A multi-screen interactive processing system and method based on smart TVs

Abstract

This invention discloses a multi-screen interaction processing system and method based on a smart TV, relating to the field of multi-screen interaction processing technology. It includes a data acquisition module, a control model creation module, a multi-screen interaction data monitoring module, and a multi-screen interaction dynamic processing module. The data acquisition module collects voice data output by the user during past multi-screen interactions and historical volume control data of the smart TV. The control model creation module establishes a volume adjustment control model for each user. The multi-screen interaction data monitoring module monitors the voice data output by the current user and the parameters of the current TV during multi-screen interaction. The multi-screen interaction dynamic processing module generates adjustment plans for the smart TV under different multi-screen interaction scenarios and adjusts parameters according to these plans, achieving adaptive parameter adjustment of the smart TV and improving the convenience of using the multi-screen interaction function.

Description

Technical Field

[0001] This invention relates to the field of multi-screen interaction processing technology, specifically a multi-screen interaction processing system and method based on a smart TV. Background Technology

[0002] The multi-screen interaction function of smart TVs refers to projecting the content of devices such as mobile phones, tablets or computers onto the smart TV screen through wireless or wired means, realizing interaction and content sharing between multiple devices. When using a smart TV for multi-screen interaction, users can cast videos from their terminals to the smart TV for viewing, and can also control the smart TV through voice to control the playback content.

[0003] When engaging in multi-screen interaction, if the volume of content played on a smart TV is inappropriate, users need to adjust the volume via voice control. Generally, users need to output specific voice commands to control the volume, such as increasing or decreasing the volume by a certain amount. However, the adjusted volume may still be inappropriate based on the user's subjective judgment, so it is necessary to repeatedly input voice commands until the volume of the content being played is adjusted to the appropriate value. Furthermore, users also need to judge how much to adjust the volume, which reduces the convenience of using the multi-screen interaction function. Secondly, since multiple users' voice information regarding volume adjustment may be recognized simultaneously, the existing technology lacks a dynamic adaptive volume processing method when recognizing voice information from multiple users, and cannot adaptively adjust the volume to meet the needs of multiple users at the same time. Summary of the Invention

[0004] The purpose of this invention is to provide a multi-screen interactive processing system and method based on a smart TV to solve the problems raised in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a multi-screen interactive processing system based on a smart TV, the system comprising a data acquisition module, a control model creation module, a multi-screen interactive data monitoring module, and a multi-screen interactive dynamic processing module;

[0006] The data acquisition module collects voice data output by users during previous multi-screen interactions, as well as historical volume control data of the smart TV.

[0007] The control model creation module establishes a separate volume adjustment control model for each user who has controlled the same smart TV.

[0008] The multi-screen interaction data monitoring module monitors the voice data output by the current user and the parameter data of the current TV when the current user interacts with the smart TV on multiple screens.

[0009] The multi-screen interaction dynamic processing module generates adjustment plans for smart TVs under different multi-screen interaction scenarios based on the volume adjustment control model, and adjusts parameters according to the plans.

[0010] Preferably, the data acquisition module includes a voice information acquisition unit, a database generation unit, and a historical control data acquisition unit;

[0011] The voice information acquisition unit is used to collect the voice of users who have previously controlled the smart TV via voice during multi-screen interaction. The voice data is collected after the user grants the permission.

[0012] The database generation unit is used to store the voice data collected from each user and generate a voice database, and to set the control level of all users on the smart TV. The level is set by the system default. The voice database contains the user's control level data and the corresponding user's voice data.

[0013] The historical control data acquisition unit is used to collect voice commands received by the smart TV when different users previously controlled the volume of the smart TV via voice, and extract control data from the voice commands. The control data includes volume increase and volume decrease data. The historical control data acquisition unit is also used to collect the initial volume data of the TV before adjusting the volume.

[0014] Preferably, the control model creation module includes a historical data training unit and an adjustment control model establishment unit;

[0015] The historical data training unit is used to combine the control data corresponding to each user and the initial volume data of the TV before adjusting the volume, and to perform fitting training on the combined data.

[0016] The adjustment control model establishment unit is used to establish a volume adjustment control model for each user on the smart TV based on the fitted training data. The volume adjustment control model includes a volume increase control model and a volume decrease control model.

[0017] Preferably, the multi-screen interactive data monitoring module includes a voice data receiving unit, an identity and command recognition unit, and a monitoring data output unit;

[0018] The voice data receiving unit is used to receive the voice command output by the current user regarding volume adjustment;

[0019] The identity and command recognition unit is used to recognize the received voice commands: match the voice commands with the voice commands in the voice database to identify the user corresponding to the voice command, and obtain the level of the corresponding user's control of the smart TV.

[0020] The monitoring data output unit is used to monitor the initial volume data of the current television.

[0021] Preferably, the multi-screen interactive dynamic processing module includes a first planning method generation unit, a second planning method generation unit, and an adaptive adjustment unit;

[0022] The first planning method generation unit is used to generate a first planning method for volume adjustment when the number of users currently outputting voice commands is 1: if the user outputs a voice command to increase the volume, the initial volume of the current TV is input into the volume increase control model corresponding to the current user, and the current optimal increase volume value is output; if the user outputs a voice command to decrease the volume, the initial volume of the current TV is input into the volume decrease control model corresponding to the current user, and the current optimal decrease volume value is output.

[0023] The second planning method generation unit is used to generate a second volume adjustment planning method when the number of users currently outputting voice commands is greater than 1 and all users output the same voice command (i.e., all users output the voice command "increase volume" or all users output the voice command "decrease volume"): If the user outputs the voice command "increase volume", the initial volume of the current TV is input into the volume increase control model corresponding to all users, and the current optimal increase volume value is set according to the volume value output by each model; if the user outputs the voice command "decrease volume", the initial volume of the current TV is input into the volume decrease control model corresponding to all users, and the current optimal decrease volume value is set according to the volume value output by each model.

[0024] The adaptive adjustment unit is used to adjust the volume of the smart TV according to a first planning method when the number of users currently outputting voice commands is 1; and to adjust the volume of the smart TV according to a second planning method when the number of users currently outputting voice commands is greater than 1 and all users output the same voice commands.

[0025] A multi-screen interaction processing method based on a smart TV includes the following steps:

[0026] S1: Collect voice data output by users during previous multi-screen interactions and historical volume control data of smart TVs;

[0027] S2: Establish a separate volume adjustment control model for each user who has controlled the same smart TV;

[0028] S3: When the current user is interacting with the smart TV on multiple screens, monitor the voice data output by the current user and the parameter data of the current TV.

[0029] S4: Generate adjustment planning methods for smart TVs under different multi-screen interaction scenarios based on the volume adjustment control model, and adjust the parameters of the smart TVs according to the planning methods.

[0030] Preferably, in step S1: voice recordings of users who have previously controlled the smart TV via voice during multi-screen interaction are collected; the collected voice data of each user is stored and a voice database is generated; the levels of all users controlling the smart TV are set to {1, 2, ... N}, where N represents the number of users who have controlled the smart TV via voice; voice commands received by the smart TV when different users previously controlled the volume of the smart TV via voice are collected; control data is extracted from the voice commands, including volume increase and volume decrease data; and the initial volume data of the TV before adjusting the volume is collected.

[0031] Preferably, in step S2: the set of volume levels that a random user has previously increased when controlling the television is {G1, G2, ... G...} is retrieved. m The initial volume set of the TV before the volume is increased is {g1, g2, ... g}. m Let m represent the number of times a random user has previously increased the TV volume, and the set of numbers corresponding to the number of times the user has previously decreased the TV volume is {H1, H2, ... H}. n The initial volume set of the TV before the volume is reduced is {h1, h2, ... h}. n}, where n represents the number of times a random user has lowered the TV volume in the past. The retrieved data is combined and processed to obtain the first training data {(g1,G1), (g2,G2), ... (g m G m )}, thus obtaining the second training data {(h1,H1), (h2,H2), ... (h n H n After fitting the first training data with a straight line, a volume increase control model for a random user is established: y = θ1*x + θ2, where θ1 and θ2 represent the fitting coefficients of the volume increase control model, * represents the multiplication sign, x represents the independent variable representing the initial volume before increase, and y represents the dependent variable representing the increased volume. After fitting the second training data with a straight line, a volume decrease control model for a random user is established: Y = α1*X + α2, where α1 and α2 represent the fitting coefficients of the volume decrease control model, X represents the independent variable representing the initial volume before decrease, and Y represents the dependent variable representing the decreased volume. Volume increase and volume decrease control models are established for all users in the same way.

[0032] By collecting historical data on how different users control and adjust smart TVs when using the multi-screen interaction function, and analyzing the volume values ​​that meet the needs of different users when adjusting the initial volume, a volume control model is established for different users. Considering that the needs of the same user when increasing and decreasing the volume may be different, separate volume increase control models and volume decrease control models are established for each user. This increases the probability that the smart TV can meet the user's needs after adaptively adjusting the volume according to the model. When users adjust the volume of the smart TV by voice control, they do not need to output specific voice commands. They only need to output the command to increase or decrease the volume, and the system can adaptively adjust the TV volume according to the model. This avoids the need to repeatedly input voice commands until the volume of the playing content is adjusted to the appropriate value, thus improving the convenience of using the multi-screen interaction function.

[0033] Preferably, in step S3: receiving a voice command about volume adjustment output by the current user, recognizing the received voice command, confirming the user corresponding to the voice command, obtaining the level of the corresponding user's control of the smart TV, and detecting that the initial volume of the current TV is L.

[0034] Preferably, in step S4: if the number of users currently outputting voice commands regarding volume adjustment is 1, the first planning method for volume adjustment is generated: if the voice command output by the current user is to increase the volume, the volume increase control model corresponding to the current user is extracted as: y1 = a*x1 + b, where a and b represent the fitting coefficients of the volume increase control model corresponding to the current user, x1 represents the independent variable representing the initial volume before increase in the volume increase control model corresponding to the current user, and y1 represents the dependent variable representing the increased volume in the volume increase control model corresponding to the current user. Let x1 = L, and output the current optimal increase volume value as a*L + b. Increase the volume of the smart TV to L+(a*L+b); If the current user's voice command is to decrease the volume, extract the volume decrease control model corresponding to the current user as: Y1=c*X1+d, where c and d represent the fitting coefficients of the volume decrease control model corresponding to the current user, X1 represents the independent variable representing the initial volume before decreasing in the volume decrease control model corresponding to the current user, and Y1 represents the dependent variable representing the decreased volume in the volume decrease control model corresponding to the current user. Let X1=L, output the current optimal volume decrease value as c*L+d, and control the volume of the smart TV to decrease to L-(c*L+d);

[0035] If the number of users currently outputting voice commands regarding volume adjustment is greater than 1 and all users output the same voice command, the second planning method for volume adjustment is generated: The number of users outputting the same voice command regarding volume adjustment is obtained as k, k>1. If the user's voice command is to increase the volume, L is input into the volume increase control model corresponding to all users, resulting in a set of volume increase values ​​output by the model as {A1, A2, ... A...}. k The set of user levels for k users is retrieved as {P1, P2, ..., P}. k Set the current optimal volume increase value to F, where F = ∑ k i＝1 [(P i / ∑ k i＝1 (P i ))*A i Let i represent the i-th user out of k users, controlling the volume of the smart TV to increase to L+F; if the user's voice command is to decrease the volume, L is input into the volume decrease control model corresponding to all users, resulting in the set of volume decrease values ​​output by the model as {B1, B2, ... B}. k Set the current optimal volume increase value to f, where f = ∑ k i＝1 [(P i / ∑ k i＝1 (P i ))*B i [Control the volume of the smart TV to Lf;]

[0036] When adjusting the volume of a smart TV based on the user's corresponding model, it not only considers the case where only one user outputs a voice command, but also the case where multiple people may simultaneously output the same voice command to adjust the volume. In this case, the optimal adjustment value is set by combining the parameters output by multiple models and the user's level. While the adjustment value is biased towards meeting the needs of the highest-level user, the probability of adjusting the volume to meet the needs of multiple users is increased, further enhancing the convenience of multi-user control of the smart TV.

[0037] Compared with the prior art, the beneficial effects of the present invention are:

[0038] This invention collects historical data on how different users control and adjust smart TVs while using multi-screen interaction functions. It analyzes the volume values ​​adjusted to meet the needs of different users when the initial volume is different, and establishes volume control models for different users. Considering that the needs of the same user when increasing and decreasing the volume may be different, volume increase control models and volume decrease control models are established for users respectively. This increases the probability that the smart TV can meet the user's needs after adaptively adjusting the volume according to the model. When users adjust the volume of the smart TV by voice control, they do not need to output specific voice commands. They only need to output the command to increase or decrease the volume, and the system can adaptively adjust the TV volume according to the model. This avoids the need to repeatedly input voice commands until the volume of the playing content is adjusted to the appropriate value, thus improving the convenience of using multi-screen interaction functions.

[0039] When adjusting the volume of a smart TV based on the user's corresponding model, it not only considers the case where only one user outputs a voice command, but also the case where multiple people may simultaneously output the same voice command to adjust the volume. In this case, the optimal adjustment value is set by combining the parameters output by multiple models and the user's level. While the adjustment value is biased towards meeting the needs of the highest-level user, the probability of adjusting the volume to meet the needs of multiple users is increased, further enhancing the convenience of multi-user control of the smart TV. Attached Figure Description

[0040] Figure 1 This is a schematic diagram of the structure of a multi-screen interactive processing system based on a smart TV according to the present invention;

[0041] Figure 2 This is a flowchart illustrating a multi-screen interaction processing method based on a smart TV according to the present invention. Detailed Implementation

[0042] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0043] Example 1:

[0044] like Figure 1As shown, this embodiment provides a multi-screen interaction processing system based on a smart TV. The system includes: a data acquisition module, a control model creation module, a multi-screen interaction data monitoring module, and a multi-screen interaction dynamic processing module. The data acquisition module collects voice data output by users during previous multi-screen interactions and historical volume control data of the smart TV. The control model creation module establishes a volume adjustment control model for each user who has controlled the same smart TV. The multi-screen interaction data monitoring module monitors the voice data output by the current user and the parameter data of the current TV during multi-screen interaction. The multi-screen interaction dynamic processing module generates adjustment planning methods for the smart TV under different multi-screen interaction scenarios based on the volume adjustment control models, and adjusts the parameters according to the planning methods.

[0045] The data acquisition module includes a voice information acquisition unit, a database generation unit, and a historical control data acquisition unit. The voice information acquisition unit is used to collect the voice data of users who have previously controlled the smart TV via voice during multi-screen interaction. The voice data is collected after the user grants the necessary permissions. The database generation unit is used to store the collected voice data of each user and generate a voice database. It sets the control level of all users on the smart TV, with the level set by the system default. The voice database contains the user's control level data and the corresponding user's voice data. The historical control data acquisition unit is used to collect the voice commands received by the smart TV when different users previously controlled the volume of the smart TV via voice. It extracts control data from the voice commands, including volume increase and decrease data. The historical control data acquisition unit is also used to collect the initial volume data of the TV before adjusting the volume.

[0046] The control model creation module includes a historical data training unit and an adjustment control model establishment unit. The historical data training unit is used to combine the control data corresponding to each user and the initial volume data of the TV before adjusting the volume, and to perform fitting training on the combined data. The adjustment control model establishment unit is used to establish a volume adjustment control model for each user on the smart TV based on the fitted training data. The volume adjustment control model includes a volume increase control model and a volume decrease control model.

[0047] The multi-screen interactive data monitoring module includes a voice data receiving unit, an identity and command recognition unit, and a monitoring data output unit. The voice data receiving unit is used to receive voice commands about volume adjustment output by the current user. The identity and command recognition unit is used to identify the received voice commands: it matches the voice commands with the voice commands in the voice database to confirm the user corresponding to the voice command and obtain the level of control of the smart TV by the corresponding user. The monitoring data output unit is used to monitor the initial volume data of the current TV.

[0048] The multi-screen interactive dynamic processing module includes a first planning method generation unit, a second planning method generation unit, and an adaptive adjustment unit. The first planning method generation unit generates a first volume adjustment planning method when the number of users currently outputting voice commands is 1: if the user's voice command is to increase the volume, the initial volume of the current TV is input into the volume increase control model corresponding to the current user, and the current optimal increase volume value is output; if the user's voice command is to decrease the volume, the initial volume of the current TV is input into the volume decrease control model corresponding to the current user, and the current optimal decrease volume value is output. The second planning method generation unit is used when the number of users currently outputting voice commands is greater than 1 and all users output the same voice command (i.e., all users output the voice command "increase volume" or...). All users output the voice command "lower volume," generating a second volume adjustment plan: if the user's voice command is to increase the volume, the initial volume of the current TV is input into the volume increase control model corresponding to all users, and the current optimal increase volume value is set according to the volume value output by each model; if the user's voice command is to decrease the volume, the initial volume of the current TV is input into the volume decrease control model corresponding to all users, and the current optimal decrease volume value is set according to the volume value output by each model; the adaptive adjustment unit is used to adjust the volume of the smart TV according to the first plan when the number of users currently outputting voice commands is 1; when the number of users currently outputting voice commands is greater than 1 and all users output the same voice command, the volume of the smart TV is adjusted according to the second plan.

[0049] Example 2:

[0050] like Figure 2 As shown, this embodiment provides a multi-screen interaction processing method based on a smart TV, which is implemented based on the multi-screen interaction processing system in this embodiment, and specifically includes the following steps:

[0051] S1: Collect voice data output by users during previous multi-screen interactions and historical volume control data of the smart TV: Collect the voices of users who have previously controlled the smart TV via voice during multi-screen interactions, store the collected voice data of each user and generate a voice database, set the control level of all users to {1, 2, ... N}, where N represents the number of users who have controlled the smart TV via voice, and when the TV recognizes the voice of more than one user, the voice command of the user with the highest level is executed first. For example, if the voices of users with levels 1, 2 and 3 are recognized at the same time, the voice command of the user with level 3 is executed first. Collect the voice commands received by the smart TV when different users previously controlled the volume of the smart TV via voice, extract control data from the voice commands, and the control data includes the volume increase and decrease data. Collect the initial volume data of the TV before adjusting the volume in the past.

[0052] S2: Establish a volume adjustment control model for each user who has controlled the same smart TV: retrieve the set of volume increases made by a random user in previous TV control actions, denoted as {G1, G2, ... G...} m The initial volume set of the TV before the volume is increased is {g1, g2, ... g}. m Let m represent the number of times a random user has previously increased the TV volume, and the set of numbers corresponding to the number of times the user has previously decreased the TV volume is {H1, H2, ... H}. n The initial volume set of the TV before the volume is reduced is {h1, h2, ... h}. n}, where n represents the number of times a random user has lowered the TV volume in the past. The retrieved data is combined and processed to obtain the first training data {(g1,G1), (g2,G2), ... (g m G m )}, thus obtaining the second training data {(h1,H1), (h2,H2), ... (h n H nAfter fitting the first training data with a straight line, a volume increase control model for a random user is established: y = θ1*x + θ2, where θ1 and θ2 represent the fitting coefficients of the volume increase control model, * represents the multiplication sign, x represents the independent variable representing the initial volume before increase, and y represents the dependent variable representing the increase in volume. After fitting the second training data with a straight line, a volume decrease control model for a random user is established: Y = α1*X + α2, where α1 and α2 represent the fitting coefficients of the volume decrease control model, X represents the independent variable representing the initial volume before decrease, and Y represents the dependent variable representing the decrease in volume. Volume increase control models and volume decrease control models are established for all users in the same way, with each user having one volume increase control model and one volume decrease control model.

[0053] S3: When the current user interacts with the smart TV in a multi-screen manner, monitor the voice data output by the current user and the parameter data of the current TV: receive the voice command output by the current user about volume adjustment, identify the received voice command, confirm the user corresponding to the voice command, obtain the level of the corresponding user controlling the smart TV, and detect that the initial volume of the current TV is L.

[0054] S4: Generate smart TV adjustment planning methods for different multi-screen interaction scenarios based on the volume adjustment control model, and adjust the parameters of the smart TV according to the planning method: If the number of users currently outputting voice commands about volume adjustment is 1, generate the first planning method for volume adjustment: If the current user's voice command is to increase the volume, extract the volume increase control model corresponding to the current user as: y1=a*x1+b, where a and b represent the fitting coefficients of the volume increase control model corresponding to the current user, x1 represents the independent variable representing the initial volume before increase in the volume increase control model corresponding to the current user, and y1 represents the dependent variable representing the increased volume in the volume increase control model corresponding to the current user. Let x1 = L, output the current optimal volume increase value as a*L+b, and control the smart TV volume to increase to L+(a*L+b); if the current user's voice command is to decrease the volume, extract the volume decrease control model corresponding to the current user as: Y1 = c*X1+d, where c and d represent the fitting coefficients of the volume decrease control model corresponding to the current user, X1 represents the independent variable representing the initial volume before decreasing in the volume decrease control model corresponding to the current user, and Y1 represents the dependent variable representing the decreased volume in the volume decrease control model corresponding to the current user. Let X1 = L, output the current optimal volume decrease value as c*L+d, and control the smart TV volume to decrease to L-(c*L+d);

[0055] If the number of users currently outputting voice commands regarding volume adjustment is greater than 1 and all users output the same voice command, the second planning method for volume adjustment is generated: The number of users outputting the same voice command regarding volume adjustment is obtained as k, k>1. If the user's voice command is to increase the volume, L is input into the volume increase control model corresponding to all users, resulting in a set of volume increase values ​​output by the model as {A1, A2, ... A...}. k The set of user levels for k users is retrieved as {P1, P2, ..., P}. k Set the current optimal volume increase value to F, where F = ∑ k i＝1 [(P i / ∑ k i＝1 (P i ))*A i Let i represent the i-th user out of k users, controlling the volume of the smart TV to increase to L+F. If F is not an integer, F is rounded. If the user's voice command is to decrease the volume, L is input into the volume decrease control model corresponding to all users, resulting in a set of volume decrease values ​​output by the model: {B1, B2, ... B}. k Set the current optimal volume increase value to f, where f = ∑ k i＝1 [(P i / ∑ k i＝1 (P i ))*B i [This command] controls the volume of the smart TV to decrease to Lf. If f is not an integer, it rounds f.

[0056] For example: If it is detected that 3 users are currently outputting voice commands regarding volume adjustment, and all users are outputting the same voice command, the second programming method is used to adjust the volume of the smart TV. The initial volume of the TV is detected to be L = 15. The voice command output by the 3 users is "increase volume." The value 15 is input into the volume increase control model corresponding to each of the 3 users. The independent variable in each model is set to 15, resulting in the set of volume increase values ​​output by each model as {A1, A2, A3} = {5, 7, 8}. The set of levels for the 3 users is retrieved as {P1, P2, P3} = {1, 2, 5}. The optimal volume increase value is set to F, where F = ∑ k i＝1 [(P i / ∑ k i＝1 (P i ))*A i ]≈7, which controls the volume of the smart TV to 22.

[0057] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A multi-screen interaction processing system based on a smart TV, characterized in that: The system comprises a data collection module, a control model creation module, a multi-screen interaction data monitoring module and a multi-screen interaction dynamic processing module; The data collection module collects voice data output by users in the past when multi-screen interaction was performed and historical volume control data for the smart TV; The control model creation module establishes a volume adjustment control model for each user who controls the same smart TV; The multi-screen interaction data monitoring module monitors voice data output by the current user and parameter data of the current TV when the current user performs multi-screen interaction with the smart TV; The multi-screen interaction dynamic processing module generates a smart TV adjustment planning mode in different multi-screen interaction scenarios according to the volume adjustment control model and adjusts parameters according to the planning mode; The multi-screen interaction dynamic processing module comprises a first planning mode generation unit, a second planning mode generation unit and an adaptive adjustment unit; The first planning mode generation unit generates a first planning mode for volume adjustment when the number of users outputting voice instructions is 1: if the voice instruction output by the user is to increase the volume, the initial volume of the current TV is input into the volume increase control model corresponding to the current user to output the current best increase volume value; if the voice instruction output by the user is to decrease the volume, the initial volume of the current TV is input into the volume decrease control model corresponding to the current user to output the current best decrease volume value; The second planning mode generation unit generates a second planning mode for volume adjustment when the number of users outputting voice instructions is greater than 1 and all users output the same voice instruction: if the voice instruction output by the user is to increase the volume, the initial volume of the current TV is input into the volume increase control model corresponding to all users to set the current best increase volume value according to the volume value output by each model; if the voice instruction output by the user is to decrease the volume, the initial volume of the current TV is input into the volume decrease control model corresponding to all users to set the current best decrease volume value according to the volume value output by each model; The adaptive adjustment unit adjusts the volume of the smart TV according to the first planning mode when the number of users outputting voice instructions is 1 and adjusts the volume of the smart TV according to the second planning mode when the number of users outputting voice instructions is greater than 1 and all users output the same voice instruction.

2. The multi-screen interaction processing system based on the intelligent TV set according to claim 1, characterized in that: The data collection module comprises a voice information collection unit, a database generation unit and a historical control data collection unit; The voice information collection unit collects the voice of users who control the smart TV through voice in the past when multi-screen interaction is performed; The database generation unit stores the voice data of each user collected and generates a voice database, sets the level of all users controlling the smart TV, and the voice database contains the control level data of the user and the voice data of the corresponding user; The historical control data collection unit is configured to collect voice instructions received by the smart television when different users control the volume of the smart television in the past, extract control data from the voice instructions, and the control data includes raised volume data and lowered volume data. The historical control data collection unit is further configured to collect initial volume data of the television before the volume is adjusted.

3. The multi-screen interaction processing system based on the intelligent TV set according to claim 2, characterized in that: The control model creation module includes a historical data training unit and an adjustment control model establishment unit. The historical data training unit is configured to combine the control data corresponding to each user and the initial volume data of the television before the volume is adjusted, and perform fitting training on the combined data. The adjustment control model establishment unit is configured to establish a volume adjustment control model for each user based on the fitting trained data, and the volume adjustment control model includes a volume raising control model and a volume lowering control model.

4. The multi-screen interaction processing system based on the intelligent TV set according to claim 3, characterized in that: The multi-screen interaction data monitoring module includes a voice data receiving unit, an identity and instruction recognition unit, and a monitoring data output unit. The voice data receiving unit is configured to receive voice instructions about volume adjustment output by the current user. The identity and instruction recognition unit is configured to recognize the received voice instructions: perform voice signal feature matching on the voice instructions and voice instructions in a voice database, confirm the user corresponding to the voice instructions, and obtain the level at which the corresponding user controls the smart television. The monitoring data output unit is configured to monitor initial volume data of the current television.

5. A method for multi-screen interaction based on an intelligent TV, characterized in that: The method includes the following steps: S1: Collect voice data output by the user when multi-screen interaction is performed in the past and historical volume control data of the smart television; S2: Establish a volume adjustment control model for each user who controls the same smart television; S3: Monitor voice data output by the current user and parameter data of the current television when the current user performs multi-screen interaction with the smart television; S4: Generate a smart television adjustment planning mode in different multi-screen interaction scenarios based on the volume adjustment control model, and adjust the parameters of the smart television based on the planning mode; In step S4: if the number of users outputting voice instructions about volume adjustment is 1, a first planning mode for volume adjustment is generated: if the voice instruction output by the current user is to raise the volume, the volume raising control model corresponding to the current user is extracted as y1=a*x1+b, a and b represent the fitting coefficients of the volume raising control model corresponding to the current user, x1=L, and the current best raised volume value a*L+b is output, and the volume of the smart television is raised to L+(a*L+b); if the voice instruction output by the current user is to lower the volume, the volume lowering control model corresponding to the current user is extracted as y1=c*x1+d, c and d represent the fitting coefficients of the volume lowering control model corresponding to the current user, x1=L, and the current best lowered volume value c*L+d is output, and the volume of the smart television is lowered to L-(c*L+d). If the number of users outputting voice instructions about volume adjustment is greater than 1 and all users output the same voice instruction, a second planning mode of volume adjustment is generated: the number of users outputting the same voice instruction about volume adjustment is k, k>1, if the voice instruction output by the user is to increase the volume, L is input into the volume increase control model corresponding to all users to obtain a set of volume increase values output by the model, which is {A1, A2,...A k}, the set of levels of the k users is {P1, P2,...P k}, the current best volume increase value is set as F, F=∑ k i=1 [(P i / ∑ k i=1 (P i ))*A i ], i represents the i-th user in the k users, and the volume of the smart TV is controlled to increase to L+F; If the voice instruction output by the user is to reduce the volume, input L to the volume reduction control model corresponding to all users to obtain a set of volume reduction values output by the model as {B1, B2,...B k}, and set the current optimal volume increase value as f, f=∑ k i=1 [(P i / ∑ k i=1 (P i ))*B i}, and control the volume of the smart television to reduce to L-f.

6. The multi-screen interaction processing method based on the intelligent TV set according to claim 5, characterized in that: In step S1: collect the past in the process of multi-screen interaction, through the voice of the user who controls the smart TV by voice, the collected voice data of each user is stored and a voice database is generated, the level of all users controlling the smart TV is set as {1, 2,..., N}, N represents the number of users who control the smart TV by voice, when the TV recognizes more than one user's voice, the voice instruction of the user with the highest level is executed preferentially, the voice instruction received by the smart TV when the different users control the volume of the smart TV in the past is collected, the control data including the increased volume and the decreased volume data is extracted from the voice instruction, the initial volume data of the TV before adjusting the volume is collected.

7. The multi-screen interaction processing method based on the intelligent TV set according to claim 6, characterized in that: In step S2: retrieve the set of volume levels that a random user has previously increased when controlling the TV, denoted as {G1, G2, ... G...}. m The initial volume set of the TV before the volume is increased is {g1, g2, ... g}. m Let m represent the number of times a random user has previously increased the TV volume, and the set of numbers corresponding to the number of times the user has previously decreased the TV volume is {H1, H2, ... H}. n The initial volume set of the TV before the volume is reduced is {h1, h2, ... h}. n }, where n represents the number of times a random user has lowered the TV volume in the past. The retrieved data is combined and processed to obtain the first training data {(g1, G1), (g2, G2), ... (g... m G m )}, thus obtaining the second training data {(h1,H1), (h2,H2), ... (h n H n After fitting the first training data with a straight line, a volume increase control model for a random user is established: y = θ1*x + θ2, where θ1 and θ2 represent the fitting coefficients of the volume increase control model, x represents the independent variable representing the initial volume before increase, and y represents the dependent variable representing the increased volume. After fitting the second training data with a straight line, a volume decrease control model for a random user is established: Y = α1*X + α2, where α1 and α2 represent the fitting coefficients of the volume decrease control model, X represents the independent variable representing the initial volume before decrease, and y represents the dependent variable representing the decreased volume. Volume increase and volume decrease control models are established for all users in the same way.

8. The multi-screen interaction processing method based on the intelligent TV set according to claim 7, characterized in that: In step S3: receive the voice instruction about volume adjustment output by the current user, identify the received voice instruction, confirm the user corresponding to the voice instruction, obtain the level of the corresponding user controlling the smart TV, and monitor that the initial volume of the current TV is L.

Images