A service platform data management system and method based on artificial intelligence

Abstract

The present invention discloses a service platform data management system and method based on artificial intelligence, which relates to the technical field of service platform data management. The present invention comprises the following steps: S10: analyzing the design quantitative feature data of each implementation design sub-idea; S20: extracting the user's design learning interaction elements; S30: analyzing the correlation between the extracted design learning interaction elements and each teaching video uploaded to and stored in the education service platform; S40: the education service platform pushes the matching teaching video to the user terminal display interface. The present invention analyzes the fluctuation of the user's understanding of the execution of each design style and design space feature by using the design quantitative feature data of each implementation design sub-idea for upload, and extracts the user's design learning interaction elements based on the user's preference for each type of implementation design sub-idea. Based on the extracted content, the present invention can also find weaknesses that the user has not discovered.

Description

Technical Field

[0001] The present invention relates to the technical field of service platform data management, and in particular to a service platform data management system and method based on artificial intelligence. Background Art

[0002] The education service platform has played an important role in the integration and sharing of educational resources, teaching support, policy publicity and supervision, and international development, and has promoted the innovation and development of education.

[0003] Educational service platforms cover a variety of teaching videos. The selection of teaching videos usually relies on keyword searches to narrow the selection range. The number of teaching videos obtained by users through keyword searches is large and the accuracy is low. At the same time, potential weaknesses that users cannot detect cannot be improved through teaching videos. Summary of the Invention

[0004] The purpose of the present invention is to provide a service platform data management system and method based on artificial intelligence to solve the problems raised in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a service platform data management method based on artificial intelligence, the method comprising:

[0006] S10: Acquire the basic data of design ideas and the implementation data of design ideas uploaded by users to the education service platform, and analyze the design quantitative feature data of each implemented design sub-idea based on the implementation status of each design sub-idea by the user;

[0007] S20: Predicting the user's learning index for various design styles and design space features based on the design quantitative feature data of each implemented design sub-idea, and extracting the user's design learning interaction factors based on the prediction results;

[0008] S30: analyzing the correlation between the extracted design learning interaction elements and the teaching videos uploaded to and stored in the education service platform;

[0009] S40: The education service platform pushes the matching teaching video to the user terminal display interface based on the analysis results.

[0010] Furthermore, the S10 includes:

[0011] S101: Acquire basic data of design ideas and implementation data of design ideas uploaded by users to the education service platform;

[0012] The basic data of design ideas include the user's basic textual description of each design sub-idea, the user's textual description of the design style of each design sub-idea, and the user's textual description of the spatial characteristics of each design sub-idea;

[0013] Design idea implementation data includes the degree of implementation of each design sub-idea by users, a textual description of the design style corresponding to each implemented design sub-idea, and a textual description of the spatial features of each implemented design sub-idea. Implementation degree = the number of design features implemented by users in a design sub-idea / the total number of design features in a design sub-idea.

[0014] S102: Design quantitative feature data includes the user's quantitative features of innovation difficulty, satisfaction, and iteration for each implemented design sub-idea;

[0015] The basic text descriptions of each implementation sub-idea uploaded by the user to the education service platform are numbered, and the numbering results are: i=1,2,…,n; n represents the total number of numbers; in the design database, the number of design works similar to the implementation design sub-idea with the number i uploaded by the user is f i , and the average score g of the professional technical review on the design works similar to the implementation design sub-idea numbered i i To obtain;

[0016] According to C i =L i *α+[1-exp(-f i )]*β quantifies the characteristic value C of the innovation difficulty of implementing the design sub-idea numbered i i Calculate, where L i represents the implementation degree of the design sub-idea numbered i, α and β are weight coefficients and α + β = 1, exp() represents the exponential function with base e and e = 2.73;

[0017] The satisfaction quantified eigenvalue M of the implementation design sub-idea numbered i i =1-exp(-g i );

[0018] The iterative quantified eigenvalue D of the implementation design sub-idea numbered i i =1-exp(-s i ), where s iRepresents the number of times a user has drawn a sub-idea numbered i. By analyzing a user's design ideas based on three aspects: user innovation difficulty, external satisfaction with the design idea, and user iteration, this helps analyze the user's understanding of the implementation of the design idea. Compared to directly analyzing the user's understanding of the implementation of the design idea based on text descriptions or images similar to the design idea's text description or the corresponding image, this method preserves the user's design style.

[0019] Furthermore, the specific method of extracting the user's design learning interaction elements for each implementation of the design sub-idea in S20 is:

[0020] Based on the textual description of the design style and the textual description of the spatial characteristics of each implemented design sub-idea, each implemented design sub-idea is classified and processed to obtain a number of classification subsets; each classification subset is numbered, and the numbering result is: j = 1, 2, ..., v; v represents the total number of classification subsets obtained; each implemented design sub-idea stored in the classification subset is renumbered, and the numbering result is: p = 1, 2, ..., q; q represents the total number of implemented design sub-ideas stored in the classification subset;

[0021] Quantify the characteristic value C of the innovation difficulty of implementing the design sub-idea p stored in the classification subset j jp , satisfying the metric eigenvalue M jp and iterative quantized eigenvalue D jp To obtain;

[0022] According to the calculation method of the average value, the average value C´ of the innovation difficulty quantitative feature corresponding to the classification subset j is calculated. jp , satisfying the quantified feature average value M´ jp and the iterative quantized feature average D´ jp Calculate; according to the abnormal value = standard deviation / average value, the innovation difficulty quantitative characteristic abnormal value c corresponding to the classification subset j is calculated. j , satisfy the quantitative characteristic change value m j and iterative quantization characteristic change value d j Perform calculations;

[0023] C´ jp The reciprocal of is the base, c j The innovation fluctuation index of the design style and design space characteristics corresponding to the user classification subset j is calculated. With 1-exp (-q j ) is calculated by multiplying the product between them to obtain the innovation difficulty quantitative feature learning coefficient c´ corresponding to the classification subset j j ;

[0024] Similarly: According to With 1-exp (-q j ), the product of the quantized feature learning coefficient m´ corresponding to the classification subset j j to calculate; according to With 1-exp (-q j ), the product of the iterative quantized feature learning coefficient d´ corresponding to the classification subset j j Perform calculations;

[0025] By calculating feature variance and feature averages, we analyze fluctuations in users' understanding of various design styles and design space features. Combined with users' preferences for various design ideas, we analyze their learning potential for each design style and design space feature. Compared to educational service platforms that directly filter educational videos based on user-uploaded keywords, this platform not only accurately meets user needs but can also identify weaknesses that users haven't yet discovered.

[0026] According to K j =c´ j *u1+m´ j *u2+d´ j *u3 calculates the learning index of the design style and design space characteristics corresponding to the user's classification subset j, and maxK j The design style and design space characteristics corresponding to the corresponding classification subset are used as the user's design learning interaction elements, where u1, u2, and u3 all represent influence coefficients and u1+u2+u3=1.

[0027] Furthermore, the S30 includes:

[0028] S301: extracting key slice videos from teaching videos stored in the education service platform. The specific extraction method is as follows: randomly selecting a teaching video in the education service platform, marking the time data of the teaching video with the dimensions of theoretical explanation, visual case, innovation analysis, and comparative analysis, obtaining a first key slice video based on the time data of the teaching video marked by the theoretical explanation dimension, obtaining a second key slice video based on the time data of the teaching video marked by the visual case dimension, obtaining a third key slice video based on the time data of the teaching video marked by the innovation analysis dimension, and obtaining a fourth key slice video based on the time data of the teaching video marked by the comparative analysis dimension;

[0029] Traverse all teaching videos in the education service platform and extract the first key slice video, the second key slice video, the third key slice video and the fourth key slice video in each teaching video;

[0030] S302: Comparing the definitions of design style and design space features in the first key slice video of each teaching video with the extracted design learning interaction elements. If the comparison is successful, the corresponding teaching video is retained; if the comparison is unsuccessful, the corresponding teaching video is not retained;

[0031] Obtaining the learning time periods of the second key slice video, the third key slice video, and the fourth key slice video in each retained teaching video for each historical user, and determining the concentrated learning time periods of the second key slice video, the third key slice video, and the fourth key slice video in each retained teaching video for each historical user;

[0032] S303: Numbering the retained teaching videos, the numbering result is: x=1,2,…,X; X represents the total number of retained teaching videos, and the historical user's concentrated learning time t for the second key slice video in the teaching video x 2x The learning time T corresponding to the second key slice video in the teaching video x 2x The ratio Y 2x Calculate according to F x =m´ r *Y 2x +c´ r *Y 3x +d´ r *Y 4x The correlation coefficient between the extracted design learning interaction elements and the teaching video x is calculated, where Y 3x is the historical user's concentrated learning time t for the third key slice video in the teaching video x 3x The learning time T corresponding to the third key slice video in the teaching video x 3x The ratio between 4x is the historical user's concentrated learning time t for the fourth key slice video in the teaching video x 4x The learning time T corresponding to the fourth key slice video in the teaching video x 4x By multi-dimensionally labeling the teaching videos and obtaining several key slice videos, combined with historical user learning of each key slice video, the correlation between the teaching videos and the extracted design learning interaction elements is analyzed, and classified comparison is performed, further improving the accuracy of finding matching teaching videos.

[0033] Furthermore, the S40 includes:

[0034] maxF xThe corresponding number is determined, and the determined number is y, y=1,2,…,X and y≠x, then the teaching video y is called the user's matching teaching video, and the education service platform pushes the teaching video y to the user terminal display interface.

[0035] An artificial intelligence-based service platform data management system, comprising a design data acquisition module, a design quantitative feature analysis module, a learning coefficient prediction module, a design learning interaction element extraction module, a correlation analysis module, and an education service platform management module;

[0036] The design data acquisition module is used to acquire the basic data of design ideas and the implementation data of design ideas uploaded by users to the education service platform;

[0037] The design quantitative feature analysis module analyzes the design quantitative feature data of each implemented design sub-idea based on the user's implementation of each design sub-idea;

[0038] The design learning interaction element extraction module is used to extract the user's design learning interaction elements based on the design quantitative feature data of each implemented design sub-idea;

[0039] The association analysis module is used to analyze the association between the extracted design learning interaction elements and the teaching videos uploaded to the education service platform;

[0040] The education service platform management module is used to push the matching teaching videos to the user terminal display interface.

[0041] Furthermore, the design quantitative feature analysis module includes an innovation difficulty quantitative feature analysis unit, a satisfaction quantification feature analysis unit and an iteration quantitative feature analysis unit;

[0042] The innovation difficulty quantitative characteristic analysis unit calculates the innovation difficulty quantitative characteristic value of each implemented design sub-idea based on the degree of implementation of each implemented design sub-idea by the user and the number of design works in the design database that are similar to each implemented design sub-idea uploaded by the user;

[0043] The satisfaction quantification feature analysis unit calculates the satisfaction quantification feature value of each implemented design sub-idea based on the average score of the design works with similar implemented design sub-ideas by professional technical review;

[0044] The iterative quantitative feature analysis unit calculates the iterative quantitative feature value of each implemented design sub-idea according to the number of times the user draws each implemented design sub-idea.

[0045] Furthermore, the learning index prediction module includes a classification unit, an anomaly value calculation unit, a learning coefficient prediction unit and a design learning interaction element extraction unit;

[0046] The classification unit classifies each implemented design sub-idea according to the design style text description and the spatial feature text description of each implemented design sub-idea, and obtains a plurality of classification subsets;

[0047] The abnormal value calculation unit calculates the innovation difficulty quantified characteristic abnormal value and the satisfaction quantified characteristic abnormal value corresponding to each classification subset according to abnormal value = standard deviation / average value. j and iteratively quantify the characteristic change value;

[0048] The learning coefficient prediction unit predicts the innovation difficulty quantization feature learning coefficient, iteration quantization feature learning coefficient and satisfaction quantization feature learning coefficient of the design style and design space characteristics corresponding to each classification subset according to the constructed mathematical model;

[0049] The design learning interaction element extraction unit extracts the user's design learning interaction elements according to the user's learning index of the design style and design space characteristics corresponding to the classification subset j.

[0050] Furthermore, the association analysis module includes a key slice video extraction unit, a teaching video screening and retention unit, and a correlation coefficient calculation unit;

[0051] The key slice video extraction unit marks the educational video time data based on the dimensions of theoretical explanation, visual case, innovation analysis and comparative analysis, and extracts the first key slice video, the second key slice video, the third key slice video and the fourth key slice video from each teaching video based on the marking results;

[0052] The teaching video screening and retention unit compares the definitions of design style and design space features in the first key slice video of each teaching video with the extracted design learning interaction elements, and based on the comparison results, screens and retains the teaching videos stored in the education service platform;

[0053] The correlation coefficient calculation unit calculates the correlation coefficient between the extracted design learning interaction elements and each teaching video according to the constructed mathematical formula.

[0054] Compared with the prior art, the present invention has the following beneficial effects:

[0055] 1. The present invention analyzes the fluctuations in users' understanding of various design styles and design space features through the design quantitative feature data of each uploaded implementation design sub-idea, and extracts the user's design learning interaction elements in combination with the user's preference for various types of implementation design sub-ideas. Based on the extracted content, it can also find weaknesses that the user has not discovered. In addition, the extracted design learning interaction elements are used as keywords to conduct a preliminary screening of teaching videos, which increases the accuracy of keywords. Compared with the existing technology, the accuracy of finding teaching videos is improved.

[0056] 2. The present invention performs multi-dimensional tagging on teaching videos and obtains multiple key slice videos. Combined with the historical user learning status of each key slice video, the present invention effectively identifies the teaching highlights in the teaching video. Combined with the learning coefficients of each quantitative feature corresponding to the extracted design learning interaction elements, the correlation coefficient between the extracted design learning interaction elements and each teaching video is calculated. Based on the calculation results, the user's matching teaching video is determined, so that the teaching video can be accurately found, and the number of teaching videos found is small, which is convenient for users to learn accurately.

[0057] 3. The present invention simplifies the complexity of analyzing teaching video data by marking and dividing the teaching video time data, which is conducive to the effective management of teaching service data by the teaching service platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a schematic diagram of the workflow of an artificial intelligence-based service platform data management method of the present invention. DETAILED DESCRIPTION

[0059] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0060] like Figure 1 As shown, the present invention provides a service platform data management system and method technical solution based on artificial intelligence, a service platform data management method based on artificial intelligence, the method comprising:

[0061] S10: Acquire the basic data of design ideas and the implementation data of design ideas uploaded by users to the education service platform, and analyze the design quantitative feature data of each implemented design sub-idea based on the implementation status of each design sub-idea by the user;

[0062] The S10 includes:

[0063] S101: Acquire basic data of design ideas and implementation data of design ideas uploaded by users to the education service platform;

[0064] The basic design idea data includes the user's basic textual description of each design sub-idea, the user's textual description of the design style of each design sub-idea (design styles include Cubism, Abstraction, and Realism), and the user's textual description of the spatial characteristics of each design sub-idea. The textual description of the spatial characteristics of the design sub-idea includes planar characteristics and depth characteristics. Planar characteristics refer to the visual characteristics and forms of expression presented in two-dimensional space (i.e., a plane). Depth characteristics refer to the spatial effects with depth and layering created by visual elements.

[0065] Design idea implementation data includes the degree of implementation of each design sub-idea by the user, the textual description of the design style corresponding to each implemented design sub-idea, and the textual description of the spatial features of each implemented design sub-idea. An implemented design sub-idea refers to a design sub-idea with an implementation degree greater than 0. The implementation degree = the number of design features in the design sub-idea that have been implemented by the user / the total number of design features in the design sub-idea. The design features are determined based on the basic textual description of each design sub-idea. For example, suppose the textual description of design sub-idea A uploaded by a user to the education service platform is: bury the chair except for the backrest and armrests in snow, and reshape the chair through the snow covering. The design features in design sub-idea A are snow, chair backrest, and chair armrests. Assuming that the design features snow and chair armrests have been implemented by the user, then the user's implementation degree of design sub-idea A = 2 / 3 = 0.67;

[0066] S102: Design quantitative feature data includes the user's quantitative features of innovation difficulty, satisfaction, and iteration for each implemented design sub-idea;

[0067] The basic text descriptions of each implementation sub-idea uploaded by the user to the education service platform are numbered, and the numbering results are: i=1,2,…,n; n represents the total number of numbers; in the design database, the number of design works similar to the implementation design sub-idea with the number i uploaded by the user is f i , and the average score g of the professional technical review on the design works similar to the implementation design sub-idea numbered i i To obtain;

[0068] According to C i =L i *α+[1-exp(-f i )]*β quantifies the characteristic value C of the innovation difficulty of implementing the design sub-idea numbered i i Calculate, where L irepresents the implementation degree of the design sub-idea numbered i, α and β are weight coefficients and α + β = 1, exp() represents the exponential function with base e and e = 2.73;

[0069] The satisfaction quantified eigenvalue M of the implementation design sub-idea numbered i i =1-exp(-g i );

[0070] The iterative quantified eigenvalue D of the implementation design sub-idea numbered i i =1-exp(-s i ), where s i Indicates the number of times the user has drawn the implemented design sub-idea numbered i;

[0071] S20: Predicting the user's learning index for various design styles and design space features based on the design quantitative feature data of each implemented design sub-idea, and extracting the user's design learning interaction factors based on the prediction results;

[0072] The specific method of S20 to extract the user's design learning interaction elements for each implementation design sub-idea is:

[0073] Based on the textual description of the design style and the textual description of the spatial characteristics of each implemented design sub-idea, each implemented design sub-idea is classified and processed to obtain a number of classification subsets. For a classification subset containing multiple implemented design sub-ideas, the textual description of the design style and the textual description of the spatial characteristics of each implemented design sub-idea stored in the classification subset are the same; each classification subset is numbered, and the numbering result is: j=1,2,…,v; v represents the total number of classification subsets obtained; each implemented design sub-idea stored in the classification subset is renumbered, and the numbering result is: p=1,2,…,q; q represents the total number of implemented design sub-ideas stored in the classification subset;

[0074] Quantify the characteristic value C of the innovation difficulty of implementing the design sub-idea p stored in the classification subset j jp , satisfying the metric eigenvalue M jp and iterative quantized eigenvalue D jp To obtain;

[0075] According to the calculation method of the average value, the average value C´ of the innovation difficulty quantitative feature corresponding to the classification subset j is calculated. jp , satisfying the quantified feature average value M´ jp and the iterative quantized feature average D´ jp The average value is calculated by dividing the sum of a set of data by the number of data, for example: M´ jp =(M´ j1 +M´ j2+…+M´ jq ) / q; According to the abnormal value = standard deviation / average value, the innovation difficulty corresponding to the classification subset j is quantitatively calculated as the abnormal value c j , satisfy the quantitative characteristic change value m j and iterative quantization characteristic change value d j The calculation is performed, where the fluctuation value of the quantitative characteristic refers to the degree of fluctuation of the quantitative characteristic value data set corresponding to the implementation design sub-idea stored in the classification subset compared to the average value of the quantitative characteristic. The calculation method of the standard deviation belongs to the existing technology;

[0076] C´ jp The reciprocal of is the base, c j The innovation fluctuation index of the design style and design space characteristics corresponding to the user classification subset j is calculated. With 1-exp (-q j ) is calculated by multiplying the product between them to obtain the innovation difficulty quantitative feature learning coefficient c´ corresponding to the classification subset j j ;

[0077] Similarly: According to With 1-exp (-q j ), the product of the quantized feature learning coefficient m´ corresponding to the classification subset j j to calculate; according to With 1-exp (-q j ), the product of the iterative quantized feature learning coefficient d´ corresponding to the classification subset j j Perform calculations;

[0078] Among them, 1-exp (-q j ) represents the user’s preference index for the design style and design space features corresponding to the classification subset j; It represents the satisfaction fluctuation index of the professional and technical review on the design style and design space characteristics corresponding to the classification subset j. Represents the iterative fluctuation index of the user's design style and design space characteristics corresponding to the classification subset j;

[0079] According to K j =c´ j *u1+m´ j *u2+d´ j *u3 calculates the learning index of the design style and design space characteristics corresponding to the user's classification subset j, and maxK j The design style and design space characteristics corresponding to the corresponding classification subset are used as the user's design learning interaction factors, where u1, u2, and u3 all represent influence coefficients and u1+u2+u3=1, K jRepresents the user's learning index of the design style and design space features corresponding to the classification subset j. The design space features include plane features and depth space features.

[0080] S30: analyzing the correlation between the extracted design learning interaction elements and the teaching videos uploaded to and stored in the education service platform;

[0081] The S30 includes:

[0082] S301: Extract key slice videos from the teaching videos stored in the education service platform. The specific extraction method is: randomly select a teaching video in the education service platform, and mark the education video time data with the dimensions of theoretical explanation (used to explain the definition and historical background of design style and design space characteristics), visual case (used to disassemble typical works), innovation analysis (used to analyze the innovative design in typical works) and comparative analysis (used to compare and analyze various design concepts with different design styles and design space characteristics). According to the education video time data marked by the theoretical explanation dimension, the first key slice video is obtained. According to the education video time data marked by the visual case dimension, the first key slice video is obtained. The second key slice video is obtained according to the educational video time data marked by the innovative analysis dimension, the third key slice video is obtained, and the fourth key slice video is obtained according to the educational video time data marked by the comparative analysis dimension; for example, the educational video time data marked with the theoretical explanation dimension are 12:00, 15:00, 16:00, and 19:00, then the first key slice video refers to the slice video with the video playback time between 12:00 and 15:00 in the teaching video and the slice video with the video playback time between 16:00 and 19:00 in the teaching video, and the learning time corresponding to the first key slice video in the teaching video is 19:00-16:00 + 15:00-12:00 = 6 minutes;

[0083] Traverse all teaching videos in the education service platform and extract the first key slice video, the second key slice video, the third key slice video and the fourth key slice video in each teaching video;

[0084] S302: Comparing the definitions of design style and design space features in the first key slice video of each teaching video with the extracted design learning interaction elements. If the comparison is successful, the corresponding teaching video is retained. If the comparison is unsuccessful, the corresponding teaching video is not retained. Successful comparison means that the definitions of design style and design space features in the first key slice video of the teaching video are the same as the definitions of the extracted design style and design space features.

[0085] Obtaining the learning time periods of the second key slice video, the third key slice video, and the fourth key slice video in each retained teaching video for each historical user, and determining the concentrated learning time periods of the second key slice video, the third key slice video, and the fourth key slice video in each retained teaching video for each historical user, wherein the concentrated learning time periods are obtained by finding the intersection of the learning time periods;

[0086] S303: Numbering the retained teaching videos, the numbering result is: x=1,2,…,X; X represents the total number of retained teaching videos, and the historical user's concentrated learning time t for the second key slice video in the teaching video x 2x The learning time T corresponding to the second key slice video in the teaching video x 2x The ratio Y 2x Calculate according to F x =m´ r *Y 2x +c´ r *Y 3x +d´ r *Y 4x The correlation coefficient between the extracted design learning interaction elements and the teaching video x is calculated, where Y 3x is the historical user's concentrated learning time t for the third key slice video in the teaching video x 3x The learning time T corresponding to the third key slice video in the teaching video x 3x The ratio between 4x is the historical user's concentrated learning time t for the fourth key slice video in the teaching video x 4x The learning time T corresponding to the fourth key slice video in the teaching video x 4x The ratio between r 、c´ r 、d´ r Represent maxK respectively j The corresponding classification subsets correspond to the satisfaction quantization feature learning coefficient, innovation difficulty quantization feature learning coefficient, and iteration quantization feature learning coefficient;

[0087] S40: The education service platform pushes the matching teaching video to the user terminal display interface based on the analysis results;

[0088] S40 includes:

[0089] maxF x The corresponding number is determined, and the determined number is y, y=1,2,…,X and y≠x, then the teaching video y is called the user's matching teaching video, and the education service platform pushes the teaching video y to the user terminal display interface.

[0090] An artificial intelligence-based service platform data management system, the system includes a design data acquisition module, a design quantitative feature analysis module, a learning coefficient prediction module, a design learning interaction element extraction module, a correlation analysis module and an education service platform management module;

[0091] The design data acquisition module is used to acquire the basic data of design ideas and the implementation data of design ideas uploaded by users to the education service platform;

[0092] The design quantitative feature analysis module analyzes the design quantitative feature data of each implemented design sub-idea based on the user's implementation of each design sub-idea;

[0093] The design quantitative feature analysis module includes the innovation difficulty quantitative feature analysis unit, the satisfaction quantification feature analysis unit and the iteration quantitative feature analysis unit;

[0094] The innovation difficulty quantitative characteristic analysis unit calculates the innovation difficulty quantitative characteristic value of each implemented design sub-idea based on the degree of implementation of each implemented design sub-idea by the user and the number of design works in the design database that are similar to each implemented design sub-idea uploaded by the user;

[0095] The satisfaction quantitative characteristic analysis unit calculates the satisfaction quantitative characteristic value of each implemented design sub-idea based on the average score of the professional technical review of the design works with similar implemented design sub-ideas;

[0096] The iterative quantitative feature analysis unit calculates the iterative quantitative feature value of each implemented design sub-idea according to the number of times the user draws each implemented design sub-idea;

[0097] The design learning interaction element extraction module is used to extract the user's design learning interaction elements based on the design quantitative feature data of each implemented design sub-idea;

[0098] The learning index prediction module includes a classification unit, an abnormal value calculation unit, a learning coefficient prediction unit, and a design learning interaction factor extraction unit;

[0099] The classification unit classifies each implemented design sub-idea according to the design style text description and the spatial feature text description of each implemented design sub-idea, and obtains a plurality of classification subsets;

[0100] The abnormal value calculation unit calculates the abnormal value of innovation difficulty corresponding to each classification subset and the abnormal value of satisfaction quantification feature according to abnormal value = standard deviation / average value. j and iteratively quantify the characteristic change value;

[0101] The learning coefficient prediction unit predicts the innovation difficulty quantization feature learning coefficient, iteration quantization feature learning coefficient and satisfaction quantization feature learning coefficient of the design style and design space characteristics corresponding to each classification subset based on the constructed mathematical model;

[0102] The design learning interaction element extraction unit extracts the user's design learning interaction elements according to the user's learning index of the design style and design space characteristics corresponding to the classification subset j;

[0103] The association analysis module is used to analyze the association between the extracted design learning interaction elements and the teaching videos uploaded to the education service platform;

[0104] The correlation analysis module includes a key slice video extraction unit, a teaching video screening and retention unit, and a correlation coefficient calculation unit;

[0105] The key slice video extraction unit labels the educational video time data based on the dimensions of theoretical explanation, visual case, innovation analysis, and comparative analysis. Based on the labeling results, the first key slice video, second key slice video, third key slice video, and fourth key slice video are extracted from each teaching video.

[0106] The teaching video screening and retention unit compares the definitions of design style and design space characteristics in the first key slice video of each teaching video with the extracted design learning interaction elements. Based on the comparison results, the teaching videos stored in the education service platform are screened and retained;

[0107] The correlation coefficient calculation unit calculates the correlation coefficient between the extracted design learning interaction elements and each teaching video according to the constructed mathematical formula;

[0108] The education service platform management module is used to push matching teaching videos to the user terminal display interface.

[0109] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A service platform data management method based on artificial intelligence, characterized by: The method comprises: S10: Acquire the basic data of design ideas and the implementation data of design ideas uploaded by users to the education service platform, and analyze the design quantitative feature data of each implemented design sub-idea based on the implementation status of each design sub-idea by the user; S20: Based on the design quantitative feature data of each implemented design sub-idea, predict the user's learning index for various design styles and design space features. Based on the prediction results, extract the user's design learning interaction factors. The specific method is as follows: Based on the textual description of the design style and the textual description of the spatial characteristics of each implemented design sub-idea, each implemented design sub-idea is classified and processed to obtain a number of classification subsets; each classification subset is numbered, and the numbering result is: j = 1, 2, ..., v; v represents the total number of classification subsets obtained; each implemented design sub-idea stored in the classification subset is renumbered, and the numbering result is: p = 1, 2, ..., q; q represents the total number of implemented design sub-ideas stored in the classification subset; Quantify the characteristic value C of the innovation difficulty of implementing the design sub-idea p stored in the classification subset j jp , satisfying the metric eigenvalue M jp and iterative quantized eigenvalue D jp To obtain; The satisfaction quantified characteristic value is determined by the average score of the professional technical review on the design works similar to the implemented design sub-idea; The iterative quantization characteristic value is determined by the number of times the user draws to implement the design sub-idea; According to the calculation method of the average value, the average value C´ of the innovation difficulty quantitative feature corresponding to the classification subset j is calculated. jp , satisfying the quantified feature average value M´ jp and the iterative quantized feature average D´ jp Calculate; according to the abnormal value = standard deviation / average value, the innovation difficulty quantitative characteristic abnormal value c corresponding to the classification subset j is calculated. j , satisfy the quantitative characteristic change value m j and iterative quantization characteristic change value d j Perform calculations; C´ jp The reciprocal of is the base, c j The innovation fluctuation index of the design style and design space characteristics corresponding to the user classification subset j is calculated. With 1-exp (-q j ) is calculated by multiplying the product between them to obtain the innovation difficulty quantitative feature learning coefficient c´ corresponding to the classification subset j j ; Similarly: According to With 1-exp (-q j ), the product of the quantized feature learning coefficient m´ corresponding to the classification subset j j to calculate; according to With 1-exp (-q j ), the product of the iterative quantized feature learning coefficient d´ corresponding to the classification subset j j Perform calculations; According to K j =c´ j *u1+m´ j *u2+d´ j *u3 calculates the learning index of the design style and design space characteristics corresponding to the user's classification subset j, and maxK j The design style and design space characteristics corresponding to the corresponding classification subset are used as the user's design learning interaction factors, where u1, u2, and u3 all represent influence coefficients and u1+u2+u3=1; S30: analyzing the correlation between the extracted design learning interaction elements and the teaching videos uploaded to and stored in the education service platform; S40: The education service platform pushes the matching teaching video to the user terminal display interface based on the analysis results.

2. The artificial intelligence-based service platform data management method according to claim 1, characterized in that: The S10 includes: S101: Acquire basic data of design ideas and implementation data of design ideas uploaded by users to the education service platform; The basic data of design ideas include the user's basic textual description of each design sub-idea, the user's textual description of the design style of each design sub-idea, and the user's textual description of the spatial characteristics of each design sub-idea; Design idea implementation data includes the degree of implementation of each design sub-idea by users, a textual description of the design style corresponding to each implemented design sub-idea, and a textual description of the spatial features of each implemented design sub-idea. Implementation degree = the number of design features implemented by users in a design sub-idea / the total number of design features in a design sub-idea. S102: Design quantitative feature data includes the user's quantitative features of innovation difficulty, satisfaction, and iteration for each implemented design sub-idea; The basic text descriptions of each implementation sub-idea uploaded by the user to the education service platform are numbered, and the numbering results are: i=1,2,…,n; n represents the total number of numbers; in the design database, the number of design works similar to the implementation design sub-idea with the number i uploaded by the user is f i , and the average score g of the professional technical review on the design works similar to the implementation design sub-idea numbered i i To obtain; According to C i =L i *α+[1-exp(-f i )]*β quantifies the characteristic value C of the innovation difficulty of implementing the design sub-idea numbered i i Calculate, where L i represents the implementation degree of the design sub-idea numbered i, α and β are weight coefficients and α + β = 1, exp() represents the exponential function with base e and e = 2.73; The satisfaction quantified eigenvalue M of the implementation design sub-idea numbered i i =1-exp(-g i ); The iterative quantified eigenvalue D of the implementation design sub-idea numbered i i =1-exp(-s i ), where s i Indicates the number of times the user draws the implemented design sub-idea numbered i.

3. The artificial intelligence-based service platform data management method according to claim 2, characterized in that: The S30 includes: S301: extracting key slice videos from teaching videos stored in the education service platform. The specific extraction method is as follows: randomly selecting a teaching video in the education service platform, marking the time data of the teaching video with the dimensions of theoretical explanation, visual case, innovation analysis, and comparative analysis, obtaining a first key slice video based on the time data of the teaching video marked by the theoretical explanation dimension, obtaining a second key slice video based on the time data of the teaching video marked by the visual case dimension, obtaining a third key slice video based on the time data of the teaching video marked by the innovation analysis dimension, and obtaining a fourth key slice video based on the time data of the teaching video marked by the comparative analysis dimension; Traverse all teaching videos in the education service platform and extract the first key slice video, the second key slice video, the third key slice video and the fourth key slice video in each teaching video; S302: Comparing the definitions of design style and design space features in the first key slice video of each teaching video with the extracted design learning interaction elements. If the comparison is successful, the corresponding teaching video is retained; if the comparison is unsuccessful, the corresponding teaching video is not retained; Obtaining the learning time periods of the second key slice video, the third key slice video, and the fourth key slice video in each retained teaching video for each historical user, and determining the concentrated learning time periods of the second key slice video, the third key slice video, and the fourth key slice video in each retained teaching video for each historical user; S303: Numbering the retained teaching videos, the numbering result is: x=1,2,…,X; X represents the total number of retained teaching videos, and the historical user's concentrated learning time t for the second key slice video in the teaching video x 2x The learning time T corresponding to the second key slice video in the teaching video x 2x The ratio Y 2x Calculate according to F x =m´ r *Y 2x +c´ r *Y 3x +d´ r *Y 4x The correlation coefficient between the extracted design learning interaction elements and the teaching video x is calculated, where Y 3x is the historical user's concentrated learning time t for the third key slice video in the teaching video x 3x The learning time T corresponding to the third key slice video in the teaching video x 3x The ratio between 4x is the historical user's concentrated learning time t for the fourth key slice video in the teaching video x 4x The learning time T corresponding to the fourth key slice video in the teaching video x 4x The ratio between them.

4. The artificial intelligence-based service platform data management method according to claim 3, characterized in that: The S40 includes: maxF x The corresponding number is determined, and the determined number is y, y=1,2,…,X and y≠x, then the teaching video y is called the user's matching teaching video, and the education service platform pushes the teaching video y to the user terminal display interface.

5. An artificial intelligence-based service platform data management system applied to the artificial intelligence-based service platform data management method according to any one of claims 1 to 4, characterized in that: The system includes a design data acquisition module, a design quantitative feature analysis module, a learning coefficient prediction module, a design learning interaction element extraction module, a correlation analysis module and an education service platform management module; The design data acquisition module is used to acquire the basic data of design ideas and the implementation data of design ideas uploaded by users to the education service platform; The design quantitative feature analysis module analyzes the design quantitative feature data of each implemented design sub-idea based on the user's implementation of each design sub-idea; The design learning interaction element extraction module is used to extract the user's design learning interaction elements based on the design quantitative feature data of each implemented design sub-idea; The association analysis module is used to analyze the association between the extracted design learning interaction elements and the teaching videos uploaded to the education service platform; The education service platform management module is used to push the matching teaching videos to the user terminal display interface.

6. The artificial intelligence-based service platform data management system according to claim 5, characterized in that: The design quantitative feature analysis module includes an innovation difficulty quantitative feature analysis unit, a satisfaction quantification feature analysis unit and an iteration quantitative feature analysis unit; The innovation difficulty quantitative characteristic analysis unit calculates the innovation difficulty quantitative characteristic value of each implemented design sub-idea based on the degree of implementation of each implemented design sub-idea by the user and the number of design works in the design database that are similar to each implemented design sub-idea uploaded by the user; The satisfaction quantification feature analysis unit calculates the satisfaction quantification feature value of each implemented design sub-idea based on the average score of the design works with similar implemented design sub-ideas by professional technical review; The iterative quantitative feature analysis unit calculates the iterative quantitative feature value of each implemented design sub-idea according to the number of times the user draws each implemented design sub-idea.

7. The artificial intelligence-based service platform data management system according to claim 6, characterized in that: The learning index prediction module includes a classification unit, an abnormal value calculation unit, a learning coefficient prediction unit and a design learning interaction element extraction unit; The classification unit classifies each implemented design sub-idea according to the design style text description and the spatial feature text description of each implemented design sub-idea, and obtains a plurality of classification subsets; The abnormal value calculation unit calculates the innovation difficulty quantified characteristic abnormal value and the satisfaction quantified characteristic abnormal value corresponding to each classification subset according to abnormal value = standard deviation / average value. j and iteratively quantify the characteristic change value; The learning coefficient prediction unit predicts the innovation difficulty quantization feature learning coefficient, iteration quantization feature learning coefficient and satisfaction quantization feature learning coefficient of the design style and design space characteristics corresponding to each classification subset according to the constructed mathematical model; The design learning interaction element extraction unit extracts the user's design learning interaction elements according to the user's learning index of the design style and design space characteristics corresponding to the classification subset j.

8. The artificial intelligence-based service platform data management system according to claim 7, characterized in that: The association analysis module includes a key slice video extraction unit, a teaching video screening and retention unit, and a correlation coefficient calculation unit; The key slice video extraction unit marks the educational video time data based on the dimensions of theoretical explanation, visual case, innovation analysis and comparative analysis, and extracts the first key slice video, the second key slice video, the third key slice video and the fourth key slice video from each teaching video based on the marking results; The teaching video screening and retention unit compares the definitions of design style and design space features in the first key slice video of each teaching video with the extracted design learning interaction elements, and based on the comparison results, screens and retains the teaching videos stored in the education service platform; The correlation coefficient calculation unit calculates the correlation coefficient between the extracted design learning interaction elements and each teaching video according to the constructed mathematical formula.

Images