Temperature abnormity control method and system of electronic whiteboard all-in-one machine
By constructing the temperature prediction model and diagnostic model, the temperature threshold is dynamically adjusted, and the problem of the lack of flexibility and accuracy of the existing electronic whiteboard all -in -one temperature control method is to achieve more effective temperature control.
Patent Information
- Application Number
- CN202411483461.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-23
- Publication Date
- 2025-01-28
AI Technical Summary
The temperature control method of existing electronic whiteboard all-in-one machines relies on fixed thresholds, and cannot predict the temperature change trend in advance, resulting in overheating of the equipment or unnecessary power outage, and lacks precise control of temperature abnormalities in different areas.
By obtaining historical temperature and environmental data, build a model training data set, train temperature predictive models, collect data in real time for pre -processing and diagnosis, and dynamically adjust the temperature threshold to achieve an intelligent response with abnormal temperature.
The temperature prediction and dynamic threshold adjustment of the electronic whiteboard all -in -one machine improve the flexibility and accuracy of the temperature control, and avoid the phenomenon of overheating or unnecessary power off the equipment.
Smart Images
Figure CN119377847A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of whiteboard all-in-one machine control, and in particular relates to a temperature abnormality control method and system for an electronic whiteboard all-in-one machine. Background Art
[0002] Existing electronic whiteboard all-in-one devices usually rely on simple temperature sensors and fixed threshold settings to monitor the internal temperature of the device. When the temperature exceeds a certain fixed threshold, the system will take corresponding measures such as reducing the brightness or powering off. However, this fixed threshold control method lacks flexibility, cannot predict the temperature change trend in advance, and cannot accurately control the temperature anomalies in different areas, which can easily lead to overheating of the device or unnecessary overall power outages. Summary of the invention
[0003] In order to solve the above problems existing in the prior art, the present invention provides a temperature abnormality control method and system of an electronic whiteboard integrated machine.
[0004] The purpose of the present invention can be achieved through the following technical solutions:
[0005] Acquire historical temperature data and historical environment data of the all-in-one whiteboard, add timestamps according to the historical temperature data and the historical environment data to obtain time series historical temperature data and time series historical environment data, construct a model training data set according to the time series historical temperature data and the time series historical environment data, acquire an initial prediction model, and perform model training on the initial prediction model according to the model training data set to obtain a temperature prediction model;
[0006] Collecting real-time temperature data and real-time environmental data of the whiteboard integrated machine through a temperature sensor group, adding timestamps according to the real-time temperature data and the real-time environmental data to obtain time series real-time temperature data and time series real-time environmental data, and constructing a real-time temperature data set and a time series real-time environmental data set according to the time series real-time temperature data and the time series real-time environmental data;
[0007] Obtaining an initial temperature threshold, calculating a normalized prediction data set through a preprocessing model according to the time series real-time temperature data set and the time series real-time environment data set, calculating a prediction duration according to the normalized prediction data set through a prediction diagnosis model, and adjusting the initial temperature threshold according to the prediction duration to obtain a secondary temperature threshold;
[0008] Obtain the partition temperature threshold, obtain the partition temperature and the current temperature through the temperature sensor group, calculate the abnormal diagnosis result through the diagnosis model according to the partition temperature, the current temperature, the partition temperature threshold, and the secondary temperature threshold, and the intelligent terminal performs an abnormal response according to the abnormal diagnosis result.
[0009] Specifically, the performing model training on the initial prediction model according to the model training data set to obtain the temperature prediction model includes:
[0010] S201: Divide the training data set into a prediction set and a test set according to the timestamp, and calculate a normalized data set according to the prediction set by using a maximum and minimum value normalization algorithm;
[0011] S202: Calculating initial predicted temperature data using the initial prediction model according to the normalized data set, and aggregating the initial predicted temperature data to obtain an initial predicted temperature set;
[0012] S203: Calculating an evaluation index according to the predicted temperature set and the test set, and performing hyperparameter correction on the initial prediction model according to the evaluation index to obtain the temperature prediction model.
[0013] Specifically, the specific calculation steps of the preprocessing model are:
[0014] S301: Calculating an average temperature set and an average environment set according to the time series real-time temperature data set and the time series real-time environment data set;
[0015] S302: splicing the average temperature set and the average environment data set according to the time series to obtain a prediction data set;
[0016] S303: Applying the maximum and minimum value normalization algorithm to the predicted data set to obtain the normalized predicted data set.
[0017] Specifically, the specific steps of S301 are:
[0018] S301-1: selecting first temperature data, second temperature data, and third temperature data according to the real-time temperature data set; the first temperature data, the second temperature data, and the third temperature data are three temperature data values that are continuous in time;
[0019] S301-2: selecting first environmental data, second environmental data, and third environmental data according to the time series real-time environmental data set; the first environmental data, the second environmental data, and the third environmental data are three temperature data values that are continuous in time;
[0020] S301-3: Calculate the average value of the first temperature data, the second temperature data, and the third temperature data to obtain average temperature data, and arrange and combine the average temperature data in chronological order to obtain the average temperature set;
[0021] S301 - 4 : Calculate the average value of the first environment data, the second environment data, and the third environment data to obtain average environment data, and arrange and combine the average environment data in chronological order to obtain the average environment data set.
[0022] Specifically, the predictive diagnosis model includes the temperature prediction model, and the specific calculation steps are:
[0023] S401: Preset a sliding window, intercept the normalized prediction data set according to the sliding window to obtain a prediction diversity, and calculate a first predicted temperature through the temperature prediction model according to the prediction diversity;
[0024] S402: judging the first predicted temperature, if the first predicted temperature is greater than the first initial temperature threshold, executing S403; if the first predicted temperature is less than the first initial temperature threshold, moving the sliding window by one point in a preset direction, and executing step S401;
[0025] S403: Calculate the predicted duration according to the normalized predicted data set length, the number of sliding window movements, and the time granularity.
[0026] Specifically, the initial temperature threshold is adjusted according to the predicted duration to obtain a secondary temperature threshold, specifically:
[0027] Obtain a comparison threshold and an adjustment threshold, compare the predicted duration with the comparison threshold, if the predicted duration is greater than the comparison threshold, the secondary temperature threshold is equal to the initial temperature threshold; if the predicted duration is less than the comparison threshold, the secondary temperature threshold is equal to the initial temperature threshold minus the adjustment threshold.
[0028] Specifically, the specific calculation steps of the diagnostic model are:
[0029] S501: judging the partition temperature according to the partition temperature threshold, and if the partition temperature is greater than the partition temperature threshold, outputting a third diagnosis result; if the partition temperature is less than the partition temperature threshold, executing step S502;
[0030] S502: judging the current temperature according to the third secondary temperature threshold, if the current temperature is greater than the third secondary temperature threshold, outputting a third diagnosis result; if the current temperature is less than the third secondary temperature threshold, executing step S503;
[0031] S503: judging the current temperature according to the second secondary temperature threshold, if the current temperature is greater than the second secondary temperature threshold, outputting a second diagnosis result; if the current temperature is less than the second secondary temperature threshold, executing step S504;
[0032] S504: judging the current temperature according to the first secondary temperature threshold, and outputting a first diagnostic result if the current temperature is greater than the first secondary temperature threshold; and not outputting a first diagnostic result if the current temperature is less than the first secondary temperature threshold.
[0033] Specifically, the temperature prediction model calculation steps are:
[0034] S601: Performing maximum and minimum value normalization processing on the prediction diversity to obtain a preprocessed prediction diversity;
[0035] S602: extracting features through a CNN unit according to the preprocessing prediction diversity to obtain feature data;
[0036] S603: Perform feature expansion through the GRU unit according to the feature data to obtain a spatiotemporal feature matrix;
[0037] S604: extracting a temporal relationship through Conv1D according to the spatiotemporal feature matrix, and calculating a weight matrix through a temporal attention mechanism according to the temporal relationship;
[0038] S605: Obtain the first predicted temperature by calculating through the output layer according to the spatiotemporal feature matrix and the weight matrix.
[0039] Specifically, constructing a model training data set based on the time series historical temperature data and the time series historical environmental data includes parallel splicing the time series historical temperature data and the time series historical environmental data according to the timestamp to obtain training data, and aggregating each of the training data to obtain the training data set.
[0040] Specifically, the temperature prediction model includes a CNN unit, a GRU unit, an ITA unit, and a fully connected layer. The CNN unit is composed of three CNN channels, the GRU unit is composed of two GRU networks, and the ITA unit is composed of Conv1D and a temporal attention mechanism.
[0041] Specifically, the historical environmental data includes historical outdoor temperature, historical indoor temperature, and historical humidity.
[0042] Specifically, the time granularity is one minute.
[0043] Specifically, the predicted duration includes a first predicted duration, a second predicted duration, and a third predicted duration.
[0044] Specifically, the abnormal diagnosis result includes a first diagnosis result, a second diagnosis result, and a third diagnosis result.
[0045] Specifically, the secondary temperature threshold includes a first secondary temperature threshold, a second secondary temperature threshold, and a third secondary temperature threshold.
[0046] Specifically, the initial temperature threshold includes a first initial temperature threshold, a second initial temperature threshold, and a third initial temperature threshold.
[0047] Specifically, the evaluation indicators include mean square error, mean absolute error, and determination coefficient.
[0048] A temperature abnormality control system for an electronic whiteboard integrated machine, comprising: a model training module, a data acquisition module, a data processing module, and a response module;
[0049] The model training module is used to obtain historical temperature data and historical environmental data of the whiteboard integrated machine, add timestamps according to the historical temperature data and the historical environmental data to obtain time-series historical temperature data and time-series historical environmental data, construct a model training data set according to the time-series historical temperature data and the time-series historical environmental data, obtain an initial prediction model, and perform model training on the initial prediction model according to the model training data set to obtain a temperature prediction model;
[0050] The data acquisition module is used to collect real-time temperature data and real-time environmental data of the whiteboard integrated machine through a temperature sensor group, add timestamps according to the real-time temperature data and the real-time environmental data to obtain time-series real-time temperature data and time-series real-time environmental data, and construct a real-time temperature data set and a time-series real-time environmental data set according to the time-series real-time temperature data and the time-series real-time environmental data;
[0051] The data processing module is used to obtain an initial temperature threshold, calculate a normalized prediction data set through a preprocessing model according to the time series real-time temperature data set and the time series real-time environment data set, calculate a prediction duration according to the normalized prediction data set through a prediction diagnosis model, and adjust the initial temperature threshold according to the prediction duration to obtain a secondary temperature threshold;
[0052] The response module is used to obtain the partition temperature threshold, obtain the partition temperature and the current temperature through the temperature sensor group, and obtain the abnormal diagnosis result through the diagnosis model calculation based on the partition temperature, the current temperature, the partition temperature threshold, and the secondary temperature threshold. The smart terminal performs an abnormal response based on the abnormal diagnosis result.
[0053] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the temperature abnormality control method of the electronic whiteboard integrated machine as described above when executing the program.
[0054] A storage medium containing computer executable instructions, wherein the computer executable instructions, when executed by a computer processor, are used to implement the temperature abnormality control method of the electronic whiteboard integrated machine as described above when executing the program.
[0055] The beneficial effects of the present invention are:
[0056] (1) By setting up a temperature prediction model, the temperature prediction result is calculated through the temperature prediction model according to the real-time collected data, thereby realizing the temperature prediction of the electronic whiteboard all-in-one machine.
[0057] (2) By calculating the predicted duration according to the predicted temperature value and dynamically adjusting the temperature threshold according to the predicted duration, the dynamic adjustment of the temperature threshold is achieved, which solves the inflexibility of the fixed threshold control method. BRIEF DESCRIPTION OF THE DRAWINGS
[0058] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.
[0059] Figure 1 The present invention is a flow chart of a method for controlling abnormal temperature of an electronic whiteboard integrated machine. DETAILED DESCRIPTION
[0060] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.
[0061] See also Figure 1 , a temperature abnormality control method for an electronic whiteboard integrated machine;
[0062] Acquire historical temperature data and historical environment data of the all-in-one whiteboard, add timestamps according to the historical temperature data and the historical environment data to obtain time series historical temperature data and time series historical environment data, construct a model training data set according to the time series historical temperature data and the time series historical environment data, acquire an initial prediction model, and perform model training on the initial prediction model according to the model training data set to obtain a temperature prediction model;
[0063] Collecting real-time temperature data and real-time environmental data of the whiteboard integrated machine through a temperature sensor group, adding timestamps according to the real-time temperature data and the real-time environmental data to obtain time series real-time temperature data and time series real-time environmental data, and constructing a real-time temperature data set and a time series real-time environmental data set according to the time series real-time temperature data and the time series real-time environmental data;
[0064] Obtaining an initial temperature threshold, calculating a normalized prediction data set through a preprocessing model according to the time series real-time temperature data set and the time series real-time environment data set, calculating a prediction duration according to the normalized prediction data set through a prediction diagnosis model, and adjusting the initial temperature threshold according to the prediction duration to obtain a secondary temperature threshold;
[0065] Obtain the partition temperature threshold, obtain the partition temperature and the current temperature through the temperature sensor group, calculate the abnormal diagnosis result through the diagnosis model according to the partition temperature, the current temperature, the partition temperature threshold, and the secondary temperature threshold, and the intelligent terminal performs an abnormal response according to the abnormal diagnosis result.
[0066] Specifically, constructing a model training data set based on the time series historical temperature data and the time series historical environmental data includes parallel splicing the time series historical temperature data and the time series historical environmental data according to the timestamp to obtain training data, and aggregating each of the training data to obtain the training data set.
[0067] The time series prediction temperature set is a set of temperatures in which the time series prediction temperatures are arranged in chronological order; the time granularity is one minute; the historical environmental data includes historical outdoor temperature, historical indoor temperature, and historical humidity; the prediction duration includes a first prediction duration, a second prediction duration, and a third prediction duration; the secondary temperature threshold includes a first secondary temperature threshold, a second secondary temperature threshold, and a third secondary temperature threshold; the initial temperature threshold includes a first initial temperature threshold, a second initial temperature threshold, and a third initial temperature threshold; the abnormal diagnosis result includes a first diagnosis result, a second diagnosis result, and a third diagnosis result.
[0068] The temperature prediction model includes a CNN unit, a GRU unit, an ITA unit, and a fully connected layer. The CNN unit is composed of three CNN channels, the GRU unit is composed of two GRU networks, and the ITA unit is composed of Conv1D and a temporal attention mechanism.
[0069] Specifically, performing model training on the initial prediction model according to the model training data set to obtain a temperature prediction model includes:
[0070] S201: Divide the training data set into a prediction set and a test set according to the timestamp, and calculate a normalized data set according to the prediction set by using a maximum and minimum value normalization algorithm;
[0071] S202: Calculating initial predicted temperature data using the initial prediction model according to the normalized data set, and aggregating the initial predicted temperature data to obtain an initial predicted temperature set;
[0072] S203: Calculate evaluation indicators according to the predicted temperature set and the test set, and perform hyperparameter correction on the initial prediction model according to the evaluation indicators to obtain the temperature prediction model, wherein the evaluation indicators include mean square error, mean absolute error, and determination coefficient.
[0073] Specifically, the specific calculation steps of the preprocessing model are:
[0074] S301: Calculating an average temperature set and an average environment set according to the time series real-time temperature data set and the time series real-time environment data set;
[0075] S302: splicing the average temperature set and the average environment data set according to the time series to obtain a prediction data set;
[0076] S303: Applying the maximum and minimum value normalization algorithm to the predicted data set to obtain the normalized predicted data set.
[0077] Specifically, the specific steps of S301 are:
[0078] S301-1: selecting first temperature data, second temperature data, and third temperature data according to the real-time temperature data set; the first temperature data, the second temperature data, and the third temperature data are three temperature data values that are continuous in time;
[0079] S301-2: selecting first environmental data, second environmental data, and third environmental data according to the time series real-time environmental data set; the first environmental data, the second environmental data, and the third environmental data are three temperature data values that are continuous in time;
[0080] S301-3: Calculate the average value of the first temperature data, the second temperature data, and the third temperature data to obtain average temperature data, and arrange and combine the average temperature data in chronological order to obtain the average temperature set;
[0081] S301 - 4 : Calculate the average value of the first environment data, the second environment data, and the third environment data to obtain average environment data, and arrange and combine the average environment data in chronological order to obtain the average environment data set.
[0082] Specifically, the predictive diagnosis model includes the temperature prediction model, and the specific calculation steps are:
[0083] S401: Preset a sliding window, intercept the normalized prediction data set according to the sliding window to obtain a prediction diversity, and calculate a first predicted temperature through the temperature prediction model according to the prediction diversity;
[0084] S402: judging the first predicted temperature, if the first predicted temperature is greater than the first initial temperature threshold, executing S403; if the first predicted temperature is less than the first initial temperature threshold, moving the sliding window by one point in a preset direction, and executing step S401;
[0085] S403: Calculate the predicted duration according to the normalized predicted data set length, the number of sliding window movement times, and the time granularity; the predicted duration calculation formula is:
[0086] Y=A(L+S+1),
[0087] Among them, Y is the prediction duration, L is the normalized prediction data set length, A is the time granularity, and S is the number of sliding window moves.
[0088] Specifically, the initial temperature threshold is adjusted according to the predicted duration to obtain a secondary temperature threshold, specifically:
[0089] Obtain a comparison threshold and an adjustment threshold, compare the predicted duration with the comparison threshold, if the predicted duration is greater than the comparison threshold, the secondary temperature threshold is equal to the initial temperature threshold; if the predicted duration is less than the comparison threshold, the secondary temperature threshold is equal to the initial temperature threshold minus the adjustment threshold.
[0090] Specifically, the specific calculation steps of the diagnostic model are:
[0091] S501: judging the partition temperature according to the partition temperature threshold, and if the partition temperature is greater than the partition temperature threshold, outputting a third diagnosis result; if the partition temperature is less than the partition temperature threshold, executing step S502;
[0092] S502: judging the current temperature according to the third secondary temperature threshold, if the current temperature is greater than the third secondary temperature threshold, outputting a third diagnosis result; if the current temperature is less than the third secondary temperature threshold, executing step S503;
[0093] S503: judging the current temperature according to the second secondary temperature threshold, if the current temperature is greater than the second secondary temperature threshold, outputting a second diagnosis result; if the current temperature is less than the second secondary temperature threshold, executing step S504;
[0094] S504: judging the current temperature according to the first secondary temperature threshold, and outputting a first diagnostic result if the current temperature is greater than the first secondary temperature threshold; and not outputting a first diagnostic result if the current temperature is less than the first secondary temperature threshold.
[0095] The temperature prediction model calculation steps are:
[0096] S601: Performing maximum and minimum value normalization processing on the prediction diversity to obtain a preprocessed prediction diversity;
[0097] S602: extracting features through a CNN unit according to the preprocessing prediction diversity to obtain feature data;
[0098] S603: Perform feature expansion through the GRU unit according to the feature data to obtain a spatiotemporal feature matrix;
[0099] S604: extracting a temporal relationship through Conv1D according to the spatiotemporal feature matrix, and calculating a weight matrix through a temporal attention mechanism according to the temporal relationship;
[0100] S605: Calculate the first predicted temperature through the output layer according to the spatiotemporal feature matrix and the weight matrix; the calculation formula of the first predicted temperature is:
[0101] Y=A(wh+b),
[0102] Among them, Y is the first predicted temperature, w is the weight matrix, h is the spatiotemporal feature matrix, and b is the bias.
[0103] A temperature abnormality control system for an electronic whiteboard integrated machine, comprising: a model training module, a data acquisition module, a data processing module, and a response module;
[0104] The model training module is used to obtain historical temperature data and historical environmental data of the whiteboard integrated machine, add timestamps according to the historical temperature data and the historical environmental data to obtain time-series historical temperature data and time-series historical environmental data, construct a model training data set according to the time-series historical temperature data and the time-series historical environmental data, obtain an initial prediction model, and perform model training on the initial prediction model according to the model training data set to obtain a temperature prediction model;
[0105] The data acquisition module is used to collect real-time temperature data and real-time environmental data of the whiteboard integrated machine through a temperature sensor group, add timestamps according to the real-time temperature data and the real-time environmental data to obtain time-series real-time temperature data and time-series real-time environmental data, and construct a real-time temperature data set and a time-series real-time environmental data set according to the time-series real-time temperature data and the time-series real-time environmental data;
[0106] The data processing module is used to obtain an initial temperature threshold, calculate a normalized prediction data set through a preprocessing model according to the time series real-time temperature data set and the time series real-time environment data set, calculate a prediction duration according to the normalized prediction data set through a prediction diagnosis model, and adjust the initial temperature threshold according to the prediction duration to obtain a secondary temperature threshold;
[0107] The response module is used to obtain the partition temperature threshold, obtain the partition temperature and the current temperature through the temperature sensor group, and obtain the abnormal diagnosis result through the diagnosis model calculation based on the partition temperature, the current temperature, the partition temperature threshold, and the secondary temperature threshold. The smart terminal performs an abnormal response based on the abnormal diagnosis result.
[0108] In this embodiment, the abnormal response includes a first-level response, a second-level response, and a third-level response. The first-level response is that the system displays a temperature abnormality warning message to the user, informs the user of the current temperature abnormality through a screen pop-up window or a sound prompt, and the system reduces the brightness of the display according to the actual situation, and reduces the power consumption of the display to reduce the internal temperature by adjusting the LED lamp drive signal; the second-level response is that the system generates a severe temperature abnormality notification, and reminds the user to take immediate measures through a pop-up window in the center of the screen. The system will reduce the brightness of the display again to further reduce the temperature rise; the third-level response is that the system will trigger a forced power-off mechanism, the system will safely save all current processes, and turn off all output devices. Disconnect the main power supply to ensure that the device stops running to prevent hardware damage. Before forced power off, the system will issue a final high temperature warning notification and record the current temperature data and system status information.
[0109] It should be noted that there is a one-to-one correspondence between abnormal diagnostic results and abnormal responses. When the diagnostic model outputs the first abnormal result, the system makes a first-level response; when the diagnostic model outputs the second abnormal result, the system makes a second-level response; when the diagnostic model outputs the third abnormal result, the system makes a third-level response.
[0110] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the temperature abnormality control method of the electronic whiteboard integrated machine as described above when executing the program.
[0111] A storage medium containing computer executable instructions, wherein the computer executable instructions, when executed by a computer processor, are used to implement the temperature abnormality control method of the electronic whiteboard integrated machine as described above when executing the program.
[0112] The working principle and use process of the present invention:
[0113] The computer storage medium of the embodiment of the present invention may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.
[0114] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.
[0115] The program code included on the computer readable medium can be transmitted with any appropriate medium, including but not limited to wireless, electric wire, optical cable, RF, etc., or any suitable combination of the above. The computer program code for performing the operation of the present invention can be written in one or more programming languages or their combinations, and the programming language includes object-oriented programming languages-such as Java, Smalltalk, C++, and also includes conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).
[0116] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still fall within the scope of the technical solution of the present invention.
Claims
1. A method for controlling temperature abnormality of an electronic whiteboard integrated machine, characterized in that: include: Acquire historical temperature data and historical environment data of the all-in-one whiteboard, add timestamps according to the historical temperature data and the historical environment data to obtain time series historical temperature data and time series historical environment data, construct a model training data set according to the time series historical temperature data and the time series historical environment data, acquire an initial prediction model, and perform model training on the initial prediction model according to the model training data set to obtain a temperature prediction model; Collecting real-time temperature data and real-time environmental data of the whiteboard integrated machine through a temperature sensor group, adding timestamps according to the real-time temperature data and the real-time environmental data to obtain time series real-time temperature data and time series real-time environmental data, and constructing a real-time temperature data set and a time series real-time environmental data set according to the time series real-time temperature data and the time series real-time environmental data; Obtaining an initial temperature threshold, calculating a normalized prediction data set through a preprocessing model according to the time series real-time temperature data set and the time series real-time environment data set, calculating a prediction duration according to the normalized prediction data set through a prediction diagnosis model, and adjusting the initial temperature threshold according to the prediction duration to obtain a secondary temperature threshold; Obtain the partition temperature threshold, obtain the partition temperature and the current temperature through the temperature sensor group, calculate the abnormal diagnosis result through the diagnosis model according to the partition temperature, the current temperature, the partition temperature threshold, and the secondary temperature threshold, and the intelligent terminal performs an abnormal response according to the abnormal diagnosis result.
2. The temperature abnormality control method of the electronic whiteboard integrated machine according to claim 1, characterized in that: The performing model training on the initial prediction model according to the model training data set to obtain a temperature prediction model comprises: S201: Divide the training data set into a prediction set and a test set according to the timestamp, and calculate a normalized data set according to the prediction set by using a maximum and minimum value normalization algorithm; S202: Calculating initial predicted temperature data using the initial prediction model according to the normalized data set, and aggregating the initial predicted temperature data to obtain an initial predicted temperature set; S203: Calculating an evaluation index according to the predicted temperature set and the test set, and performing hyperparameter correction on the initial prediction model according to the evaluation index to obtain the temperature prediction model.
3. The temperature abnormality control method of the electronic whiteboard integrated machine according to claim 1, characterized in that: The specific calculation steps of the preprocessing model are: S301: Calculating an average temperature set and an average environment set according to the time series real-time temperature data set and the time series real-time environment data set; S302: splicing the average temperature set and the average environment data set according to the time series to obtain a prediction data set; S303: Applying the maximum and minimum value normalization algorithm to the predicted data set to obtain the normalized predicted data set.
4. The temperature abnormality control method of the electronic whiteboard integrated machine according to claim 3, characterized in that: The specific steps of S301 are: S301-1: selecting first temperature data, second temperature data, and third temperature data according to the real-time temperature data set; the first temperature data, the second temperature data, and the third temperature data are three temperature data values that are continuous in time; S301-2: selecting first environmental data, second environmental data, and third environmental data according to the time series real-time environmental data set; the first environmental data, the second environmental data, and the third environmental data are three temperature data values that are continuous in time; S301-3: Calculate the average value of the first temperature data, the second temperature data, and the third temperature data to obtain average temperature data, and arrange and combine the average temperature data in chronological order to obtain the average temperature set; S301 - 4 : Calculate the average value of the first environment data, the second environment data, and the third environment data to obtain average environment data, and arrange and combine the average environment data in chronological order to obtain the average environment data set.
5. The temperature abnormality control method of the electronic whiteboard integrated machine according to claim 1, characterized in that: The predictive diagnosis model includes the temperature prediction model, and the specific calculation steps are: S401: Preset a sliding window, intercept the normalized prediction data set according to the sliding window to obtain a prediction diversity, and calculate a first predicted temperature through the temperature prediction model according to the prediction diversity; S402: judging the first predicted temperature, if the first predicted temperature is greater than the first initial temperature threshold, executing S403; if the first predicted temperature is less than the first initial temperature threshold, moving the sliding window by one point in a preset direction, and executing step S401; S403: Calculate the predicted duration according to the normalized predicted data set length, the number of sliding window movements, and the time granularity.
6. The temperature abnormality control method of the electronic whiteboard integrated machine according to claim 1, characterized in that: The secondary temperature threshold is obtained by adjusting the initial temperature threshold according to the predicted duration, specifically: Obtain a comparison threshold and an adjustment threshold, compare the predicted duration with the comparison threshold, if the predicted duration is greater than the comparison threshold, the secondary temperature threshold is equal to the initial temperature threshold; if the predicted duration is less than the comparison threshold, the secondary temperature threshold is equal to the initial temperature threshold minus the adjustment threshold.
7. The temperature abnormality control method of the electronic whiteboard integrated machine according to claim 1, characterized in that: The specific calculation steps of the diagnostic model are: S501: judging the partition temperature according to the partition temperature threshold, and if the partition temperature is greater than the partition temperature threshold, outputting a third diagnosis result; if the partition temperature is less than the partition temperature threshold, executing step S502; S502: judging the current temperature according to the third secondary temperature threshold, if the current temperature is greater than the third secondary temperature threshold, outputting a third diagnosis result; if the current temperature is less than the third secondary temperature threshold, executing step S503; S503: judging the current temperature according to the second secondary temperature threshold, if the current temperature is greater than the second secondary temperature threshold, outputting a second diagnosis result; if the current temperature is less than the second secondary temperature threshold, executing step S504; S504: judging the current temperature according to the first secondary temperature threshold, and outputting a first diagnostic result if the current temperature is greater than the first secondary temperature threshold; and not outputting a first diagnostic result if the current temperature is less than the first secondary temperature threshold.
8. The temperature abnormality control method of the electronic whiteboard integrated machine according to claim 5, characterized in that: The temperature prediction model calculation steps are: S601: Performing maximum and minimum value normalization processing on the prediction diversity to obtain a preprocessed prediction diversity; S602: extracting features through a CNN unit according to the preprocessing prediction diversity to obtain feature data; S603: Perform feature expansion through the GRU unit according to the feature data to obtain a spatiotemporal feature matrix; S604: extracting a temporal relationship through Conv1D according to the spatiotemporal feature matrix, and calculating a weight matrix through a temporal attention mechanism according to the temporal relationship; S605: Obtain the first predicted temperature by calculating through the output layer according to the spatiotemporal feature matrix and the weight matrix.
9. The temperature abnormality control method of the electronic whiteboard integrated machine according to claim 1, characterized in that: Constructing a model training data set according to the time series historical temperature data and the time series historical environmental data includes parallel splicing the time series historical temperature data and the time series historical environmental data according to the timestamp to obtain training data, and aggregating each of the training data to obtain the training data set.
10. The temperature abnormality control method of the electronic whiteboard integrated machine according to claim 1, characterized in that: The temperature prediction model includes a CNN unit, a GRU unit, an ITA unit, and a fully connected layer. The CNN unit is composed of three CNN channels, the GRU unit is composed of two GRU networks, and the ITA unit is composed of Conv1D and a temporal attention mechanism.
11. The temperature abnormality control method of the electronic whiteboard integrated machine according to claim 1, characterized in that: The historical environmental data includes historical outdoor temperature, historical indoor temperature, and historical humidity.
12. The temperature abnormality control method of the electronic whiteboard integrated machine according to claim 1, characterized in that: The time granularity is one minute.
13. The temperature abnormality control method of the electronic whiteboard integrated machine according to claim 1, characterized in that: The predicted duration includes a first predicted duration, a second predicted duration, and a third predicted duration.
14. The temperature abnormality control method of the electronic whiteboard integrated machine according to claim 1, characterized in that: The abnormal diagnosis result includes a first diagnosis result, a second diagnosis result, and a third diagnosis result.
15. The temperature abnormality control method of the electronic whiteboard integrated machine according to claim 1, characterized in that: The secondary temperature thresholds include a first secondary temperature threshold, a second secondary temperature threshold, and a third secondary temperature threshold.
16. The temperature abnormality control method of the electronic whiteboard integrated machine according to claim 1, characterized in that: The initial temperature threshold includes a first initial temperature threshold, a second initial temperature threshold, and a third initial temperature threshold.
17. The temperature abnormality control method of the electronic whiteboard integrated machine according to claim 2, characterized in that: The evaluation indicators include mean square error, mean absolute error, and determination coefficient.
18. A temperature abnormality control system for an electronic whiteboard integrated machine, characterized in that: include: Model training module, data acquisition module, data processing module, response module; The model training module is used to obtain historical temperature data and historical environmental data of the whiteboard integrated machine, add timestamps according to the historical temperature data and the historical environmental data to obtain time series historical temperature data and time series historical environmental data, construct a model training data set according to the time series historical temperature data and the time series historical environmental data, obtain an initial prediction model, and perform model training on the initial prediction model according to the model training data set to obtain a temperature prediction model; The data acquisition module is used to collect real-time temperature data and real-time environmental data of the whiteboard integrated machine through a temperature sensor group, add timestamps according to the real-time temperature data and the real-time environmental data to obtain time-series real-time temperature data and time-series real-time environmental data, and construct a real-time temperature data set and a time-series real-time environmental data set according to the time-series real-time temperature data and the time-series real-time environmental data; The data processing module is used to obtain an initial temperature threshold, calculate a normalized prediction data set through a preprocessing model according to the time series real-time temperature data set and the time series real-time environment data set, calculate a prediction duration according to the normalized prediction data set through a prediction diagnosis model, and adjust the initial temperature threshold according to the prediction duration to obtain a secondary temperature threshold; The response module is used to obtain the partition temperature threshold, obtain the partition temperature and the current temperature through the temperature sensor group, and obtain the abnormal diagnosis result through the diagnosis model calculation based on the partition temperature, the current temperature, the partition temperature threshold, and the secondary temperature threshold. The smart terminal performs an abnormal response based on the abnormal diagnosis result.
19. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the temperature abnormality control method of the electronic whiteboard integrated machine as described in any one of claims 1 to 17 is implemented.
20. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to execute the temperature abnormality control method of the electronic whiteboard integrated machine as described in any one of claims 1 to 17 when executed by a computer processor.