CN110689079A - Processing method, processing device and electronic equipment - Google Patents
Processing method, processing device and electronic equipment Download PDFInfo
- Publication number
- CN110689079A CN110689079A CN201910938111.XA CN201910938111A CN110689079A CN 110689079 A CN110689079 A CN 110689079A CN 201910938111 A CN201910938111 A CN 201910938111A CN 110689079 A CN110689079 A CN 110689079A
- Authority
- CN
- China
- Prior art keywords
- design drawing
- target
- parameters
- design
- information
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Processing Or Creating Images (AREA)
Abstract
The embodiment of the application provides a processing method, a processing device and electronic equipment, wherein the method comprises the following steps: obtaining first characteristic data, wherein the first characteristic data is used for generating a design drawing; generating a first number of plans based on at least the first feature data; determining a first target parameter in response to at least one operation satisfying a condition; training a first target model based at least on the first target parameters; wherein the first target model is used for outputting a target design drawing. The processing method of the embodiment of the application can be applied to electronic equipment, so that the electronic equipment can rapidly and efficiently acquire the design requirements of a user and output a target design drawing expected by the user.
Description
Technical Field
The embodiment of the application relates to the field of intelligent equipment, in particular to a processing method, a processing device and electronic equipment.
Background
The existing scheme for generating pictures by using a deep learning algorithm relies on a large number of excellent pictures as training data and needs very large manual labeling workload. For example, capturing and collecting the training pictures from the picture library manually, and then, inputting a large amount of manpower to label the design semantics of the selected pictures at a later stage, so that the training picture data for supporting the deep learning of the device is determined from the large amount of pictures based on the design semantics. The method has two main defects, namely 1) a large amount of manpower is required to be invested, and 2) the marked data has strong subjectivity and does not have a unified standard. 3) The equipment learning effect is poor, and the learning result can not meet the user requirement
Disclosure of Invention
The embodiment of the application provides a processing method, which comprises the following steps:
obtaining first characteristic data, wherein the first characteristic data is used for generating a design drawing;
generating a first number of plans based on at least the first feature data;
determining a first target parameter in response to at least one operation satisfying a condition;
training a first target model based at least on the first target parameters;
wherein the first target model is used for outputting a target design drawing.
Preferably, the obtaining the first feature data includes:
obtaining the first characteristic data based on the attribute information of the design drawing;
wherein the attribute information characterizes constituent elements of the design drawing.
Preferably, the generating a first number of plans based on at least the first feature data comprises:
determining a material library matched with the first characteristic data;
generating a first number of design drawings based on the material library and a first strategy;
wherein each of the plans has parameters for characterizing the plans.
Preferably, the determining the first target parameter in response to the at least one operation satisfying the condition comprises:
associating first identification information or second identification information for each of the plans in response to an evaluation operation on the first number of plans;
and extracting parameters of the design drawing associated with the first identification information based on a second strategy, and processing the extracted parameters to obtain the first target parameters.
Preferably, the evaluation operation on the first number of design drawings includes:
determining an evaluation operation for the first number of plans based on the obtained identification input information; or the like, or, alternatively,
an evaluation operation for the first number of plans is determined based on the obtained evaluation information.
Preferably, the extracting parameters of the design drawing associated with the first identification information based on the second policy includes:
obtaining evaluation result information of each design drawing associated with the first identification information, the evaluation result information being generated based on the evaluation operation;
performing parameter extraction on the design drawing which satisfies parameter extraction conditions and is associated with the first identification information based on the evaluation result information, and processing the extracted parameters;
wherein the parameter extraction condition is related to the evaluation result information.
Preferably, the method further comprises the following steps:
extracting parameters of the design drawing associated with the second identification information based on a third strategy, and processing the extracted parameters to obtain second target parameters;
training a second target model based on the second target parameters;
the design drawing associated with the second identification information is a design drawing in the first quantity of design drawings except the design drawing associated with the first identification information, and the second target model is used for filtering feature data which do not conform to the first target model.
Preferably, the method further comprises the following steps:
outputting a target design drawing based on at least the first target model and the second model.
An embodiment of the present application also provides a processing apparatus, including:
the acquisition module is used for acquiring first characteristic data, and the first characteristic data is used for generating a design drawing;
a processing module for generating a first number of plans based on at least the first feature data, and in response to at least one operation satisfying a condition, determining a first target parameter, training a first target model based on at least the first target parameter;
wherein the first target model is used for outputting a target design drawing.
An embodiment of the present application simultaneously provides an electronic device, including:
a memory for storing at least one set of instructions;
a processor for calling and executing said set of instructions in said memory, said method being performed by executing said set of instructions.
Based on the disclosure of the embodiment, the beneficial effects of the embodiment of the application include that the workload of manually collecting picture materials and manually marking can be reduced by the processing method of the embodiment of the application, the efficiency of obtaining training data of the target model for generating the target design drawings in batch is improved, and a user of the target model trained by the target parameters can accurately and conveniently obtain the desired design drawings, so that the user experience is improved while convenience is brought to the user. In addition, on the other hand, the success rate of the target design drawing meeting the requirements of the user and the production efficiency of the target design drawing are improved, and the probability of abandoning the design drawing can be effectively reduced at least in a certain proportion, namely the generation of the design drawing which cannot meet the requirements of the user is reduced, so that the processing load of equipment and even workers on the design drawing is reduced.
Drawings
FIG. 1 is a flow chart of a processing method in an embodiment of the invention.
FIG. 2 is a flow chart of a processing method according to another embodiment of the invention.
FIG. 3 is a flow chart of a practical application of the processing method in another embodiment of the present invention.
Fig. 4 is a block diagram of a processing device according to an embodiment of the present invention.
Fig. 5 is a block diagram of an electronic device in an embodiment of the present invention.
Detailed Description
Specific embodiments of the present application will be described in detail below with reference to the accompanying drawings, but the present application is not limited thereto.
It will be understood that various modifications may be made to the embodiments disclosed herein. The following description is, therefore, not to be taken in a limiting sense, but is made merely as an exemplification of embodiments. Other modifications will occur to those skilled in the art within the scope and spirit of the disclosure.
The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the disclosure and, together with a general description of the disclosure given above, and the detailed description of the embodiments given below, serve to explain the principles of the disclosure.
These and other characteristics of the present application will become apparent from the following description of preferred forms of embodiment, given as non-limiting examples, with reference to the attached drawings.
It should also be understood that, although the present application has been described with reference to some specific examples, a person of skill in the art shall certainly be able to achieve many other equivalent forms of application, having the characteristics as set forth in the claims and hence all coming within the field of protection defined thereby.
The above and other aspects, features and advantages of the present disclosure will become more apparent in view of the following detailed description when taken in conjunction with the accompanying drawings.
Specific embodiments of the present disclosure are described hereinafter with reference to the accompanying drawings; however, it is to be understood that the disclosed embodiments are merely examples of the disclosure that may be embodied in various forms. Well-known and/or repeated functions and structures have not been described in detail so as not to obscure the present disclosure with unnecessary or unnecessary detail. Therefore, specific structural and functional details disclosed herein are not to be interpreted as limiting, but merely as a basis for the claims and as a representative basis for teaching one skilled in the art to variously employ the present disclosure in virtually any appropriately detailed structure.
The specification may use the phrases "in one embodiment," "in another embodiment," "in yet another embodiment," or "in other embodiments," which may each refer to one or more of the same or different embodiments in accordance with the disclosure.
Hereinafter, embodiments of the present application will be described in detail with reference to the accompanying drawings.
As shown in fig. 1, an embodiment of the present invention provides a processing method, including:
S1O, obtaining first characteristic data, wherein the first characteristic data is used for generating a design drawing;
S2O, generating a first number of plans at least based on the first characteristic data;
S3O, responding to at least one operation meeting the condition, determining a first target parameter;
S4O, training a first target model based on at least the first target parameter;
wherein the first target model is used for outputting a target design drawing.
The processing method of the embodiment is used for generating training data for training a model capable of outputting a required design drawing, so as to solve the problem that training data is obtained by manually capturing a large number of pictures and manually labeling in the related art, so that a user adopting the processing method of the scheme can efficiently and conveniently obtain the training data of a target model for outputting the target design drawing, and thus the target design drawing is obtained based on a target label.
For example, a user wants to obtain a logo design drawing or a poster design drawing of a certain type, and the poster design drawing is taken as an example in this embodiment for explanation. Firstly, a user inputs a set of information into a data processing device, such as a system or an electronic device of a computer, a graphic processing device, and the like, based on an input device such as a touch interface or a keyboard, or through an acquisition device such as a camera, and the set of information may include some feature data, such as text data that may be input for the user, and image data, for describing a poster design drawing that the user wants to obtain. In other embodiments, the first feature data may also be modular content included in the design drawing. The system or the electronic device generates a first number of design drawings based on the received feature data, the generation mode may be that the first number of design drawings are obtained based on a graphic output model, or the first number of design drawings are associated and related in a corresponding design drawing library based on the feature data, the association mode may be that the feature data is directly or abstracted into keywords and/or association relations among the keywords, and then the related design drawings in the design drawing library are obtained based on retrieval. After obtaining the first number of design drawings, the design drawings may be displayed based on a certain policy, at this time, the user may perform a further screening operation or an operation of associating identifiers based on the display information of each design drawing, that is, obtain a second number of design drawings desired or expected by the user through at least one operation satisfying a condition, where the second number is smaller than the first number, then perform an operation of determining a first target parameter on the second number of design drawings, such as classifying or clustering or screening labels attached to the second number of design drawings, and then determine the first target parameter based on a classification result or a clustering result or a screening result, where the first target parameter may be used as training data for training a target model capable of outputting a target design drawing, so as to train the first target model through the first target parameter, and the user can conveniently obtain the target design drawing through the first target model. Therefore, the processing method of the embodiment of the application can not only improve the determination speed of the target parameters, the success rate of the target design drawing meeting the requirements of the user and the production efficiency of the target design drawing, but also effectively reduce the probability of abandoning the design drawing at least in a certain proportion, namely reduce the generation of the design drawing which cannot meet the requirements of the user, thereby reducing the processing load of equipment and even workers on the design drawing.
Further, as shown in fig. 2, the step S1O of obtaining the first feature data includes:
S1O1, obtaining first characteristic data based on the attribute information of the design drawing;
wherein the attribute information characterizes constituent elements of the design drawing.
That is, the first characteristic data in the embodiment is obtained based on the attribute information of the target design drawing to be obtained, and the attribute information may include at least one of the following:
design drawing color matching rule data, design drawing page material layout rule data, elements contained in design drawing materials, emotion type data reflected by design drawing contents and the like.
That is, the attribute information at least includes data of the constituent elements, the style type, and the like of the design drawing, and based on the attribute information, the system or the electronic device can basically know the content, the style type, and the like of the target design drawing. The attribute information of the design drawing may be included in instruction information input by the user into the system or the electronic device, that is, instruction information input by the user for generating what design drawing is included in the design drawing. The first feature data may be all data included in the attribute information or may be part of the data included in the attribute information. For example, the system or the electronic device may analyze and understand the feature data in the attribute information by itself, determine the true intention of the user, and then filter the data in the attribute information based on the analysis result to determine the first feature data.
In other embodiments, the attribute information may also characterize display parameters of the design drawing, such as display brightness, size, contrast, and the like, and further, the attribute information may also characterize authority information of the design drawing to characterize whether the design drawing can be edited and modified.
Specifically, for example, continuing with the above-described embodiment, the system or the electronic device, after receiving the feature data input by the user, identifies the feature data, and determines attribute information for characterizing the attribute of the target design poster, which is specifically the design drawing color matching rule data, the design drawing page material layout rule data, the elements included in the design drawing material, the emotion type data reflected by the design drawing content, and so on, as described above, such as the color matching rule data including a blue hue, the emotion type data characterizing the happy mood, and so on, included in the attribute information. The system or electronic device then determines, based on the attribute information, first characteristic data that reflects the user's actual desire for the poster design, which may include all or some of the attribute information.
In other embodiments, the user may also input a foreground description of the design drawing to be generated, such as which characteristics, colors, styles, layout and constituent elements, and proportions of each element are provided in the design drawing desired to be output, and the system or the electronic device may determine the first feature data for generating the design drawing after obtaining the above feature data for characterizing the attribute information of the design drawing.
Further, with continued reference to fig. 2 and 3, generating a first number of plans based at least on the first feature data by S2O includes:
s201, determining a material library matched with the first characteristic data;
s202, generating a first number of design drawings based on the material library and a first strategy;
wherein each design has parameters for characterizing the design.
For example, the above-described embodiment continues, wherein a plurality of material libraries are pre-stored in the system or the electronic device, and the material types or material representations in the plurality of material libraries have different meanings, such as a first material library containing structural materials, a second material library containing warm-tone color materials, a third material library containing cold-tone color materials, and a fourth material library containing structural distribution rules, arrangement materials, and the like, such as randomly stacked distribution rules, overall arrangement rules, high-high and low classification arrangement rules, and the like. The system or the electronic device can determine which material library or material libraries the first characteristic data is matched with after being analyzed, and the method can be determined according to the specific expression meaning of the characteristic data contained in the first characteristic data, and if the first characteristic data contains the characteristic data representing warm and soft meanings, the material library with curve-shaped and streamline-shaped structure materials and the material library with warm-tone color matching materials can be determined to be matched with the first characteristic data. Then, after the system or electronic device determines a library of materials, the system or electronic device generates a first number of candidate poster designs based on the library of materials and a first policy. The first policy may be how to select specific materials in the material library and how to use the materials, or may be a policy of classifying the overall style and color matching of the design drawing, or a policy of classifying the production quantity of each type of design drawing, a policy of classifying and storing the design drawing, and the like.
In order to facilitate later determination of the characteristics of each design drawing, when the design drawing is selected or screened, the system or the electronic device may generate parameters matching the characteristics of the design drawing at the same time as each design drawing is generated, for example, the parameters characterizing the characteristics of the design drawing may be corresponding parameters of the materials adopted by the design drawing, that is, the materials in each material library have the parameters matching therewith and representing the materials, and the parameters include at least one or more of the following parameters:
display angle parameter, display size parameter, display scale parameter, display color parameter, display brightness parameter, and display position parameter
The set of the plurality of materials forms a corresponding design drawing, and the set of the specific materials used by the design drawing can represent the characteristics of the design drawing.
Specifically, for example, the system or the electronic device knows that the user wants to obtain a poster design drawing of a blue color system, which is easy and cheerful and makes people feel happy based on the attribute information of the target poster design drawing, so the system or the electronic device can analyze and determine a color tone matching rule for selecting a blue color tone and matching the blue color tone, select a material with a larger display proportion and a larger size, a higher display brightness parameter, a middle display position parameter, two sides of a picture and the like, and select a very simple wind and diffusion type material layout rule, an arrangement rule and the like so as to cooperatively create a poster design drawing of a beach style, an ocean style and a vacation style.
Further, S30, in response to the at least one operation satisfying the condition, determining the target parameter includes:
s301, responding to the evaluation operation of the first number of the design drawings, and associating first identification information or second identification information for each design drawing;
s302, extracting parameters of the design drawing associated with the first identification information based on the second strategy, and processing the extracted parameters to obtain a first target parameter.
For example, the system or the electronic device receives the evaluation operation of each poster design drawing in the first quantity, which is input by the user based on the input device or the acquisition device, or calculated and output by the data processing module in the system or the electronic device, and determines the identification information of the poster design drawing corresponding to the evaluation operation based on the evaluation operation, specifically, the identification information may be the first identification information or the second identification information. In the embodiment, the first identification information represents that the poster design drawing is qualified in design and basically meets the design requirement input by a user in advance; the second identification information represents that the poster design drawing is not designed properly and cannot meet the design requirements expected by the user. Then, the system or the electronic device extracts parameters of the poster design drawing associated with the first identification information based on a second policy, that is, extracts parameters of the design drawing evaluated as a design passing through according to the second policy, where the parameters may be the parameters representing the characteristics of the design drawing, and the second policy may be a policy of extracting the number and the type of the parameters, such as a policy of selectively extracting part of the parameters, or a technical policy of extracting the parameters, and is not specific. After the parameters are extracted, the system or the electronic equipment processes the extracted parameters to obtain first target parameters.
Specifically, the evaluation operation for the first number of design drawings in step S301 includes:
s300, determining evaluation operation on a first number of design drawings based on the obtained identification input information; or the like, or, alternatively,
an evaluation operation for the first number of plans is determined based on the obtained evaluation information.
For example, as shown in fig. 3, the first evaluation operation is an evaluation operation manually implemented by a user, that is, after the system or the electronic device outputs a first number of individual poster design drawings, the user personally reviews the individual poster design drawings, determines that evaluation result information and identification information about the individual poster design drawings are input based on the input device or the acquisition device, and inputs identification input information corresponding to the evaluation result information into the system or the electronic device, so that the system or the electronic device obtains the evaluation operation of the individual poster design drawings. Alternatively, the system or the electronic device may determine evaluation result information for each of the first number of poster designs from a design having a design similar to that of each poster design and corresponding historical evaluation information integrated with user instruction information for generating the design, and instruction information for obtaining a target poster design input in advance by a user, and determine a corresponding evaluation operation based on the generation of the evaluation result information.
Wherein, the identification input information is identification information for evaluating each design drawing, namely labeling or associating identification information for each design drawing; the obtained evaluation information comprises identity information of an evaluator, identity information of a designer and historical evaluation information of similar design drawings, and when each design drawing is evaluated, an evaluation result of each design drawing can be obtained based on the obtained evaluation information. If the historical evaluation information of the designer is obtained based on the identity information of the designer, and then the evaluation result of each design drawing is estimated based on the historical evaluation information; and if the evaluation result estimation is carried out on each design drawing based on the historical evaluation information of the similar design drawings, or the evaluation result estimation is carried out on each design drawing based on the historical evaluation information of the designer, so that the evaluation result information is obtained.
The evaluation operation in this embodiment may specifically be a scoring operation, for example, evaluation result data of each material, color matching rule, material distribution rule, and the like in each poster design drawing is evaluated/scored based on a history similarity map, a preset matching degree rule for characterizing an effect to be expressed by a material selected by a poster design drawing and a target poster design drawing, and corresponding parameters such as each material in each poster design drawing and the used rule are evaluated/scored, and then a poster design drawing whose total score satisfies a first preset score threshold is determined to be a qualified poster design drawing, which may be associated with first identification information, and a poster design drawing which does not satisfy the score threshold is determined to be an unqualified poster design drawing, which is associated with second identification information. Wherein the score information of each poster design drawing forms part or all of the evaluation result information.
Further, the method for extracting parameters of the design drawing associated with the first identification information based on the second policy includes, when executing S302, processing the extracted parameters:
s3021, obtaining evaluation result information of each design drawing associated with the first identification information, the evaluation result information being generated based on the evaluation operation;
s3022, extracting parameters of the design drawing which satisfies the parameter extraction conditions and is associated with the first identification information based on the evaluation result information, and processing the extracted parameters;
wherein the parameter extraction condition is related to the evaluation result information.
Specifically, the poster design drawings associated with the first identification information are classified or ordered, and the specific classification mode can be based on evaluation result information obtained by each design drawing, namely machine scoring or manual scoring criteria; the method further includes the steps of selecting the first n design drawings in the sequence with the highest score to carry out parameter extraction, processing the parameters and then using the processed parameters to train the first target model, wherein the sorting mode can be realized based on the degree of association with the first feature data, and then the design drawings which satisfy the parameter extraction conditions and are associated with the first identification information can be regarded as the design drawings with the higher degree of association with the first feature data, so that the accuracy can be improved when the target design drawings are generated based on the first target model.
For example, the system or the electronic device extracts the evaluation result information of the poster design drawing associated with the first identification information from all the received evaluation result information, and after the result information is extracted, the system or the electronic device processes the extracted result information, for example, extracts the parameters corresponding to the materials and the rules corresponding to the poster design drawing with the total score meeting the second preset score threshold value, and sets the parameters as the first target parameters. That is, the system or the electronic device may perform secondary screening on the selected qualified poster design drawing based on the evaluation result information, finally determine an optimal poster design drawing, and determine, as the first target parameter, each parameter included in the optimal poster design drawing according to the optimal poster design drawing, for training the first target model.
Further, the method in this embodiment further includes:
s50, extracting parameters of the design drawing associated with the second identification information based on the third strategy, and processing the extracted parameters to obtain a second target parameter;
s60, training a second target model based on the second target parameters;
the design drawing associated with the second identification information is a design drawing in the first quantity of design drawings except the design drawing associated with the first identification information, and the second target model is used for filtering feature data which do not conform to the first target model. And
and S70, outputting the target design drawing based on at least the first target model and the second model.
That is, in the previous step, the second target model is trained according to the parameters of the unqualified design drawing, so that the second target model can screen the feature data, which is input to the first target model by a user and used for describing the target design drawing to be obtained, the feature data, which can mislead the first target model to generate the design drawing with the second identification information, is removed, and the efficiency of generating the target design drawing by the first target model is improved.
Specifically, for example, the system or the electronic device may perform parameter extraction on the poster design drawings associated with the second identification information based on a third policy similar to the second policy (see above), specifically, classify or sort the poster design drawings associated with the second identification information, specifically, classify the poster design drawings based on the evaluation result information obtained from each design drawing, that is, machine scoring or manual scoring, as a criterion, further, select the top n design drawings in the sorted sequence to perform parameter extraction, the parameters are processed and used for training a second target model, the sorting mode can also be realized based on the correlation degree with the first characteristic data, the blueprint associated with the second identification information satisfying the parameter extraction condition can be regarded as a blueprint less associated with the first feature data, thereby, the accuracy can be improved when generating the target design drawing based on the first target model and the second target model. Then, the parameters are judged and graded based on the parameters, the parameters contained in the poster design drawing with the low score and the total score within the unqualified score threshold range are determined as second target parameters, a second target model is trained based on the second target parameters, so that the second target model can identify and filter the characteristic data input into the first target model by a user based on an input device and the like, the characteristic data which can influence the first target model to output the unqualified poster design drawing is screened out, and in the process of generating the target poster design drawing by the second target model and the first target model, the characteristic data to be input into the first target model are processed in advance by the second target model, so that the characteristic data entering the first target model are screened data which are helpful for the first target model to generate and output the target model rapidly, efficiently and accurately, therefore, the working efficiency of the first target model is greatly improved, the data processing load of the first target model is effectively reduced, and the response speed of the first target model is improved.
As shown in fig. 4, an embodiment of the present invention also provides a processing apparatus, including:
the system comprises an acquisition module 1, a processing module and a processing module, wherein the acquisition module is used for acquiring first characteristic data, and the first characteristic data is used for generating a design drawing;
a processing module 2 for generating a first number of plans based on at least the first characteristic data and determining a first target parameter in response to at least one operation satisfying a condition; training a first target model based at least on the first target parameters;
wherein the first target model is used for outputting a target design drawing.
The processing method of the embodiment is used for generating training data for training a model capable of outputting a required design drawing, so as to solve the problem that training data is obtained by manually capturing a large number of pictures and manually labeling in the related art, so that a user adopting the processing method of the scheme can efficiently and conveniently obtain the training data of a target model for outputting the target design drawing, and thus the target design drawing is obtained based on a target label.
For example, a user wants to obtain a logo design drawing or a poster design drawing of a certain type, and the poster design drawing is taken as an example in this embodiment for explanation. First, a user may input a set of information into the acquisition module 1 of a data processing device, such as a computer, a graphic processing device, and the like, based on a virtual input device, where the set of information may include some feature data, such as text data that may be input for the user, and image data for describing a poster design drawing that the user wants to obtain, and in other embodiments, the first feature data may also be modular content included in the design drawing, and the like. The obtaining module 1 inputs the obtained first feature data into the processing module 2, so that the processing module 2 generates a first number of design drawings based on the received feature data, where the generation manner may be to obtain the first number of design drawings based on a graph output model, or may be to associate related design drawings in a corresponding design drawing library based on the feature data, and the association manner may be to directly or abstract the feature data into keywords and/or association relations among the keywords, and then obtain the related design drawings in the design drawing library based on retrieval. After obtaining the first number of design drawings, the design drawings may be displayed based on a certain policy, at this time, the user may perform a further screening operation or an operation of associating identifiers based on the display information of each design drawing, that is, obtain a second number of design drawings desired or expected by the user through at least one operation satisfying a condition, where the second number is smaller than the first number, then perform an operation of determining a first target parameter on the second number of design drawings, such as classifying or clustering or screening labels attached to the second number of design drawings, and then determine the first target parameter based on a classification result or a clustering result or a screening result, where the first target parameter may be used as training data for training a target model capable of outputting a target design drawing, so as to train the first target model through the first target parameter, and the user can conveniently obtain the target design drawing through the first target model.
Therefore, the processing method of the embodiment of the application can not only improve the determination speed of the target parameters, the success rate of the target design drawing meeting the requirements of the user and the production efficiency of the target design drawing, but also effectively reduce the probability of abandoning the design drawing at least in a certain proportion, namely reduce the generation of the design drawing which cannot meet the requirements of the user, thereby reducing the processing load of equipment and even workers on the design drawing.
Further, the obtaining of the first feature data in the present embodiment includes:
obtaining first feature data based on attribute information of the design drawing;
wherein the attribute information characterizes constituent elements of the design drawing.
That is, the first characteristic data in the embodiment is obtained based on the attribute information of the target design drawing to be obtained, and the attribute information may include at least one of the following:
design drawing color matching rule data, design drawing page material layout rule data, elements contained in design drawing materials, emotion type data reflected by design drawing contents and the like.
That is, the attribute information at least includes data such as constituent elements and style types of the design drawing, and based on the attribute information, the obtaining module can basically know the content, style types, and the like of the target design drawing. The attribute information of the design drawing may be included in instruction information input by the user into the system or the electronic device, that is, instruction information input by the user for generating what design drawing is included in the design drawing. The first feature data may be all data included in the attribute information or may be part of the data included in the attribute information. For example, the obtaining module may analyze and understand the feature data in the attribute information by itself, determine the true intention of the user, and then filter the data in the attribute information based on the analysis result to determine the first feature data.
In other embodiments, the attribute information may also characterize display parameters of the design drawing, such as display brightness, size, contrast, and the like, and further, the attribute information may also characterize authority information of the design drawing to characterize whether the design drawing can be edited and modified.
Specifically, for example, continuing with the above-mentioned embodiment, after receiving the feature data input by the user, the obtaining module identifies the feature data, and determines attribute information for characterizing the attribute of the target design poster, which is specifically the design drawing color matching rule data, the design drawing page material layout rule data, the elements included in the design drawing material, the emotion type data reflected by the design drawing content, and so on, as for example, the color matching rule data including a blue hue, the representation clearness, the emotion type data with joy, and so on included in the attribute information. Then, the obtaining module determines first characteristic data capable of reflecting actual wishes of users for poster design drawings based on the attribute information, wherein the first characteristic data can comprise all data in the attribute information and can also comprise part of the data.
In other embodiments, the user may also input a foreground description of the design drawing to be generated, such as which characteristics, colors, styles, layout and constituent elements, and proportions of each element are provided in the design drawing desired to be output, and the system or the electronic device may determine the first feature data for generating the design drawing after obtaining the above feature data for characterizing the attribute information of the design drawing.
Further, the processing module 2 generating a first number of plans based on at least the first feature data comprises:
determining a material library matched with the first characteristic data;
generating a first number of design drawings based on the material library and a first strategy;
wherein each design has parameters for characterizing the design.
For example, the above embodiment is continued, wherein the processing module 2 is pre-stored with a plurality of material libraries, the material types or the material meanings of the plurality of material libraries are different, for example, the first material library contains the materials of the structure class, the second material library contains the warm-tone color matching materials, the third material library contains the cold-tone color matching materials, the fourth material library contains the materials of the structure distribution rule and the arrangement mode, for example, the distribution rule of the disordered pile, the rule of the whole arrangement, the high-high and low classification arrangement rule, and the like. The processing module 2 may determine, after analyzing, which material library or material libraries the first feature data matches, specifically according to the specific expression meaning of the feature data included in the first feature data, and if the first feature data includes feature data representing warm and soft meanings, it may determine that a material library having a curved-shaped and streamlined structure material and a material library having a warm-tone color matching material match the first feature data. Then, after the processing module 2 determines the corpus, the processing module 2 generates a first number of candidate poster designs based on the corpus and the first policy. The first policy may be how to select specific materials in the material library and how to use the materials, or may be a policy of classifying the overall style and color matching of the design drawing, or a policy of classifying the production quantity of each type of design drawing, a policy of classifying and storing the design drawing, and the like.
In order to facilitate later determination of characteristics of each design drawing, for example, when selecting and screening the design drawings, the processing module 2 may generate parameters matching the characteristics of the design drawing while generating each design drawing, for example, the parameters characterizing the characteristics of the design drawing may be corresponding parameters of materials used by the design drawing, that is, the materials in each material library have parameters matching therewith and representing the materials, and the parameters include at least one or more of the following parameters:
display angle parameter, display size parameter, display scale parameter, display color parameter, display brightness parameter, and display position parameter
The set of the plurality of materials forms a corresponding design drawing, and the set of the specific materials used by the design drawing can represent the characteristics of the design drawing.
Specifically, for example, the processing module 2 knows that the user wants to obtain a poster design drawing of a blue color system, relaxation and joy type, which makes people feel happy, based on the attribute information of the target poster design drawing, so the processing module 2 can analyze and determine a hue matching rule for selecting a blue hue and matching the blue hue, select a material with a larger display ratio and a larger size, a higher display brightness parameter, a middle display position parameter and two sides of a picture, and select a simple wind, a diffusion type material layout rule, an arrangement rule and the like, so as to create a poster design drawing of a beach style, an ocean style and a vacation style in a matching manner.
Further, in the present embodiment, the processing module 2, in response to at least one operation satisfying the condition, determines the target parameter including:
in response to an evaluation operation on a first number of the design drawings, associating first identification information or second identification information for each design drawing;
and extracting parameters of the design drawing associated with the first identification information based on a second strategy, and processing the extracted parameters to obtain a first target parameter.
For example, the processing module 2 receives the evaluation operation of each poster design drawing in the first quantity, which is input by the user based on the input device or the acquisition device described above, or calculated and output by the data processing module 2 in the processing module 2, and determines the identification information of the poster design drawing corresponding to the evaluation operation based on the evaluation operation, specifically, the first identification information or the second identification information. In the embodiment, the first identification information represents that the poster design drawing is qualified in design and basically meets the design requirement expected by a user; the second identification information represents that the poster design drawing is not designed properly and cannot meet the design requirements input by the user in advance. Next, the processing module 2 extracts parameters of the poster design drawing associated with the first identification information based on a second policy, that is, extracts parameters of the design drawing evaluated as a design passing through according to the second policy, where the parameters may be the parameters characterizing the characteristics of the design drawing, and the second policy may be a policy of extracting the number and the type of the parameters, such as a policy of selectively extracting part of the parameters, or a technical policy of implementing parameter extraction, and is not particularly determined. After the parameters are extracted, the processing module 2 processes the extracted parameters to obtain first target parameters.
Specifically, the evaluation operation of the first number of design drawings in the above steps includes:
determining an evaluation operation for the first number of plans based on the obtained identification input information; or the like, or, alternatively,
an evaluation operation for the first number of plans is determined based on the obtained evaluation information.
For example, the first evaluation operation is an evaluation operation manually implemented by a user, that is, the processing module 2 outputs a first number of prepared individual poster design drawings, and after the user personally reviews the individual poster design drawings, it is determined that evaluation result information and identification information about the individual poster design drawings are input based on the input device or the acquisition device, and identification input information corresponding to the evaluation result information is input into the processing module 2, so that the processing module 2 obtains the evaluation operation of the individual poster design drawings. Alternatively, the processing module 2 may determine the evaluation result information of each of the first number of poster designs from a design having a similar design to each poster design and corresponding historical evaluation information integrated with user instruction information for generating the design, and instruction information for obtaining a target poster design input in advance by a user, and determine the corresponding evaluation operation based on the generation of the evaluation result information.
Wherein, the identification input information is identification information for evaluating each design drawing, namely labeling or associating identification information for each design drawing; the obtained evaluation information comprises identity information of an evaluator, identity information of a designer and historical evaluation information of similar design drawings, and when each design drawing is evaluated, an evaluation result of each design drawing can be obtained based on the obtained evaluation information. If the historical evaluation information of the designer is obtained based on the identity information of the designer, and then the evaluation result of each design drawing is estimated based on the historical evaluation information; and if the evaluation result estimation is carried out on each design drawing based on the historical evaluation information of the similar design drawings, or the evaluation result estimation is carried out on each design drawing based on the historical evaluation information of the designer, so that the evaluation result information is obtained.
The evaluation operation in this embodiment may specifically be a scoring operation, for example, evaluation result data of each material, color matching rule, material distribution rule, and the like in each poster design drawing is evaluated/scored based on a history similarity map, a preset matching degree rule for characterizing an effect to be expressed by a material selected by a poster design drawing and a target poster design drawing, and corresponding parameters such as each material in each poster design drawing and the used rule are evaluated/scored, and then a poster design drawing whose total score satisfies a first preset score threshold is determined to be a qualified poster design drawing, which may be associated with first identification information, and a poster design drawing which does not satisfy the score threshold is determined to be an unqualified poster design drawing, which is associated with second identification information. Wherein the score information of each poster design drawing forms part or all of the evaluation result information.
Further, the processing module 2, when performing parameter extraction on the design drawing associated with the first identification information based on the second policy, includes:
obtaining evaluation result information of each design drawing associated with the first identification information, the evaluation result information being generated based on an evaluation operation;
performing parameter extraction on the design drawing which meets the parameter extraction condition and is associated with the first identification information based on the evaluation result information, and processing the extracted parameters;
wherein the parameter extraction condition is related to the evaluation result information.
Specifically, the poster design drawings associated with the first identification information are classified or ordered, and the specific classification mode can be based on evaluation result information obtained by each design drawing, namely machine scoring or manual scoring criteria; the method further includes the steps of selecting the first n design drawings in the sequence with the highest score to carry out parameter extraction, processing the parameters and then using the processed parameters to train the first target model, wherein the sorting mode can be realized based on the degree of association with the first feature data, and then the design drawings which satisfy the parameter extraction conditions and are associated with the first identification information can be regarded as the design drawings with the higher degree of association with the first feature data, so that the accuracy can be improved when the target design drawings are generated based on the first target model.
For example, the processing module 2 extracts evaluation result information of the poster design drawing associated with the first identification information from all the received evaluation result information, and after the result information is extracted, the processing module 2 processes the extracted result information, for example, extracts parameters corresponding to each material and rule corresponding to the poster design drawing with the total score satisfying the second preset score threshold, and sets the parameters as the first target parameters. That is, the processing module 2 may perform secondary screening on the selected qualified poster design drawing based on the evaluation result information, finally determine an optimal poster design drawing, and determine, as the first target parameter, each parameter included in the optimal poster design drawing according to the optimal poster design drawing, for training the first target model.
Further, the processing module 2 in this embodiment is further configured to:
extracting parameters of the design drawing associated with the second identification information based on a third strategy, and processing the extracted parameters to obtain second target parameters;
training a second target model based on the second target parameters;
the design drawing associated with the second identification information is a design drawing in the first quantity of design drawings except the design drawing associated with the first identification information, and the second target model is used for filtering feature data which do not conform to the first target model. And
and outputting the target design drawing based on at least the first target model and the second model.
That is, in the previous step, the second target model is trained according to the parameters of the unqualified design drawing, so that the second target model can screen the feature data, which is input to the first target model by a user and used for describing the target design drawing to be obtained, the feature data, which can mislead the first target model to generate the design drawing with the second identification information, is removed, and the efficiency of generating the target design drawing by the first target model is improved.
Specifically, for example, the processing module 2 may perform parameter extraction on the poster design drawings associated with the second identification information based on a third policy similar to the second policy (see above in detail), specifically, classify or sort the poster design drawings associated with the second identification information, specifically, classify the poster design drawings based on the evaluation result information obtained from each design drawing, that is, machine scoring or manual scoring, for the criterion, further, may select the top n design drawings in the sorted sequence to perform parameter extraction, the parameters are processed and used for training a second target model, the sorting mode can also be realized based on the correlation degree with the first characteristic data, the blueprint associated with the second identification information satisfying the parameter extraction condition can be regarded as a blueprint less associated with the first feature data, thereby, the accuracy can be improved when generating the target design drawing based on the first target model and the second target model. Then, the parameters are judged and graded based on the parameters, the parameters contained in the poster design drawing with the low score and the total score within the unqualified score threshold range are determined as second target parameters, a second target model is trained based on the second target parameters, so that the second target model can identify and filter the characteristic data input into the first target model by a user based on an input device and the like, the characteristic data which can influence the first target model to output the unqualified poster design drawing is screened out, and in the process of generating the target poster design drawing by the second target model and the first target model, the characteristic data to be input into the first target model are processed in advance by the second target model, so that the characteristic data entering the first target model are screened data which are helpful for the first target model to generate and output the target model rapidly, efficiently and accurately, therefore, the working efficiency of the first target model is greatly improved, the data processing load of the first target model is effectively reduced, and the response speed of the first target model is improved.
As shown in fig. 5, an electronic device according to an embodiment of the present invention is an electronic device for realizing and implementing the processing apparatus, the electronic device including:
a memory 3 for storing at least one set of instructions;
a processor 4 for calling and executing said set of instructions in said memory 3, by executing said set of instructions, performing the method as described above.
Specifically, first characteristic data is obtained, and the first characteristic data is used for generating a design drawing;
generating a first number of plans based on at least the first feature data and determining a first target parameter in response to at least one operation satisfying a condition; training a first target model based at least on the first target parameters;
wherein the first target model is used for outputting a target design drawing.
Further, in this embodiment, the obtaining the first feature data includes:
obtaining the first characteristic data based on the attribute information of the design drawing;
wherein the attribute information characterizes constituent elements of the design drawing.
Further, in this embodiment, the process module 2, when generating the first number of plans based on at least the first feature data, includes:
determining a material library matched with the first characteristic data;
generating a first number of design drawings based on the material library and a first strategy;
wherein each of the plans has parameters for characterizing the plans.
Further, in response to at least one operation satisfying the condition, the processing module 2 in this embodiment determines the target parameter by:
associating first identification information or second identification information for each of the plans in response to an evaluation operation on the first number of plans;
and extracting parameters of the design drawing associated with the first identification information based on a second strategy, and processing the extracted parameters to obtain the first target parameters.
Further, in this embodiment, the determining, by the processing module 2, the evaluation operation on the first number of design drawings includes:
determining an evaluation operation for the first number of plans based on the obtained identification input information; or the like, or, alternatively,
an evaluation operation for the first number of plans is determined based on the obtained evaluation information.
Further, in this embodiment, the processing module 2 extracts parameters of the design drawing associated with the first identification information based on the second policy, and when processing the extracted parameters, includes:
obtaining evaluation result information of each design drawing associated with the first identification information, the evaluation result information being generated based on the evaluation operation;
performing parameter extraction on the design drawing which satisfies parameter extraction conditions and is associated with the first identification information based on the evaluation result information, and prohibiting processing on the extracted parameters;
wherein the parameter extraction condition is related to the evaluation result information.
Further, in this embodiment, the processing module 2 further includes:
extracting parameters of the design drawing associated with the second identification information based on a third strategy, and processing the extracted parameters to obtain second target parameters;
training a second target model based on the second target parameters;
the design drawing associated with the second identification information is a design drawing in the first quantity of design drawings except the design drawing associated with the first identification information, and the second target model is used for filtering feature data which do not conform to the first target model.
Further, in this embodiment, the processing module 2 further includes:
outputting a target design drawing based on at least the first target model and the second model.
The above embodiments are only exemplary embodiments of the present application, and are not intended to limit the present application, and the protection scope of the present application is defined by the claims. Various modifications and equivalents may be made by those skilled in the art within the spirit and scope of the present application and such modifications and equivalents should also be considered to be within the scope of the present application.
Claims (10)
1. A method of processing, comprising:
obtaining first characteristic data, wherein the first characteristic data is used for generating a design drawing;
generating a first number of plans based on at least the first feature data;
determining a first target parameter in response to at least one operation satisfying a condition;
training a first target model based at least on the first target parameters;
wherein the first target model is used for outputting a target design drawing.
2. The method of claim 1, wherein the obtaining first feature data comprises:
obtaining the first characteristic data based on the attribute information of the design drawing;
wherein the attribute information characterizes constituent elements of the design drawing.
3. The method of claim 1, wherein the generating a first number of blueprints based at least on the first feature data comprises:
determining a material library matched with the first characteristic data;
generating a first number of design drawings based on the material library and a first strategy;
wherein each of the plans has parameters for characterizing the plans.
4. The method of claim 3, wherein the determining a first target parameter in response to at least one operation satisfying a condition comprises:
associating first identification information or second identification information for each of the plans in response to an evaluation operation on the first number of plans;
and extracting parameters of the design drawing associated with the first identification information based on a second strategy, and processing the extracted parameters to obtain the first target parameters.
5. The method of claim 4, wherein the evaluating operation on the first number of plans comprises:
determining an evaluation operation for the first number of plans based on the obtained identification input information; or the like, or, alternatively,
an evaluation operation for the first number of plans is determined based on the obtained evaluation information.
6. The method of claim 4, wherein the extracting parameters of the design drawing associated with the first identification information based on the second policy comprises:
obtaining evaluation result information of each design drawing associated with the first identification information, the evaluation result information being generated based on the evaluation operation;
performing parameter extraction on the design drawing which satisfies parameter extraction conditions and is associated with the first identification information based on the evaluation result information, and processing the extracted parameters;
wherein the parameter extraction condition is related to the evaluation result information.
7. The method of claim 4, further comprising:
extracting parameters of the design drawing associated with the second identification information based on a third strategy, and processing the extracted parameters to obtain second target parameters;
training a second target model based on the second target parameters;
the design drawing associated with the second identification information is a design drawing in the first quantity of design drawings except the design drawing associated with the first identification information, and the second target model is used for filtering feature data which do not conform to the first target model.
8. The method of claim 7, further comprising:
outputting a target design drawing based on at least the first target model and the second model.
9. A processing apparatus, comprising:
the acquisition module is used for acquiring first characteristic data, and the first characteristic data is used for generating a design drawing;
a processing module for generating a first number of plans based on at least the first feature data, and in response to at least one operation satisfying a condition, determining a first target parameter, training a first target model based on at least the first target parameter;
wherein the first target model is used for outputting a target design drawing.
10. An electronic device, comprising:
a memory for storing at least one set of instructions;
a processor for invoking and executing said set of instructions in said memory, the method of any of claims 1 to 8 being performed by executing said set of instructions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910938111.XA CN110689079B (en) | 2019-09-30 | 2019-09-30 | Processing method, processing device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910938111.XA CN110689079B (en) | 2019-09-30 | 2019-09-30 | Processing method, processing device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110689079A true CN110689079A (en) | 2020-01-14 |
| CN110689079B CN110689079B (en) | 2023-01-17 |
Family
ID=69111051
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910938111.XA Active CN110689079B (en) | 2019-09-30 | 2019-09-30 | Processing method, processing device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110689079B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108062341A (en) * | 2016-11-08 | 2018-05-22 | 中国移动通信有限公司研究院 | The automatic marking method and device of data |
| CN109492249A (en) * | 2018-09-26 | 2019-03-19 | 深圳变设龙信息科技有限公司 | Rapid generation, device and the terminal device of design drawing |
| CN109815448A (en) * | 2019-02-02 | 2019-05-28 | 天津字节跳动科技有限公司 | Lantern slide generation method and device |
| CN110008450A (en) * | 2018-01-05 | 2019-07-12 | 阿里巴巴集团控股有限公司 | Generation method, device, equipment and the medium of picture |
| US10402726B1 (en) * | 2018-05-03 | 2019-09-03 | SparkCognition, Inc. | Model building for simulation of one or more target features |
-
2019
- 2019-09-30 CN CN201910938111.XA patent/CN110689079B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108062341A (en) * | 2016-11-08 | 2018-05-22 | 中国移动通信有限公司研究院 | The automatic marking method and device of data |
| CN110008450A (en) * | 2018-01-05 | 2019-07-12 | 阿里巴巴集团控股有限公司 | Generation method, device, equipment and the medium of picture |
| US10402726B1 (en) * | 2018-05-03 | 2019-09-03 | SparkCognition, Inc. | Model building for simulation of one or more target features |
| CN109492249A (en) * | 2018-09-26 | 2019-03-19 | 深圳变设龙信息科技有限公司 | Rapid generation, device and the terminal device of design drawing |
| CN109815448A (en) * | 2019-02-02 | 2019-05-28 | 天津字节跳动科技有限公司 | Lantern slide generation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110689079B (en) | 2023-01-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI703458B (en) | Data processing model construction method, device, server and client | |
| US11238310B2 (en) | Training data acquisition method and device, server and storage medium | |
| US11468550B2 (en) | Utilizing object attribute detection models to automatically select instances of detected objects in images | |
| US20180173788A1 (en) | System And Method For Providing Inclusion-Based Electronically Stored Information Item Classification Suggestions With The Aid Of A Digital Computer | |
| CN110543592B (en) | Information searching method and device and computer equipment | |
| US20080097937A1 (en) | Distributed method for integrating data mining and text categorization techniques | |
| CN109447958B (en) | Image processing method, image processing device, storage medium and computer equipment | |
| WO2020237872A1 (en) | Method and apparatus for testing accuracy of semantic analysis model, storage medium, and device | |
| CN110378206B (en) | Intelligent image examination system and method | |
| CN111179935B (en) | Voice quality inspection method and device | |
| CN110612524B (en) | Information processing apparatus, information processing method, and recording medium | |
| CN107491435A (en) | Method and device based on Computer Automatic Recognition user feeling | |
| CN107436916B (en) | Intelligent answer prompting method and device | |
| JP2008084151A (en) | Information display device and information display method | |
| CN112069326A (en) | Knowledge graph construction method and device, electronic equipment and storage medium | |
| CN113821296B (en) | Visual interface generation method, electronic equipment and storage medium | |
| CN116882414B (en) | Automatic comment generation method and related device based on large-scale language model | |
| CN114253990A (en) | Database query method and device, computer equipment and storage medium | |
| Díaz et al. | A comparative approach between different computer vision tools, including commercial and open-source, for improving cultural image access and analysis | |
| CN107656760A (en) | Data processing method and device, electronic equipment | |
| CN110689079B (en) | Processing method, processing device and electronic equipment | |
| CN114416664A (en) | Information display method, information display device, electronic apparatus, and readable storage medium | |
| CN114266921A (en) | Image description information acquisition method, device, server and storage medium | |
| JP2001022727A (en) | Method and device for classifying and learning text and storage medium storing text classifying and learning program | |
| CN113704623A (en) | Data recommendation method, device, equipment and storage medium |
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 |