Display optimization method based on touch data of liquid crystal display module

By using visual page segmentation algorithm and interest model on the LCD display module, the page layout is optimized to prioritize the content that users are interested in, solving the problem of positioning difficulties on small-sized display panels and improving the user experience.

CN119089034AInactive Publication Date: 2024-12-06SHENZHEN TECHSTAR ELECTRONICS
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202410966792.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-18
Publication Date
2024-12-06
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

When the existing LCD display module displays page content, the fixed layout causes the user to slide the screen multiple times on the small-sized display panel to locate the content of interest, resulting in poor user experience.

Method used

The page is divided into multiple blocks through a vision-based page segmentation algorithm, extract the space, content and text features of each page block, input a pre-trained interest model to predict user interest, and adjust the page layout to prioritize user interest. content.

Benefits of technology

Without the need for users to slide the screen multiple times, save positioning time, improve user experience, and enable users to quickly find content of interest by optimizing page layout.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119089034A_ABST
    Figure CN119089034A_ABST
Patent Text Reader

Abstract

The invention discloses a display optimization method based on touch data of a liquid crystal display module, and relates to the technical field of display. The display optimization method based on the touch data of the liquid crystal display module comprises the following steps: segmenting a to-be-displayed page through a vision-based page segmentation algorithm to obtain a plurality of page blocks; extracting spatial features, content features and text features of each page block; inputting the spatial features, the content features and the text features corresponding to the page blocks into a pre-trained interestingness model to obtain predicted interestingness parameters of the user for the page blocks; adjusting the layout of the page blocks of the to-be-displayed page based on the predicted interestingness parameter of the user for each page block to obtain an adjusted page; and displaying the adjusted page through the liquid crystal display module. According to the display optimization method based on the touch data of the liquid crystal display module, the content which a user is interested in can be preferentially displayed in the page, the user can conveniently browse the page, and the use experience of the user is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of display technology, and in particular relates to a display optimization method based on touch data of a liquid crystal display module. Background Art

[0002] Liquid crystal display module is a display device that integrates components such as liquid crystal panel, driver IC (integrated circuit) and backlight source. It is widely used in various electronic products such as mobile phones, tablet computers, televisions, etc.

[0003] At present, when the page content of the page browsed by the user is displayed through the LCD display module, the layout of the displayed page content is often fixed. Especially for some LCD display modules with smaller display panels (such as tablets, smart phones, etc.), due to the limited size of their display panels, users often need to slide the screen multiple times to locate the content they are interested in, resulting in a poor user experience.

[0004] Therefore, how to provide an effective solution to preferentially display the content that users are interested in on a page has become a problem that needs to be solved urgently in the prior art. Summary of the invention

[0005] The purpose of the present invention is to provide a display optimization method based on touch data of a liquid crystal display module, so as to solve the above-mentioned problems existing in the prior art.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a display optimization method based on touch data of a liquid crystal display module, which is used to optimize the page content displayed by the liquid crystal display module, comprising:

[0008] The page to be displayed is segmented by a vision-based page segmentation algorithm to obtain multiple page blocks;

[0009] Extracting spatial features, content features and text features of each page block;

[0010] Inputting the spatial features, content features and text features corresponding to each page block into a pre-trained interest model to obtain the user's predicted interest parameters for each page block;

[0011] Based on the predicted interest parameters of the user for each page block, adjusting the layout of the page blocks of the page to be displayed to obtain an adjusted page;

[0012] Displaying the adjusted page through a liquid crystal display module;

[0013] Among them, the interest model is trained by taking the spatial features, content features and text features corresponding to each page block of the user's historically visited pages as sample inputs, and taking the user's interest parameters for each page block of the historically visited pages as outputs. The user's interest parameters for each page block of the historically visited pages are obtained based on statistics of the user's touch data for each page block of the historically visited pages.

[0014] Based on the above disclosed content, the present invention segments the page to be displayed through a vision-based page segmentation algorithm to obtain multiple page blocks; extracts the spatial features, content features and text features of each page block; inputs the spatial features, content features and text features corresponding to each page block into a pre-trained interest model to obtain the user's predicted interest parameters for each page block; adjusts the layout of the page blocks of the page to be displayed based on the user's predicted interest parameters for each page block to obtain an adjusted page; displays the adjusted page through a liquid crystal display module; wherein the interest model is trained using the spatial features, content features and text features corresponding to each page block of the historically visited pages of the user as sample inputs and the user's interest parameters for each page block of the historically visited pages as outputs, and the user's interest parameters for each page block of the historically visited pages are obtained based on statistics of the user's touch data for each page block of the historically visited pages. In this way, before displaying the page to be displayed through the LCD display module, the page to be displayed can be divided into blocks, and the user's interest in each page block can be predicted according to the characteristics of the page block, and the layout of the page to be displayed can be adjusted accordingly, and then the adjusted page can be displayed, so as to give priority to displaying the content that the user is interested in on the page. That is, the page content that the user may be interested in can be displayed in a position on the page that is convenient for the user to browse as much as possible, without the user having to slide the screen multiple times to locate the content that he is interested in, thus saving positioning time, facilitating users to browse pages, and improving the user experience.

[0015] In a possible design, the spatial features of each page block are extracted, including:

[0016] Get the center coordinates, width and height of each page block;

[0017] The center coordinates, width and height of each page block are combined to obtain the spatial features of each page block.

[0018] In a possible design, the content features of each page block are extracted, including:

[0019] Obtain the image features, hyperlink features and tag features of each page block;

[0020] The image features include the number of images, the size of the images and / or the color of the images, the hyperlink features include the number of hyperlinks and / or the length of the hyperlink text, and the tag features include the length, number and / or size of the elements in the specified tag;

[0021] The image features, hyperlink features and tag features of each page block are combined to obtain the content features of each page block.

[0022] In a possible design, the step of obtaining the image features, hyperlink features, and tag features of each page block includes:

[0023] The image features, hyperlink features and tag features of each page block are obtained through the MSHTML component.

[0024] In a possible design, the text features of each page block are extracted, including:

[0025] Extract the text content in each page block;

[0026] After word segmentation processing is performed on the text content in each page block, a plurality of first keywords corresponding to the text content in each page block are extracted by a word frequency-inverse file frequency algorithm;

[0027] Calculating similarity between the first keywords corresponding to each page block and the second keywords in the user interest word library to obtain a similarity value corresponding to each page block;

[0028] The similarity value corresponding to each page block is used as a text feature to obtain the text feature of each page block;

[0029] The plurality of second keywords are obtained by extracting keywords from text contents corresponding to the page blocks that the user is interested in in the user's historically visited pages using a word frequency-inverse document frequency algorithm.

[0030] In a possible design, adjusting the layout of the page blocks of the to-be-displayed page based on the predicted interest parameter of the user for each page block includes:

[0031] Based on the predicted interest parameters of each page block by the user, selecting at least one page block with the highest predicted interest parameter;

[0032] Adjusting the page content corresponding to the at least one page block to the area of ​​interest in the page;

[0033] The region of interest refers to a region that can be observed without sliding the page.

[0034] In one possible design, the interest model is a convolutional neural network model.

[0035] In a second aspect, the present invention provides a display optimization device based on touch data of a liquid crystal display module, which is used to optimize the page content displayed by the liquid crystal display module, comprising:

[0036] A segmentation unit, used for segmenting the page to be displayed by a vision-based page segmentation algorithm to obtain a plurality of page blocks;

[0037] An extraction unit, used to extract the spatial features, content features and text features of each page block;

[0038] A computing unit, used to input the spatial features, content features and text features corresponding to each page block into a pre-trained interest model to obtain a user's predicted interest parameter for each page block;

[0039] An adjusting unit, configured to adjust the layout of the page blocks of the to-be-displayed page based on the predicted interest parameter of the user for each page block, to obtain an adjusted page;

[0040] A display unit, used for displaying the adjusted page through a liquid crystal display module;

[0041] Among them, the interest model is trained by taking the spatial features, content features and text features corresponding to each page block of the user's historically visited pages as sample inputs, and taking the user's interest parameters for each page block of the historically visited pages as outputs. The user's interest parameters for each page block of the historically visited pages are obtained based on statistics of the user's touch data for each page block of the historically visited pages.

[0042] In a third aspect, the present invention provides an electronic device comprising a memory, a processor and a transceiver which are communicatively connected in sequence, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the display optimization method based on liquid crystal display module touch data as described in the first aspect or any possible design of the first aspect.

[0043] In a fourth aspect, the present invention provides a computer-readable storage medium having instructions stored thereon. When the instructions are executed on a computer, the display optimization method based on touch data of a liquid crystal display module as described in the first aspect or any possible design of the first aspect is executed.

[0044] In a fifth aspect, the present invention provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute a display optimization method based on touch data of a liquid crystal display module as described in the first aspect or any possible design of the first aspect.

[0045] Beneficial effects:

[0046] The display optimization method based on liquid crystal display module touch data provided by the present invention can divide the page to be displayed into blocks before displaying the page through the liquid crystal display module, and predict the user's interest in each page block according to the characteristics of the page block, and adjust the layout of the page to be displayed accordingly, and then display the adjusted page, so as to give priority to displaying the content that the user is interested in on the page, that is, it can display the page content that the user may be interested in at a position on the page that is convenient for the user to browse as much as possible, without the user having to slide the screen multiple times to locate the content that he is interested in, thus saving positioning time, facilitating the user to browse the page, improving the user experience, and facilitating practical application and promotion. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A flow chart of a display optimization method based on touch data of a liquid crystal display module provided in an embodiment of the present application;

[0048] Figure 2 A schematic block diagram of a display optimization device based on touch data of a liquid crystal display module provided in an embodiment of the present application;

[0049] Figure 3 A schematic block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in combination with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the structure of the drawings is only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.

[0051] It should be understood that although the terms first, second, etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another unit. For example, a first unit can be referred to as a second unit, and similarly, a second unit can be referred to as a first unit without departing from the scope of the exemplary embodiments of the present invention.

[0052] It should be understood that the term "and / or" that may appear in this article is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B can represent three situations: A exists alone, B exists alone, and A and B exist at the same time. The term " / and" that may appear in this article describes another type of association object relationship, indicating that two relationships may exist. For example, A / and B can represent two situations: A exists alone, and A and B exist alone. In addition, the character " / " that may appear in this article generally indicates that the previous and next associated objects are in an "or" relationship.

[0053] In order to facilitate users to browse pages, an embodiment of the present application provides a display optimization method based on liquid crystal display module touch data. The display optimization method based on liquid crystal display module touch data can give priority to displaying content that users are interested in on the page, facilitate users to browse pages, and enhance user experience.

[0054] The display optimization method based on touch data of the liquid crystal display module provided in the embodiment of the present application can be applied to the page content provider (such as the background server of the application) or the liquid crystal display module. It can be understood that the execution subject does not constitute a limitation on the embodiment of the present application.

[0055] The display optimization method based on touch data of a liquid crystal display module provided in an embodiment of the present application will be described in detail below.

[0056] like Figure 1 , which is a flow chart of a display optimization method based on touch data of a liquid crystal display module provided in the first aspect of an embodiment of the present application. The display optimization method based on touch data of a liquid crystal display module may include but is not limited to the following steps S101-S105.

[0057] Step S101: Segment a page to be displayed using a vision-based page segmentation algorithm to obtain multiple page blocks.

[0058] In the embodiment of the present application, before the liquid crystal display module displays the page to be displayed, the page to be displayed can be segmented using a vision-based page segmentation (VIPS) algorithm to obtain a plurality of page blocks.

[0059] The page segmentation by VIPS algorithm mainly includes three parts: page block extraction, separator detection and semantic reconstruction. When segmenting the display page, the VIPS algorithm can first extract all the appropriate page blocks (semantic blocks) from the DOM tree of the page, and then detect all the separators between them according to these page blocks, including horizontal and vertical directions. Finally, based on these separators, the semantic structure of the web page is reconstructed to obtain multiple page blocks. It can be understood that each page block can continue to be segmented into smaller page blocks using the VIPS algorithm.

[0060] Step S102: Extracting the spatial features, content features and text features of each page block.

[0061] The extraction of the spatial features of each page block may include, but is not limited to, the following steps S1021-S1022.

[0062] Step S1021. Obtain the center coordinates, width and height of each page block.

[0063] Step S1022. Combine the center coordinates, width, and height of each page block to obtain the spatial features of each page block.

[0064] In one or more embodiments, after the center coordinates, width, and height of each page block are combined to obtain the spatial features of each page block, the spatial features of each page block may be standardized (normalized).

[0065] Extracting the content features of each page block may include, but is not limited to, the following steps S1023-S1024.

[0066] Step S1023. Obtain the image features, hyperlink features and tag features of each page block.

[0067] Among them, the image features may include but are not limited to the number of images (in the page area corresponding to the page block), the image size and / or the image color, the hyperlink features may include but are not limited to the number of hyperlinks (in the page area corresponding to the page block) and / or the length of the hyperlink text, and the tag features may include but are not limited to the length, number and / or size of the elements in the specified tag (in the page content corresponding to the page block). The specified tag may include but are not limited to the HTML tag, INPUT tag, SELECT tag and / or FORM tag in the page content corresponding to the page block.

[0068] Step S1024: Combine the image features, hyperlink features and tag features of each page block to obtain the content features of each page block.

[0069] In one or more embodiments, after combining the image features, hyperlink features, and tag features of each page block to obtain the content features of each page block, the content features of each page block may be standardized.

[0070] In the embodiment of the present application, the image features, hyperlink features and tag features of the page block can be directly obtained through the MSHTML component. The MSHTML component is a COM component of Microsoft Corporation. The component encapsulates all elements and their attributes in the HTML language. Through the standard interface it provides, all elements of the specified web page can be accessed, so that data such as the image features, hyperlink features and tag features of each page block can be directly read.

[0071] Extracting text features of each page block may include, but is not limited to, the following steps S1025-S1028.

[0072] Step S1025. Extract the text content in each page block.

[0073] Step S1026: After word segmentation processing is performed on the text content in each page block, a plurality of first keywords corresponding to the text content in each page block are extracted using a word frequency-inverse file frequency algorithm.

[0074] Among them, the number of first keywords can be set according to actual conditions and is not specifically limited in the embodiments of the present application.

[0075] The term frequency-inverse document frequency (TF-IDF) algorithm is a statistical method used to evaluate the importance of a word to a document set or one of the documents in a corpus. The importance of a word increases in direct proportion to the number of times it appears in a document, but at the same time it decreases in inverse proportion to the frequency of its appearance in the corpus. The specific principle will not be described in detail in the embodiments of this application.

[0076] Step S1027: Calculate the similarity between the multiple first keywords corresponding to each page block and the multiple second keywords in the user interest word library to obtain the similarity value corresponding to each page block.

[0077] In the embodiment of the present application, similarity calculation can be performed between a plurality of first keywords corresponding to each page block and a plurality of second keywords in the user interest word library through, but not limited to, cosine similarity or Euclidean distance calculation.

[0078] The plurality of second keywords may be obtained by extracting keywords from the text content corresponding to the user's interested page blocks in the user's historically visited pages using a word frequency-reverse file frequency algorithm. The number of second keywords is the same as the number of first keywords, or the number of second keywords is greater than the number of first keywords. The user's interested pages may be obtained based on statistics of the user's touch data (such as the number of clicks) on each page block in the historically visited pages.

[0079] Step S1028: Using the similarity value corresponding to each page block as a text feature to obtain the text feature of each page block.

[0080] In one or more embodiments, after the text features of each page block are obtained, the text features of each page block may be standardized.

[0081] Step S103: Input the spatial features, content features and text features corresponding to each page block into a pre-trained interest model to obtain the user's predicted interest parameters for each page block.

[0082] In the embodiment of the present application, an interest model for predicting the user's interest in each page block in a page is pre-trained. After obtaining the spatial features, content features, and text features corresponding to each page block, the spatial features, content features, and text features corresponding to each page block can be input into the pre-trained interest model to obtain the user's predicted interest parameters for each page block. The larger the value corresponding to the user's predicted interest parameter for the page block, the greater the possibility that the user is interested in the page content corresponding to the page block.

[0083] In the embodiment of the present application, the interest model can be obtained by training with the spatial features, content features and text features corresponding to each page block of the historically visited pages of the user as sample inputs and the interest parameters of the user for each page block of the historically visited pages as outputs. The interest parameters of the user for each page block of the historically visited pages can be obtained by statistics based on the touch data (such as the number of clicks) of the user for each page block of the historically visited pages. For example, the more times the user clicks on a certain page block (the corresponding page content) in the historically visited pages, the more interested the user is in the certain page block (the corresponding page content), that is, the greater the value of the interest parameter corresponding to the certain page block.

[0084] The interest model may be, but is not limited to, a Convolutional Neural Networks (CNN) model or a Recurrent Neural Network (RNN) model, which is not specifically limited in the embodiments of the present application.

[0085] Step S104: Based on the predicted interest parameters of the user for each page block, the layout of the page blocks of the page to be displayed is adjusted to obtain an adjusted page.

[0086] Specifically, based on the predicted interest parameters of each page block by the user, at least one page block with the highest predicted interest parameter may be selected, and then the page content corresponding to the at least one page block may be adjusted to the region of interest in the page. The region of interest may refer to an area that can be observed without sliding the page. In this way, when the adjusted page is displayed, the user can directly browse to the page content of interest without sliding the screen.

[0087] Step S105: Displaying the adjusted page via the liquid crystal display module.

[0088] In summary, the display optimization method based on touch data of a liquid crystal display module provided by the present invention segments a page to be displayed through a vision-based page segmentation algorithm to obtain a plurality of page blocks; extracts spatial features, content features and text features of each page block; inputs the spatial features, content features and text features corresponding to each page block into a pre-trained interest model to obtain a user's predicted interest parameter for each page block; adjusts the layout of the page blocks of the page to be displayed based on the user's predicted interest parameter for each page block to obtain an adjusted page; and displays the adjusted page through a liquid crystal display module; wherein the interest model is trained using the spatial features, content features and text features corresponding to each page block of the historically visited pages of the user as sample inputs and the user's interest parameters for each page block of the historically visited pages as outputs, and the user's interest parameters for each page block of the historically visited pages are obtained based on statistics of the user's touch data for each page block of the historically visited pages. In this way, before displaying the page to be displayed through the LCD display module, the page to be displayed can be divided into blocks, and the user's interest in each page block can be predicted based on the characteristics of the page block, and the layout of the page to be displayed can be adjusted accordingly, and then the adjusted page can be displayed, so as to give priority to displaying the content that the user is interested in on the page. That is, the page content that the user may be interested in can be displayed in a position on the page that is convenient for the user to browse as much as possible, without the user having to slide the screen multiple times to locate the content that he is interested in, thus saving positioning time, facilitating user page browsing, improving user experience, and facilitating practical application and promotion.

[0089] See also Figure 2 In a second aspect of an embodiment of the present application, a display optimization device based on touch data of a liquid crystal display module is provided, which is used to optimize the page content displayed by the liquid crystal display module. The display optimization device based on touch data of the liquid crystal display module includes:

[0090] A segmentation unit, used for segmenting the page to be displayed by a vision-based page segmentation algorithm to obtain a plurality of page blocks;

[0091] An extraction unit, used to extract the spatial features, content features and text features of each page block;

[0092] A computing unit, used to input the spatial features, content features and text features corresponding to each page block into a pre-trained interest model to obtain a user's predicted interest parameter for each page block;

[0093] An adjusting unit, configured to adjust the layout of the page blocks of the to-be-displayed page based on the predicted interest parameter of the user for each page block, to obtain an adjusted page;

[0094] A display unit, used for displaying the adjusted page through a liquid crystal display module;

[0095] Among them, the interest model is trained by taking the spatial features, content features and text features corresponding to each page block of the user's historically visited pages as sample inputs, and taking the user's interest parameters for each page block of the historically visited pages as outputs. The user's interest parameters for each page block of the historically visited pages are obtained based on statistics of the user's touch data for each page block of the historically visited pages.

[0096] The working process, working details and technical effects of the display optimization device based on touch data of a liquid crystal display module provided in the second aspect of this embodiment can be found in the first aspect of the embodiment and will not be described in detail here.

[0097] like Figure 3 As shown, the third aspect of an embodiment of the present application provides an electronic device, comprising a memory, a processor and a transceiver that are communicatively connected in sequence, wherein the memory is used to store computer programs, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the display optimization method based on liquid crystal display module touch data as described in the first aspect of the embodiment.

[0098] For specific examples, the memory may include but is not limited to random access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out memory (FIFO) and / or first-in-last-out memory (FILO), etc.; the processor may be but is not limited to a microprocessor of the STM32F105 series, an ARM (Advanced RISC-Machines), an X86 or other architecture processor, or a processor with an integrated NPU (neural-network processing units); the transceiver may be but is not limited to a WiFi (Wireless Fidelity) wireless transceiver, a Bluetooth wireless transceiver, a General Packet Radio Service (GPRS) wireless transceiver, a ZigBee protocol (a low-power local area network protocol based on the IEEE802.15.4 standard, ZigBee) wireless transceiver, a 3G transceiver, a 4G transceiver and / or a 5G transceiver, etc.

[0099] The fourth aspect of this embodiment provides a computer-readable storage medium storing instructions for the display optimization method based on the touch data of the liquid crystal display module as described in the first aspect of the embodiment, that is, the computer-readable storage medium stores instructions, and when the instructions are run on a computer, the display optimization method based on the touch data of the liquid crystal display module as described in the first aspect is executed. The computer-readable storage medium refers to a carrier for storing data, which may include but is not limited to a floppy disk, an optical disk, a hard disk, a flash memory, a USB flash drive and / or a memory stick, etc., and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0100] The fifth aspect of this embodiment provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the display optimization method based on touch data of a liquid crystal display module as described in the first aspect of the embodiment, wherein the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0101] It should be understood that certain details are provided in the following description to facilitate a complete understanding of the example embodiments. However, it should be understood by those of ordinary skill in the art that the example embodiments can be implemented without these certain details. For example, the system can be shown in a block diagram to avoid obscuring the example with unnecessary details. In other examples, well-known processes, structures, and techniques may not be shown in unnecessary detail to avoid obscuring the example embodiments.

[0102] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A display optimization method based on touch data of a liquid crystal display module, used to optimize the page content displayed by the liquid crystal display module, characterized in that: include: The page to be displayed is segmented by a vision-based page segmentation algorithm to obtain multiple page blocks; Extracting spatial features, content features and text features of each page block; Inputting the spatial features, content features and text features corresponding to each page block into a pre-trained interest model to obtain the user's predicted interest parameters for each page block; Based on the predicted interest parameters of the user for each page block, adjusting the layout of the page blocks of the page to be displayed to obtain an adjusted page; Displaying the adjusted page through a liquid crystal display module; Among them, the interest model is trained by taking the spatial features, content features and text features corresponding to each page block of the user's historically visited pages as sample inputs, and taking the user's interest parameters for each page block of the historically visited pages as outputs. The user's interest parameters for each page block of the historically visited pages are obtained based on statistics of the user's touch data for each page block of the historically visited pages.

2. The display optimization method based on touch data of liquid crystal display module according to claim 1, characterized in that: Extract the spatial features of each page block, including: Get the center coordinates, width and height of each page block; The center coordinates, width and height of each page block are combined to obtain the spatial features of each page block.

3. The display optimization method based on touch data of liquid crystal display module according to claim 1, characterized in that: Extract the content features of each page block, including: Obtain the image features, hyperlink features and tag features of each page block; The image features include the number of images, the size of the images and / or the color of the images, the hyperlink features include the number of hyperlinks and / or the length of the hyperlink text, and the tag features include the length, number and / or size of the elements in the specified tag; The image features, hyperlink features and tag features of each page block are combined to obtain the content features of each page block.

4. The display optimization method based on touch data of a liquid crystal display module according to claim 3, characterized in that: The step of obtaining the image features, hyperlink features and tag features of each page block includes: The image features, hyperlink features and tag features of each page block are obtained through the MSHTML component.

5. The display optimization method based on touch data of liquid crystal display module according to claim 1, characterized in that: Extract text features of each page block, including: Extract the text content in each page block; After word segmentation processing is performed on the text content in each page block, a plurality of first keywords corresponding to the text content in each page block are extracted through a word frequency-inverse file frequency algorithm; Calculating similarity between the first keywords corresponding to each page block and the second keywords in the user interest word library to obtain a similarity value corresponding to each page block; The similarity value corresponding to each page block is used as a text feature to obtain the text feature of each page block; The plurality of second keywords are obtained by extracting keywords from text contents corresponding to the page blocks that the user is interested in in the user's historically visited pages using a word frequency-inverse document frequency algorithm.

6. The display optimization method based on touch data of liquid crystal display module according to claim 5, characterized in that: The adjusting the layout of the page blocks of the to-be-displayed page based on the predicted interest parameter of the user for each page block includes: Based on the predicted interest parameters of each page block by the user, selecting at least one page block with the highest predicted interest parameter; Adjusting the page content corresponding to the at least one page block to the area of ​​interest in the page; The region of interest refers to a region that can be observed without sliding the page.

7. The display optimization method based on touch data of liquid crystal display module according to claim 1, characterized in that: The interest model is a convolutional neural network model.

8. A display optimization device based on touch data of a liquid crystal display module, used for optimizing the page content displayed by the liquid crystal display module, characterized in that: include: A segmentation unit, used for segmenting the page to be displayed by a vision-based page segmentation algorithm to obtain a plurality of page blocks; An extraction unit, used to extract the spatial features, content features and text features of each page block; A computing unit, used to input the spatial features, content features and text features corresponding to each page block into a pre-trained interest model to obtain a user's predicted interest parameter for each page block; An adjusting unit, configured to adjust the layout of the page blocks of the to-be-displayed page based on the predicted interest parameter of the user for each page block, to obtain an adjusted page; A display unit, used for displaying the adjusted page through a liquid crystal display module; Among them, the interest model is trained by taking the spatial features, content features and text features corresponding to each page block of the user's historically visited pages as sample inputs, and taking the user's interest parameters for each page block of the historically visited pages as outputs. The user's interest parameters for each page block of the historically visited pages are obtained based on statistics of the user's touch data for each page block of the historically visited pages.

9. An electronic device, characterized in that: It includes a memory, a processor and a transceiver which are communicatively connected in sequence, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program to execute the display optimization method based on the touch data of the liquid crystal display module as described in any one of claims 1 to 7.

10. A computer program product comprising a computer program or instructions, characterized in that When the computer program or the instruction is executed by a computer, the display optimization method based on touch data of a liquid crystal display module is implemented as claimed in any one of claims 1 to 7.

Citation Information

Patent Citations

  • Web page display method and browser

    CN101930475A

  • Individual display method and device for mobile terminal webpage

    CN105204806A

  • Page optimization method and device, equipment and storage medium

    CN117271927A

  • Webpage cutting method and device, webpage response type layout method and device, equipment and medium

    CN117555638A

  • System and method for dynamically changing a display

    US20090164896A1