CN117216300A - Picture uploading method and system based on H5 generation by one key - Google Patents
Picture uploading method and system based on H5 generation by one key Download PDFInfo
- Publication number
- CN117216300A CN117216300A CN202311358080.3A CN202311358080A CN117216300A CN 117216300 A CN117216300 A CN 117216300A CN 202311358080 A CN202311358080 A CN 202311358080A CN 117216300 A CN117216300 A CN 117216300A
- Authority
- CN
- China
- Prior art keywords
- information
- analysis
- function
- demand
- picture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000004458 analytical method Methods 0.000 claims abstract description 247
- 230000006870 function Effects 0.000 claims description 185
- 238000004364 calculation method Methods 0.000 claims description 25
- 230000004927 fusion Effects 0.000 claims description 18
- 238000007781 pre-processing Methods 0.000 claims description 16
- 238000012163 sequencing technique Methods 0.000 claims description 8
- 238000010586 diagram Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 5
- 230000007246 mechanism Effects 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 claims description 4
- 238000012015 optical character recognition Methods 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000012098 association analyses Methods 0.000 claims 2
- 238000003860 storage Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 230000001172 regenerating effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a picture uploading method and a system for generating H5 based on one key, comprising the following steps: acquiring user uploading picture information, and analyzing the user uploading picture information to obtain first analysis result information; acquiring user demand information, carrying out function matching by combining the first analysis result information, and generating a final page; carrying out relevance analysis according to the user demand information and the first analysis result information to obtain relevance analysis information; acquiring history generation instance information, and performing preference use function analysis according to the history generation instance information to obtain preference use function analysis information; and carrying out potential intention function analysis and function recommendation, and generating a recommendation page. The convenience and the richness of the generation of the H5 webpage are improved, and the user experience is improved.
Description
Technical Field
The application relates to the technical field of H5 generation, in particular to a picture uploading method and system based on one-key generation of H5.
Background
With the rapid development of the mobile internet, H5 web pages become an interactive media form widely applied to mobile devices, and they can be used in various fields of advertising, promotion, education, entertainment, etc. However, creating an H5 web page can be a cumbersome and technically intensive task for many users and web page producers. The traditional method requires the steps of manual selection, uploading, selection, adjustment and the like by a user so as to manufacture a satisfactory H5 webpage, and greatly limits the speed and quality of creation.
At present, an authoring mode of generating an H5 webpage by one key in a picture uploading mode gradually becomes a mainstream, and a system automatically generates HTML, CSS and JavaScript codes required by the H5 webpage by automatically identifying the content and the theme of the picture, wherein the HTML, the CSS and the JavaScript codes comprise picture display, interaction elements and responsive design. Meanwhile, personalized function recommendation is performed according to the requirements of users, and the problems of creation speed and quality can be greatly solved.
Disclosure of Invention
The application overcomes the defects of the prior art, and provides a picture uploading method and a system based on one-key generation of H5, which have the important purposes of improving the convenience and the richness of H5 webpage generation and improving user experience.
In order to achieve the above object, a first aspect of the present application provides a method for uploading a picture in which H5 is generated based on one key, including:
acquiring user uploading picture information, and analyzing the user uploading picture information to obtain first analysis result information;
acquiring user demand information, carrying out function matching by combining the first analysis result information, and generating a final page;
carrying out relevance analysis according to the user demand information and the first analysis result information to obtain relevance analysis information;
acquiring history generation instance information, and performing preference use function analysis according to the history generation instance information to obtain preference use function analysis information;
and carrying out potential intention function analysis and function recommendation, and generating a recommendation page.
In this scheme, obtain user's uploading picture information, carry out recognition analysis to user's uploading picture information, specifically do:
acquiring user uploading picture information, and performing enhancement and denoising preprocessing on the user uploading picture information to obtain preprocessing information;
acquiring scene and object picture information of various categories based on big data retrieval, and constructing a comparison data set;
performing similarity calculation on the preprocessing information and the comparison data set, judging with a preset threshold value, and selecting a category larger than the preset threshold value as an analysis result to obtain picture identification analysis information;
performing character recognition and conversion on the preprocessing information based on an optical character recognition technology to obtain character recognition information;
constructing a semantic analysis model, and importing the text recognition information into the semantic analysis model for semantic analysis to obtain semantic analysis information;
and combining the picture analysis information and the semantic analysis information to form first analysis result information.
In the scheme, the user demand information is acquired, the function matching is carried out by combining the first analysis result information, and a final page is generated, specifically;
acquiring user demand information and first analysis result information, presetting a plurality of scene categories, and calculating attention scores of each scene category, the user demand information and the first analysis result information based on a multi-head attention mechanism;
judging and analyzing the calculated attention score and a preset threshold value to obtain scene category analysis information;
acquiring historical use function information according to scene analysis information, calculating historical use frequencies of all functions, and sequencing according to the frequency to obtain a use function frequency sequencing diagram;
presetting a selection threshold, and selecting an applicable function by combining the selection threshold with a function frequency ranking chart to obtain applicable function analysis information;
extracting features of the user demand information and the first analysis result information, and extracting feature information containing expected styles to obtain the expected style feature information;
acquiring historical typesetting information according to the expected style characteristic information, wherein the historical typesetting information comprises typesetting style information and typesetting style scoring information;
screening candidate typesetting styles conforming to the scene by combining the scene category analysis information with the historical typesetting information, taking the score of each typesetting style as weight, and carrying out weighted calculation on the candidate typesetting styles;
presetting a typesetting style selection threshold, and carrying out final typesetting style selection by combining the typesetting style selection threshold with a weighted calculation result to obtain final typesetting style information;
and generating a final page by combining the applicable function analysis information and the final typesetting style information.
In this scheme, the correlation analysis is performed according to the user demand information and the first analysis result information, specifically:
acquiring first analysis result information and user demand information, and carrying out feature extraction and fusion on the first analysis result information and the user demand information to obtain fusion feature information;
acquiring various demand type information based on big data retrieval, and classifying by a clustering algorithm to obtain demand classification information;
constructing a demand level assessment model, and importing the demand classification information into the demand level assessment model to carry out demand level assessment to obtain demand level assessment information;
performing grade marking on each demand type through the demand grade evaluation information to obtain demand grade analysis information;
calculating the mahalanobis distance between the fusion characteristic information and the demand level analysis information based on a mahalanobis distance algorithm to obtain mahalanobis distance information;
and carrying out relevance analysis according to the mahalanobis distance information, and judging and analyzing the preset threshold value of the mahalanobis distance information to obtain relevance analysis information.
In this solution, the performing the analysis of the preference use function according to the history generated instance information, to obtain the analysis information of the preference use function specifically includes:
obtaining history generation instance information based on big data retrieval, the history generation instance information comprising: historical generation page information and historical user demand information;
extracting characteristics of the history generation example information, extracting the theme, style, function, typesetting and user demand characteristics of the history generation example, and obtaining generation example characteristic information;
obtaining fusion characteristic information, carrying out similarity calculation on the fusion characteristic information and the generated instance characteristic information, judging with a preset threshold value, and obtaining a similar instance according to a judging result to obtain similar instance information;
extracting features of the similar instance information, obtaining historical use functions of the similar instance, and performing time sequence arrangement to obtain historical use function information;
and carrying out frequency statistics on the historical use function information, presetting a preference function judging threshold value, and analyzing the preference use function of the similar instance through the preference function judging threshold value to obtain preference use function analysis information.
In this scheme, the potential intention function analysis and function recommendation are performed, and a recommendation page is generated, specifically:
acquiring historical usage function information, preference usage function analysis information, relevance analysis information, final typesetting style information and user demand information;
constructing a knowledge graph according to the historical use function information and the preference use function analysis information, linking different types of functions according to time sequences, and marking the preference according to the use frequency of each function to obtain a function knowledge graph;
constructing a potential intention function analysis model, and constructing a training data set through an energy-through knowledge graph to perform deep learning and training to obtain the potential intention function analysis model which meets the expectations;
importing the user demand information and the relevance analysis information into the potential intention function analysis model for analysis to obtain potential intention function analysis information;
extracting the use frequency of the potential intention function according to the potential intention function analysis information and the function knowledge graph, and carrying out weighted calculation on the potential intention function analysis information as recommendation weight;
judging the weighted calculation result and a preset threshold value, and selecting potential intention functions larger than the preset threshold value to recommend so as to obtain potential intention function recommendation information;
and generating a recommendation page according to the final typesetting style information and the potential intention function recommendation information, and performing personalized recommendation.
The second aspect of the present application provides a system for uploading a picture based on one-key generation of H5, the system comprising: the device comprises a memory and a processor, wherein the memory contains a picture uploading method program for generating H5 based on one key, and the picture uploading method program for generating H5 based on one key realizes the following steps when being executed by the processor:
acquiring user uploading picture information, and analyzing the user uploading picture information to obtain first analysis result information;
acquiring user demand information, carrying out function matching by combining the first analysis result information, and generating a final page;
carrying out relevance analysis according to the user demand information and the first analysis result information to obtain relevance analysis information;
acquiring history generation instance information, and performing preference use function analysis according to the history generation instance information to obtain preference use function analysis information;
and carrying out potential intention function analysis and function recommendation, and generating a recommendation page.
The application discloses a picture uploading method and a system for generating H5 based on one key, comprising the following steps: acquiring user uploading picture information, and analyzing the user uploading picture information to obtain first analysis result information; acquiring user demand information, carrying out function matching by combining the first analysis result information, and generating a final page; carrying out relevance analysis according to the user demand information and the first analysis result information to obtain relevance analysis information; acquiring history generation instance information, and performing preference use function analysis according to the history generation instance information to obtain preference use function analysis information; and carrying out potential intention function analysis and function recommendation, and generating a recommendation page. The convenience and the richness of the generation of the H5 webpage are improved, and the user experience is improved.
Drawings
In order to more clearly illustrate the technical solutions of embodiments or examples of the present application, the drawings that are required to be used in the embodiments or examples of the present application will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to the drawings without inventive efforts for those skilled in the art.
Fig. 1 is a flowchart of a picture uploading method for generating H5 based on one key according to an embodiment of the present application;
FIG. 2 is a data processing flow chart of a method for uploading a picture based on one-key generation H5 according to an embodiment of the present application;
FIG. 3 is a block diagram of a system for uploading pictures based on H5 generation by one key according to an embodiment of the present application;
the achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, however, the present application may be practiced in other ways than those described herein, and therefore the scope of the present application is not limited to the specific embodiments disclosed below.
Fig. 1 is a flowchart of a picture uploading method for generating H5 based on one key according to an embodiment of the present application;
as shown in fig. 1, the present application provides a picture uploading method flowchart based on one-key generation of H5, including:
s102, obtaining user uploading picture information, and analyzing the user uploading picture information to obtain first analysis result information;
acquiring user uploading picture information, and performing enhancement and denoising preprocessing on the user uploading picture information to obtain preprocessing information;
acquiring scene and object picture information of various categories based on big data retrieval, and constructing a comparison data set;
performing similarity calculation on the preprocessing information and the comparison data set, judging with a preset threshold value, and selecting a category larger than the preset threshold value as an analysis result to obtain picture identification analysis information;
performing character recognition and conversion on the preprocessing information based on an optical character recognition technology to obtain character recognition information;
constructing a semantic analysis model, and importing the text recognition information into the semantic analysis model for semantic analysis to obtain semantic analysis information;
and combining the picture analysis information and the semantic analysis information to form first analysis result information.
When a user uploads a picture, compressing a target picture to a target proportion according to the picture compression rule, regenerating new picture data, performing Base64 coding on the new picture data, storing an original file name of a picture file and a generated Base64 coding into an object array in a Json data format, converting the original file name and the generated Base64 coding into a Json file, and finally transmitting the Json file to a server. After receiving Json data requested by a client, the server analyzes the Json data, separates out Base codes corresponding to original file names and pictures, decodes the picture data to obtain a target picture, analyzes and redraws the target picture, regenerates new picture files and file names, and returns the new file names to the client for viewing and changing by a user.
S104, obtaining user demand information, carrying out function matching by combining the first analysis result information, and generating a final page;
acquiring user demand information and first analysis result information, presetting a plurality of scene categories, and calculating attention scores of each scene category, the user demand information and the first analysis result information based on a multi-head attention mechanism;
judging and analyzing the calculated attention score and a preset threshold value to obtain scene category analysis information;
acquiring historical use function information according to scene analysis information, calculating historical use frequencies of all functions, and sequencing according to the frequency to obtain a use function frequency sequencing diagram;
presetting a selection threshold, and selecting an applicable function by combining the selection threshold with a function frequency ranking chart to obtain applicable function analysis information;
extracting features of the user demand information and the first analysis result information, and extracting feature information containing expected styles to obtain the expected style feature information;
acquiring historical typesetting information according to the expected style characteristic information, wherein the historical typesetting information comprises typesetting style information and typesetting style scoring information;
screening candidate typesetting styles conforming to the scene by combining the scene category analysis information with the historical typesetting information, taking the score of each typesetting style as weight, and carrying out weighted calculation on the candidate typesetting styles;
presetting a typesetting style selection threshold, and carrying out final typesetting style selection by combining the typesetting style selection threshold with a weighted calculation result to obtain final typesetting style information;
and generating a final page by combining the applicable function analysis information and the final typesetting style information.
It should be noted that, for a plurality of preset scene categories, a multi-head attention mechanism is used to calculate an attention score between each scene category and the user demand information and the first analysis result information, so as to represent the matching degree of the user demand and the analysis result with different scenes. And then comparing the calculated attention score with a preset threshold value to judge which scene categories are related to the user demands, and generating scene category analysis information which indicates which scenes are possibly matched with the user demands. Then, based on the scene category analysis information, history use function information is acquired, and history use frequency of each function is calculated for revealing which functions are frequently used in history similar scenes. The method comprises the steps of presetting a threshold value for selecting applicable functions, determining which functions are applicable to a current scene by combining a historical use function frequency ranking chart and the threshold value, and generating applicable function analysis information which indicates which functions are possibly related to the current scene. Then, feature information including a style desired by the user is extracted from the user demand information and the first analysis result information, which may include fonts, colors, typesetting elements, and the like. And acquiring historical typesetting information, combining scene category analysis information, screening out candidate typesetting styles related to the current scene, and taking scores of the candidate typesetting styles as weights to carry out weighted calculation. Presetting a typesetting style selection threshold, and determining a final typesetting style by combining a weighted calculation result and the threshold to generate final typesetting style information. And finally, combining the applicable function analysis information and the final typesetting style information to generate a final page which meets the requirements, scenes and expected styles of the user. Therefore, the H5 page which highly accords with the user requirement is obtained, the original idea of the user is attached, and the user experience is improved.
Further, user feedback information after the final page is pushed is obtained; extracting features of the user feedback information, carrying out semantic analysis according to the extracted features, and analyzing whether typesetting style change and change requirements are needed to be carried out or not to obtain user feedback semantic analysis information; acquiring final typesetting style information, and analyzing the final typesetting style information based on a principal component analysis algorithm to obtain principal component style analysis information; extracting features of the final typesetting style information, extracting typesetting style features, and calculating the duty ratio of each style feature to the total style features to obtain typesetting style feature information; projecting typesetting style characteristic information to the style direction of the main components according to the style analysis information of the main components to obtain a style projection matrix; acquiring style modification requirement information based on the user feedback semantic analysis information, performing feature extraction on the style modification requirement information, and extracting target modification style characteristics to obtain modification style characteristic information; performing similarity calculation on the changed style characteristic information and the style projection matrix to obtain a similarity value for evaluating style consistency; presetting a judgment threshold, judging the similarity value and the judgment threshold to obtain consistency judgment result information, and performing auxiliary decision according to the consistency judgment result information; if the style increment is smaller than the judgment threshold, similar style recommendation is performed; if the style increment is larger than the judging threshold, the position recommendation is carried out according to the style change requirement information, so that the user experience is improved, and the degree of violation of style change is reduced.
S106, carrying out relevance analysis according to the user demand information and the first analysis result information to obtain relevance analysis information;
acquiring first analysis result information and user demand information, and carrying out feature extraction and fusion on the first analysis result information and the user demand information to obtain fusion feature information;
acquiring various demand type information based on big data retrieval, and classifying by a clustering algorithm to obtain demand classification information;
constructing a demand level assessment model, and importing the demand classification information into the demand level assessment model to carry out demand level assessment to obtain demand level assessment information;
performing grade marking on each demand type through the demand grade evaluation information to obtain demand grade analysis information;
calculating the mahalanobis distance between the fusion characteristic information and the demand level analysis information based on a mahalanobis distance algorithm to obtain mahalanobis distance information;
and carrying out relevance analysis according to the mahalanobis distance information, and judging and analyzing the preset threshold value of the mahalanobis distance information to obtain relevance analysis information.
It should be noted that, by fusing the features of the user demand information and the first analysis result information, multiple data are comprehensively considered, and more comprehensive demand expression is provided, so that accuracy and comprehensiveness of demand analysis are improved. The classification of the various demand types to understand the relationships and features between the different types of demands helps to more accurately meet the user's demands, ensuring that the different types of demands are properly processed and analyzed. And then, allocating a grade to each demand through a demand grade assessment model, wherein the grade is used for determining the importance of the type of each demand, simultaneously, the importance arrangement of the same type of demands is facilitated, the priority of the demands is analyzed, and the demand type is marked according to the demand grade assessment information. Finally, the mahalanobis distance between the fused feature information and the demand level analysis information is calculated to determine which demand types have higher correlation with the feature information of the user demands, so that the intention and the demands of the user are deduced better, the user demands are understood, the demand processing flow is optimized, more personalized and accurate service is provided, the user experience and satisfaction are improved, and the efficiency and the accuracy are improved.
S108, acquiring history generation instance information, and performing preference use function analysis according to the history generation instance information to obtain preference use function analysis information;
obtaining history generation instance information based on big data retrieval, the history generation instance information comprising: historical generation page information and historical user demand information;
extracting characteristics of the history generation example information, extracting the theme, style, function, typesetting and user demand characteristics of the history generation example, and obtaining generation example characteristic information;
obtaining fusion characteristic information, carrying out similarity calculation on the fusion characteristic information and the generated instance characteristic information, judging with a preset threshold value, and obtaining a similar instance according to a judging result to obtain similar instance information;
extracting features of the similar instance information, obtaining historical use functions of the similar instance, and performing time sequence arrangement to obtain historical use function information;
and carrying out frequency statistics on the historical use function information, presetting a preference function judging threshold value, and analyzing the preference use function of the similar instance through the preference function judging threshold value to obtain preference use function analysis information.
S110, carrying out potential intention function analysis and function recommendation, and generating a recommendation page;
acquiring historical usage function information, preference usage function analysis information, relevance analysis information, final typesetting style information and user demand information;
constructing a knowledge graph according to the historical use function information and the preference use function analysis information, linking different types of functions according to time sequences, and marking the preference according to the use frequency of each function to obtain a function knowledge graph;
constructing a potential intention function analysis model, and constructing a training data set through an energy-through knowledge graph to perform deep learning and training to obtain the potential intention function analysis model which meets the expectations;
importing the user demand information and the relevance analysis information into the potential intention function analysis model for analysis to obtain potential intention function analysis information;
extracting the use frequency of the potential intention function according to the potential intention function analysis information and the function knowledge graph, and carrying out weighted calculation on the potential intention function analysis information as recommendation weight;
judging the weighted calculation result and a preset threshold value, and selecting potential intention functions larger than the preset threshold value to recommend so as to obtain potential intention function recommendation information;
and generating a recommendation page according to the final typesetting style information and the potential intention function recommendation information, and performing personalized recommendation.
It should be noted that, a functional knowledge graph is constructed through the history use function information and the preference use function analysis information, the functional knowledge graph contains functions of different types, the history use functions under different demand types are associated according to the adoption time, and then the use frequency of each function is marked for analyzing the application degree. The functions that may be of interest to the user are mined by importing user demand information and relevance analysis information into a potential intent function analysis model to analyze the user's potential demand. And then, extracting the use frequency of the potential intention function from the functional knowledge graph, taking the use frequency as a recommendation weight, weighting and calculating the potential intention function of the user, and selecting the function exceeding a preset threshold value for recommendation. And finally, combining the final typesetting style information of the user with the potential intention function recommendation information to generate a personalized recommendation page. Including functions of interest to the user and employing typesetting style of user preferences to provide a highly personalized experience.
FIG. 2 is a data processing flow chart of a method for uploading a picture based on one-key generation H5 according to an embodiment of the present application;
as shown in fig. 2, the present application provides a data processing flow chart of a picture uploading method based on one-key generation H5, which includes:
s202, analyzing the picture information uploaded by the user to obtain first analysis result information;
s204, obtaining user demand information, and carrying out function matching by combining the first analysis result information to obtain applicable function analysis information;
s206, analyzing the applicable typesetting style, and generating a final page by combining the applicable function analysis information;
s208, performing grade evaluation on the user demands and performing relevance analysis;
s210, carrying out potential intention function analysis, carrying out function recommendation according to an analysis result, and generating a recommendation page;
and S212, pushing the final page and the recommended page.
Further, first analysis result information and user demand information are obtained, and theme feature extraction is carried out on the first analysis result information and the user demand information to obtain theme feature information; based on big data retrieval, obtaining various picture features, scene features, demand features and keyword features with different purposes to form a comparison data set; performing similarity calculation on the theme characteristic information and the comparison data set to obtain a similarity value; presetting a use judgment threshold value, and comparing and analyzing the similarity value with the use judgment threshold value to obtain use analysis information; acquiring audience user information based on the usage analysis information, and extracting characteristics of the audience user information to acquire audience user characteristic information; performing main feature analysis on the audience user feature information based on an association rule mining algorithm, and taking high-frequency features of the audience users as main features to obtain main feature analysis information; constructing an audience characteristic analysis model, and inputting the main characteristic analysis information into the audience attribute analysis model to perform audience attribute analysis to obtain audience attribute analysis information; according to the audience attribute information function adaptation and typesetting style selection, generating an optimization scheme, and obtaining optimization scheme information; extracting audience user activity time information according to the audience user characteristic information, presetting an activity time selection threshold, and carrying out user activity time analysis according to the activity time selection threshold to obtain activity time analysis information; generating a popularization proposal according to the active time analysis information, pushing the proposal to a visual interface in combination with the optimization proposal, providing better use proposal and optimization proposal for users, fitting target audience, and improving economic benefit or propagation efficiency.
Fig. 3 is a block diagram 3 of a picture uploading system based on one-key generation of H5 according to an embodiment of the present application, where the system includes: the memory 31 and the processor 32, wherein the memory 31 contains a picture uploading method program based on one-key generation H5, and the picture uploading method program based on one-key generation H5 realizes the following steps when being executed by the processor 32:
acquiring user uploading picture information, and analyzing the user uploading picture information to obtain first analysis result information;
acquiring user demand information, carrying out function matching by combining the first analysis result information, and generating a final page;
carrying out relevance analysis according to the user demand information and the first analysis result information to obtain relevance analysis information;
acquiring history generation instance information, and performing preference use function analysis according to the history generation instance information to obtain preference use function analysis information;
and carrying out potential intention function analysis and function recommendation, and generating a recommendation page.
It should be noted that the recommended page and the final page are two independent pages, and the generation of the H5 page is first performed strictly according to the picture and the requirement uploaded by the user, so as to obtain the page close to the basic requirement of the user. And then, personalized recommendation is carried out, basic characteristics of the user are mapped by analyzing user demand information and user uploading picture information, favorite styles and wanted functions are mapped from the user demand information, adaptive functions and styles are mapped from the content of the user uploading picture information, and therefore the function of combining and analyzing potential intention of the user is carried out, and personalized recommendation with high fitting degree is carried out. After the two pages are generated, the two pages are pushed to the user together so as to provide various choices, so that the user can expect other potential functions on the premise of guaranteeing the requirement of highly fitting the user, the generation rate is improved, and the participation degree and experience sense of the user are also improved.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present application may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present application may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. The picture uploading method for generating H5 based on one key is characterized by comprising the following steps:
acquiring user uploading picture information, and analyzing the user uploading picture information to obtain first analysis result information;
acquiring user demand information, carrying out function matching by combining the first analysis result information, and generating a final page;
carrying out relevance analysis according to the user demand information and the first analysis result information to obtain relevance analysis information;
acquiring history generation instance information, and performing preference use function analysis according to the history generation instance information to obtain preference use function analysis information;
and carrying out potential intention function analysis and function recommendation, and generating a recommendation page.
2. The method for uploading the picture based on the one-key generation of the H5 according to claim 1, wherein the step of obtaining the user uploading picture information and performing recognition analysis on the user uploading picture information comprises the following steps:
acquiring user uploading picture information, and performing enhancement and denoising preprocessing on the user uploading picture information to obtain preprocessing information;
acquiring scene and object picture information of various categories based on big data retrieval, and constructing a comparison data set;
performing similarity calculation on the preprocessing information and the comparison data set, judging with a preset threshold value, and selecting a category larger than the preset threshold value as an analysis result to obtain picture identification analysis information;
performing character recognition and conversion on the preprocessing information based on an optical character recognition technology to obtain character recognition information;
constructing a semantic analysis model, and importing the text recognition information into the semantic analysis model for semantic analysis to obtain semantic analysis information;
and combining the picture analysis information and the semantic analysis information to form first analysis result information.
3. The method for uploading a picture based on one-key generation of H5 according to claim 1, wherein the obtaining user demand information, performing function matching in combination with the first analysis result information, and generating a final page specifically includes;
acquiring user demand information and first analysis result information, presetting a plurality of scene categories, and calculating attention scores of each scene category, the user demand information and the first analysis result information based on a multi-head attention mechanism;
judging and analyzing the calculated attention score and a preset threshold value to obtain scene category analysis information;
acquiring historical use function information according to scene analysis information, calculating historical use frequencies of all functions, and sequencing according to the frequency to obtain a use function frequency sequencing diagram;
presetting a selection threshold, and selecting an applicable function by combining the selection threshold with a function frequency ranking chart to obtain applicable function analysis information;
extracting features of the user demand information and the first analysis result information, and extracting feature information containing expected styles to obtain the expected style feature information;
acquiring historical typesetting information according to the expected style characteristic information, wherein the historical typesetting information comprises typesetting style information and typesetting style scoring information;
screening candidate typesetting styles conforming to the scene by combining the scene category analysis information with the historical typesetting information, taking the score of each typesetting style as weight, and carrying out weighted calculation on the candidate typesetting styles;
presetting a typesetting style selection threshold, and carrying out final typesetting style selection by combining the typesetting style selection threshold with a weighted calculation result to obtain final typesetting style information;
and generating a final page by combining the applicable function analysis information and the final typesetting style information.
4. The method for uploading the picture based on the one-key generation H5 according to claim 1, wherein the performing the association analysis according to the user requirement information and the first analysis result information specifically comprises:
acquiring first analysis result information and user demand information, and carrying out feature extraction and fusion on the first analysis result information and the user demand information to obtain fusion feature information;
acquiring various demand type information based on big data retrieval, and classifying by a clustering algorithm to obtain demand classification information;
constructing a demand level assessment model, and importing the demand classification information into the demand level assessment model to carry out demand level assessment to obtain demand level assessment information;
performing grade marking on each demand type through the demand grade evaluation information to obtain demand grade analysis information;
calculating the mahalanobis distance between the fusion characteristic information and the demand level analysis information based on a mahalanobis distance algorithm to obtain mahalanobis distance information;
and carrying out relevance analysis according to the mahalanobis distance information, and judging and analyzing the preset threshold value of the mahalanobis distance information to obtain relevance analysis information.
5. The method for uploading pictures based on one-key generation H5 according to claim 1, wherein the performing the preference use function analysis according to the history generation instance information to obtain preference use function analysis information specifically comprises:
obtaining history generation instance information based on big data retrieval, the history generation instance information comprising: historical generation page information and historical user demand information;
extracting characteristics of the history generation example information, extracting the theme, style, function, typesetting and user demand characteristics of the history generation example, and obtaining generation example characteristic information;
obtaining fusion characteristic information, carrying out similarity calculation on the fusion characteristic information and the generated instance characteristic information, judging with a preset threshold value, and obtaining a similar instance according to a judging result to obtain similar instance information;
extracting features of the similar instance information, obtaining historical use functions of the similar instance, and performing time sequence arrangement to obtain historical use function information;
and carrying out frequency statistics on the historical use function information, presetting a preference function judging threshold value, and analyzing the preference use function of the similar instance through the preference function judging threshold value to obtain preference use function analysis information.
6. The method for uploading pictures based on one-key generation of H5 according to claim 1, wherein the performing potential intent function analysis and function recommendation and generating a recommendation page specifically comprises:
acquiring historical usage function information, preference usage function analysis information, relevance analysis information, final typesetting style information and user demand information;
constructing a knowledge graph according to the historical use function information and the preference use function analysis information, linking different types of functions according to time sequences, and marking the preference according to the use frequency of each function to obtain a function knowledge graph;
constructing a potential intention function analysis model, and constructing a training data set through an energy-through knowledge graph to perform deep learning and training to obtain the potential intention function analysis model which meets the expectations;
importing the user demand information and the relevance analysis information into the potential intention function analysis model for analysis to obtain potential intention function analysis information;
extracting the use frequency of the potential intention function according to the potential intention function analysis information and the function knowledge graph, and carrying out weighted calculation on the potential intention function analysis information as recommendation weight;
judging the weighted calculation result and a preset threshold value, and selecting potential intention functions larger than the preset threshold value to recommend so as to obtain potential intention function recommendation information;
and generating a recommendation page according to the final typesetting style information and the potential intention function recommendation information, and performing personalized recommendation.
7. A picture upload system for generating H5 based on one key, the system comprising: the device comprises a memory and a processor, wherein the memory contains a picture uploading method program for generating H5 based on one key, and the picture uploading method program for generating H5 based on one key realizes the following steps when being executed by the processor:
acquiring user uploading picture information, and analyzing the user uploading picture information to obtain first analysis result information;
acquiring user demand information, carrying out function matching by combining the first analysis result information, and generating a final page;
carrying out relevance analysis according to the user demand information and the first analysis result information to obtain relevance analysis information;
acquiring history generation instance information, and performing preference use function analysis according to the history generation instance information to obtain preference use function analysis information;
and carrying out potential intention function analysis and function recommendation, and generating a recommendation page.
8. The system for uploading pictures based on one-key generation of H5 according to claim 7, wherein said obtaining the user-uploaded picture information and performing the recognition analysis on the user-uploaded picture information specifically comprises:
acquiring user uploading picture information, and performing enhancement and denoising preprocessing on the user uploading picture information to obtain preprocessing information;
acquiring scene and object picture information of various categories based on big data retrieval, and constructing a comparison data set;
performing similarity calculation on the preprocessing information and the comparison data set, judging with a preset threshold value, and selecting a category larger than the preset threshold value as an analysis result to obtain picture identification analysis information;
performing character recognition and conversion on the preprocessing information based on an optical character recognition technology to obtain character recognition information;
constructing a semantic analysis model, and importing the text recognition information into the semantic analysis model for semantic analysis to obtain semantic analysis information;
and combining the picture analysis information and the semantic analysis information to form first analysis result information.
9. The system for uploading pictures based on one-key generation of H5 as set forth in claim 7, wherein said obtaining user demand information, performing function matching in combination with the first analysis result information, and generating a final page comprises;
acquiring user demand information and first analysis result information, presetting a plurality of scene categories, and calculating attention scores of each scene category, the user demand information and the first analysis result information based on a multi-head attention mechanism;
judging and analyzing the calculated attention score and a preset threshold value to obtain scene category analysis information;
acquiring historical use function information according to scene analysis information, calculating historical use frequencies of all functions, and sequencing according to the frequency to obtain a use function frequency sequencing diagram;
presetting a selection threshold, and selecting an applicable function by combining the selection threshold with a function frequency ranking chart to obtain applicable function analysis information;
extracting features of the user demand information and the first analysis result information, and extracting feature information containing expected styles to obtain the expected style feature information;
acquiring historical typesetting information according to the expected style characteristic information, wherein the historical typesetting information comprises typesetting style information and typesetting style scoring information;
screening candidate typesetting styles conforming to the scene by combining the scene category analysis information with the historical typesetting information, taking the score of each typesetting style as weight, and carrying out weighted calculation on the candidate typesetting styles;
presetting a typesetting style selection threshold, and carrying out final typesetting style selection by combining the typesetting style selection threshold with a weighted calculation result to obtain final typesetting style information;
and generating a final page by combining the applicable function analysis information and the final typesetting style information.
10. The system for uploading pictures based on one-key generation H5 according to claim 7, wherein the performing the association analysis according to the user requirement information and the first analysis result information specifically comprises:
acquiring first analysis result information and user demand information, and carrying out feature extraction and fusion on the first analysis result information and the user demand information to obtain fusion feature information;
acquiring various demand type information based on big data retrieval, and classifying by a clustering algorithm to obtain demand classification information;
constructing a demand level assessment model, and importing the demand classification information into the demand level assessment model to carry out demand level assessment to obtain demand level assessment information;
performing grade marking on each demand type through the demand grade evaluation information to obtain demand grade analysis information;
calculating the mahalanobis distance between the fusion characteristic information and the demand level analysis information based on a mahalanobis distance algorithm to obtain mahalanobis distance information;
and carrying out relevance analysis according to the mahalanobis distance information, and judging and analyzing the preset threshold value of the mahalanobis distance information to obtain relevance analysis information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311358080.3A CN117216300B (en) | 2023-10-19 | 2023-10-19 | Picture uploading method and system based on H5 generation by one key |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311358080.3A CN117216300B (en) | 2023-10-19 | 2023-10-19 | Picture uploading method and system based on H5 generation by one key |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117216300A true CN117216300A (en) | 2023-12-12 |
| CN117216300B CN117216300B (en) | 2024-05-10 |
Family
ID=89037313
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311358080.3A Active CN117216300B (en) | 2023-10-19 | 2023-10-19 | Picture uploading method and system based on H5 generation by one key |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117216300B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090094137A1 (en) * | 2005-12-22 | 2009-04-09 | Toppenberg Larry W | Web Page Optimization Systems |
| CN103106259A (en) * | 2013-01-25 | 2013-05-15 | 西北工业大学 | Mobile webpage content recommending method based on situation |
| US20140282943A1 (en) * | 2013-03-18 | 2014-09-18 | Rawllin International Inc. | Universal management of user profiles |
| CN105912548A (en) * | 2015-12-15 | 2016-08-31 | 乐视致新电子科技（天津）有限公司 | Method and device for sharing electronic note |
| US20170310791A1 (en) * | 2016-04-20 | 2017-10-26 | Servicenow, Inc. | Performance-based generation of content |
| CN107832469A (en) * | 2017-11-29 | 2018-03-23 | 北京洪泰同创信息技术有限公司 | A kind of generation method and device of enterprise logo images |
| CN110232589A (en) * | 2019-05-16 | 2019-09-13 | 浙江华坤道威数据科技有限公司 | A kind of intention customer analysis system based on big data |
| CN111679827A (en) * | 2020-04-28 | 2020-09-18 | 平安国际智慧城市科技股份有限公司 | H5 page generation method, device, equipment and storage medium |
| CN115600031A (en) * | 2022-11-03 | 2023-01-13 | 上海浦东发展银行股份有限公司（Cn） | Page generation method, device, terminal, server and storage medium |
| CN115756464A (en) * | 2022-11-25 | 2023-03-07 | 南方电网数字平台科技(广东)有限公司 | Dynamic generation method and device of overview page |
| CN116069328A (en) * | 2023-02-08 | 2023-05-05 | 北京中亦安图科技股份有限公司 | Processing method and device of flow page, processor and electronic equipment |
| CN116484136A (en) * | 2023-04-07 | 2023-07-25 | 亨得昂信息科技(上海)有限公司 | Webpage generation method based on picture identification |
-
2023
- 2023-10-19 CN CN202311358080.3A patent/CN117216300B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090094137A1 (en) * | 2005-12-22 | 2009-04-09 | Toppenberg Larry W | Web Page Optimization Systems |
| CN103106259A (en) * | 2013-01-25 | 2013-05-15 | 西北工业大学 | Mobile webpage content recommending method based on situation |
| US20140282943A1 (en) * | 2013-03-18 | 2014-09-18 | Rawllin International Inc. | Universal management of user profiles |
| CN105912548A (en) * | 2015-12-15 | 2016-08-31 | 乐视致新电子科技（天津）有限公司 | Method and device for sharing electronic note |
| US20170310791A1 (en) * | 2016-04-20 | 2017-10-26 | Servicenow, Inc. | Performance-based generation of content |
| CN107832469A (en) * | 2017-11-29 | 2018-03-23 | 北京洪泰同创信息技术有限公司 | A kind of generation method and device of enterprise logo images |
| CN110232589A (en) * | 2019-05-16 | 2019-09-13 | 浙江华坤道威数据科技有限公司 | A kind of intention customer analysis system based on big data |
| CN111679827A (en) * | 2020-04-28 | 2020-09-18 | 平安国际智慧城市科技股份有限公司 | H5 page generation method, device, equipment and storage medium |
| CN115600031A (en) * | 2022-11-03 | 2023-01-13 | 上海浦东发展银行股份有限公司（Cn） | Page generation method, device, terminal, server and storage medium |
| CN115756464A (en) * | 2022-11-25 | 2023-03-07 | 南方电网数字平台科技(广东)有限公司 | Dynamic generation method and device of overview page |
| CN116069328A (en) * | 2023-02-08 | 2023-05-05 | 北京中亦安图科技股份有限公司 | Processing method and device of flow page, processor and electronic equipment |
| CN116484136A (en) * | 2023-04-07 | 2023-07-25 | 亨得昂信息科技(上海)有限公司 | Webpage generation method based on picture identification |
Non-Patent Citations (2)
| Title |
|---|
| TODOR RACHOVSKI 等: "Models and Methodologies for Automated Creating of Webpage Mobile Versions", 《IOP CONFERENCE SERIES: MATERIALS SCIENCE AND ENGINEERING》, vol. 1031, 31 December 2021 (2021-12-31), pages 1 - 8 * |
| 魏力恺: "基于CBR和HTML5的建筑空间检索与生成研究", 《中国博士学位论文全文数据库 工程科技Ⅱ辑》, no. 12, 15 December 2014 (2014-12-15), pages 038 - 27 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117216300B (en) | 2024-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112533051B (en) | Barrage information display method, barrage information display device, computer equipment and storage medium | |
| US11763145B2 (en) | Article recommendation method and apparatus, computer device, and storage medium | |
| CN106339507B (en) | Streaming Media information push method and device | |
| US10235680B2 (en) | System and method for populating a database with user input | |
| CN109168047B (en) | Video recommendation method and device, server and storage medium | |
| CN113094552A (en) | Video template searching method and device, server and readable storage medium | |
| CN112015928B (en) | Information extraction method and device for multimedia resources, electronic equipment and storage medium | |
| KR102111720B1 (en) | Method for design recommending using cloud literary work analysis | |
| CN113469298B (en) | Model training method and resource recommendation method | |
| CN117540101B (en) | Online bookend management method and system based on artificial intelligence | |
| CN113742567B (en) | Recommendation method and device for multimedia resources, electronic equipment and storage medium | |
| CN111062439A (en) | Video definition classification method, device, equipment and storage medium | |
| CN113704509B (en) | Multimedia recommendation method and device, electronic equipment and storage medium | |
| CN112052352B (en) | Video ordering method, device, server and storage medium | |
| CN111597361B (en) | Multimedia data processing method, device, storage medium and equipment | |
| CN113297520A (en) | Page design auxiliary processing method and device and electronic equipment | |
| CN112906376A (en) | Self-adaptive matching user English learning text pushing system and method | |
| CN117216300B (en) | Picture uploading method and system based on H5 generation by one key | |
| CN106570003B (en) | Data pushing method and device | |
| CN116956183A (en) | Multimedia resource recommendation method, model training method, device and storage medium | |
| CN113641914A (en) | Search recommendation method, system and storage medium based on user preference | |
| CN113821677A (en) | Method, device and equipment for generating cover image and storage medium | |
| KR20230044589A (en) | Method for providing video content platform recommendation service | |
| CN112613775A (en) | Resource quality evaluation method and device, electronic device and storage medium | |
| KR101591297B1 (en) | Course recommendation system and method thereof, recording medium for performing the method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |