阅读说明：本技术 基于ai图像识别的产品原型处理方法、装置及相关设备 (AI image recognition-based product prototype processing method and device and related equipment ) 是由 马亿凯 于 2021-08-31 设计创作，主要内容包括：本申请涉及人工智能技术,提供一种基于AI图像识别的产品原型处理方法、装置、计算机设备与存储介质,包括：获取功能页面截图集；识别所述功能页面截图集中的每一张功能页面截图,得到所述功能页面截图中的目标组件；获取所述目标组件对应的目标元素以及所述目标元素对应的初始属性信息；获取预设需求文档,并从所述预设需求文档中获取所述目标元素对应的目标需求信息；根据所述目标需求信息调整所述初始属性信息,得到目标属性信息；根据所述目标属性信息在预设编辑器中组合所述目标组件,得到目标页面原型。本申请能够提高产品原型的处理效率,促进智慧城市的快速发展。(The application relates to artificial intelligence technology, and provides a product prototype processing method, a device, computer equipment and a storage medium based on AI image recognition, which comprises the following steps: acquiring a function page cutting set; identifying each functional page screenshot in the functional page screenshot set to obtain a target component in the functional page screenshot; acquiring a target element corresponding to the target component and initial attribute information corresponding to the target element; acquiring a preset demand document, and acquiring target demand information corresponding to the target element from the preset demand document; adjusting the initial attribute information according to the target demand information to obtain target attribute information; and combining the target components in a preset editor according to the target attribute information to obtain a target page prototype. The application can improve the processing efficiency of product prototype, promotes the rapid development in wisdom city.)

1. A product prototype processing method based on AI image recognition is characterized by comprising the following steps:

acquiring a function page screenshot set, wherein each function page screenshot in the function page screenshot set comprises a plurality of target components;

identifying each functional page screenshot in the functional page screenshot set to obtain the target component in the functional page screenshot;

acquiring a target element corresponding to the target component and initial attribute information corresponding to the target element;

acquiring a preset demand document, and acquiring target demand information corresponding to the target element from the preset demand document;

adjusting the initial attribute information according to the target demand information to obtain target attribute information;

and combining the target components in a preset editor according to the target attribute information to obtain a target page prototype.

2. The AI image recognition-based product prototype processing method according to claim 1, wherein the identifying each of the set of function page screen shots, and the obtaining the target component in the set of function page screen shots comprises:

acquiring a target picture set, and dividing the target picture set into training data and test data by taking the target picture set as input data and a target component contained in each target picture in the target picture set as output data;

inputting the training data into an initial neural network model for training to obtain a component identification model;

inputting the test data into the component recognition model, and calculating the model accuracy of the component recognition model;

detecting whether the model accuracy rate exceeds a preset model accuracy rate threshold value;

and when the detection result is that the model accuracy rate exceeds the preset model accuracy rate threshold value, calling the trained component recognition model to recognize each functional page screenshot in the functional page screenshot set, and obtaining a target component in the functional page screenshot.

3. The AI image recognition-based product prototype processing method according to claim 1, wherein the obtaining of the target element corresponding to the target component and the initial attribute information corresponding to the target element comprises:

acquiring initial component description information corresponding to the target component;

performing word segmentation processing on the initial component description information through a preset word segmentation tool to obtain target component description information;

determining a first keyword in the target component description information, and taking the attached information corresponding to the first keyword as a target element;

and determining a second keyword in the scanning information of the target component, and taking the auxiliary information corresponding to the second keyword as the initial attribute information corresponding to the target element.

4. The AI image recognition-based product prototype processing method according to claim 1, wherein the obtaining target requirement information corresponding to the target element from the preset requirement document comprises:

acquiring the target component and a target element corresponding to the target component;

and according to the mapping relation between the target element and the preset element and the requirement information, obtaining the target requirement information corresponding to the target element.

5. The AI image recognition-based product prototype processing method according to claim 1, wherein the adjusting the initial attribute information according to the target requirement information to obtain target attribute information comprises:

acquiring the target demand information and the initial attribute information;

detecting whether the target demand information is consistent with the initial attribute information;

when the detection result is that the target demand information is inconsistent with the initial attribute information, determining the difference content and the difference position in the target demand information and the initial attribute information;

and adjusting the difference content at the difference position according to the target demand information to obtain target attribute information.

6. The AI image recognition-based product prototype processing method according to claim 1, wherein the combining the target components in a preset editor according to the target attribute information to obtain a target page prototype comprises:

acquiring position attribute information of the target assembly and target attribute information corresponding to each target element in the target assembly;

generating a visual component corresponding to the target element in the preset editor according to the target attribute information;

and combining the positions of the visual components according to the position attribute information to obtain a target page prototype.

7. The AI image recognition-based product prototype processing method of claim 1, wherein the acquiring a set of function page screen shots comprises:

acquiring a function module set required by the target page prototype;

determining demand preference information corresponding to each functional module in the functional module set;

and screening page information containing the functional module set according to the demand preference information, and intercepting a functional page cutout set corresponding to the functional module set from the page information.

8. An AI image recognition-based product prototype processing apparatus, comprising:

the screenshot obtaining module is used for obtaining a functional page screenshot set, wherein each functional page screenshot in the functional page screenshot set comprises a plurality of target components;

the component identification module is used for identifying each functional page screenshot in the functional page screenshot set to obtain the target component in the functional page screenshot;

the attribute acquisition module is used for acquiring a target element corresponding to the target component and initial attribute information corresponding to the target element;

the demand acquisition module is used for acquiring a preset demand document and acquiring target demand information corresponding to the target element from the preset demand document;

the attribute adjusting module is used for adjusting the initial attribute information according to the target demand information to obtain target attribute information;

and the component combination module is used for combining the target components in a preset editor according to the target attribute information to obtain a target page prototype.

9. A computer device characterized in that the computer device comprises a processor for implementing the AI image recognition based product prototype processing method according to any one of claims 1 to 7 when executing a computer program stored in a memory.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the AI image recognition-based product prototype processing method according to any one of claims 1 to 7.

Technical Field

The present application relates to the field of artificial intelligence technologies, and in particular, to a method, an apparatus, a computer device, and a medium for prototype processing of a product based on AI image recognition.

Background

Prototype design is the framing of structured requirements, so the prototype is also called wire-frame diagram. The product prototype is a frame design before the whole product is listed on the market, the product prototype can be used for more clearly knowing the requirements of the product, and the product intention can be more intuitively known by design and technicians or a boss. In the design process of a traditional product prototype, a certain function page screenshot used by a demand party or in an auction product is obtained firstly, then drawing of each component is carried out according to the function page screenshot, and finally a product prototype graph is output. This redesign results in a product prototype that is time-consuming and inefficient to design.

In the process of implementing the present application, the applicant finds that the following technical problems exist in the prior art: at present, some templates which can be directly applied are provided in the industry for product prototype design, but in the actual product design process, because the actual requirements of each scene are different, more universalization is page layout and typesetting, and the personalized requirements of actual functional components are more, so that the modification of the templates is more, and the design efficiency of product prototypes cannot be ensured.

Therefore, it is necessary to provide a product prototype processing method based on AI image recognition, which can improve the processing efficiency of the product prototype.

Disclosure of Invention

In view of the above, it is desirable to provide a product prototype processing method based on AI image recognition, a product prototype processing apparatus based on AI image recognition, a computer device and a medium, which can improve the processing efficiency of product prototypes.

In a first aspect of the embodiments of the present application, a method for processing a product prototype based on AI image recognition is provided, where the method for processing a product prototype based on AI image recognition includes:

acquiring a function page screenshot set, wherein each function page screenshot in the function page screenshot set comprises a plurality of target components;

identifying each functional page screenshot in the functional page screenshot set to obtain the target component in the functional page screenshot;

acquiring a target element corresponding to the target component and initial attribute information corresponding to the target element;

acquiring a preset demand document, and acquiring target demand information corresponding to the target element from the preset demand document;

adjusting the initial attribute information according to the target demand information to obtain target attribute information;

and combining the target components in a preset editor according to the target attribute information to obtain a target page prototype.

Further, in the above method for processing a product prototype based on AI image recognition provided in this embodiment of the present application, the identifying each screenshot of the function page in the set of screenshots of the function page, and obtaining the target component in the screenshot of the function page includes:

acquiring a target picture set, and dividing the target picture set into training data and test data by taking the target picture set as input data and a target component contained in each target picture in the target picture set as output data;

inputting the training data into an initial neural network model for training to obtain a component identification model;

inputting the test data into the component recognition model, and calculating the model accuracy of the component recognition model;

detecting whether the model accuracy rate exceeds a preset model accuracy rate threshold value;

and when the detection result is that the model accuracy rate exceeds the preset model accuracy rate threshold value, calling the trained component recognition model to recognize each functional page screenshot in the functional page screenshot set, and obtaining a target component in the functional page screenshot.

Further, in the above method for processing a product prototype based on AI image recognition provided by the embodiment of the present application, the acquiring a target element corresponding to the target component and initial attribute information corresponding to the target element includes:

acquiring initial component description information corresponding to the target component;

performing word segmentation processing on the initial component description information through a preset word segmentation tool to obtain target component description information;

determining a first keyword in the target component description information, and taking the attached information corresponding to the first keyword as a target element;

and determining a second keyword in the scanning information of the target component, and taking the auxiliary information corresponding to the second keyword as the initial attribute information corresponding to the target element.

Further, in the above method for processing a prototype of a product based on AI image recognition provided in an embodiment of the present application, the acquiring target requirement information corresponding to the target element from the preset requirement document includes:

acquiring the target component and a target element corresponding to the target component;

and according to the mapping relation between the target element and the preset element and the requirement information, obtaining the target requirement information corresponding to the target element.

Further, in the above method for processing a prototype of a product based on AI image recognition provided in an embodiment of the present application, the adjusting the initial attribute information according to the target requirement information to obtain the target attribute information includes:

acquiring the target demand information and the initial attribute information;

detecting whether the target demand information is consistent with the initial attribute information;

when the detection result is that the target demand information is inconsistent with the initial attribute information, determining the difference content and the difference position in the target demand information and the initial attribute information;

and adjusting the difference content at the difference position according to the target demand information to obtain target attribute information.

Further, in the method for processing a prototype of a product based on AI image recognition provided in an embodiment of the present application, the combining the target component in a preset editor according to the target attribute information to obtain a target page prototype includes:

acquiring position attribute information of the target assembly and target attribute information corresponding to each target element in the target assembly;

generating a visual component corresponding to the target element in the preset editor according to the target attribute information;

and combining the positions of the visual components according to the position attribute information to obtain a target page prototype.

Further, in the method for processing a product prototype based on AI image recognition provided in an embodiment of the present application, the acquiring a screenshot set of a function page includes:

acquiring a function module set required by the target page prototype;

determining demand preference information corresponding to each functional module in the functional module set;

and screening page information containing the functional module set according to the demand preference information, and intercepting a functional page cutout set corresponding to the functional module set from the page information.

The second aspect of the embodiments of the present application further provides a product prototype processing apparatus based on AI image recognition, where the product prototype processing apparatus based on AI image recognition includes:

the screenshot obtaining module is used for obtaining a functional page screenshot set, wherein each functional page screenshot in the functional page screenshot set comprises a plurality of target components;

the component identification module is used for identifying each functional page screenshot in the functional page screenshot set to obtain the target component in the functional page screenshot;

the attribute acquisition module is used for acquiring a target element corresponding to the target component and initial attribute information corresponding to the target element;

the demand acquisition module is used for acquiring a preset demand document and acquiring target demand information corresponding to the target element from the preset demand document;

the attribute adjusting module is used for adjusting the initial attribute information according to the target demand information to obtain target attribute information;

and the component combination module is used for combining the target components in a preset editor according to the target attribute information to obtain a target page prototype.

The third aspect of the embodiments of the present application further provides a computer device, which includes a processor, and the processor is configured to implement the method for processing a product prototype based on AI image recognition according to any one of the above items when executing the computer program stored in the memory.

The fourth aspect of the embodiments of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the method for processing a prototype of a product based on AI image recognition is implemented as any one of the above methods.

According to the AI image recognition-based product prototype processing method, the AI image recognition-based product prototype processing device, the computer equipment and the computer-readable storage medium, the AI image is used for recognizing the function page screenshot, the product function design is converted into the editable target component, then the target element corresponding to the target component and the initial attribute information corresponding to the target element are obtained, the initial attribute information is adjusted to the target attribute information, the target component is combined in the preset editor to obtain the target page prototype, the product prototype is prevented from being output in a mode of manually drawing each component in the function page screenshot, and the design efficiency of the product prototype can be improved; in addition, the method and the device can acquire the target demand information corresponding to each target element in the target assembly from the preset demand document, then combine the target assembly according to the target demand information, avoid the mode that the assembly template is directly applied mechanically to complete product prototype design, improve the flexibility of product prototype design and ensure the design efficiency of product prototypes. The intelligent city development method can be applied to various functional modules of intelligent cities such as intelligent government affairs and intelligent traffic, for example, an AI image recognition-based product prototype processing module of the intelligent government affairs can promote the rapid development of the intelligent city.

Drawings

Fig. 1 is a flowchart of a product prototype processing method based on AI image recognition according to an embodiment of the present application.

Fig. 2 is a schematic diagram of a target assembly provided by an embodiment of the present application.

Fig. 3 is a schematic diagram of a target assembly provided in another embodiment of the present application.

Fig. 4 is a block diagram of a product prototype processing apparatus based on AI image recognition according to a second embodiment of the present application.

Fig. 5 is a schematic structural diagram of a computer device provided in the third embodiment of the present application.

The following detailed description will further illustrate the present application in conjunction with the above-described figures.

Detailed Description

In order that the above objects, features and advantages of the present application can be more clearly understood, a detailed description of the present application will be given below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.

In the following description, numerous specific details are set forth to provide a thorough understanding of the present application, and the described embodiments are a part, but not all, of the present application.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.

The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.

The product prototype processing method based on the AI image recognition provided by the embodiment of the invention is executed by computer equipment, and correspondingly, the product prototype processing device based on the AI image recognition is operated in the computer equipment.

Fig. 1 is a flowchart of a product prototype processing method based on AI image recognition according to a first embodiment of the present application. As shown in fig. 1, the AI image recognition-based product prototype processing method may include the following steps, and the sequence of the steps in the flowchart may be changed and some steps may be omitted according to different requirements:

s11, acquiring a function page screenshot set, wherein each function page screenshot in the function page screenshot set comprises a plurality of target components.

In at least one embodiment of the present application, the function page screenshot set includes a plurality of function page screenshots, and the function page screenshot may be a screenshot of a certain function page from a used product or a competitive product of a demand party. For each screenshot of the function page, one or more target components exist, and the target components may include components such as a button component (button) and a segment control (tab), where the button component may be composed of a button and button text, please refer to fig. 2, fig. 2 shows three button components in different display forms, a first button component composed of a transparent button and button text, a second button component composed of a white button and button text, and a third button component composed of a black button and button text. The segmentation component may be composed of several tags, see fig. 3, fig. 3 shows two different presentation forms of segmentation components, the first being a framed segmentation component and the second being a frameless segmentation component. In other embodiments, the button assembly and the segment assembly may be displayed in other manners, which is not limited herein. The function page screenshot sets are stored in a preset database, and can be stored in a target node of the block chain in consideration of the reliability and privacy of data storage.

In an embodiment, the function page screenshot set may be manually intercepted by a demand party, for example, the function page screenshot set may be designed by a traditional business team (also called demand party) or a product manager, when designing a product function, by referring to product design of an APP of the same kind of contest, or by contacting one or two good function designs in a daily use of the APP, and storing a similar function page screenshot locally.

In other embodiments, the function page screenshot set may also be intelligently intercepted by a machine learning method, and optionally, the obtaining the function page screenshot set includes:

acquiring a function module set required by the target page prototype;

determining demand preference information corresponding to each functional module in the functional module set;

and screening page information containing the functional module set according to the demand preference information, and intercepting a functional page cutout set corresponding to the functional module set from the page information.

The function module set may be a set of function modules pre-stored in a preset database and required for designing a target page prototype. For each functional module in the functional module set, there is demand preference information corresponding to the functional module, where the demand preference information may refer to information such as a component type and a component attribute of the functional module. The page information refers to a page containing the function module set in big data.

And S12, identifying each function page screenshot in the function page screenshot set to obtain a target component in the function page screenshot.

In at least one embodiment of the present application, each screenshot of a function page carries one or more target components, and in one embodiment, a component recognition model may be trained in advance, and then the component recognition model is called to process each screenshot of a function page, so as to obtain a target component in the screenshot of a function page. In an embodiment, during model training, input data of the component recognition model is a functional page screenshot labeled with a component name in advance, and output data is a target component of the functional page screenshot. In other embodiments, the input data of the component recognition model may also be a standardized functional component picture stored in a preset database, and the output data is a target component of the screenshot of the functional page.

Optionally, the identifying each functional page screenshot in the set of functional page screenshots, and the obtaining the target component in the set of functional page screenshots includes:

acquiring a target picture set, and dividing the target picture set into training data and test data by taking the target picture set as input data and a target component contained in each target picture in the target picture set as output data;

inputting the training data into an initial neural network model for training to obtain a component identification model;

inputting the test data into the component recognition model, and calculating the model accuracy of the component recognition model;

detecting whether the model accuracy rate exceeds a preset model accuracy rate threshold value;

and when the detection result is that the model accuracy rate exceeds the preset model accuracy rate threshold value, calling the trained component recognition model to recognize each functional page screenshot in the functional page screenshot set, and obtaining a target component in the functional page screenshot.

The target picture can be a functional page screenshot marked with a component name in advance, or a standardized functional component picture. The preset model accuracy threshold is a preset threshold for evaluating model accuracy, for example, the preset model accuracy threshold may be 95%. The training data and the test data may be distributed according to a preset distribution ratio, which may be 7:3, and this is not limited herein.

And S13, acquiring a target element corresponding to the target component and initial attribute information corresponding to the target element.

In at least one embodiment of the present application, the target component includes a number of editable elements therein, each element including corresponding initial attribute information. Illustratively, the button components can be abstracted into three editable elements, a button box shape, a button box fill color, and a button text. For the shape of the button frame, the initial attribute information may be in a shape of a rectangle, an ellipse, or the like; for the button box filling color, the initial attribute information may be gray, green, or the like; for the button text, the initial attribute information may be various text information.

Optionally, the obtaining of the target element corresponding to the target component and the initial attribute information corresponding to the target element includes:

acquiring initial component description information corresponding to the target component;

performing word segmentation processing on the initial component description information through a preset word segmentation tool to obtain target component description information;

determining a first keyword in the target component description information, and taking the attached information corresponding to the first keyword as a target element;

and determining a second keyword in the scanning information of the target component, and taking the auxiliary information corresponding to the second keyword as the initial attribute information corresponding to the target element.

The preset word segmentation tool may be a tool preset by a system worker and used for performing word segmentation processing on the initial component description information, for example, the preset word segmentation tool may be a Chinese word segmentation tool. In a preset database, for each target component, there exists corresponding initial component description information. The initial component description information is information describing each editable element of the target component, and the initial component description information includes element information of the target component and initial attribute information corresponding to each element information. And performing word segmentation processing on the initial attribute information to obtain structured target assembly description information. The first keyword is a keyword for identifying the target element, the second keyword is a keyword for identifying the initial attribute information, and the target element corresponding to the target component and the initial attribute information corresponding to the target element can be obtained by querying the first keyword and the second keyword.

S14, acquiring a preset requirement document, and acquiring target requirement information corresponding to the target element from the preset requirement document.

In at least one embodiment of the present application, the preset requirement document is a document composed by a requirement party according to actual requirements of each target element. The preset requirement document comprises a target assembly, a plurality of target elements contained in the target assembly and target requirement information corresponding to the target elements.

Optionally, the obtaining target requirement information corresponding to the target element from the preset requirement document includes:

acquiring the target component and a target element corresponding to the target component;

and according to the mapping relation between the target element and the preset element and the requirement information, obtaining the target requirement information corresponding to the target element.

And traversing the mapping relation to obtain the target demand information corresponding to the target element.

And S15, adjusting the initial attribute information according to the target demand information to obtain target attribute information.

In at least one embodiment of the present application, the attribute information of each target element in the target requirement information may be different from the initial attribute information, and the target attribute information corresponding to the target element can be obtained by adjusting the initial attribute information according to the target requirement information.

Optionally, the adjusting the initial attribute information according to the target demand information to obtain the target attribute information includes:

acquiring the target demand information and the initial attribute information;

detecting whether the target demand information is consistent with the initial attribute information;

when the detection result is that the target demand information is inconsistent with the initial attribute information, determining the difference content and the difference position in the target demand information and the initial attribute information;

and adjusting the difference content at the difference position according to the target demand information to obtain target attribute information.

The difference content refers to the content where the target demand information and the initial attribute information are different, and the difference position refers to the position information where the content is different.

And S16, combining the target components in a preset editor according to the target attribute information to obtain a target page prototype.

In at least one embodiment of the present application, the preset encoder may be an H5 page editor, and is configured to edit the target components included in the functional page screenshot set, and output a target page prototype. The preset requirement document comprises target components, a plurality of target elements contained in the target components and target requirement information corresponding to the target elements, and also comprises position attribute information of each target component, wherein the position attribute information is used for identifying the position relation of the target components in a product prototype.

Optionally, the combining the target component in a preset editor according to the target attribute information to obtain a target page prototype includes:

acquiring position attribute information of the target assembly and target attribute information corresponding to each target element in the target assembly;

generating a visual component corresponding to the target element in the preset editor according to the target attribute information;

and combining the positions of the visual components according to the position attribute information to obtain a target page prototype.

Wherein the generating of the visualization component corresponding to the target element in the preset editor according to the target attribute information may include: determining a standardized component corresponding to the type information according to the type information in the target attribute information; and producing the visual component corresponding to the target element according to the target attribute information and the standardized component.

According to the method for processing the product prototype based on the AI image recognition, the AI image is used for recognizing the screenshot of the function page, the function design of the product is converted into an editable target component, then a target element corresponding to the target component and initial attribute information corresponding to the target element are obtained, the initial attribute information is adjusted to the target attribute information, the target component is combined in a preset editor to obtain the target page prototype, the phenomenon that the product prototype is output in a mode of manually drawing each component in the screenshot of the function page is avoided, and the design efficiency of the product prototype can be improved; in addition, the method and the device can acquire the target demand information corresponding to each target element in the target assembly from the preset demand document, then combine the target assembly according to the target demand information, avoid the mode that the assembly template is directly applied mechanically to complete product prototype design, improve the flexibility of product prototype design and ensure the design efficiency of product prototypes. The intelligent city development method can be applied to various functional modules of intelligent cities such as intelligent government affairs and intelligent traffic, for example, an AI image recognition-based product prototype processing module of the intelligent government affairs can promote the rapid development of the intelligent city.

Fig. 4 is a block diagram of a product prototype processing apparatus based on AI image recognition according to a second embodiment of the present application.

In some embodiments, the AI image recognition-based product prototype processing apparatus 20 may include a plurality of functional modules composed of computer program segments. The computer programs of the respective program segments in the AI image recognition based product prototype processing apparatus 20 may be stored in a memory of a computer device and executed by at least one processor to perform (see fig. 1 for details) the functions of the AI image recognition based product prototype processing.

In the present embodiment, the AI image recognition-based product prototype processing apparatus 20 may be divided into a plurality of functional modules according to the functions performed by the apparatus. The functional module may include: a screenshot obtaining module 201, a component identification module 202, an attribute obtaining module 203, a requirement obtaining module 204, an attribute adjusting module 205, and a component combining module 206. A module as referred to herein is a series of computer program segments capable of being executed by at least one processor and capable of performing a fixed function and is stored in a memory. In the present embodiment, the functions of the modules will be described in detail in the following embodiments.

The screenshot obtaining module 201 may be configured to obtain a functional page screenshot set, where each functional page screenshot in the functional page screenshot set includes a plurality of target components.

In at least one embodiment of the present application, the function page screenshot set includes a plurality of function page screenshots, and the function page screenshot may be a screenshot of a certain function page from a used product or a competitive product of a demand party. For each screenshot of the function page, one or more target components exist, and the target components may include a button component (button), a segment control (tab), and other components, where the button component may be composed of a button itself and button text, and the segment component may be composed of several labels, which is not limited herein. The function page screenshot sets are stored in a preset database, and can be stored in a target node of the block chain in consideration of the reliability and privacy of data storage.

In an embodiment, the function page screenshot set may be manually intercepted by a demand party, for example, the function page screenshot set may be designed by a traditional business team (also called demand party) or a product manager, when designing a product function, by referring to product design of an APP of the same kind of contest, or by contacting one or two good function designs in a daily use of the APP, and storing a similar function page screenshot locally.

In other embodiments, the function page screenshot set may also be intelligently intercepted by a machine learning method, and optionally, the obtaining the function page screenshot set includes:

acquiring a function module set required by the target page prototype;

determining demand preference information corresponding to each functional module in the functional module set;

and screening page information containing the functional module set according to the demand preference information, and intercepting a functional page cutout set corresponding to the functional module set from the page information.

The function module set may be a set of function modules pre-stored in a preset database and required for designing a target page prototype. For each functional module in the functional module set, there is demand preference information corresponding to the functional module, where the demand preference information may refer to information such as a component type and a component attribute of the functional module. The page information refers to a page containing the function module set in big data.

The component identification module 202 may be configured to identify each screenshot of the set of screenshots of the function page to obtain a target component in the screenshot of the function page.

In at least one embodiment of the present application, each screenshot of a function page carries one or more target components, and in one embodiment, a component recognition model may be trained in advance, and then the component recognition model is called to process each screenshot of a function page, so as to obtain a target component in the screenshot of a function page. In an embodiment, during model training, input data of the component recognition model is a functional page screenshot labeled with a component name in advance, and output data is a target component of the functional page screenshot. In other embodiments, the input data of the component recognition model may also be a standardized functional component picture stored in a preset database, and the output data is a target component of the screenshot of the functional page.

Optionally, the identifying each screenshot of the set of screenshots of the function page, and obtaining the target component in the screenshot of the function page includes:

acquiring a target picture set, and dividing the target picture set into training data and test data by taking the target picture set as input data and a target component contained in each target picture in the target picture set as output data;

inputting the training data into an initial neural network model for training to obtain a component identification model;

inputting the test data into the component recognition model, and calculating the model accuracy of the component recognition model;

detecting whether the model accuracy rate exceeds a preset model accuracy rate threshold value;

and when the detection result is that the model accuracy rate exceeds the preset model accuracy rate threshold value, calling the trained component recognition model to recognize each functional page screenshot in the functional page screenshot set, and obtaining a target component in the functional page screenshot.

The target picture can be a functional page screenshot marked with a component name in advance, or a standardized functional component picture. The preset model accuracy threshold is a preset threshold for evaluating model accuracy, for example, the preset model accuracy threshold may be 95%. The training data and the test data may be distributed according to a preset distribution ratio, which may be 7:3, and this is not limited herein.

The attribute obtaining module 203 may be configured to obtain a target element corresponding to the target component and initial attribute information corresponding to the target element.

In at least one embodiment of the present application, the target component includes a number of editable elements therein, each element including corresponding initial attribute information. Illustratively, the button components can be abstracted into three editable elements, a button box shape, a button box fill color, and a button text. For the shape of the button frame, the initial attribute information may be in a shape of a rectangle, an ellipse, or the like; for the button box filling color, the initial attribute information may be gray, green, or the like; for the button text, the initial attribute information may be various text information.

Optionally, the obtaining of the target element corresponding to the target component and the initial attribute information corresponding to the target element includes:

acquiring initial component description information corresponding to the target component;

performing word segmentation processing on the initial component description information through a crust word segmentation tool to obtain target component description information;

determining a first keyword in the target component description information, and taking the attached information corresponding to the first keyword as a target element;

and determining a second keyword in the scanning information of the target component, and taking the auxiliary information corresponding to the second keyword as the initial attribute information corresponding to the target element.

And in a preset database, corresponding initial component description information exists for each target component. The initial component description information is information describing each editable element of the target component, and the initial component description information includes element information of the target component and initial attribute information corresponding to each element information. And performing word segmentation processing on the initial attribute information to obtain structured target assembly description information. The first keyword is a keyword for identifying the target element, the second keyword is a keyword for identifying the initial attribute information, and the target element corresponding to the target component and the initial attribute information corresponding to the target element can be obtained by querying the first keyword and the second keyword.

The requirement obtaining module 204 may be configured to obtain a preset requirement document, and obtain target requirement information corresponding to the target element from the preset requirement document.

In at least one embodiment of the present application, the preset requirement document is a document composed by a requirement party according to actual requirements of each target element. The preset requirement document comprises a target assembly, a plurality of target elements contained in the target assembly and target requirement information corresponding to the target elements.

Optionally, the obtaining target requirement information corresponding to the target element from the preset requirement document includes:

acquiring the target component and a target element corresponding to the target component;

and according to the mapping relation between the target element and the preset element and the requirement information, obtaining the target requirement information corresponding to the target element.

And traversing the mapping relation to obtain the target demand information corresponding to the target element.

The attribute adjusting module 205 may be configured to adjust the initial attribute information according to the target demand information to obtain target attribute information.

In at least one embodiment of the present application, the attribute information of each target element in the target requirement information may be different from the initial attribute information, and the target attribute information corresponding to the target element can be obtained by adjusting the initial attribute information according to the target requirement information.

Optionally, the adjusting the initial attribute information according to the target demand information to obtain the target attribute information includes:

acquiring the target demand information and the initial attribute information;

detecting whether the target demand information is consistent with the initial attribute information;

when the detection result is that the target demand information is inconsistent with the initial attribute information, determining the difference content and the difference position in the target demand information and the initial attribute information;

and adjusting the difference content at the difference position according to the target demand information to obtain target attribute information.

The difference content refers to the content where the target demand information and the initial attribute information are different, and the difference position refers to the position information where the content is different.

The component combination module 206 may be configured to combine the target components in a preset editor according to the target attribute information to obtain a target page prototype.

In at least one embodiment of the present application, the preset encoder may be an H5 page editor, and is configured to edit the target components included in the functional page screenshot set, and output a target page prototype. The preset requirement document comprises target components, a plurality of target elements contained in the target components and target requirement information corresponding to the target elements, and also comprises position attribute information of each target component, wherein the position attribute information is used for identifying the position relation of the target components in a product prototype.

Optionally, the combining the target component in a preset editor according to the target attribute information to obtain a target page prototype includes:

acquiring position attribute information of the target assembly and target attribute information corresponding to each target element in the target assembly;

generating a visual component corresponding to the target element in the preset editor according to the target attribute information;

and combining the positions of the visual components according to the position attribute information to obtain a target page prototype.

Wherein the generating of the visualization component corresponding to the target element in the preset editor according to the target attribute information may include: determining a standardized component corresponding to the type information according to the type information in the target attribute information; and producing the visual component corresponding to the target element according to the target attribute information and the standardized component.

Fig. 5 is a schematic structural diagram of a computer device according to a third embodiment of the present application. In the preferred embodiment of the present application, the computer device 3 includes a memory 31, at least one processor 32, at least one communication bus 33, and a transceiver 34.

It will be appreciated by those skilled in the art that the configuration of the computer device shown in fig. 5 is not a limitation of the embodiments of the present application, and may be a bus-type configuration or a star-type configuration, and the computer device 3 may include more or less hardware or software than those shown, or different arrangements of components.

In some embodiments, the computer device 3 is a device capable of automatically performing numerical calculation and/or information processing according to instructions set or stored in advance, and the hardware includes but is not limited to a microprocessor, an application specific integrated circuit, a programmable gate array, a digital processor, an embedded device, and the like. The computer device 3 may also include a client device, which includes, but is not limited to, any electronic product capable of interacting with a client through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device, for example, a personal computer, a tablet computer, a smart phone, a digital camera, etc.

It should be noted that the computer device 3 is only an example, and other existing or future electronic products, such as those that may be adapted to the present application, are also included in the scope of the present application and are incorporated herein by reference.

In some embodiments, the memory 31 has stored therein a computer program that, when executed by the at least one processor 32, implements all or part of the steps of the AI image recognition based product prototyping method as described. The Memory 31 includes a Read-Only Memory (ROM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), a One-time Programmable Read-Only Memory (OTPROM), an electronically Erasable rewritable Read-Only Memory (Electrically-Erasable Programmable Read-Only Memory (EEPROM)), an optical Read-Only disk (CD-ROM) or other optical disk Memory, a magnetic disk Memory, a tape Memory, or any other medium readable by a computer capable of carrying or storing data.

Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.

The block chain referred by the application is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.

In some embodiments, the at least one processor 32 is a Control Unit (Control Unit) of the computer device 3, connects various components of the entire computer device 3 by using various interfaces and lines, and executes various functions and processes data of the computer device 3 by running or executing programs or modules stored in the memory 31 and calling data stored in the memory 31. For example, the at least one processor 32, when executing the computer program stored in the memory, implements all or part of the steps of the AI image recognition-based product prototype processing method described in the embodiments of the present application; or implement all or part of the functions of the product prototype processing device based on AI image recognition. The at least one processor 32 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips.

In some embodiments, the at least one communication bus 33 is arranged to enable connection communication between the memory 31 and the at least one processor 32 or the like.

Although not shown, the computer device 3 may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 32 through a power management device, so as to implement functions of managing charging, discharging, and power consumption through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The computer device 3 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.

The integrated unit implemented in the form of a software functional module may be stored in a computer-readable storage medium. The software functional module is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a computer device, or a network device) or a processor (processor) to execute parts of the methods according to the embodiments of the present application.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

In addition, functional modules in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.

It will be evident to those skilled in the art that the present application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned. Furthermore, it is obvious that the word "comprising" does not exclude other elements or that the singular does not exclude the plural. A plurality of units or means recited in the specification may also be implemented by one unit or means through software or hardware. The terms first, second, etc. are used to denote names, but not any particular order.

Finally, it should be noted that the above embodiments are only used for illustrating the technical solutions of the present application and not for limiting, and although the present application is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made on the technical solutions of the present application without departing from the spirit and scope of the technical solutions of the present application.