Intelligent equipment management cloud platform and method based on Internet of Things and big data analysis

Abstract

The invention provides an intelligent device management cloud platform and method based on the Internet of Things and big data analysis, and the platform comprises a device data obtaining subsystem which is used for accessing a plurality of intelligent devices which need to be managed based on the Internet of Things technology, and obtaining the device data of the intelligent devices; the big data analysis subsystem is used for analyzing the equipment data based on a big data analysis technology to generate an analysis result; and the dynamic display subsystem is used for dynamically displaying the equipment data and the analysis result based on the intelligent billboard. The invention discloses an intelligent device management cloud platform and method based on Internet of Things and big data analysis. A plurality of intelligent devices needing to be managed are connected to obtain device data; a big data analysis technology is introduced to analyze equipment data to obtain an analysis result, so that the accuracy of the analysis result is improved; and the equipment data and the analysis result are dynamically displayed based on the intelligent billboard, which is more intuitive.

Description

Technical Field

[0001] The present invention relates to the technical field of the Internet of Things, and particularly to an intelligent device management cloud platform and method based on the Internet of Things and big data analysis. Background Art

[0002] The Internet of Things (IoT) is a technology that connects physical devices (such as sensors, controllers, and intelligent devices, etc.) through the Internet to achieve data interaction and collaborative work between devices. Its core lies in "connecting things to things". Through the network, devices can autonomously sense, collect data, and perform intelligent processing, thereby realizing intelligent management and control. Big data analysis technology is used to process and mine the value in these data, including data cleaning, storage, analysis, and visualization. Through this combination, the IoT system can achieve more efficient decision-making support and intelligent management.

[0003] However, the data uploaded by intelligent devices is multi-modal and multi-dimensional. Analyzing complex data types is prone to analysis errors, whether by humans or large models, which in turn affects the accuracy of the analysis results.

[0004] In view of this, there is an urgent need for an intelligent device management cloud platform and method based on the Internet of Things and big data analysis to at least solve the above deficiencies. Summary of the Invention

[0005] One of the purposes of the present invention is to provide an intelligent device management cloud platform and method based on the Internet of Things and big data analysis, which accesses multiple intelligent devices to be managed to obtain device data; introduces big data analysis technology to analyze the device data to obtain analysis results, improving the accuracy of the analysis results; and dynamically displays the device data and analysis results based on an intelligent dashboard, which is more intuitive.

[0006] The intelligent device management cloud platform based on the Internet of Things and big data analysis provided by the embodiments of the present invention includes:

[0007] A device data acquisition subsystem, which is used to access multiple intelligent devices to be managed based on Internet of Things technology and obtain the device data of the intelligent devices; the device data includes: working status, operating parameters, and maintenance information;

[0008] A big data analysis subsystem, which is used to analyze the device data based on big data analysis technology to generate analysis results; the analysis results include: fault warnings, energy efficiency reports, and operation trends;

[0009] A dynamic display subsystem, which is used to dynamically display the device data and analysis results based on an intelligent dashboard.

[0010] Preferably, the device data acquisition subsystem is based on Internet of Things technology and accesses multiple intelligent devices to be managed, including:

[0011] Obtain the API call requests of the devices to be accessed;

[0012] Obtain the parsing information of the API call requests by the open API;

[0013] Perform corresponding processing according to the parsing information and generate response data;

[0014] Send back the response data through the open API.

[0015] Preferably, the big data analysis subsystem analyzes the device data based on big data analysis technology and generates analysis results, including:

[0016] Obtain the data tags of the device data;

[0017] Connect to the big data platform and obtain the analysis big data corresponding to the data tags in the big data platform;

[0018] Train a deep learning model according to the analysis big data to obtain an analysis big model for the analysis data type corresponding to the data tags;

[0019] Input the device data into the analysis big model for the corresponding analysis data type of the data tags according to the corresponding data tags to obtain analysis results.

[0020] Preferably, the big data analysis subsystem connects to the big data platform and obtains the analysis big data corresponding to the data tags in the big data platform, including:

[0021] Obtain the page tags of the big data platform;

[0022] Input the page tags, data tags, and tag correlation query statements into the large language model to obtain the tag correlation;

[0023] If the tag correlation is greater than or equal to the preset tag correlation threshold, obtain the page content of the subordinate pages of the page tags;

[0024] Predict the access intention of the access users of the page content;

[0025] If the access intention is to query the analysis process of the target device data corresponding to the data tags, obtain the historical page browsing information of the access users with the corresponding access intention;

[0026] Locate the analysis big data according to the historical page browsing information.

[0027] Preferably, the big data analysis subsystem locates the analysis big data according to the historical page browsing information, including:

[0028] Determine a preset page viewing progress marker based on historical page viewing information, and calculate the movement rate of the page viewing progress marker;

[0029] If the movement rate is less than the average movement rate within a preset duration, locate the first viewed page;

[0030] Determine the horizontal line where the virtual pointer of the first viewed page is located;

[0031] Analyze the first line-of-sight information of the first viewed page to obtain the line-of-sight point trajectory on both sides of the horizontal line;

[0032] According to the line-of-sight point trajectory, attempt to obtain the saccade feature;

[0033] If the attempt to obtain is successful, determine the local viewed page in the first viewed page according to the saccade point trajectory, and use it as the second viewed page;

[0034] If the attempt to obtain fails, determine the first viewing area above the horizontal line and the second viewing area below the horizontal line in the first viewed page according to the line-of-sight point trajectory;

[0035] Compare the density of the line-of-sight points in the first viewing area and the second viewing area, and determine the first viewing area or the second viewing area with a higher density of line-of-sight points as the third viewed page;

[0036] Use the second viewed page or the third viewed page as the fourth viewed page, perform text recognition on the fourth viewed page, and determine the text recognition result;

[0037] If the line-of-sight dwell time corresponding to the recognized character in the text recognition result is greater than or equal to the preset duration threshold, use the corresponding text recognition result as the analyzed big data.

[0038] Preferably, the dynamic display subsystem dynamically displays the device data and analysis results based on an intelligent dashboard, including:

[0039] Construct a virtual entity network according to the device data and a preset virtual entity network construction template;

[0040] Associate the virtual entity and the analysis result according to the corresponding relationship between the analysis result and the virtual entity in the virtual entity network;

[0041] Configure the viewing trigger condition for the analysis result associated with the virtual entity;

[0042] Obtain the current operation information of the intelligent dashboard;

[0043] Perform dynamic display according to the viewing trigger condition and the current operation information of the intelligent dashboard.

[0044] Preferably, the viewing trigger conditions for dynamically displaying the analysis results associated with the virtual entities configured by the subsystem include:

[0045] When the warning features of the intelligent device corresponding to the virtual entity conform to the first target warning features, and the current operation features of the virtual entity satisfy any of the standard operation features, display the analysis results associated with the first target virtual entity, where the first target virtual entity is: the virtual entity that affects access to the cloud platform determined according to the first target warning features;

[0046] When the warning features of the intelligent device corresponding to the virtual entity conform to the second target warning features, and the current operation features of the virtual entity satisfy any of the standard operation features, display the analysis results associated with the second target virtual entity, where the second target virtual entity is: the virtual entity and the trace virtual entity, and the trace virtual entity is: the virtual entity of the intelligent device that causes the intelligent device to generate the second target warning features;

[0047] When there is no warning information for the intelligent device corresponding to the virtual entity, and the current operation features of the virtual entity satisfy any of the standard operation features, display the analysis results associated with the corresponding virtual entity;

[0048] Among them, the standard operation features include: the viewing duration of the virtual entity is greater than or equal to the preset viewing duration threshold and the virtual entity is clicked by the pointer of the dashboard control.

[0049] Preferably, the dynamic display subsystem obtains the current operation information of the intelligent dashboard, including:

[0050] Obtain the second line-of-sight information of the intelligent dashboard;

[0051] Obtain the pointer operation of the dashboard control pointer;

[0052] Use the second line-of-sight information and the pointer operation together as the current operation information.

[0053] Preferably, the dynamic display subsystem performs dynamic display according to the viewing trigger conditions and the current operation information of the intelligent dashboard, including:

[0054] Obtain the viewing condition factor extraction template;

[0055] Based on the preset factor extraction timing determination rule, determine whether the virtual entity meets the viewing condition factor extraction timing;

[0056] If it is satisfied, use the corresponding virtual entity as the third target virtual entity;

[0057] According to the third target virtual entity, the current operation information, and the viewing condition factor extraction template, extract the first viewing condition factor;

[0058] Extract the second viewing condition factor according to the viewing trigger condition configuration information and the viewing condition factor extraction template of the third target virtual entity;

[0059] Calculate the factor matching degree of the first viewing condition factor and the second viewing condition factor. If the factor matching degree is greater than or equal to the preset factor matching degree threshold, determine the display content according to the viewing trigger condition of the corresponding third target virtual entity.

[0060] Preferably, perform dynamic display according to the viewing trigger condition and the current operation information of the intelligent dashboard, and further include:

[0061] Obtain the operation gesture when the dashboard viewer views the analysis result text box;

[0062] If the acquisition is successful, perform gesture matching between the operation gesture and the preset information capture operation gesture;

[0063] If the gesture matching is successful, generate a pre-export reminder for the result data in the corresponding analysis result text box based on the preset pre-export reminder rule;

[0064] Obtain the confirmation operation of the pre-export reminder, and the confirmation operation includes: confirm export and export withdrawal;

[0065] If the confirmation operation is to confirm export, store the corresponding result data in the export form;

[0066] If the confirmation operation is export withdrawal, obtain the previous gesture operation within the preset time period before the dashboard viewer makes the operation gesture;

[0067] Extract the target features of the historical previous gesture operation, and the target features include: different gesture actions, the sequence relationship and time interval between different gesture actions;

[0068] Perform clustering of the previous gesture operations according to the target features;

[0069] If the clustering result meets the clustering conditions, use the corresponding previous gesture operation as the pre-determined action set of the operation gesture; the clustering conditions are: the number of clustering targets of the previous gesture operation in the clustering result is greater than the first threshold, and the number of actions of the previous gesture operation in the clustering result is greater than the second threshold;

[0070] Obtain the confirmed export form of the export form;

[0071] Extract the graph features according to the analysis entity and the analysis entity knowledge graph of the result data of the confirmed cause form;

[0072] Train the knowledge model corresponding to the analysis entity according to the graph characteristics;

[0073] Input the result data in the confirmation export form into the knowledge model, obtain the analysis results output by the knowledge model, and display the analysis results to the personnel viewing the dashboard;

[0074] Perform dynamic display according to the viewing trigger conditions and the current operation information of the intelligent dashboard, and further include:

[0075] After recording the pre-determined action set of the operation gesture, before there is a successful gesture match for the corresponding operation gesture and a pre-export reminder is generated in the future, analyze the necessity of the pre-export reminder according to the pre-determined action set of the corresponding operation gesture. If necessary, give a pre-export reminder; otherwise, do not give a reminder.

[0076] The intelligent device management method based on the Internet of Things and big data analysis provided by the embodiments of the present invention includes:

[0077] Step 1: Based on the Internet of Things technology, access multiple intelligent devices that need to be managed, and obtain the device data of the intelligent devices; the device data includes: working status, operating parameters, and maintenance information;

[0078] Step 2: Analyze the device data based on big data analysis technology to generate analysis results; the analysis results include: fault warning, energy efficiency report, and operation trend;

[0079] Step 3: Dynamically display the device data and the analysis results based on the intelligent dashboard.

[0080] The beneficial effects of the present invention are:

[0081] The present invention accesses multiple intelligent devices that need to be managed to obtain device data; introduces big data analysis technology to analyze the device data to obtain analysis results, improving the accuracy of the analysis results; and dynamically displays the device data and the analysis results based on the intelligent dashboard, which is more intuitive.

[0082] Other features and advantages of the present invention will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in this application document.

[0083] The technical solutions of the present invention will be further described in detail below through the accompanying drawings and embodiments. Description of the Drawings

[0084] The accompanying drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention. In the accompanying drawings:

[0085] Figure 1Schematic diagram of the intelligent device management cloud platform based on the Internet of Things and big data analysis in the embodiments of the present invention;

[0086] Figure 2 Schematic diagram of the intelligent device management method based on the Internet of Things and big data analysis in the embodiments of the present invention. Detailed implementation manners

[0087] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only for the purpose of illustrating and explaining the present invention, and are not intended to limit the present invention.

[0088] The embodiments of the present invention provide an intelligent device management cloud platform based on the Internet of Things and big data analysis, as Figure 1 shown, including:

[0089] The device data acquisition subsystem 1 is used to access multiple intelligent devices to be managed based on the Internet of Things technology and acquire the device data of the intelligent devices; the device data includes: working status (such as: "normal operation", "abnormal operation"), operating parameters (such as: internal component temperature, electrical parameters (such as: current, voltage)), and maintenance information (such as: historical maintenance records (including: historical maintenance fault types, historical maintenance strategies, fault time, and maintenance time));

[0090] The device data acquisition subsystem accesses multiple intelligent devices to be managed based on the Internet of Things technology, including:

[0091] Obtaining an API call request for the device to be accessed; wherein, the API call request is a request sent by the device to be accessed to the server (intelligent device management cloud platform), for example: the device to be accessed sends a data reporting request to the intelligent device management cloud platform;

[0092] Obtaining the parsing information of the API call request by the open API; wherein, the open API is an API interface publicly provided by the intelligent device management cloud platform to allow external systems to access the functions and services of the platform; the parsing information is the information obtained after the cloud platform parses the request content after receiving the API call request, and the parsing process includes verifying the request format and extracting the request parameters;

[0093] Performing corresponding processing according to the parsing information and generating response data; wherein, performing corresponding processing according to the parsing information is to verify the request and determine whether to execute the corresponding request, for example: verifying the API key, and if the verification passes, storing the data reported by the device in the database; the response data is the data fed back by the cloud platform to the intelligent device after processing the API call request, for example: returning a confirmation message indicating successful data storage;

[0094] Return the response data through the open API;

[0095] The big data analysis subsystem 2 is used to analyze the device data based on big data analysis technology to generate analysis results; the analysis results include: fault warning, energy efficiency report, and operation trend;

[0096] The dynamic display subsystem 3 is used to dynamically display the device data and analysis results based on an intelligent dashboard.

[0097] The working principle and beneficial effects of the above technical solution are as follows:

[0098] The intelligent device management cloud platform based on the Internet of Things and big data analysis in the embodiment of the present invention includes a series of management functions such as device management, user management, agent management, order management, after-sales management, and data analysis; the platform supports multi-role login and unified management of multi-brand and multi-category devices, can view the operation status of different product data by independently editing the dashboard, and also has an open API to dock with the enterprise management system; the platform collects the working status, operation parameters, and maintenance information of various devices in real time through the Internet of Things technology and transmits the data to the cloud platform for storage; the platform analyzes the operation data of the devices through big data analysis technology to generate fault warnings, energy efficiency reports, operation trends, etc., to help users optimize the operation and maintenance strategies of the devices.

[0099] The present invention docks with multiple intelligent devices to be managed to obtain device data; introduces big data analysis technology to analyze the device data to obtain analysis results, improving the accuracy of the analysis results; dynamically displays the device data and analysis results based on an intelligent dashboard, which is more intuitive.

[0100] In one embodiment, the big data analysis subsystem analyzes the device data based on big data analysis technology to generate analysis results, including:

[0101] Obtain the data tags of the device data; where the data tags are: keywords for classifying and marking the device data, such as: "working status data", "operation parameter data", and "maintenance information data", etc.;

[0102] Dock with the big data platform to obtain the analysis big data corresponding to the data tags in the big data platform; where the analysis big data is: the process data of analyzing the data of the corresponding data type of the data tags in the big data platform, such as: the big data platform is: the Internet of Things communication forum, the data tag is: the working status data of the remotely connected camera, then the analysis big data is: the discussion content in the discussion thread about the handling experience of the remotely connected camera dropping the line, the discussion content in the discussion thread about the handling experience of the remotely connected camera image upload delay, etc.;

[0103] An analytical large model that trains a deep learning model based on analytical big data to obtain the analytical data type corresponding to the data label; where the analytical data type is the analytical data category of the analytical big data corresponding to the data label. For example, if the data label is: the working status data of a remotely connected camera, then the analytical data category is: analyzing the working status of a remotely connected camera; during training, the historical device data in the analytical big data is used as the model input, and the analysis result is used as the model output to train a preset neural network model until convergence.

[0104] Input the device data into the analytical large model of the analytical data type corresponding to the data label according to the corresponding data label, and obtain the analysis result.

[0105] The docking with the big data platform to obtain the analytical big data corresponding to the data label in the big data platform includes:

[0106] Obtain the page labels of the big data platform; where the page labels are the marks preset in the big data platform page for classifying the page content, such as: "Industry", "Logistics", "Smart City", and "Contact Us", etc., and are crawled through web crawlers.

[0107] Input the page label, data label, and label correlation query statement into the large language model to obtain the label correlation; where the large language model is: GPT4, claude2, etc.; the label correlation characterizes the degree of association of the label content and is obtained by asking questions to the large language model. For example, the question: Please help me query the label correlation between "the working status data of a remotely connected camera" and "Industry", and the model answers: 90 / 100; Another example: the question: Please help me query the label correlation between "the working status data of a remotely connected camera" and "Contact Us", and the model answers: 20 / 100.

[0108] If the label correlation is greater than or equal to the preset label correlation threshold, obtain the page content of the subordinate page of the page label; where the preset label correlation threshold is set manually in advance, such as: 85.

[0109] Predict the access intention of the access user of the page content; where the access user is: the user who has accessed the page content historically; the access intention is inferred based on the search content input by the access user into the search box, and the search box is the retrieval box of the web content of the big data platform.

[0110] If the access intention is to query the analysis process of the target device data corresponding to the data label, obtain the historical page browsing information of the access user with the corresponding access intention; where the historical page browsing information is: the browsing action information of the access user, including: the page stay data of the browsing page, the line-of-sight data of the page, and the operation data (such as: mouse click, selection, etc.).

[0111] Locate and analyze big data based on historical page view information;

[0112] The locating and analyzing of big data based on historical page view information includes:

[0113] Determine a preset page view progress marker according to historical page view information, and calculate the moving rate of the page view progress marker; wherein, the preset page view progress marker is: a marker used to track the page view progress of an accessing user when the user browses a page, such as: the progress identifier in a page view progress bar;

[0114] If the moving rate is less than the average moving rate within a preset duration, locate the first viewed page; wherein, the preset duration is: within 10 seconds before the determination moment for determining the moving rate, and the determination time period is preset manually, such as: 1 second; the first viewed page is: the content displayed on the page display device when the moving rate of the page view progress marker is less than the average moving rate within the preset duration;

[0115] Determine the horizontal line where the virtual pointer of the first viewed page is located; wherein, the virtual pointer is: a pointer representing the current browsing focus of the accessing user, such as: a mouse pointer; the horizontal line where the virtual pointer is located is: a straight line passing through the display point selected by the pointer on the display device and perpendicular to the changing direction of the content displayed on the display device and within the plane of the display screen of the display device;

[0116] Analyze the first line-of-sight information of the first viewed page to obtain the line-of-sight point trajectories on both sides of the horizontal line; wherein, the line-of-sight point trajectory is: the line-of-sight points of the accessing user on both sides of the horizontal line of the first viewed page;

[0117] According to the line-of-sight point trajectories, attempt to obtain saccade features; wherein, the saccade features are: the features of the accessing user's saccadic viewing of the content when browsing the first viewed page, such as: the point interval between adjacent line-of-sight points is less than or equal to a preset point interval threshold, and the variance of the point intervals is less than or equal to a preset variance threshold;

[0118] If the attempt to obtain is successful, determine the local viewed page in the first viewed page according to the saccade point trajectories and use it as the second viewed page;

[0119] If the attempt to obtain fails, determine the first viewing area above the horizontal line and the second viewing area below the horizontal line in the first viewed page according to the line-of-sight point trajectories;

[0120] Compare the line-of-sight point density of the first viewing area and the second viewing area, and determine the first viewing area or the second viewing area with a larger line-of-sight point density as the third viewed page; wherein, the line-of-sight point density is: the result obtained by dividing the number of line-of-sight points by the area of the viewing area;

[0121] Take the second browsing page or the third browsing page as the fourth browsing page, perform text recognition on the fourth browsing page, and determine the text recognition result; wherein, the text recognition result is the result of analyzing and recognizing the text content on the page.

[0122] If the fixation duration of the line of sight corresponding to the text recognition result for the recognized characters is greater than or equal to the preset duration threshold, then take the corresponding text recognition result as the analyzed big data. The preset duration threshold is set manually in advance.

[0123] The working principle and beneficial effects of the above technical solution are as follows:

[0124] The present invention introduces the moving speed of the page browsing progress mark. When the moving speed is less than the average moving speed, determine the current first browsing page; analyze the first line of sight information of the first browsing page to obtain the line of sight point trajectory on both sides of the horizontal line; according to the line of sight point trajectory, try to obtain the saccade feature; when the saccade feature is recognized, it means that the target user has not yet located the word they want to view. Therefore, take the second browsing page corresponding to all saccade point trajectories as the page for extracting analyzed big data; when the saccade feature is not recognized, it means that the viewer has initially located the area to be viewed. Compare the line of sight point density of the first viewing area and the second viewing area, and determine the first viewing area or the second viewing area with a larger line of sight point density as the third browsing page; perform text recognition on the second browsing page or the third browsing page, determine the text recognition result, and determine the text recognition result whose fixation duration of the line of sight corresponding to the recognized characters is greater than or equal to the preset duration threshold as the analyzed big data, improving the selection accuracy of the analyzed big data.

[0125] In one embodiment, the dynamic display subsystem dynamically displays device data and analysis results based on an intelligent dashboard, including:

[0126] Construct a virtual entity network according to the device data and a preset virtual entity network construction template; wherein, the virtual entity network construction template includes multiple intelligent devices and digital mapping rules for the relationships between devices, and the virtual entity network is an architecture that simulates the behavior and state of physical devices through virtual entities generated by comparing the device data with the virtual entity network construction template.

[0127] Associate the virtual entity and the analysis result according to the corresponding relationship between the analysis result and the virtual entity in the virtual entity network.

[0128] Configure the viewing trigger condition for the analysis result associated with the virtual entity.

[0129] Obtain the current operation information of the intelligent dashboard; wherein, the current operation information includes: the second line-of-sight information of the intelligent dashboard (the line-of-sight trajectory of the person viewing the intelligent dashboard) and the pointer operation of the dashboard control pointer.

[0130] Perform dynamic display according to the view trigger condition and the current operation information of the intelligent dashboard.

[0131] The view trigger condition for configuring the analysis result associated with the virtual entity includes:

[0132] When the warning feature of the intelligent device corresponding to the virtual entity conforms to the first target warning feature, and the current operation feature of the virtual entity satisfies any standard operation feature, display the analysis result associated with the first target virtual entity. The first target virtual entity is: the virtual entity that affects access to the cloud platform determined according to the first target warning feature; wherein, the warning feature is: the characteristic representation of the warning information when there is a warning information in the analysis result of the intelligent device, and the first target warning feature is: device failure and communication interruption; the first target virtual entity includes: the virtual entity itself corresponding to the first target warning feature and the virtual entities corresponding to other intelligent devices affected by it, for example: the subordinate intelligent device whose communication is interrupted due to the failure of the intelligent device corresponding to the first target warning feature.

[0133] When the warning feature of the intelligent device corresponding to the virtual entity conforms to the second target warning feature, and the current operation feature of the virtual entity satisfies any standard operation feature, display the analysis result associated with the second target virtual entity. The second target virtual entity is: the virtual entity and the trace virtual entity. The trace virtual entity is: the virtual entity of the intelligent device that causes the second target warning feature of the intelligent device; wherein, the second target warning feature is: communication interruption.

[0134] When there is no warning information in the intelligent device corresponding to the virtual entity, and the current operation feature of the virtual entity satisfies any standard operation feature, display the analysis result associated with the corresponding virtual entity.

[0135] Among them, the standard operation features include: the viewing duration of the virtual entity is greater than or equal to the preset viewing duration threshold and the virtual entity is clicked by the dashboard control pointer; the preset viewing duration threshold is set manually in advance, for example: 8 seconds.

[0136] The performing dynamic display according to the view trigger condition and the current operation information of the intelligent dashboard includes:

[0137] Obtain the view condition factor extraction template; wherein, the view condition factor extraction template is: a template for extracting view condition factors by comparison. The view condition factor is: a description vector of the view condition, for example: [communication interruption, view for 8 seconds,...].

[0138] Based on a preset determination rule for the factor extraction timing, determine whether the virtual entity meets the viewing condition factor extraction timing; among them, the preset determination rule for the factor extraction timing is set in advance manually, for example: the line-of-sight stay duration on the virtual entity is 3 seconds, or the pointer stays for 2 seconds;

[0139] If it is satisfied, use the corresponding virtual entity as the third target virtual entity;

[0140] According to the third target virtual entity, the current operation information, and the viewing condition factor extraction template, extract the first viewing condition factor; among them, the first viewing condition factor is: the viewing condition description vector for the intelligent dashboard viewer to view the third target virtual entity;

[0141] According to the viewing trigger condition configuration information of the third target virtual entity and the viewing condition factor extraction template, extract the second viewing condition factor; the second viewing condition factor is: the viewing condition description vector extracted from the viewing trigger condition of the third target virtual entity with reference to the viewing condition factor extraction template;

[0142] Calculate the factor matching degree between the first viewing condition factor and the second viewing condition factor. If the factor matching degree is greater than or equal to the preset factor matching degree threshold, determine the display content according to the viewing trigger condition of the corresponding third target virtual entity. Among them, the factor matching degree is: the cosine value of the vectors of the first viewing condition factor and the second viewing condition factor; the preset factor matching degree threshold is set in advance manually, for example: 0.85.

[0143] The working principle and beneficial effects of the above technical solution are as follows:

[0144] The present invention introduces a preset virtual entity network construction template to visualize intelligent devices, obtains a virtual entity network, associates the analysis results and the virtual entities in the virtual entity network, and configures the viewing trigger conditions for the analysis results associated with the virtual entities;

[0145] When configuring the viewing trigger conditions, when the virtual entity meets the first target warning feature and the dashboard viewer wants to view the corresponding device information, display the analysis results of the device and the devices it affects to the dashboard viewer. In this way, the influence range of the first target warning feature can be intuitively known, which is convenient for subsequent maintenance; when the virtual entity meets the second target warning feature and the dashboard viewer wants to view the corresponding device information, display the analysis results of the device and the analysis results of the causes of the device failure to the dashboard viewer. In this way, it can help the dashboard viewer quickly locate the fault source and improve the fault handling efficiency. When there is no warning information for the intelligent device corresponding to the virtual entity and the dashboard viewer wants to view the corresponding device information, it is a routine inspection, and only display the analysis results associated with the corresponding virtual entity;

[0146] Next, obtain the current operation information of the intelligent dashboard in real time, introduce a template for extracting viewing condition factors and a determination rule for the timing of factor extraction, extract the first viewing condition factors of the third target virtual entity that the dashboard viewer may be interested in at an appropriate time, and perform factor matching with the second viewing condition factors of the third target virtual entity. Based on the real-time matching results, present the corresponding trigger content that meets the viewing trigger conditions, which is more intelligent and intuitive.

[0147] In one embodiment, for dynamic display according to the viewing trigger conditions and the current operation information of the intelligent dashboard, it further includes:

[0148] Obtain the operation gesture of the dashboard viewer when viewing the analysis result text box; the operation gesture is a hand movement, such as grasping or pinching;

[0149] If the acquisition is successful, perform gesture matching between the operation gesture and the preset information grasping operation gesture; the preset information grasping operation gesture is preset manually, such as grasping;

[0150] If the gesture matching is successful, generate a pre-export reminder for the result data in the corresponding analysis result text box based on the preset pre-export reminder rule; the preset pre-export reminder rule is: pop up a notification box "Do you want to export the analysis result you are viewing?", and the notification box also includes "Yes" and "No" option buttons;

[0151] Obtain the confirmation operation of the pre-export reminder, and the confirmation operation includes: confirm export and export withdrawal;

[0152] If the confirmation operation is to confirm export, store the corresponding result data in the export form; the export form is a data table used to temporarily store the system data that the user wants to export;

[0153] If the confirmation operation is export withdrawal, obtain the previous gesture operation within a preset time period before the dashboard viewer makes the operation gesture; the preset time period is set manually in advance, such as 5 minutes;

[0154] Extract the target features of the historical previous gesture operation, and the target features include: different gesture actions, the sequence relationship and time interval between different gesture actions;

[0155] Perform clustering of the previous gesture operations according to the target features; when clustering, cluster the previous gesture operations with a target feature similarity greater than the similarity threshold;

[0156] If the clustering result meets the clustering conditions, the corresponding previous gesture operations are used as the pre-determined action set of the operation gesture; the clustering conditions are: the number of clustering targets of the previous gesture operations in the clustering result is greater than the first threshold, and the number of actions of the previous gesture operations in the clustering result is greater than the second threshold; both the first threshold and the second threshold are set in advance by humans. The number of clustering targets is the number of previous gesture operations in the same clustering result; the number of actions is the number of gestures in the previous gesture operations.

[0157] Obtain the confirmed export form for the export form; the confirmed export form is a data table containing all analysis result data finally determined by the user after viewing all virtual entities they want to view.

[0158] According to the analysis entity and the analysis entity knowledge graph of the result data of the confirmed export form, extract the graph features; the analysis entity is the actual physical device corresponding to the result data, and the analysis entity knowledge graph is the knowledge graph of the actual physical device; the graph features are the entities (actual physical devices) and entity relationships (the association relationships between actual physical devices, such as the mutual influence of different connection methods) in the analysis entity knowledge graph.

[0159] Train the knowledge model corresponding to the analysis entity according to the graph characteristics; the knowledge model is an AI model that stores relevant knowledge of the analysis entity (such as the failure principles of different failure types).

[0160] Input the result data in the confirmed export form into the knowledge model, obtain the analysis result output by the knowledge model, and display the analysis result to the dashboard viewer.

[0161] Perform dynamic display according to the view trigger condition and the current operation information of the intelligent dashboard, and also include:

[0162] After the pre-determined action set of the operation gesture is recorded, before the corresponding operation gesture has a successful gesture match and generates a pre-export reminder in the future, conduct a necessity analysis of the pre-export reminder according to the pre-determined action set of the corresponding operation gesture. If necessary, give a pre-export reminder; otherwise, do not remind. When conducting the necessity analysis of the pre-export reminder, when the action matching degree between the future previous gesture set corresponding to the action duration of the future corresponding operation gesture and the pre-determined action set is greater than or equal to the preset action matching degree threshold, it is unnecessary; otherwise, it is necessary. The preset action matching degree threshold is set by humans.

[0163] The working principle and beneficial effects of the above technical solution are:

[0164] When the kanban viewer views the analysis results of virtual entities based on the intelligent kanban, there is a situation: when wanting to export the analysis result data that is being viewed immediately, and manual export requires selecting the data one by one and then exporting, which is very inconvenient. The present invention matches the operation gestures of the kanban viewer when viewing the analysis result text box with the preset information capture operation gestures. When the gesture matching is successful, a pre-export reminder is generated for the kanban viewer to prevent accidental export; then, the confirmation operation of the pre-export reminder is obtained to determine whether to store the corresponding result data in the export form. If confirmed, since the user may want to export multiple analysis result data at one time for comparison and viewing, a temporary form is established for temporary storage of the result data; if the export is withdrawn, there is a situation where the information capture operation gesture is accidentally triggered. The previous gesture operations within a preset time period before the kanban viewer makes the operation gesture are obtained, the target features of the historical previous gesture operations are extracted and clustered, and the previous gesture operations are clustered according to the target features; a first threshold and a second threshold are introduced to limit the clustering conditions: the number of clustering targets of the previous gesture operations in the clustering result is greater than the first threshold to ensure that the number of occurrences of the previous gesture operations in the same situation (recognizing capture and then withdrawal) in history is sufficient; the number of actions of the previous gesture operations in the clustering result is greater than the second threshold to ensure the accuracy of the subsequent pre-judgment of the pre-determined action set; when the clustering result meets the clustering conditions, it is used as the pre-determined action set of the operation gesture; when the kanban viewing user determines that all the required data is pre-exported to the export form, the real-time export form is exported as the confirmed export form; the graph features are extracted according to the analysis entity knowledge graph corresponding to the analysis form, and an AI model for storing relevant knowledge of the analysis entity is trained according to the graph characteristics. The result data in the confirmed export form is input into the knowledge model, and the knowledge model can output analysis results according to the needs of the kanban viewer, which is more user-friendly. In addition, after the pre-determined action set of the operation gesture is recorded, before the corresponding operation gesture has a successful gesture match and generates a pre-export reminder in the future, the necessity of the pre-export reminder is analyzed according to the pre-determined action set of the corresponding operation gesture, reducing the number of false reminders and improving the user's system usage experience.

[0165] The embodiment of the present invention provides an intelligent device management method based on the Internet of Things and big data analysis, as Figure 2 shown, including:

[0166] Step 1: Based on the Internet of Things technology, access multiple intelligent devices that need to be managed, and obtain the device data of the intelligent devices; the device data includes: working status, operating parameters, and maintenance information;

[0167] Step 2: Analyze the device data based on big data analysis technology to generate analysis results; the analysis results include: fault warning, energy efficiency report, and operation trend;

[0168] Step 3: Dynamically display the device data and analysis results based on the intelligent dashboard.

[0169] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. Intelligent device management cloud platform based on Internet of Things and big data analysis, characterized by: include: The device data acquisition subsystem is used to access multiple smart devices that need to be managed based on the Internet of Things technology and obtain the device data of the smart devices; the device data includes: working status, operating parameters and maintenance information; Big data analysis subsystem, used to analyze equipment data based on big data analysis technology and generate analysis results; the analysis results include: fault warning, energy efficiency report and operation trend; The dynamic display subsystem is used to dynamically display equipment data and analysis results based on the smart dashboard.

2. The intelligent device management cloud platform based on the Internet of Things and big data analysis as claimed in claim 1, characterized in that: The device data acquisition subsystem is based on the Internet of Things technology and is connected to multiple smart devices that need to be managed, including: Get the API call request of the required access device; Get the parsing information of the open API for the API call request; Perform corresponding processing according to the parsed information and generate response data; Send the response data back through the open API.

3. The intelligent device management cloud platform based on the Internet of Things and big data analysis as claimed in claim 1, characterized in that: The big data analysis subsystem analyzes device data based on big data analysis technology and generates analysis results, including: Get the data tag of the device data; Connect to the big data platform and obtain analytical big data corresponding to data tags in the big data platform; According to the analysis of big data, the deep learning model is trained to obtain the analysis model of the analysis data type corresponding to the data label; Input the device data into the analysis model of the analysis data type corresponding to the data tag according to the corresponding data tag to obtain the analysis result.

4. The intelligent device management cloud platform based on the Internet of Things and big data analysis as claimed in claim 3, characterized in that: The big data analysis subsystem connects to the big data platform to obtain analytical big data corresponding to data tags in the big data platform, including: Get the page tags of the big data platform; Input page tags, data tags, and tag relevance query statements into the big language model to obtain tag relevance; If the tag association degree is greater than or equal to a preset tag association degree threshold, obtain the page content of the subordinate pages of the page tag; Predict the visitor's intention to access the page content; If the access intention is to query the analysis process of the target device data corresponding to the data tag, obtain the historical page browsing information of the access user with the corresponding access intention; Locate and analyze big data based on historical page browsing information.

5. The intelligent device management cloud platform based on the Internet of Things and big data analysis as claimed in claim 4, characterized in that: The big data analysis subsystem locates and analyzes big data based on historical page browsing information, including: Determine a preset page browsing progress mark according to historical page browsing information, and calculate a moving speed of the page browsing progress mark; If the moving speed is less than the average moving speed within the preset time period, locate the first browsing page; Determine the horizontal line where the virtual pointer of the first browsing page is located; Parse the first sight line information of the first browsing page to obtain sight line point trajectories on both sides of the horizontal line; According to the gaze point trajectory, try to obtain the scanning features; If the acquisition attempt is successful, a partial browsing page in the first browsing page is determined according to the scanning point trajectory and used as the second browsing page; If the acquisition attempt fails, determining a first viewing area above the horizontal line in the first browsing page and a second viewing area below the horizontal line in the first browsing page according to the sight point trajectory; Compare the sight point density of the first viewing area and the second viewing area, and determine the first viewing area or the second viewing area with a larger sight point density as the third browsing page; taking the second browsing page or the third browsing page as the fourth browsing page, performing text recognition on the fourth browsing page, and determining a text recognition result; If the sight lingering time of the recognized character corresponding to the text recognition result is greater than or equal to the preset time threshold, the corresponding text recognition result will be used as big data for analysis.

6. The intelligent device management cloud platform based on the Internet of Things and big data analysis as claimed in claim 1, characterized in that: The dynamic display subsystem dynamically displays equipment data and analysis results based on the smart dashboard, including: Build a virtual entity network based on device data and a preset virtual entity network building template; Associating the virtual entity with the analysis result according to the corresponding relationship between the analysis result and the virtual entity in the virtual entity network; Configure the trigger conditions for viewing the analysis results associated with the virtual entity; Get the current operation information of the smart dashboard; Dynamic display is performed based on the viewing trigger conditions and the current operation information of the smart dashboard.

7. The intelligent device management cloud platform based on the Internet of Things and big data analysis as claimed in claim 6, characterized in that: The trigger conditions for viewing the analysis results associated with the dynamic display subsystem configuration virtual entity include: When the warning feature of the smart device corresponding to the virtual entity meets the first target warning feature, and the current operation feature of the virtual entity meets any standard operation feature, the analysis result associated with the first target virtual entity is displayed, and the first target virtual entity is: the virtual entity that affects access to the cloud platform determined according to the first target warning feature; When the warning feature of the smart device corresponding to the virtual entity meets the second target warning feature, and the current operation feature of the virtual entity meets any standard operation feature, the analysis result associated with the second target virtual entity is displayed, and the second target virtual entity is: the virtual entity and the tracing virtual entity, and the tracing virtual entity is: the virtual entity of the smart device that causes the smart device to generate the second target warning feature; When there is no warning information for the smart device corresponding to the virtual entity, and the current operation feature of the virtual entity meets any standard operation feature, the analysis result associated with the corresponding virtual entity is displayed; Among them, the standard operation features include: the viewing time of the virtual entity is greater than or equal to a preset viewing time threshold and the virtual entity is clicked by the board control pointer.

8. The intelligent device management cloud platform based on the Internet of Things and big data analysis as claimed in claim 6, characterized in that: The dynamic display subsystem obtains the current operation information of the smart dashboard, including: Get the second sight information of the smart signboard; Get the pointer operation of the Kanban control pointer; The second sight line information and the pointer operation are used together as current operation information.

9. The intelligent device management cloud platform based on the Internet of Things and big data analysis as claimed in claim 6, characterized in that: The dynamic display subsystem performs dynamic display based on the viewing trigger conditions and the current operation information of the smart dashboard, including: Get the template for extracting conditional factors; Based on the preset factor extraction timing determination rule, determine whether the virtual entity meets the viewing condition factor extraction timing; If satisfied, the corresponding virtual entity is used as the third target virtual entity; Extracting a template according to the third target virtual entity, current operation information and viewing condition factor, extracting a first viewing condition factor; Extracting a second viewing condition factor according to the viewing trigger condition configuration information of the third target virtual entity and the viewing condition factor extraction template; The factor matching degree of the first viewing condition factor and the second viewing condition factor is calculated, and if the factor matching degree is greater than or equal to a preset factor matching degree threshold, the display content is determined according to the viewing trigger condition of the corresponding third target virtual entity.

10. An intelligent device management method based on the Internet of Things and big data analysis, characterized in that: include: Step 1: Based on the Internet of Things technology, connect multiple smart devices that need to be managed and obtain the device data of the smart devices; Equipment data includes: working status, operating parameters and maintenance information; Step 2: Analyze the equipment data based on big data analysis technology to generate analysis results; the analysis results include: fault warning, energy efficiency report and operation trend; Step 3: Dynamically display device data and analysis results based on the smart dashboard.

Images