A data intelligent management system and method based on user portrait

Abstract

The application discloses a kind of data intelligent management system and method based on user portrait, it is related to data management technical field, including: obtaining the occupation of user and template selection record, establish the user portrait of user, obtain the matching degree of each design template, design template is recommended to user according to matching degree;Corresponding mark template is obtained to user, mark template and user portrait are analyzed, and mark user in template resource platform is extracted;The attribute feature corresponding to each template is obtained, and the key word in feature word is extracted, and the key word set corresponding to mark user is established based on key word;Template preference survey is carried out to user, and the user portrait of user is reestablished, and design template is recommended to user.The application reestablishes user portrait for user by combining the historical selection record of user and combining the individual factor of user, can accurately recommend suitable design template for user, and the reliability of template recommendation is improved.

Description

A data intelligence management system and method based on user profiles Technical Field

[0001] This invention relates to the field of data management technology, specifically a data intelligent management system and method based on user profiles. Background Technology

[0002] User personas are virtual user models with typical characteristics, typically abstracted by integrating various types of user data. Based on data, they extract tags such as core user attributes, behavioral patterns, and needs and preferences to help enterprises or product teams quickly understand target users and provide accurate basis for decision-making. Currently, when recommending design templates to target users, such as resumes and electronic business cards, user personas are usually built based on the target user's industry or occupation characteristics and historical selection records, and simple similar recommendations are made. However, the individual factors of the target user, such as style preferences and personal tastes, are not taken into account. As a result, the construction of user personas ignores the individual factors of the target user, and it is impossible to accurately recommend suitable design templates to the target user, making the recommended information unreliable. Summary of the Invention

[0003] The purpose of this invention is to provide a data intelligent management system and method based on user profiles to solve the problems raised in the prior art.

[0004] To achieve the above objectives, the present invention provides the following technical solution:

[0005] A data intelligence management method based on user profiles includes the following steps:

[0006] Step S100: Obtain the user's occupation and template selection records, extract the attribute features of the corresponding design templates in the template selection records, build a user profile based on the occupation and attribute features, obtain the matching degree of each design template to the user based on the user profile, and recommend design templates to the user according to the matching degree.

[0007] Step S200: Based on the user's actions on the template resource platform, obtain the user's corresponding tag template; and analyze the tag template and user profile to extract the tag users from the template resource platform;

[0008] Step S300: Based on the design templates that marked users like and dislike on the template resource platform, and the corresponding marked templates, obtain the feature words corresponding to the attribute features of each template; and obtain the user's bias and deviation from the feature words, then extract the keywords in the feature words, and establish a keyword set corresponding to the marked users based on the keywords;

[0009] Step S400: Conduct a template preference survey on users. Based on the user's previous user profile, as well as the survey results and keyword set, reconstruct the user's user profile and recommend design templates to the user according to the reconstructed user profile.

[0010] Furthermore, step S100 includes:

[0011] Step S110: Obtain all design templates corresponding to the user's template selection record, extract the attribute features of each design template, including style, theme, applicable profession, and applicable scenario; the user's user profile corresponds to several preference tags, including style preference, theme preference, profession preference, and scenario preference; summarize all feature words corresponding to each attribute feature in the template selection record, obtain the quantity corresponding to each feature word, and use the feature words with a quantity greater than a preset quantity threshold as the tag words in the user's corresponding preference tag; then obtain all tag words corresponding to each preference tag in the user's user profile, and set the initial word weight of each tag word to 1;

[0012] Step S120: Obtain the feature word W of a certain attribute feature d corresponding to a certain design template T in the template resource platform. d Extract all tag words under the preference label corresponding to attribute feature d in the user profile, and match a certain tag word L with the feature word W. d The similarity between the two is multiplied by the word weight of the tag word L to obtain the pair of tag word L and feature word W. d The relevance is then calculated, and the relevance of each tag is obtained. The maximum relevance is taken as the degree of relevance R between attribute feature d and user profile. d Then, the correlation between each attribute feature in the design template T and the user profile is obtained, and the weights corresponding to each attribute feature are pre-set to obtain the matching degree of the design template T with the user. The design templates are then recommended to the user in descending order of matching degree.

[0013] Furthermore, step S200 includes:

[0014] Step S210: The template resource platform has the function of users searching and filtering design templates; the design template recommended in step S100 is used as the recommended template. If a user U selects a design template A using any of the search or filtering functions on the template resource platform and modifies all the required fields in all editable content on design template A, and the required fields are the user's personal information, and design template A is not a recommended template, then design template A is used as the marked template, and all marked templates are obtained.

[0015] Step S220: Obtain all attribute features of a certain tag template B and the user profile of the current user. Based on all the tag words under the preference tag, and analogous to step S120, obtain the matching degree of tag template B to the user. Then obtain the matching degree of each tag template to the user and add them up to calculate the average value. If the average value is less than the preset numerical threshold, then user U is designated as the tag user.

[0016] Furthermore, step S300 includes:

[0017] Step S310: The template resource platform has the function of marking users' likes and dislikes for design templates; obtain all the design templates and corresponding marked templates that a user V likes, and extract the feature words corresponding to the attribute features of each template as the bias feature words of user V. Statistically summarize the same bias feature words to obtain the quantity corresponding to each bias feature word, and then obtain the degree of bias of user V towards a certain bias feature word i: X=1- Where e is the natural constant, K1 is the bias coefficient, and N i The number of features corresponding to feature word i; and normalization is performed based on the degree of bias of each biased feature word;

[0018] Step S320: Obtain all the design templates that user V dislikes, and extract the feature words corresponding to the attribute features of each template as the deviation feature words of user V. Statistically summarize the same deviation feature words to obtain the quantity corresponding to each deviation feature word, and then obtain the degree of deviation of user V from a certain deviation feature word j as: Y = -(1- ), where e is the natural constant, K2 is the deviation coefficient, and N j The number of features corresponding to feature word j; normalization is performed based on the deviation of each feature word;

[0019] Step S330: If a feature word h is not simultaneously a biased feature word and a deviated feature word, then feature word h is taken as a keyword; if a feature word h is simultaneously a biased feature word and a deviated feature word, then the bias degree X after normalization of feature word h is used as the keyword. h And the degree of deviation Y h The feature degree Z of feature word h is obtained. h =X h -|Y h To find the absolute value, if |Z h If the value is greater than a preset threshold, then the feature word h will be used as a keyword; and a keyword set for user V will be established based on all of user V's keywords.

[0020] Because the formula y=1-e -xWhen x takes the value x≥0, y takes the value [0,1), and is a function of y increasing as x increases. In this scheme, the bias coefficients K1 and K2 are both not less than 0. Since N i and N j This refers to the quantity, which is not less than 0. Therefore, the bias X ranges from 0 to 1, and the deviation Y ranges from -1 to 0. The feature degree Z of feature word h... h The value of Z ranges from -1 to 1. h A value close to -1 indicates that the user's deviation from the feature word h is relatively large (bias degree X). h Smaller, degree of deviation Y h absolute value | Y h |larger), similarly, when Z h When the value is close to 1, it indicates that the user has a relatively high degree of bias towards the feature word h. The following step S400, which uses the feature degree as the word weight, is reasonable and in line with the expectations of this scheme.

[0021] Here, we use the condition |Z h The reason for using keywords with a pre-set threshold for degree is that when the degree of bias and deviation of a certain feature word are similar, it means that this feature word is irrelevant to the user. For example, if a user's profession is present in both favorite and disliked templates, then this word cannot be used as a keyword for the following decision. The keyword set is obtained based on the design templates that users like and dislike on the template resource platform. The keyword set includes styles, themes, etc. that mark user likes and dislikes, and is a set that can represent the characteristics of the marked user.

[0022] Furthermore, step S400 includes:

[0023] Step S410: Conduct a template preference survey for all users. The survey includes users' style preferences, theme preferences, occupational preferences, and scenario preferences. Set the word weight of all preference keywords in the survey to 1. If a user is not a labeled user, extract all corresponding tag words from the previous user profile. Summarize all preference keywords and all tag words in the survey to obtain the final tag words. Add the corresponding word weights. Based on the final tag words, reconstruct the user profile for that user.

[0024] Step S420: If a user is a labeled user, extract all keywords from the user's keyword set, and use the feature degree corresponding to the keyword as the keyword weight. Extract all corresponding tag words from the previous user profile, summarize all preference keywords and all tag words in the survey content, as well as all keywords in the keyword set, to obtain the final tag words, and add the corresponding word weights. Based on the final tag words, reconstruct the user profile of the user; and recommend design templates to the user according to the reconstructed user profile.

[0025] A data intelligence management system based on user profiles includes a user profile creation module, a user tag extraction module, a keyword set creation module, and a design template recommendation module;

[0026] User profile building module: used to obtain the user's occupation and template selection records, extract the attribute features of the corresponding design templates in the template selection records, build the user profile based on the occupation and attribute features, obtain the matching degree of each design template to the user based on the user profile, and recommend design templates to the user according to the matching degree.

[0027] User tag extraction module: This module is used to obtain the user's corresponding tag template based on the user's actions and behaviors on the template resource platform; and to analyze the tag templates and user profiles to extract the tagged users from the template resource platform.

[0028] Keyword set building module: Based on the design templates that marked users like and dislike on the template resource platform, and the corresponding marked templates, it obtains the feature words corresponding to the attribute features of each template; and obtains the degree of user bias and deviation from the feature words, thereby extracting keywords from the feature words, and building a keyword set corresponding to the marked users based on the keywords;

[0029] The design template recommendation module is used to conduct template preference surveys on users. Based on the user's previous user profile, as well as the survey results and keyword set, it reconstructs the user's user profile and recommends design templates to the user according to the reconstructed user profile.

[0030] Furthermore, the user tagging extraction module includes a tag template extraction unit and a user tagging extraction unit;

[0031] The tag template extraction unit is used to extract tag templates from the design templates based on the template resource platform's function of allowing users to search and filter design templates, as well as the recommended templates obtained.

[0032] User tag extraction unit: used to obtain all attribute features of the tag template, as well as the user profile of the current user, and obtain the tagged user based on all tag words under the preference tag.

[0033] Furthermore, the design template recommendation module includes a user profile reconstruction unit and a design template recommendation unit;

[0034] User profile reconstruction unit: used to conduct template preference surveys for all users and set word weights for all preference keywords in the survey content; extract all corresponding tag words from the user's previous user profile to obtain the final tag words, and then reconstruct the user profile for a user.

[0035] Design Template Recommendation Unit: Used to recommend design templates to users based on a newly created user profile.

[0036] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention provides a data intelligent management system and method based on user profiles, including: acquiring users' occupations and template selection records, establishing user profiles, obtaining the matching degree of each design template, and recommending design templates to users according to the matching degree; obtaining the user's corresponding tagged templates, analyzing the tagged templates and user profiles, and extracting tagged users from the template resource platform; obtaining the feature words corresponding to the attribute characteristics of each template, extracting keywords from the feature words, and establishing a keyword set corresponding to the tagged users based on the keywords; conducting a template preference survey on users, reconstructing user profiles, and recommending design templates to users. This invention, by combining users' historical selection records and user personality factors, reconstructs user profiles for users, enabling accurate recommendation of suitable design templates and improving the reliability of template recommendations. Attached Figure Description

[0037] Figure 1 is a flowchart illustrating a data intelligence management method based on user profiles according to the present invention;

[0038] Figure 2 is a structural diagram of a data intelligent management system based on user profiles according to the present invention. Detailed Implementation

[0039] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0040] Example: As shown in Figure 1, this invention provides a data intelligent management method based on user profiles, comprising the following steps:

[0041] Step S100: Obtain the user's occupation and template selection records, extract the attribute features of the corresponding design templates in the template selection records, build a user profile based on the occupation and attribute features, obtain the matching degree of each design template to the user based on the user profile, and recommend design templates to the user according to the matching degree.

[0042] Step S110: Obtain all design templates corresponding to the user's template selection record, extract the attribute features of each design template, including style, theme, applicable profession, and applicable scenario; the user's user profile corresponds to several preference tags, including style preference, theme preference, profession preference, and scenario preference; summarize all feature words corresponding to each attribute feature in the template selection record, obtain the quantity corresponding to each feature word, and use the feature words with a quantity greater than a preset quantity threshold as the tag words in the user's corresponding preference tag; then obtain all tag words corresponding to each preference tag in the user's user profile, and set the initial word weight of each tag word to 1;

[0043] Step S120: Obtain the feature word W of a certain attribute feature d corresponding to a certain design template T in the template resource platform. d Extract all tag words under the preference label corresponding to attribute feature d in the user profile, and match a certain tag word L with the feature word W. d The similarity between the two is multiplied by the word weight of the tag word L to obtain the pair of tag word L and feature word W. d The relevance is then calculated, and the relevance of each tag is obtained. The maximum relevance is taken as the degree of relevance R between attribute feature d and user profile. d Then, the correlation between each attribute feature in the design template T and the user profile is obtained, and the weights corresponding to each attribute feature are pre-set to obtain the matching degree of the design template T with the user. The design templates are then recommended to the user in descending order of matching degree.

[0044] Step S200: Based on the user's actions on the template resource platform, obtain the user's corresponding tag template; and analyze the tag template and user profile to extract the tag users from the template resource platform;

[0045] Step S210: The template resource platform has the function of users searching and filtering design templates; the design template recommended in step S100 is used as the recommended template. If a user U selects a design template A using any of the search or filtering functions on the template resource platform and modifies all the required fields in all editable content on design template A, and the required fields are the user's personal information, and design template A is not a recommended template, then design template A is used as the marked template, and all marked templates are obtained.

[0046] Step S220: Obtain all attribute features of a certain tag template B and the user profile of the current user. Based on all the tag words under the preference tag, and analogous to step S120, obtain the matching degree of tag template B to the user. Then obtain the matching degree of each tag template to the user and add them up to calculate the average value. If the average value is less than the preset numerical threshold, then user U is designated as the tag user.

[0047] In this scheme, the personality factors are obtained based on the results of a template preference survey of users, and the results of the template preference survey are what meet the user's expectations. In this step, the marked users refer to those users whose recommended design templates do not meet their expectations. When recommending design templates for these users based on their personality factors in step S400 (that is, based on the results of the template preference survey in this scheme), their information (that is, the information related to the design template they ultimately want) should be taken into account so that a more suitable design template can be recommended to the user. For users who are not marked in step S400, since the recommended design templates meet the user's expectations, when recommending design templates based on their personality factors, only the results of the template preference survey need to be taken into account.

[0048] Step S300: Based on the design templates that marked users like and dislike on the template resource platform, and the corresponding marked templates, obtain the feature words corresponding to the attribute features of each template; and obtain the user's bias and deviation from the feature words, then extract the keywords in the feature words, and establish a keyword set corresponding to the marked users based on the keywords;

[0049] Step S310: The template resource platform has the function of marking users' likes and dislikes for design templates; obtain all the design templates and corresponding marked templates that a user V likes, and extract the feature words corresponding to the attribute features of each template as the bias feature words of user V. Statistically summarize the same bias feature words to obtain the quantity corresponding to each bias feature word, and then obtain the degree of bias of user V towards a certain bias feature word i: X=1- Where e is the natural constant, K1 is the bias coefficient, and N i The number of features corresponding to feature word i; and normalization is performed based on the degree of bias of each biased feature word;

[0050] Step S320: Obtain all the design templates that user V dislikes, and extract the feature words corresponding to the attribute features of each template as the deviation feature words of user V. Statistically summarize the same deviation feature words to obtain the quantity corresponding to each deviation feature word, and then obtain the degree of deviation of user V from a certain deviation feature word j as: Y = -(1- ), where e is the natural constant, K2 is the deviation coefficient, and N jThe number of features corresponding to feature word j; normalization is performed based on the deviation of each feature word;

[0051] Step S330: If a feature word h is not simultaneously a biased feature word and a deviated feature word, then feature word h is taken as a keyword; if a feature word h is simultaneously a biased feature word and a deviated feature word, then the bias degree X after normalization of feature word h is used as the keyword. h And the degree of deviation Y h The feature degree Z of feature word h is obtained. h =X h -|Y h To find the absolute value, if |Z h If the value is greater than a preset threshold, then the feature word h will be used as a keyword; and a keyword set for user V will be established based on all of user V's keywords.

[0052] Because the formula y=1-e -x When x takes the value x≥0, y takes the value [0,1), and is a function of y increasing as x increases. In this scheme, the bias coefficients K1 and K2 are both not less than 0. Since N i and N j This refers to the quantity, which is not less than 0. Therefore, the bias X ranges from 0 to 1, and the deviation Y ranges from -1 to 0. The feature degree Z of feature word h... h The value of Z ranges from -1 to 1. h A value close to -1 indicates that the user's deviation from the feature word h is relatively large (bias degree X). h Smaller, degree of deviation Y h absolute value | Y h |larger), similarly, when Z h When the value is close to 1, it indicates that the user has a relatively high degree of bias towards the feature word h. The following step S400, which uses the feature degree as the word weight, is reasonable and in line with the expectations of this scheme.

[0053] Step S400: Conduct a template preference survey on users. Based on the user's previous user profile, as well as the survey results and keyword set, reconstruct the user's user profile and recommend design templates to the user according to the reconstructed user profile.

[0054] Step S410: Conduct a template preference survey for all users. The survey includes users' style preferences, theme preferences, occupational preferences, and scenario preferences. Set the word weight of all preference keywords in the survey to 1. If a user is not a labeled user, extract all corresponding tag words from the previous user profile. Summarize all preference keywords and all tag words in the survey to obtain the final tag words. Add the corresponding word weights. Based on the final tag words, reconstruct the user profile for that user.

[0055] Step S420: If a user is a labeled user, extract all keywords from the user's keyword set, and use the feature degree corresponding to the keyword as the keyword weight. Extract all corresponding tag words from the previous user profile, summarize all preference keywords and all tag words in the survey content, as well as all keywords in the keyword set, to obtain the final tag words, and add the corresponding word weights. Based on the final tag words, reconstruct the user profile of the user; and recommend design templates to the user according to the reconstructed user profile.

[0056] Based on the established user profile, the matching degree is obtained based on step S100, and design templates are recommended to users in descending order of matching degree. This will not be elaborated further here.

[0057] The present invention also provides a data intelligent management system based on user profiles, as shown in Figure 2, including: a user profile building module, a user tag extraction module, a keyword set building module, and a design template recommendation module;

[0058] User profile building module: used to obtain the user's occupation and template selection records, extract the attribute features of the corresponding design templates in the template selection records, build the user profile based on the occupation and attribute features, obtain the matching degree of each design template to the user based on the user profile, and recommend design templates to the user according to the matching degree.

[0059] User tag extraction module: This module is used to obtain the user's corresponding tag template based on the user's actions and behaviors on the template resource platform; and to analyze the tag templates and user profiles to extract the tagged users from the template resource platform.

[0060] Keyword set building module: Based on the design templates that marked users like and dislike on the template resource platform, and the corresponding marked templates, it obtains the feature words corresponding to the attribute features of each template; and obtains the degree of user bias and deviation from the feature words, thereby extracting keywords from the feature words, and building a keyword set corresponding to the marked users based on the keywords;

[0061] The design template recommendation module is used to conduct template preference surveys on users. Based on the user's previous user profile, as well as the survey results and keyword set, it reconstructs the user's user profile and recommends design templates to the user according to the reconstructed user profile.

[0062] 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 implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A data intelligence management method based on user profiles, characterized in that, Includes the following steps: Step S100: Obtain the user's occupation and template selection records, extract the attribute features of the corresponding design templates from the template selection records, build a user profile based on the occupation and attribute features, and obtain the matching degree of each design template to the user based on the user profile, and recommend design templates to the user according to the matching degree; Step S200: Based on the user's actions on the template resource platform, obtain the user's corresponding tagged templates; and analyze the tagged templates and user profiles to extract tagged users from the template resource platform; Step S300: Based on the tagged users' likes and dislikes of design templates on the template resource platform, and the corresponding tagged templates, obtain the feature words corresponding to the attribute features of each template; The process involves obtaining the user's bias and deviation from the feature words, extracting keywords from the feature words, and establishing a keyword set corresponding to the user based on the keywords; Step S400: Conduct a template preference survey on the user, reconstruct the user's user profile based on the user's previous user profile, the survey results, and the keyword set, and recommend design templates to the user according to the reconstructed user profile; Step S300 includes: Step S310: The template resource platform has the function of marking users' likes and dislikes for design templates; Obtain all the design templates and corresponding marked templates that a marked user V likes, and extract the feature words corresponding to the attribute features of each template as the bias feature words of user V, statistically summarize the same bias feature words, obtain the number corresponding to each bias feature word, and then obtain the bias degree of user V towards a certain bias feature word i: X=1- Where e is the natural constant, K1 is the bias coefficient, and N i The number corresponding to feature word i; and normalization based on the degree of bias of each biased feature word; Step S320: Obtain all the design templates that user V dislikes, and extract the feature words corresponding to the attribute features of each template as the deviation feature words of user V, statistically summarize the same deviation feature words, obtain the number corresponding to each deviation feature word, and then obtain the degree of deviation of user V from a certain deviation feature word j: Y = -(1 ), where e is the natural constant, K2 is the deviation coefficient, and N j The number of features j; normalization is performed based on the deviation degree of each feature word; step S330: if a feature word h is not simultaneously a biased feature word and a deviation feature word, then feature word h is taken as a keyword; if a feature word h is simultaneously a biased feature word and a deviation feature word, then the deviation degree X after normalization of feature word h is used as the keyword. h And the degree of deviation Y h The feature degree Z of feature word h is obtained. h =X h -|Y h |,|| are used to find the absolute value, if |Z h If the value is greater than a preset threshold, then the feature word h will be used as a keyword; and a keyword set for user V will be established based on all of user V's keywords.

2. The data intelligent management method based on user profiles according to claim 1, characterized in that, Step S100 includes: Step S110: Obtain all design templates corresponding to the user's template selection record, extract the attribute features of each design template, including style, theme, applicable profession, and applicable scenario; the user's user profile corresponds to several preference tags, including style preference, theme preference, profession preference, and scenario preference; summarize all feature words corresponding to each attribute feature in the template selection record, obtain the quantity corresponding to each feature word, and use the feature words with a quantity greater than a preset quantity threshold as the tag words in the user's corresponding preference tag; then obtain all tag words corresponding to each preference tag in the user's user profile, and set the initial word weight of each tag word to 1; Step S120: Obtain the feature word W corresponding to a certain attribute feature d of a certain design template T in the template resource platform. d Extract all tag words under the preference label corresponding to attribute feature d in the user profile, and match a certain tag word L with the feature word W. d The similarity between the two is multiplied by the word weight of the tag word L to obtain the pair of tag word L and feature word W. d The relevance is then calculated, and the relevance of each tag is obtained. The maximum relevance is taken as the degree of relevance R between attribute feature d and user profile. d Then, the correlation between each attribute feature in the design template T and the user profile is obtained, and the weights corresponding to each attribute feature are pre-set to obtain the matching degree of the design template T with the user. The design templates are then recommended to the user in descending order of matching degree.

3. The data intelligent management method based on user profiles according to claim 2, characterized in that, Step S200 includes: Step S210: The template resource platform has the function of users searching and filtering design templates; the design template recommended in step S100 is used as the recommended template. If a user U selects a design template A using either the search or filtering function on the template resource platform and modifies all the required fields in all editable content of design template A, where the required fields are the user's personal information, and design template A is not a recommended template, then design template A is used as the marked template, thereby obtaining all marked templates; Step S220: All attribute features of a marked template B and the user profile of the current user are obtained. Based on all the tag words under the preference tags, and analogous to step S120, the matching degree of marked template B to the user is obtained, thereby obtaining the matching degree of each marked template to the user, and the average value is calculated. If the average value is less than a preset numerical threshold, then the user U is used as the marked user.

4. The data intelligent management method based on user profiles according to claim 1, characterized in that, Step S400 includes: Step S410: Conduct a template preference survey for all users. The survey includes users' style preferences, theme preferences, occupational preferences, and scenario preferences. All preference keywords in the survey are assigned a weight of 1. If a user is not a labeled user, extract all corresponding tags from the previous user profile. Combine all preference keywords from the survey with all the tags to obtain the final tags. Add the corresponding weights. Based on the final tags, reconstruct the user profile for that user. Step S420: If a user is a labeled user, extract all keywords from the user's keyword set. Use the characteristic degree of each keyword as its weight. Extract all corresponding tags from the previous user profile. Combine all preference keywords from the survey with all the tags and all the keywords from the keyword set to obtain the final tags. Add the corresponding weights. Based on the final tags, reconstruct the user profile for that user. Recommend design templates to the user based on the reconstructed user profile.

5. A data intelligence management system, used to execute the data intelligence management method based on user profiles as described in any one of claims 1-4, characterized in that, The system includes a user profile creation module, a user tag extraction module, a keyword set creation module, and a design template recommendation module; The user profile building module is used to obtain the user's occupation and template selection records, extract the attribute features of the corresponding design templates from the template selection records, build a user profile based on the occupation and attribute features, and obtain the matching degree of each design template to the user based on the user profile, and recommend design templates to the user according to the matching degree; the user tagging extraction module is used to obtain the user's corresponding tag template based on the user's actions and behaviors on the template resource platform; and analyze the tag templates and user profiles to extract the tag users in the template resource platform; Keyword set building module: used to obtain the feature words corresponding to the attribute features of each template based on the design templates that marked users like and dislike on the template resource platform, as well as the corresponding marked templates; It obtains the user's bias and deviation from the feature words, then extracts keywords from the feature words, and establishes a keyword set corresponding to the user based on the keywords; the template recommendation module is used to conduct template preference surveys on users, reconstruct the user profile based on the user's previous user profile, as well as the survey results and keyword set, and recommend design templates to the user according to the reconstructed user profile.

6. A data intelligent management system according to claim 5, characterized in that, The user tagging extraction module includes a user tagging template extraction unit and a user tagging extraction unit. The user tagging template extraction unit is used to extract user tagging templates from the design templates based on the template resource platform's function of allowing users to search and filter design templates and the obtained recommended templates. User tag extraction unit: used to obtain all attribute features of the tag template, as well as the user profile of the current user, and obtain the tagged user based on all tag words under the preference tag.

7. A data intelligent management system according to claim 5, characterized in that, The design template recommendation module includes a user profile reconstruction unit and a design template recommendation unit; User profile reconstruction unit: used to conduct template preference surveys for all users and set word weights for all preference keywords in the survey content; extract all corresponding tag words from the user's previous user profile to obtain the final tag words, and then reconstruct the user profile for a user. Design Template Recommendation Unit: Used to recommend design templates to users based on a newly created user profile.

Images