CN115271827A - Advertisement audio pushing method and device, electronic equipment and storage medium - Google Patents

Advertisement audio pushing method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN115271827A
CN115271827A CN202210991273.1A CN202210991273A CN115271827A CN 115271827 A CN115271827 A CN 115271827A CN 202210991273 A CN202210991273 A CN 202210991273A CN 115271827 A CN115271827 A CN 115271827A
Authority
CN
China
Prior art keywords
advertisement
audio
advertisement audio
estimated
audios
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210991273.1A
Other languages
Chinese (zh)
Inventor
汤宗锦
贺来朋
周鸿斌
叶剑豪
吕翔
印晶晶
浦晟骄
赵光程
卢恒
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Himalaya Technology Co ltd
Original Assignee
Shanghai Himalaya Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Himalaya Technology Co ltd filed Critical Shanghai Himalaya Technology Co ltd
Priority to CN202210991273.1A priority Critical patent/CN115271827A/en
Publication of CN115271827A publication Critical patent/CN115271827A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0251—Targeted advertisements
    • G06Q30/0269—Targeted advertisements based on user profile or attribute
    • G06Q30/0271—Personalized advertisement
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/63—Querying
    • G06F16/635—Filtering based on additional data, e.g. user or group profiles
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/68—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/683—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0241—Advertisements
    • G06Q30/0277—Online advertisement

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Data Mining & Analysis (AREA)
  • Game Theory and Decision Science (AREA)
  • Multimedia (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Library & Information Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The embodiment of the invention provides a method and a device for pushing advertisement audio, electronic equipment and a storage medium, and relates to the technical field of computers. Firstly, an advertisement audio set corresponding to a main broadcast identification of a current main broadcast is obtained, wherein the advertisement audio set comprises a plurality of advertisement audios with tone characteristics corresponding to the tone characteristics of the current main broadcast. And then determining a target advertisement audio frequency from the advertisement audio frequency set, wherein the target advertisement audio frequency is the advertisement audio frequency with the maximum estimated click rate or the maximum estimated output value in the advertisement audio frequency set. And then, playing the target advertisement audio at the advertisement playing time node corresponding to the currently played audio, wherein the currently played audio belongs to the current anchor. Therefore, the tone characteristics of the target advertisement audio pushed to the user and the currently played audio currently listened to by the user are ensured to be consistent, and the listening experience of the user is not interfered.

Description

Advertisement audio pushing method and device, electronic equipment and storage medium
Technical Field
The invention relates to the technical field of computers, in particular to a method and a device for pushing advertisement audio, electronic equipment and a storage medium.
Background
Nowadays, the consumption of internet information contents is developing vigorously, and a large amount of new contents are generated every day. In an audio scenario, the advertisement needs to be pushed to the user in the form of audio.
In the prior art, an advertiser usually makes an advertisement and then delivers the advertisement to a platform, and the platform is responsible for advertisement delivery, but under the condition, the condition that the pushed advertisement audio is different from the sound which the user listens to can occur, and the user experience can be seriously reduced.
Disclosure of Invention
The invention aims to provide a method and a device for pushing advertisement audio, electronic equipment and a storage medium, so as to solve the problems in the prior art.
Embodiments of the invention may be implemented as follows:
in a first aspect, the present invention provides a method for pushing advertisement audio, including:
acquiring an advertisement audio set corresponding to a main broadcast identification of a current main broadcast; the advertisement audio frequency set comprises a plurality of advertisement audio frequencies; the tone color characteristics of the advertisement audio correspond to the tone color characteristics of the current anchor;
determining a target advertisement audio from the set of advertisement audio; the target advertisement audio is the advertisement audio with the maximum estimated click rate or the maximum estimated output value in the advertisement audio set;
and playing the target advertisement audio at an advertisement playing time node corresponding to the currently played audio, wherein the currently played audio belongs to the current anchor.
In an optional embodiment, each of the advertisement audios has corresponding attribute information, and when the attribute information in the advertisement audio set is at least one first advertisement audio of an advertisement to be displayed, the step of determining a target advertisement audio from the advertisement audio set includes:
calculating the estimated click rate of each first advertisement audio;
sorting the estimated click rates of all the first advertisement audios in a descending order to obtain a first sorting result;
and taking the first advertisement audio corresponding to the first estimated click rate in the first sequencing result as the target advertisement audio.
In an optional embodiment, each of the advertisement audios has corresponding attribute information, and when the advertisement audio set includes at least one second advertisement audio of an advertisement to be clicked, the step of determining a target advertisement audio from the advertisement audio set includes:
calculating the estimated click rate of each second advertisement audio;
calculating an estimated output value of each second advertisement audio based on the estimated click rate and click output parameters;
sorting the estimated output values of all the second advertisement audios in a descending order to obtain a second sorting result;
and taking the second advertisement audio positioned at the first in the second sequencing result as the target advertisement audio.
In an optional embodiment, each of the advertisement audios has corresponding attribute information, and when the advertisement audio set includes at least one third advertisement audio of an advertisement to be converted, the step of determining a target advertisement audio from the advertisement audio set includes:
calculating the estimated click rate and the estimated conversion rate of each third advertisement audio;
calculating an estimated output value of each third advertisement audio based on the estimated click rate, the estimated conversion rate and the conversion output parameter;
sorting the estimated output values of all the third advertisement audios in a descending order to obtain a third sorting result;
and taking the third advertisement audio corresponding to the first estimated output value in the third sequencing result as the target advertisement audio.
In an optional embodiment, each of the advertisement audios has corresponding attribute information, and when the advertisement audio set includes at least one second advertisement audio of which the attribute information is an advertisement to be clicked and at least one third advertisement audio of which the attribute information is an advertisement to be converted, the step of determining a target advertisement audio from the advertisement audio set includes:
calculating the estimated click rate of each second advertisement audio, and calculating the estimated output value of each second advertisement audio based on the estimated click rate and the click output parameters;
calculating the estimated click rate and the estimated conversion rate of each third advertisement audio, and calculating the estimated output value of each third advertisement audio based on the estimated click rate, the estimated conversion rate and the conversion output parameter;
mixing the estimated output values of all the second advertisement audios and the estimated output values of all the third advertisement audios, and then performing descending sorting to obtain a mixed sorting result;
and taking the second advertisement audio or the third advertisement audio corresponding to the first estimated output value in the mixed sequencing result as the target advertisement audio.
In an optional embodiment, before the step of obtaining the set of advertisement audio corresponding to the anchor identification of the current anchor, the method further comprises:
inputting an advertisement text into a voice synthesis model corresponding to the current anchor to obtain an advertisement audio, wherein the voice synthesis model is obtained by utilizing the recorded audio of the current anchor to train in advance;
and establishing a mapping relation between the advertisement audio and the anchor mark, and determining attribute information of the advertisement audio based on a preset advertisement putting mode.
In an alternative embodiment, the method further comprises:
acquiring the current-day actual push data of each advertisement audio;
and aiming at each advertisement audio frequency, calculating the delivery profit of the current anchor according to the actual delivery data of the current day and the output parameters of the advertisement audio frequency.
In a second aspect, the present invention provides an advertisement audio pushing apparatus, including:
the acquisition module is used for acquiring an advertisement audio set corresponding to the anchor identification of the current anchor; the advertisement audio set comprises a plurality of advertisement audios; the tone color characteristics of the advertisement audio correspond to the tone color characteristics of the current anchor; a processing module to:
determining a target advertisement audio from the set of advertisement audio; the target advertisement audio is the advertisement audio with the maximum estimated click rate or the maximum estimated output value in the advertisement audio set;
and playing the target advertisement audio at an advertisement playing time node corresponding to the currently played audio, wherein the currently played audio belongs to the current anchor.
In a third aspect, the present invention provides an electronic device comprising: a memory and a processor, the memory storing machine readable instructions executable by the processor, the processor executing the machine readable instructions when the electronic device is running to implement the method according to any one of the preceding embodiments.
In a fourth aspect, the present invention provides a storage medium storing a computer program which, when executed by a processor, implements the method of any one of the preceding embodiments.
Compared with the prior art, the embodiment of the invention provides an advertisement audio pushing method, an advertisement audio pushing device, electronic equipment and a storage medium. And then determining a target advertisement audio frequency from the advertisement audio frequency set, wherein the target advertisement audio frequency is the advertisement audio frequency with the maximum estimated click rate or the maximum estimated output value in the advertisement audio frequency set. And then, playing the target advertisement audio at the advertisement playing time node corresponding to the currently played audio, wherein the currently played audio belongs to the current anchor. Therefore, the tone characteristics of the target advertisement audio pushed to the user and the currently played audio currently listened to by the user are ensured to be consistent, and the listening experience of the user is not interfered.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a flowchart illustrating a method for pushing advertisement audio according to an embodiment of the present invention.
Fig. 2 is a second flowchart illustrating a method for pushing advertisement audio according to an embodiment of the present invention.
Fig. 3 is a third schematic flowchart of a method for pushing an advertisement audio according to an embodiment of the present invention.
Fig. 4 is a fourth flowchart illustrating a method for pushing advertisement audio according to an embodiment of the present invention.
Fig. 5 is a fifth flowchart illustrating a method for pushing an advertisement audio according to an embodiment of the present invention.
Fig. 6 is a schematic structural diagram of an advertisement audio pushing device according to an embodiment of the present invention.
Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
Furthermore, the appearances of the terms "first," "second," and the like, if any, are only used to distinguish one description from another and are not to be construed as indicating or implying relative importance.
It should be noted that the features of the embodiments of the present invention may be combined with each other without conflict.
Nowadays, the consumption of internet information contents is developing vigorously, and a large amount of new contents are generated every day. In an audio scene, advertisement push needs to be performed to a user in the form of sound stream advertisement.
The mainstream thinking at present is that the commercialization and the user experience are in opposite positions, most of the advertisement styles and contents at present pursue memory points and ignore the user experience, however, the stinging feeling brought by the memory points is very objectionable to the user, and thus, the thought and research for balancing the advertisement and the user experience are urgent. In the prior art, the sound stream advertisement is usually made by an advertiser and delivered to a platform for advertisement delivery, the making and delivery are completely split, the tone of the advertisement material made by the advertiser is solidified, and the condition that the tone is completely different from the current audio tone of the user can exist, so that the listening experience of the user is damaged.
In view of this, the embodiment of the present invention provides a method for pushing an advertisement audio, which can ensure that a target advertisement audio pushed to a user is consistent with a tone characteristic of a currently played audio currently listened to by the user, and does not interfere with listening experience of the user. The following detailed description is given by way of example with reference to the accompanying drawings.
Referring to fig. 1, fig. 1 is a schematic flowchart illustrating a method for pushing an advertisement audio according to an embodiment of the present invention, where the method includes the following steps S120 to S140:
and S120, acquiring an advertisement audio set corresponding to the anchor identification of the current anchor.
In this embodiment, the set of advertisement audio may include a plurality of advertisement audio. The tone color characteristics of each advertisement audio correspond to the tone color characteristics of the current anchor. Each advertisement audio can be synthesized by using a Text To Speech (TTS) model, that is, the voiceprint feature of each advertisement audio is consistent with the voiceprint feature of the current anchor.
S130, determining the target advertisement audio frequency from the advertisement audio frequency set.
The target advertisement audio can be the advertisement audio with the maximum estimated click rate or the maximum estimated output value in the advertisement audio set.
S140, the target advertisement audio is played at the advertisement playing time node corresponding to the currently played audio.
It is understood that currently playing audio is the work of the current anchor that the user is listening to. The advertisement playing time node may be any time point of the currently played audio, for example, may be a starting time, an ending time, or any time in the middle of the currently played audio.
According to the advertisement audio pushing method provided by the embodiment of the invention, the advertisement audio set corresponding to the anchor identification of the current anchor is obtained firstly, and the advertisement audio set comprises a plurality of advertisement audios with tone characteristics corresponding to the tone characteristics of the current anchor. And then determining a target advertisement audio frequency from the advertisement audio frequency set, wherein the target advertisement audio frequency is the advertisement audio frequency with the maximum estimated click rate or the maximum estimated output value in the advertisement audio frequency set. And then, playing the target advertisement audio at the advertisement playing time node corresponding to the currently played audio, wherein the currently played audio belongs to the current anchor. Therefore, the tone characteristics of the target advertisement audio pushed to the user and the currently played audio currently listened to by the user are ensured to be consistent, and the listening experience of the user is not interfered.
In an alternative embodiment, each of the set of advertisement audios is derived based on advertisement text and a pre-trained speech synthesis model. Accordingly, referring to fig. 2, before step S120, the method may further include steps S100 to S110:
and S100, inputting the advertisement text into a voice synthesis model corresponding to the current anchor to obtain advertisement audio.
The voice synthesis model is obtained by pre-training by using the recorded audio of the current anchor as a training sample. The recorded audio may be obtained by self-recording the current anchor according to the tagged text provided by the platform, and the tagged text is composed of open source available advertising words.
S110, establishing a mapping relation between the advertisement audio and the anchor mark, and determining attribute information of the advertisement audio based on a preset advertisement putting mode.
It can be understood that, for each obtained advertisement audio based on the speech synthesis model corresponding to the current anchor, after the mapping relationship between the anchor identifier of the current anchor and the advertisement audio is established, all the corresponding advertisement audio can be found subsequently based on the anchor identifier of the current anchor directly.
The ad placement mode selected by the advertiser is different based on the advertiser's different needs. In voice stream advertising, three advertisement delivery modes that an advertiser can usually select are: CPM (Cost Per thousand people), CPC (Cost Per Click), CPA (Cost Per Action generated ).
CPM is a kind of show paid advertisement, show one thousand advertisement contents accumulatively, the advertiser needs to pay the exposure cost for this, for the sound stream advertisement, the advertisement audio frequency plays once and is exposed once. Typically, selecting the ad placement mode as the CPM mode is typically some brand advertising. If the advertisement audio of a certain CPM mode is for new product promotion, the advertisement audio is played once at the user client, which means that the advertisement audio is for promotion. And when the advertisement audio is played, the interface of the client can also pop up the corresponding pop-up window related to the new product, so that the user can jump to the corresponding commodity detail page after clicking.
CPC is a pay-per-click advertisement, charges according to the number of times the advertisement is clicked, and for sound stream advertisements, when the advertisement audio frequency of which the advertisement putting mode is the CPC mode is played at a user client, a corresponding clickable popup window can be popped up on an interface, and when a user clicks the popup window, the user calculates to be promoted once, and an advertiser needs to pay for the promotion.
CPA is an advertisement calculated according to the actual effect of advertisement delivery, which requires the user to click and download, click to fill in, or click to register, etc. For example, an advertisement audio with a CPA mode is for promoting a website and increasing the number of registered users of the website, so that when the advertisement audio is played at a user client, a corresponding clickable popup window can pop up on the interface, when the user clicks the popup window, the user can jump to the registration interface of the website, and when the user finishes registration, the exposure counts as promotion, and the advertiser needs to pay for the promotion.
The attribute information of the advertisement audio frequency corresponding to the CPM, CPC and CPA advertisement delivery modes is the advertisement to be displayed, the advertisement to be clicked and the advertisement to be converted. The advertisement delivery mode of each advertisement audio may determine its corresponding attribute information. The advertising audio obtained by each anchor through its corresponding speech synthesis model may be stored in a database.
In an optional embodiment, each advertisement audio in the set of advertisement audio corresponding to the current anchor corresponds to one attribute information (advertisement to be shown/advertisement to be clicked/advertisement to be converted). It is to be appreciated that targeted advertising audio can be selected with a view to maximizing advertising audio revenue while preserving user experience. Four ways of determining the target advertisement audio when there are advertisement audios with different attribute information in the advertisement audio set are described below.
In a first possible example, when the attribute information in the advertisement audio set is at least one first advertisement audio to be shown with an advertisement, please refer to fig. 3, the sub-step of the above step S130 may include S131 to S133:
s131, calculating the estimated click rate of each first advertisement audio.
In this embodiment, the estimated click rate may represent a click probability of a user clicking a popup window corresponding to a first advertisement audio displayed on the client.
S132, conducting descending order sorting on the estimated click rate of all the first advertisement audios to obtain a first sorting result.
S133, taking the first advertisement audio corresponding to the first estimated click rate in the first sequencing result as the target advertisement audio.
In this embodiment, the behavior attribute information of the current user and the click prediction model may be utilized to calculate the estimated click rate of the current user for each first advertisement audio. The behavior attribute information may include personal attribute information of a current user, in-station behavior attribute information, out-station behavior attribute information, device attribute information, and the like.
In a second possible example, when the set of advertisement audios includes at least one second advertisement audio with attribute information of the advertisement to be clicked, referring to fig. 4, the sub-step of the above step S130 may include S13A to S13D:
S13A, calculating the estimated click rate of each second advertisement audio.
In this embodiment, the estimated click rate of the current user for each second advertisement audio may also be calculated by using the behavior attribute information of the current user and the click prediction model. The estimated click rate may represent a click probability of a user clicking a popup window corresponding to the second advertisement audio displayed on the client.
And S13B, calculating an estimated output value of each second advertisement audio based on the estimated click rate and the click output parameters.
And S13C, performing descending sorting on the estimated output values of all the second advertisement audios to obtain a second sorting result.
And S13D, taking the second advertisement audio positioned at the first in the second sequencing result as the target advertisement audio.
In this embodiment, the click yield parameter may represent a single click revenue for the second advertising audio. The estimated output value of each second advertisement audio may be calculated as follows:
C ecpm2 ＝C cpc ×P pctr2 ×1000
wherein, C ecpm2 Estimated output value, C, representing thousands of exposures of the second advertisement audio cpc For one click revenue of the second advertisement audio, P pctr2 The estimated click rate of the second advertisement audio.
In a third possible example, when the set of advertisement audios includes at least one third advertisement audio with attribute information of the advertisement to be converted, referring to fig. 5, the sub-step of the above step S130 may include S13a to S13d:
and S13a, calculating the estimated click rate and the estimated conversion rate of each third advertisement audio.
Likewise, the estimated click rate of the current user for each third advertisement audio may be calculated using the behavior attribute information of the current user and the click prediction model. The estimated click rate of the current user to each third advertisement audio can be calculated by using the behavior attribute information of the current user and the conversion prediction model.
The estimated click rate may represent a click probability of a user clicking a popup window corresponding to a third advertisement audio displayed on the client. The estimated conversion rate may represent a probability of a subsequent operation generated after the user clicks a popup window corresponding to the third advertisement audio displayed on the client. The subsequent operation may represent the user performing a registration operation, a filling operation, a downloading operation, a purchasing operation, and the like. And S13b, calculating the estimated output value of each third advertisement audio based on the estimated click rate, the estimated conversion rate and the conversion output parameters.
And S13c, sequencing the estimated output values of all the third advertisement audios in a descending order to obtain a third sequencing result.
And S13d, taking the third advertisement audio corresponding to the first estimated output value in the third sequencing result as the target advertisement audio.
In this embodiment, the conversion yield parameter may represent a single conversion yield of the third advertising audio. The estimated output value of each third advertisement audio may be calculated as follows:
C ecpm3 ＝C cpm ×P pctr3 ×P pcvr3 ×1000
wherein, C ecpm3 Estimated output value, C, representing thousands of exposures of third advertisement audio cpm Profit, P, for a single conversion of the third advertisement audio pctr3 Estimated click rate, P, for third advertisement audio pcvr3 The estimated conversion rate of the third advertisement audio.
In a fourth possible example, when the set of advertisement audios includes only at least one second advertisement audio whose attribute information is the advertisement to be clicked and at least one third advertisement audio whose attribute information is the advertisement to be converted, the sub-step of the above step S130 may include S130-1 to S130-4:
s130-1, calculating the estimated click rate of each second advertisement audio, and calculating the estimated output value of each second advertisement audio based on the estimated click rate and the click output parameters.
S130-2, calculating the estimated click rate and the estimated conversion rate of each third advertisement audio, and calculating the estimated output value of each third advertisement audio based on the estimated click rate, the estimated conversion rate and the conversion output parameters.
S130-3, mixing the estimated output values of all the second advertisement audios and the estimated output values of all the third advertisement audios, and then performing descending order to obtain a mixed order result.
S130-4, taking the second advertisement audio or the third advertisement audio corresponding to the first estimated output value in the mixed sequencing result as the target advertisement audio.
It can be understood that, in this embodiment, the process of step S130-1 is the same as the process of steps S13A and S13B, the process of step S130-2 is the same as the process of steps S13A and S13B, and the specific working process of step S130-1 and step S130-2 may refer to the corresponding process in the foregoing embodiment, and is not described herein again.
In an optional embodiment, the method may further include settling the revenue of the advertisement of each advertisement audio for a single day of the current anchor, and the method may further include:
and S150, acquiring the current-day actual push data of each advertisement audio.
The actual push data of the current day may represent the actual number of times of presentation of the advertisement audio of the current day, the actual number of clicks of the current day, or the actual number of conversions of the current day.
And S160, aiming at each advertisement audio, calculating the release profit of the current anchor according to the actual push data of the current day and the output parameters of the advertisement audio.
For the first advertisement audio with the attribute information of the advertisement to be displayed, the profit brought by the first advertisement audio to the current anchor can be calculated based on the actual display times of the day, the display output parameter, the anchor share proportion and the removal cost proportion. For the second advertisement audio with the attribute information of the advertisement to be clicked, the profit of the second advertisement audio brought to the current anchor can be calculated based on the actual click times, the click output parameters, the anchor share proportion and the removal cost proportion of the current anchor on the day. For the third advertisement audio with the attribute information of the advertisement to be clicked, the profit of the third advertisement audio brought to the current anchor can be calculated based on the actual conversion times, the conversion output parameters, the anchor share proportion and the removal cost proportion of the current anchor.
The revenue of the current anchor on the current day may be the sum of the revenue of each first advertisement audio for the current anchor, the revenue of each second advertisement audio for the current anchor, and the revenue of each third advertisement audio for the current anchor.
It should be noted that, the execution sequence of each step in the foregoing method embodiments is not limited to that shown in the accompanying drawings, and the execution sequence of each step is subject to practical application.
In order to perform the corresponding steps in the above method embodiments and various possible embodiments, an implementation of the advertisement audio push device is given below.
Referring to fig. 6, fig. 6 is a schematic structural diagram illustrating an advertisement audio pushing apparatus according to an embodiment of the present invention. The pushing device 200 includes: an obtaining module 210 and a processing module 220.
The obtaining module 210 is configured to obtain an advertisement audio set corresponding to a anchor identifier of a current anchor; the advertisement audio set comprises a plurality of advertisement audios; the tone features of the advertisement audio correspond to the tone features of the current anchor.
The processing module 220 is configured to: determining a target advertisement audio from the set of advertisement audios; the target advertisement audio is the advertisement audio with the maximum estimated click rate or the maximum estimated output value in the advertisement audio set; and playing the target advertisement audio at the advertisement playing time node corresponding to the currently played audio, wherein the currently played audio belongs to the current anchor.
It is understood that the obtaining module 210 may be configured to perform the steps S100 to S120 and the sub-steps thereof, and the processing module 220 may be configured to perform the steps S130 to S160 and the sub-steps thereof. It can be clearly understood by those skilled in the art that, for convenience and simplicity of description, the specific working process of the pushing device 200 described above may refer to the corresponding process in the foregoing method embodiment, and details are not described herein again.
Referring to fig. 7, fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. The electronic device 300 includes a processor 310, a memory 320, and a bus 330, the processor 310 being coupled to the memory 320 via the bus 330.
The electronic device 300 may be, but is not limited to, a smart phone, a tablet, a personal computer, etc.
The memory 320 may be used to store a software program, such as the push device 200 shown in FIG. 6. The Memory 320 may be, but is not limited to, a Random Access Memory (RAM), a Read Only Memory (ROM), a Flash Memory (Flash), a Programmable Read-Only Memory (PROM), an Erasable Read-Only Memory (EPROM), an electrically Erasable Read-Only Memory (EEPROM), and the like. The processor 310 may be an integrated circuit chip having signal processing capabilities.
The Processor 310 may be a general-purpose Processor including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.
Memory 320 stores machine-readable instructions executable by processor 310. The processor 310, when executing the machine readable instructions, implements the method for pushing the advertisement audio disclosed in the above embodiments.
It will be appreciated that the configuration shown in fig. 7 is merely illustrative and that electronic device 300 may include more or fewer components than shown in fig. 7 or have a different configuration than shown in fig. 7. The components shown in fig. 7 may be implemented in hardware, software, or a combination thereof.
The embodiment of the invention also provides a storage medium, wherein a computer program is stored on the storage medium, and when the computer program is executed by a processor, the method for pushing the advertisement audio disclosed by the embodiment is realized. The readable storage medium may be, but is not limited to: u disk, removable hard disk, ROM, RAM, PROM, EPROM, EEPROM, FLASH disk or optical disk, etc.
To sum up, embodiments of the present invention provide a method, an apparatus, an electronic device, and a storage medium for pushing an advertisement audio, where an advertisement audio set corresponding to a broadcaster identifier of a current anchor is obtained first, and the advertisement audio set includes advertisement audios with multiple tone characteristics corresponding to tone characteristics of the current anchor. And then determining a target advertisement audio frequency from the advertisement audio frequency set, wherein the target advertisement audio frequency is the advertisement audio frequency with the maximum estimated click rate or the maximum estimated output value in the advertisement audio frequency set. And then, playing the target advertisement audio at the advertisement playing time node corresponding to the currently played audio, wherein the currently played audio belongs to the current anchor. Therefore, the tone characteristics of the target advertisement audio pushed to the user and the currently played audio currently listened to by the user are ensured to be consistent, and the listening experience of the user is not interfered. And the advertisement audio with the maximum estimated click rate or the maximum estimated output value is selected as the target advertisement audio, so that the profits of both the platform and the anchor can be ensured, and the establishment of the media anchor ecosphere is facilitated.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (10)

1. A method for pushing advertisement audio is characterized by comprising the following steps:
acquiring an advertisement audio set corresponding to a main broadcast identification of a current main broadcast; the advertisement audio frequency set comprises a plurality of advertisement audio frequencies; the tone color characteristics of the advertisement audio correspond to the tone color characteristics of the current anchor;
determining a target advertisement audio from the set of advertisement audio; the target advertisement audio is the advertisement audio with the maximum estimated click rate or the maximum estimated output value in the advertisement audio set;
and playing the target advertisement audio at an advertisement playing time node corresponding to the currently played audio, wherein the currently played audio belongs to the current anchor.
2. The method of claim 1, wherein each of the advertisement audios has corresponding attribute information, and when the attribute information exists in the set of advertisement audios as at least one first advertisement audio to be shown with an advertisement, the step of determining a target advertisement audio from the set of advertisement audios comprises:
calculating the estimated click rate of each first advertisement audio;
sorting the estimated click rates of all the first advertisement audios in a descending order to obtain a first sorting result;
and taking the first advertisement audio corresponding to the first estimated click rate in the first sequencing result as the target advertisement audio.
3. The method of claim 1, wherein each of the advertisement audios has corresponding attribute information, and when the set of advertisement audios includes at least one second advertisement audio of the advertisement to be clicked, the step of determining the target advertisement audio from the set of advertisement audios comprises:
calculating the estimated click rate of each second advertisement audio;
calculating an estimated output value of each second advertisement audio based on the estimated click rate and click output parameters;
sorting the estimated output values of all the second advertisement audios in a descending order to obtain a second sorting result;
and taking the second advertisement audio positioned at the first in the second sequencing result as the target advertisement audio.
4. The method of claim 1, wherein each of the advertisement audios has corresponding attribute information, and when the advertisement audio set includes at least one third advertisement audio of an advertisement to be converted, the step of determining a target advertisement audio from the advertisement audio set comprises:
calculating the estimated click rate and the estimated conversion rate of each third advertisement audio;
calculating an estimated output value of each third advertisement audio based on the estimated click rate, the estimated conversion rate and the conversion output parameter;
sorting the estimated output values of all the third advertisement audios in a descending order to obtain a third sorting result;
and taking the third advertisement audio corresponding to the first estimated output value in the third sequencing result as the target advertisement audio.
5. The method of claim 1, wherein each of the advertisement audios has corresponding attribute information, and when the advertisement audio set includes at least one second advertisement audio in which the attribute information is a to-be-clicked advertisement and at least one third advertisement audio in which the attribute information is a to-be-converted advertisement, the step of determining the target advertisement audio from the advertisement audio set comprises:
calculating the estimated click rate of each second advertisement audio, and calculating the estimated output value of each second advertisement audio based on the estimated click rate and the click output parameters;
calculating the estimated click rate and the estimated conversion rate of each third advertisement audio, and calculating the estimated output value of each third advertisement audio based on the estimated click rate, the estimated conversion rate and the conversion output parameter;
mixing all the estimated output values of the second advertisement audios and the estimated output values of the third advertisement audios, and then performing descending sorting to obtain a mixed sorting result;
and taking the second advertisement audio or the third advertisement audio corresponding to the first estimated output value in the mixed sequencing result as the target advertisement audio.
6. The method of claim 1, wherein prior to the step of obtaining the set of advertising audio corresponding to the anchor identification of the current anchor, the method further comprises:
inputting the advertisement text into a voice synthesis model corresponding to the current anchor to obtain advertisement audio, wherein the voice synthesis model is obtained by utilizing the recorded audio of the current anchor to train in advance;
and establishing a mapping relation between the advertisement audio and the anchor mark, and determining attribute information of the advertisement audio based on a preset advertisement putting mode.
7. The method of claim 1, further comprising:
acquiring the current-day actual push data of each advertisement audio;
and aiming at each advertisement audio frequency, calculating the release profit of the current anchor according to the actual push data of the current day and the output parameters of the advertisement audio frequency.
8. A device for pushing advertisement audio, comprising:
the acquisition module is used for acquiring an advertisement audio set corresponding to a main broadcast identification of a current main broadcast; the advertisement audio frequency set comprises a plurality of advertisement audio frequencies; the tone color characteristics of the advertisement audio correspond to the tone color characteristics of the current anchor;
a processing module to:
determining a target advertisement audio from the set of advertisement audios; the target advertisement audio is the advertisement audio with the maximum estimated click rate or the maximum estimated output value in the advertisement audio set;
and playing the target advertisement audio at an advertisement playing time node corresponding to the currently played audio, wherein the currently played audio belongs to the current anchor.
9. An electronic device, comprising: a memory and a processor, the memory storing machine-readable instructions executable by the processor, the processor executing the machine-readable instructions when the electronic device is running to implement the method of any one of claims 1-7.
10. A storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method of any one of claims 1 to 7.
CN202210991273.1A 2022-08-18 2022-08-18 Advertisement audio pushing method and device, electronic equipment and storage medium Pending CN115271827A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210991273.1A CN115271827A (en) 2022-08-18 2022-08-18 Advertisement audio pushing method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210991273.1A CN115271827A (en) 2022-08-18 2022-08-18 Advertisement audio pushing method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN115271827A true CN115271827A (en) 2022-11-01

Family

ID=83753155

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210991273.1A Pending CN115271827A (en) 2022-08-18 2022-08-18 Advertisement audio pushing method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN115271827A (en)

Similar Documents

Publication Publication Date Title
US9819622B2 (en) Method and system for communicating between a sender and a recipient via a personalized message including an audio clip extracted from a pre-existing recording
CN107590689B (en) Advertisement data recommendation method and system
US8117067B2 (en) Achieving advertising campaign goals
US8612860B2 (en) Systems, methods, and media for coordinating the presentation of media with an event
CN110570232A (en) Internet advertisement putting method, device, server and storage medium
US20090313120A1 (en) Goal-Based Front End Buying of Radio Advertisements
US11120077B2 (en) Electronic media signature based applications
KR20090084965A (en) Determining advertisement effectiveness
US20110225026A1 (en) Map-Based Interface for Booking Broadcast Advertisements
US20170053323A1 (en) Engine and system for the transcription and assessment of media files
US20100036731A1 (en) Animated audible contextual advertising
CN107566856B (en) The method and system of pushed information are provided
CN108737486B (en) Information pushing method and device
WO2011151715A1 (en) Method of and system for determining contextually relevant advertisements to be provided to a web page
CN112819528A (en) Crowd pack online method and device and electronic equipment
CN116383480A (en) Method and device for recommending media in call scene, electronic equipment and storage medium
CN111666059A (en) Reminding information broadcasting method and device and electronic equipment
US8527343B1 (en) Distributing content across multiple content locations
CN108260005A (en) A kind of video broadcasting method and device
CN115271827A (en) Advertisement audio pushing method and device, electronic equipment and storage medium
CN116228324A (en) Advertisement delivery party determining method, device, equipment and storage medium
US11640578B2 (en) Break-based inventory forecasting
CN107203892B (en) Method and device for pushing value added service information and electronic equipment
CN111985971A (en) Advertisement screening method, device, equipment and storage medium
CN114782081A (en) Method and system for judging advertisement putting quality

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination