Data screening method and system based on video quality

Abstract

The invention relates to the technical field of big data, in particular to a data screening method and system based on video quality, and the method comprises the steps: obtaining the overall to-be-screened video set encryption information of a to-be-screened video set based on network attributes, and obtaining a plurality of to-be-screened video set encryption information signatures under the overall to-be-screened video set encryption information; generating a quality evaluation and diagnosis system of the to-be-screened video set according to the quality evaluation and diagnosis parameters of the to-be-screened video set; analyzing diagnosis scores of the encrypted information signatures of the plurality of video sets to be screened in a quality evaluation diagnosis system of the video sets to be screened in combination with a diagnosis formula and the parameter importance; and obtaining the optimal quality video in the encrypted information signatures of the plurality of to-be-screened video sets according to the diagnosis scores. According to the method, the difference of quality evaluation parameters among different to-be-screened video set product designs can be seen, and the to-be-screened video set product optimization design direction is guided by complementing the short plate.

Description

Technical Field

[0001] The present application relates to the field of big data technology, and in particular to a data screening method and system based on video quality. Background Art

[0002] TV series are a combination of film, drama, literature, music, dance, painting, modeling and other modern art elements. They are a modern art style that adapts to the characteristics of television broadcasting and integrates the performance methods of stage and film art. They are loved by many viewers. Before a TV series is released, it is particularly important to analyze the plot of the TV series, judge its excitement, the audience's love for it, and its click volume, etc. for the development of TV series and film companies.

[0003] At present, major e-commerce platforms provide case references, creation skills and basic video attribute requirements for creators who make product videos in the form of production guides. However, most of the content is relatively broad and fixed, and it is impossible to provide creators with personalized creation assistance, which makes it difficult for creators to correctly implement the content of the guide in the process of video creation. In the field of computer vision, the existing work of evaluating assisted video production mainly targets videos on social platforms, predicting aesthetics, fun, memorability, and innovation. However, due to the purpose of displaying products, short time, and rich information, product videos have stronger requirements for the effectiveness of information presentation and viewing comfort. In addition, previous methods mainly completed the function of predicted evaluation results, and could not provide creators with insufficient feature analysis. Therefore, it is difficult to help novice creators optimize videos, solve practical problems in the production process, and screen the video content of the platform with high quality. Summary of the invention

[0004] The main purpose of this application is to provide a data screening solution based on video quality to solve the problem of screening optimization during video viewing in the prior art.

[0005] To achieve the above objectives, this application provides the following technical solutions:

[0006] Based on the first aspect of the present invention, the present invention claims a data screening method based on video quality, characterized in that it includes:

[0007] Based on the network attributes, the overall video set encryption information of the video set to be screened is obtained, and multiple video set encryption information signatures to be screened under the overall video set encryption information to be screened are obtained;

[0008] Generating a quality evaluation and diagnosis system for the video set to be screened based on the quality evaluation and diagnosis parameters of the video set to be screened;

[0009] In combination with the diagnostic formula and the parameter importance, the diagnostic scores of the encrypted information signatures of the plurality of video sets to be screened under the quality evaluation diagnostic system of the video sets to be screened are analyzed;

[0010] According to the diagnosis score, the best quality video among the encrypted information signatures of the plurality of video sets to be screened is obtained.

[0011] Furthermore, the quality evaluation diagnostic parameters of the video set to be screened include at least:

[0012] Content quality evaluation parameters, music quality evaluation parameters, security quality evaluation parameters, and picture quality evaluation parameters;

[0013] The content quality evaluation parameters include the script quality of the video set to be screened and the length of the video set to be screened;

[0014] The music quality evaluation parameters include the song quality and background music quality of the video set to be screened;

[0015] The safety quality evaluation parameters include the bad video ratio and advertisement insertion situation of the video set to be screened;

[0016] The picture quality evaluation parameters include the color or script balance of the video set to be screened.

[0017] Furthermore, the method further comprises:

[0018] The script quality is a core quality evaluation parameter, and a semantic detection instrument is used to compare the quality evaluation differences of encrypted information signatures of multiple video sets to be screened under the same script source using a historical similarity source method.

[0019] Furthermore, the method further comprises:

[0020] The song quality reflects the music auxiliary characteristics of the video set to be screened, and its quality evaluation depends on the background sound of the music itself and the background sound after the singer's voice is muted. The song quality is tested by an audio detection instrument;

[0021] The method for testing the background music quality is obtained by analyzing the initial size of the video set to be screened with encrypted information signatures of the plurality of video sets to be screened without accompaniment quality and the size difference after adding accompaniment multiple times.

[0022] Furthermore, the method further comprises:

[0023] The balance of the color or script includes the size uniformity of the video set to be screened before and after the script or color processing, the advertising insertion situation, the song quality, and the change range of the script quality.

[0024] Furthermore, the combining of the diagnostic formula and the parameter importance to analyze the diagnostic scores of the encrypted information signatures of the plurality of video sets to be screened under the quality evaluation diagnostic system of the video sets to be screened also includes:

[0025] According to the diagnostic formula of each quality evaluation diagnostic parameter under the video set to be screened, the diagnostic value of each quality evaluation diagnostic parameter is analyzed and obtained;

[0026] Assigning parameter importance to each quality evaluation diagnostic parameter value according to the importance of each parameter quality evaluation to the quality evaluation of the video set to be screened;

[0027] Analyze the diagnosis scores of the encrypted information signatures of the plurality of video sets to be screened under the quality evaluation diagnosis system of the video sets to be screened.

[0028] Based on the second aspect of the present invention, the present invention claims a data screening system based on video quality, characterized in that it includes:

[0029] one or more processors;

[0030] A memory having one or more programs stored therein, when the one or more programs are executed by the one or more processors, the one or more processors implement the data screening method based on video quality.

[0031] The present application relates to the field of big data technology, and in particular to a data screening method and system based on video quality, which obtains the overall encrypted information of the video set to be screened based on network attributes, and obtains multiple encrypted information signatures of the video set to be screened under the overall encrypted information of the video set to be screened; generates a quality evaluation diagnosis system for the video set to be screened based on the quality evaluation diagnosis parameters of the video set to be screened; analyzes the diagnosis scores of multiple encrypted information signatures of the video set to be screened under the quality evaluation diagnosis system of the video set to be screened by combining the diagnosis formula and the parameter importance; and obtains the best quality video among the multiple encrypted information signatures of the video set to be screened based on the diagnosis score. The present invention can not only screen out the best product design of the video set to be screened, but also can see the differences in quality evaluation parameters between different product designs of the video set to be screened, and guide the optimization design direction of the video set to be screened products by making up for the shortcomings. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A workflow diagram of a data screening method based on video quality claimed in the present invention;

[0033] Figure 2 A second working flow chart of a data screening method based on video quality claimed in the present invention;

[0034] Figure 3A structural diagram of a data screening system based on video quality claimed by the present invention. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0036] The terms "first", "second" and "third" in this application are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Thus, the features defined as "first", "second" and "third" can explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined. All directional indications in the embodiments of the present application (such as up, down, left, right, front, back...) are only used to explain the relative position relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally also includes steps or units that are not listed, or optionally also includes other steps or units inherent to these processes, methods, products or devices.

[0037] Reference to "embodiments" herein means that a particular feature, signature, or indication described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0038] Based on the first embodiment of the present invention, the present invention claims a data screening method based on video quality, referring to Figure 1 ,include:

[0039] S1, based on the network attributes, deriving the overall encrypted information of the video set to be screened, and obtaining multiple encrypted information signatures of the video set to be screened under the overall encrypted information of the video set to be screened;

[0040] S2, generating a quality evaluation and diagnosis system for the video set to be screened according to the quality evaluation and diagnosis parameters of the video set to be screened;

[0041] S3, combining the diagnosis formula and the parameter importance, analyzing the diagnosis scores of the encrypted information signatures of the multiple video sets to be screened under the quality evaluation diagnosis system of the video sets to be screened;

[0042] S4, based on the diagnosis score, obtain the best quality video among the encrypted information signatures of multiple video sets to be screened.

[0043] Among them, in this embodiment, the video set to be screened is short drama videos;

[0044] Furthermore, the quality evaluation diagnostic parameters of the video set to be screened include at least:

[0045] Content quality evaluation parameters, music quality evaluation parameters, security quality evaluation parameters, and picture quality evaluation parameters;

[0046] Content quality evaluation parameters include the script quality and length of the video set to be screened;

[0047] The music quality evaluation parameters include the song quality and background music quality of the video set to be screened;

[0048] Safety quality evaluation parameters include the proportion of bad videos and advertisement insertion in the video set to be screened;

[0049] Picture quality evaluation parameters include the color or script balance of the video set to be screened.

[0050] Among them, in this embodiment, for one, the mechanical quality evaluation under different combinations of encrypted information of the video sets to be screened has great differences. Due to the differences in signatures, there are differences in the overall quality evaluation.

[0051] Furthermore, the method further comprises:

[0052] Script quality is the core quality evaluation parameter. A semantic detection instrument is used to compare the quality evaluation differences of encrypted information signatures of multiple video sets to be screened under the same script source using the historical similarity source method.

[0053] Furthermore, the method further comprises:

[0054] The song quality reflects the music-assisted characteristics of the video set to be screened. Its quality evaluation depends on the background sound of the music itself and the background sound after the singer's voice is muted. The song quality is tested by audio detection instruments.

[0055] The testing method for background music quality is obtained by analyzing the initial size of the video set to be screened without accompaniment and the size difference after adding accompaniment multiple times of the encrypted information signatures of the video set to be screened.

[0056] Furthermore, the method further comprises:

[0057] The balance of color or script includes the size uniformity of the video set to be screened before and after script or color processing, the advertising insertion situation, the song quality, and the degree of change of script quality.

[0058] Among them, in this embodiment, the charge M of the color or script to be processed is measured, the semantic distribution range N of the color or script to be processed is measured, the balance of the color or script to be processed is measured, and the starting quality of the color or script to be processed is measured.

[0059] The theoretical length X0 of the video set to be screened is calculated according to the solid content of the color or script.

[0060] The accompaniment adding capability of the video set to be screened is verified based on audio detection test and dynamic accompaniment adding test.

[0061] The effect applicability of the video set to be screened is verified based on the sound silencing test.

[0062] Further, see Figure 2 , step S3, further comprising:

[0063] According to the diagnostic formula of each quality evaluation diagnostic parameter under the video set to be screened, the diagnostic value of each quality evaluation diagnostic parameter is analyzed and obtained;

[0064] Assigning parameter importance to each quality evaluation diagnostic parameter value according to the importance of each parameter quality evaluation to the quality evaluation of the video set to be screened;

[0065] Analyze the diagnostic scores of the encrypted information signatures of multiple video sets to be screened under the quality evaluation diagnostic system of the video sets to be screened.

[0066] Based on the above data, we compare the types of video sets that need to be screened on a large scale with the conventional types currently used through audio detection tests, dynamic accompaniment addition tests, and mute tests, and select the most appropriate types of video sets to be screened in order to reduce customer investment and costs.

[0067] The audio detection experiment is to use the type of video set to be screened that needs to be screened on a large scale, the type of regular video set to be screened, and the color or script to be processed to react, and then use an audio detection instrument to detect the audio detection time T.

[0068] Select the most appropriate type X based on the time value.

[0069] The specific data are shown in Table 1:

[0070] Table 1. Audio detection schedule for the types of video sets to be screened

[0071] Type of video collection to be filtered A B C D E F G H General Type Audio detection time S T1 T2 T3 T4 T5 T6 T7 T8 T0

[0072] The dynamic accompaniment adding experiment is to use the types of video sets to be screened that need to be screened on a large scale, the types of regular video sets to be screened, and the colors and scripts to be processed to react, and then use the added accompaniment Y per unit time to determine the applicability of the video sets to be screened.

[0073] According to the value of the dynamic accompaniment quality, the most suitable type X2 is selected, and the specific data is shown in Table 2.

[0074] Table 2 Quality table of dynamically added accompaniment for video set types to be screened

[0075] Type of video collection to be filtered A B C D E F G H General Type Dynamically add accompaniment quality g Y1 Y2 Y3 Y4 Y5 Y6 Y7 Y8 Y0

[0076] The silencing experiment is to use the types of video sets to be screened that need to be screened on a large scale, the types of regular video sets to be screened, and the colors and scripts that need to be processed to react. The most suitable type X3 is selected through the script quality, anti-cutting, quality Z1 of the processed color or script, and the comment sentiment tendency value of the processed color or script. The specific data are shown in Table 3.

[0077] Table 3. Table of silencing experiments of video sets to be screened

[0078] Type of video collection to be filtered A B C D E F G H General Type Dynamically add accompaniment quality P1 P2 P3 P4 P5 P6 P7 P8 P0 Quality of processed comments Z1 Z2 Z3 Z4 Z5 Z6 Z7 Z8 Z0 Comment sentiment after processing Q1 Q2 Q3 Q4 Q5 Q6 Q7 Q8 Q0

[0079] Based on the types selected from the above experiments, we calculate the most cost-effective type by combining the market prices of different types to reduce investment and costs for customers.

[0080] Unit color or script cost calculation: Unit cost = input * unit price.

[0081] In addition to relying on the comprehensive evaluation parameter system, selecting the best quality video from the signature quality videos with different encrypted information distributions of the video sets to be screened also requires the support of diagnostic formulas and parameter importance. Based on the test results and the generated scoring formula / importance, the signature quality video products with different encrypted information distributions of the video sets to be screened are comprehensively scored to obtain the best solution. The maximum score for a single parameter is 100 points, which is multiplied by the importance factor to obtain the final score.

[0082] The size uniformity is diagnosed by the size variation coefficient x1 (size standard deviation divided by the average size), and the maximum size variation coefficient Tmax in the signature quality video of the encrypted information distribution of different video sets to be screened is selected as the lower limit of the score, and the minimum size variation coefficient Tmin in the signature quality video of the encrypted information distribution of different video sets to be screened is selected as the upper limit of the score. That is, the maximum value (max) and minimum value (min) existing in the multiple distribution signatures of the encrypted information of each fixed video set to be screened. However, when the maximum value meets the technical requirements of first-class products, full marks can be obtained directly.

[0083] Based on the second embodiment of the present invention, the present invention claims a data screening system based on video quality, referring to Figure 3 ,include:

[0084] one or more processors;

[0085] The memory stores one or more programs, and when the one or more programs are executed by one or more processors, the one or more processors implement a data screening method based on video quality.

[0086] This embodiment can not only screen out the best product design, but also identify the differences in quality evaluation parameters between different product designs, and guide the direction of product optimization design by making up for shortcomings.

[0087] In the several embodiments provided in the present application, it should be understood that the disclosed systems, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or units, which can be electrical, physical or other forms.

[0088] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. The above is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent signature or equivalent process transformation made using the contents of the specification and drawings of this application, or directly or indirectly used in other related technical fields, is also included in the patent protection scope of the present application.

[0089] The specific implementation methods of the invention are described in detail above, but they are only examples, and the present application is not limited to the specific implementation methods described above. For those skilled in the art, any equivalent modification or substitution of the invention is also within the scope of the present application, and therefore, the equalization, modification, and improvement made without departing from the spirit and principle of the present application should be included in the scope of the present application.

Claims

1. A data screening method based on video quality, characterized in that: include: Based on the network attributes, the overall video set encryption information of the video set to be screened is obtained, and multiple video set encryption information signatures to be screened under the overall video set encryption information to be screened are obtained; Generating a quality evaluation and diagnosis system for the video set to be screened based on the quality evaluation and diagnosis parameters of the video set to be screened; In combination with the diagnostic formula and the parameter importance, the diagnostic scores of the encrypted information signatures of the plurality of video sets to be screened under the quality evaluation diagnostic system of the video sets to be screened are analyzed; According to the diagnosis score, the best quality video among the encrypted information signatures of the plurality of video sets to be screened is obtained.

2. A data screening method based on video quality as claimed in claim 1, characterized in that: The quality evaluation diagnostic parameters of the video set to be screened include at least: Content quality evaluation parameters, music quality evaluation parameters, security quality evaluation parameters, and picture quality evaluation parameters; The content quality evaluation parameters include the script quality of the video set to be screened and the length of the video set to be screened; The music quality evaluation parameters include the song quality and background music quality of the video set to be screened; The safety quality evaluation parameters include the bad video ratio and advertisement insertion situation of the video set to be screened; The picture quality evaluation parameters include the color or script balance of the video set to be screened.

3. A data screening method based on video quality as claimed in claim 2, characterized in that: Also includes: The script quality is a core quality evaluation parameter, and a semantic detection instrument is used to compare the quality evaluation differences of encrypted information signatures of multiple video sets to be screened under the same script source using a historical similarity source method.

4. A data screening method based on video quality as claimed in claim 3, characterized in that: Also includes: The song quality reflects the music auxiliary characteristics of the video set to be screened, and its quality evaluation depends on the background sound of the music itself and the background sound after the singer's voice is muted. The song quality is tested by an audio detection instrument; The method for testing the background music quality is obtained by analyzing the initial size of the video set to be screened with encrypted information signatures of the plurality of video sets to be screened without accompaniment quality and the size difference after adding accompaniment multiple times.

5. The method for data screening based on video quality as claimed in claim 4, characterized in that: Also includes: The balance of the color or script includes the size uniformity of the video set to be screened before and after the script or color processing, the advertising insertion situation, the song quality, and the change range of the script quality.

6. A method for screening data based on video quality as claimed in claim 5, characterized in that: The combining of the diagnostic formula and the parameter importance to analyze the diagnostic scores of the encrypted information signatures of the plurality of video sets to be screened under the quality evaluation diagnostic system of the video sets to be screened also includes: According to the diagnostic formula of each quality evaluation diagnostic parameter under the video set to be screened, the diagnostic value of each quality evaluation diagnostic parameter is analyzed and obtained; Assigning parameter importance to each quality evaluation diagnostic parameter value according to the importance of each parameter quality evaluation to the quality evaluation of the video set to be screened; Analyze the diagnosis scores of the encrypted information signatures of the plurality of video sets to be screened under the quality evaluation diagnosis system of the video sets to be screened.

7. A data screening system based on video quality, characterized in that: include: one or more processors; A memory having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement a data screening method based on video quality as described in any one of claims 1 to 6.

Images