Method and device for carrying out art work analysis based on multi-dimensional features

Abstract

The invention provides a method and device for carrying out art work analysis based on multi-dimensional features, and the method comprises the steps: carrying out the sampling of art work, and forming an art work image set; obtaining a text information set based on a preset semantic feature extraction unit; obtaining a numerical feature set based on a preset numerical feature extraction unit; obtaining a first analysis result set based on analysis results of different text information in the text information set; performing low-dimensional feature expression on numeralization features in the numeralization feature set, and obtaining a second analysis result set based on analysis results of expressions of different low-dimensional features; and combining corresponding analysis result parts in the first analysis result set and the second analysis result set to obtain a comprehensive analysis result of the art work. According to the method, the art work features are extracted, and then analysis is performed according to the extracted feature information, so that the effect of objectively and comprehensively analyzing the art work of students is realized, the efficiency of correcting the art work by teachers is improved, and the time is saved.

Description

Technical Field

[0001] The present application relates to the field of data analysis technology, and specifically to a method and device for analyzing and processing art work based on multi-dimensional features. Background Art

[0002] As an art, fine arts has its own unique artistic language and form of expression. Learning fine arts is inseparable from artistic language. Only when students master the corresponding artistic language and skills can they form corresponding artistic literacy.

[0003] At present, the main method for analyzing students' art homework is manual analysis. Manual analysis of art homework requires teachers to have rich art knowledge and experience, and the analysis speed is slow. In addition, the analysis standards of art homework often vary from teacher to teacher, school to school, or region to region, and there is a lack of unified measurement indicators. This makes it impossible to effectively compare and analyze between different analysis standards, and also increases the requirements for fairness and objectivity of students.

[0004] Therefore, how to overcome the above-mentioned technical problems and defects becomes a key issue that needs to be addressed. Summary of the invention

[0005] This application provides a method and device for analyzing and processing art homework based on multi-dimensional features to solve the problem that there is a lack of unified analysis indicators when analyzing students' art homework, so that comprehensive and objective analysis cannot be performed. This application adopts the following technical solutions:

[0006] In a first aspect, the present application provides a method for analyzing and processing art homework based on multi-dimensional features, including:

[0007] Sampling art homework, obtaining original image information of the art homework, and forming an art homework image set;

[0008] Based on a preset semantic feature extraction unit, the images in the art homework image set are converted into text information, the image text information in the same art homework image set constitutes the same text information, and the image text information in different art homework image sets constitutes the text information set of the art homework image set;

[0009] Inputting the images in the art homework image set into a preset numerical feature extraction unit to obtain numerical features of the images in the art homework image set, wherein the numerical features of the images in the same art homework image set constitute the same numerical feature, and the numerical features of the images in different art homework image sets constitute a numerical feature set;

[0010] Segmenting text information in the text information set to generate phrases of the text information, acquiring analysis results of the text information based on analysis of the phrases, and acquiring a first analysis result set based on analysis results of different text information in the text information set;

[0011] Performing feature selection on the numerical features in the numerical feature set to generate an expression of low-dimensional features of the numerical feature set, obtaining analysis results of the expression of the low-dimensional features based on the analysis of the expression of the low-dimensional features, and obtaining a second analysis result set based on the analysis results of the expressions of different low-dimensional features;

[0012] The corresponding analysis result parts of the first analysis result set and the second analysis result set are combined to obtain a comprehensive analysis result of the art assignment.

[0013] Furthermore, the sampling of the art homework includes: acquiring image information of the art homework through an external device such as a digital camera or a scanner, that is, sampling the art homework.

[0014] Furthermore, the preset semantic feature extraction unit converts the art homework image set into text information, including:

[0015] (1) extracting semantic features from the images in the art homework image set based on a preset semantic feature extraction unit, and converting the semantic features into semantic feature vectors, wherein the semantic feature vectors represent the similarity between different semantic features;

[0016] (2) dividing the semantic features into different groups based on the similarity of the semantic feature vectors, and associating the different groups according to the average values ​​of the semantic feature vectors;

[0017] (3) Based on the association information of the different groups, a text description is performed on the association information of the different groups using natural language, the text description information between the different groups is integrated into one text information, and the text information of the images in the art homework image set is obtained.

[0018] Furthermore, the obtaining a first analysis result set based on the analysis results of different text information in the text information set includes:

[0019] (1) segmenting the text information in the text information set to generate phrases of the text information, deleting stop words in the phrases based on a preset sentiment dictionary, converting the phrase information set into a multidimensional vector, and generating a phrase word vector set to capture the semantic features of the entire text information;

[0020] (2) traversing the phrase word vector set and matching it with the preset sentiment dictionary, and assigning a value to the phrase in the phrase word vector set after successful matching;

[0021] (3) summing the phrase values ​​in the phrase word vector set to obtain a comprehensive emotional value of the art homework;

[0022] (4) Acquire emotional tendency information of the art homework based on a comparison result between the emotional comprehensive value and a preset threshold.

[0023] Furthermore, the traversal of the phrase word vector set and matching with the preset sentiment dictionary, and assigning values ​​to the phrases in the phrase word vector set after successful matching, include:

[0024] When the phrase expresses a positive emotion, a positive value is assigned, when the phrase expresses a negative emotion, a negative value is assigned, and when the phrase expresses no emotion, a value of zero is assigned.

[0025] Furthermore, the step of inputting the images in the art homework image set into a preset numerical feature extraction unit to obtain the numerical features of the images in the art homework image set includes:

[0026] The images in the art homework image set are input into a convolutional neural network, and different convolution kernels are used to slide on the images in the art homework image set, and a feature value is obtained after completing one slide; based on the different features extracted by sliding different convolution kernels on different parts of the images in the art homework image set, the numerical features of the images in the art homework image set are constructed.

[0027] Furthermore, the performing feature selection on the numerical features in the numerical feature set to generate an expression of low-dimensional features of the numerical feature set includes:

[0028] The numerical feature set is converted into a feature matrix, the feature matrix is ​​diagonalized, the correlation of the feature vectors in the original feature matrix is ​​eliminated through KL transformation, the feature vectors with less information are removed to achieve the purpose of reducing the dimension of the feature space, and the expression of the low-dimensional features of the numerical feature set is obtained.

[0029] Further, the low-dimensional feature expressions of the numerical feature set are obtained, including color features, line features, texture features, and space features;

[0030] Furthermore, the color type, brightness and saturation in the color feature are obtained, and the color type, brightness and saturation are compared with the color type, brightness and saturation of the corresponding area of ​​the preset color template to obtain the analysis result of the color feature.

[0031] The line feature is compared with a preset line feature, and the line thickness, line length, line curvature and line direction in the line feature are analyzed to obtain an analysis result of the line feature.

[0032] The texture feature is compared with a preset texture feature, roughness information and smoothness information in the texture feature are analyzed, and an analysis result of the texture feature is obtained.

[0033] The spatial feature is compared with a preset spatial feature, and the layout information and proportion information of the spatial feature are analyzed to obtain an analysis result of the spatial feature.

[0034] Furthermore, the student's previous art homework information is obtained, and by comparing the previous art homework information with the current art homework information, the improved part and the regressed part of the current art homework are obtained.

[0035] In a second aspect, the present application also provides a device for performing art homework analysis and processing based on multi-dimensional features, including: an art homework sampling module, a text information set acquisition module, a numerical feature set acquisition module, a text information set result analysis module, a numerical feature set result analysis module, and a comprehensive analysis result acquisition module;

[0036] Art homework sampling module: used to sample art homework, obtain the original image information of the art homework, and form an art homework image set;

[0037] A text information set acquisition module: used for converting the images in the art homework image set into text information based on a preset semantic feature extraction unit, wherein the image text information in the same art homework image set constitutes the same text information, and the image text information in different art homework image sets constitutes the text information set of the art homework image set;

[0038] A numerical feature set acquisition module: used for inputting the images in the art homework image set into a preset numerical feature extraction unit to acquire the numerical features of the images in the art homework image set, wherein the numerical features of the images in the same art homework image set constitute the same numerical feature, and the numerical features of the images in different art homework image sets constitute a numerical feature set;

[0039] A text information set result analysis module: used to segment text information in the text information set, generate phrases of the text information, obtain analysis results of the text information based on analysis of the phrases, and obtain a first analysis result set based on analysis results of different text information in the text information set;

[0040] Numerical feature set result analysis module: used for reducing the dimension of the numerical features in the numerical feature set, generating an expression of low-dimensional features of the numerical feature set, obtaining an analysis result of the expression of the low-dimensional features based on the analysis of the expression of the low-dimensional features, and obtaining a second analysis result set based on the analysis results of the expressions of different low-dimensional features;

[0041] Comprehensive analysis result acquisition module: used to merge the corresponding analysis result parts of the first analysis result set and the second analysis result set to obtain the comprehensive analysis result of the art homework.

[0042] In a third aspect, the present application provides an electronic device, including:

[0043] One or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, which, when executed by the device, cause the device to perform the method as described in the first aspect.

[0044] In a fourth aspect, the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer executes the method described in the first aspect.

[0045] In a fifth aspect, the present application provides a computer program, which, when executed by a computer, is used to execute the method described in the first aspect.

[0046] In one possible design, the program in the fifth aspect may be stored in whole or in part on a storage medium packaged together with the processor, or may be stored in whole or in part on a memory not packaged together with the processor.

[0047] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0048] 1. This application analyzes the emotional tendency of art homework by obtaining semantic features in art homework and obtaining the emotional tendency of art homework based on the semantic features.

[0049] 2. This application obtains the numerical features of art assignments and analyzes them to understand students' mastery of colors, lines, textures, and space, and give reasonable suggestions.

[0050] 3. Through multi-dimensional feature analysis of students' art homework, students can identify their own strengths and goals in learning, and gradually develop the habit of discovering beautiful things in life from an art perspective, thereby loving life and achieving the goal of improving students' artistic literacy and perfecting their personality. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 This is an exemplary system architecture diagram to which the embodiments of the present application can be applied.

[0052] Figure 2 It is a method flow chart of an embodiment of the present application.

[0053] Figure 3 It is a flow chart of text information conversion in an embodiment of the present application.

[0054] Figure 4 It is a flowchart of text information analysis of an embodiment of the present application.

[0055] Figure 5 It is a schematic diagram of a device module of an embodiment of the present application.

[0056] Figure 6 It is a schematic diagram of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0058] Reference to "embodiments" herein means that a particular feature, structure, or characteristic 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.

[0059] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0060] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0061] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0062] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, etc.

[0063] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0064] It should be noted that the method for analyzing and processing art assignments based on multi-dimensional features provided in the embodiments of the present application is generally executed by a server / terminal device, and accordingly, the device for analyzing and processing art assignments based on multi-dimensional features is generally set in the server / terminal device.

[0065] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0066] Continue to refer Figure 2 , the figure shows a flow chart of the method for analyzing and processing art work based on multi-dimensional features of the present application, the method comprising the following steps:

[0067] Step S201, sampling art homework, obtaining original image information of the art homework, and forming an art homework image set;

[0068] The image information of the art homework is obtained through external devices such as digital cameras and scanners, that is, the art homework is sampled.

[0069] Step S202, converting the images in the art homework image set into text information based on a preset semantic feature extraction unit, wherein the image text information in the same art homework image set constitutes the same text information, and the image text information in different art homework image sets constitutes a text information set of the art homework image set;

[0070] Please continue to refer to Figure 3 , the preset semantic feature extraction unit converts the art homework image set into text information, including:

[0071] Step 301, extracting semantic features from the images in the art homework image set based on a preset semantic feature extraction unit, and converting the semantic features into semantic feature vectors, where the semantic feature vectors represent the similarity between different semantic features;

[0072] Step 302, dividing the semantic features into different groups based on the similarity of the semantic feature vectors, and associating the different groups according to the average values ​​of the semantic feature vectors;

[0073] Step 303: Based on the association information of the different groups, the association information of the different groups is described in text using natural language, the text description information between the different groups is integrated into one text information, and the text information of the images in the art homework image set is obtained.

[0074] Please continue to refer to Figure 4 , the obtaining of a first analysis result set based on the analysis results of different text information in the text information set includes:

[0075] Step 401, segmenting the text information in the text information set to generate phrases of the text information, deleting stop words in the phrases based on a preset sentiment dictionary, converting the phrase information set into a multidimensional vector, and generating a phrase word vector set to capture the semantic features of the entire text information;

[0076] Step 402, traversing the phrase word vector set, matching it with the preset sentiment dictionary, and assigning a value to the phrase in the phrase word vector set after successful matching;

[0077] Step 403, summing up the phrase values ​​in the phrase word vector set to obtain the comprehensive emotional value of the art homework; when the phrase expresses a positive emotion, a positive value is assigned, when the phrase expresses a negative emotion, a negative value is assigned, and when the phrase expresses no emotion, a value of zero is assigned.

[0078] Step 404: acquiring the emotional tendency information of the art homework according to the comparison result between the emotional comprehensive value and the preset threshold.

[0079] Step S203, input the images in the art homework image set into a preset numerical feature extraction unit to obtain the numerical features of the images in the art homework image set. The numerical features of the images in the same art homework image set constitute the same numerical feature, and the numerical features of the images in different art homework image sets constitute a numerical feature set.

[0080] The step of inputting the images in the art homework image set into a preset numerical feature extraction unit to obtain numerical features of the images in the art homework image set includes:

[0081] The images in the art homework image set are input into a convolutional neural network, and different convolution kernels are used to slide on the images in the art homework image set, and a feature value is obtained after completing one slide; based on the different features extracted by sliding different convolution kernels on different parts of the images in the art homework image set, the numerical features of the images in the art homework image set are constructed.

[0082] Step S204, segmenting the text information in the text information set to generate phrases of the text information, obtaining analysis results of the text information based on analysis of the phrases, and obtaining a first analysis result set based on analysis results of different text information in the text information set.

[0083] Step S205, perform feature selection on the numerical features in the numerical feature set to generate an expression of low-dimensional features of the numerical feature set, obtain analysis results of the expression of the low-dimensional features based on the analysis of the expression of the low-dimensional features, and obtain a second analysis result set based on the analysis results of the expressions of different low-dimensional features.

[0084] The step of performing feature selection on the numerical features in the numerical feature set to generate a low-dimensional feature expression of the numerical feature set includes: converting the numerical feature set into a feature matrix, diagonalizing the feature matrix, eliminating the correlation of feature vectors in the original feature matrix through KL transformation, removing feature vectors with less information to achieve the purpose of reducing the dimension of the feature space, and obtaining the low-dimensional feature expression of the numerical feature set.

[0085] The low-dimensional feature expressions of the numerical feature set include color features, line features, texture features, and space features.

[0086] The color type, brightness and saturation in the color feature are obtained, and the color type, brightness and saturation are compared with the color type, brightness and saturation of the corresponding area of ​​the preset color template to obtain the analysis result of the color feature. The line feature is compared with the preset line feature, and the line thickness, line length, line curvature and line direction in the line feature are analyzed to obtain the analysis result of the line feature. The texture feature is compared with the preset texture feature, and the roughness information and smoothness information in the texture feature are analyzed to obtain the analysis result of the texture feature. The space feature is compared with the preset space feature, and the layout information and proportion information of the space feature are analyzed to obtain the analysis result of the space feature.

[0087] Step S206: merging the corresponding analysis result parts of the first analysis result set and the second analysis result set to obtain a comprehensive analysis result of the art homework.

[0088] The comprehensive analysis results of the art assignments include semantic feature analysis results and numerical feature analysis results.

[0089] For example, the results of analyzing students' art assignments are as follows: "The overall emotional expression is relatively positive", "The color contrast of the picture is not strong, and the color purity can be improved", "The lines are smooth, but lack changes in thickness and density", "The texture is clear", and "The spatial composition is reasonable, highlighting the stability of the picture."

[0090] In a possible implementation, the student's previous art homework information is obtained, and the improved and degraded parts of the current art homework are obtained by comparing the previous art homework information with the current art homework information.

[0091] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0092] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0093] Continue to refer Figure 5 The device for performing art homework analysis and processing based on multi-dimensional features described in this embodiment includes: an art homework sampling module 501, a text information set acquisition module 502, a numerical feature set acquisition module 503, a text information set result analysis module 504, a numerical feature set result analysis module 505, and a comprehensive analysis result acquisition module 506;

[0094] Artwork sampling module 501: used to sample artwork, obtain original image information of the artwork, and form an artwork image set;

[0095] The text information set acquisition module 502 is used to convert the images in the art homework image set into text information based on a preset semantic feature extraction unit, the image text information in the same art homework image set constitutes the same text information, and the image text information in different art homework image sets constitutes the text information set of the art homework image set;

[0096] The numerical feature set acquisition module 503 is used to input the images in the art homework image set into a preset numerical feature extraction unit to acquire the numerical features of the images in the art homework image set, wherein the numerical features of the images in the same art homework image set constitute the same numerical feature, and the numerical features of the images in different art homework image sets constitute a numerical feature set;

[0097] The text information set result analysis module 504 is used to segment the text information in the text information set, generate phrases of the text information, obtain analysis results of the text information based on the analysis of the phrases, and obtain a first analysis result set based on the analysis results of different text information in the text information set;

[0098] Numerical feature set result analysis module 505: used to reduce the dimension of the numerical features in the numerical feature set, generate the expression of low-dimensional features of the numerical feature set, obtain the analysis result of the expression of the low-dimensional features based on the analysis of the expression of the low-dimensional features, and obtain the second analysis result set based on the analysis results of the expression of different low-dimensional features;

[0099] Comprehensive analysis result acquisition module 506: used to merge the corresponding analysis result parts of the first analysis result set and the second analysis result set to obtain a comprehensive analysis result of the art homework.

[0100] To solve the above technical problems, the present application also provides a computer device. Figure 6 , Figure 6 This is a basic structural block diagram of the computer device in this embodiment.

[0101] The computer device 6 includes a memory 6a, a processor 6b, and a network interface 6c that are interconnected through a system bus. It should be noted that the figure only shows a computer device 6 with components 6a-6c, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), digital signal processors (DSP), embedded devices, etc.

[0102] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0103] The memory 6a includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 6a can be an internal storage unit of the computer device 6, such as a hard disk or memory of the computer device 6. In other embodiments, the memory 6a can also be an external storage device of the computer device 6, such as a plug-in hard disk equipped on the computer device 6, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Of course, the memory 6a can also include both the internal storage unit of the computer device 6 and its external storage device. In this embodiment, the memory 6a is usually used to store the operating system and various application software installed on the computer device 6, such as the program code of the method and device for analyzing and processing art homework based on multi-dimensional features, etc. In addition, the memory 6a can also be used to temporarily store various types of data that have been output or are to be output.

[0104] The processor 6b may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 6b is generally used to control the overall operation of the computer device 6. In this embodiment, the processor 6b is used to run the program code stored in the memory 6a or process data, such as running the program code of the method and device for performing art homework analysis and processing based on multi-dimensional features.

[0105] The network interface 6c may include a wireless network interface or a wired network interface. The network interface 6c is generally used to establish a communication connection between the computer device 6 and other electronic devices.

[0106] The present application also provides another embodiment, namely, providing a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a program of a method and apparatus for analyzing and processing art homework based on multi-dimensional features, and the method and apparatus for analyzing and processing art homework based on multi-dimensional features can be executed by at least one processor, so that the at least one processor executes the steps of the method and apparatus for analyzing and processing art homework based on multi-dimensional features as described above.

[0107] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0108] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for analyzing art work based on multi-dimensional features, characterized in that: include: Sampling art homework, obtaining original image information of the art homework, and forming an art homework image set; Based on a preset semantic feature extraction unit, the images in the art homework image set are converted into text information, the image text information in the same art homework image set constitutes the same text information, and the image text information in different art homework image sets constitutes the text information set of the art homework image set; Inputting the images in the art homework image set into a preset numerical feature extraction unit to obtain numerical features of the images in the art homework image set, wherein the numerical features of the images in the same art homework image set constitute the same numerical feature, and the numerical features of the images in different art homework image sets constitute a numerical feature set; Segmenting text information in the text information set to generate phrases of the text information, acquiring analysis results of the text information based on analysis of the phrases, and acquiring a first analysis result set based on analysis results of different text information in the text information set; Performing feature selection on the numerical features in the numerical feature set to generate an expression of low-dimensional features of the numerical feature set, obtaining analysis results of the expression of the low-dimensional features based on the analysis of the expression of the low-dimensional features, and obtaining a second analysis result set based on the analysis results of the expressions of different low-dimensional features; The corresponding analysis result parts of the first analysis result set and the second analysis result set are combined to obtain a comprehensive analysis result of the art assignment.

2. The method for analyzing and processing art work based on multidimensional features according to claim 1, characterized in that: The sampling of art work includes: The image information of the art homework is obtained through external devices such as digital cameras and scanners, that is, the art homework is sampled.

3. The method for analyzing and processing art work based on multi-dimensional features according to claim 1, characterized in that: The preset semantic feature extraction unit converts the art homework image set into text information, including: (1) extracting semantic features from the images in the art homework image set based on a preset semantic feature extraction unit, and converting the semantic features into semantic feature vectors, wherein the semantic feature vectors represent the similarity between different semantic features; (2) dividing the semantic features into different groups based on the similarity of the semantic feature vectors, and associating the different groups according to the average values ​​of the semantic feature vectors; (3) Based on the association information of the different groups, a text description is performed on the association information of the different groups using natural language, the text description information between the different groups is integrated into one text information, and the text information of the images in the art homework image set is obtained.

4. The method for analyzing and processing art work based on multi-dimensional features according to claim 3, characterized in that: The obtaining of a first analysis result set based on the analysis results of different text information in the text information set includes: (1) segmenting the text information in the text information set to generate phrases of the text information, deleting stop words in the phrases based on a preset sentiment dictionary, converting the phrase information set into a multidimensional vector, and generating a phrase word vector set to capture the semantic features of the entire text information; (2) traversing the phrase word vector set and matching it with the preset sentiment dictionary, and assigning a value to the phrase in the phrase word vector set after successful matching; (3) summing the phrase values ​​in the phrase word vector set to obtain a comprehensive emotional value of the art homework; (4) Acquire emotional tendency information of the art homework based on a comparison result between the emotional comprehensive value and a preset threshold.

5. The method for analyzing and processing art work based on multi-dimensional features according to claim 4, characterized in that: The traversing of the phrase word vector set and matching with the preset sentiment dictionary, and assigning values ​​to the phrases in the phrase word vector set after successful matching, includes: When the phrase expresses a positive emotion, a positive value is assigned, when the phrase expresses a negative emotion, a negative value is assigned, and when the phrase expresses no emotion, a value of zero is assigned.

6. The method for analyzing and processing art work based on multi-dimensional features according to claim 1, characterized in that: The step of inputting the images in the art homework image set into a preset numerical feature extraction unit to obtain the numerical features of the images in the art homework image set includes: The images in the art homework image set are input into a convolutional neural network, and different convolution kernels are used to slide on the images in the art homework image set, and a feature value is obtained after completing one slide; based on the different features extracted by sliding different convolution kernels on different parts of the images in the art homework image set, the numerical features of the images in the art homework image set are constructed.

7. The method for analyzing and processing art work based on multi-dimensional features according to claim 1, characterized in that: The step of performing feature selection on the numerical features in the numerical feature set to generate a low-dimensional feature expression of the numerical feature set includes: The numerical feature set is converted into a feature matrix, the feature matrix is ​​diagonalized, the correlation of the feature vectors in the original feature matrix is ​​eliminated through KL transformation, the feature vectors with less information are removed to achieve the purpose of reducing the dimension of the feature space, and the expression of the low-dimensional features of the numerical feature set is obtained.

8. A device for analyzing and processing art work based on multi-dimensional features, characterized in that: The device comprises: Art homework sampling module: used to sample art homework, obtain the original image information of the art homework, and form an art homework image set; A text information set acquisition module: used for converting the images in the art homework image set into text information based on a preset semantic feature extraction unit, wherein the image text information in the same art homework image set constitutes the same text information, and the image text information in different art homework image sets constitutes the text information set of the art homework image set; A numerical feature set acquisition module: used for inputting the images in the art homework image set into a preset numerical feature extraction unit to acquire the numerical features of the images in the art homework image set, wherein the numerical features of the images in the same art homework image set constitute the same numerical feature, and the numerical features of the images in different art homework image sets constitute a numerical feature set; A text information set result analysis module: used to segment text information in the text information set, generate phrases of the text information, obtain analysis results of the text information based on analysis of the phrases, and obtain a first analysis result set based on analysis results of different text information in the text information set; Numerical feature set result analysis module: used for reducing the dimension of the numerical features in the numerical feature set, generating an expression of low-dimensional features of the numerical feature set, obtaining an analysis result of the expression of the low-dimensional features based on the analysis of the expression of the low-dimensional features, and obtaining a second analysis result set based on the analysis results of the expressions of different low-dimensional features; Comprehensive analysis result acquisition module: used to merge the corresponding analysis result parts of the first analysis result set and the second analysis result set to obtain the comprehensive analysis result of the art homework.

9. An electronic device, characterized in that: include: One or more processors, a memory, and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions, and when the instructions are executed by the device, the device performs the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed on a computer, enables the computer to execute the method according to any one of claims 1 to 7.

Images