Literature voice library storage method and system based on big data, and medium

Abstract

The embodiment of the invention provides a literature voice library storage method and system based on big data and a medium, and the method comprises the steps: obtaining literature voice, carrying out the noise reduction of the literature voice, and obtaining optimized voice information; performing encryption processing on the optimized voice information to obtain encrypted information; performing encrypted transmission on the literature voice according to the encrypted information to generate transmission information; storing the optimized voice information according to the transmission information to obtain storage information; the optimized voice information is stored according to the storage information, storage blocks are generated, and the voice information is stored to different storage nodes according to the types of the storage blocks; the literature voice is analyzed, encrypted and transmitted, the transmission safety is improved, and the transmitted voice information is stored to different storage nodes according to categories, so that classified storage of the voice information is realized, and the storage precision is improved.

Description

Technical Field

[0001] This application relates to the field of voice storage, and more particularly, to a method, system, and medium for storing a literary voice library based on big data. Background Art

[0002] During the storage of literary materials, by analyzing the categories of literary voices, the literary voices are stored in the corresponding storage areas to improve the storage accuracy. In the existing storage methods, it is impossible to automatically generate the corresponding level of encryption keys according to the differences in the content of literary voices, resulting in poor data transmission security during the transmission of literary voices. Moreover, during the analysis of literary voices, due to the noise characteristics in the literary voices, the content of the literary voices will be interfered, affecting the semantics of the literary voices and causing ambiguity; in view of the above problems, effective technical solutions are urgently needed. Summary of the Invention

[0003] The purpose of the embodiments of this application is to provide a method, system, and medium for storing a literary voice library based on big data. By analyzing literary voices and performing encrypted transmission, the transmission security is improved, and the transmitted voice information is stored in different storage nodes according to categories, realizing the classified storage of voice information and improving the storage accuracy.

[0004] The embodiments of this application also provide a method for storing a literary voice library based on big data, including:

[0005] Obtain literary voices, perform noise reduction processing on the literary voices to obtain optimized voice information;

[0006] Perform encryption processing on the optimized voice information to obtain encrypted information;

[0007] Perform encrypted transmission on the literary voices according to the encrypted information to generate transmission information;

[0008] Store the optimized voice information according to the transmission information to obtain storage information;

[0009] Store the optimized voice information according to the storage information to generate storage blocks, and store the voice information in different storage nodes according to the categories of the storage blocks.

[0010] Optionally, in the method for storing a literary voice library based on big data described in the embodiments of this application, obtaining literary voices and performing noise reduction processing on the literary voices to obtain optimized voice information specifically includes:

[0011] Obtain literary voices, perform semantic analysis on the literary voices to generate semantic information;

[0012] Segment the literary voices according to the semantic information to obtain several segments of voice information;

[0013] Perform noise analysis on each piece of voice information and eliminate noise features;

[0014] Fuse the voice information after eliminating the features to obtain optimized voice information.

[0015] Optionally, in the method for storing a literature voice library based on big data described in the embodiments of the present application, performing noise analysis on each piece of voice information and eliminating noise features specifically includes:

[0016] Obtain several pieces of voice information, extract features from each piece of voice information to obtain voice features;

[0017] Analyze the fluctuations of the voice features to obtain fluctuation information;

[0018] Compare the fluctuation information with the set fluctuation information to obtain a volatility rate;

[0019] Determine whether the volatility rate is greater than or equal to the set volatility threshold;

[0020] If it is greater than or equal to, perform smoothing processing on the corresponding voice features;

[0021] If it is less than, obtain optimized voice information.

[0022] Optionally, in the method for storing a literature voice library based on big data described in the embodiments of the present application, encrypting the optimized voice information to obtain encrypted information specifically includes:

[0023] Obtain the optimized voice information, input the optimized voice information into an encryption model to generate an encryption key;

[0024] Encode the optimized voice information through the encryption key to obtain encoded information;

[0025] Encrypt the optimized voice information according to the encoded information to obtain encrypted information;

[0026] Analyze the encryption level according to the encrypted information, compare the encryption level with the set encryption level to obtain level difference information;

[0027] Adjust the encryption parameters of the encryption key according to the level difference information.

[0028] Optionally, in the method for storing a literature voice library based on big data described in the embodiments of the present application, the training method of the encryption model is as follows:

[0029] Generate historical encryption data through big data;

[0030] Input the historical encryption data into the encryption model for iterative training to obtain a training result;

[0031] Determine whether the training result converges;

[0032] If it converges, input the optimized voice information into the encryption model;

[0033] If it does not converge, generate feedback information, adjust the number of iterations according to the feedback information, and optimize and adjust the model parameters of the encryption model.

[0034] Optionally, in the method for storing a literature voice library based on big data described in the embodiments of the present application, the optimized voice information is stored according to the storage information, a storage block is generated, and the voice information is stored in different storage nodes according to the category of the storage block. Specifically, it includes:

[0035] Obtain the optimized voice information, perform semantic analysis on the optimized voice information to obtain voice category information;

[0036] Obtain a storage node and generate storage category information;

[0037] Calculate the similarity between the voice category information and the storage category information to obtain a category similarity;

[0038] Determine whether the category similarity is greater than or equal to a set category similarity threshold;

[0039] If it is greater than or equal to, store the voice information in the storage node corresponding to the category;

[0040] If it is less than, adjust the voice category information.

[0041] In a second aspect, an embodiment of the present application provides a system for storing a literature voice library based on big data. The system includes: a memory and a processor. The memory includes a program for the method of storing a literature voice library based on big data. When the program for the method of storing a literature voice library based on big data is executed by the processor, the following steps are implemented:

[0042] Obtain literary voice, perform noise reduction processing on the literary voice to obtain optimized voice information;

[0043] Perform encryption processing on the optimized voice information to obtain encrypted information;

[0044] Perform encrypted transmission on the literary voice according to the encrypted information to generate transmission information;

[0045] Store the optimized voice information according to the transmission information to obtain storage information;

[0046] Store the optimized voice information according to the storage information, generate a storage block, and store the voice information in different storage nodes according to the category of the storage block.

[0047] Optionally, in the big data-based literary speech library storage system described in the embodiments of the present application, to obtain literary speech and perform noise reduction processing on the literary speech to obtain optimized speech information, specifically including:

[0048] Obtain literary speech, perform semantic parsing on the literary speech, and generate semantic information;

[0049] Segment the literary speech according to the semantic information to obtain several segments of speech information;

[0050] Perform noise analysis on each segment of speech information and eliminate noise features;

[0051] Perform fusion processing on the speech information after eliminating the noise features to obtain optimized speech information.

[0052] Optionally, in the big data-based literary speech library storage system described in the embodiments of the present application, to perform noise analysis on each segment of speech information and eliminate noise features, specifically including:

[0053] Obtain several segments of speech information, perform feature extraction on each segment of speech information to obtain speech features;

[0054] Analyze the fluctuations of the speech features to obtain fluctuation information;

[0055] Compare the fluctuation information with the set fluctuation information to obtain a volatility rate;

[0056] Determine whether the volatility rate is greater than or equal to the set volatility threshold;

[0057] If it is greater than or equal to, perform smoothing processing on the corresponding speech features;

[0058] If it is less than, obtain optimized speech information.

[0059] In a third aspect, the embodiments of the present application further provide a computer-readable storage medium, which includes a program for the big data-based literary speech library storage method. When the program for the big data-based literary speech library storage method is executed by a processor, the steps of the big data-based literary speech library storage method described in any one of the above are implemented.

[0060] As can be seen from the above, a method, system and medium for storing a literary speech library based on big data provided by an embodiment of the present application obtain literary speech, perform noise reduction processing on the literary speech to obtain optimized speech information; perform encryption processing on the optimized speech information to obtain encrypted information; perform encrypted transmission on the literary speech according to the encrypted information to generate transmission information; store the optimized speech information according to the transmission information to obtain storage information; store the optimized speech information according to the storage information to generate a storage block, and store the speech information in different storage nodes according to the category of the storage block; by analyzing the literary speech and performing encrypted transmission, the transmission security is improved, and the transmitted speech information is stored in different storage nodes according to the category, realizing the classified storage of the speech information and improving the storage accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required to be used in the embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application, and therefore 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.

[0062] Figure 1 It is a flowchart of the method for storing a literary speech library based on big data provided by an embodiment of the present application;

[0063] Figure 2 It is a flowchart of the noise feature elimination method of the method for storing a literary speech library based on big data provided by an embodiment of the present application;

[0064] Figure 3 It is a flowchart of optimizing speech information according to fluctuation information of the method for storing a literary speech library based on big data provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0065] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the detailed description of the embodiments of the present application provided in the drawings below is not intended to limit the scope of the present application to be protected, but only represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0066] It should be noted that similar reference numerals and letters indicate similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present application, terms such as "first", "second", etc. are only used for distinguishing descriptions and cannot be construed as indicating or implying relative importance.

[0067] Please refer to Figure 1 , Figure 1 which is a flowchart of a method for storing a literary speech library based on big data in some embodiments of the present application. The method for storing a literary speech library based on big data is used in a terminal device. The method for storing a literary speech library based on big data includes the following steps:

[0068] S101, obtain literary speech, perform noise reduction processing on the literary speech to obtain optimized speech information;

[0069] S102, perform encryption processing on the optimized speech information to obtain encrypted information;

[0070] S103, perform encrypted transmission on the literary speech according to the encrypted information to generate transmission information;

[0071] S104, store the optimized speech information according to the transmission information to obtain stored information;

[0072] S105, store the optimized speech information according to the stored information to generate a storage block, and store the speech information to different storage nodes according to the category of the storage block.

[0073] It should be noted that by performing noise reduction processing on the literary speech, the optimization of speech information is achieved, the response accuracy of speech information is improved, and distortion is prevented during the transmission of speech information. During the storage of speech information, encrypted transmission of speech information is performed to improve the transmission security of speech information. Different types of speech information are stored in different storage nodes to improve the flexibility of storage.

[0074] Please refer to Figure 2 , Figure 2 which is a flowchart of a method for removing noise features of a method for storing a literary speech library based on big data in some embodiments of the present application. According to an embodiment of the present invention, obtaining literary speech and performing noise reduction processing on the literary speech to obtain optimized speech information specifically includes:

[0075] S201, obtain literary speech, perform semantic parsing on the literary speech to generate semantic information;

[0076] S202, segment the literary speech according to the semantic information to obtain several segments of speech information;

[0077] S203. Perform noise analysis on each piece of voice information and eliminate noise features.

[0078] S204. Perform fusion processing on the voice information after eliminating the noise features to obtain optimized voice information.

[0079] It should be noted that semantic parsing is performed on literary voices, and the literary voices are segmented and denoised according to semantic information, and the voice information of different segments is fused again to optimize the voice information and improve the accuracy of the voice information.

[0080] Please refer to Figure 3 , Figure 3 FIG. is a flowchart for optimizing voice information according to fluctuation information in a method for storing a literary voice library based on big data in some embodiments of the present application. According to an embodiment of the present invention, noise analysis is performed on each piece of voice information, and noise features are eliminated, specifically including:

[0081] S301. Obtain several pieces of voice information, perform feature extraction on each piece of voice information to obtain voice features.

[0082] S302. Analyze the fluctuations of the voice features to obtain fluctuation information, and compare the fluctuation information with the set fluctuation information to obtain a volatility rate.

[0083] S303. Determine whether the volatility rate is greater than or equal to the set volatility threshold.

[0084] S304. If it is greater than or equal to, perform smoothing processing on the corresponding voice features.

[0085] S305. If it is less than, obtain optimized voice information.

[0086] It should be noted that during the analysis of voice information, the voice features are smoothed by analyzing the fluctuation of the voice information to improve the optimization effect of the voice information.

[0087] According to an embodiment of the present invention, encrypt the optimized voice information to obtain encrypted information, specifically including:

[0088] Obtain the optimized voice information, input the optimized voice information into an encryption model to generate an encryption key.

[0089] Encode the optimized voice information with the encryption key to obtain encoded information.

[0090] Encrypt the optimized voice information according to the encoded information to obtain encrypted information.

[0091] Analyze the encryption level according to the encrypted information, and compare the encryption level with the set encryption level to obtain level difference information.

[0092] Adjust the encryption parameters of the encryption key according to the level difference information.

[0093] It should be noted that the optimized voice information is input into the encryption model to automatically generate an encryption key, thereby improving the data security during the transmission of voice information. Different voice information generates different encryption keys according to different encryption levels, and the encryption parameters are dynamically adjusted according to the encryption level to improve encryption flexibility.

[0094] According to an embodiment of the present invention, the training method of the encryption model is as follows:

[0095] Generate historical encryption data through big data;

[0096] Input the historical encryption data into the encryption model for iterative training to obtain a training result;

[0097] Judge whether the training result converges;

[0098] If it converges, input the optimized voice information into the encryption model;

[0099] If it does not converge, generate feedback information, adjust the number of iterations according to the feedback information, and optimize and adjust the model parameters of the encryption model.

[0100] It should be noted that by generating a training set through big data to continuously train the encryption model, the output accuracy of the encryption model is improved, ensuring that the encryption key output by the encryption model better matches the corresponding voice information and improving data encryption security.

[0101] According to an embodiment of the present invention, the optimized voice information is stored according to the stored information to generate a storage block, and the voice information is stored in different storage nodes according to the category of the storage block, specifically including:

[0102] Obtain the optimized voice information, perform semantic analysis on the optimized voice information to obtain voice category information;

[0103] Obtain storage nodes and generate storage category information;

[0104] Calculate the similarity between the voice category information and the storage category information to obtain a category similarity;

[0105] Judge whether the category similarity is greater than or equal to a set category similarity threshold;

[0106] If it is greater than or equal to, store the voice information in the storage node corresponding to the category;

[0107] If it is less than, adjust the voice category information.

[0108] It should be noted that by performing semantic analysis on the voice information, the voice information is classified by accumulation. By analyzing the similarity between the voice category and the storage category, the voice information is accurately stored in the corresponding storage area, improving the storage accuracy.

[0109] According to an embodiment of the present invention, it further includes: obtaining voice information and generating a corresponding encryption key according to the voice information;

[0110] Generating a matching decryption key according to the encryption key;

[0111] Receiving a calling program, calling the voice information in the storage area according to the calling program, and activating the decryption key;

[0112] Parsing the encrypted voice information according to the decryption key to obtain parsing information;

[0113] Decrypting the voice according to the parsing information to obtain decryption information;

[0114] Restoring the encrypted voice information according to the decryption information to obtain the restored voice information.

[0115] It should be noted that when calling the encrypted voice information, the voice information needs to be decrypted. In order to ensure the decryption accuracy, a matching decryption key is generated according to the encryption key, so as to accurately decrypt the voice information and ensure that there is no semantic deviation in the decrypted voice information.

[0116] In a second aspect, an embodiment of the present application provides a literary voice library storage system based on big data. The system includes: a memory and a processor. The memory includes a program of the literary voice library storage method based on big data. When the program of the literary voice library storage method based on big data is executed by the processor, the following steps are implemented:

[0117] Obtaining literary voice, performing noise reduction processing on the literary voice to obtain optimized voice information;

[0118] Performing encryption processing on the optimized voice information to obtain encrypted information;

[0119] Performing encrypted transmission on the literary voice according to the encrypted information to generate transmission information;

[0120] Storing the optimized voice information according to the transmission information to obtain stored information;

[0121] Storing the optimized voice information according to the stored information to generate a storage block, and storing the voice information in different storage nodes according to the category of the storage block.

[0122] It should be noted that by performing noise reduction processing on literary speech, the optimization of speech information is achieved, the response accuracy of speech information is improved, and distortion is prevented during the transmission of speech information. During the storage of speech information, the speech information is encrypted for transmission to improve the transmission security of speech information. Different types of speech information are stored in different storage nodes to improve the flexibility of storage.

[0123] According to an embodiment of the present invention, obtaining literary speech and performing noise reduction processing on the literary speech to obtain optimized speech information specifically includes:

[0124] Obtaining literary speech, performing semantic parsing on the literary speech, and generating semantic information;

[0125] Segmenting the literary speech according to the semantic information to obtain several segments of speech information;

[0126] Performing noise analysis on each segment of speech information and removing noise features;

[0127] Performing fusion processing on the speech information from which the noise-causing features have been removed to obtain optimized speech information.

[0128] It should be noted that by performing semantic parsing on literary speech, segmenting and performing noise reduction processing on the literary speech according to the semantic information, and re-fusing the speech information of different segments, the speech information is optimized and the accuracy of the speech information is improved.

[0129] According to an embodiment of the present invention, performing noise analysis on each segment of speech information and removing noise features specifically includes:

[0130] Obtaining several segments of speech information, performing feature extraction on each segment of speech information to obtain speech features;

[0131] Analyzing the fluctuations of the speech features to obtain fluctuation information;

[0132] Comparing the fluctuation information with the set fluctuation information to obtain a volatility rate;

[0133] Judging whether the volatility rate is greater than or equal to the set volatility threshold;

[0134] If it is greater than or equal to, smoothing the corresponding speech features;

[0135] If it is less than, obtaining optimized speech information.

[0136] It should be noted that during the analysis of speech information, by analyzing the fluctuation situation of the speech information, the speech features are smoothed to improve the optimization effect of the speech information.

[0137] According to an embodiment of the present invention, performing encryption processing on the optimized speech information to obtain encrypted information specifically includes:

[0138] Obtain optimized voice information, input the optimized voice information into an encryption model to generate an encryption key;

[0139] Encode the optimized voice information with the encryption key to obtain encoded information;

[0140] Perform encryption processing on the optimized voice information according to the encoded information to obtain encrypted information;

[0141] Analyze the encryption level according to the encrypted information, compare the encryption level with the set encryption level to obtain level difference information;

[0142] Adjust the encryption parameters of the encryption key according to the level difference information.

[0143] It should be noted that the optimized voice information is input into the encryption model to automatically generate an encryption key, thereby improving the data security during the transmission of voice information. Different voice information generates different encryption keys according to different encryption levels, and the encryption parameters are dynamically adjusted according to the encryption level to improve encryption flexibility.

[0144] According to an embodiment of the present invention, the training method of the encryption model is as follows:

[0145] Generate historical encryption data through big data;

[0146] Input the historical encryption data into the encryption model for iterative training to obtain a training result;

[0147] Judge whether the training result converges;

[0148] If it converges, input the optimized voice information into the encryption model;

[0149] If it does not converge, generate feedback information, adjust the number of iterations according to the feedback information, and optimize and adjust the model parameters of the encryption model.

[0150] It should be noted that by generating a training set through big data to continuously train the encryption model, the output accuracy of the encryption model is improved, ensuring that the encryption key output by the encryption model better matches the corresponding voice information and improving data encryption security.

[0151] According to an embodiment of the present invention, the optimized voice information is stored according to the stored information to generate a storage block, and the voice information is stored in different storage nodes according to the category of the storage block, specifically including:

[0152] Obtain optimized voice information, perform semantic analysis on the optimized voice information to obtain voice category information;

[0153] Obtain a storage node and generate storage category information;

[0154] Calculate the similarity between the voice category information and the storage category information to obtain the category similarity;

[0155] Determine whether the category similarity is greater than or equal to a set category similarity threshold;

[0156] If it is greater than or equal to, store the voice information in the storage node corresponding to the category;

[0157] If it is less than, adjust the voice category information.

[0158] It should be noted that by performing semantic analysis on the voice information, the voice information is classified by category. By analyzing the similarity between the voice category and the storage category, the voice information is accurately stored in the storage area corresponding to the category, improving the storage accuracy.

[0159] According to an embodiment of the present invention, it further includes: obtaining voice information and generating a corresponding encryption key according to the voice information;

[0160] Generate a matching decryption key according to the encryption key;

[0161] Receive a calling program, call the voice information in the storage area according to the calling program, and activate the decryption key;

[0162] Parse the encrypted voice information according to the decryption key to obtain the parsed information;

[0163] Decrypt the voice according to the parsed information to obtain the decrypted information;

[0164] Restore the encrypted voice information according to the decrypted information to obtain the restored voice information.

[0165] It should be noted that when calling the encrypted voice information, the voice information needs to be decrypted. In order to ensure the decryption accuracy, a matching decryption key is generated according to the encryption key, so as to accurately decrypt the voice information and ensure that the decrypted voice information does not have semantic deviation.

[0166] The third aspect of the present invention provides a computer-readable storage medium. The readable storage medium includes a program for the method of storing a literary voice library based on big data. When the program for the method of storing a literary voice library based on big data is executed by a processor, the steps of the method of storing a literary voice library based on big data as described in any one of the above are implemented.

[0167] A method, system and medium for storing a literary speech database based on big data disclosed by the present invention obtain literary speech, perform noise reduction processing on the literary speech to obtain optimized speech information; perform encryption processing on the optimized speech information to obtain encrypted information; perform encrypted transmission on the literary speech according to the encrypted information to generate transmission information; store the optimized speech information according to the transmission information to obtain stored information; store the optimized speech information according to the stored information to generate a storage block, and store the speech information in different storage nodes according to the category of the storage block; by analyzing the literary speech and performing encrypted transmission, improve the transmission security, and store the transmitted speech information in different storage nodes according to the category, so as to realize the classified storage of the speech information and improve the storage accuracy.

[0168] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the couplings, direct couplings, or communication connections between the components shown or discussed may be through some interfaces, and the indirect couplings or communication connections of devices or units may be electrical, mechanical, or other forms.

[0169] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units; they may be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0170] In addition, in each embodiment of the present invention, each functional unit can be all integrated in a processing unit, or each unit can be separately used as a unit, or two or more units can be integrated in a unit; the above-mentioned integrated unit can be implemented in the form of hardware, or in the form of a hardware plus software functional unit.

[0171] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a readable storage medium. When the program is executed, it executes the steps including the above method embodiments; and the foregoing storage medium includes: various media such as a removable storage device, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk, or an optical disc that can store program codes.

[0172] Alternatively, if the above-mentioned integrated units of the present invention are implemented in the form of software function modules and sold or used as independent products, they can also be stored in a readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention essentially or the part that contributes to the prior art can be embodied in the form of a software product. The software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as removable storage devices, ROM, RAM, magnetic disks, or optical discs.

Claims

1. A method for storing a literary speech database based on big data, characterized in that, Including: Obtain literary speech, perform noise reduction processing on the literary speech to obtain optimized speech information; Perform encryption processing on the optimized speech information to obtain encrypted information; Perform encrypted transmission of the literary speech according to the encrypted information to generate transmission information; Store the optimized speech information according to the transmission information to obtain stored information; Store the optimized speech information according to the stored information to generate a storage block, and store the speech information in different storage nodes according to the category of the storage block.

2. The method for storing a literary speech database based on big data according to claim 1, wherein, Obtain literary speech, perform noise reduction processing on the literary speech to obtain optimized speech information, specifically including: Obtain literary speech, perform semantic analysis on the literary speech to generate semantic information; Segment the literary speech according to the semantic information to obtain several segments of speech information; Perform noise analysis on each segment of speech information and remove noise features; Perform fusion processing on the speech information with noise features removed to obtain optimized speech information.

3. The method for storing a literary speech database based on big data according to claim 2, wherein Perform noise analysis on each segment of speech information and remove noise features, specifically including: Obtain several segments of speech information, perform feature extraction on each segment of speech information to obtain speech features; Analyze the fluctuations of the speech features to obtain fluctuation information; Compare the fluctuation information with the set fluctuation information to obtain a volatility rate; Judge whether the volatility rate is greater than or equal to the set volatility threshold; If it is greater than or equal to, perform smoothing processing on the corresponding speech features; If it is less than, obtain optimized speech information.

4. The method for storing a literary speech database based on big data according to claim 3, wherein Perform encryption processing on the optimized speech information to obtain encrypted information, specifically including: Obtain optimized speech information, input the optimized speech information into an encryption model to generate an encryption key; Encode the optimized speech information through the encryption key to obtain encoded information; Perform encryption processing on the optimized speech information according to the encoded information to obtain encrypted information; Analyze the encryption level according to the encrypted information, compare the encryption level with the set encryption level to obtain level difference information; Adjust the encryption parameters of the encryption key according to the level difference information.

5. The method for storing a literary speech database based on big data according to claim 4, wherein The training method of the encryption model is as follows: Generate historical encryption data through big data; Input the historical encryption data into the encryption model for iterative training to obtain a training result; Judge whether the training result converges; If it converges, input the optimized speech information into the encryption model; If it does not converge, generate feedback information, adjust the number of iterations according to the feedback information, and optimize and adjust the model parameters of the encryption model.

6. The method for storing a literary speech database based on big data according to claim 5, characterized in that Store the optimized speech information according to the stored information to generate a storage block, and store the speech information in different storage nodes according to the category of the storage block, specifically including: Obtain optimized speech information, perform semantic analysis on the optimized speech information to obtain speech category information; Obtain storage nodes and generate storage category information; Calculate the similarity between the speech category information and the storage category information to obtain a category similarity; Judge whether the category similarity is greater than or equal to the set category similarity threshold; If it is greater than or equal to, store the speech information in the corresponding category of storage node; If it is less than, adjust the speech category information.

7. A literary speech database storage system based on big data, characterized in that, The system includes: a memory and a processor. The memory includes a program for the method of storing a literary speech library based on big data. When the program for the method of storing a literary speech library based on big data is executed by the processor, the following steps are implemented: Obtain literary speech, perform noise reduction processing on the literary speech to obtain optimized speech information; Perform encryption processing on the optimized speech information to obtain encrypted information; Perform encrypted transmission on the literary speech according to the encrypted information to generate transmission information; Store the optimized speech information according to the transmission information to obtain stored information; Store the optimized speech information according to the stored information to generate a storage block, and store the speech information in different storage nodes according to the category of the storage block.

8. The literary speech database storage system based on big data according to claim 7, wherein Obtain literary speech, perform noise reduction processing on the literary speech to obtain optimized speech information, specifically including: Obtain literary speech, perform semantic parsing on the literary speech to generate semantic information; Segment the literary speech according to the semantic information to obtain several segments of speech information; Perform noise analysis on each segment of speech information and remove noise features; Perform fusion processing on the speech information after removing the noise features to obtain optimized speech information.

9. The literary speech database storage system based on big data according to claim 8, characterized in that, Perform noise analysis on each segment of speech information and remove noise features, specifically including: Obtain several segments of speech information, perform feature extraction on each segment of speech information to obtain speech features; Analyze the fluctuations of the speech features to obtain fluctuation information; Compare the fluctuation information with the set fluctuation information to obtain a fluctuation rate; Judge whether the fluctuation rate is greater than or equal to the set fluctuation rate threshold; If it is greater than or equal to, perform smoothing processing on the corresponding speech features; If it is less than, obtain optimized speech information.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a program for the method of storing a literary speech library based on big data. When the program for the method of storing a literary speech library based on big data is executed by a processor, the steps of the method of storing a literary speech library based on big data as described in any one of claims 1 to 6 are implemented.

Images