CN114218514A - Page generation method, device, equipment and storage medium - Google Patents
Page generation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114218514A CN114218514A CN202111562633.8A CN202111562633A CN114218514A CN 114218514 A CN114218514 A CN 114218514A CN 202111562633 A CN202111562633 A CN 202111562633A CN 114218514 A CN114218514 A CN 114218514A
- Authority
- CN
- China
- Prior art keywords
- page
- target
- information
- user
- unit
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/957—Browsing optimisation, e.g. caching or content distillation
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Information Transfer Between Computers (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention relates to the technical field of artificial intelligence, and discloses a page generation method, a device, equipment and a storage medium, which are used for enabling page layout and page content to accord with the operation habit of a user and improving the vision and operation experience of the user. The method comprises the following steps: acquiring behavior data when a user accesses a target page, inputting the behavior data into a feature extraction model, and outputting preference feature parameters of the user; the preference characteristic parameter is used for indicating the page layout preference and the page content preference of the user; configuring UI units of the target page and attribute information corresponding to each UI unit based on the preference characteristic parameters to obtain page layout information of the target page; acquiring page content information of a target page based on the preference characteristic parameters; and sending the page layout information and the page content information to the client so as to update the target page on the client based on the page layout information and the page content information.
Description
Technical Field
The present invention relates to the field of artificial intelligence, and in particular, to a page generation method, apparatus, device, and storage medium.
Background
An application installed on the terminal may provide various types of content to the user. The page layout of an application is typically designed and encoded by an engineer. Generally, the page layout of the application program browsed by each user is basically the same, or an engineer may design a plurality of page layout styles in advance to be selected by the user. The page layout of the application is relatively single, the selectable margin is small, the operation habits of part of users can be difficult to meet, and for users who frequently use the application, the visual aesthetic fatigue can be caused, and the improvement of the user viscosity and the user experience are not facilitated. If the local part of the page is frequently replaced, a large amount of manpower is required to be invested for development, and the waste of human resources is caused.
Disclosure of Invention
The invention provides a page generation method, a device, equipment and a storage medium, which are used for enabling page layout and page content to accord with the operation habit of a user, the personalized page layout is rich and diverse, when the operation habit of the user changes, the page layout also changes, the vision and the operation experience of the user are improved, and meanwhile, a large amount of cost is not required to be invested to develop various page layouts of the page, and the development cost is saved.
In order to achieve the above object, a first aspect of the present invention provides a page generating method, including: acquiring behavior data when a user accesses a target page, inputting the behavior data into a feature extraction model which is trained in advance, and outputting preference feature parameters of the user; wherein the preference feature parameters are used to: indicating a user's page layout preferences and page content preferences; configuring UI units of the target page and attribute information corresponding to each UI unit based on the preference characteristic parameters to obtain page layout information of the target page; the target page is composed of a plurality of UI units, and each UI unit is used for displaying a part of page content of the target page; acquiring page content information of a target page based on the preference characteristic parameters; and sending the page layout information and the page content information to the client so as to update the target page on the client based on the page layout information and the page content information.
Optionally, in a first implementation manner of the first aspect of the present invention, the step of configuring, based on the preference feature parameter, the UI units of the target page and the attribute information corresponding to each UI unit to obtain the page layout information of the target page includes: acquiring a UI unit of a target page from a preset UI unit library based on the preference characteristic parameters, and generating attribute information of the acquired UI unit; the UI unit comprises a text display area, a picture playing plug-in and a video playing plug-in; the attribute information of the UI unit includes: the shape, size, position in the target page, whether it is movable, and display mode of the UI unit; and determining page layout information of the target page based on the acquired UI unit and the acquired attribute information of the UI unit.
Optionally, in a second implementation manner of the first aspect of the present invention, the step of determining the page layout information of the target page based on the acquired attribute information of the UI unit and the UI unit includes: acquiring an initial page layout of a target page; and adjusting the UI unit in the initial page layout and/or the attribute information of the UI unit in the initial page layout based on the acquired attribute information of the UI unit and the acquired attribute information of the UI unit to obtain the page layout information of the target page.
Optionally, in a third implementation manner of the first aspect of the present invention, the step of obtaining the page content information of the target page based on the preference feature parameter includes: inputting the preference characteristic parameters into a content recommendation model, and outputting content labels of the user preference content corresponding to the preference characteristic parameters; the content recommendation model is trained and learned in advance to obtain the corresponding relation between the preference characteristic parameters and the user preference content; and acquiring page content information of the target page from a preset service database based on the content tag.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the step of sending the page layout information and the page content information to the client includes: based on an application service middle layer corresponding to a target page, binding page layout information and page content information to obtain a data set; wherein the data set comprises: the type and the attribute of each UI unit and the page content required to be displayed by each UI unit; and converting the format of the data set into a data format which can be recognized by the client, and sending the data set after format conversion to the client.
Optionally, in a fifth implementation manner of the first aspect of the present invention, the feature extraction model is obtained by training in the following manner: acquiring a training data set; the training data set comprises a plurality of groups of training data, and each group of training data comprises training behavior data and label values corresponding to the training behavior data; the label value comprises preference characteristic parameters set aiming at the training behavior data; determining target training data from the training data set, and inputting the target training data into the initial network model to obtain an output result; inputting the output result and the label value of the target training data into a preset loss function, and calculating to obtain a loss value; updating the parameters of the initial network model through the loss value; and continuing to execute the step of determining target training data from the training data set until the loss value is converged, and finishing training to obtain the feature extraction model.
Optionally, in a sixth implementation manner of the first aspect of the present invention, the behavior data includes: the method comprises the steps of page identification of a target page, browsing time of each page area in the target page accessed by a user, identification of the page area clicked by the user and the type of service data clicked by the user.
A second aspect of the present invention provides a page generating apparatus, including: the parameter output module is used for acquiring behavior data when a user accesses a target page, inputting the behavior data into a feature extraction model which is trained in advance, and outputting preference feature parameters of the user; wherein the preference feature parameters are used to: indicating a user's page layout preferences and page content preferences; the layout configuration module is used for configuring the UI units of the target page and the attribute information corresponding to each UI unit based on the preference characteristic parameters to obtain the page layout information of the target page; the target page is composed of a plurality of UI units, and each UI unit is used for displaying a part of page content of the target page; the information acquisition module is used for acquiring page content information of the target page based on the preference characteristic parameters; and the sending module is used for sending the page layout information and the page content information to the client so as to update the target page on the client based on the page layout information and the page content information.
Optionally, in a first implementation manner of the second aspect of the present invention, the layout configuration module is further configured to: acquiring a UI unit of a target page from a preset UI unit library based on the preference characteristic parameters, and generating attribute information of the acquired UI unit; the UI unit comprises a text display area, a picture playing plug-in and a video playing plug-in; the attribute information of the UI unit includes: the shape, size, position in the target page, whether it is movable, and display mode of the UI unit; and determining page layout information of the target page based on the acquired UI unit and the acquired attribute information of the UI unit.
Optionally, in a second implementation manner of the second aspect of the present invention, the layout configuration module is further configured to: acquiring an initial page layout of a target page; and adjusting the UI unit in the initial page layout and/or the attribute information of the UI unit in the initial page layout based on the acquired attribute information of the UI unit and the acquired attribute information of the UI unit to obtain the page layout information of the target page.
Optionally, in a third implementation manner of the second aspect of the present invention, the information obtaining module is further configured to: inputting the preference characteristic parameters into a content recommendation model, and outputting content labels of the user preference content corresponding to the preference characteristic parameters; the content recommendation model is trained and learned in advance to obtain the corresponding relation between the preference characteristic parameters and the user preference content; and acquiring page content information of the target page from a preset service database based on the content tag.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the sending module is further configured to: based on an application service middle layer corresponding to a target page, binding page layout information and page content information to obtain a data set; wherein the data set comprises: the type and the attribute of each UI unit and the page content required to be displayed by each UI unit; and converting the format of the data set into a data format which can be recognized by the client, and sending the data set after format conversion to the client.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the apparatus further includes a model training module, configured to: training to obtain a feature extraction model by the following method: acquiring a training data set; the training data set comprises a plurality of groups of training data, and each group of training data comprises training behavior data and label values corresponding to the training behavior data; the label value comprises preference characteristic parameters set aiming at the training behavior data; determining target training data from the training data set, and inputting the target training data into the initial network model to obtain an output result; inputting the output result and the label value of the target training data into a preset loss function, and calculating to obtain a loss value; updating the parameters of the initial network model through the loss value; and continuing to execute the step of determining target training data from the training data set until the loss value is converged, and finishing training to obtain the feature extraction model.
Optionally, in a sixth implementation manner of the second aspect of the present invention, the behavior data includes: the method comprises the steps of page identification of a target page, browsing time of each page area in the target page accessed by a user, identification of the page area clicked by the user and the type of service data clicked by the user.
A third aspect of the present invention provides a page generating apparatus, including: a memory and at least one processor, the memory having instructions stored therein; the at least one processor calls the instructions in the memory to cause the page generation device to perform the page generation method described above.
A fourth aspect of the present invention provides a computer-readable storage medium having stored therein instructions, which, when run on a computer, cause the computer to execute the above-described page generation method.
According to the technical scheme provided by the invention, behavior data when a user accesses a target page are collected, the behavior data are input into a feature extraction model which is trained in advance, and preference feature parameters of the user are output; wherein the preference feature parameters are used to: indicating a user's page layout preferences and page content preferences; configuring UI units of the target page and attribute information corresponding to each UI unit based on the preference characteristic parameters to obtain page layout information of the target page; the target page is composed of a plurality of UI units, and each UI unit is used for displaying a part of page content of the target page; acquiring page content information of a target page based on the preference characteristic parameters; and sending the page layout information and the page content information to the client so as to update the target page on the client based on the page layout information and the page content information. In the above mode, the preference characteristic parameters of the user are extracted from the behavior data of the user through the characteristic extraction model, and the page layout and the page content of the target page are configured based on the preference characteristic parameters, so that the page layout and the page content conform to the operation habits of the user, the personalized page layout is rich and diverse, when the operation habits of the user change, the page layout also changes, the vision and the operation experience of the user are improved, meanwhile, a large amount of cost is not required to be invested to develop various page layouts of the page, and the development cost is saved.
Drawings
FIG. 1 is a diagram of an embodiment of a page generation method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of another embodiment of a page generation method in the embodiment of the present invention;
fig. 3 is a schematic diagram of a system architecture for implementing the page generation method according to the embodiment of the present invention;
FIG. 4 is a diagram of an embodiment of a page generation apparatus according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of another embodiment of a page generation apparatus according to an embodiment of the present invention;
fig. 6 is a schematic diagram of an embodiment of a page generation device in the embodiment of the present invention.
Detailed Description
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The embodiment of the invention 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 page generation method provided by the invention can be applied to a server, and the server can be an independent server, and can also be a cloud server for providing basic cloud computing services such as cloud service, a cloud database, cloud computing, a cloud function, cloud storage, Network service, cloud communication, middleware service, domain name service, security service, Content Delivery Network (CDN), big data and an artificial intelligence platform.
Most of traditional APP (Application) intelligent recommendations mostly stay on contents, namely, related contents commonly used or browsed by users are returned according to some algorithms of big data, but the contents are displayed based on the existing page layout styles of the APPs, only the content data is changed, the page styles of each user are basically consistent, and even if slight differences exist, partial different template styles are prefabricated for display and distinction. For most mainstream APPs, especially for the APP with high use frequency, the style of the page layout basically has no great difference, so that the visual aesthetic fatigue may be caused when the user uses the APP for a long time, a new version needs to be developed and put on shelf when the style of the page layout is updated every time, and the iOS system and the android system need to invest manpower simultaneously to develop the same functions. Causing unnecessary waste of human resources.
Based on the above problem, embodiments of the present invention provide a page generation method, apparatus, device and storage medium. For convenience of understanding, a specific flow of the embodiment of the present invention is described below, and referring to fig. 1, an embodiment of a page generation method in the embodiment of the present invention includes:
step S101, collecting behavior data when a user accesses a target page, inputting the behavior data into a feature extraction model which is trained in advance, and outputting preference feature parameters of the user; wherein the preference feature parameter is used for: indicating a user's page layout preferences and page content preferences;
behavioral data may be collected through a big data system. In practical implementation, the behavior data may include: the method comprises the steps of page identification of a target page, browsing time of each page area in the target page accessed by a user, identification of the page area clicked by the user and the type of service data clicked by the user. Generally, an application system includes a plurality of pages, and the target page may be understood as a page accessed by a user. When the user accesses the target page, behavior data aiming at the target page is collected, and based on the behavior data, the behavior data comprises a page identifier of the target page and is used for indicating which pages are accessed by the user. The target page can be divided into a plurality of page areas in advance, when a user accesses the target page, the browsing duration of each page area is counted, and the browsing duration can reflect the preference degree of the layout and the content of the page areas to a certain extent. Since the target page is composed of a plurality of UI (User Interface) units, page areas each including a first or a plurality of UI units may be divided based on the UI units.
When the user is interested in the content in the page area, usually, a click operation is also executed in the page area to view the specific content of the content in the page area, and based on this, the behavior data also includes the identification of the page area clicked by the user; in addition, the behavior data also records the service data types clicked by the user, and when the types of the application programs are different, the service data types are also different. Taking news APP as an example, the service data type may be social news, financial information, city information, and the like.
After the behavior data is collected, screening and integrating processing can be performed on the behavior data, wherein the screening and integrating processing comprises the processes of cleaning dirty data, adding time identification, converting data formats and the like. And then, inputting the processed behavior data into a feature extraction model to obtain the preference feature parameters of the user. The feature extraction model needs to be trained in advance, and may be implemented by various artificial intelligence networks or models, for example, Network models such as a convolutional Network, a residual Network ResNet, a BERT (Bidirectional Encoder representation from converters), a VGG (Visual Geometry Group Network), and so on.
The preference feature parameter may be in a data form or a matrix form. In this embodiment, the preference feature parameter may include two parts, one part is used to indicate the page layout preference of the user, for example, the layout style, plug-in type, etc. that the user is interested in; another portion is for indicating page content preferences of the user, including page content of interest to the user.
Step S102, configuring UI units of the target page and attribute information corresponding to each UI unit based on the preference characteristic parameters to obtain page layout information of the target page; the target page is composed of a plurality of UI units, and each UI unit is used for displaying a part of page content of the target page;
a UI element may be understood as a minimum editable page layout element, e.g. a text display area of various shapes, a picture playing plug-in, a video playing plug-in, etc. The target page usually includes a plurality of UI elements, that is, a plurality of UI elements are combined into a display page, and the types of the plurality of UI elements may be the same or different. The attribute corresponding to the UI element may specifically include information such as a size of the UI element, a position in the page, whether the UI element is movable in the page, and a display mode of the UI element.
Since different users access the same target page with different behavior data, the preference feature parameters will be different. In this embodiment, the page layout is performed based on the preference characteristic parameters, and therefore, the obtained page layout information better conforms to the behavior habit of the user.
Step S103, acquiring page content information of the target page based on the preference characteristic parameters;
because the preference characteristic parameters also include the page content preference of the user, the acquired page content information also accords with the interest of the user. In actual implementation, because the page content is rich and diverse, the page content in the application system can be divided into a plurality of types in advance, which type of content the user is interested in is determined based on the preference characteristic parameters, and then the page content information of the target page is obtained from the type of content.
And step S104, sending the page layout information and the page content information to the client so as to update the target page on the client based on the page layout information and the page content information.
The server sends the page layout information and the page content information to the client, and the client can update and display a target page based on the page layout information and the page content information; in the process of displaying the target page, the behavior data of the user when accessing the target page can be continuously collected, so that the target page is changed along with the change of the behavior habits of the user.
The page generation method comprises the steps of collecting behavior data when a user accesses a target page, inputting the behavior data into a feature extraction model which is trained in advance, and outputting preference feature parameters of the user; wherein the preference feature parameters are used to: indicating a user's page layout preferences and page content preferences; configuring UI units of the target page and attribute information corresponding to each UI unit based on the preference characteristic parameters to obtain page layout information of the target page; the target page is composed of a plurality of UI units, and each UI unit is used for displaying a part of page content of the target page; acquiring page content information of a target page based on the preference characteristic parameters; and sending the page layout information and the page content information to the client so as to update the target page on the client based on the page layout information and the page content information. In the above mode, the preference characteristic parameters of the user are extracted from the behavior data of the user through the characteristic extraction model, and the page layout and the page content of the target page are configured based on the preference characteristic parameters, so that the page layout and the page content conform to the operation habits of the user, the personalized page layout is rich and diverse, when the operation habits of the user change, the page layout also changes, the vision and the operation experience of the user are improved, meanwhile, a large amount of cost is not required to be invested to develop various page layouts of the page, and the development cost is saved.
Referring to fig. 2, another embodiment of the page generating method according to the embodiment of the present invention includes:
step S201, collecting behavior data when a user accesses a target page, inputting the behavior data into a feature extraction model which is trained in advance, and outputting preference feature parameters of the user; wherein the preference feature parameter is used for: indicating a user's page layout preferences and page content preferences;
the above feature extraction model can be realized by the following steps 1 to 4.
Step 1, acquiring a training data set; the training data set comprises a plurality of groups of training data, and each group of training data comprises training behavior data and label values corresponding to the training behavior data; the label value comprises preference characteristic parameters set aiming at the training behavior data;
for example, behavior data of a user may be collected in an application system as training behavior data, and then a label value corresponding to the training behavior data may be set in a manual setting manner. In order to ensure that the trained feature extraction model can accurately output the preference feature parameters. The users can be divided into multiple classes in advance, and then behavior data of multiple users are collected for each class of users, so that overfitting of model training caused by single user type is avoided.
Step 2, determining target training data from the training data set, and inputting the target training data into an initial network model to obtain an output result;
in the process of one training, one training data can be randomly obtained from a training data set and used as a target training data; the training data may also be acquired from the training data set one by one based on the order of the training data in the training data set. Each network layer in the initial network model is typically provided with default parameters, such as the size of the convolution kernel, weighting coefficients, etc. And calculating the target training data through default parameters in the initial network model to obtain an output result.
Step 3, inputting the output result and the label value of the target training data into a preset loss function, and calculating to obtain a loss value;
the loss function may be implemented in various forms, such as an absolute value loss function, a cross-entropy loss function, a perceptual loss function, and so forth. The loss value may be understood as the distance between the output result and the tag value.
Step 4, updating the parameters of the initial network model through the loss value; and continuing to execute the step of determining target training data from the training data set until the loss value is converged, and finishing training to obtain the feature extraction model.
In the process of updating the network parameters, the method can be realized by a gradient descent method, so that the updating operation amount of the parameters of the network model is reduced.
The feature extraction model trained in the above manner learns the corresponding relationship between the behavior data of the user and the preference feature parameters of the user, so that in the above step, the behavior data of the user is input to the feature extraction model, and the preference feature parameters of the user can be predicted by the model. The preference characteristic parameter may be in an array form or a matrix form for indicating the preference of the user, for example, a frequently operated page area, a clicking habit, a common clicking gesture, and the like. The feature extraction model mainly analyzes elements which are frequently clicked by a user and related contents concerned by the user, and analyzes a page area which is frequently operated by the user and a template pattern contained in the area, and if a certain user prefers to click elements in the middle area of the page, the user prefers to click a carousel template.
Step S202, acquiring a UI unit of a target page from a preset UI unit library based on the preference characteristic parameters, and generating attribute information of the acquired UI unit; and determining page layout information of the target page based on the acquired UI unit and the acquired attribute information of the UI unit.
The UI unit comprises a text display area, a picture playing plug-in and a video playing plug-in; the attribute information of the UI unit includes: the shape, size, position in the target page, whether it is movable, and display manner of the UI unit. The UI unit library may include various types of UI units, each type of UI unit may preset default attribute information, and if the preference characteristic parameter indicates that the attribute information needs to be modified, new attribute information of the UI unit may be generated on the basis of the default attribute information.
In one implementation, an initial page layout of the target page may be set, and the initial page layout may be adjusted based on a preference characteristic parameter of the user. Specifically, an initial page layout of a target page is obtained; and adjusting the UI unit in the initial page layout and/or the attribute information of the UI unit in the initial page layout based on the acquired attribute information of the UI unit and the acquired attribute information of the UI unit to obtain the page layout information of the target page.
When the initial page layout needs to be adjusted to a greater extent, the UI unit in the initial page layout and the attribute information of the UI unit in the initial page layout can be adjusted at the same time; when the initial page layout needs to be adjusted to a smaller extent, only one of the UI elements in the initial page layout or the attribute information of the UI elements in the initial page layout may be adjusted. As an example, when the preference feature parameter indicates that the user prefers to view a video, UI elements of a plurality of video playing plug-ins may be configured in the destination page, and the display size of the video playing plug-ins may be appropriately enlarged.
Step S203, inputting the preference characteristic parameters into a content recommendation model, and outputting content labels of the user preference content corresponding to the preference characteristic parameters; the content recommendation model is trained and learned in advance to obtain the corresponding relation between the preference characteristic parameters and the user preference content; and acquiring page content information of the target page from a preset service database based on the content tag.
Similar to the feature extraction network, the content recommendation model can also be realized by various artificial intelligence networks or models, such as network models of a convolution network, a residual error network ResNet, a BERT network, a VGG and the like; the content recommendation model may also be implemented through steps 1-4 described above. Different from the feature extraction network, in the training data set of the content recommendation model, the training data includes a preference feature parameter and a tag value corresponding to the preference feature parameter, and the tag value includes a content tag for the preference feature parameter.
Step S204, based on the application service middle layer corresponding to the target page, binding the page layout information and the page content information to obtain a data set; wherein the data set includes: the type and the attribute of each UI unit and the page content required to be displayed by each UI unit;
specifically, the page layout information and the recommended content data are subjected to data binding through the App Server middle layer and assembled into a data set which can be identified by the APP, and the data set comprises the page layout information, the identification of the corresponding type of the UI unit and the service data required by the display of each UI unit.
Step S205, converting the format of the data set into a data format recognizable by the client, and sending the data set after format conversion to the client, so as to update the target page on the client based on the page layout information and the page content information.
For further understanding, fig. 3 shows a system architecture for implementing the page generation method of the present embodiment, and the system architecture includes: the system comprises an application program APP, a server corresponding to the APP, an intermediate layer, a big data system, an AI system, an interactive system and a service system.
The APP is installed and operated on a user terminal, and is used for obtaining data from a server and providing page content for a user. The big data system can collect the behavior data of the user through the APP. User behavior data acquired by a big data system is sent to an AI system, a feature extraction model runs in the AI system, and the behavior data of the user is analyzed through the feature extraction model to obtain preference feature parameters of the user; the service system generates recommended content data based on the preference characteristic parameter, and in the process, the service system can also generate recommended content data by using an AI system, and a recommended content model can be operated in the AI system. In addition, the interactive system generates page layout data based on the preference feature parameter. And then, binding the recommended content data and the page layout data through the middle layer to obtain a data set, and further sending the data set to the APP of the user terminal for displaying.
The page generation method can automatically issue and arrange page styles according to the operation habits and visual preferences of users, big data records user behavior data and the browsing time of a visual area, a plurality of preference characteristic parameters of the users are generated by training an AI model through artificial intelligence, similar and different style templates are generated according to the characteristic parameters, the generated templates and data are issued to the users when the users browse APP pages next time, and the APP pages are displayed after being arranged. Namely, the APP style of 'thousands of people and faces' is realized. The intelligent layout can promote the user to the satisfaction of APP, promotes APP and user's degree of adhesion, and it is long when promoting the user to use, makes the user like to use such APP more, reduces unnecessary development simultaneously, saves development resource and cost.
In the above description of the page generating method in the embodiment of the present invention, referring to fig. 4, a page generating apparatus in the embodiment of the present invention is described below, where an embodiment of the page generating apparatus in the embodiment of the present invention includes:
the parameter output module 401 is configured to collect behavior data of a user when the user accesses a target page, input the behavior data into a feature extraction model which is trained in advance, and output preference feature parameters of the user; wherein the preference feature parameters are used to: indicating a user's page layout preferences and page content preferences;
a layout configuration module 402, configured to configure UI units of the target page and attribute information corresponding to each UI unit based on the preference feature parameters, to obtain page layout information of the target page; the target page is composed of a plurality of UI units, and each UI unit is used for displaying a part of page content of the target page;
an information obtaining module 403, configured to obtain page content information of the target page based on the preference feature parameter;
a sending module 404, configured to send the page layout information and the page content information to the client, so as to update the target page on the client based on the page layout information and the page content information.
The page generation device acquires behavior data when a user accesses a target page, inputs the behavior data into a feature extraction model which is trained in advance, and outputs preference feature parameters of the user; wherein the preference feature parameters are used to: indicating a user's page layout preferences and page content preferences; configuring UI units of the target page and attribute information corresponding to each UI unit based on the preference characteristic parameters to obtain page layout information of the target page; the target page is composed of a plurality of UI units, and each UI unit is used for displaying a part of page content of the target page; acquiring page content information of a target page based on the preference characteristic parameters; and sending the page layout information and the page content information to the client so as to update the target page on the client based on the page layout information and the page content information. In the above mode, the preference characteristic parameters of the user are extracted from the behavior data of the user through the characteristic extraction model, and the page layout and the page content of the target page are configured based on the preference characteristic parameters, so that the page layout and the page content conform to the operation habits of the user, the personalized page layout is rich and diverse, when the operation habits of the user change, the page layout also changes, the vision and the operation experience of the user are improved, meanwhile, a large amount of cost is not required to be invested to develop various page layouts of the page, and the development cost is saved.
Referring to fig. 5, another embodiment of the page generating apparatus according to the embodiment of the present invention includes:
the parameter output module 401 is configured to collect behavior data of a user when the user accesses a target page, input the behavior data into a feature extraction model which is trained in advance, and output preference feature parameters of the user; wherein the preference feature parameters are used to: indicating a user's page layout preferences and page content preferences;
a layout configuration module 402, configured to configure UI units of the target page and attribute information corresponding to each UI unit based on the preference feature parameters, to obtain page layout information of the target page; the target page is composed of a plurality of UI units, and each UI unit is used for displaying a part of page content of the target page;
an information obtaining module 403, configured to obtain page content information of the target page based on the preference feature parameter;
a sending module 404, configured to send the page layout information and the page content information to the client, so as to update the target page on the client based on the page layout information and the page content information.
The layout configuration module is further configured to: acquiring a UI unit of a target page from a preset UI unit library based on the preference characteristic parameters, and generating attribute information of the acquired UI unit; the UI unit comprises a text display area, a picture playing plug-in and a video playing plug-in; the attribute information of the UI unit includes: the shape, size, position in the target page, whether it is movable, and display mode of the UI unit; and determining page layout information of the target page based on the acquired UI unit and the acquired attribute information of the UI unit.
The layout configuration module is further configured to: acquiring an initial page layout of a target page; and adjusting the UI unit in the initial page layout and/or the attribute information of the UI unit in the initial page layout based on the acquired attribute information of the UI unit and the acquired attribute information of the UI unit to obtain the page layout information of the target page.
The information obtaining module is further configured to: inputting the preference characteristic parameters into a content recommendation model, and outputting content labels of the user preference content corresponding to the preference characteristic parameters; the content recommendation model is trained and learned in advance to obtain the corresponding relation between the preference characteristic parameters and the user preference content; and acquiring page content information of the target page from a preset service database based on the content tag.
The sending module is further configured to: based on an application service middle layer corresponding to a target page, binding page layout information and page content information to obtain a data set; wherein the data set comprises: the type and the attribute of each UI unit and the page content required to be displayed by each UI unit; and converting the format of the data set into a data format which can be recognized by the client, and sending the data set after format conversion to the client.
The apparatus further comprises a model training module 405 for: training to obtain a feature extraction model by the following method: acquiring a training data set; the training data set comprises a plurality of groups of training data, and each group of training data comprises training behavior data and label values corresponding to the training behavior data; the label value comprises preference characteristic parameters set aiming at the training behavior data; determining target training data from the training data set, and inputting the target training data into the initial network model to obtain an output result; inputting the output result and the label value of the target training data into a preset loss function, and calculating to obtain a loss value; updating the parameters of the initial network model through the loss value; and continuing to execute the step of determining target training data from the training data set until the loss value is converged, and finishing training to obtain the feature extraction model.
The behavior data includes: the method comprises the steps of page identification of a target page, browsing time of each page area in the target page accessed by a user, identification of the page area clicked by the user and the type of service data clicked by the user.
Fig. 4 and 5 describe the page generation apparatus in the embodiment of the present invention in detail, and the page generation device in the embodiment of the present invention is described in detail from the perspective of hardware processing.
Fig. 6 is a schematic structural diagram of a page generating device provided in an embodiment of the present invention, where the page generating device includes: a memory and at least one processor, the memory having instructions stored therein; at least one processor calls instructions in the memory to cause the page generation device to execute the page generation method.
The page generating device 500 may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 510 (e.g., one or more processors) and a memory 520, one or more storage media 530 (e.g., one or more mass storage devices) storing applications 533 or data 532. Memory 520 and storage media 530 may be, among other things, transient or persistent storage. The program stored on the storage medium 530 may include one or more modules (not shown), each of which may include a series of instruction operations on the page generation apparatus 500. Still further, processor 510 may be configured to communicate with storage medium 530 to execute a series of instruction operations in storage medium 530 on page generating device 500.
The page generation apparatus 500 may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input-output interfaces 560, and/or one or more operating systems 531, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, and so forth. Those skilled in the art will appreciate that the page generation device configuration shown in FIG. 6 does not constitute a limitation of the page generation device, and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
The invention also provides a computer readable storage medium, on which instructions are stored, and when the instructions are executed by a processor, the page generation method is realized. The computer readable storage medium may be a non-volatile computer readable storage medium, which may also be a volatile computer readable storage medium having stored therein instructions that, when executed on a computer, cause the computer to perform the steps of the page generation method.
The invention further provides a page generation device, which includes a memory and a processor, where the memory stores instructions, and when the instructions are executed by the processor, the processor executes the steps of the page generation method in the embodiments.
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 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.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A page generation method is characterized by comprising the following steps:
acquiring behavior data when a user accesses a target page, inputting the behavior data into a feature extraction model which is trained in advance, and outputting preference feature parameters of the user; wherein the preference feature parameter is to: indicating page layout preferences and page content preferences of the user;
configuring UI units of the target page and attribute information corresponding to each UI unit based on the preference characteristic parameters to obtain page layout information of the target page; the target page is composed of a plurality of UI units, and each UI unit is used for displaying a part of page content of the target page;
acquiring page content information of the target page based on the preference characteristic parameters;
and sending the page layout information and the page content information to a client so as to update the target page on the client based on the page layout information and the page content information.
2. The page generation method according to claim 1, wherein the step of configuring the UI elements of the target page and the attribute information corresponding to each UI element based on the preference feature parameter to obtain the page layout information of the target page includes:
acquiring a UI unit of the target page from a preset UI unit library based on the preference characteristic parameters, and generating the acquired attribute information of the UI unit; the UI unit comprises a text display area, a picture playing plug-in and a video playing plug-in; the attribute information of the UI element includes: the shape, size, position in the target page, whether it is movable, and display mode of the UI element;
and determining the page layout information of the target page based on the acquired UI unit and the acquired attribute information of the UI unit.
3. The page generation method according to claim 2, wherein the step of determining the page layout information of the target page based on the acquired attribute information of the UI unit and the UI unit includes:
acquiring an initial page layout of the target page;
and adjusting the UI unit in the initial page layout and/or the attribute information of the UI unit in the initial page layout based on the acquired attribute information of the UI unit and the acquired attribute information of the UI unit to obtain the page layout information of the target page.
4. The page generating method according to claim 1, wherein the step of obtaining the page content information of the target page based on the preference characteristic parameter includes:
inputting the preference characteristic parameters into a content recommendation model, and outputting content labels of user preference content corresponding to the preference characteristic parameters; the content recommendation model is trained and learned in advance to obtain the corresponding relation between the preference characteristic parameters and the user preference content;
and acquiring the page content information of the target page from a preset service database based on the content tag.
5. The page generating method according to claim 1, wherein the step of sending the page layout information and the page content information to a client includes:
based on an application service middle layer corresponding to a target page, binding the page layout information and the page content information to obtain a data set; wherein the data set comprises: the type and the attribute of each UI unit and the page content required to be displayed by each UI unit;
and converting the format of the data set into a data format which can be recognized by a client, and sending the data set after format conversion to the client.
6. The page generation method of claim 1, wherein the feature extraction model is trained by:
acquiring a training data set; the training data set comprises a plurality of groups of training data, and each group of training data comprises training behavior data and label values corresponding to the training behavior data; the label value comprises a preference characteristic parameter set aiming at the training behavior data;
determining target training data from the training data set, and inputting the target training data into an initial network model to obtain an output result;
inputting the output result and the label value of the target training data into a preset loss function, and calculating to obtain a loss value;
updating the parameters of the initial network model according to the loss value; and continuing to execute the step of determining target training data from the training data set until the loss value is converged, and finishing training to obtain the feature extraction model.
7. The page generation method of any of claims 1 to 6, wherein the behavior data comprises: the page identification of the target page, the browsing time of each page area accessed by the user in the target page, the identification of the page area clicked by the user and the service data type clicked by the user.
8. A page generating apparatus, characterized in that the page generating apparatus comprises:
the parameter output module is used for acquiring behavior data when a user accesses a target page, inputting the behavior data into a feature extraction model which is trained in advance, and outputting preference feature parameters of the user; wherein the preference feature parameter is to: indicating page layout preferences and page content preferences of the user;
the layout configuration module is used for configuring the UI units of the target page and the attribute information corresponding to each UI unit based on the preference characteristic parameters to obtain the page layout information of the target page; the target page is composed of a plurality of UI units, and each UI unit is used for displaying a part of page content of the target page;
the information acquisition module is used for acquiring page content information of the target page based on the preference characteristic parameters;
and the sending module is used for sending the page layout information and the page content information to a client so as to update the target page on the client based on the page layout information and the page content information.
9. A page generating apparatus, characterized in that the page generating apparatus comprises: a memory and at least one processor, the memory having instructions stored therein;
the at least one processor invokes the instructions in the memory to cause the page generation apparatus to perform the page generation method of any of claims 1-7.
10. A computer-readable storage medium having instructions stored thereon, wherein the instructions, when executed by a processor, implement the page generation method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111562633.8A CN114218514A (en) | 2021-12-20 | 2021-12-20 | Page generation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111562633.8A CN114218514A (en) | 2021-12-20 | 2021-12-20 | Page generation method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114218514A true CN114218514A (en) | 2022-03-22 |
Family
ID=80704319
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111562633.8A Pending CN114218514A (en) | 2021-12-20 | 2021-12-20 | Page generation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114218514A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114995814A (en) * | 2022-06-07 | 2022-09-02 | 重庆大学 | Method and device for engineering intelligent view layout of application system |
| CN115098217A (en) * | 2022-08-24 | 2022-09-23 | 中关村科学城城市大脑股份有限公司 | Application page rendering method, device, equipment, readable medium and program product |
| CN117806585A (en) * | 2024-02-29 | 2024-04-02 | 山东京运维科技有限公司 | Screen control method and system based on intelligent terminal |
-
2021
- 2021-12-20 CN CN202111562633.8A patent/CN114218514A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114995814A (en) * | 2022-06-07 | 2022-09-02 | 重庆大学 | Method and device for engineering intelligent view layout of application system |
| CN114995814B (en) * | 2022-06-07 | 2023-03-28 | 重庆大学 | Method and device for engineering intelligent view layout of application system |
| CN115098217A (en) * | 2022-08-24 | 2022-09-23 | 中关村科学城城市大脑股份有限公司 | Application page rendering method, device, equipment, readable medium and program product |
| CN115098217B (en) * | 2022-08-24 | 2023-01-24 | 中关村科学城城市大脑股份有限公司 | Application page rendering method, device, equipment, readable medium and program product |
| CN117806585A (en) * | 2024-02-29 | 2024-04-02 | 山东京运维科技有限公司 | Screen control method and system based on intelligent terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10970463B2 (en) | System and method for optimizing electronic document layouts | |
| CN114218514A (en) | Page generation method, device, equipment and storage medium | |
| US11860968B2 (en) | System and method for integrating user feedback into website building system services | |
| US11392840B2 (en) | System and method for generating recommendations | |
| CN108874992A (en) | The analysis of public opinion method, system, computer equipment and storage medium | |
| CN110019616B (en) | POI (Point of interest) situation acquisition method and equipment, storage medium and server thereof | |
| CN108804133B (en) | Method, system, computer device and storage medium for acquiring virtual resources | |
| CN109408821B (en) | Corpus generation method and device, computing equipment and storage medium | |
| CN108809718B (en) | Network access method, system, computer device and medium based on virtual resources | |
| CN104915426B (en) | Information sorting method, the method and device for generating information sorting model | |
| CN110598095B (en) | Method, device and storage medium for identifying article containing specified information | |
| CN113220657B (en) | Data processing method and device and computer equipment | |
| CN112131837A (en) | Service report configuration method, device, computer equipment and storage medium | |
| CN113139141A (en) | User label extension labeling method, device, equipment and storage medium | |
| CN114035793A (en) | Page generation method, page generation device, equipment and storage medium | |
| CN115358200A (en) | Template document automatic generation method based on SysML meta model | |
| CN109831488A (en) | Information recommendation method and system, readable storage medium storing program for executing | |
| CN108153754B (en) | Data processing method and device | |
| CN109063059B (en) | Behavior log processing method and device and electronic equipment | |
| CN114662470A (en) | Product comment information processing method and system combining big data | |
| CN112799658B (en) | Model training method, model training platform, electronic device, and storage medium | |
| Santoso et al. | Importance of user experience aspects for different software product categories | |
| Upadhyaya et al. | Extracting restful services from web applications | |
| CN116701791B (en) | Course recommendation method and system based on artificial intelligence | |
| Vinay et al. | A quantitative approach using goal-oriented requirements engineering methodology and analytic hierarchy process in selecting the best alternative |
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 |