Indoor space reverberation time intelligent control system

Abstract

The invention discloses an intelligent control system for indoor space reverberation time, which relates to the field of intelligent reverberation time control and comprises a data acquisition module, a film module, a material module, an environment module and a control module. According to the method, the language voice characteristics, the language complexity, the macro and spectacular picture, the background music complexity and the background music motion of the movie played in each time period are judged and analyzed to obtain the sound motion value of the background music in each time period, the background music and the sound complexity of the movie in each time period, and the sound motion value, the background music and the sound complexity of the movie in each time period are analyzed with the beat speed of the background music of the movie in each time period; the method comprises the following steps: obtaining a film language drawing sound reverberation demand value in each time period, analyzing material characteristics, suspension conditions and surface characteristics of a sound absorption curtain material to obtain a sound absorption level value of the sound absorption curtain, judging a sound absorption area demand value of the sound absorption curtain in each time period, and adjusting the sound absorption area of the electric sound absorption curtain in real time, so that proper reverberation time can be adjusted in real time. And the film watching experience is greatly improved.

Description

Technical Field

[0001] The invention relates to the field of intelligent control of reverberation time, and in particular to an intelligent control system for indoor space reverberation time. Background Art

[0002] With the continuous improvement of living standards, people's pursuit of spiritual level is getting higher and higher. Movies are an important way for people to improve their spiritual pursuit during their rest time. Of course, ensuring a good movie sound experience is more conducive to improving the pursuit of spiritual level. Therefore, it is more important to accurately control the appropriate reverberation time in different time periods. The traditional indoor space reverberation time control is too dependent on manual work and it is difficult to meet people's needs. Therefore, the indoor space reverberation time intelligent control system came into being.

[0003] When the existing intelligent control system of indoor space reverberation time is in operation, it is unable to analyze the style characteristics of movies in different playing periods, cannot accurately determine the reverberation demand values ​​of movies in different playing periods, cannot accurately analyze the material characteristics of electric sound-absorbing curtain materials and the different environments of cinemas, and cannot adjust the appropriate reverberation time in real time, which greatly reduces the viewing experience.

[0004] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0005] In order to solve the technical problems raised by the above background technology, the present invention is proposed. An embodiment of the present invention provides an intelligent control system for indoor space reverberation time.

[0006] The purpose of the present invention can be achieved through the following technical solutions: an intelligent control system for indoor space reverberation time, including a data acquisition module, a movie module, a material module, an environment module, and a control module.

[0007] The data acquisition module is used to collect movie information, material information, and environmental information, and send them to the movie module, material module, and environmental module respectively; The movie module is used to receive movie information and make judgments and analyses on the language and speech features, language complexity, grandeur of the pictures, complexity of the background music, and dynamics of the background music played in each period of the movie, so as to obtain the required value of the language, picture and sound reverberation of the movie in each period; The material module is used to receive the sound-absorbing curtain material information and analyze the material properties, suspension conditions, and surface properties of the sound-absorbing curtain material to obtain the sound absorption level value of the sound-absorbing curtain; The environment module is used to receive environment information and analyze the human body size ratio, wall material, and seat material in the cinema environment to obtain the required reverberation value of the cinema environment at each time period; The control module is used to receive the required value of movie voice and image reverberation in each time period, the sound absorption level value of the sound absorption curtain, and the required value of the movie theater environment reverberation in each time period, judge the required value of the sound absorption area of ​​the sound absorption curtain in each time period, and adjust the sound absorption area of ​​the electric sound absorption curtain in real time.

[0008] Furthermore, the steps for analyzing the required values ​​of the movie speech, picture and sound reverberation in each time period are as follows: The volume and dynamic range of the movie background music in each time period are obtained and added to obtain the sound dynamic value of the background music in each time period; the number of tracks of the movie background music in each time period and the part markings on the music score are calculated through music production software to obtain the number of parts; the chord conversion time points of the movie background music in each time period are obtained through music analysis software, the number of harmonic changes in a unit time is calculated, and marked as the harmonic change frequency; the chord type and the number of modulations of the movie background music in each time period are obtained, and added with the number of parts and the harmonic change frequency to obtain the harmonic complexity of the movie background music in each time period; the beat speed of the movie background music in each time period is obtained, and the sound dynamic value of the background music in each time period and the harmonic complexity of the movie background music in each time period are marked as yjs, ydz and sfd respectively, normalized, and substituted into the set formula , calculate to obtain the required reverberation value BYZ of the movie background music in each period, g1, g2, g3, g4, g5 and g6 are all set weight factor coefficients, and g1>g4, g2>g5, g3>g6; The required film language reverberation value at each time period, the grandeur and magnificence of the picture at each time period, and the required film background music reverberation value at each time period are normalized, weighted calculated, and multiplied by the corresponding correction factor coefficient to obtain the required film language, picture and sound reverberation value DHX at each time period.

[0009] Furthermore, the steps for analyzing the grandeur and magnificence value of the pictures in each time period are as follows: Identify the object category of the movie screen in each period, match it with the object category and corresponding size in the database, obtain the object size cc of the movie screen, obtain the pixels xs occupied by the object in the movie screen, the total pixel value zx of the movie screen, substitute it into the set formula sy=ψ×cc / xs×zx, and obtain the field of view sy of the screen in each period, where ψ is the set correction factor coefficient; The scene depth, scene element value, and color brightness value of each time period are marked as cs, ys, and mx, respectively, and normalized with the field of view sy of each time period, and substituted into the set formula In the model, calculations are performed to obtain the grand and spectacular value Hdz of the picture in each time period, where tg1, tg2, tg3 and tg4 are all set influencing factor coefficients.

[0010] Furthermore, the scene depth of the picture in each time period, the scene element value of the picture in each time period, and the color brightness value of the picture in each time period are analyzed as follows: The movie screens of each time period are converted into grayscale images. A straight line from the foreground to the background is selected as the analysis path in the screen. A point is taken at a certain distance along the analysis path, and the grayscale difference between two adjacent points is calculated and averaged to obtain the scene depth of the screen of each time period. The movie screens of each time period are converted into a two-dimensional pixel matrix, and the spatial position feature vector, texture feature vector and color feature vector of the pixel are extracted. The K-Means clustering algorithm is used to select K cluster centers, and then the Euclidean distance between the spatial position, texture and color feature vectors of each pixel and the cluster center is calculated. Each pixel is assigned to the cluster where the nearest cluster center is located, and then the new cluster center position is recalculated according to the feature vector of the pixel in the cluster. The process of assigning pixels is repeated until the set number of iterations is reached and the sum of the number of pixels in each cluster is counted and marked as the scene element value of the screen of each time period. The color saturation, color brightness and light and shadow contrast of the movie screen of each time period are obtained, and the color brightness and shadow value of the screen of each time period is obtained by summing them. The light and shadow contrast refers to the brightness difference between the maximum brightness and the minimum brightness in the screen.

[0011] Furthermore, the steps of analyzing the required values ​​of movie language reverberation in each time period are as follows: The movie playing is divided into several time periods, and the phoneme accuracy and tone accuracy of the language in each time period of the movie playing are obtained and summed up to obtain the speech feature value of the movie language in each time period, wherein the phoneme accuracy and tone accuracy of the language are calculated through the speech recognition system and alignment tools; the grammatical structure difference degree and the proportion of dialect vocabulary of the language in each time period of the movie playing are obtained, and the sum is obtained to obtain the word difference value of the movie language in each time period, wherein the grammatical structure difference degree of the language is to match the movie lines with the grammatical rule template in each time period of the movie playing, and the proportion of sentences that do not conform to the template in the total number of sentences is counted and marked as the grammatical structure difference degree of the language; The speech feature values, word difference values, rhyme speed values, and timbre, harmonic and jitter values ​​of the film language in each period are normalized. The speech feature values ​​of the film language in each period are taken as the radius of a sphere, and the center of the sphere is taken as the center point of the cuboid. A cuboid is constructed inside the sphere. The word difference values ​​of the film language in each period are taken as the length of the bottom of the cuboid, the rhyme speed values ​​of the film language in each period are taken as the width of the bottom of the cuboid, and the timbre, harmonic and jitter values ​​of the film language in each period are taken as the height of the cuboid. The non-overlapping volumes formed by the sphere and the cuboid are identified and marked as the required reverberation values ​​of the film language in each period.

[0012] Furthermore, the steps for analyzing the rhyme speed value and the timbre, harmonic and jitter value of the film language in each time period are as follows: The speech rate, rhythm rate, and rhythm complexity of the language in each period of the movie are obtained, and added to obtain the speech and rhythm complexity of the movie language in each period. The language audio in each period of the movie is converted into a waveform and a spectrum diagram. The rhythm rate of the language is obtained by adding the number of peaks, the change value of the spectrum bandwidth, the movement speed of the spectrum center of gravity, and the spectrum flux. The rhythm complexity of the language is obtained by adding the pitch contour richness value, the rhythm pattern duration change rate, and the syllable intensity standard deviation. The spectrum flux refers to the difference value of the spectrum between adjacent time frames, the pitch contour richness value refers to the average change of the pitch in a unit time, and the rhythm pattern duration is the movie language based on personal expression. The speaking speed and pauses are adjusted according to the content and emotion to form a certain rhythm pattern duration; the harmonic peak factor, audio frequency jitter rate and amplitude flicker rate of the language in each period of the movie playback are obtained and added to obtain the timbre harmonic jitter value of the movie language in each period. The harmonic peak factor is the ratio of the peak value of the harmonic component in the speech signal to the fundamental peak value, the audio frequency jitter rate is the ratio of the average value of the absolute value of the difference between adjacent fundamental periods to the average fundamental period, and the amplitude flicker rate is the ratio of the average value of the absolute value of the difference between adjacent amplitude peaks to the average amplitude. The fundamental tone is the sound with the lowest frequency and the largest amplitude in the composite tone, and the fundamental wave is the sine wave component with the lowest frequency in a periodic composite wave.

[0013] Furthermore, the steps of analyzing the sound absorption area of ​​the electric sound absorption curtain in real time are as follows: Normalize the required value DHX of the movie voice and picture reverberation at each time period, the sound absorption level value XJZ of the sound absorption curtain, and the required value HHZ of the movie theater environment reverberation at each time period, and obtain the required value ZHZ of the sound absorption area of ​​the sound absorption curtain at each time period according to the set formula ZHZ=β / (x1×DHX+x2×XJZ+x3×HHZ), where β is the set correction factor coefficient, and x1, x2 and x3 are all preset weight factor coefficients; The sound absorption area of ​​the electric sound absorption curtain is obtained in real time. If the sound absorption area of ​​the electric sound absorption curtain is less than the required sound absorption area of ​​the sound absorption curtain in each time period, the sound absorption area of ​​the sound absorption curtain is increased and the increased value is equal to the required sound absorption area of ​​the sound absorption curtain in each time period; if the sound absorption area of ​​the electric sound absorption curtain is equal to the required sound absorption area of ​​the sound absorption curtain in each time period, no adjustment is made; if the sound absorption area of ​​the electric sound absorption curtain is greater than the required sound absorption area of ​​the sound absorption curtain in each time period, the sound absorption area of ​​the sound absorption curtain is reduced and the reduced value is equal to the required sound absorption area of ​​the sound absorption curtain in each time period.

[0014] Furthermore, the sound absorption level value analysis steps of the sound absorption curtain are as follows: The material characteristic value of the electric sound-absorbing curtain, the suspension deviation value of the sound-absorbing curtain, the surface value of the sound-absorbing curtain knot, and the thickness of the sound-absorbing curtain are obtained from the material information of the electric sound-absorbing curtain, and are marked as xlt, xtz, xjb, and xhd, respectively. After normalization, the sound absorption level value XJZ of the sound-absorbing curtain is calculated according to the set formula XJZ=(t1×xlt+t3×xjb+t4×xhd) / (t2×xtz), where t1, t2, t3, and t4 are all set influencing factor coefficients.

[0015] Furthermore, the steps for analyzing the deflection of the suspended state of the sound-absorbing curtain are as follows: Through acoustic simulation software, modeling is carried out according to the size and shape of the cinema space, the hanging height, angle and size of the sound-absorbing curtain are set in the model, and the location information of the cinema sound-emitting device is set in the model. The receiving points are set in the model according to the seats of the cinema auditorium, and the sound absorption coefficient, sound pressure level and reverberation time of each receiving point are calculated. The sound wave frequency of the sound-emitting device is adjusted, and the sound absorption coefficient, sound pressure level and reverberation time of each receiving point at different sound wave frequencies are calculated. The standard deviation of the sound absorption coefficient, the standard deviation of the sound pressure level and the standard deviation of the reverberation time of each receiving point at different sound wave frequencies are solved, and the sum is calculated to obtain the deviation of the suspended state of the sound-absorbing curtain.

[0016] Furthermore, the steps for analyzing the reverberation demand value of the cinema environment in each time period are as follows: The human body size ratio, wall material reflection coefficient, and seat material absorption value of each time period in the cinema environment information are obtained, marked as lyz, qfx, and zyc respectively, and normalized. According to the set formula HHZ=h2×qfx / (h1×lyz+h3×zyc), calculation is performed to obtain the required reverberation value HHZ of the cinema environment in each time period, where h1, h2, and h3 are preset proportional factor coefficients.

[0017] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention determines and analyzes the language and speech features, language complexity, grandeur of the picture, complexity of the background music, and the sound movement of the background music of the movie in each time period to obtain the sound movement value of the background music in each time period and the harmony complexity of the movie background music in each time period, and analyzes it with the beat speed of the movie background music in each time period to obtain the required reverberation value of the movie language, picture and sound in each time period, analyzes the material properties, hanging conditions, and surface properties of the sound-absorbing curtain material to obtain the sound absorption level value of the sound-absorbing curtain, analyzes the human body size ratio, wall materials, and seat materials in the cinema environment to obtain the required reverberation value of the cinema environment in each time period, can analyze the style characteristics of movies in different playing time periods, can accurately determine the reverberation demand value of movies in different playing time periods, and can accurately analyze the material properties of the electric sound-absorbing curtain material and different cinema environments.

[0018] 2. The present invention determines the required value of the sound absorption area of ​​the sound absorption curtain in each time period, and adjusts the sound absorption area of ​​the electric sound absorption curtain in real time, and can adjust the appropriate reverberation time in real time, which greatly improves the viewing experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. The following drawings are not intentionally scaled according to the actual sizes, and the focus is on illustrating the main purpose of the present invention.

[0020] Figure 1 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work also fall within the scope of protection of the present invention.

[0022] like Figure 1 As shown, an intelligent control system for indoor space reverberation time includes a data acquisition module, a movie module, a material module, an environment module, and a control module.

[0023] The data acquisition module is used to collect movie information, material information, and environmental information, and send them to the movie module, material module, and environmental module respectively; The movie module is used to receive movie information and make judgments and analyses on the language and speech features, language complexity, grandeur of the pictures, complexity of the background music, and the dynamics of the background music played in each period of the movie, so as to obtain the required values ​​of the language, picture and sound reverberation of the movie in each period. The specific analysis is as follows: The movie playing is divided into several time periods, and the phoneme accuracy and tone accuracy of the language in each time period of the movie playing are obtained and summed up to obtain the speech feature value of the movie language in each time period, wherein the phoneme accuracy and tone accuracy of the language are calculated through the speech recognition system and alignment tools; the grammatical structure difference and dialect vocabulary proportion of the language in each time period of the movie playing are obtained, and summed up to obtain the word difference value of the movie language in each time period, wherein the grammatical structure difference of the language is to match the movie lines with the grammatical rule template in each time period of the movie playing, and count the proportion of sentences that do not conform to the template in the total number of sentences, which is marked as the grammatical structure difference of the language, the grammatical rule template is the grammatical rule content in the database, and the dialect vocabulary is stored in the database; the speech speed value, rhythm rate, and rhythmic complexity of the language in each time period of the movie playing are obtained, and the speech speed and rhythmic complexity are added together to obtain the speech speed and rhythmic complexity value of the movie language in each time period, and the language audio in each time period of the movie playing is converted into a waveform and a spectrum diagram, and the peak number, spectrum bandwidth change value, and spectrum weight are obtained by The rhythm rate of the language is obtained by adding the heart rate and the spectrum flux. The rhythm complexity of the language is obtained by adding the pitch contour richness value, the rhythm pattern duration change rate, and the syllable intensity standard deviation. The spectrum flux refers to the difference value of the spectrum between adjacent time frames. The pitch contour richness value refers to the average change of the pitch in a unit time. The rhythm pattern duration is the speed and pauses in the movie language adjusted according to the content and emotions of personal expression to form a certain rhythm pattern duration; the harmonic peak factor, audio frequency jitter rate, and amplitude flicker rate of the language in each period of movie playback are obtained and added to obtain the timbre harmonic jitter value of the movie language in each period. The harmonic peak factor is the ratio of the peak value of the harmonic component in the speech signal to the fundamental peak value, the audio frequency jitter rate is the ratio of the average value of the absolute value of the difference between adjacent fundamental periods to the average fundamental period, and the amplitude flicker rate is the ratio of the average value of the absolute value of the difference between adjacent amplitude peaks to the average amplitude. The fundamental tone is the sound with the lowest frequency and the largest amplitude in the composite tone, and the fundamental wave is the sine wave component with the lowest frequency in a periodic composite wave; Normalize the speech feature values, word difference values, rhyme speed repetition values, and timbre, harmonic, and jitter values ​​of the film language in each period of time, take the speech feature values ​​of the film language in each period of time as the radius of a sphere, take the center of the sphere as the center point of the cuboid, construct a cuboid inside the sphere, take the word difference values ​​of the film language in each period of time as the bottom length of the cuboid, take the rhyme speed repetition values ​​of the film language in each period of time as the bottom width of the cuboid, take the timbre, harmonic, and jitter values ​​of the film language in each period of time as the height of the cuboid, identify the non-overlapping volume formed by the sphere and the cuboid, and mark it as the required reverberation value of the film language in each period of time; It should be noted that when the speech feature value of the film language is lower, the word difference value of the language is higher, the rhyme speed value of the language is higher, and the timbre and jitter value of the language is higher, the reverberation time setting needs to be lower, and a lower reverberation time is required to ensure a certain level of speech clarity; Identify the object category of the movie screen in each time period, match it with the object category and corresponding size in the database, obtain the object size cc of the movie screen, obtain the pixels xs occupied by the object in the movie screen, the total pixel value zx of the movie screen, substitute it into the set formula sy=ψ×cc / xs×zx, and obtain the field of view sy of the screen in each time period, where ψ is the set correction factor coefficient; convert the movie screen in each time period into a grayscale image, select a straight line from the foreground to the background in the picture as the analysis path, take a point at a certain distance along the analysis path, calculate the grayscale difference between two adjacent points, and average them to obtain the scene depth of the screen in each time period, where a certain distance refers to 5 pixels. The larger the grayscale gradient value, the greater the scene depth, and the more magnificent the movie screen; convert the movie screen in each time period into a grayscale image. Convert to a two-dimensional pixel matrix, extract the spatial position feature vector, texture feature vector, and color feature vector of the pixel, use the K-Means clustering algorithm, select K cluster centers, and then calculate the Euclidean distance between the spatial position, texture, and color feature vectors of each pixel and the cluster center, assign each pixel to the cluster where the nearest cluster center is located, and then recalculate the new cluster center position based on the feature vector of the pixel in the cluster, repeat the process of assigning pixels until the set number of iterations is reached, and count the total number of pixels in each cluster, and mark it as the scene element value of the picture in each time period; obtain the color saturation, color brightness, and light and shadow contrast of the movie picture in each time period, and sum them to obtain the color brightness value of the picture in each time period, where the light and shadow contrast refers to the brightness difference between the maximum brightness and the minimum brightness in the picture; The scene depth, scene element value, and color brightness value of each time period are marked as cs, ys, and mx, respectively, and normalized with the field of view sy of each time period, and substituted into the set formula In the model, calculations are performed to obtain the grand and spectacular value Hdz of the picture in each period, where tg1, tg2, tg3 and tg4 are respectively the setting influence factor coefficients of the scene depth, scene element value, color brightness value and field of view of the picture in each period, which are set by professionals in this field, and are specifically set to 1.1, 2.1, 3.2 and 0.9, respectively. e is a natural constant, and its value is 2.718; The volume and dynamic range of the movie background music in each time period are obtained and added to obtain the sound dynamic value of the background music in each time period; the number of tracks of the movie background music in each time period and the part markings on the music score are calculated through music production software to obtain the number of parts; the chord conversion time points of the movie background music in each time period are obtained through music analysis software, the number of harmonic changes in a unit time is calculated, and marked as the harmonic change frequency; the chord type and the number of modulations of the movie background music in each time period are obtained, and added with the number of parts and the harmonic change frequency to obtain the harmonic complexity of the movie background music in each time period; the beat speed of the movie background music in each time period is obtained, and the sound dynamic value of the background music in each time period and the harmonic complexity of the movie background music in each time period are marked as yjs, ydz and sfd respectively, normalized, and substituted into the set formula , calculate to obtain the required reverberation value BYZ of the movie background music in each period, g1, g2, g3, g4, g5 and g6 are all set weight factor coefficients, and g1>g4, g2>g5, g3>g6. It should be noted that when the beat speed of the movie background music reaches 120BPM or more, it is necessary to consider setting a smaller reverberation time; Normalize the required reverberation value of the movie language at each time period, the grand and spectacular value of the picture at each time period, and the required reverberation value of the movie background music at each time period, perform weighted calculation, and multiply by the corresponding correction factor coefficient to obtain the required reverberation value DHX of the movie language, picture and sound at each time period; The material module is used to receive the sound-absorbing curtain material information and analyze the material properties, suspension conditions, and surface properties of the sound-absorbing curtain material to obtain the sound absorption level value of the sound-absorbing curtain. The specific analysis is as follows: Obtain the sound-absorbing curtain material characteristic value, sound-absorbing curtain installation and suspension state deviation value, sound-absorbing curtain knot surface value, and sound-absorbing curtain thickness in the electric sound-absorbing curtain material information, and mark them as xlt, xtz, xjb, and xhd, respectively, and perform normalization processing. According to the set formula XJZ=(t1×xlt+t3×xjb+t4×xhd) / (t2×xtz), calculate to obtain the sound absorption level value XJZ of the sound-absorbing curtain, where t1, t2, t3, and t4 are the set influencing factor coefficients of the sound-absorbing curtain material characteristic value, sound-absorbing curtain installation and suspension state deviation value, sound-absorbing curtain knot surface value, and sound-absorbing curtain thickness, respectively, and the specific values ​​are determined by personnel in this professional field; It should be noted that the material characteristic value of the sound-absorbing curtain refers to the sum of the sound absorption coefficient, density and suitable flow resistance of the sound-absorbing curtain, the suitable flow resistance value is the reciprocal value of the absolute value of the difference between the flow resistance and the set flow resistance threshold, and the flow resistance is the resistance encountered by air when passing through the sound-absorbing curtain; the surface value of the sound-absorbing curtain refers to the sum of the roughness, porosity and air permeability standard values ​​of the curtain surface, and the air permeability standard value is the reciprocal value of the absolute value of the difference between the air permeability and the set air permeability; It should also be noted that the steps for solving the suspended deflection of the sound-absorbing curtain are as follows: Through acoustic simulation software, modeling is performed according to the size and shape of the cinema space, the hanging height, angle and size of the sound-absorbing curtain are set in the model, and the location information of the cinema sound-emitting device is set in the model, and the receiving point is set in the model according to the seat position of the cinema auditorium, and the sound absorption coefficient, sound pressure level and reverberation time of each receiving point are calculated, and the sound wave frequency of the sound-emitting device is adjusted to calculate the sound absorption coefficient, sound pressure level and reverberation time of each receiving point at different sound wave frequencies, and the standard deviation of the sound absorption coefficient, the standard deviation of the sound pressure level and the standard deviation of the reverberation time of each receiving point at different sound wave frequencies are solved, and summed to obtain the deviation of the sound absorption curtain installation suspension state; The environment module is used to receive environmental information and analyze the human body size ratio, wall materials, and seat materials in the cinema environment to obtain the required reverberation value of the cinema environment at each time period. The specific analysis is as follows: Obtain the human body size ratio, wall material reflection coefficient, and seat material absorption value in each time period in the cinema environment information, mark them as lyz, qfx, and zyc respectively, perform normalization processing, and calculate according to the set formula HHZ=h2×qfx / (h1×lyz+h3×zyc) to obtain the required value HHZ of the cinema environment reverberation in each time period. h1, h2, and h3 are the preset proportional factor coefficients of human body size ratio, wall material reflection coefficient, and seat material absorption value respectively, and the specific values ​​are 1.2, 2.1, and 3.1; It should be noted that the human body size ratio refers to the ratio of the elderly and children in the cinema audience. According to the age of the people in the ticket purchase information, those over 60 years old are considered elderly, and those under 12 years old are considered children; the wall material reflection coefficient refers to the reflection coefficient of the cinema wall material; the seat material absorption value refers to the sound absorption coefficient of the seat material; The control module is used to receive the required value of movie voice and picture reverberation at each time period, the sound absorption level value of the sound absorption curtain, and the required value of the movie theater environment reverberation at each time period, judge the required value of the sound absorption area of ​​the sound absorption curtain at each time period, and adjust the sound absorption area of ​​the electric sound absorption curtain in real time. The specific analysis is as follows: Normalize the required value DHX of the movie speech, picture and sound reverberation at each time period, the sound absorption level value XJZ of the sound absorption curtain, and the required value HHZ of the movie theater environment reverberation at each time period, and obtain the required value ZHZ of the sound absorption area of ​​the sound absorption curtain at each time period according to the set formula ZHZ=β / (x1×DHX+x2×XJZ+x3×HHZ), β is the set correction factor coefficient, x1, x2 and x3 are the preset weight factor coefficients of the required value of the movie speech, picture and sound reverberation at each time period, the sound absorption level value of the sound absorption curtain, and the required value of the movie theater environment reverberation at each time period; The sound absorption area of ​​the electric sound absorption curtain is obtained in real time. If the sound absorption area of ​​the electric sound absorption curtain is less than the required sound absorption area of ​​the sound absorption curtain in each time period, the sound absorption area of ​​the sound absorption curtain is increased and the increased value is equal to the required sound absorption area of ​​the sound absorption curtain in each time period; if the sound absorption area of ​​the electric sound absorption curtain is equal to the required sound absorption area of ​​the sound absorption curtain in each time period, no adjustment is made; if the sound absorption area of ​​the electric sound absorption curtain is greater than the required sound absorption area of ​​the sound absorption curtain in each time period, the sound absorption area of ​​the sound absorption curtain is reduced and the reduced value is equal to the required sound absorption area of ​​the sound absorption curtain in each time period; The above is an explanation of the present invention and should not be considered as a limitation thereof. Although several exemplary embodiments of the present invention have been described, it will be readily appreciated by those skilled in the art that many modifications may be made to the exemplary embodiments without departing from the novel teachings and advantages of the present invention. Therefore, all such modifications are intended to be included within the scope of the present invention as defined in the claims. It should be understood that the above is an explanation of the present invention and should not be considered as being limited to the specific embodiments disclosed, and modifications to the disclosed embodiments and other embodiments are intended to be included within the scope of the appended claims. The present invention is defined by the claims and their equivalents.

Claims

1. An intelligent control system for indoor space reverberation time, characterized in that: include: The data collection module is used to collect movie information, material information, and environmental information, and send them to the movie module, material module, and environmental module respectively; The movie module is used to receive movie information and make judgments and analyses on the language and speech features, language complexity, grandeur of the pictures, complexity of the background music, and the dynamics of the background music played in each period of the movie, so as to obtain the required values ​​of the language, picture and sound reverberation of the movie in each period of time; The material module is used to receive the sound-absorbing curtain material information and analyze the material properties, suspension conditions, and surface properties of the sound-absorbing curtain material to obtain the sound absorption level value of the sound-absorbing curtain; The environment module is used to receive environmental information and analyze the human body size ratio, wall materials, and seat materials in the cinema environment to obtain the required reverberation value of the cinema environment at each time period; The control module is used to receive the required value of movie voice and picture reverberation at each time period, the sound absorption level value of the sound absorption curtain, and the required value of the movie theater environment reverberation at each time period, judge the required value of the sound absorption area of ​​the sound absorption curtain at each time period, and adjust the sound absorption area of ​​the electric sound absorption curtain in real time.

2. The intelligent control system for indoor space reverberation time according to claim 1, characterized in that: The steps for analyzing the required values ​​of the movie speech, picture and sound reverberation in each time period are as follows: The volume and dynamic range of the movie background music in each time period are obtained and added to obtain the sound dynamic value of the background music in each time period; the number of tracks of the movie background music in each time period and the part markings on the music score are calculated through music production software to obtain the number of parts; the chord conversion time points of the movie background music in each time period are obtained through music analysis software, the number of harmonic changes in a unit time is calculated, and marked as the harmonic change frequency; the chord type and the number of modulations of the movie background music in each time period are obtained, and added with the number of parts and the harmonic change frequency to obtain the harmonic complexity of the movie background music in each time period; the beat speed of the movie background music in each time period is obtained, and the sound dynamic value of the background music in each time period and the harmonic complexity of the movie background music in each time period are marked as yjs, ydz and sfd respectively, normalized, and substituted into the set formula , calculate to obtain the required reverberation value BYZ of the movie background music in each period, g1, g2, g3, g4, g5 and g6 are all set weight factor coefficients, and g1>g4, g2>g5, g3>g6; The required film language reverberation value at each time period, the grandeur and magnificence of the picture at each time period, and the required film background music reverberation value at each time period are normalized, weighted calculated, and multiplied by the corresponding correction factor coefficient to obtain the required film language, picture and sound reverberation value DHX at each time period.

3. The intelligent control system for indoor space reverberation time according to claim 2, characterized in that: The steps for analyzing the grandeur and spectacular value of the pictures in each time period are as follows: Identify the object category of the movie screen in each period, match it with the object category and corresponding size in the database, obtain the object size cc of the movie screen, obtain the pixels xs occupied by the object in the movie screen, the total pixel value zx of the movie screen, substitute it into the set formula sy=ψ×cc / xs×zx, and obtain the field of view sy of the screen in each period, where ψ is the set correction factor coefficient; The scene depth, scene element value, and color brightness value of each time period are marked as cs, ys, and mx, respectively, and normalized with the field of view sy of each time period, and substituted into the set formula In the model, calculations are performed to obtain the grand and spectacular value Hdz of the picture in each time period, where tg1, tg2, tg3 and tg4 are all set influencing factor coefficients.

4. The intelligent control system for indoor space reverberation time according to claim 3, characterized in that: The steps for analyzing the scene depth, scene element value, and color brightness value of the picture in each time period are as follows: Convert the movie screen of each time period into a grayscale image, select a straight line from the foreground to the background in the screen as the analysis path, take a point at a certain distance along the analysis path, calculate the grayscale difference between two adjacent points, and average them to obtain the scene depth of the screen of each time period; convert the movie screen of each time period into a two-dimensional pixel matrix, extract the spatial position feature vector, texture feature vector, and color feature vector of the pixel, use the K-Means clustering algorithm, select K cluster centers, and then calculate the Euclidean distance between the spatial position, texture, and color feature vector of each pixel and the cluster center, assign each pixel to the cluster with the nearest cluster center, and then recalculate the new cluster center position based on the feature vector of the pixel in the cluster, repeat the process of assigning pixels until the set number of iterations is reached, and count the total number of pixels in each cluster, and mark it as the scene element value of the screen of each time period; The color saturation, color brightness, and light-shadow contrast of the movie screen in each time period are obtained, and the color brightness value of the screen in each time period is obtained by summing them up. The light-shadow contrast refers to the brightness difference between the maximum brightness and the minimum brightness in the screen.

5. The intelligent control system for indoor space reverberation time according to claim 2, characterized in that: The steps for analyzing the required value of movie language reverberation in each time period are as follows: The movie playing is divided into several time periods, and the phoneme accuracy and tone accuracy of the language in each time period of the movie playing are obtained and summed up to obtain the speech feature value of the movie language in each time period, wherein the phoneme accuracy and tone accuracy of the language are calculated through the speech recognition system and alignment tools; the grammatical structure difference degree and the proportion of dialect vocabulary of the language in each time period of the movie playing are obtained, and the sum is obtained to obtain the word difference value of the movie language in each time period, wherein the grammatical structure difference degree of the language is to match the movie lines with the grammatical rule template in each time period of the movie playing, and the proportion of sentences that do not conform to the template in the total number of sentences is counted and marked as the grammatical structure difference degree of the language; The speech feature values, word difference values, rhyme speed values, and timbre, harmonic and jitter values ​​of the film language in each period are normalized. The speech feature values ​​of the film language in each period are taken as the radius of a sphere, and the center of the sphere is taken as the center point of the cuboid. A cuboid is constructed inside the sphere. The word difference values ​​of the film language in each period are taken as the length of the bottom of the cuboid, the rhyme speed values ​​of the film language in each period are taken as the width of the bottom of the cuboid, and the timbre, harmonic and jitter values ​​of the film language in each period are taken as the height of the cuboid. The non-overlapping volumes formed by the sphere and the cuboid are identified and marked as the required reverberation values ​​of the film language in each period.

6. The intelligent control system for indoor space reverberation time according to claim 5, characterized in that: The steps for analyzing the rhyme speed value and the timbre, harmonic and jitter value of the movie language in each time period are as follows: The speech rate, rhythm rate, and rhythm complexity of the language in each period of the movie are obtained, and the speech rate and rhythm complexity of the language in each period of the movie are obtained by adding them up, and the speech rate and rhythm complexity of the language in each period of the movie are obtained by adding the number of peaks, the change value of the spectrum bandwidth, the moving speed of the spectrum center of gravity, and the spectrum flux. The rhythm complexity of the language is obtained by adding the pitch contour richness value, the rhythm pattern duration change rate, and the syllable intensity standard deviation. The spectrum flux refers to the difference value of the spectrum between adjacent time frames, the pitch contour richness value refers to the average change of the pitch in a unit time, and the rhythm pattern duration is to adjust the speech rate and pauses in the movie language according to the content and emotion of personal expression to form a certain rhythm pattern duration; The harmonic peak factor, audio frequency jitter rate and amplitude flicker rate of the language in each period of movie playback are obtained and added to obtain the timbre harmonic jitter value of the movie language in each period. The harmonic peak factor is the ratio of the peak value of the harmonic component in the voice signal to the fundamental peak value, the audio frequency jitter rate is the ratio of the average value of the absolute value of the difference between adjacent fundamental periods to the average fundamental period, and the amplitude flicker rate is the ratio of the average value of the absolute value of the difference between adjacent amplitude peaks to the average amplitude. The fundamental tone is the sound with the lowest frequency and the largest amplitude in the composite tone, and the fundamental wave is the sine wave component with the lowest frequency in a periodic composite wave.

7. The intelligent control system for indoor space reverberation time according to claim 1, characterized in that: The steps for analyzing the sound absorption area of ​​the electric sound absorption curtain in real time are as follows: Normalize the required value DHX of the movie voice and picture reverberation at each time period, the sound absorption level value XJZ of the sound absorption curtain, and the required value HHZ of the movie theater environment reverberation at each time period, and obtain the required value ZHZ of the sound absorption area of ​​the sound absorption curtain at each time period according to the set formula ZHZ=β / (x1×DHX+x2×XJZ+x3×HHZ), where β is the set correction factor coefficient, and x1, x2 and x3 are all preset weight factor coefficients; The sound absorption area of ​​the electric sound absorption curtain is obtained in real time. If the sound absorption area of ​​the electric sound absorption curtain is less than the required sound absorption area of ​​the sound absorption curtain in each time period, the sound absorption area of ​​the sound absorption curtain is increased and the increased value is equal to the required sound absorption area of ​​the sound absorption curtain in each time period; if the sound absorption area of ​​the electric sound absorption curtain is equal to the required sound absorption area of ​​the sound absorption curtain in each time period, no adjustment is made; if the sound absorption area of ​​the electric sound absorption curtain is greater than the required sound absorption area of ​​the sound absorption curtain in each time period, the sound absorption area of ​​the sound absorption curtain is reduced and the reduced value is equal to the required sound absorption area of ​​the sound absorption curtain in each time period.

8. The intelligent control system for indoor space reverberation time according to claim 7, characterized in that: The steps for analyzing the sound absorption level value of the sound absorbing curtain are as follows: The material characteristic value of the electric sound-absorbing curtain, the suspension deviation value of the sound-absorbing curtain, the surface value of the sound-absorbing curtain knot, and the thickness of the sound-absorbing curtain are obtained from the material information of the electric sound-absorbing curtain, and are marked as xlt, xtz, xjb, and xhd, respectively. After normalization, the sound absorption level value XJZ of the sound-absorbing curtain is calculated according to the set formula XJZ=(t1×xlt+t3×xjb+t4×xhd) / (t2×xtz), where t1, t2, t3, and t4 are all set influencing factor coefficients.

9. The intelligent control system for indoor space reverberation time according to claim 8, characterized in that: The steps for analyzing the deflection value of the suspended state of the sound-absorbing curtain are as follows: Through acoustic simulation software, modeling is carried out according to the size and shape of the cinema space, the hanging height, angle and size of the sound-absorbing curtain are set in the model, and the location information of the cinema sound-emitting device is set in the model. The receiving points are set in the model according to the seats of the cinema auditorium, and the sound absorption coefficient, sound pressure level and reverberation time of each receiving point are calculated. The sound wave frequency of the sound-emitting device is adjusted, and the sound absorption coefficient, sound pressure level and reverberation time of each receiving point at different sound wave frequencies are calculated. The standard deviation of the sound absorption coefficient, the standard deviation of the sound pressure level and the standard deviation of the reverberation time of each receiving point at different sound wave frequencies are solved, and the sum is calculated to obtain the deviation of the suspended state of the sound-absorbing curtain.

10. The intelligent control system for indoor space reverberation time according to claim 7, characterized in that: The steps for analyzing the reverberation demand value of the cinema environment in each time period are as follows: The human body size ratio, wall material reflection coefficient, and seat material absorption value of each time period in the cinema environment information are obtained, marked as lyz, qfx, and zyc respectively, and normalized. According to the set formula HHZ=h2×qfx / (h1×lyz+h3×zyc), calculation is performed to obtain the required reverberation value HHZ of the cinema environment in each time period, where h1, h2, and h3 are preset proportional factor coefficients.

Images