A multi-user cloud gathering stereo sound effect processing method and system based on a VR cinema

Abstract

A multi-user cloud gathering stereo sound effect processing method and system based on a VR cinema provided by the present application determines the second monitored data to be identified that has been updated according to the first monitored data to be identified and the second monitored data to be identified, so that the situation where there is a difference between the monitoring data evaluation result of the first monitored data to be identified and the monitoring data evaluation result of the second monitored data to be identified that has been updated is smaller than the monitoring data evaluation result of the first monitored data to be identified and the monitoring data evaluation result of the second monitored data to be identified. The accuracy of the first sound effect comparison data determined according to the first monitored data to be identified and the second monitored data to be identified that has been updated is based on the first monitored data to be identified and the second monitored data to be identified, thereby ensuring the accuracy and reliability of the sound effect comparison data.

Description

Technical Field

[0001] This application relates to the technical fields of VR and data processing. Specifically, it relates to a multi-user cloud-gathered stereo sound effect processing method and system based on a VR cinema. Background Art

[0002] The shipment volume of VR devices has been continuously increasing in the past two years and is expected to accelerate in the next few years. New content and features are needed to attract a large number of users. The market also predicts that since 2016, the VR content market has exceeded the VR head-mounted device market and become the largest segment market. Film and television is one of the most eye-catching fields in the VR content market, including panoramic movies, TV dramas, variety shows, animations, live broadcasts, etc., which are committed to giving users a real immersive experience through a strong virtual immersive viewing form.

[0003] With the continuous improvement of users' living standards, users' requirements for the viewing effect are also getting higher and higher. In this way, users need a more perfect visual and auditory sense. Since the layout of each cinema is different, if the same equipment is used, it may not be possible to achieve the best auditory sense in each cinema. Therefore, it is necessary to check the monitoring data to be identified to ensure the accuracy and reliability of the sound effect comparison data. Summary of the Invention

[0004] To improve the technical problems existing in the related art, this application provides a multi-user cloud-gathered stereo sound effect processing method and system based on a VR cinema.

[0005] In a first aspect, a multi-user cloud-gathered stereo sound effect processing method based on a VR cinema is provided. The method at least includes: determining cinema sound effect monitoring data, where the cinema sound effect monitoring data includes first monitoring data to be identified and second monitoring data to be identified, and the monitoring data evaluation result of the first monitoring data to be identified exceeds the monitoring data evaluation result of the second monitoring data to be identified; combining the first monitoring data to be identified and the second monitoring data to be identified to determine the second monitoring data to be identified that has been updated, where the monitoring data dimension of the second monitoring data to be identified that has been updated is the same as the monitoring data dimension of the second monitoring data to be identified, and the monitoring data evaluation result of the second monitoring data to be identified that has been updated exceeds the monitoring data evaluation result of the second monitoring data to be identified; combining the first monitoring data to be identified and the second monitoring data to be identified that has been updated to obtain first sound effect comparison data between the first monitoring data to be identified and the second monitoring data to be identified that has been updated.

[0006] In an independently implemented embodiment, the process of combining the first monitoring data to be identified and the second monitoring data to be identified to determine the updated second monitoring data to be identified includes: performing a first clustering process on the first monitoring data to be identified and the second monitoring data to be identified to determine the first user keyword description monitoring data, where the first user keyword description monitoring data covers the first keyword description quantization result between the first thermal distribution in the first monitoring data to be identified and the second thermal distribution in the second monitoring data to be identified, and the first thermal distribution and the second thermal distribution are the same thermal distribution; using the first user keyword description monitoring data as a feature extraction unit to perform a feature extraction operation on the first monitoring data to be identified to obtain the updated second monitoring data to be identified.

[0007] In an independently implemented embodiment, after determining the theater sound effect monitoring data, the method further includes: performing a second clustering process on the first monitoring data to be identified and the second monitoring data to be identified to determine the second user keyword description monitoring data, where the second user keyword description monitoring data covers the abnormal description result between the first thermal distribution and the second thermal distribution; the process of using the first user keyword description monitoring data as a feature extraction unit to perform a feature extraction operation on the first monitoring data to be identified to obtain the updated second monitoring data to be identified in the dimension of the second monitoring data to be identified includes: using the first user keyword description monitoring data and the second user keyword description monitoring data respectively as feature extraction units to perform a feature extraction operation on the first monitoring data to be identified to obtain the updated second monitoring data to be identified.

[0008] In an independently implemented embodiment, the process of using the first user keyword description monitoring data as a feature extraction unit to perform a feature extraction operation on the first monitoring data to be identified to determine the updated second monitoring data to be identified includes: combining the first keyword description quantization result to determine the first feature extraction unit; using the first feature extraction unit to perform a feature extraction operation on the first thermal distribution to obtain the updated second monitoring data to be identified.

[0009] In an independently implemented embodiment, the first clustering process on the first monitoring data to be recognized and the second monitoring data to be recognized to determine the first user keyword description monitoring data includes: integrating the first monitoring data to be recognized and the second monitoring data to be recognized to determine the third monitoring data to be recognized; performing X feature analysis processes on the third monitoring data to be recognized to determine the first intermediate description monitoring data, where X is an integer greater than or equal to 1; performing Y first translation processes on the first intermediate description monitoring data to obtain the first user keyword description monitoring data, where Y is an integer greater than or equal to 1.

[0010] In an independently implemented embodiment, the performing Y first translation processes on the first intermediate description monitoring data to obtain the first user keyword description monitoring data includes: splicing the significance monitoring data transmitted by the A-th feature analysis process among the X feature analysis processes and the significance monitoring data transmitted by the B-th first translation process among the Y first translation processes to obtain the real-time data of the (M + 1)-th first translation process among the Y first translation processes, where N is an integer greater than or equal to 1 and not exceeding X, and M is an integer greater than or equal to 1 and not greater than Y - 1.

[0011] In an independently implemented embodiment, the performing Y first translation processes on the first intermediate description monitoring data to obtain the first user keyword description monitoring data includes: performing the Y first translation processes on the intermediate description monitoring data to determine the second intermediate description monitoring data; performing feature extraction processing on the second intermediate description monitoring data using the first monitoring data to be recognized as the sample monitoring data, so that the distribution of the local part in the second intermediate description monitoring data is the same as the distribution of the local part in the first monitoring data to be recognized, to obtain the first user keyword description monitoring data.

[0012] In an independently implemented embodiment, combining the first monitoring data to be recognized and the second monitoring data to be recognized that has been updated to obtain first sound effect comparison data between the first monitoring data to be recognized and the second monitoring data to be recognized that has been updated includes: respectively performing clustering processing on the first monitoring data to be recognized and the second monitoring data to be recognized that has been updated to obtain first significant monitoring data of the first monitoring data to be recognized and second significant monitoring data of the second monitoring data to be recognized that has been updated; combining the similarity between the first significant monitoring data and the second significant monitoring data to obtain a second keyword description quantization result between the first heat distribution and the same heat distribution in the second monitoring data to be recognized that has been updated; and combining the second keyword description quantization result to obtain the first sound effect comparison data.

[0013] In an independently implemented embodiment, before combining the similarity between the first significant monitoring data and the second significant monitoring data to obtain the first sound effect comparison data, the method further includes: using the heat distribution situation in the first significant monitoring data as a feature extraction unit to perform a feature extraction operation on the heat distribution situation in the second significant monitoring data to obtain the similarity between the first significant monitoring data and the second significant monitoring data; or using the heat distribution situation in the second significant monitoring data as a feature extraction unit to perform a feature extraction operation on the heat distribution situation in the first significant monitoring data to obtain the similarity between the first significant monitoring data and the second significant monitoring data.

[0014] In an independently implemented embodiment, the method further includes: performing feature analysis processing on the first sound effect comparison data and the first significant monitoring data to determine third significant monitoring data; and performing translation processing on the third significant monitoring data to obtain second sound effect comparison data between the first monitoring data to be recognized and the second monitoring data to be recognized that has been updated, where the heat index of the second sound effect comparison data exceeds the heat index of the first sound effect comparison data.

[0015] In an independently implemented embodiment, performing feature analysis processing on the first sound effect comparison data and the first significant monitoring data to determine third significant monitoring data includes: integrating the first significant monitoring data and the first monitoring data to be recognized to determine fourth monitoring data to be recognized; and performing feature analysis processing on the fourth monitoring data to be recognized to obtain the third significant monitoring data.

[0016] In an independently implemented embodiment, before integrating and processing the first sound effect comparison data and the first significance monitoring data to determine the fourth monitoring data to be recognized, the method further includes: performing clustering processing on the first significance monitoring data to obtain the fourth significance monitoring data of the first significance monitoring data; the integrating and processing the first sound effect comparison data and the first significance monitoring data to determine the fourth monitoring data to be recognized includes: integrating and processing the fourth significance monitoring data and the first sound effect comparison data to obtain the fourth monitoring data to be recognized.

[0017] In a second aspect, a VR full-sense space control system based on deep learning is provided, including a processor and a memory that communicate with each other. The processor is configured to retrieve a computer program from the memory and implement the above method by running the computer program.

[0018] A multi-user cloud-gathered stereo sound effect processing method and system based on a VR cinema provided by an embodiment of the present application determine the second monitoring data to be recognized that has been updated according to the first monitoring data to be recognized and the second monitoring data to be recognized, so that the difference between the monitoring data evaluation result of the first monitoring data to be recognized and the monitoring data evaluation result of the second monitoring data to be recognized that has been updated is less than the monitoring data evaluation result of the first monitoring data to be recognized and the monitoring data evaluation result of the second monitoring data to be recognized. However, the accuracy of the first sound effect comparison data determined according to the first monitoring data to be recognized and the second monitoring data to be recognized that has been updated is based on the first monitoring data to be recognized and the second monitoring data to be recognized, thereby ensuring the accuracy and reliability of the sound effect comparison data. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application and should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0020] Figure 1 It is a flowchart of a multi-user cloud-gathered stereo sound effect processing method based on a VR cinema provided by an embodiment of the present application.

[0021] Figure 2 It is a block diagram of a multi-user cloud-gathered stereo sound effect processing device based on a VR cinema provided by an embodiment of the present application.

[0022] Figure 3The architecture diagram of a multi - user cloud - aggregated stereo sound effect processing system based on a VR cinema provided by the embodiments of the present application. Specific implementation manners

[0023] To better understand the above - mentioned technical solutions, the technical solutions of the present application will be described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solutions of the present application, rather than limitations on the technical solutions of the present application. Without conflict, the technical features in the embodiments of the present application and the embodiments can be combined with each other.

[0024] Please refer to Figure 1 , which shows a multi - user cloud - aggregated stereo sound effect processing method based on a VR cinema. The method may include the technical solutions described in the following steps 201 - 203.

[0025] 201. Determine the cinema sound effect monitoring data. The above - mentioned cinema sound effect monitoring data includes the first monitoring data to be identified and the second monitoring data to be identified. The monitoring data evaluation result of the first monitoring data to be identified exceeds the monitoring data evaluation result of the second monitoring data to be identified.

[0026] The above - mentioned monitoring data evaluation result includes at least one of the thermal index of the monitoring data, the interference result of the monitoring data, and the accuracy of the monitoring data. The thermal index of the monitoring data is positively correlated with the monitoring data evaluation result, the interference result of the monitoring data is positively correlated with the monitoring data evaluation result, and the accuracy of the monitoring data is related to the monitoring data evaluation result.

[0027] According to the above - described content, this embodiment can be used to weaken the difference in the monitoring data evaluation results between two pieces of monitoring data in the cinema sound effect monitoring data on the premise that there is a difference in the monitoring data evaluation results of the two pieces of monitoring data in the cinema sound effect monitoring data. Therefore, the monitoring data evaluation result of the first monitoring data to be identified exceeds the monitoring data evaluation result of the second monitoring data to be identified.

[0028] Further, after determining the cinema sound effect monitoring data, the monitoring data evaluation result evaluation indexes of two pieces of monitoring data in the cinema sound effect monitoring data can be determined according to the pre - configured monitoring data evaluation result evaluation method. Among them, the monitoring data evaluation result evaluation method includes at least one of the following: the thermal index of the monitoring data, the interference result of the monitoring data, and the accuracy of the monitoring data. After determining the monitoring data evaluation result indexes of two pieces of monitoring data in the cinema sound effect monitoring data, the first monitoring data to be identified and the second monitoring data to be identified can be further determined.

[0029] 202. Determine the second piece of monitoring data to be recognized that has been updated based on the above-mentioned first piece of monitoring data to be recognized and the above-mentioned second piece of monitoring data to be recognized. The dimension of the monitoring data of the second piece of monitoring data to be recognized that has been updated is the same as that of the second piece of monitoring data to be recognized, and the monitoring data evaluation result of the second piece of monitoring data to be recognized that has been updated exceeds the monitoring data evaluation result of the second piece of monitoring data to be recognized.

[0030] In this embodiment, determining the second piece of monitoring data to be recognized that has been updated based on the first piece of monitoring data to be recognized and the second piece of monitoring data to be recognized can be performed in the following manner: Perform clustering processing on the first piece of monitoring data to be recognized and the second piece of monitoring data to be recognized to determine the significant monitoring data of the first piece of monitoring data to be recognized and the significant monitoring data of the second piece of monitoring data to be recognized. Determine the keyword description quantification result between the same heat distribution in the first piece of monitoring data to be recognized and the second piece of monitoring data to be recognized according to the significant monitoring data of the first piece of monitoring data to be recognized and the significant monitoring data of the second piece of monitoring data to be recognized. Then, the distribution of the heat distribution in the first piece of monitoring data to be recognized can be trimmed according to the keyword description quantification result to determine the monitoring data whose monitoring data dimension is the same as that of the second piece of monitoring data to be recognized (which can be understood as the second piece of monitoring data to be recognized that has been updated).

[0031] The monitoring data evaluation result of the second piece of monitoring data to be recognized that has been updated determined in the above manner is the same as the monitoring data evaluation result of the first piece of monitoring data to be recognized, and the monitoring data dimension of the second piece of monitoring data to be recognized that has been updated is the same as the monitoring data dimension of the second piece of monitoring data to be recognized.

[0032] In the implementation of the possible method for determining the second piece of monitoring data to be recognized that has been updated based on the first piece of monitoring data to be recognized and the second piece of monitoring data to be recognized, the second piece of monitoring data to be recognized can be processed by de-optimization processing and / or anti-interference processing and / or processing for improving the heat index of the monitoring data, so as to improve the monitoring data evaluation result of the second piece of monitoring data to be recognized to be the same as the monitoring data evaluation result of the first piece of monitoring data to be recognized, and determine the second piece of monitoring data to be recognized that has been updated.

[0033] 203. Determine the first sound effect comparison data between the above-mentioned first piece of monitoring data to be recognized and the above-mentioned second piece of monitoring data to be recognized that has been updated.

[0034] Since the monitoring data dimensions of the second monitoring data to be identified that has been updated are the same as those of the second monitoring data to be identified, the first monitoring data to be identified and the second monitoring data to be identified that has been updated can be regarded as a set of theater sound effect monitoring data. Therefore, based on the first monitoring data to be identified and the second monitoring data to be identified that has been updated, the first sound effect comparison data between the first monitoring data to be identified and the second monitoring data to be identified that has been updated can be determined. The above-mentioned first sound effect comparison data includes the keyword description quantization results between the same heat distributions in the first monitoring data to be identified and the second monitoring data to be identified that has been updated.

[0035] In the implementation method of determining the first sound effect comparison data between the first monitoring data to be identified and the second monitoring data to be identified that has been updated based on the first monitoring data to be identified and the second monitoring data to be identified that has been updated, the clustering process can be performed on the first monitoring data to be identified and the second monitoring data to be identified that has been updated to determine the significant monitoring data of the first monitoring data to be identified and the significant monitoring data of the second monitoring data to be identified that has been updated. By performing a correlation recognition operation on the significant monitoring data of the first monitoring data to be identified and the significant monitoring data of the second monitoring data to be identified that has been updated, the same heat distributions in the significant monitoring data of the first monitoring data to be identified and the significant monitoring data of the second monitoring data to be identified that has been updated can be determined. The above-mentioned first sound effect comparison data is determined according to the keyword description quantization results between the same heat distributions in the significant monitoring data of the first monitoring data to be identified and the significant monitoring data of the second monitoring data to be identified that has been updated.

[0036] In the implementation method of determining the first sound effect comparison data between the first monitoring data to be identified and the second monitoring data to be identified that has been updated based on the first monitoring data to be identified and the second monitoring data to be identified that has been updated, the correlation recognition operation can be performed on the first monitoring data to be identified and the second monitoring data to be identified that has been updated to determine the same heat distributions in the first monitoring data to be identified and the second monitoring data to be identified that has been updated. The above-mentioned first sound effect comparison data is determined according to the keyword description quantization results between the same heat distributions in the first monitoring data to be identified and the second monitoring data to be identified that has been updated.

[0037] In this embodiment, the updated second piece of monitoring data to be recognized is determined based on the first piece of monitoring data to be recognized and the second piece of monitoring data to be recognized, so that the difference between the monitoring data evaluation result of the first piece of monitoring data to be recognized and the monitoring data evaluation result of the updated second piece of monitoring data to be recognized is less than the difference between the monitoring data evaluation result of the first piece of monitoring data to be recognized and the monitoring data evaluation result of the second piece of monitoring data to be recognized. However, the accuracy of the first sound effect comparison data determined based on the first piece of monitoring data to be recognized and the updated second piece of monitoring data to be recognized is based on the first piece of monitoring data to be recognized and the second piece of monitoring data to be recognized, thereby ensuring the accuracy and reliability of the sound effect comparison data.

[0038] The embodiment of the present disclosure further defines step 202, which may include the following content.

[0039] 301. Perform a first clustering process on the above-mentioned first piece of monitoring data to be recognized and the above-mentioned second piece of monitoring data to be recognized to determine the first user keyword description monitoring data. The first user keyword description monitoring data covers the first keyword description quantization result between the first heat distribution in the first piece of monitoring data to be recognized and the second heat distribution in the second piece of monitoring data to be recognized. The first heat distribution and the second heat distribution are the same heat distribution.

[0040] Further, before performing the first clustering process on the first piece of monitoring data to be recognized and the second piece of monitoring data to be recognized, an integration process may be performed on the first piece of monitoring data to be recognized and the second piece of monitoring data to be recognized to determine the spliced monitoring data to be recognized (i.e., the third piece of monitoring data to be recognized). The first clustering process on the first piece of monitoring data to be recognized and the second piece of monitoring data to be recognized can be implemented by performing a first clustering process on the third piece of monitoring data to be recognized.

[0041] Performing a first clustering process on the third piece of monitoring data to be recognized includes performing a first clustering process on each heat distribution in the third piece of monitoring data to be recognized. By performing a first clustering process on each heat distribution in the third piece of monitoring data to be recognized, the description situation of each heat distribution in the third piece of monitoring data to be recognized can be selected, and the keyword description quantization result of each heat distribution can be determined according to the description situation of each heat distribution, so as to obtain the first user keyword description monitoring data covering the keyword description quantization results of each heat distribution. Among them, the keyword description quantization result of each heat distribution includes the keyword description quantization result between the same heat distributions in the first piece of monitoring data to be recognized and the second piece of monitoring data to be recognized.

[0042] For example, the first thermal distribution in the first monitoring data to be recognized and the second thermal distribution in the second monitoring data to be recognized are the same thermal distribution. By performing a first clustering process on the first monitoring data to be recognized and the second monitoring data to be recognized, the first keyword description quantization result between the first thermal distribution and the second thermal distribution can be determined.

[0043] 302. Use the above first user keyword description monitoring data as a feature extraction unit to perform a feature extraction operation on the above first monitoring data to be recognized, and determine the above second monitoring data to be recognized that has been updated.

[0044] Using the first user keyword description monitoring data as a feature extraction unit to perform a feature extraction operation on the first monitoring data to be recognized, the thermal distribution in the first monitoring data to be recognized can be changed by the keyword description quantization result included in the first user keyword description monitoring data, so that the first distribution of the changed thermal distribution is consistent with the first distribution of the same thermal distribution in the second monitoring data to be recognized. Since the monitoring data evaluation result of the first monitoring data to be recognized exceeds the monitoring data evaluation result of the second monitoring data to be recognized, in this way, by changing the thermal distribution in the first monitoring data to be recognized so that the first distribution of the changed thermal distribution is consistent with the first distribution of the thermal distribution in the second monitoring data to be recognized, it is equivalent to determining the second monitoring data to be recognized after improving the monitoring data evaluation result, that is, the second monitoring data to be recognized that has been updated.

[0045] The first user keyword description monitoring data determined in step 301 includes all the keyword description quantization results of the same thermal distribution in the first monitoring data to be recognized and the second monitoring data to be recognized. Therefore, when using the first user keyword description monitoring data as a feature extraction unit to perform a feature extraction operation on the first monitoring data to be recognized, the feature extraction unit of the same thermal distribution in the first monitoring data to be recognized can be determined according to the keyword description quantization result of each thermal distribution in the first user keyword description monitoring data, and this feature extraction unit is used to perform a feature extraction operation on the same thermal distribution in the first monitoring data to be recognized. After completing the feature extraction operation on all thermal distributions in the first monitoring data to be recognized, the second monitoring data to be recognized that has been updated can be determined.

[0046] For a possible embodiment, by performing a weighted sum of the keyword description quantization results between each of the thermal distributions in the thermal distribution of the second monitoring data to be identified and the thermal distribution in the first monitoring data to be identified, the feature extraction unit of the thermal distribution in the first monitoring data to be identified can be determined. For example, the first thermal distribution in the first monitoring data to be identified and the second thermal distribution in the second monitoring data to be identified are the same thermal distribution. The thermal distribution situation constructed with the first thermal distribution as the center in the first monitoring data to be identified includes the third thermal distribution and the fourth thermal distribution. The keyword description quantization result of the first thermal distribution and the second thermal distribution is 4a, the keyword description quantization result of the second thermal distribution and the third thermal distribution is 4b, and the keyword description quantization result of the second thermal distribution and the fourth thermal distribution is 4c. The proportionality coefficient of the second thermal distribution is two-fifths, the proportionality coefficient of the third thermal distribution is three-tenths, and the proportionality coefficient of the fourth thermal distribution is three-tenths. Then, the keyword description quantization result of the first thermal distribution covered in the first user keyword description monitoring data determined by clustering the first significant monitoring data and the second significant monitoring data is: two-fifths * 4a + three-tenths * 4b + three-tenths * 4c. Then, the feature extraction unit of the first thermal distribution is determined according to the keyword description quantization result of the first thermal distribution in the first user keyword description monitoring data, and the feature extraction unit is used to perform a feature extraction operation on the first thermal distribution to change the first thermal distribution.

[0047] Furthermore, the process of determining the feature extraction unit of the thermal distribution in the first monitoring data to be identified according to the first user keyword description monitoring data can be implemented through an artificial intelligence thread. The thermal distribution in the second monitoring data to be identified, the thermal distribution situation bound in the first monitoring data to be identified (such as the thermal distribution situation bound by the second thermal distribution in the above example includes the first thermal distribution, the third thermal distribution, and the fourth thermal distribution), and the proportionality coefficients bound by the different thermal distributions in the thermal distribution situation can all be determined by the artificial intelligence thread.

[0048] Since the quantization results of keyword descriptions for the same thermal distribution in the first monitoring data to be recognized with different thermal distributions may be inconsistent compared to those in the second monitoring data to be recognized. For example, the thermal distribution (a) in the first monitoring data to be recognized and the thermal distribution (b) in the second monitoring data to be recognized are the same thermal distribution, and the thermal distribution (c) in the first monitoring data to be recognized and the thermal distribution (d) in the second monitoring data to be recognized are the same thermal distribution. The quantization result of the keyword description for the thermal distribution (a) and the thermal distribution (b) is X1, and the quantization result of the keyword description for the thermal distribution (c) and the thermal distribution (d) is X2, where X1 and X2 are different. In this embodiment, a feature extraction unit can be determined for each thermal distribution in the first monitoring data to be recognized according to the quantization results of the keyword descriptions in the first user keyword description monitoring data, and the feature extraction operation can be performed on the thermal distributions in the first monitoring data to be recognized through the determined feature extraction units to trim the first distribution of the thermal distributions in the first monitoring data to be recognized. In this embodiment, by determining different feature extraction units for different thermal distributions, the difference in the first distribution of the thermal distributions in the first monitoring data to be recognized and the first distribution of the same thermal distributions in the second monitoring data to be recognized can be reduced, and thus the difference between the determined updated second monitoring data to be recognized and the first monitoring data to be recognized can be reduced.

[0049] In this embodiment, clustering processing is performed on the first monitoring data to be recognized and the second monitoring data to be recognized to determine the first user keyword description monitoring data that covers the quantization results of keyword descriptions between the same thermal distributions in the first monitoring data to be recognized and the second monitoring data to be recognized. Then, according to the quantization results of the keyword descriptions in the first user keyword description monitoring data, a feature extraction unit is determined for each thermal distribution in the first monitoring data to be recognized, and the feature extraction operation is performed on the thermal distributions in the first monitoring data to be recognized using the feature extraction unit to trim the first distribution of the thermal distributions in the first monitoring data to be recognized, which can reduce the difference between the determined updated second monitoring data to be recognized and the first monitoring data to be recognized.

[0050] Further, when there is an abnormal description result between the same thermal distributions in the first monitoring data to be recognized and the second monitoring data to be recognized, in the process of determining the second monitoring data to be recognized that has been updated by changing the thermal distribution in the first monitoring data to be recognized, it is necessary to not only trim the first distribution of the thermal distribution in the first monitoring data to be recognized, but also trim the second distribution of the thermal distribution in the first monitoring data to be recognized. This can weaken the difference between the second monitoring data to be recognized that has been updated after changing the thermal distribution in the first monitoring data to be recognized and the first monitoring data to be recognized.

[0051] Determine the first feature extraction unit and the second feature extraction unit based on the first monitoring data to be recognized and the second monitoring data to be recognized, and how to use the first feature extraction unit and the second feature extraction unit to perform feature extraction operations on the thermal distribution in the first monitoring data to be recognized to determine the second monitoring data to be recognized that has been updated.

[0052] The content described by a multi-user cloud aggregation stereo sound effect processing method based on a VR cinema provided by an embodiment of the present disclosure may specifically include the following steps.

[0053] 601. Determine the cinema sound effect monitoring data. The above-mentioned cinema sound effect monitoring data includes the first monitoring data to be recognized and the second monitoring data to be recognized, and the monitoring data evaluation result of the above-mentioned first monitoring data to be recognized exceeds the monitoring data evaluation result of the above-mentioned second monitoring data to be recognized.

[0054] 602. Perform a first clustering process on the above-mentioned first monitoring data to be recognized and the above-mentioned second monitoring data to be recognized to determine the first user keyword description monitoring data, and perform a second clustering process on the above-mentioned first monitoring data to be recognized and the above-mentioned second monitoring data to be recognized to determine the second user keyword description monitoring data. The above-mentioned first user keyword description monitoring data covers the keyword description quantization result between the first thermal distribution in the above-mentioned first monitoring data to be recognized and the second thermal distribution in the above-mentioned second monitoring data to be recognized, and the above-mentioned second user keyword description monitoring data covers the abnormal description result between the above-mentioned first thermal distribution and the above-mentioned second thermal distribution. The above-mentioned first thermal distribution and the above-mentioned second thermal distribution are the same thermal distribution.

[0055] It can be understood that although the processes covered by the first clustering process and the second clustering process can be the same, the first clustering process and the second clustering process can select significant monitoring data with different coverage from the first monitoring data to be recognized and the second monitoring data to be recognized. For example, the first artificial intelligence thread and the second artificial intelligence thread are artificial intelligence threads with the same structure but different coefficients. Using the first artificial intelligence thread to perform clustering processing on the first monitoring data to be recognized and the second monitoring data to be recognized, the first user keyword description monitoring data covering the quantization result of the keyword description between the same heat distributions in the first monitoring data to be recognized and the second monitoring data to be recognized can be determined. Using the second artificial intelligence thread to perform clustering processing on the first monitoring data to be recognized and the second monitoring data to be recognized, the second user keyword description monitoring data covering the abnormal description result between the same heat distributions in the first monitoring data to be recognized and the second monitoring data to be recognized can be determined.

[0056] 603. Respectively use the above-mentioned first user keyword description monitoring data and the above-mentioned second user keyword description monitoring data as the feature extraction unit to perform feature extraction operations on the above-mentioned first monitoring data to be recognized, and determine the above-mentioned second monitoring data to be recognized that has been updated.

[0057] After determining the first user keyword description monitoring data and the second user keyword description monitoring data, the first user keyword description monitoring data and the second user keyword description monitoring data can be respectively used as the feature extraction unit to perform feature extraction operations on the first monitoring data to be recognized, and determine the second monitoring data to be recognized that has been updated.

[0058] For a possible embodiment, using the first user keyword description monitoring data as the feature extraction unit to perform feature extraction operations on the first monitoring data to be recognized, the fifth monitoring data to be recognized can be determined. Using the second user keyword description monitoring data as the feature extraction unit to perform feature extraction operations on the fifth monitoring data to be recognized, the second monitoring data to be recognized that has been updated can be determined. In an alternative embodiment, using the second user keyword description monitoring data as the feature extraction unit to perform feature extraction operations on the first monitoring data to be recognized, the sixth monitoring data to be recognized can be determined. Using the first user keyword description monitoring data as the feature extraction unit to perform feature extraction operations on the sixth monitoring data to be recognized, the second monitoring data to be recognized that has been updated can be determined.

[0059] Further, according to the above description, when using the first user keyword to describe the monitoring data for feature extraction of the first monitoring data to be identified, a feature extraction unit can be determined for each heat distribution in the first monitoring data to be identified according to the keyword description quantization result in the first user keyword description monitoring data, and the feature extraction unit is used to perform feature extraction operations on the corresponding heat distribution to improve the accuracy of feature extraction. In this step, a first feature extraction unit and a second feature extraction unit can also be determined for each heat distribution in the first monitoring data to be identified according to the first user keyword description monitoring data and the second user keyword description monitoring data, and then the first feature extraction unit and the second feature extraction unit are used one by one to perform feature extraction operations on the corresponding heat distribution to determine the updated second monitoring data to be identified.

[0060] Further, the embodiments of the present disclosure perform feature extraction processing on the first user keyword description monitoring data and / or the second user keyword description monitoring data, so that the distribution of the local part in the first user keyword description monitoring data is consistent with the distribution of the local part in the first monitoring data to be identified in the first monitoring data to be identified and / or the distribution of the local part in the second user keyword description monitoring data is consistent with the distribution of the local part in the first monitoring data to be identified in the first monitoring data to be identified, improving the credibility of the first monitoring data to be identified, and further improving the accuracy of the data covered by the first feature extraction unit determined according to the first user keyword description monitoring data and / or the credibility of the data covered by the second feature extraction unit determined according to the second user keyword description monitoring data.

[0061] Further, the above feature extraction processing can be sample feature extraction processing, that is, using the first monitoring data to be identified as the sample monitoring data to perform feature extraction processing on the first user keyword description monitoring data and / or the second user keyword description monitoring data, so that the distribution of the local part in the first user keyword description monitoring data is consistent with the distribution of the local part in the first monitoring data to be identified in the first monitoring data to be identified and / or the distribution of the local part in the second user keyword description monitoring data is consistent with the distribution of the local part in the first monitoring data to be identified in the first monitoring data to be identified.

[0062] In this embodiment, by performing a second clustering process on the first monitoring data to be recognized and the second monitoring data to be recognized, a second user keyword description monitoring data covering the abnormal description results between the same thermal distributions in the first monitoring data to be recognized and the second monitoring data to be recognized is determined. Using the abnormal description result monitoring data to perform a feature extraction operation on the thermal distribution in the first monitoring data to be recognized can trim the second distribution of the thermal distribution in the first monitoring data to be recognized, so as to weaken the difference between the updated second monitoring data to be recognized determined through the feature extraction operation and the first monitoring data to be recognized.

[0063] An embodiment of the present disclosure provides a method for performing a first clustering process on the first monitoring data to be recognized and the second monitoring data to be recognized to determine the first user keyword description monitoring data and performing a first clustering process on the first monitoring data to be recognized and the second monitoring data to be recognized to determine the second user keyword description monitoring data, which may specifically include the following steps.

[0064] 701. Integrate the above-mentioned first monitoring data to be recognized and the above-mentioned second monitoring data to be recognized to determine the third monitoring data to be recognized.

[0065] 702. Perform X times of feature parsing processing on the above-mentioned third monitoring data to be recognized to determine the first transitional description monitoring data, where X is an integer greater than or equal to 1.

[0066] 703. Perform Y times of first translation processing on the above-mentioned transitional description monitoring data to determine the second transitional description monitoring data, and perform Y times of second translation processing on the above-mentioned transitional description monitoring data to determine the third transitional description monitoring data.

[0067] 704. Use the above-mentioned first monitoring data to be recognized as the sample monitoring data to perform a feature extraction process on the above-mentioned second transitional description monitoring data, so that the distribution of the local part in the above-mentioned second transitional description monitoring data is the same as the distribution of the local part in the above-mentioned first monitoring data to be recognized, and determine the above-mentioned first user keyword description monitoring data. Use the above-mentioned first monitoring data to be recognized as the sample monitoring data to perform a feature extraction process on the above-mentioned third transitional description monitoring data, so that the distribution of the local part in the above-mentioned third transitional description monitoring data is the same as the distribution of the local part in the above-mentioned first monitoring data to be recognized, and determine the above-mentioned second user keyword description monitoring data.

[0068] By performing the first clustering process and the second clustering process on the first monitoring data to be recognized and the second monitoring data to be recognized provided by this embodiment, the possibility of data anomalies can be reduced, thereby ensuring the accuracy of the monitoring data described by the user keywords.

[0069] The second monitoring data to be recognized that has been updated can be determined based on the first monitoring data to be recognized. Further, the acoustic comparison data of the keyword description quantization results between the same heat distributions covering the first monitoring data to be recognized and the second monitoring data to be recognized that has been updated can be determined based on the first monitoring data to be recognized and the second monitoring data to be recognized that has been updated. For a possible embodiment, the second keyword description quantization result between the first heat distribution and the same heat distribution of the first heat distribution in the second monitoring data to be recognized that has been updated is determined, and the first acoustic comparison data between the first monitoring data to be recognized and the second monitoring data to be recognized that has been updated can be determined according to the second keyword description quantization result.

[0070] The first acoustic comparison data between the first monitoring data to be recognized and the second monitoring data to be recognized that has been updated is determined based on the first monitoring data to be recognized and the second monitoring data to be recognized that has been updated. A possible implementation manner of step 203 provided by the embodiments of the present disclosure may specifically include the following steps.

[0071] 1001. Perform clustering processes on the above-mentioned first monitoring data to be recognized and the above-mentioned second monitoring data to be recognized that has been updated respectively, and determine the first significant monitoring data of the above-mentioned first monitoring data to be recognized and the second significant monitoring data of the above-mentioned second monitoring data to be recognized that has been updated.

[0072] By performing clustering processes on the first monitoring data to be recognized and the second monitoring data to be recognized that has been updated respectively, when alleviating the first monitoring data to be recognized and the second monitoring data to be recognized that has been updated, the first significant monitoring data can be selected from the first monitoring data to be recognized, and the second significant monitoring data can be selected from the second monitoring data to be recognized that has been updated. In this way, the data recognition efficiency can be improved.

[0073] 1002. Determine the second keyword description quantization result between the first heat distribution and the same heat distribution of the first heat distribution in the above-mentioned second monitoring data to be recognized that has been updated according to the similarity between the above-mentioned first significant monitoring data and the above-mentioned second significant monitoring data.

[0074] In a possible embodiment, the quantization result of the keyword description between the third thermal distribution and the fourth thermal distribution is the same as the quantization result of the second keyword description between the first thermal distribution and the same thermal distribution of the first thermal distribution in the second monitoring data to be identified that has been updated.

[0075] 1003. Determine the above-mentioned first sound effect comparison data according to the above-mentioned quantization result of the second keyword description.

[0076] After determining the quantization result of the second keyword description through step 1003, the first sound effect comparison data can be determined according to the quantization result of the second keyword description.

[0077] On this basis, please refer to Figure 2 and a multi-user cloud gathering stereo sound effect processing device 200 based on a VR cinema is provided, which is applied to a multi-user cloud gathering stereo sound effect processing system based on a VR cinema. The device includes:

[0078] A result evaluation module 210, configured to determine cinema sound effect monitoring data, where the cinema sound effect monitoring data includes first monitoring data to be identified and second monitoring data to be identified, and the monitoring data evaluation result of the first monitoring data to be identified exceeds the monitoring data evaluation result of the second monitoring data to be identified;

[0079] A data update module 220, configured to combine the first monitoring data to be identified and the second monitoring data to be identified to determine the second monitoring data to be identified that has been updated. The monitoring data dimension of the second monitoring data to be identified that has been updated is consistent with the monitoring data dimension of the second monitoring data to be identified, and the monitoring data evaluation result of the second monitoring data to be identified that has been updated exceeds the monitoring data evaluation result of the second monitoring data to be identified;

[0080] A data comparison module 230, configured to combine the first monitoring data to be identified and the second monitoring data to be identified that has been updated to obtain first sound effect comparison data between the first monitoring data to be identified and the second monitoring data to be identified that has been updated.

[0081] On this basis, please refer to Figure 3 and shows a multi-user cloud gathering stereo sound effect processing system 300 based on a VR cinema, including a processor 310 and a memory 320 that communicate with each other. The processor 310 is configured to read and execute a computer program from the memory 320 to implement the above method.

[0082] On this basis, a computer-readable storage medium is also provided, and the computer program stored thereon implements the above method when running.

[0083] In summary, based on the above solution, the second monitored data to be recognized that has been updated is determined according to the first monitored data to be recognized and the second monitored data to be recognized, so that the difference between the monitoring data evaluation result of the first monitored data to be recognized and the monitoring data evaluation result of the second monitored data to be recognized that has been updated is less than the monitoring data evaluation result of the first monitored data to be recognized and the monitoring data evaluation result of the second monitored data to be recognized. However, the accuracy of the first sound effect comparison data determined according to the first monitored data to be recognized and the second monitored data to be recognized that has been updated is based on the first monitored data to be recognized and the second monitored data to be recognized, thereby ensuring the accuracy and reliability of the sound effect comparison data.

[0084] It should be understood that the above-described system and its modules can be implemented in various ways. For example, in some embodiments, the system and its modules can be implemented by hardware, software, or a combination of software and hardware. Among them, the hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. Those skilled in the art can understand that the above methods and systems can be implemented using computer-executable instructions and / or included in processor control code, such as provided on a carrier medium such as a disk, CD, or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The systems and modules of the present application can be implemented not only by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also by software implemented by various types of processors, or by a combination of the above hardware circuits and software (e.g., firmware).

[0085] It should be noted that different embodiments may produce different beneficial effects. In different embodiments, the beneficial effects that may be produced can be any one or several of the above combinations, or any other beneficial effects that may be obtained.

[0086] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only an example and does not constitute a limitation to this application. Although not explicitly stated here, those skilled in the art may make various modifications, improvements, and corrections to this application. Such modifications, improvements, and corrections are suggested in this application, so such modifications, improvements, and corrections still fall within the spirit and scope of the exemplary embodiments of this application.

[0087] Meanwhile, this application uses specific terms to describe the embodiments of this application. Such as "one embodiment", "an embodiment", and / or "some embodiments" mean a certain feature, structure, or characteristic related to at least one embodiment of this application. Therefore, it should be emphasized and noted that the "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more at different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this application can be appropriately combined.

[0088] In addition, those skilled in the art can understand that various aspects of this application can be illustrated and described by several patentable types or situations, including any new and useful processes, machines, products, or combinations of substances, or any new and useful improvements to them. Accordingly, various aspects of this application can be executed entirely by hardware, can be executed entirely by software (including firmware, resident software, microcode, etc.), or can be executed by a combination of hardware and software. The above hardware or software can all be referred to as "data blocks", "modules", "engines", "units", "components", or "systems". In addition, various aspects of this application may be embodied as a computer product located in one or more computer-readable media, which includes computer-readable program codes.

[0089] The computer storage medium may contain a propagated data signal containing computer program codes, such as on a baseband or as part of a carrier wave. This propagated signal may have various forms of manifestation, including electromagnetic form, optical form, etc., or a suitable combination of forms. The computer storage medium can be any computer-readable medium other than a computer-readable storage medium, which can be connected to an instruction execution system, device, or equipment to achieve communication, propagation, or transmission for use of the program. The program codes located on the computer storage medium can be propagated through any suitable medium, including radio, cable, fiber optic cable, RF, or similar media, or any combination of the above media.

[0090] The computer program codes required for the operations of various parts of this application can be written in any one or more programming languages, including object-oriented programming languages such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python, etc., conventional procedural programming languages such as C language, Visual Basic, Fortran 2003, Perl, COBOL 2002, PHP, ABAP, dynamic programming languages such as Python, Ruby and Groovy, or other programming languages. This program code can run entirely on the user's computer, or run as an independent software package on the user's computer, or run partially on the user's computer and partially on a remote computer, or run entirely on a remote computer or server. In the latter case, the remote computer can be connected to the user's computer through any network form, such as a local area network (LAN) or a wide area network (WAN), or connected to an external computer (for example, through the Internet), or in a cloud computing environment, or used as a service such as software as a service (SaaS).

[0091] In addition, unless clearly stated in the claims, the order of the processing elements and sequences, the use of numbers and letters, or the use of other names in this application are not used to limit the order of the processes and methods of this application. Although some currently considered useful embodiments of the invention are discussed through various examples in the above disclosure, it should be understood that such details only serve the purpose of illustration, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that conform to the essence and scope of the embodiments of this application. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only through software solutions, such as installing the described system on an existing server or mobile device.

[0092] Similarly, it should be noted that, in order to simplify the expression of the disclosure of this application and thus help the understanding of one or more embodiments of the invention, in the previous description of the embodiments of this application, sometimes multiple features are merged into one embodiment, drawing or description thereof. However, this disclosure method does not mean that the features required by the object of this application are more than those mentioned in the claims. In fact, the features of the embodiments are less than all the features of the individual embodiments disclosed above.

[0093] In some embodiments, numbers are used to describe components and the quantity of attributes. It should be understood that such numbers used in the description of embodiments are, in some examples, modified by the modifiers "about", "approximately" or "substantially". Unless otherwise specified, "about", "approximately" or "substantially" indicate that the said numbers allow for adaptive variations. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may vary according to the characteristics required by individual embodiments. In some embodiments, the numerical parameters should consider the specified significant digits and adopt the method of retaining the general number of digits. Although the numerical ranges and parameters used in some embodiments of this application to confirm the breadth of their scope are approximate values, in specific embodiments, such numerical settings are as precise as possible within the feasible range.

[0094] For each patent, patent application, patent application publication and other materials cited in this application, such as articles, books, specifications, publications, documents, etc., their entire contents are hereby incorporated into this application by reference. Except for the application history documents that are inconsistent with or conflict with the content of this application, and also except for the documents that limit the broadest scope of the claims of this application (currently or subsequently attached to this application). It should be noted that if there are inconsistencies or conflicts between the descriptions, definitions, and / or uses of terms in the attached materials of this application and the content described in this application, the descriptions, definitions, and / or uses of terms in this application shall prevail.

[0095] Finally, it should be understood that the embodiments described in this application are only used to illustrate the principles of the embodiments of this application. Other variations may also fall within the scope of this application. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this application may be considered consistent with the teachings of this application. Accordingly, the embodiments of this application are not limited to the embodiments explicitly introduced and described in this application.

[0096] The above are only the embodiments of this application and are not used to limit this application. For those skilled in the art, this application can have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included within the scope of the claims of this application.

Claims

1. A multi-user cloud gathering stereo sound effect processing method based on a VR cinema, characterized in that, The method at least includes: Determine theater sound effect monitoring data, where the theater sound effect monitoring data includes first monitoring data to be recognized and second monitoring data to be recognized, and the monitoring data evaluation result of the first monitoring data to be recognized exceeds the monitoring data evaluation result of the second monitoring data to be recognized; Combine the first monitoring data to be recognized and the second monitoring data to be recognized to determine the second monitoring data to be recognized that has been updated. The monitoring data dimension of the second monitoring data to be recognized that has been updated is consistent with the monitoring data dimension of the second monitoring data to be recognized, and the monitoring data evaluation result of the second monitoring data to be recognized that has been updated exceeds the monitoring data evaluation result of the second monitoring data to be recognized; Combine the first monitoring data to be recognized and the second monitoring data to be recognized that has been updated to obtain first sound effect comparison data between the first monitoring data to be recognized and the second monitoring data to be recognized that has been updated; Among them, the step of combining the first monitoring data to be recognized and the second monitoring data to be recognized to determine the second monitoring data to be recognized that has been updated includes: Perform first clustering processing on the first monitoring data to be recognized and the second monitoring data to be recognized to determine first user keyword description monitoring data. The first user keyword description monitoring data covers the first keyword description quantization result between the first heat distribution in the first monitoring data to be recognized and the second heat distribution in the second monitoring data to be recognized, and the first heat distribution and the second heat distribution are the same heat distribution; Use the first user keyword description monitoring data as a feature extraction unit to perform feature extraction operations on the first monitoring data to be recognized to obtain the second monitoring data to be recognized that has been updated.

2. The method according to claim 1, wherein After determining the theater sound effect monitoring data, the method further includes: performing second clustering processing on the first monitoring data to be recognized and the second monitoring data to be recognized to determine second user keyword description monitoring data. The second user keyword description monitoring data covers the abnormal description result between the first heat distribution and the second heat distribution; The step of using the first user keyword description monitoring data as a feature extraction unit to perform feature extraction operations on the first monitoring data to be recognized to obtain the second monitoring data to be recognized that has been updated under the dimension of the second monitoring data to be recognized includes: using the first user keyword description monitoring data and the second user keyword description monitoring data as feature extraction units respectively to perform feature extraction operations on the first monitoring data to be recognized to obtain the second monitoring data to be recognized that has been updated.

3. The method according to claim 1, characterized in that Performing a feature extraction operation on the first monitoring data to be recognized by using the first user keyword description monitoring data as a feature extraction unit to determine the second monitoring data to be recognized that has been updated, including: determining a first feature extraction unit in combination with the first keyword description quantization result; and performing a feature extraction operation on the first heat distribution by using the first feature extraction unit to obtain the second monitoring data to be recognized that has been updated.

4. The method according to claim 3, characterized in that, Performing a first clustering process on the first monitoring data to be recognized and the second monitoring data to be recognized to determine the first user keyword description monitoring data, including: Performing an integration process on the first monitoring data to be recognized and the second monitoring data to be recognized to determine the third monitoring data to be recognized; Performing X times of feature parsing processes on the third monitoring data to be recognized to determine the first transitional description monitoring data, where X is an integer greater than or equal to 1; Performing Y times of first translation processes on the first transitional description monitoring data to obtain the first user keyword description monitoring data, where Y is an integer greater than or equal to 1.

5. The method according to claim 4, wherein Performing Y times of first translation processes on the first transitional description monitoring data to obtain the first user keyword description monitoring data, including: splicing the significance monitoring data transmitted from the A-th feature parsing process in the X times of feature parsing processes and the significance monitoring data transmitted from the B-th first translation process in the Y times of first translation processes to obtain the real-time data of the (M + 1)-th first translation process in the Y times of first translation processes, where N is an integer greater than or equal to 1 and not exceeding X, and M is an integer greater than or equal to 1 and not greater than Y - 1.

6. The method according to claim 4, wherein Performing Y times of first translation processes on the first transitional description monitoring data to obtain the first user keyword description monitoring data, including: performing the Y times of first translation processes on the transitional description monitoring data to determine the second transitional description monitoring data; and performing a feature extraction process on the second transitional description monitoring data by using the first monitoring data to be recognized as a sample monitoring data, so that the distribution of the local part in the second transitional description monitoring data is the same as the distribution of the local part in the first monitoring data to be recognized, to obtain the first user keyword description monitoring data.

7. The method according to claim 1, characterized in that, Combining the first monitoring data to be recognized and the second monitoring data to be recognized that has been updated to obtain the first sound effect comparison data between the first monitoring data to be recognized and the second monitoring data to be recognized that has been updated, including: Performing clustering processes on the first monitoring data to be recognized and the second monitoring data to be recognized that has been updated respectively to obtain the first significance monitoring data of the first monitoring data to be recognized and the second significance monitoring data of the second monitoring data to be recognized that has been updated; Obtain the second keyword description quantification result between the first heat distribution and the same heat distribution of the first heat distribution in the second monitoring data to be identified that has been updated; obtain the first sound effect comparison data in combination with the second keyword description quantification result.

8. The method according to claim 7, wherein Before obtaining the first sound effect comparison data by combining the similarity between the first significance monitoring data and the second significance monitoring data, the method further includes: Taking the heat distribution situation in the first significance monitoring data as a feature extraction unit to perform a feature extraction operation on the heat distribution situation in the second significance monitoring data, and obtaining the similarity between the first significance monitoring data and the second significance monitoring data; Or, taking the heat distribution situation in the second significance monitoring data as a feature extraction unit to perform a feature extraction operation on the heat distribution situation in the first significance monitoring data, and obtaining the similarity between the first significance monitoring data and the second significance monitoring data; Wherein, the method further includes: performing feature analysis processing on the first sound effect comparison data and the first significance monitoring data to determine the third significance monitoring data; performing translation processing on the third significance monitoring data to obtain the second sound effect comparison data between the first monitoring data to be identified and the second monitoring data to be identified that has been updated, and the heat index of the second sound effect comparison data exceeds the heat index of the first sound effect comparison data; Wherein, the performing feature analysis processing on the first sound effect comparison data and the first significance monitoring data to determine the third significance monitoring data includes: performing integration processing on the first significance monitoring data and the first monitoring data to be identified to determine the fourth monitoring data to be identified; performing feature analysis processing on the fourth monitoring data to be identified to obtain the third significance monitoring data; Wherein, before performing integration processing on the first sound effect comparison data and the first significance monitoring data to determine the fourth monitoring data to be identified, the method further includes: performing clustering processing on the first significance monitoring data to obtain the fourth significance monitoring data of the first significance monitoring data; the performing integration processing on the first sound effect comparison data and the first significance monitoring data to determine the fourth monitoring data to be identified includes: performing integration processing on the fourth significance monitoring data and the first sound effect comparison data to obtain the fourth monitoring data to be identified.

9. A VR full-sensory space control system based on deep learning, characterized in that, Comprising a processor and a memory that communicate with each other, the processor is configured to retrieve a computer program from the memory and implement the method according to any one of claims 1-8 by running the computer program.

Images