Audio advertisement putting method, device and system

Abstract

An audio advertisement putting method, comprising: when a client (100) plays an audio program, sending an advertisement request (301) to a cloud device (20, 90, 110), the advertisement request comprising information about the audio program, an identifier of a target advertisement slot, and user characteristics, the cloud device (20, 90, 110) determining a vector representation of the target advertisement slot according to the information about the audio program and the identifier of the target advertisement slot (302), the vector representation of the target advertisement slot is used for describing contents involved in the audio program in a period of time before the target advertisement slot; the cloud device (20, 90, 110) determines an audio advertisement matching the target advertisement slot according to the user characteristics and the vector representation of the target advertisement slot (303); the cloud device (20, 90, 110) sends an audio advertisement to the client (100) (304), and the client (100) plays the audio advertisement when playing the audio program to the target advertisement slot (305). Therefore, the matching degree of the audio advertisement and the audio program is higher, the user characteristics are combined, the personalized requirements of the user can be better met, and the putting effect of the audio advertisement can be improved.

Description

Method, device and system for delivering audio advertisements

[0001] The present application relates to the field of computer technology, and in particular to a method, device, and system for delivering audio advertisements.

[0002] Podcasts are recorded online radio or audio programs, such as audiobooks, crosstalk, and current events. The podcast market is growing rapidly, with hundreds of millions of users. With the booming podcast market, the corresponding advertising market share is also growing. With the development of podcasts both domestically and internationally, audio advertising has become a significant advertising format.

[0003] To insert audio ads into an audio program, you first need to find the ad slots in the audio program offline. This is the location where the audio ad is inserted. Then, you configure an audio ad for each ad slot. This way, when the audio program reaches that slot, the configured audio ad will play.

[0004] This type of offline audio advertising has a low degree of matching with the audio program, often affecting the continuity of users listening to the audio program and resulting in poor delivery effect.

[0005] Summary of the Invention

[0006] This application provides a method for delivering audio advertisements to users in audio programs, which is used to deliver audio advertisements that meet the user's personalized needs. This application also provides corresponding devices, systems, computer-readable storage media, and computer program products.

[0007] In a first aspect, the present application provides a method for delivering audio advertisements, comprising: a cloud receiving an advertisement request from a client, the advertisement request including information about an audio program, an identifier of a target advertisement slot, and user characteristics, the target advertisement slot being one of at least one advertisement slot mined from the audio program, and the advertisement request being triggered when the client plays the audio program; the cloud determining a vector representation of the target advertisement slot based on the information about the audio program and the identifier of the target advertisement slot, the vector representation of the target advertisement slot being used to describe the content involved in the audio program within a period of time before the target advertisement slot; the cloud obtaining an audio advertisement matching the target advertisement slot based on the user characteristics and the vector representation of the target advertisement slot; and the cloud sending the audio advertisement to the client, the audio advertisement being used to be played by the client when the audio program is played to the target advertisement slot.

[0008] In this application, the cloud can be software or services on a cloud platform, or software or services deployed on nodes in a network, such as edge nodes. The cloud can run on independent physical machines or on virtualized resources.

[0009] In this application, the client can be a terminal device or an application, for example, the application runs on the terminal device for the user to use.

[0010] In this application, when the client plays an audio program usually refers to when the client is about to play the audio program to the target advertising slot, and usually triggers an advertising request at a preset time point before reaching the target advertising slot. The preset time point can be a time point 5 seconds before the target advertising slot or other numerical values ​​representing the duration.

[0011] In this application, audio ads refer to ads played via audio. Ad requests are used to request audio ads from the cloud.

[0012] In this application, the information of the audio program may be an identifier or index of the audio program. The audio program is an audio program that the client is about to play, is currently playing, or has just finished playing. The audio program may be an audio book, an audio song, a crosstalk, or current affairs news.

[0013] In the present application, during the ad slot mining phase, one or more ad slots can be mined in an audio program, and each ad slot in an audio program will have a unique identifier. Each ad slot will have a vector representation, and the identifier of the same ad slot will be associated with the vector representation of the ad slot, and the representation and vector representation of at least one ad slot of each audio program will be associated with the audio program and stored, and this information can be stored in the audio content library of the cloud platform. Among them, the vector representation of the ad slot refers to the vector obtained by encoding the content involved in the previous period of time of the ad slot. The "period of time" in the present application can be a period of time, such as 1 minute or other numerical values ​​representing the duration. For example, in one implementation, the specific numerical value can be pre-set, and in another implementation, the duration can be a random value within a range.

[0014] In this application, user characteristics may include user portraits and user behavior characteristics. User portraits may include basic information about the user, such as gender, age, hobbies, etc. User behavior characteristics may include user behavior information such as clicks, favorites, and comments on historical audio programs.

[0015] In this application, the identifiers of all advertising slots associated with the audio program and the vector representation of the advertising slots can be found based on the information of the audio program. Furthermore, based on the identifier of the target advertising slot, the vector representation of the target advertising slot can be determined.

[0016] In this application, based on the vector representation of the target ad slot, one or more audio ads that are strongly related to the audio program the user was listening to before the target ad slot can be determined. Furthermore, the audio ads can be further filtered or processed based on user characteristics to obtain an audio ad that matches the target ad slot. Because the audio ads determined in this application have a higher degree of match with the audio program and incorporate user characteristics, they can better meet the user's personalized needs and improve the effectiveness of audio ad delivery.

[0017] In one possible implementation, the above steps: the cloud determines the audio advertisement that matches the target ad slot based on user characteristics and the vector representation of the target ad slot, including: the cloud recalls multiple audio advertisements from the audio advertisement library based on the vector representation of the target ad slot; the cloud obtains the audio advertisement that matches the target ad slot from the multiple audio advertisements based on the user characteristics.

[0018] In this possible implementation, the cloud recalls multiple audio ads that are strongly related to the audio program the user was listening to before the target ad slot based on the vector representation of the target ad slot, and then selects the ad with the highest match to the user's characteristics. This can improve the match between the audio ad and the audio program being played on the client.

[0019] In one possible implementation, the above steps: the cloud obtains an audio advertisement that matches the target ad slot from multiple audio advertisements based on user characteristics, including: the cloud predicts the completion rates of multiple audio advertisements based on user characteristics and an ad ranking model, wherein the audio advertisement with the highest completion rate is the audio advertisement that matches the target ad slot, or the audio advertisement with the highest completion rate is the source advertisement of the audio advertisement that matches the target ad slot, and the ad ranking model is a model that takes user characteristics as input and completion rate as output.

[0020] In this possible implementation, the completion rate refers to the predicted probability of an audio ad being played in its entirety. The more closely an audio ad's content and style align with user preferences, the greater its probability of being played in its entirety, and the better the delivery performance. Therefore, completion rates can be predicted for multiple recalled audio ads based on user characteristics. The audio ad with the highest completion rate can be selected as the audio ad or as the source ad for the audio ad, thereby improving the delivery performance of audio ads.

[0021] In one possible implementation, when the audio advertisement with the highest completion rate is the source advertisement of the audio advertisement that matches the target advertisement slot, the method further includes: the cloud adjusts the style of the audio advertisement with the highest completion rate according to the style of the audio program and user characteristics to obtain the audio advertisement that matches the target advertisement slot.

[0022] In this possible implementation, after the cloud determines the audio advertisement with the highest completion rate through the advertisement sorting model, it can adjust the style of the audio advertisement with the highest completion rate according to the style of the audio program that the user wants to play or is currently playing and the user characteristics. This can increase the user's acceptance of audio advertisements, thereby improving the effectiveness of audio advertisement delivery.

[0023] In one possible implementation, the above steps: the cloud adjusts the style of the audio advertisement with the highest completion rate according to the style of the audio program and user characteristics to obtain an audio advertisement that matches the target advertising slot, including: the cloud adjusts the object sound in the audio advertisement with the highest completion rate according to the style vector of the object sound in the audio program and the style vector of the user's preference, the style vector of the object sound in the audio program is obtained by encoding the object sound in the audio program, and the style vector of the user's preference is obtained by encoding the user characteristics; the cloud adjusts the background music in the audio advertisement with the highest completion rate according to the style vector of the background music in the audio program and the style vector of the user's preference, the style vector of the background music in the audio program is obtained by encoding the background music in the audio program; the cloud integrates the adjusted object sound in the audio advertisement with the highest completion rate and the adjusted background music in the audio advertisement with the highest completion rate to obtain the audio advertisement that matches the target advertising slot.

[0024] In this possible implementation, if an audio program includes both target sound and background music, the target sound and background music can be separated and encoded to obtain style vectors for the target sound and background music, respectively. The style vectors are then combined with the user's preferred style vectors to adjust the target sound and background music in the highest-scoring audio ad to produce the audio ad. This adjustment aligns the style of the audio ad with that of the audio program, satisfying the user's style preferences and enhancing the user experience, thereby improving the effectiveness of the audio ad delivery.

[0025] In one possible implementation, before the cloud receives the advertising request sent by the client, the method also includes: the cloud determines at least one advertising slot based on the time domain information of the audio program in the voice state and the text content after the audio program is converted into text; the cloud encodes the text content of each advertising slot in the at least one advertising slot within a previous period of time to obtain a vector representation of each advertising slot.

[0026] In this possible implementation, in the present application, the time domain information may include amplitude (amplitude may also be described as sound intensity), changes in amplitude over time, and the like.

[0027] The cloud can also perform ad slot mining before receiving an ad request. The process of mining ad slots can be to determine the ad slot of the audio program from the time domain information of the audio program in the voice state and the text content after the audio program is converted into text. In this application, because ad slots can be mined based on both the time domain information and the text content of the audio program, the mined ad slots are of high quality. Generally, inserting ads in these ad slots will not affect the continuity of the audio program, thereby improving the user experience and the effectiveness of audio advertising.

[0028] In a possible implementation, the method further includes: the cloud stores the audio program, the identifier of each advertising slot, and the vector representation of each advertising slot in an associated manner.

[0029] In this possible implementation, the audio program, the identifier of each ad slot in the audio program, and the vector representation of each ad slot are associated and stored. This can facilitate the rapid determination of the audio ad that matches the requested target ad slot when the client sends an ad request, thereby improving the efficiency of audio ad delivery.

[0030] In one possible implementation, the above steps: the cloud determines at least one advertising slot based on the time domain information of the audio program in the voice state and the text content after the audio program is converted into text, including: when the time domain information is amplitude, if the duration for which the amplitude of the audio program in the voice state is continuously lower than the amplitude threshold exceeds a first threshold, the cloud determines the duration for which the amplitude is continuously lower than the amplitude threshold as the first basic advertising slot; if the time interval between two adjacent words in the text content after the audio program is converted is greater than a second threshold, the cloud determines the time interval between the two adjacent words as the second basic advertising slot, and the time interval between the two adjacent words is determined by the timestamp of each word during text conversion; the cloud determines at least one advertising slot from the union of the first basic advertising slot and the second basic advertising slot.

[0031] In this possible implementation, the advertisement slot is selected from the union of the first basic advertisement slot and the second basic advertisement slot, which can expand the range of advertisement slot selection.

[0032] In one possible implementation, the above-mentioned step: the cloud determines at least one advertising slot from the union of the first basic advertising slot and the second basic advertising slot, including: the cloud selects at least one advertising slot with the largest weight from the union of the first basic advertising slot and the second basic advertising slot to determine as at least one advertising slot of the audio program, and the weight of each advertising slot in the at least one advertising slot is determined by the punctuation marks and / or text segment segmentation positions corresponding to each advertising slot.

[0033] In this possible implementation, the weight of the corresponding basic ad slots can be increased by using punctuation marks, text segmentation, etc., and then at least one basic ad slot with the highest weight is selected to be the at least one ad slot for the audio program. This can improve the quality of the selected ad slots.

[0034] In one possible implementation, the user characteristics include user portraits and user behavior characteristics regarding historical audio programs.

[0035] A second aspect of the present application provides a method for delivering audio advertisements, comprising: when a client plays an audio program, sending an advertisement request to a cloud, wherein the advertisement request includes information about the audio program, an identifier of a target advertisement slot, and user characteristics, wherein the target advertisement slot is one of at least one advertisement slot mined from the audio program; the client receives an audio advertisement sent by the cloud that matches the target advertisement slot; and the client plays the audio advertisement when playing the audio program to the target advertisement slot.

[0036] In this application, when the client plays an audio program usually refers to when the client is about to play the audio program to the target advertising slot, and usually triggers an advertising request at a preset time point before reaching the target advertising slot. The preset time point can be a time point 5 seconds before the target advertising slot or other numerical values ​​representing the duration.

[0037] In a possible implementation, the user characteristics include user characteristics and user preference characteristics for audio programs.

[0038] A third aspect of the present application provides a method for mining advertising slots, including: obtaining an audio program for the advertising slot to be mined in the cloud; determining at least one advertising slot based on the time domain information of the audio program in the voice state and the text content after the audio program is converted into text in the cloud; and encoding the text content of each advertising slot in the at least one advertising slot within a previous period of time in the cloud to obtain a vector representation of each advertising slot.

[0039] In a possible implementation, the method further includes: the cloud stores the audio program, the identifier of each advertising slot, and the vector representation of each advertising slot in an associated manner.

[0040] In one possible implementation, the above steps: the cloud determines at least one advertising slot based on the time domain information of the audio program in the voice state and the text content after the audio program is converted into text, including: when the time domain information is amplitude, if the duration for which the amplitude of the audio program in the voice state is continuously lower than the amplitude threshold exceeds a first threshold, the cloud determines the duration for which the amplitude is continuously lower than the amplitude threshold as the first basic advertising slot; if the time interval between two adjacent words in the text content after the audio program is converted is greater than a second threshold, the cloud determines the time interval between the two adjacent words as the second basic advertising slot, and the time interval between the two adjacent words is determined by the timestamp of each word during text conversion; the cloud determines at least one advertising slot from the union of the first basic advertising slot and the second basic advertising slot.

[0041] In one possible implementation, the above-mentioned step: the cloud determines at least one advertising slot from the union of the first basic advertising slot and the second basic advertising slot, including: the cloud selects at least one advertising slot with the largest weight from the union of the first basic advertising slot and the second basic advertising slot to determine as at least one advertising slot of the audio program, and the weight of each advertising slot in the at least one advertising slot is determined by the punctuation marks and / or text segment segmentation positions corresponding to each advertising slot.

[0042] In a fourth aspect of the present application, a cloud device is provided for executing the method of the first aspect or any possible implementation of the first aspect. Specifically, the cloud device includes modules or units for executing the method of the first aspect or any possible implementation of the first aspect, such as a processing unit, a sending unit, and a receiving unit.

[0043] In a fifth aspect, the present application provides a client for executing the method of the second aspect. Specifically, the client includes modules or units for executing the method of the second aspect or any possible implementation of the second aspect, such as a receiving unit, a display unit, and a sending unit.

[0044] In a sixth aspect of the present application, a cloud device is provided for executing the method of the first aspect or any possible implementation of the first aspect. Specifically, the cloud device includes modules or units for executing the method of the third aspect or any possible implementation of the third aspect, such as a processing unit, a sending unit, and a receiving unit.

[0045] In a seventh aspect, the present application provides a cloud device. The cloud device may include at least one processor, a memory, and a communication interface. The processor is coupled to the memory and the communication interface. The memory is configured to store instructions, the processor is configured to execute the instructions, and the communication interface is configured to communicate with other network elements under the control of the processor. When executed by the processor, the instructions cause the processor to perform the method of the first aspect or any possible implementation of the first aspect.

[0046] In an eighth aspect, the present application provides a client comprising a transceiver, a processor and a memory, wherein the transceiver and the processor are coupled to the memory, and the memory is used to store programs or instructions. When the programs or instructions are executed by the processor, the cloud device executes the method in the aforementioned second aspect or any possible implementation of the second aspect.

[0047] In a ninth aspect of the present application, a cloud device is provided. The cloud device may include at least one processor, a memory, and a communication interface. The processor is coupled to the memory and the communication interface. The memory is configured to store instructions, the processor is configured to execute the instructions, and the communication interface is configured to communicate with other network elements under the control of the processor. When executed by the processor, the instructions cause the processor to perform the method of the third aspect or any possible implementation of the third aspect.

[0048] The tenth aspect of the present application provides a chip system, which includes one or more interface circuits and one or more processors; the interface circuit and the processor are interconnected by lines; the interface circuit is used to receive signals from the memory of the cloud device and send signals to the processor, and the signals include computer instructions stored in the memory; when the processor executes the computer instructions, the cloud device executes the method in the aforementioned first aspect or any possible implementation of the first aspect.

[0049] In the eleventh aspect of the present application, a chip system is provided, which includes one or more interface circuits and one or more processors; the interface circuits and the processors are interconnected by lines; the interface circuits are used to receive signals from the client's memory and send signals to the processor, and the signals include computer instructions stored in the memory; when the processor executes the computer instructions, the client executes the method in the aforementioned second aspect or any possible implementation of the second aspect.

[0050] The twelfth aspect of the present application provides a chip system, which includes one or more interface circuits and one or more processors; the interface circuit and the processor are interconnected by lines; the interface circuit is used to receive signals from the memory of the cloud device and send signals to the processor, and the signals include computer instructions stored in the memory; when the processor executes the computer instructions, the cloud device executes the method in the aforementioned third aspect or any possible implementation of the third aspect.

[0051] The thirteenth aspect of the present application provides a computer-readable storage medium on which a computer program or instruction is stored. When the computer program or instruction is executed on a computer device, the computer device executes the method in the aforementioned first aspect or any possible implementation of the first aspect.

[0052] The fourteenth aspect of the present application provides a computer-readable storage medium on which a computer program or instruction is stored. When the computer program or instruction is run on a computer device, the computer device executes the method in the aforementioned second aspect or any possible implementation of the second aspect.

[0053] The fifteenth aspect of the present application provides a computer-readable storage medium on which a computer program or instruction is stored. When the computer program or instruction is run on a computer device, the computer device executes the method in the aforementioned third aspect or any possible implementation of the third aspect.

[0054] In a sixteenth aspect, the present application provides a computer device program product, which includes a computer device program code. When the computer device program code is executed on a computer device, the computer device executes the method in the aforementioned first aspect or any possible implementation of the first aspect.

[0055] In the seventeenth aspect, the present application provides a computer device program product, which includes a computer device program code. When the computer device program code is executed on a computer device, the computer device executes the method in the aforementioned second aspect or any possible implementation of the second aspect.

[0056] In an eighteenth aspect, the present application provides a computer device program product, which includes a computer device program code. When the computer device program code is executed on a computer device, the computer device executes the method in the aforementioned third aspect or any possible implementation of the third aspect.

[0057] In the nineteenth aspect of the present application, there is provided an audio advertising system, which includes a cloud device and a client. The cloud device is used to execute the method in the aforementioned first aspect or any possible implementation of the first aspect, and the client is used to execute the method in the aforementioned second aspect or any possible implementation of the second aspect.

[0058] The twentieth aspect of the present application provides an audio advertising system, which includes a cloud device and an audio content library. The cloud device obtains audio programs from the audio content library and executes the method in the above-mentioned third aspect or any possible implementation of the third aspect.

[0059] Among them, the technical effects brought about by the second to twentieth aspects or any possible implementation methods thereof can refer to the technical effects brought about by the first aspect or different possible implementation methods of the first aspect, and will not be repeated here.

[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0061] FIG1A is a schematic diagram of an architecture of an audio advertising system provided by an embodiment of the present application;

[0062] FIG1B is another schematic diagram of the architecture of the audio advertising system provided in an embodiment of the present application;

[0063] FIG2A is a schematic diagram of a structure of a client provided in an embodiment of the present application;

[0064] FIG2B is a schematic diagram of a structure of a cloud device provided in an embodiment of the present application;

[0065] FIG3 is a schematic diagram of an embodiment of a method for delivering audio advertisements provided in an embodiment of the present application;

[0066] FIG4 is a schematic diagram of the structure of an advertisement ranking model provided in an embodiment of the present application;

[0067] FIG5 is a schematic diagram of another embodiment of the method for delivering audio advertisements provided in an embodiment of the present application;

[0068] FIG6 is a schematic diagram of an embodiment of a method for mining advertising slots provided in an embodiment of the present application;

[0069] FIG7 is a schematic diagram of an example scenario provided by an embodiment of the present application;

[0070] FIG8 is a schematic diagram of an embodiment of mining advertising slots and delivering audio advertisements provided by an embodiment of the present application;

[0071] FIG9 is another structural diagram of a cloud device provided in an embodiment of the present application;

[0072] FIG10 is another schematic diagram of the structure of the client provided in an embodiment of the present application;

[0073] FIG11 is another structural diagram of the cloud device provided in an embodiment of the present application.

[0074] The following describes the embodiments of the present application in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of the present application, rather than all the embodiments. Those skilled in the art will appreciate that with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0075] The terms "first," "second," and the like in the specification and claims of this application and in the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions, e.g., a process, method, system, product, or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to these processes, methods, products, or apparatus.

[0076] Embodiments of this application provide a method for delivering audio advertisements to users during audio programs, specifically tailored to their individual needs. This application also provides corresponding devices, systems, computer-readable storage media, and computer program products. These are described in detail below.

[0077] FIG1A is a schematic diagram of an architecture of an audio advertising system provided in an embodiment of the present application.

[0078] As shown in Figure 1A, the audio advertising system provided in the embodiment of the present application includes a cloud and multiple clients, and the cloud can communicate with the multiple clients via a network. The audio advertising system provided in the embodiment of the present application can also include an audio content library and an audio advertising library. Of course, the audio content library and / or the audio advertising library can also be integrated into the cloud.

[0079] In the embodiments of the present application, the cloud can be software or services on a cloud platform, or software or services deployed on a node in the network, such as an edge node. The client can be a terminal device, or an application, such as an application running on a terminal device for user use.

[0080] When using a podcast-type app, a client can retrieve audio programs from the audio content library. While playing the audio programs, the client can send an ad request to the cloud. Based on the information about the audio programs carried in the ad request and the user's characteristics, the cloud can identify an audio ad from the audio ad library that meets the user's personalized needs. The cloud then sends this ad to the client, which then delivers it to the audio program during playback.

[0081] In this application, audio ads refer to ads played via audio. Ad requests are used to request audio ads from the cloud.

[0082] In this application, user characteristics may include user portraits and user behavior characteristics. User portraits may include basic information about the user, such as gender, age, hobbies, etc. User behavior characteristics may include user behavior information such as clicks, favorites, and comments on historical audio programs.

[0083] The audio advertising system provided in the embodiment of the present application can determine audio advertisements based on user characteristics. The audio advertisements determined in this way can better meet the personalized needs of users and improve the delivery effect of audio advertisements.

[0084] In this embodiment of the present application, the information related to the audio program may include the identifier of the audio program and the identifier of the ad slot pre-mined from the audio program. This allows the cloud to determine the audio ad for the ad slot specified in the ad request, further improving the matching between the audio ad and the audio program. An ad slot refers to the time period within an audio program that is reserved for playing audio ads.

[0085] In the embodiment of the present application, the process of mining advertisement slots is usually offline mining, of course, it can also be online mining. The following is an introduction to the audio advertisement system for mining advertisement slots in conjunction with FIG1B.

[0086] As shown in Figure 1B, the audio advertising system may include a cloud and an audio content library. The audio content library may be integrated in the cloud, which may be the same device as the cloud in Figure 1A or a different device.

[0087] When mining ad slots, the cloud can obtain the audio program of the ad slot to be mined from the audio content library, and then determine at least one ad slot based on the time domain information of the audio program in the voice state and the text content after the audio program is converted into text; the cloud encodes the text content of each ad slot in the at least one ad slot in the previous period of time to obtain a vector representation of each ad slot.

[0088] In the embodiment of the present application, the time domain information may include amplitude (amplitude may also be described as sound intensity), changes in amplitude over time, etc.

[0089] The cloud will associate and store the identifier of each ad slot of the same audio program and the vector representation of each ad slot with the audio program. If the audio program is stored in an audio content library, the identifier of each ad slot of the same audio program and the vector representation of each ad slot can be returned to the audio content library. The audio content library associates and stores the audio program, as well as the identifier of each ad slot of the audio program and the vector representation of each ad slot. As shown in Figure 1B, the audio content library can associate and store many audio programs and the identifiers and vector representations of the ad slots in the audio program. For example: Audio program 1 has x corresponding ad slots. The identifiers and vector representations of the ad slots corresponding to audio program 1 are ad slot 1, vector representation 1, ..., ad slot x, vector representation x. Audio program M has y corresponding ad slots. The identifiers and vector representations of the ad slots corresponding to audio program 1 are ad slot 1, vector representation 1, ..., ad slot y, vector representation y. Where x, y, and M are all positive integers.

[0090] The ad slot mining scheme provided in the embodiment of the present application can mine ad slots based on the time domain information of the audio program in the voice state and the text content of the audio program after conversion to text format. The mined ad slots are of high quality and generally do not affect the continuity of the audio program due to the insertion of audio ads in the ad slots, thereby improving the user experience and the effect of audio ad delivery. Moreover, the audio program, the identifier of each ad slot in the audio program, and the vector representation of each ad slot are associated and stored in the audio content library. This makes it easier for the client to quickly determine the audio ad that matches the requested target ad slot when sending an ad request, thereby improving the efficiency of audio ad delivery.

[0091] In the embodiment of the present application, the cloud can be a physical machine or a computing instance such as a virtual machine (VM) or a container. The cloud can also be understood as an advertising system, or the cloud is a device in the advertising system.

[0092] When the client is a terminal device, the terminal device (also called user equipment (UE)) is a device with wireless transceiver capabilities. It can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; it can also be deployed on water (such as ships); it can also be deployed in the air (for example, on airplanes, balloons, and satellites). The terminal can be a mobile phone, tablet computer, computer with wireless transceiver capabilities, virtual reality (VR) terminal, augmented reality (AR) terminal, wireless terminal in industrial control (industrial control), wireless terminal in self-driving (autonomous driving), wireless terminal in remote medical (remote medical), wireless terminal in smart grid (smart grid), wireless terminal in transportation safety (transportation safety), wireless terminal in smart city (smart city), wireless terminal in smart home (smart home), wireless terminal in the Internet of Things (IoT), etc.

[0093] The structure of the terminal device provided in the embodiment of the present application can be understood by referring to FIG. 2A below, and the structure of the cloud device can be understood by referring to FIG. 2B below.

[0094] Please refer to Figure 2A, which is a structural diagram of a terminal device provided in an embodiment of the present application. As shown in Figure 2A, the terminal device may include a processor 101, a transceiver 102, a memory 103 and a bus 104. The processor 101, the transceiver 102 and the memory 103 are interconnected via the bus 104. In an embodiment of the present application, the processor 101 is used to control and manage the actions of the terminal device 10. For example, the processor 101 is used to control the process of playing audio programs and audio advertisements. The transceiver 102 is used to support the terminal device 10 to communicate. For example, the transceiver 102 can execute the steps of sending advertisement requests and receiving audio advertisements. The memory 103 is used to store program codes and data of the terminal device 10.

[0095] The processor 101 may be a central processing unit (CPU), a general-purpose processor (GPOR), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic device (PLD), a transistor logic device (TLD), a hardware component, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. A processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The bus 104 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, for example. Buses may be classified as address buses, data buses, control buses, and the like. For ease of illustration, FIG. 2A shows only one thick line, but this does not imply that there is only one bus or only one type of bus.

[0096] FIG2A above introduces the structure of the terminal device. The structure of the cloud device will be introduced below in conjunction with FIG2B .

[0097] Figure 2B is a schematic diagram of a possible logical structure of a cloud device provided in an embodiment of the present application. As shown in Figure 2B, the cloud device 20 provided in an embodiment of the present application includes: a processor 201, a communication interface 202, a memory 203 and a bus 204. The processor 201, the communication interface 202 and the memory 203 are interconnected via the bus 204. In an embodiment of the present application, the processor 201 is used to control and manage the actions of the cloud device 20. For example, the processor 201 is used to execute the process of determining audio advertisements. The communication interface 202 is used to support the cloud device 20 to communicate. For example, the communication interface 202 can execute the steps of receiving advertisement requests and sending audio advertisements. The memory 203 is used to store the program code and data of the cloud device 20.

[0098] The processor 201 may be a central processing unit (CPU), a general-purpose processor (GPOR), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic device (PLD), a transistor logic device (TLD), a hardware component, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. A processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The bus 204 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, for example. Buses may be classified as address buses, data buses, control buses, and the like. For ease of illustration, FIG. 2B shows only one thick line, but this does not imply that there is only one bus or only one type of bus.

[0099] The following describes the method for delivering audio advertisements provided by an embodiment of the present application. The content involved in the cloud execution in the method can be executed by the cloud or by components of the cloud (such as a processor, chip, or chip system, etc.).

[0100] FIG3 is a schematic diagram of an embodiment of a method for delivering audio advertisements provided in an embodiment of the present application.

[0101] As shown in FIG3 , an embodiment of the method for delivering audio advertisements provided in an embodiment of the present application includes:

[0102] 301. The client sends an ad request to the cloud. In return, the cloud receives the ad request from the client.

[0103] Ad requests are triggered when the client plays an audio program.

[0104] In the embodiment of the present application, when the client plays an audio program, it usually refers to when the client is about to play the audio program to the target advertising slot. Usually, an advertising request is triggered at a preset time point before reaching the target advertising slot. The preset time point can be a time point 5 seconds before the target advertising slot or other numerical values ​​representing the duration.

[0105] In the embodiment of the present application, the advertisement request includes information about the audio program, an identifier of the target advertisement slot, and user characteristics.

[0106] In the embodiment of the present application, the target advertising slot is one of at least one advertising slot mined from the audio program, such as advertising slot 1 corresponding to audio program 1 in Figure 1B. Of course, it can also be other advertising slots.

[0107] 302. The cloud determines a vector representation of the target advertising slot based on the information of the audio program and the identifier of the target advertising slot.

[0108] The vector representation of the target advertisement slot is used to describe the content involved in the audio program in a period of time before the target advertisement slot.

[0109] In the embodiment of the present application, the information of the audio program may be an identifier or index of the audio program. The audio program is an audio program that the client is about to play, is currently playing, or has just finished playing. The audio program may be an audio book, an audio song, a crosstalk, or current affairs news.

[0110] In an embodiment of the present application, during the ad slot mining stage, one or more ad slots can be mined in an audio program, and each ad slot in an audio program will have a unique identifier. Each ad slot will have a vector representation, and the identifier of the same ad slot will be associated with the vector representation of the ad slot, and the representation and vector representation of at least one ad slot of each audio program will be associated with the audio program and stored, and this information can be stored in the audio content library of the cloud platform. Among them, the vector representation of the ad slot refers to the vector obtained by encoding the content involved in the previous period of time of the ad slot, and the "period of time" of the present application can be a period of time, such as: 1 minute or other numerical values ​​representing the length of time. For example, in one implementation, the specific numerical value can be pre-set, and in another implementation, the duration can be a random value within a range.

[0111] As shown in FIG1B , if the audio program information is audio program 1 and the target advertisement slot is identified as advertisement slot 1 , then vector representation 1 of advertisement slot 1 can be determined based on audio program 1 and advertisement slot 1 .

[0112] 303. The cloud determines an audio advertisement that matches the target ad slot based on the user characteristics and the vector representation of the target ad slot.

[0113] In the embodiment of the present application, the user characteristics may reflect the user's preference for the type or style of audio programs, for example, the type and content of the audio programs that the user likes to listen to, and the audio program reader that the user likes to listen to.

[0114] In this embodiment of the present application, because the vector representation of the ad slot reflects the content of the audio program, when matching audio ads, audio ads that are relevant to the audio program content can be selected. This ensures a high degree of integration between the audio ad and the audio program, without affecting the user's listening continuity. The cloud then further determines the audio ad based on the user's preferences, and can obtain the audio ad that best matches the target ad slot.

[0115] 304. The cloud sends the audio advertisement to the client. In response, the client receives the audio advertisement from the cloud.

[0116] Audio ads are played when the client plays an audio program and reaches the target ad slot.

[0117] 305. The client plays the audio advertisement in the target advertisement slot.

[0118] In this embodiment of the present application, based on the vector representation of the target ad slot, one or more audio ads that are strongly related to the audio program the user was listening to before the target ad slot can be determined. Furthermore, the audio ads can be further filtered or processed based on user characteristics to obtain an audio ad that matches the target ad slot. Because the audio ads determined by this application have a higher degree of match with the audio program and incorporate user characteristics, they can better meet the user's personalized needs and improve the effectiveness of audio ad delivery.

[0119] The above step 303 may include: the cloud recalls multiple audio advertisements from the audio advertisement library according to the vector representation of the target advertisement slot; and the cloud obtains an audio advertisement matching the target advertisement slot from the multiple audio advertisements according to user characteristics.

[0120] Further, it may include: the cloud predicts the completion rate of multiple audio advertisements based on user characteristics and an advertisement ranking model, wherein the audio advertisement with the highest completion rate is the audio advertisement that matches the target advertisement slot, or the audio advertisement with the highest completion rate is the source advertisement of the audio advertisement that matches the target advertisement slot. The advertisement ranking model is a model that takes user characteristics as input and completion rate as output.

[0121] That is to say, in an embodiment of the present application, the process of determining audio advertisements may include advertisement recall, advertisement sorting, and style transfer, which are introduced below respectively.

[0122] 1. Advertisement recall.

[0123] Ad recall refers to fetching multiple audio ads from the audio ad library that are relevant to the content described by the vector representation of the target ad slot.

[0124] 2. Advertisement sorting.

[0125] The cloud can use the ad ranking model to score each recalled audio ad, or it can sort them based on the scores and select the audio ad with the highest score.

[0126] In the embodiment of the present application, the advertisement ranking model is a model that takes user features as input and outputs completion rate. The advertisement ranking model can be a machine learning model. For the advertisement ranking model, please refer to Figure 4 for understanding. As shown in Figure 4, the input in the advertisement ranking model may include audio programs, audio advertisements, audio advertisement texts (audio advertisements in text form), slot texts (advertisement slots in text form), and may also include slot weights, audio advertisement features, audio program features, contextual features, etc. In addition, the input of the advertisement ranking model provided in the embodiment of the present application also includes user features. In this way, after the embedding layer processes the slot weights, audio advertisement features, audio program features, contextual features, and user feature information, and after audio encoding the audio program and audio advertisement, and text encoding the audio advertisement text and slot text, they are all input into the connection (Concat) & flattening (Flatten) layer for processing, and the completion rate of the audio advertisement for the user is input through the neural network. The neural network may include a convolutional neural network (deep neural network, DNN), a deep interest network (deep interest network, DIN) or a deep factorization machine (deep factorization machine, DeepFM).

[0127] Multiple recalled audio ads can be fed into the ad ranking model individually, all at once, or in batches to determine the completion rate for each audio ad. The completion rate can be thought of as a score for the audio ad, with the highest-scoring audio ad having the highest completion rate.

[0128] The completion rate refers to the predicted probability that an audio ad will be played in its entirety. The more closely an audio ad's content and style align with user preferences, the greater its probability of being played in its entirety, and the better the delivery performance. Therefore, the completion rate of multiple recalled audio ads can be predicted based on user characteristics. The audio ad with the highest completion rate can be selected as the final audio ad, thereby improving the delivery performance of audio ads.

[0129] 3. Style transfer.

[0130] In this embodiment of the present application, after the cloud determines the audio ad with the highest completion rate using an ad ranking model, it can adjust the style of the audio ad with the highest completion rate based on the style of the audio program the user wants to play or is currently playing and the user's characteristics, thereby obtaining an audio ad that matches the target ad slot. This can increase user acceptance of audio ads and thus improve the effectiveness of audio ad delivery.

[0131] It should be noted that after determining the audio advertisement with the highest completion rate, the audio advertisement with the highest completion rate can be directly determined as the audio advertisement that matches the target advertisement slot, or the audio advertisement with the highest completion rate can be used as the source advertisement to perform the above-mentioned style migration to obtain the audio advertisement that matches the target advertisement slot. This application does not limit this.

[0132] The style transfer process provided in the embodiment of the present application can be understood by referring to FIG5 .

[0133] As shown in Figure 5, the process may include:

[0134] 501. Cloud-based separation of object sound and background music in audio advertisements.

[0135] The target sound is usually the main sound in the audio advertisement, such as the narrator who explains the advertisement.

[0136] 502. Cloud-based separation of object sound and background music in audio programs.

[0137] 503. Encode the object sound in the audio program in the cloud to obtain a style vector of the object sound.

[0138] 504. Cloud-encode the background music in the audio program to obtain a style vector of the background music.

[0139] 505. Cloud-based encoding of user features to obtain user preference style vectors.

[0140] 506. The cloud adjusts the object sound in the audio advertisement with the highest score based on the style vector of the object sound and the style vector of the user preference.

[0141] The step 506 is to transfer the style of the object sound in the audio advertisement.

[0142] 507. The cloud adjusts the background music in the highest-scoring audio advertisement based on the background music style vector and the user's preferred style vector.

[0143] The step 507 is to transfer the style of the background sound in the audio advertisement.

[0144] Style transfer can be the replacement or partial adjustment of the style of the object sound or background music.

[0145] 508. The object sound and background music after the style transfer in steps 506 and 507 are merged to obtain an audio advertisement.

[0146] It should be noted that if there is no background music in the audio advertisement or audio program, steps related to background music processing may not be performed, such as one or more steps in steps 501, 502, 504, 507 or 508.

[0147] In the embodiment of the present application, the style of the audio advertisement is consistent with the style of the audio advertisement after adjustment, which can meet the user's style preferences, improve the user experience, and thus improve the delivery effect of the audio advertisement.

[0148] The above describes the process of online audio advertising. The following further describes the process of mining advertising slots offline or online in FIG. 1B .

[0149] As shown in FIG6 , an embodiment of the method for mining advertisement slots provided by the present application includes:

[0150] 601. Obtain audio programs with advertising slots to be mined from the cloud.

[0151] The cloud can obtain audio programs with advertising slots to be mined from the audio content library.

[0152] 602. The cloud detects the audio program in voice state.

[0153] 603. When the time domain information is amplitude, if the duration during which the amplitude of the audio program in the voice state is continuously lower than the amplitude threshold exceeds the first threshold, the cloud determines the duration during which the amplitude is continuously lower than the amplitude threshold as the first basic advertising slot.

[0154] 604. The cloud converts the audio program into text content and records the timestamps of the words in the text content, and determines the time interval between two adjacent words based on the timestamps of the two adjacent words.

[0155] The first threshold and the second threshold may be the same or different.

[0156] 605. If the time interval between two adjacent words in the text content converted from the audio program is greater than the second threshold, the cloud determines the time interval between the two adjacent words as the second basic advertising slot.

[0157] 606. Recover punctuation marks in text content in the cloud.

[0158] 607. The cloud increases the weight of the basic ad slot corresponding to the ending punctuation mark in the punctuation mark.

[0159] The basic advertisement slot in the embodiment of the present application refers to the advertisement slot that is the union of the first basic advertisement slot and the second basic advertisement slot.

[0160] Of course, the first basic advertisement slot and the second basic advertisement slot may overlap.

[0161] 608. The cloud divides the text content of the recovery symbol into text segments and increases the weight of the basic advertising slot between the two text segments.

[0162] The processes of the above steps 602 to 608 can be understood by referring to the example in FIG. 7.

[0163] As shown in FIG. 7, the cloud can first detect an audio program (a segment shown in FIG. 7 can be intercepted from the audio program). If it is detected that there is a segment of audio with a very small amplitude (less than the amplitude threshold) and the duration exceeds the first threshold, it can be determined that the object in the audio program does not make a sound during this duration, that is, it is in a pause state. This duration can also be determined as a first basic advertisement slot.

[0164] Then, the cloud can convert a segment of audio shown in FIG. 7 into text through speech recognition. As can be seen from FIG. 7, the converted text content includes: "Today the weather is really nice. Where shall we go to play? The Summer Palace is in Haidian District." Among them, the timestamp of "Today" is 1, the timestamp of "weather" is 2, the timestamp of "really nice" is 3, the timestamp of "shall we" is 6, the timestamp of "where" is 7, the timestamp of "go to play" is 8, the timestamp of "the Summer Palace" is 12, the timestamp of "is in" is 13, and the timestamp of "Haidian District" is 14. From the timestamps of each word, it can be determined that the timestamps 4 and 5 are missing between "really nice" and "shall we", that is, there is a pause between the two words "really nice" and "shall we". If the second threshold is equal to 1 (or other values between 0 and 2), then this place can be determined as a second basic advertisement slot. Similarly, between the timestamps of "go to play" and "the Summer Palace", 9, 10, and 11 are missing, so this place can be determined as a second basic advertisement slot. A second basic advertisement slot can also be determined at "Haidian District". As can be seen from FIG. 7, the first basic advertisement slot basically overlaps with the second basic advertisement slot between "go to play" and "the Summer Palace". For the convenience of description, hereinafter, the first basic advertisement slot and the second basic advertisement slot shown in FIG. 7 are both collectively referred to as the basic advertisement slot.

[0165] Next, the punctuation marks in the text can be restored. As shown in FIG. 7, the text content after restoring the punctuation marks includes: "Today the weather is really nice. Where shall we go to play? The Summer Palace is in Haidian District." Because the pauses of the question mark "?" and the full stop "." in the punctuation marks are usually longer than that of the comma ",", the weights of the two basic advertisement slots corresponding to "?" and "." can be boosted, that is, the weights of these two basic advertisement slots are increased.

[0166] Furthermore, the text content shown in FIG. 7 can be segmented. "Today the weather is really nice. Where shall we go to play?" can be divided into text segment 1, and "The Summer Palace is in Haidian District." can be divided into text segment 2. The pause at the segmentation of the two text segments is longer, so the weights of the basic advertisement slots at the segmentation of the two text segments can be further boosted, that is, the weight of the basic advertisement slot between "go to play" and "the Summer Palace" is further increased.

[0167] 609. The cloud selects at least one base ad slot with the largest weight as at least one ad slot for the audio program.

[0168] After performing the above operations, the weight of the base ad slot between "play" and "Summer Palace" is the largest. If one ad slot is selected in this segment of audio shown in Figure 7, the base ad slot between "play" and "Summer Palace" can be selected as the ad slot for this segment of audio.

[0169] 610. The cloud encodes the text content with a preset length before each ad slot in at least one ad slot to obtain a vector representation of each ad slot.

[0170] The cloud can encode the text content of "It's a nice day today. Where shall we go play?", and thus obtain the vector representation of the ad slot between "play" and "Summer Palace".

[0171] 611.The cloud can send the identifier and vector representation of each ad slot to the audio content library for associated storage with the audio content. <00003,45>In this way, when the user plays this segment of audio and reaches the ad slot between "play" and "Summer Palace", audio ads related to tourism can be selected for pushing. When pushing, the user's location and the types of scenic spots the user has visited in the past can also be considered to screen audio ads that match "It's a nice day today. Where shall we go play?" and put them in the ad slot between "play" and "Summer Palace". In this way, the audio program and the audio ads are continuous, which will not affect the user's listening experience and can improve the delivery effect of the audio ads

[0173] To better understand the connection between the ad mining process and the ad delivery process provided in the embodiments of the present application, the following provides a combined description of the two processes with reference to Figure 8.

[0174] 801. Ad slot mining based on audio content. <00003,50>

[0175] This process may include ad slot identification and ad slot vector representation.

[0176] The process of this step 801 can be understood by referring to the previous steps 601 to 611, and will not be repeated here.

[0177] 802. During the audio ad delivery process, when the client plays an audio program, it determines whether it has reached an ad slot. If so, it executes step 803; if not, it continues to play the audio program.

[0178] 803. When playing to the advertisement slot, determine whether to send an advertisement request. If so, execute step 804. If not, continue playing the audio program.

[0179] If enough ads have been played before, that is, the duration of playing music ads has exceeded the preset value, no ads will be played in subsequent ad slots, and there is no need to send an ad request.

[0180] 804. Recall multiple audio ads from the audio ad library.

[0181] 805. Personalize audio advertisement sorting for multiple audio advertisements.

[0182] Steps 804 and 805 may be understood by referring to the above introduction of advertisement recall and advertisement scoring.

[0183] 806. Determine whether to deliver audio advertisements.

[0184] Determine whether to deliver the audio advertisement based on the scoring result. If all audio advertisement scores are below the score threshold, the audio advertisement will not be delivered. If the audio advertisement with the highest score is above the score threshold, the audio advertisement with the highest score will be delivered, and step 807 will be performed.

[0185] 807. Audio Advertising Style Transfer.

[0186] The step 807 may be understood by referring to the introduction of the previous style transfer section.

[0187] 808. Play the audio advertisement after style transfer, and continue playing the audio program after playing.

[0188] The ad slot mining process described above combines text content with a vector representation. This allows us to identify audio ads that better match the audio content when delivering ads. Furthermore, user characteristics are used when delivering audio ads, which better meets the personalized needs of users and improves the effectiveness of audio ad delivery.

[0189] The above introduces the method of mining advertising slots and the method of audio advertising delivery. The cloud device and client in the embodiment of the present application are introduced below with reference to the accompanying drawings.

[0190] As shown in FIG9 , a structure of a cloud device 90 provided in an embodiment of the present application includes:

[0191] Receiving unit 901 is configured to receive an advertisement request from a client. The advertisement request includes information about the audio program, an identifier of a target advertisement slot, and user characteristics. The target advertisement slot is one of at least one advertisement slot mined from the audio program. The advertisement request is triggered when the client plays the audio program. Receiving unit 901 may perform step 301 in the above-described method embodiment.

[0192] A first processing unit 902 is configured to determine a vector representation of the target ad slot based on the audio program information and the identifier of the target ad slot. The vector representation of the target ad slot describes the content of the audio program within a period of time preceding the target ad slot. The first processing unit 902 may execute step 302 in the aforementioned method embodiment.

[0193] The second processing unit 903 is configured to obtain an audio advertisement matching the target advertisement slot according to the user characteristics and the vector representation of the target advertisement slot. The second processing unit 903 may execute step 303 in the above method embodiment.

[0194] The sending unit 904 is configured to send an audio advertisement to the client, where the audio advertisement is played when the client plays the audio program to the target advertisement slot. The sending unit 904 may execute step 304 in the above method embodiment.

[0195] In this embodiment of the present application, based on the vector representation of the target ad slot, one or more audio ads that are strongly related to the audio program the user was listening to before the target ad slot can be determined. Furthermore, the audio ads can be further filtered or processed based on user characteristics to obtain an audio ad that matches the target ad slot. Because the audio ads determined by this application have a higher degree of match with the audio program and incorporate user characteristics, they can better meet the user's personalized needs and improve the effectiveness of audio ad delivery.

[0196] Optionally, the second processing unit 903 is specifically configured to recall multiple audio advertisements from the audio advertisement library according to the vector representation of the target advertisement slot; and obtain an audio advertisement matching the target advertisement slot from the multiple audio advertisements according to user characteristics.

[0197] Optionally, the second processing unit 903 is specifically used to predict the completion rate of multiple audio advertisements based on user characteristics and an advertisement sorting model, wherein the audio advertisement with the highest completion rate is the audio advertisement that matches the target advertisement slot, or the audio advertisement with the highest completion rate is the source advertisement of the audio advertisement that matches the target advertisement slot. The advertisement sorting model is a model that takes user characteristics as input and completion rate as output.

[0198] Optionally, the second processing unit 903 is specifically used to adjust the style of the audio advertisement with the highest completion rate according to the style of the audio program and user characteristics to obtain an audio advertisement that matches the target advertisement slot when the audio advertisement with the highest completion rate is the source advertisement of the audio advertisement that matches the target advertisement slot.

[0199] Optionally, the second processing unit 903 is specifically used to adjust the object sound in the audio advertisement with the highest completion rate based on the style vector of the object sound in the audio program and the style vector of the user's preference, the style vector of the object sound in the audio program is obtained by encoding the object sound in the audio program, and the style vector of the user's preference is obtained by encoding the user's features; adjust the background music in the audio advertisement with the highest completion rate based on the style vector of the background music in the audio program and the style vector of the user's preference, the style vector of the background music in the audio program is obtained by encoding the background music in the audio program; and fuse the adjusted object sound in the audio advertisement with the highest completion rate and the adjusted background music in the audio advertisement with the highest completion rate to obtain an audio advertisement that matches the target advertising slot.

[0200] Optionally, the first processing unit 902 is further used to determine at least one advertising slot based on time domain information of the audio program in a voice state and text content after the audio program is converted into text; and encode the text content of each advertising slot in the at least one advertising slot within a previous period of time to obtain a vector representation of each advertising slot.

[0201] Optionally, the first processing unit 902 is specifically configured to, when the time domain information is amplitude, determine the time duration during which the amplitude of the audio program in the voice state is continuously lower than the amplitude threshold as a first basic advertising slot if the duration exceeds a first threshold; determine the time duration between two adjacent words in the text content after the audio program is converted from the audio program as a second basic advertising slot if the time interval between the two adjacent words is greater than a second threshold, where the time interval between the two adjacent words is determined by the timestamp of each word during text conversion; and determine at least one advertising slot from the union of the first basic advertising slot and the second basic advertising slot.

[0202] Optionally, the first processing unit 902 is specifically used to select at least one advertising slot with the largest weight from the union of the first basic advertising slot and the second basic advertising slot to determine as at least one advertising slot of the audio program, and the weight of each advertising slot in the at least one advertising slot is determined by the punctuation marks and / or text segment segmentation positions corresponding to each advertising slot.

[0203] Optionally, the user characteristics include user portraits and user behavior characteristics regarding historical audio programs.

[0204] In the embodiment of the present application, the operations performed by each unit in the cloud device 90 are similar to those described in the embodiments shown in Figures 3 to 8 above, and will not be repeated here.

[0205] As shown in FIG10 , a structure of a client 100 provided in an embodiment of the present application includes:

[0206] The sending unit 1001 is used to send an advertisement request to the cloud when playing an audio program. The advertisement request includes information about the audio program, an identifier of a target advertisement slot, and user characteristics. The target advertisement slot is one of at least one advertisement slot mined from the audio program.

[0207] The receiving unit 1002 is configured to receive an audio advertisement sent by the cloud that matches a target advertisement slot.

[0208] The processing unit 1003 is configured to play an audio advertisement when the audio program reaches a target advertisement slot.

[0209] Optionally, the user characteristics include user portraits and user behavior characteristics regarding historical audio programs.

[0210] In the embodiment of the present application, the operations performed by each unit in the client 100 are similar to those described in the embodiments shown in Figures 3 to 8 above, and will not be repeated here.

[0211] As shown in FIG11 , the embodiment of the present application further provides another structure of the cloud device 110 including:

[0212] The acquisition unit 1101 is configured to acquire the audio program for which the advertisement slot is to be mined.

[0213] The first processing unit 1102 is configured to determine at least one advertisement slot based on time domain information of the audio program in a speech state and text content after the audio program is converted into text.

[0214] The second processing unit 1103 is configured to encode text content of each advertisement slot in the at least one advertisement slot within a previous period of time to obtain a vector representation of each advertisement slot.

[0215] Optionally, the first processing unit 1102 is specifically configured to, when the time domain information is amplitude, determine the duration during which the amplitude of the audio program in the voice state is continuously lower than the amplitude threshold as a first basic advertising slot if the duration during which the amplitude is continuously lower than the amplitude threshold exceeds a first threshold; determine the duration during which the amplitude is continuously lower than the amplitude threshold as a second basic advertising slot if the time interval between two adjacent words in the text content after the audio program is converted is greater than a second threshold, where the time interval between the two adjacent words is determined by the timestamp of each word during text conversion; and determine at least one advertising slot from the union of the first basic advertising slot and the second basic advertising slot.

[0216] Optionally, the first processing unit 1102 is specifically used to select at least one advertising slot with the largest weight from the union of the first basic advertising slots and the second basic advertising slots to determine as at least one advertising slot of the audio program, and the weight of each advertising slot in the at least one advertising slot is determined by the punctuation marks and / or text segment segmentation positions corresponding to each advertising slot.

[0217] In the embodiment of the present application, the operations performed by each unit in the cloud device 110 are similar to those described in the embodiments shown in Figures 3 to 8 above, and will not be repeated here.

[0218] In another embodiment of the present application, a computer-readable storage medium is also provided, in which computer-executable instructions are stored. When the processor of the cloud device executes the computer-executable instructions, the cloud device executes the steps performed by the cloud device in Figures 3 to 8 above.

[0219] In another embodiment of the present application, a computer-readable storage medium is provided, in which computer-executable instructions are stored. When the processor of the client executes the computer-executable instructions, the client executes the steps performed by the client in Figures 3 to 8 above.

[0220] In another embodiment of the present application, a computer program product is further provided. The computer program product includes computer program code. When the computer program code is executed on a computer, the computer device executes the steps executed by the cloud device or client in Figures 3 to 8 above.

[0221] In another embodiment of the present application, a chip system is also provided, which includes one or more interface circuits and one or more processors; the interface circuit and the processor are interconnected by lines; the interface circuit is used to receive signals from the memory of the terminal and send signals to the processor, and the signals include computer instructions stored in the memory; when the processor executes the computer instructions, the terminal executes the steps performed by the cloud device or client in Figures 3 to 8 above. In one possible design, the chip system may also include a memory, which is used to store program instructions and data necessary for the control device. The chip system can be composed of chips, or it can include chips and other discrete devices.

[0222] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0223] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0224] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in whole or in part through software, hardware, firmware, or any combination thereof.

[0225] When software is used to implement the integrated unit, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)).

Claims

A method for delivering audio advertisements, characterized in that: include: The cloud receives an advertisement request from a client, wherein the advertisement request includes information of an audio program, an identifier of a target advertisement slot, and user characteristics, wherein the target advertisement slot is one of at least one advertisement slot mined from the audio program, and the advertisement request is triggered when the client plays the audio program; the cloud determines a vector representation of the target advertisement slot based on the information of the audio program and the identifier of the target advertisement slot, wherein the vector representation of the target advertisement slot is used to describe the content involved in the audio program within a period of time before the target advertisement slot; the cloud obtains an audio advertisement matching the target advertisement slot based on the user characteristics and the vector representation of the target advertisement slot; the cloud sends the audio advertisement to the client, and the audio advertisement is used to be played by the client when the audio program is played to the target advertisement slot. The method according to claim 1, characterized in that The cloud determines an audio advertisement matching the target advertisement slot according to the user characteristics and the vector representation of the target advertisement slot, including: the cloud recalls a plurality of audio advertisements from an audio advertisement library according to the vector representation of the target advertisement slot; the cloud obtains an audio advertisement matching the target advertisement slot from the plurality of audio advertisements according to the user characteristics. The method according to claim 2, characterized in that The cloud obtains the audio advertisement matching the target advertisement slot from the multiple audio advertisements according to the user characteristics, including: the cloud predicts the completion rates of the multiple audio advertisements according to the user characteristics and an advertisement sorting model, wherein the audio advertisement with the largest completion rate is the audio advertisement matching the target advertisement slot, or the audio advertisement with the largest completion rate is the source advertisement of the audio advertisement matching the target advertisement slot, and the advertisement sorting model is a model that takes user characteristics as input and completion rate as output. The method according to claim 3, characterized in that When the audio advertisement with the highest completion rate is the source advertisement of the audio advertisement that matches the target advertisement slot, the method further includes: the cloud adjusts the style of the audio advertisement with the highest completion rate according to the style of the audio program and the user characteristics to obtain the audio advertisement that matches the target advertisement slot. The method according to claim 4, characterized in that The cloud adjusts the style of the audio advertisement with the highest completion rate according to the style of the audio program and the user characteristics to obtain an audio advertisement matching the target advertisement slot, including: the cloud adjusts the object sound in the audio advertisement with the highest completion rate according to the style vector of the object sound in the audio program and the style vector of the user preference, the style vector of the object sound in the audio program being obtained by encoding the object sound in the audio program, and the style vector of the user preference being obtained by encoding the user characteristics; the cloud adjusts the background music in the audio advertisement with the highest completion rate according to the style vector of the background music in the audio program and the style vector of the user preference, the style vector of the background music in the audio program being obtained by encoding the background music in the audio program; the cloud merges the adjusted object sound in the audio advertisement with the highest completion rate and the adjusted background music in the audio advertisement with the highest completion rate to obtain the audio advertisement matching the target advertisement slot. The method according to any one of claims 1 to 5, characterized in that Before the cloud receives the advertisement request sent by the client, the method further includes: the cloud determines at least one advertisement slot based on the time domain information of the audio program in the voice state and the text content after the audio program is converted into text; the cloud encodes the text content of each advertisement slot in the at least one advertisement slot within a previous period of time to obtain a vector representation of each advertisement slot. The method according to claim 6, characterized in that The method also includes: the cloud stores the audio program, the identifier of each advertising slot, and the vector representation of each advertising slot in an associated manner. The method according to claim 6 or 7, characterized in that The cloud determines at least one advertising slot based on the time domain information of the audio program in the voice state and the text content after the audio program is converted into text, including: when the time domain information is amplitude, if the duration for which the amplitude of the audio program in the voice state is continuously lower than the amplitude threshold exceeds a first threshold, the cloud determines the duration for which the amplitude is continuously lower than the amplitude threshold as a first basic advertising slot; if the time interval between two adjacent words in the text content after the audio program is converted is greater than a second threshold, the cloud determines the time interval between the two adjacent words as a second basic advertising slot, and the time interval between the two adjacent words is determined by the timestamp of each word during text conversion; the cloud determines the at least one advertising slot from the union of the first basic advertising slot and the second basic advertising slot. The method according to claim 8, characterized in that The cloud determines the at least one advertisement slot from the union of the first basic advertisement slots and the second basic advertisement slots, including: the cloud selects at least one advertisement slot with the largest weight from the union of the first basic advertisement slots and the second basic advertisement slots as at least one advertisement slot of the audio program, and the weight of each advertisement slot in the at least one advertisement slot is determined by the punctuation marks and / or text segment segmentation positions corresponding to each advertisement slot. The method according to any one of claims 1 to 9, characterized in that The user characteristics include user portraits and user behavior characteristics for historical audio programs. A method for delivering audio advertisements, characterized in that: include: When the client plays an audio program, it sends an advertisement request to the cloud, wherein the advertisement request includes information of the audio program, an identifier of a target advertisement slot, and user characteristics, wherein the target advertisement slot is one of at least one advertisement slot mined from the audio program; the client receives an audio advertisement matching the target advertisement slot sent by the cloud; and the client plays the audio advertisement when playing the audio program to the target advertisement slot. The method according to claim 11, characterized in that The user characteristics include user portraits and user behavior characteristics for historical audio programs. A method for mining advertising slots, characterized in that: include: The cloud obtains an audio program for an advertisement slot to be mined; the cloud determines at least one advertisement slot based on time domain information of the audio program in a voice state and text content after the audio program is converted into text; the cloud encodes the text content of each advertisement slot in the at least one advertisement slot within a previous period of time to obtain a vector representation of each advertisement slot. The method according to claim 13, characterized in that The method also includes: the cloud stores the audio program, the identifier of each advertising slot, and the vector representation of each advertising slot in an associated manner. The method according to claim 13 or 14, characterized in that The cloud determines at least one advertising slot based on the time domain information of the audio program in the voice state and the text content after the audio program is converted into text, including: when the time domain information is amplitude, if the duration for which the amplitude of the audio program in the voice state is continuously lower than the amplitude threshold exceeds a first threshold, the cloud determines the duration for which the amplitude is continuously lower than the amplitude threshold as a first basic advertising slot; if the time interval between two adjacent words in the text content after the audio program is converted is greater than a second threshold, the cloud determines the time interval between the two adjacent words as a second basic advertising slot, and the time interval between the two adjacent words is determined by the timestamp of each word during text conversion; the cloud determines the at least one advertising slot from the union of the first basic advertising slot and the second basic advertising slot. The method according to claim 15, characterized in that The cloud determines the at least one advertisement slot from the union of the first basic advertisement slots and the second basic advertisement slots, including: the cloud selects at least one advertisement slot with the largest weight from the union of the first basic advertisement slots and the second basic advertisement slots as at least one advertisement slot of the audio program, and the weight of each advertisement slot in the at least one advertisement slot is determined by the punctuation marks and / or text segment segmentation positions corresponding to each advertisement slot. A cloud device, characterized in that: include: A communication interface, a processor and a memory, wherein the communication interface and the processor are coupled to the memory, and the memory is used to store programs or instructions. When the program or instructions are executed by the processor, the cloud device executes the method as described in any one of claims 1 to 10, or executes the method as described in any one of claims 13 to 16. A client, characterized in that: include: A transceiver, a processor and a memory, wherein the transceiver and the processor are coupled to the memory, and the memory is used to store programs or instructions. When the programs or instructions are executed by the processor, the client executes the method as claimed in claim 11 or 12. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed on a computer device, the computer device is caused to perform the method according to any one of claims 1 to 16. A computer program product, characterized in that The computer program product comprises a computer program code, which, when executed on a computer device, causes the computer device to perform the method according to any one of claims 1 to 16. A chip system, characterized in that: The chip system includes one or more interface circuits and one or more processors; the interface circuit and the processor are interconnected through lines; the interface circuit is used to receive signals from the memory of the cloud device and send signals to the processor, and the signals include computer instructions stored in the memory; when the processor executes the computer instructions, the cloud device executes the method as described in any one of claims 1 to 10, or executes the method as described in any one of claims 13 to 16. A chip system, characterized in that: The chip system includes one or more interface circuits and one or more processors; the interface circuits and the processors are interconnected via lines; the interface circuits are used to receive signals from the client's memory and send signals to the processor, the signals including computer instructions stored in the memory; when the processor executes the computer instructions, the client executes the method as described in claim 11 or 12. An audio advertising system, characterized in that: include: A client and a cloud, wherein the cloud is used to execute the method according to any one of claims 1 to 10, and the client is used to execute the method according to claim 11 or 12

Images