A method for switching and displaying digital visualization layers of community information

Abstract

The present invention discloses a method for switching and displaying digital visualization layers of community information. The method generates information of each push layer based on the information division and bit mapping of each data node of the target data. During the process, the overall compression of the data is achieved through multi-layer compression settings and bit synchronization between feature calibration points, thereby ensuring the integrity of the platform data. The compression step also reduces the computing pressure of the platform. At the same time, after obtaining the underlying logic, the corresponding levels between the layers are determined, and the sequential arrangement between the levels is determined through a deep neural optimization network model. The basic layers are integrated and arranged in the order of the levels, thereby ensuring the smooth switching and display of the layers. The method solves the problem that the existing smart community information integration platform has limited information transmission channels and the real-time update of a large amount of information will cause delays and freezes in the switching display of the information layers.

Description

Technical Field

[0001] The present invention relates to the technical field of digital information processing, and in particular to a method for switching and displaying digital visualization layers of community information. Background Art

[0002] As the most important place for residents' life and entertainment, building smart communities has become an important part of smart city construction.

[0003] In the smart community information integration platform, a large amount of community information is widely included, such as the information release section, video surveillance section, parking management section, visitor management section, etc. Each section integrates a large amount of real-time information. Due to the limited information transmission channels of the smart platform, updating a large amount of information in real time will cause "congestion" in the platform information conversion, and the switching display between information layers will be delayed and stuck. At present, the solution mainly involves adding CPU computing functions, which in exchange for the smooth switching display of information layer sections will undoubtedly cause a large increase in costs. Therefore, it is of great significance to consider a method to achieve relatively smooth switching display between information layers without affecting the integrity of the data. Summary of the Invention

[0004] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of this application to avoid obscuring the purpose of this section, the abstract and the title of the invention, and such simplifications or omissions should not be used to limit the scope of the present invention.

[0005] In view of the above-mentioned problems existing in the existing smart community information integration platform, the present invention is proposed.

[0006] Therefore, the technical problem solved by the present invention is to solve the problem that due to the limited information transmission channels of the existing smart community information integration platform, real-time updating of a large amount of information will cause delays and freezes in the switching display of information layers.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for switching and displaying digital visualization layers of community information, comprising the following steps: obtaining target data of each layer, generating information of each push layer based on the target data, and displaying node information of multiple data nodes on the push layer; obtaining the underlying logic between each layer based on the push layer information, and determining the corresponding levels between each layer based on the correlation between the underlying logics; generating a training data set based on the number of data nodes and the number of real-time transmission messages of the corresponding node information; constructing a deep neural optimization network model, and inputting the training data set into the deep neural optimization network model for optimization training to obtain a trained rate data set; determining the sequential arrangement between levels based on the message volume of the rate data set; establishing a mapping relationship topology set to connect different levels, integrating the arrangement between corresponding layers of different levels according to the arrangement order between levels, and displaying it on the touch screen on the display interface.

[0008] As a preferred solution of the community information digital visualization layer switching display method described in the present invention, obtaining the target data of each layer specifically includes using the selenium library to drive the browser to access the target layer and taking a screenshot of the target layer; performing image recognition on the screenshot through the pytesseract library; and parsing the target data.

[0009] As a preferred solution of the community information digital visualization layer switching display method described in the present invention, wherein: generating each push layer information based on the target data specifically includes: obtaining the target data corresponding to each layer; determining each data node of the target data and the network data corresponding to each data node, and synchronously completing the information division of each data node; establishing a new layer, completing the bitwise mapping on the new layer according to each data node, and generating the push information.

[0010] As a preferred solution of the community information digital visualization layer switching display method described in the present invention, after completing the information division of each data node, it also includes the following steps: compressing the network data under each data node, and setting a multi-layer compression setting; establishing feature calibration points on the basic layer and its corresponding push layer; establishing a second feature calibration point on the compressed network data; using a data matrix to perform alignment synchronization between the feature calibration point and the second feature calibration point, and defining that when the position matrix between the feature calibration point and the second feature calibration point is a unit matrix after normalization using the data matrix, the alignment synchronization is successful.

[0011] As a preferred solution of the community information digital visualization layer switching display method described in the present invention, wherein: obtaining the underlying logic between each layer based on the push layer information specifically includes assigning corresponding operation information to each layer, and the operation information includes arc elements and chord elements, wherein arc elements are used to represent data nodes, and chord elements are used to represent mutual correlation relationships; determining the connection relationship between each of the operation information based on the chord elements is the underlying logic.

[0012] As a preferred solution of the community information digital visualization layer switching display method described in the present invention, the deep neural optimization network model includes the following training steps: using a deep convolutional neural network structure to feed the data in the training data set into the deep neural optimization network model;

[0013] The deep neural optimization network model is defined as:

[0014]

[0015] The model output is calculated by encoding and decoding the deep neural network and the discriminant network, combined with the data in the training data set; and the process is repeated until the output result is satisfactory.

[0016] As a preferred solution of the community information digital visualization layer switching display method described in the present invention, the constructed deep neural optimization network model is built by a fully connected layer and an activation layer.

[0017] As a preferred solution of the community information digital visualization layer switching display method described in the present invention, the deep neural optimization network model training also includes precision control. When the training data set is input into the deep neural optimization network model, if the root mean square error between the rate data set output after training and the training data set is less than a set threshold, the model accuracy is considered to be high, and the output result of the corresponding rate data set after training is satisfactory.

[0018] As a preferred solution of the community information digital visualization layer switching display method described in the present invention, the threshold value is set to 10 messages / ms.

[0019] Beneficial effects of the present invention: The present invention provides a method for switching and displaying digital visualization layers of community information, which generates push layer information based on the information division and bit mapping of each data node of the target data. During the process, the overall compression of the data is achieved through multi-layer compression settings and bit synchronization between feature calibration points, which ensures the integrity of the platform data. The compression step also reduces the platform computing pressure. At the same time, after obtaining the underlying logic, the corresponding levels between the layers are determined, and the sequence arrangement between the levels is determined through the deep neural optimization network model. The basic layers are integrated and arranged in the order of the levels to ensure smooth layer switching and display, which solves the problem that the existing smart community information integration platform has limited information transmission channels and the real-time update of a large amount of information will cause delays and freezes in the information layer switching display. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them:

[0021] Figure 1 This is a flow chart of the overall method of switching and displaying the digital visualization layer of community information provided by the present invention.

[0022] Figure 2 This is a flow chart of the method for obtaining target data of each layer provided by the present invention.

[0023] Figure 3 This is a flow chart of the method provided by the present invention for generating information of each push layer based on target data.

[0024] Figure 4 A flow chart of the steps and methods provided by the present invention after completing the information division of each data node.

[0025] Figure 5 Schematic diagram of the convolution operation provided by the present invention.

[0026] Figure 6 Schematic diagram of the deep convolutional network structure provided by the present invention. DETAILED DESCRIPTION

[0027] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0028] Under the smart community information integration platform, a large amount of community information is widely included, such as the information release section, video surveillance section, parking lot management section, visitor management section, etc. Each section integrates a large amount of real-time information. Due to the limited information transmission channels of the smart platform, real-time updating of a large amount of information will cause "congestion" in the platform information conversion, and there will be delays and freezes in the switching display between information layers.

[0029] Therefore, please refer to Figure 1 The present invention provides a method for switching and displaying digital visualization layers of community information, comprising the following steps:

[0030] S1: Obtain target data for each layer, generate information for each push layer based on the target data, and display node information of multiple data nodes on the push layer;

[0031] For further information, see Figure 2 , obtaining target data of each layer specifically includes:

[0032] Use the selenium library to drive the browser to access the target layer and take a screenshot of the target layer;

[0033] The program is defined as follows:

[0034] from selenium import webdriver

[0035] driver = webdriver.Chrome()

[0036] driver.get('url')

[0037] driver.get_screenshot_as_png()

[0038] driver.save_screenshot('file_path')

[0039] Perform image recognition on screenshots using the pytesseract library;

[0040] The program is defined as follows:

[0041] importpytesseract

[0042] from PIL importImage

[0043] image=Image.open('screenshot.png')

[0044] code=pytesseract.image_to_string(image)

[0045] print(code).

[0046] OCR recognizes and parses the target data.

[0047] It should be noted that if you use OCR recognition for analysis, you only need to focus on what the human eye sees, take a screenshot and perform image recognition.

[0048] OCR programs can directly recognize text content without analyzing whether a website uses asynchronous loading technologies like Ajax. Optical Character Recognition (OCR) refers to the process by which an electronic device (such as a scanner or digital camera) examines printed characters, determines their shape by detecting patterns of light and dark, and then uses character recognition methods to translate these shapes into computer text. Specifically, for printed characters, the text in a paper document is optically converted into a black-and-white dot matrix image file. Recognition software then converts the imaged text into a text format for further editing and processing in word processing software. Debugging or improving recognition accuracy using auxiliary information is a crucial aspect of OCR, which is why the term "Intelligent Character Recognition" (ICR) was coined. Key metrics for measuring the performance of an OCR system include rejection rate, false positive rate, recognition speed, user interface friendliness, product stability, ease of use, and feasibility.

[0049] For further information, see Figure 3 , based on the target data, the push layer information is generated, including:

[0050] Get the target data corresponding to each layer;

[0051] Determine each data node of the target data and the network data corresponding to each data node, and simultaneously complete the information division of each data node;

[0052] Create a new layer, complete the bit mapping on the new layer according to each data node, and generate a push layer.

[0053] It should be noted that after OCR recognizes the target data, it can obtain multiple data nodes. For example, the defined node 1 represents the data of the first block of the current layer. Each node corresponds to a set of network data. The operator then completes the information division of each data node. The division process is based on the characteristics of the layer data. The relevant steps are the direct application of existing conventional technologies and will not be elaborated here.

[0054] The process of creating a new layer is directly generated by the software, and the generation process is the application of existing technology. After the new layer is generated, the data nodes in the target layer are aligned and mapped. The mapping process is directly completed by the software, which is equivalent to "copying" the data nodes in the target layer to the new layer.

[0055] The data node information partitioning process includes:

[0056] The following calculations are performed based on the description principle of the quaternary information system:

[0057]

[0058] Among them, G bi Feature b i The value set of W is the set of all individuals in the data system, which is a non-empty finite set, b is the characteristic of the individual, G a is the value range of feature b.

[0059] Furthermore, it also includes:

[0060] Use the data operation matrix to map to the entire data set, define W = {d1, d2…dn}, b = {MS1, MS2…MSq}, G a =OPr is the value range of feature b, that is, G a =∪1≤i≤n,1≤j≤qOPrij;

[0061] The mapping function f is defined as the function output of the task in the planned task sequence for the change operation of di in the data set W as A, and the output of the non-change operation as N;

[0062] For any feature subset of an individual in the data system, an indistinguishable relation R(b) = {(u,u′)∈U×U: f(u,b) = f(u′,b)} is defined in the U×U space;

[0063] According to the indistinguishability relation R(b) on U, the data block U / R(b) is recorded as [u]b, which is defined as the data primitive after division.

[0064] Some of the core codes used to implement the above algorithm are as follows:

[0065]

[0066] For additional information, see Figure 4 After completing the information division of each data node, the following steps are also included:

[0067] Compression of network data under each data node, with multi-layer compression settings;

[0068] Establish feature calibration points on the base layer and its corresponding push layer;

[0069] Establishing a second feature calibration point on the compressed network data;

[0070] A data matrix is used to perform alignment synchronization between the feature calibration point and the second feature calibration point, and it is defined that the alignment synchronization is successful when the position matrix between the feature calibration point and the second feature calibration point is a unit matrix after normalization using the data matrix.

[0071] It should be noted that, considering the smoothness of data transmission and the simplicity of bit mapping, the network data corresponding to the data node is subjected to multi-layer compression settings. The compression processing includes:

[0072] Use ASCII code to define letters and symbols in data information;

[0073] Convert integer and floating point data from string type to int type;

[0074] The converted data is fused and processed using binary strategies to compress the amount of transmitted data.

[0075] At the same time, the calibration of the characteristic calibration point and the second characteristic calibration point is that the data processor directly considers the corresponding point positions to be directly calibrated. Considering that the characteristic calibration point and the second characteristic calibration point have different coordinate system positions, the characteristic calibration points of the two are aligned through the data matrix.

[0076] The data matrix is specifically:

[0077]

[0078] C c (X c 、Y c 、Z c ) is the position description of the characteristic calibration point, (X u 、Y u ) is the calibration matrix of the second characteristic calibration point. When f is normalized to 1, the calibration is defined as successful.

[0079] S2: Based on the information of each push layer, the underlying logic between each layer is obtained, and the corresponding hierarchy between each layer is determined according to the relationship between the underlying logic;

[0080] Furthermore, the underlying logic between each layer is obtained based on the information of each push layer, including:

[0081] Assign corresponding operation information to each layer. The operation information includes arc elements and chord elements. Arc elements are used to represent data nodes, and chord elements are used to represent mutual relationships.

[0082] The underlying logic is to determine the connection relationship between each operation information based on the chord elements.

[0083] It should be noted that after the underlying logic is obtained, the connection relationship between each operation information is also obtained, and the connection relationship between each layer is also obtained. The initial layer is directly defined by the calculation unit as the basic layer, and the subsequent layers are directly defined as the second layer, third layer, fourth layer, etc. in sequence according to the corresponding layer connection relationship. The definition of the basic layer is directly selected by the processing unit, and no unnecessary details are given here.

[0084] S3: Generate a training data set based on the number of data nodes and the number of real-time transmissions of corresponding node information messages;

[0085] The training data set is directly generated by integrating the corresponding message transmission data after the processing unit obtains it.

[0086] S4: Build a deep neural optimization network model and input the training data set into the deep neural optimization network model for optimization training to obtain a trained rate data set;

[0087] It should be noted that the deep neural optimization network model includes the following training steps:

[0088] Use the deep convolutional neural network structure to feed the data in the training dataset into the deep neural optimization network model;

[0089] The deep neural optimization network model is defined as:

[0090]

[0091] The model output is calculated by encoding and decoding the deep neural network and the discriminator network, combined with the data in the training dataset;

[0092] Repeat the process until the output is satisfactory.

[0093] Among them, the constructed deep neural optimization network model is built by fully connected layers and activation layers. The number of input interfaces is determined by the number of input parameters, and the number of output interfaces is determined by the number of control instructions issued; each layer is a digital matrix, and the matrix multiplication is performed between each layer.

[0094] The construction method of the deep neural optimization network model and the output results of the model after data inclusion are both creatively constructed using existing conventional software technology. The specific details of the construction are directly generated and output by the software in a standardized manner, so no unnecessary elaboration is required here.

[0095] Furthermore, the training of the deep neural optimization network model also includes precision control. When the training data set is input into the deep neural optimization network model, if the root mean square error between the rate data set output after training and the training data set is less than the set threshold, the model accuracy is considered to be high, and the corresponding output result of the trained rate data set is satisfactory.

[0096] Furthermore, the threshold is set to 10 packets / ms, that is, when the rate is less than 10 packets / ms, the model is considered to have a high accuracy.

[0097] It should be noted that: Figure 5 As shown in the figure, it is a schematic diagram of the convolution operation. Figure 6 As shown in Figure 2, it is a schematic diagram of the deep convolutional network structure.

[0098] S5: Determine the order of the layers based on the message volume of the rate data set;

[0099] The arrangement method can prioritize the message volume from large to small to determine the first level, second level and corresponding subsequent arrangement.

[0100] S6: Establish a mapping relationship topology set, connect different levels, integrate the arrangement of corresponding layers of different levels according to the arrangement order between the levels, and switch the display on the display interface through touch screen.

[0101] It should be noted that the process of establishing the mapping relationship topology set is the application of existing conventional integration technology, which will not be described in detail here.

[0102] The present invention provides a method for switching and displaying digital visualization layers of community information. The method generates information of each push layer based on the information division and bit mapping of each data node of the target data. During the process, the overall compression of the data is achieved through multi-layer compression settings and bit synchronization between feature calibration points, thereby ensuring the integrity of the platform data. The compression step also reduces the computing pressure of the platform. At the same time, after obtaining the underlying logic, the corresponding levels between the layers are determined, and the sequential arrangement between the levels is determined through a deep neural optimization network model. The basic layers are integrated and arranged according to the arrangement order between the levels, thereby ensuring smooth layer switching and display, and solving the problem that the existing smart community information integration platform has limited information transmission channels and the real-time update of a large amount of information will cause delays and freezes in the information layer switching display.

[0103] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for switching and displaying digital visualization layers of community information, characterized by: The following steps are included: Obtain target data of each layer, and generate information of each push layer based on the target data, wherein the push layer displays node information of multiple data nodes; Obtaining the underlying logic between each layer based on the push layer information, and determining the corresponding hierarchy between each layer according to the association relationship between the underlying logic; Generate a training data set based on the number of data nodes and the number of real-time transmissions of corresponding node information messages; Constructing a deep neural optimization network model, and inputting the training data set into the deep neural optimization network model for optimization training to obtain a trained rate data set; Determining the order of the levels according to the message volume of the rate data set; Establish a mapping relationship topology set, connect different levels, integrate the arrangement of corresponding layers of different levels according to the arrangement order between levels, and switch the display by touch screen on the display interface.

2. The method for switching and displaying digital visualization layers of community information according to claim 1, characterized in that: Obtaining the target data of each layer specifically includes: Use the selenium library to drive the browser to access the target layer and take a screenshot of the target layer; Perform image recognition on the screenshot using the pytesseract library; The target data is parsed.

3. The method for switching and displaying digital visualization layers of community information according to claim 2, characterized in that: Generating each push layer information based on the target data specifically includes: Obtaining the target data corresponding to each layer; Determine each data node of the target data and the network data corresponding to each data node, and simultaneously complete the information division of each data node; A new layer is created, and bit mapping is completed on the new layer according to each data node to generate the push layer.

4. The method for switching and displaying digital visualization layers of community information according to claim 3, characterized in that: After completing the information division of each data node, the following steps are also included: Compression of network data under each data node, with multi-layer compression settings; Establishing feature calibration points on the base layer and its corresponding push layer; Establishing a second feature calibration point on the compressed network data; A data matrix is used to perform alignment synchronization between the feature calibration point and the second feature calibration point, and it is defined that when the position matrix between the feature calibration point and the second feature calibration point is a unit matrix after normalization using the data matrix, the alignment synchronization is successful.

5. The method for switching and displaying digital visualization layers of community information according to claim 4, characterized in that: The underlying logic between each layer is obtained based on the push layer information, specifically including: Assign corresponding operation information to each layer, wherein the operation information includes arc elements and chord elements, wherein arc elements are used to represent data nodes, and chord elements are used to represent mutual associations; Determining the connection relationship between each piece of operation information based on the chord element is the underlying logic.

6. The method for switching and displaying digital visualization layers of community information according to claim 5, characterized in that: The deep neural optimization network model includes the following training steps: Using a deep convolutional neural network structure to feed the data in the training data set into the deep neural optimization network model; The deep neural optimization network model is defined as: Calculating the model output by encoding and decoding the deep neural network and the discriminant network in combination with the data in the training dataset; Repeat the process until the output is satisfactory.

7. The method for switching and displaying digital visualization layers of community information according to claim 6, characterized in that: The constructed deep neural optimization network model is built by fully connected layers and activation layers.

8. The method for switching and displaying digital visualization layers of community information according to claim 7, characterized in that: The deep neural optimization network model training also includes precision control. When the training data set is input into the deep neural optimization network model, if the root mean square error between the rate data set output after training and the training data set is less than a set threshold, the model accuracy is considered to be high, and the output result of the corresponding rate data set after training is satisfactory.

9. The method for switching and displaying digital visualization layers of community information according to claim 8, characterized in that: The threshold is set to 10 messages / ms.

Images