Voice advertisement processing method based on paper separator

Abstract

The embodiment of the invention relates to a voice advertisement processing method based on a paper separator. The method comprises the following steps: receiving a voice instruction of a user; processing the voice instruction, and determining a first advertisement data set; playing a plurality of advertisement data in the first advertisement data set according to the first score, and recording the playing time of each advertisement data; obtaining a first advertisement data set of each user of each place within a preset time length to form a second advertisement data set of the place; the second number is not less than the first number; calculating the playing rate of the advertisement data according to the playing time of each piece of advertisement data; paper data and advertisement data types of the place are acquired; calculating a second score of the advertisement data according to the advertisement data type and the playing rate; determining a playing mode of advertisement data according to the paper data; and playing the advertisement data in the playing mode according to the second score and the paper separator ID bound with the place.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a voice advertisement processing method based on a paper separator. Background Art

[0002] Traditional advertising methods such as television, radio, and newspapers, although they have a wide coverage, are not very targeted and are easily restricted by time and location. For example, new media advertising methods such as Internet, mobile communications, and social media, although they have the advantages of being complex and niche, they are also overloaded with information, have uneven quality, and may have problems with privacy leakage and information security. Summary of the invention

[0003] The purpose of the present invention is to provide a voice advertisement processing method based on a paper separator in view of the defects in the prior art, so as to solve the problems in the prior art.

[0004] To achieve the above object, the present invention provides a first aspect of a voice advertisement processing method based on a paper separator, the method comprising:

[0005] Receive user's voice command;

[0006] Processing the voice command to determine a first advertising data set; wherein the first advertising data set includes a first number of advertising data, each of which has a first score;

[0007] Playing multiple advertisement data in the first advertisement data set according to the first score, and recording the playing time of each advertisement data;

[0008] Acquire a first advertising data set of each user at each location within a preset time period to form a second advertising data set at the location; wherein the second advertising data set includes a second number of advertising data; the second number is not less than the first number;

[0009] Calculate the play rate of the advertisement data according to the play time of each advertisement data;

[0010] Obtaining paper usage data and advertisement data type of the location;

[0011] Calculating a second score of the advertisement data according to the advertisement data type and the play rate;

[0012] Determining a play mode of the advertisement data according to the paper usage data;

[0013] According to the second score and the paper separator ID bound to the location, the advertisement data is played in the play mode.

[0014] In a possible implementation, the processing the voice instruction to determine the first advertisement data set specifically includes:

[0015] Filtering, denoising, and framing the voice command;

[0016] Perform feature extraction on the processed voice command to obtain feature parameters;

[0017] Matching the characteristic parameters with the models in the acoustic model library to identify speech units; the speech units include phonemes and keywords;

[0018] Obtaining text output according to the phonemes and keywords;

[0019] After word segmentation and stop word removal, the text is semantically analyzed through the AI ​​voice model to determine the intent;

[0020] Matching the intent with the intent classification model to determine the user's target intent;

[0021] According to the target intent, a first advertisement data set is screened out from an advertisement database;

[0022] Processing the target intent and determining keywords;

[0023] According to the keyword matching algorithm, a first advertisement data set is determined.

[0024] In a possible implementation, after determining the first advertisement data set according to the keyword matching algorithm, the method further includes:

[0025] Performing semantic matching on the first advertisement data set;

[0026] According to the semantic matching result, the first advertisement data set is determined again.

[0027] In a possible implementation, the processing the voice instruction to determine the first advertisement data set specifically includes:

[0028] Extracting features from the voice command to determine acoustic features and language features of the voice command; the acoustic features include speech rate features, intonation features, volume features, and timbre features; and the language features include vocabulary selection features, grammatical structure features, and expression features;

[0029] Constructing a user profile based on the acoustic features and language features;

[0030] The user portrait is matched with a preset user portrait to determine a first advertisement data set.

[0031] In a possible implementation, the method further includes:

[0032] Get the historical voice commands of historical users;

[0033] Performing feature processing on the historical voice instructions to determine acoustic features and language features of the historical voice instructions;

[0034] A voice portrait is constructed based on the acoustic features and the language features to form a preset voice portrait.

[0035] In a possible implementation, calculating the play rate of the advertisement data according to the play time of each advertisement data specifically includes:

[0036] Calculating the total number of plays of all the advertisement data in the second number of advertisement data;

[0037] Calculate the number of plays of any advertisement data;

[0038] The play rate of any advertisement data is calculated by the ratio of the play number of any advertisement data to the total play number.

[0039] In a possible implementation manner, calculating the second score of the advertisement data further includes:

[0040] Receiving a user's operation instruction for the advertising data; the operation instruction includes a user ID; the operation instruction includes following a public account, receiving a coupon, or obtaining an electronic redemption code;

[0041] Calculating the conversion rate of the advertisement data according to the operation instruction;

[0042] A second score of the advertisement data is calculated according to the conversion rate, the type and the play rate.

[0043] In a possible implementation, calculating the second score of the advertisement data according to the advertisement data type and the play rate specifically includes:

[0044] Analyze the voice command to obtain the user's age data and gender data;

[0045] Determining a user category based on the age data and gender data;

[0046] A second score of the advertisement data is calculated according to the user category, advertisement data type and play rate.

[0047] In a possible implementation, the advertising data playback mode includes a toilet equipment advertising playback mode and a toilet wall equipment advertising playback mode, the toilet equipment advertising playback mode includes an occupied playback mode and a paper output playback mode; the toilet wall equipment advertising playback mode includes a timed playback mode and a paper output playback mode.

[0048] In a second aspect, the present invention provides a computer server, comprising: a memory, a processor and a transceiver;

[0049] The processor is used to couple with the memory, read and execute instructions in the memory, so as to implement the voice advertisement processing method based on the paper separator according to any one of the first aspects;

[0050] The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

[0051] In a third aspect, the present invention provides a chip system, including a processor, the processor is coupled to a memory, the memory stores program instructions, and when the program instructions stored in the memory are executed by the processor, the paper separator-based voice advertising processing method described in any one of the first aspects is implemented.

[0052] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to implement the paper separator-based voice advertisement processing method described in any one of the first aspects.

[0053] The voice advertising processing method based on a paper separator and the voice advertising method based on a paper separator provided by the present invention can utilize the paper separator, an everyday item, to accurately deliver advertising information to the target audience, thereby realizing innovation in the way of advertising dissemination. By implanting advertisements into the control system of the paper separator, advertisements can be automatically played when the user takes paper, without the need for the user to actively search for or receive information. This method not only saves the user's time, but also improves the efficiency of advertising dissemination. The voice advertising system based on the paper separator can intelligently play related or interesting advertising content based on the user's paper-taking behavior, thereby enhancing the user's experience. For example, placing a paper separator in the bathroom of a shopping mall can play advertisements for merchant activities in the mall, which not only meets the needs of users, but also increases the accuracy of advertising delivery and enhances attractiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A schematic flow chart of a method for processing voice advertisements based on a paper separator provided in an embodiment of the present invention;

[0055] Figure 2 for Figure 1 One of the flowcharts of step 120;

[0056] Figure 3 for Figure 1 Flowchart 2 of step 120;

[0057] Figure 4 for Figure 3 Previous flow chart;

[0058] Figure 5 for Figure 1 Flowchart of step 170;

[0059] Figure 6 A schematic diagram of the computer server structure provided in Embodiment 2 of the present invention;

[0060] Figure 7 A schematic diagram of the chip system structure provided in Embodiment 3 of the present invention;

[0061] Figure 8 This is a schematic diagram of the chip system structure provided in Example 4 of the present invention. DETAILED DESCRIPTION

[0062] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments.

[0064] Embodiment 1

[0065] Figure 1 The present invention provides a flow chart of a method for processing voice advertisements based on a paper separator according to an embodiment of the present invention. The method is performed by a paper separator having a computing and processing capability, such as Figure 1 As shown, the method comprises the following steps:

[0066] Step 110, receiving a user's voice command;

[0067] Specifically, the paper separator can be set in the toilet seat or toilet wall, with a built-in sensor, such as a millimeter wave radar, through which it can detect whether there is someone. At the same time, the paper separator is provided with a voice recognition module, which can receive and process voice commands.

[0068] Step 120, processing the voice command to determine a first advertising data set;

[0069] The first advertisement data set includes a first number of advertisement data, each of the advertisement data has a first score, and the first score may be a rating value of each advertisement data.

[0070] Specifically, the first advertisement data set may be determined in the following two ways.

[0071] The first one, such as Figure 2 As shown, the following steps are included:

[0072] Step 201, filtering, denoising, and framing the voice command;

[0073] Specifically, speech signal preprocessing is performed to improve recognition accuracy in subsequent steps.

[0074] Step 202, extracting features from the processed voice command to obtain feature parameters;

[0075] Specifically, feature parameters that can reflect speech characteristics, such as Mel-Frequency Cepstral Coefficients (MFCC), are extracted from the preprocessed speech signal.

[0076] Step 203, matching the characteristic parameters with the models in the acoustic model library to identify speech units; the speech units include phonemes and keywords;

[0077] Specifically, the extracted feature parameters are matched with the models in the acoustic model library to identify corresponding speech units, such as phonemes, keywords, etc.

[0078] Step 204, obtaining text output according to the phonemes and keywords;

[0079] Specifically, according to the recognition result of the acoustic model, decoding is performed in combination with the language model to obtain the final text output.

[0080] Step 205, after word segmentation and stop word removal, semantic analysis is performed through an AI speech model to determine intent;

[0081] Specifically, text preprocessing is performed to perform word segmentation, stop word removal and other preprocessing operations on the text output by the speech recognition algorithm. Using AI speech large model processing technology, semantic analysis is performed on the preprocessed text to understand its intention and meaning.

[0082] Step 206, matching the intent with the intent classification model to determine the user's target intent;

[0083] Specifically, the result of semantic understanding is matched with a preset intent classification model to determine the user's intent.

[0084] Step 207, filtering out a first advertisement data set from an advertisement database according to the target intent;

[0085] The advertisement database is pre-established and includes various advertisement information and related metadata. For example, the information in the advertisement database includes advertisement classification, advertisement content, delivery time, target user group, advertisement label, and advertisement priority.

[0086] Step 208, processing the target intent to determine keywords;

[0087] Specifically, a voice request is sent to the paper separator through voice commands, such as "What discounts are there in the mall today?" to determine that the user's intention is "to view today's mall discounts," thereby filtering out related advertisements from the advertisement database. The filtering and matching method is as follows:

[0088] Keyword matching, through target intent, obtains keywords such as today, mall, discount, etc., and then matches them with the advertising data in the advertising database.

[0089] Step 209: Determine the first advertisement data set according to the keyword matching algorithm.

[0090] Specifically, according to the matching degree, a first advertisement data set is obtained.

[0091] Furthermore, in order to improve the accuracy of the first advertisement set, step 210 and step 211 may be performed after step 209 .

[0092] Step 210, performing semantic matching on the first advertisement data set;

[0093] Specifically, semantic matching is performed again on the acquired advertisement data to obtain similar advertisement data.

[0094] Step 211: determine the first advertisement data set again according to the semantic matching result.

[0095] Specifically, according to the semantic matching result, the first advertisement data set in step 210 is screened, and the recognized text is semantically matched to obtain similar advertisement data.

[0096] The second type, such as Figure 3 As shown, the following steps are included:

[0097] Step 301, extracting features from the voice command to determine acoustic features and language features of the voice command; the acoustic features include speech rate features, intonation features, volume features, and timbre features, and the language features include vocabulary selection features, grammatical structure features, and expression features;

[0098] Step 302, constructing a user profile based on the acoustic features and language features;

[0099] Step 303: Match the user portrait with a preset user portrait to determine a first advertising data set.

[0100] Before step 301, the process also includes the step of establishing a user portrait. Figure 4 As shown, the following steps are included:

[0101] Step 401, obtaining historical voice commands of historical users;

[0102] Step 402, performing feature processing on the historical voice instructions to determine acoustic features and language features of the historical voice instructions;

[0103] Step 403: construct a voice portrait based on the acoustic features and the language features to form a preset voice portrait.

[0104] The first score can be Figure 2 and Figure 3 The matching degree value calculated after the step is used as the first score. The higher the matching degree, the greater the first score, and vice versa.

[0105] Step 130, playing a plurality of advertisement data in the first advertisement data set according to the first score, and recording the playing time of each advertisement data;

[0106] Step 140 , obtaining a first advertisement data set of each user at each location within a preset time period to form a second advertisement data set of the location.

[0107] Among them, the second advertising data set includes a second number of advertising data; the second number is not less than the first number; the location can be a location coordinate, the toilet in the clean area can be encoded, the toilet seats in the toilet can be encoded, each code corresponds to a coordinate position, or the location can be directly represented by the code, and the present application does not limit this.

[0108] Step 150, calculating the play rate of the advertisement data according to the play time of each advertisement data;

[0109] Specifically, step 150 includes: calculating the total number of plays of all advertisement data in the second number of advertisement data; calculating the number of plays of any advertisement data; and calculating the play rate of any advertisement data by the ratio of the number of plays of any advertisement data to the total number of plays.

[0110] Step 160, obtaining paper usage data and advertisement data type of the location;

[0111] Specifically, the paper separator will record the paper usage data, including the paper usage time and the paper usage length or the number of times the paper is used, so as to facilitate the subsequent determination of the advertising data playback mode through the paper usage data.

[0112] The advertisement data type may include categories such as entertainment, education, fashion, etc. Each piece of advertisement data has attribute information, which may be stored in the form of a tag, and the attribute information includes but is not limited to the advertisement data type.

[0113] Step 170, calculating a second score of the advertisement data according to the advertisement data type and the play rate;

[0114] Specifically, the second score of the advertisement data may be determined by weighting according to the advertisement data type and the play rate. For example, different weights may be set for each advertisement data type, and a weight may be set for the play rate, so that the second score is determined according to the weighted value. The weight of the advertisement data type may be set according to the target audience and each type in the advertisement data type. For example, a weight may be set for a male target audience aged 25-30 years old.

[0115] Furthermore, when calculating the second score of the advertisement data, the conversion rate may be considered to improve the calculation accuracy. Figure 5 As shown:

[0116] Step 501, receiving a user's operation instruction for the advertisement data; the operation instruction includes a user ID; the operation instruction includes following a public account, receiving a coupon, or obtaining an electronic redemption code;

[0117] Step 502, calculating the conversion rate of the advertisement data according to the operation instruction;

[0118] Step 503: Calculate a second score of the advertisement data according to the conversion rate, the type, and the play rate.

[0119] Specifically, the advertisement is converted into the following corresponding conversions by opening and listening to the relevant pages on a mobile phone:

[0120] (1) Users can be guided to follow the official account or corporate WeChat account on the conversion page to achieve new user acquisition and conversion.

[0121] (2) Users can be guided to enter their mobile phone numbers on the conversion page to receive electronic coupons, and the conversion is completed when the coupons are redeemed at the customer's location.

[0122] (3) Users can be guided to obtain the electronic redemption code on the conversion page, and then jump to the customer's official account or mini program to redeem the coupon code. The conversion is completed when the coupon is redeemed at the customer's place.

[0123] Therefore, the conversion rate of a certain advertisement data can be calculated by dividing the total number of broadcasts of the certain advertisement data by whether the advertisement data has been converted.

[0124] Furthermore, the advertising exposure rate can be calculated through operation instructions. The advertising exposure rate means that when a user listens to a voice advertisement, he or she can use a mobile phone to scan the QR code on the body of the paper separator to open the conversion page related to the advertisement. The second score of the advertising data can be further calculated in combination with the exposure rate.

[0125] Furthermore, in order to further improve the calculation accuracy of the second score, user categories can be considered, such as Figure 6 As shown, the following steps are included:

[0126] Step 601, determining the user category according to the age data and gender data;

[0127] Specifically, by performing voice recognition on voice commands, the user's age data and gender data can be determined, thereby constructing user categories.

[0128] Step 602: Calculate a second score of the advertisement data according to the user category, advertisement data type and play rate.

[0129] Specifically, the second score of the advertisement data may be calculated based on the user category, advertisement data type, play rate, and conversion rate.

[0130] Step 180, determining a play mode of the advertisement data according to the paper data;

[0131] Specifically, the advertising data playback modes include toilet equipment advertising playback mode and toilet wall equipment advertising playback mode. The toilet equipment advertising playback mode includes occupancy playback mode and paper output playback mode. The playback rule of the occupancy playback mode can be to play an advertisement once when it is detected that there is someone for 10 seconds (freely settable), and to play it again when paper is first output when there is someone. The paper output playback mode can be to play advertisements based on the user's paper use behavior.

[0132] Playing rules: Every 3 times paper is discharged, an advertisement can be freely set to be played. The toilet wall device advertising playing mode includes a timed playing mode and a paper discharge playing mode. The timed playing mode can be set to play an advertisement every 5 minutes. The paper discharge playing mode can be set to play an advertisement every 3 times paper is discharged (freely set).

[0133] In the present application, when setting the timed play mode, the play frequency can be set according to the paper usage data, such as the paper usage frequency, so as to determine the play mode.

[0134] In the present application, the peak period of paper usage can also be determined based on the paper usage data, thereby determining the playback frequency.

[0135] Step 190: Play the advertisement data in the play mode according to the second score and the paper separator ID bound to the location.

[0136] Specifically, after the play mode is determined, the advertisement can be played according to the play mode, and then steps 110 - 190 are continued to be performed to update the advertisement data in real time, thereby improving the user experience.

[0137] The voice advertising processing method based on a paper separator and the voice advertising method based on a paper separator provided by the present invention can utilize the paper separator, an everyday item, to accurately deliver advertising information to the target audience, thereby realizing innovation in the way of advertising dissemination. By implanting advertisements into the control system of the paper separator, advertisements can be automatically played when the user takes paper, without the need for the user to actively search for or receive information. This method not only saves the user's time, but also improves the efficiency of advertising dissemination. The voice advertising system based on the paper separator can intelligently play related or interesting advertising content based on the user's paper-taking behavior, thereby enhancing the user's experience. For example, placing a paper separator in the bathroom of a shopping mall can play advertisements for merchant activities in the mall, which not only meets the needs of users, but also increases the accuracy of advertising delivery and enhances attractiveness.

[0138] Embodiment 2

[0139] Embodiment 2 of the present invention provides a computer server, such as Figure 6 As shown, it includes: a memory, a processor and a transceiver;

[0140] The processor is used to couple with the memory, read and execute instructions in the memory, so as to implement any one of the voice advertisement processing methods based on the paper separator provided in the first embodiment above;

[0141] The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

[0142] Embodiment 3

[0143] Embodiment 3 of the present invention provides a chip system, such as Figure 7 As shown, it includes a processor, a coupling between the processor and a memory, the memory stores program instructions, and when the program instructions stored in the memory are executed by the processor, any one of the paper separator-based voice advertisement processing methods provided in the first embodiment is implemented.

[0144] Embodiment 4

[0145] Embodiment 4 of the present invention provides a computer-readable storage medium, such as Figure 8As shown, it includes a program or instruction. When the program or instruction is run on a computer, any one of the paper separator-based voice advertisement processing methods provided in the first embodiment is implemented.

[0146] The professionals should further realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0147] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0148] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A voice advertisement processing method based on a paper separator, characterized in that: The method comprises: Receive user's voice command; Processing the voice command to determine a first advertising data set; wherein the first advertising data set includes a first number of advertising data, each of which has a first score; Playing multiple advertisement data in the first advertisement data set according to the first score, and recording the playing time of each advertisement data; Acquire a first advertising data set of each user at each location within a preset time period to form a second advertising data set at the location; wherein the second advertising data set includes a second number of advertising data; the second number is not less than the first number; Calculate the play rate of the advertisement data according to the play time of each advertisement data; Obtaining paper usage data and advertisement data type of the location; Calculating a second score of the advertisement data according to the advertisement data type and the play rate; Determining a play mode of the advertisement data according to the paper usage data; According to the second score and the paper separator ID bound to the location, the advertisement data is played in the play mode.

2. The method according to claim 1, characterized in that The processing of the voice command to determine the first advertisement data set specifically includes: Filtering, denoising, and framing the voice command; Perform feature extraction on the processed voice command to obtain feature parameters; Matching the characteristic parameters with the models in the acoustic model library to identify speech units; the speech units include phonemes and keywords; Obtaining text output according to the phonemes and keywords; After word segmentation and stop word removal, the text is semantically analyzed through the AI ​​voice model to determine the intent; Matching the intent with the intent classification model to determine the user's target intent; According to the target intent, a first advertisement data set is screened out from an advertisement database; Processing the target intent and determining keywords; According to the keyword matching algorithm, a first advertisement data set is determined.

3. The method according to claim 2, characterized in that After determining the first advertisement data set according to the keyword matching algorithm, the method further includes: Performing semantic matching on the first advertisement data set; According to the semantic matching result, the first advertisement data set is determined again.

4. The method according to claim 1, characterized in that: The processing of the voice command to determine the first advertisement data set specifically includes: Extracting features from the voice command to determine acoustic features and language features of the voice command; the acoustic features include speech rate features, intonation features, volume features, and timbre features; and the language features include vocabulary selection features, grammatical structure features, and expression features; Constructing a user profile based on the acoustic features and language features; The user portrait is matched with a preset user portrait to determine a first advertisement data set.

5. The method according to claim 4, characterized in that The method also includes: Get the historical voice commands of historical users; Performing feature processing on the historical voice instructions to determine acoustic features and language features of the historical voice instructions; A voice portrait is constructed based on the acoustic features and the language features to form a preset voice portrait.

6. The method according to claim 1, characterized in that The calculating the playing rate of the advertisement data according to the playing time of each advertisement data specifically includes: Calculating the total number of plays of all the advertisement data in the second number of advertisement data; Calculate the number of plays of any advertisement data; The play rate of any advertisement data is calculated by the ratio of the play number of any advertisement data to the total play number.

7. The method according to claim 1, characterized in that The calculating the second score of the advertisement data further comprises: Receiving a user's operation instruction for the advertising data; the operation instruction includes a user ID; the operation instruction includes following a public account, receiving a coupon, or obtaining an electronic redemption code; Calculating the conversion rate of the advertisement data according to the operation instruction; A second score of the advertisement data is calculated according to the conversion rate, the type and the play rate.

8. The method according to claim 1, characterized in that Calculating the second score of the advertisement data according to the advertisement data type and the play rate specifically includes: Analyze the voice command to obtain the user's age data and gender data; Determining a user category based on the age data and gender data; A second score of the advertisement data is calculated according to the user category, advertisement data type and play rate.

9. The method according to claim 1, characterized in that: The advertising data playback modes include toilet equipment advertising playback mode and toilet wall equipment advertising playback mode. The toilet equipment advertising playback mode includes an occupied playback mode and a paper output playback mode. The toilet wall equipment advertising playback mode includes a timed playback mode and a paper output playback mode.

10. A computer server, characterized in that: include: memory, processors, and transceivers; The processor is used to couple with the memory, read and execute instructions in the memory, so as to implement the voice advertisement processing method based on the paper separator according to any one of claims 1 to 9; The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

Images