a method shown in formula 4.

z＝x₁*a+x₂*b+x₃*c+x₄D + y e (formula 4)

In formula 4, z is the popularity of the target live broadcast room, x₁A is the target heat weight of the number of viewers, x₂Target heat weight, x, of number of barrages, b₃A target popularity weight of the number of delivered virtual gifts, c，x₄D is the target heat weight of the attention number, y is the historical popularity value, and e is the target historical weight of the historical popularity value.

For example, the at least one popularity value includes the number of viewers, the number of barrages, the number of virtual gifts sent, and the number of concerns, and the popularity value of the current target live broadcast room is determined by integrating each popularity value and the historical popularity value, as shown in table 4. It should be noted that the heat value given in table 4 is a processed heat value, i.e., the first abnormal heat value is used for the historical heat value. In this case, the air value of the target live broadcast room can be determined by equation 4, that is, the air value of the target live broadcast room is 0.2 × 1000+750 × 0.1+300 × 0.1+200 × 0.3+500 × 0.3 — 515.

TABLE 4 parameters for various Heat values and historical popularity values

In one or more embodiments of this embodiment, after the popularity value of the target live broadcast room is determined, the target live broadcast room may be determined as a high-quality live broadcast room and recommended to a user when the popularity value of the target live broadcast room is greater than a popularity threshold, and the target live broadcast room is determined as a common live broadcast room when the popularity value of the target live broadcast room is less than or equal to the popularity threshold; and/or determining the popularity ranking of the target live broadcast room according to the popularity value of the target live broadcast room, recommending the target live broadcast room to a user under the condition that the popularity ranking of the target live broadcast room is before the nth name, wherein n is a positive integer greater than or equal to 2, and under the condition that the popularity ranking of the target live broadcast room is after the nth name and the nth name, not recommending the target live broadcast room.

Specifically, the popularity threshold refers to a preset basis for judging whether the target live broadcast room is a high-quality live broadcast room. In practical application, whether the popularity value of the target live broadcast room is larger than a preset popularity threshold value or not can be judged. If yes, the target live broadcast room is liked by the public, and the target live broadcast room is determined to be a high-quality live broadcast room and recommended to the user; if not, the target live broadcast room is a common live broadcast room, and only a small part of people probably like the live broadcast room, so that the target live broadcast room is not recommended. In addition, the popularity ranking of the target live broadcast room can be determined according to the popularity value of the target live broadcast room, when the ranking of the target live broadcast room is before the nth name, the target live broadcast room is particularly popular and popular with high probability, and the target live broadcast room is recommended to the user; the ranking of the target live broadcast room is the nth name or after the nth name, which indicates that the popularity of the target live broadcast room is low, most people probably do not like the target live broadcast room, and therefore the target live broadcast room is not recommended. Where n can be determined according to the actual situation. It should be noted that the two recommendation methods can be used separately or comprehensively, that is, as long as the target live broadcast room meets one of the recommendation conditions, the target live broadcast room is recommended to the user.

For example, the popularity value of a food live broadcast room is 500, the popularity threshold value is 550, and at this time, the popularity value of the food live broadcast room is lower than the popularity threshold value, that is, the food live broadcast room is a common live broadcast room; and the popularity ranking of the food live broadcasting room is 9 th, n is preset to be 10, and the food live broadcasting room is recommended to the user by combining the two conditions.

The following will further describe the data processing method with reference to fig. 5A and 5B by taking an application of the data processing method provided by the present application in a singing live broadcast as an example. Fig. 5A and 5B show a processing flow chart of a data processing method applied to a singing live broadcast room according to an embodiment of the present application, and specifically include the following steps:

step 502: the number of viewers/the number of barracks/the number of virtual gifts/the number of concerns in each live broadcast room in nearly five minutes are acquired.

Step 504: the number of live broadcast rooms for which the number of viewers/the number of barrages/the number of virtual gifts/the number of concerns are jittered is determined.

Step 506: and determining the live broadcast room number fluctuation rate.

It should be noted that, step 504 and step 506 may be performed sequentially or simultaneously, which is not limited in this application.

Step 508: the jitter rate parameter of the number of watching persons/the number of bullet screens/the number of virtual gifts/the number of concerns is calculated.

Step 510: and judging whether the jitter rate parameter of the number of watching people/the number of the bullet screens/the number of sending the virtual gifts/the number of the attention is larger than a jitter rate threshold value or not.

If yes, go to step 512, otherwise go to step 514.

Step 512: the shaking rate of the number of watching persons/the number of the pop-ups/the number of sending the virtual gifts/the number of concerns is determined to be the difference value of the shaking rate parameter of the number of watching persons/the number of the pop-ups/the number of sending the virtual gifts/the number of concerns and the shaking rate threshold value.

Step 514: the shaking rate of the number of watching persons/the number of the bullet screens/the number of sending the virtual gifts/the number of concerns is determined to be zero, and the number of watching persons/the number of the bullet screens/the number of sending the virtual gifts/the number of concerns of each live broadcast room currently in live broadcast are stored.

It should be noted that steps 502 to 514 are processes of determining the shake rate of the number of viewers, determining the shake rate of the number of pop-ups, the shake rate of the number of virtual gifts, and the shake rate of the number of attention. In addition, the judder rate of the number of viewers, the judder rate of the number of pop-ups, the judder rate of the number of virtual gifts sent, and the judder rate of the number of attention may be determined sequentially, or may be determined in parallel, or may be determined in other sequences, which is not limited in the present application.

Step 516: the method comprises the steps of obtaining the number of watching persons, the number of barrages, the number of virtual gifts and the number of concerns in a target singing live broadcast room, and respectively obtaining the shaking rate of the number of watching persons, the shaking rate of the number of barrages, the shaking rate of the number of virtual gifts and the shaking rate of the number of concerns.

Step 518: and acquiring historical popularity values of the target singing live broadcast room.

Step 520: and acquiring the weights of the number of the watching people, the number of the bullet screens, the number of the delivered virtual gifts, the number of the concerns and the historical popularity value.

Step 522: it is determined whether the jitter rate of the number of viewers/the number of barracks/the number of virtual gifts/the number of concerns is equal to zero.

If yes, go to step 524; if not, go to step 526.

Step 524: the weights of the number of viewers/the number of barracks/the number of delivered virtual gifts/the number of concerns and the number of viewers/the number of barracks/the number of delivered virtual gifts/the number of concerns are kept constant.

Step 526: whether the jitter rate of the number of watching persons/the number of the bullet screens/the number of sending the virtual gifts/the number of the concerns is smaller than a safety threshold value is judged.

If yes, go to step 528; if not, go to step 530.

Step 528: keeping the number of watching persons/the number of the barrage/the number of sending the virtual gifts/the number of the attention unchanged, adjusting the weight of the number of watching persons/the number of the barrage/the number of sending the virtual gifts/the number of the attention, and simultaneously adjusting the weight of the historical popularity value.

For example, if the weight of the number of viewers before the adjustment is a and the weight of the number of viewers before the adjustment is e, the weight of the number of viewers after the adjustment is a ═ a (1 — the jitter rate of the number of viewers), and the weight of the number of viewers after the adjustment is e ═ e-a ═ the jitter rate of the number of viewers.

Step 530: the new historical watching number/bullet screen number/virtual gift number/attention number is used to replace the watching number/bullet screen number/virtual gift number/attention number with the same weight as the watching number/bullet screen number/virtual gift number/attention number.

Step 532: and determining the popularity value of the target singing live broadcast room according to the processed watching population, the number of the barrages, the number of the virtual gifts, the attention number, the historical popularity value and the corresponding weight.

Step 534: and judging whether the popularity value of the target singing live broadcast room is greater than the popularity threshold value.

If yes, go to step 536; if not, go to step 538.

Step 536: and recommending a target singing live broadcast room.

Step 538: a target singing live room is not recommended.

According to the data processing method applied to the singing live broadcast room, the number of people watching, the number of barrage, the number of delivered virtual gifts, the number of concerns and the corresponding shaking rate of the target singing live broadcast room are obtained, the number of people watching, the number of barrage, the number of delivered virtual gifts and the number of concerns are further determined, and meanwhile the weight of the historical popularity value is adjusted, so that the popularity value of the target live broadcast room is determined. The problem of unstable people's qi value of final calculation under the condition that the acquired heat value appears unusually is solved, reliability and validity that the people's qi value is confirmed have been improved. In addition, the method starts from the jitter rate of each heat value, automatically degrades according to the jitter condition, can dynamically adjust the weight of each heat value, improves the stability of the popularity value, and improves the experience of the user.

Corresponding to the above method embodiment, the present application further provides an embodiment of a data processing apparatus, and fig. 6 shows a schematic structural diagram of a data processing apparatus provided in an embodiment of the present application. As shown in fig. 6, the apparatus includes:

a first obtaining module 602 configured to obtain at least one heat value of a target live broadcast room and a jitter rate of each heat value;

a first determining module 604 configured to determine a first abnormal heat value of the at least one heat value, wherein the first abnormal heat value is a heat value with a jitter rate greater than or equal to a safety threshold;

a replacing module 606 configured to obtain a first historical heat value corresponding to the first abnormal heat value, and replace the first abnormal heat value with the first historical heat value;

a processing module 608 configured to determine a popularity value of the target live broadcast room according to the replaced first abnormal heat value.

In one or more implementations of this embodiment, the apparatus further includes a second obtaining module configured to:

in order to obtain the initial heat weight of each heat value, the initial heat weight of the first abnormal heat value is determined as the target heat weight of the replaced first abnormal heat value.

In one or more implementations of this embodiment, the apparatus further includes a second determining module configured to:

determining a second abnormal heat value of the at least one heat value, wherein the second abnormal heat value is a heat value with a jitter rate greater than zero and less than a safety threshold;

and determining the target heat weight of the second abnormal heat value according to the jitter rate and the initial heat weight of the second abnormal heat value.

In one or more implementations of this embodiment, the apparatus further includes:

a third obtaining module configured to obtain a historical popularity value of the target live broadcast room and an initial historical popularity weight of the historical popularity value;

a third determination module configured to determine a target historical popularity weight of the historical popularity value according to the target popularity weight of the second abnormal popularity value and the initial historical popularity weight of the historical popularity value.

In one or more implementations of this embodiment, the apparatus further includes a fourth determining module further configured to:

determining the popularity value of the target live broadcast room according to the historical popularity value and the target historical popularity weight, the target popularity weight of the first abnormal popularity value and the first abnormal popularity value, the target popularity weight of the second abnormal popularity value and/or the target popularity weights of other popularity values and the other popularity values, wherein the other popularity values are popularity values of the at least one popularity value except the first abnormal popularity value and the second abnormal popularity value.

In one or more implementations of this embodiment, the apparatus further includes a recommendation module configured to:

under the condition that the popularity value of the target live broadcast room is larger than the popularity threshold value, determining the target live broadcast room as a high-quality live broadcast room and recommending the high-quality live broadcast room to a user; and/or

And determining the popularity ranking of the target live broadcast room according to the popularity value of the target live broadcast room, and recommending the target live broadcast room to a user under the condition that the popularity ranking of the target live broadcast room is before the nth name, wherein n is a positive integer greater than or equal to 2.

a fifth determination module configured to determine a jitter rate for each of the at least one thermal value.

In one or more implementations of this embodiment, the fifth determining module is further configured to:

determining the number of live broadcast rooms in live broadcast in first preset time, and acquiring an ith heat value of each live broadcast room in the live broadcast rooms, wherein i is a positive integer;

acquiring the jitter condition of the ith heat value of each live broadcast room in the live broadcast rooms, and determining the number of live broadcast rooms with jittered ith heat values;

determining the change rate of the number of live broadcast rooms according to the number of live broadcast rooms in live broadcast in the first preset time;

and determining the jitter rate of the ith heat value according to the change rate of the number of the live broadcasting rooms, the number of live broadcasting rooms which are live broadcasting in the first preset time and the number of live broadcasting rooms in which the ith heat value is jittered.

and judging whether the jitter rate of each heat value in the at least one heat value is determined, if not, increasing by 1, and continuously executing the step of acquiring the ith heat value of each live broadcast room in the live broadcast room.

selecting a jth live broadcast room in the live broadcast rooms, and acquiring at least two ith heat values of the jth live broadcast room in the first preset time, wherein j is a positive integer;

carrying out differential calculation on the at least two ith heat values to obtain at least one differential value;

determining the ith heat value jitter of the jth live broadcast room under the condition that the at least one differential value has a differential value larger than a jitter threshold;

and judging whether the jitter condition of the ith heat value of each live broadcast room in the live broadcast rooms is determined to be finished, if not, increasing j by 1, and continuously executing the step of acquiring at least two ith heat values in the preset time of the jth live broadcast room.

and calculating the ratio of the absolute value of the difference between the number of live broadcasting rooms which are live broadcasting in the first preset time and the number of live broadcasting rooms which are live broadcasting in the second preset time to obtain the change rate of the number of live broadcasting rooms.

calculating the sum of the change rate of the number of the live broadcast rooms, the number of live broadcast rooms with jittering ith heat value and the ratio of the number of live broadcast rooms with live broadcast in the first preset time to obtain a jitter rate parameter of the ith heat value;

under the condition that the jitter rate parameter of the ith heat value is smaller than or equal to a jitter rate threshold value, storing the ith heat value of each live broadcast room in the live broadcast rooms at the current moment, and setting the jitter rate of the ith heat value to be zero;

and under the condition that the jitter rate parameter of the ith heat value is larger than the jitter rate threshold, calculating the difference value between the jitter rate parameter of the ith heat value and the jitter rate threshold to obtain the jitter rate of the ith heat value.

In one or more implementations of this embodiment, the at least one popularity value includes at least one of a number of viewers, a number of barrages, a number of virtual gifts sent, and a number of concerns.

The application provides a data processing device, through at least one heat value and the corresponding shake rate that acquire the live room of target, confirm first unusual heat value in the at least one heat value to use first historical heat value to replace first unusual heat value, further confirm the people's smell value of the live room of target. The problem of unstable people's qi value of final calculation under the condition that the acquired heat value appears unusually is solved, reliability and validity that the people's qi value is confirmed have been improved. In addition, the method starts from the jitter rate of each heat value, automatically degrades according to the jitter condition, can dynamically adjust the weight of each heat value, improves the stability of the popularity value, and improves the experience of the user.

The above is a schematic configuration of a data processing apparatus of the present embodiment. It should be noted that the technical solution of the data processing apparatus and the technical solution of the data processing method belong to the same concept, and details that are not described in detail in the technical solution of the data processing apparatus can be referred to the description of the technical solution of the data processing method.

FIG. 7 illustrates a block diagram of a computing device 700 provided in accordance with one embodiment of the present description. The components of the computing device 700 include, but are not limited to, memory 710 and a processor 720. Processor 720 is coupled to memory 710 via bus 730, and database 750 is used to store data.

Computing device 700 also includes access device 740, access device 740 enabling computing device 700 to communicate via one or more networks 760. Examples of such networks include the Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the internet. Access device 740 may include one or more of any type of network interface, e.g., a Network Interface Card (NIC), wired or wireless, such as an IEEE802.11 Wireless Local Area Network (WLAN) wireless interface, a worldwide interoperability for microwave access (Wi-MAX) interface, an ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a bluetooth interface, a Near Field Communication (NFC) interface, and so forth.

In one embodiment of the present description, the above-described components of computing device 700, as well as other components not shown in FIG. 7, may also be connected to each other, such as by a bus. It should be understood that the block diagram of the computing device architecture shown in FIG. 7 is for purposes of example only and is not limiting as to the scope of the present description. Those skilled in the art may add or replace other components as desired.

Computing device 700 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., tablet, personal digital assistant, laptop, notebook, netbook, etc.), mobile phone (e.g., smartphone), wearable computing device (e.g., smartwatch, smartglasses, etc.), or other type of mobile device, or a stationary computing device such as a desktop computer or PC. Computing device 700 may also be a mobile or stationary server.

Wherein the steps of the data processing method are implemented by processor 720 when executing the computer instructions.

The above is an illustrative scheme of a computing device of the present embodiment. It should be noted that the technical solution of the computing device and the technical solution of the data processing method belong to the same concept, and details that are not described in detail in the technical solution of the computing device can be referred to the description of the technical solution of the data processing method.

An embodiment of the present application further provides a computer readable storage medium, which stores computer instructions, and the computer instructions, when executed by a processor, implement the steps of the data processing method as described above.

The above is an illustrative scheme of a computer-readable storage medium of the present embodiment. It should be noted that the technical solution of the storage medium belongs to the same concept as the technical solution of the data processing method, and details that are not described in detail in the technical solution of the storage medium can be referred to the description of the technical solution of the data processing method.

The foregoing description of specific embodiments of the present application has been presented. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The computer instructions comprise computer program code which may be in the form of source code, object code, an executable file or some intermediate form, or the like. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.

It should be noted that, for the sake of simplicity, the above-mentioned method embodiments are described as a series of acts or combinations, but those skilled in the art should understand that the present application is not limited by the described order of acts, as some steps may be performed in other orders or simultaneously according to the present application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

The preferred embodiments of the present application disclosed above are intended only to aid in the explanation of the application. Alternative embodiments are not exhaustive and do not limit the invention to the precise embodiments described. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the application and its practical applications, to thereby enable others skilled in the art to best understand and utilize the application. The application is limited only by the claims and their full scope and equivalents.

Claims

1. A data processing method, comprising:

2. The method of claim 1, wherein prior to determining the popularity value of the target live broadcast room based on the replaced first outlier heat value, further comprising:

and acquiring an initial heat weight of each heat value, and determining the initial heat weight of the first abnormal heat value as a target heat weight of the replaced first abnormal heat value.

3. The method of claim 2, wherein after determining the initial heat weight for the first abnormal heat value as the target heat weight for the replaced first abnormal heat value, further comprising:

4. The method of claim 3, further comprising:

acquiring a historical popularity value of the target live broadcast room and an initial historical popularity weight of the historical popularity value;

and determining the target historical popularity weight of the historical popularity value according to the target popularity weight of the second abnormal popularity value and the initial historical popularity weight of the historical popularity value.

5. The method of claim 4, further comprising:

6. The method of any one of claims 1-5, further comprising:

7. The method of claim 1, wherein before obtaining at least one heat value and a jitter rate for each heat value of the target live broadcast room, further comprising:

determining a jitter rate for the at least one thermal value.

8. The method of claim 7, wherein determining the jitter rate for the at least one thermal value comprises:

9. The method of claim 8, wherein after determining the jitter rate for the ith heat value according to the live broadcast room number variation rate, the live broadcast room number being live broadcast in the first preset time and the live broadcast room number jittered by the ith heat value, the method further comprises:

10. The method of claim 8, wherein obtaining jitter of an ith heat value of each of the live broadcast rooms comprises:

11. The method of claim 8, wherein determining the live broadcast time number change rate according to the live broadcast time number in the first preset time comprises:

12. The method of claim 11, wherein determining the live broadcast time number change rate according to the live broadcast time number in the first preset time and the live broadcast time number in the second preset time comprises:

13. The method of claim 8, wherein determining the jitter rate for the ith heat value according to the live broadcast room number variation rate, the live broadcast room number being live broadcast within the first preset time, and the live broadcast room number jittered by the ith heat value comprises:

14. A data processing apparatus, comprising:

15. A computing device comprising a memory, a processor, and computer instructions stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any one of claims 1-13 when executing the computer instructions.

16. A computer-readable storage medium storing computer instructions, which when executed by a processor, perform the steps of the method of any one of claims 1 to 13.