Image design visual communication system and method based on big data

Abstract

The invention discloses an image design visual communication system and method based on big data, and relates to the field of image design, and the system comprises an image design platform which is provided with a data collection module, a user analysis module, a design analysis module, a frame analysis module, a cooperative adjustment module and a design feedback module; the data acquisition module acquires image data information, user data information and design data information; the user analysis module constructs a user portrait of the user according to the user data information; the design analysis module obtains design trend data according to the image data information; the framework analysis module sets an initial design image according to the design data information; the collaborative adjustment module performs collaborative adjustment on the initial design image according to the design trend data and the user portrait to generate a collaborative design image; the design feedback module is used for performing feedback adjustment on the collaborative design image by the user to obtain a visual transmission image; according to the method, the efficiency in the image design process is improved to a certain extent.

Description

Technical Field

[0001] The present invention relates to the field of image design, and in particular to an image design visual communication system and method based on big data. Background Art

[0002] In traditional image design, designers usually need to complete a work through repeated attempts and modifications. This process is time-consuming and laborious, and the aesthetics and innovation of the final result cannot be guaranteed. Therefore, how to improve the efficiency and quality of image design has become an important research direction in the design field. With the continuous development of big data technology, more and more application scenarios have begun to use big data technology, such as image recognition and natural language processing. The emergence of these application scenarios has brought new opportunities for image design and provided a broader application space for image design.

[0003] After searching, the invention patent with publication number CN113032598A discloses an image design visual communication system based on big data, including: a client, which is used to assist users in the development of relevant system structures, and can be connected to the data transmission server by simply filling in parameters and calling functions; a design module, which is used to call the design object image from the object database as a basis, and call the corresponding design material from the material database to design in the target object image, and obtain the corresponding design effect diagram. The present invention can perform visual design and communication on images, and can be used for on-site design and effect display, which meets the daily design needs of designers and design teams. In addition, multiple security encryption mechanisms are also used in big data transmission. Manual configuration of file fragmentation can be performed at the sending end, and the server adopts an instant forwarding strategy, that is, the server receives the file fragmentation information without integration, and directly pushes it to the receiving end. The server records the file transmission, and the receiving end integrates the files.

[0004] However, compared with the prior art, in the process of image design, the use of object database and material database cannot effectively identify the latest design trends, and cannot grasp the user's acceptance of design trends and design styles, which leads to a large amount of feedback and communication in the image design process, thereby reducing the efficiency and accuracy of image design. Therefore, how to improve the efficiency and accuracy of image design is a problem we need to solve. To this end, a big data-based image design visual communication system and method are provided. Summary of the invention

[0005] In order to solve the above technical problems, the purpose of the present invention is to provide an image design visual communication system and method based on big data.

[0006] The object of the present invention can be achieved by the following technical solutions: an image design visual communication system based on big data, comprising an image design platform, wherein the image design platform is provided with a data acquisition module, a user analysis module, a design analysis module, a framework analysis module, a collaborative adjustment module and a design feedback module;

[0007] The data acquisition module is used to collect image data information, user data information and design data information, and send the acquired data information to other modules for analysis and processing respectively;

[0008] The user analysis module is used to obtain user data information, construct a user portrait of the corresponding user according to the user data information, and update and store the user portrait;

[0009] The design analysis module is used to obtain image data information, perform feature extraction on the image data information, obtain image element information, set a visual element database according to the image element information, and obtain design trend data according to changes in element proportion data in the visual element database;

[0010] The framework analysis module is used to obtain design data information, obtain design purposes according to the design data information, build a corresponding framework analysis decision chain according to the design purposes, perform design analysis on image areas and functions in sequence according to the framework analysis decision chain, and obtain an initial design image;

[0011] The collaborative adjustment module is used to obtain an initial design image, design trend data and a user portrait, and collaboratively adjust the initial design image according to the design trend data and the user portrait to generate a collaborative design image;

[0012] The design feedback module is used for the corresponding design user to obtain the collaborative design image, and to make feedback adjustments to the corresponding collaborative design image, repeat the operations of other modules, and output the corresponding visual communication image.

[0013] Furthermore, the process of collecting data information by the data collection module includes:

[0014] Setting up an image acquisition unit, a user acquisition unit and a design acquisition unit;

[0015] The image acquisition unit is provided with an image public data source, and the image public data source is monitored in real time based on the big data retrieval technology to obtain the corresponding image data information;

[0016] The user acquisition unit is provided with a feature image library, which obtains user information of the image design platform, obtains the corresponding preference image test questionnaire in the feature image library based on the user information, and the user answers the preference image test questionnaire, and the answer process and the preference image test answer sheet obtained after the answer are completed are combined with the user information to generate corresponding user data information;

[0017] The design data unit is used for corresponding users to submit design requirement information, wherein the design requirement information includes design type, design keywords, design style preference and design purpose; the obtained design requirement information is marked according to the corresponding users to generate corresponding design data information.

[0018] Furthermore, the process of the user analysis module constructing the user portrait of the corresponding user includes:

[0019] Obtain the corresponding preferred image test answer sheet in the user data information, analyze and process the obtained preferred image test answer sheet content, obtain the user's selection result, and generate a corresponding presentation image layer according to the selection result;

[0020] The answering process of the preference image test paper is obtained, and the user's stay time during the answering process is analyzed and processed to generate a corresponding hidden portrait layer;

[0021] The obtained hidden portrait layer and the presented portrait layer are fused and rendered to construct a user portrait of the corresponding user, and the user portrait is stored.

[0022] Furthermore, the process of the design analysis module acquiring image data information and setting up a visual element database includes:

[0023] Acquire image data information, perform image preprocessing on the acquired image data information, perform feature extraction on the corresponding image data information according to the image preprocessing result, acquire element information in each image data information, analyze the corresponding element information based on a semantic analysis algorithm, and acquire label semantic information and description semantic information corresponding to the element information;

[0024] Build element sub-libraries respectively according to the tag semantic information corresponding to the element information, wherein the element sub-libraries are used to store the element information corresponding to the tag semantic information, and mark and store each element information in the element sub-library according to the description semantic information;

[0025] Obtain each element sub-library in the design analysis module, integrate the obtained element sub-libraries in sequence, generate a visual element database according to the integration results, and mark the update time.

[0026] Furthermore, the process of obtaining design trend data by the design analysis module includes:

[0027] Obtain the visual element database and the corresponding tag update time, preset the trend time period according to the tag update time, obtain the element update frequency in the element sub-library within each unit time within the trend time period, and obtain the inventory change data of each element sub-library according to the change of the element update frequency;

[0028] Perform feature classification analysis on the updated content in the element sub-library in each unit time of the trend time period, set corresponding feature quantization values ​​for each element data according to the feature classification results, obtain the proportion data of each feature quantization value in the element sub-library in each unit time; obtain the corresponding element change data according to the change of the proportion data;

[0029] The inventory change data and corresponding element change data of each element sub-library in the visual element database obtained within the trend time period are marked, and corresponding design trend data are generated according to the marking results.

[0030] Furthermore, the process of obtaining the initial design image by the framework analysis module includes:

[0031] Acquire design data information, and acquire a corresponding framework analysis decision chain according to the design purpose of the design data information, wherein the framework analysis decision chain is sequentially provided with a plurality of framework analysis decision points, and the framework analysis decision points sequentially correspond to design types, style preferences, and design keywords;

[0032] The obtained design data information is input into the corresponding framework analysis decision points in sequence according to the framework analysis decision chain, and the framework analysis decision points perform superposition processing in sequence to output the corresponding initial design image, which includes area filling data, color temperature layout data and feature element data respectively. The obtained initial design image is sent to the collaborative adjustment module.

[0033] Furthermore, the process of generating the collaborative design image by the collaborative adjustment module includes:

[0034] Acquire design trend data and user portraits, perform feature analysis on the design trend data and user portraits respectively, acquire trend vectors and portrait vectors, analyze and process the obtained trend vectors and portrait vectors, acquire similarity data corresponding to the trend vectors and portrait vectors, and acquire similarity data corresponding to the trend vectors and portrait vectors and the initial design images respectively;

[0035] According to the obtained similarity data, weight factors corresponding to the design trend data and the user portrait are respectively allocated;

[0036] According to the weight factors corresponding to the design trend data and the user portraits, the corresponding elements in the initial design image are collaboratively adjusted, and the corresponding collaborative design image is generated according to the collaborative adjustment results.

[0037] Furthermore, the process of designing the feedback module to output the visual communication image includes:

[0038] The obtained collaborative design image is sent to the corresponding design user, and the design user makes feedback and adjustments to the obtained collaborative design image;

[0039] The design user chooses to directly output the corresponding visual communication image or generate feedback adjustment information based on the feedback adjustment result, sends the feedback adjustment information to the framework analysis module and the collaborative adjustment module to adjust the collaborative design image, and outputs the corresponding visual communication image based on the adjustment result.

[0040] Furthermore, a method for visual communication of image design based on big data includes the following steps:

[0041] Step 1: Setting up an image design platform, and collecting image data information, user data information and design data information through the image design platform;

[0042] Step 2: construct a user portrait of the corresponding user based on the obtained user data information, perform feature extraction on the obtained image data information, obtain image element information, and construct a visual element database, and obtain design trend data based on the visual element database;

[0043] Step 3: Obtain the corresponding design type according to the design data information, build the corresponding framework analysis decision chain according to the design type, and use the framework analysis decision chain to perform design analysis on the image area and function in turn to obtain the initial design image;

[0044] Step 4: Obtain an initial design image, design trend data, and user portrait, and collaboratively adjust the initial design image according to the design trend data and user portrait to generate a collaborative design image;

[0045] Step 5: The user obtains the collaborative design image corresponding to the design data information, and makes feedback adjustments to the obtained collaborative design image to output a corresponding visual communication image.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] 1. In the present invention, by obtaining user information in the image design platform, setting a preference image test questionnaire according to the user information, and having the design user answer the preference image test questionnaire according to personal preference, obtaining the preference image test answer sheet and the answering process corresponding to the corresponding preference image test questionnaire, generating the hidden portrait layer and the presented portrait layer corresponding to the user according to the answering process and the answering result of the preference image test answer sheet, constructing the user portrait of the corresponding user according to the hidden portrait layer and the presented portrait layer, and constructing the user portrait through the hidden portrait layer, thereby improving the accuracy of the user portrait construction process to a certain extent;

[0048] 2. In the present invention, by classifying each element in the visual element database, setting a corresponding element sub-library, performing statistical analysis based on the inventory change data of the element sub-library and the element change data of each element, obtaining design trend data, and coordinating the obtained initial design image based on the design trend data and the user portrait, the designed image is improved to a certain extent with the preference of the design user, and the popular design trend is also combined to a certain extent, thereby improving the design efficiency in the image design process, avoiding large-scale repeated design, and connecting to the fashion trend to a certain extent;

[0049] 3. In the present invention, by setting a framework analysis decision chain, corresponding framework analysis decision points are set in sequence for the design data information submitted by the design user, and corresponding types of design data information are superimposed in sequence according to the framework analysis decision points to generate corresponding initial design images. In this process, the image design process is made more planned and coordinated. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a schematic diagram of a big data-based image design visual communication system according to an embodiment of the present application;

[0051] Figure 2 This is a schematic diagram of a method for visual communication of image design based on big data according to an embodiment of the present application. DETAILED DESCRIPTION

[0052] like Figure 1 As shown, an image design visual communication system based on big data includes an image design platform, wherein the image design platform is provided with a data acquisition module, a user analysis module, a design analysis module, a framework analysis module, a collaborative adjustment module and a design feedback module;

[0053] The data acquisition module is used to collect image data information, user data information and design data information, and send the acquired data information to other modules for analysis and processing. The specific implementation process includes:

[0054] Setting up an image acquisition unit, a user acquisition unit and a design acquisition unit;

[0055] The image acquisition unit is provided with an image public data source, and the image public data source is monitored in real time based on the big data retrieval technology to obtain the corresponding image data information, wherein:

[0056] The public image data sources are verified and permitted data collection channels, including professional design platforms, social media platforms, corporate official websites, e-commerce platforms, design magazines and other channels; a web crawler is set up based on big data retrieval technology, and a starting URL, crawling rules and collection frequency are set according to each public image data source, and corresponding image data information is obtained in sequence, and the collection time of the image data information is marked;

[0057] The user acquisition unit is used to obtain user information, which includes user registration information, user identity information and user behavior information, wherein:

[0058] User registration information includes the user's name, the user's real-name authenticated mobile phone number, and the user's ID number. Based on the user registration information, it is determined whether the corresponding user is a new user, and the user registration information is registered, and the corresponding user account is granted, and the user account is marked as a new user or an old user;

[0059] User identity information includes user age, user gender, user region, user occupation, user education level, etc.;

[0060] User behavior information includes platform usage frequency data, historical design data, etc.

[0061] A feature image library is preset, user information of the image design platform is obtained, and the corresponding preferred image test questionnaire in the feature image library is obtained based on the user information, wherein:

[0062] If the user is an old user, then obtain his user behavior information, analyze and process the user behavior information, obtain the corresponding preference image test questions in the feature image library according to the analysis and processing results, and set up a supplementary preference image test question questionnaire;

[0063] If the user is a new user, then obtain the user identity information, analyze and process the user identity information, obtain the corresponding preference image test questions in the feature image library according to the analysis and processing results, and set up a detailed preference image test question questionnaire;

[0064] The characteristic image library statistically marks the preference images corresponding to different groups of people based on a big data algorithm, and marks the preference images according to the statistical marking results;

[0065] The preference image test questions are used to analyze and test the user's aesthetic preferences. The preference image test question questionnaire includes multiple preference image test questions, wherein the number of preference image test questions in the detailed preference image test question questionnaire is greater than the number of preference image test questions in the supplementary preference image test question questionnaire;

[0066] The user answers the preference image test questionnaire, and the answer sheet of the preference image test obtained after the answering process and the user information are combined to generate corresponding user data information;

[0067] The response process includes the response time and repeated selection data for each preference image test item;

[0068] The response result includes the user's selection of each preferred image question in the preferred image question questionnaire;

[0069] The design data unit is used for corresponding users to submit design requirement information, wherein the design requirement information includes design type, design keywords, design style preference and design purpose; the obtained design requirement information is marked according to the corresponding users to generate corresponding design data information.

[0070] The user analysis module is used to obtain user data information, construct a user profile of the corresponding user according to the user data information, and update and store the user profile. The specific implementation process includes:

[0071] Obtain the corresponding preferred image test answer sheet in the user data information, analyze and process the obtained preferred image test answer sheet content, obtain the user's selection result, and generate the corresponding presentation image layer according to the selection result:

[0072] Obtaining answer sheets for the preference image test, summarizing and analyzing the answer sheets for the preference image test, and generating a response data set;

[0073] Classify the response results in the response data set to obtain a color preference subset, a style preference subset, a subject preference subset, and a composition preference subset;

[0074] Perform statistical analysis on the response results of the preference image test questions in the color preference subset, style preference subset, subject preference subset, and composition preference subset, obtain the selection frequency of the corresponding types in different subsets, sort the selection frequency of each subset, obtain the label of each subset according to the sorting result, and set the obtained label to present the portrait layer;

[0075] Conduct statistical analysis on the response process of the preference image test items in the color preference subset, style preference subset, subject preference subset, and composition preference subset, and obtain the response time and repeated selection data of the response process;

[0076] A preset response time limit is set. If the response time is less than the response time limit and the repeated selection data is 0, the preferred image question will not be analyzed or processed;

[0077] If the response time is greater than or equal to the response time limit or the repeated selection data is not 0, the selection results in the preference image test question are marked as hidden selection results, and the coefficient is selected according to the response time and repeated selection data;

[0078] According to the selection coefficient of the preferred image test question, statistical analysis is re-performed on the selection frequency of the corresponding type in each subset, the selection frequency of each subset is sorted respectively, the label of each subset is obtained according to the sorting result, and the obtained label is set as the hidden image layer;

[0079] The obtained hidden portrait layer and the presented portrait layer are fused and rendered; the hidden portrait layer is used to supplement the presented portrait layer, and the corresponding weight distribution coefficient is set according to the supplement result, and the priority of each label is sorted and adjusted according to the weight distribution coefficient, the user portrait of the corresponding user is obtained, and the user portrait is stored.

[0080] The design analysis module is used to obtain image data information, perform feature extraction on the image data information, obtain image element information, set a visual element database according to the image element information, and obtain design trend data according to the change of element proportion data in the visual element database. The specific implementation process includes:

[0081] Set up element storage unit and trend analysis unit;

[0082] The element storage unit is used to obtain image data information, perform image preprocessing on the obtained image data information, perform feature extraction on the corresponding image data information according to the image preprocessing result, obtain element information in each image data information, analyze the corresponding element information based on the semantic analysis algorithm, and obtain label semantic information and description semantic information corresponding to the element information;

[0083] The label semantic information is the label corresponding to the element color semantics, element style semantics, element body semantics and element composition semantics of the corresponding element information;

[0084] The descriptive semantic information is textual description information of the corresponding element information, including corresponding description keywords and description key words;

[0085] Build element sub-libraries respectively according to the tag semantic information corresponding to the element information, wherein the element sub-libraries are used to store the element information corresponding to the tag semantic information, and mark and store each element information in the element sub-library according to the description semantic information;

[0086] Obtain each element sub-library in the design analysis module, integrate the obtained element sub-libraries in sequence, generate a visual element database according to the integration results, and mark the update time.

[0087] The trend analysis unit is used to obtain the visual element database and the corresponding mark update time, preset the trend time period according to the mark update time, obtain the element update frequency in the element sub-library within each unit time within the trend time period, and obtain the inventory change data of each element sub-library according to the change of the element update frequency;

[0088] Perform feature classification analysis on the updated content in the element sub-library in each unit time of the trend time period, set corresponding feature quantization values ​​for each element data according to the feature classification results, obtain the proportion data of each feature quantization value in the element sub-library in each unit time; obtain the corresponding element change data according to the change of the proportion data, where:

[0089] The feature quantization values ​​respectively represent the numerical values ​​of the type element data corresponding to the corresponding feature classification results;

[0090] The inventory change data and corresponding element change data of each element sub-library in the visual element database obtained within the trend time period are marked, and corresponding design trend data are generated according to the marking results.

[0091] The framework analysis module is used to obtain design data information, obtain design purposes according to the design data information, build a corresponding framework analysis decision chain according to the design purposes, perform design analysis on image areas and functions in sequence according to the framework analysis decision chain, and obtain an initial design image. The specific implementation process includes:

[0092] Acquire design data information, and acquire a corresponding framework analysis decision chain according to the design purpose of the design data information, wherein the framework analysis decision chain is sequentially provided with a plurality of framework analysis decision points, and the framework analysis decision points sequentially correspond to design types, style preferences, and design keywords;

[0093] The obtained design data information is sequentially input into the corresponding framework analysis decision points according to the framework analysis decision chain, and the framework analysis decision points sequentially perform superposition processing to output the corresponding initial design image, where:

[0094] Obtain design data information, and input the design type corresponding to the obtained design data information into the corresponding framework analysis decision point. The design types include graphic design, UI / UX design, illustration design, product design, etc. Different design types have different design specifications and tool requirements. The tool requirements in the corresponding framework analysis decision point are obtained according to the design type;

[0095] Output the design specifications and tool requirements in the framework analysis decision point corresponding to the design type and send them to the framework analysis decision point corresponding to the style preference;

[0096] The framework analysis decision point sets the area filling data and color temperature layout data according to the design style preference; the area filling data is the filling ratio data; the color temperature layout data is the division result and color temperature data of the corresponding area filling data, and the corresponding sketch data is output and sent to the framework analysis decision point corresponding to the design keyword;

[0097] The framework analysis decision point obtains the corresponding element sub-library according to the sketch data, obtains the element information corresponding to the corresponding description semantic information in the corresponding element sub-library according to the design keyword, and sets the obtained elements into the corresponding element set;

[0098] Get each element set;

[0099] Sort and combine each element set, obtain the matching between the element set and the design keyword, sort the matching data, and obtain the corresponding visual element queue according to the sorting result of the matching data;

[0100] Fill the obtained visual element queue into the corresponding sketch data, arrange and organize the sketch data, perform color rendering adjustment on each element information in each sketch data, and output the corresponding initial design image;

[0101] The initial design image includes area filling data, color temperature layout data and feature element data, wherein the color temperature layout data and the feature element data are both replaceable data, and the replaceable data corresponding to the color temperature layout data is an adjustable range corresponding to the design style preference; the replaceable data corresponding to the feature element data is a visual element queue corresponding to each element set;

[0102] The obtained initial design image is sent to the collaborative adjustment module.

[0103] The collaborative adjustment module is used to obtain an initial design image, design trend data and a user portrait, and collaboratively adjust the initial design image according to the design trend data and the user portrait to generate a collaborative design image. The specific implementation process includes:

[0104] Acquire design trend data and user portraits, perform feature analysis on the design trend data and user portraits, and obtain trend vectors and portrait vectors, wherein the trend vectors and portrait vectors respectively include description data of different styles, elements, colors, etc.; perform feature analysis on the initial design image to obtain an initial vector;

[0105] Label the trend vector as Q U =(q u1 ,q u2 , ..., q un ); the image vector is marked as H V =(H v1 , H v2, ..., H vn ); the initial vector is marked as C U =(C w1 , C w2 , ..., C wn ), where n is the corresponding feature dimension;

[0106] The obtained trend vector and portrait vector are analyzed and processed to obtain similarity data corresponding to the trend vector and the portrait vector, and similarity data corresponding to the trend vector and the portrait vector and the initial design image, respectively. The specific implementation process includes:

[0107] The similarity data corresponding to the trend vector and the portrait vector is

[0108] The similarity data corresponding to the trend vector and the initial vector is

[0109] The similarity data corresponding to the portrait vector and the initial vector is

[0110] According to the obtained similarity data, the weight factors corresponding to the design trend data and the user portrait are respectively assigned, and the weight factors corresponding to the design trend data and the user portrait are respectively marked as Q weight and H weight ,in:

[0111] Obtain a weight function of similarity data corresponding to the trend vector and the portrait vector, and mark it as f(sim), and obtain the corresponding synergy factor β according to the weight function, β=f(sim);

[0112]

[0113] According to the weight factors corresponding to the design trend data and the user portraits, the corresponding elements in the initial design image are collaboratively adjusted, and the corresponding collaborative design image is generated according to the collaborative adjustment results.

[0114] The design feedback module is used for the corresponding design user to obtain the collaborative design image, and to make feedback adjustments to the corresponding collaborative design image, and output the corresponding visual communication image. The specific implementation process includes:

[0115] The obtained collaborative design image is sent to the corresponding design user, and the design user makes feedback and adjustments to the obtained collaborative design image;

[0116] The design user manually adjusts the collaborative design image according to personal selection, and outputs the corresponding visual communication image according to his selection;

[0117] Or generate corresponding feedback adjustment information, the feedback adjustment information includes corresponding adjustment design requirement information, input the obtained adjustment design requirement information into the corresponding framework analysis decision point in the framework analysis decision chain according to the collaborative design image for adjustment, obtain the corresponding initial feedback design image, and the collaborative adjustment module collaboratively adjusts the initial feedback design image according to the feedback adjustment information until it meets user needs, and outputs the corresponding visual communication image.

[0118] like Figure 2 As shown, a method for visual communication of image design based on big data includes the following steps:

[0119] Step 1: Setting up an image design platform, and collecting image data information, user data information and design data information through the image design platform;

[0120] Step 2: construct a user portrait of the corresponding user based on the obtained user data information, perform feature extraction on the obtained image data information, obtain image element information, and construct a visual element database, and obtain design trend data based on the visual element database;

[0121] Step 3: Obtain the corresponding design type according to the design data information, build the corresponding framework analysis decision chain according to the design type, and use the framework analysis decision chain to perform design analysis on the image area and function in turn to obtain the initial design image;

[0122] Step 4: Obtain an initial design image, design trend data, and user portrait, and collaboratively adjust the initial design image according to the design trend data and user portrait to generate a collaborative design image;

[0123] Step 5: The user obtains the collaborative design image corresponding to the design data information, and makes feedback adjustments to the obtained collaborative design image to output a corresponding visual communication image.

[0124] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An image design visual communication system based on big data, including an image design platform, characterized in that: The image design platform is provided with a data acquisition module, a user analysis module, a design analysis module, a framework analysis module, a collaborative adjustment module and a design feedback module; The data acquisition module is used to collect image data information, user data information and design data information, and send the acquired data information to other modules for analysis and processing respectively; The user analysis module is used to obtain user data information, construct a user portrait of the corresponding user according to the user data information, and update and store the user portrait; The design analysis module is used to obtain image data information, perform feature extraction on the image data information, obtain image element information, set a visual element database according to the image element information, and obtain design trend data according to changes in element proportion data in the visual element database; The framework analysis module is used to obtain design data information, obtain design purposes according to the design data information, build a corresponding framework analysis decision chain according to the design purposes, perform design analysis on image areas and functions in sequence according to the framework analysis decision chain, and obtain an initial design image; The collaborative adjustment module is used to obtain an initial design image, design trend data and a user portrait, and collaboratively adjust the initial design image according to the design trend data and the user portrait to generate a collaborative design image; The design feedback module is used for the design user to obtain the corresponding collaborative design image, perform feedback adjustment on the corresponding collaborative design image, and output the corresponding visual communication image.

2. According to the big data-based image design visual communication system of claim 1, it is characterized in that: The process of collecting data information by the data acquisition module includes: Setting up an image acquisition unit, a user acquisition unit and a design acquisition unit; The image acquisition unit is provided with an image public data source, and the image public data source is monitored in real time based on the big data retrieval technology to obtain the corresponding image data information; The user acquisition unit is provided with a feature image library, which obtains user information of the image design platform, obtains the corresponding preference image test questionnaire in the feature image library based on the user information, and the user answers the preference image test questionnaire, and the answer process and the preference image test answer sheet obtained after the answer are completed are combined with the user information to generate corresponding user data information; The design data unit is used for corresponding users to submit design requirement information, wherein the design requirement information includes design type, design keywords, design style preference and design purpose; the obtained design requirement information is marked according to the corresponding users to generate corresponding design data information.

3. The image design visual communication system based on big data according to claim 2 is characterized in that: The process of building a user profile for the corresponding user in the user analysis module includes: Obtain the corresponding preferred image test answer sheet in the user data information, analyze and process the obtained preferred image test answer sheet content, obtain the user's selection result, and generate a corresponding presentation image layer according to the selection result; The answering process of the preference image test paper is obtained, and the user's stay time during the answering process is analyzed and processed to generate a corresponding hidden portrait layer; The obtained hidden portrait layer and the presented portrait layer are fused and rendered to construct a user portrait of the corresponding user, and the user portrait is stored.

4. The image design visual communication system based on big data according to claim 3 is characterized in that: The process of designing and analyzing the module to obtain image data information and set up the visual element database includes: Acquire image data information, perform image preprocessing on the acquired image data information, perform feature extraction on the corresponding image data information according to the image preprocessing result, acquire image element information in each image data information, analyze the corresponding image element information based on a semantic analysis algorithm, and acquire label semantic information and description semantic information corresponding to the image element information; According to the label semantic information corresponding to the image element information, element sub-libraries are respectively constructed, wherein the element sub-libraries are used to store the image element information corresponding to the label semantic information, and each image element information in the element sub-library is marked and stored according to the description semantic information; Obtain each element sub-library in the design analysis module, integrate the obtained element sub-libraries in sequence, generate a visual element database according to the integration results, and mark the update time.

5. The image design visual communication system based on big data according to claim 4 is characterized in that: The process of obtaining design trend data by the design analysis module includes: Obtain the visual element database and the corresponding tag update time, preset the trend time period according to the tag update time, obtain the element update frequency in the element sub-library within each unit time within the trend time period, and obtain the inventory change data of each element sub-library according to the change of the element update frequency; Perform feature classification analysis on the updated content in the element sub-library in each unit time of the trend time period, set corresponding feature quantization values ​​for each image element data according to the feature classification results, obtain the proportion data of each feature quantization value in each unit time in the element sub-library; obtain the corresponding element change data according to the change of the proportion data; The inventory change data and corresponding element change data of each element sub-library in the visual element database obtained within the trend time period are marked, and corresponding design trend data are generated according to the marking results.

6. The image design visual communication system based on big data according to claim 5 is characterized in that: The process of obtaining the initial design image by the framework analysis module includes: Acquire design data information, and acquire a corresponding framework analysis decision chain according to the design purpose of the design data information, wherein the framework analysis decision chain is sequentially provided with a plurality of framework analysis decision points, and the framework analysis decision points sequentially correspond to design types, style preferences, and design keywords; The obtained design data information is input into the corresponding framework analysis decision points in sequence according to the framework analysis decision chain, and the framework analysis decision points perform superposition processing in sequence to output the corresponding initial design image, which includes area filling data, color temperature layout data and feature element data respectively. The obtained initial design image is sent to the collaborative adjustment module.

7. The image design visual communication system based on big data according to claim 6 is characterized in that: The process of generating collaborative design images by the collaborative adjustment module includes: Acquire design trend data and user portraits, perform feature analysis on the design trend data and user portraits respectively, acquire trend vectors and portrait vectors, analyze and process the obtained trend vectors and portrait vectors, acquire similarity data between the trend vectors and the portrait vectors, and acquire similarity data between the trend vectors and the portrait vectors and the initial design images respectively; According to the obtained similarity data, weight factors corresponding to the design trend data and the user portrait are respectively allocated; According to the weight factors corresponding to the design trend data and the user portraits, the corresponding elements in the initial design image are collaboratively adjusted, and the corresponding collaborative design image is generated according to the collaborative adjustment results.

8. The image design visual communication system based on big data according to claim 7 is characterized in that: The process of designing the visual communication image output by the feedback module includes: The obtained collaborative design image is sent to a corresponding user, and the user makes feedback and adjustments to the obtained collaborative design image; The user chooses to directly output the corresponding visual communication image or generate feedback adjustment information according to the feedback adjustment result, sends the feedback adjustment information to the framework analysis module and the collaborative adjustment module to adjust the collaborative design image, and outputs the corresponding visual communication image according to the adjustment result.

9. A method for visual communication of image design based on big data, characterized in that: The following steps are involved: Step 1: Setting up an image design platform, and collecting image data information, user data information and design data information through the image design platform; Step 2: construct a user portrait of the corresponding user based on the obtained user data information, perform feature extraction on the obtained image data information, obtain image element information, and construct a visual element database, and obtain design trend data based on the visual element database; Step 3: Obtain the corresponding design type according to the design data information, build the corresponding framework analysis decision chain according to the design type, and use the framework analysis decision chain to perform design analysis on the image area and function in turn to obtain the initial design image; Step 4: Obtain an initial design image, design trend data, and user portrait, and collaboratively adjust the initial design image according to the design trend data and user portrait to generate a collaborative design image; Step 5: The user obtains the collaborative design image corresponding to the design data information, and makes feedback adjustments to the obtained collaborative design image to output a corresponding visual communication image.

Images