Temperature detection method and system, air conditioner, device and storage medium

Abstract

The invention relates to a temperature detection method and system, an air conditioner, a device and a storage medium. The method comprises the steps that a central control node obtains confidence scores uploaded by distributed sensor nodes and temperature data collected by the distributed sensor nodes in the same round of detection task; wherein the confidence score is used for representing the temperature detection credibility of the sensor node; correcting the confidence score to obtain a corrected confidence score; calculating the dynamic weight of each sensor node based on the corrected confidence score; and carrying out weighted calculation on the temperature data by using a dynamic weight to obtain a final detection temperature. Compared with the prior art, the temperature detection system can more scientifically and comprehensively fuse various influence factors, and the technical effect of more accurately and stably carrying out temperature detection is achieved.

Description

Technical Field

[0001] This application relates to the field of air conditioning indoor temperature detection technology, and in particular to a temperature detection method, system, air conditioner, device and storage medium. Background Technology

[0002] With the rapid development of smart home appliance technology, smart air conditioners and other home appliances are demanding increasingly precise temperature control in indoor environments. In modern smart air conditioning systems, the accuracy of temperature detection directly affects indoor comfort and energy efficiency.

[0003] Traditional temperature detection methods typically rely on a single or small number of temperature sensors deployed in fixed locations. This approach struggles to accurately reflect temperature changes in indoor activity areas. Furthermore, existing temperature detection methods, such as the one disclosed in patent CN121067435A, involve setting up multiple sensors and then directly using a weighted average method to fuse the temperatures from each sensor, resulting in a single average temperature value.

[0004] Therefore, the weights of sensors in the temperature detection systems provided by existing technical solutions are generally statically set, which reduces the overall stability and reliability of the system's temperature detection. Summary of the Invention

[0005] This application provides a temperature detection method, device, system, air conditioner, and storage medium to solve the problem of low stability and reliability in the prior art when using the static weighted average method to calculate temperature.

[0006] In a first aspect, this application provides a temperature detection method, which is applied to the central control node of a temperature detection system. The temperature detection system deploys multiple distributed sensor nodes. The method includes: The confidence scores and collected temperature data uploaded by each distributed sensor node in the same round of detection task are obtained; wherein, the confidence scores are used to characterize the reliability of the temperature detection by the sensor node. The confidence score is then corrected to obtain the corrected confidence score; Based on the corrected confidence score, the dynamic weight of each sensor node is calculated; The temperature data is weighted using the dynamic weights to obtain the final detected temperature.

[0007] In an optional embodiment of this application, the confidence score is calculated by the sensor node based on the environmental data it collects and the communication data with neighboring sensor nodes.

[0008] In an optional embodiment of this application, the confidence score is obtained by weighted calculation of any one or more of the following scores: Human activity detection score, used to characterize the strength and stability of human activity signals detected by the sensor node; The carbon dioxide concentration detection score is used to characterize whether the current carbon dioxide concentration detected by the sensor node is within the range of human activity. Spatial consistency score is used to characterize the degree of difference between the temperature data collected by the sensor node and the average temperature of neighboring sensor nodes; The stability score is used to characterize the fluctuation of the temperature values ​​measured historically by the sensor node.

[0009] In an optional embodiment of this application, the step of correcting the confidence score to obtain a corrected confidence score includes: Based on the performance of all sensor nodes in the global network, the confidence score is globally corrected to obtain a globally corrected value. The confidence score is historically corrected based on the sensor node's own historical detection data to obtain a historically corrected value; The corrected confidence score of the sensor node is calculated by combining the global correction value and the historical correction value.

[0010] In an optional embodiment of this application, the step of globally correcting the confidence score based on the performance of all sensor nodes in the global network to obtain a globally corrected value includes: Calculate the mean confidence score for all sensor nodes; The confidence score of this sensor node is compared with the mean, and a global correction value is obtained based on the comparison result.

[0011] In an optional embodiment of this application, the step of historically correcting the confidence score based on the sensor node's own historical detection data to obtain a historically corrected value includes: Based on the time decay mechanism, the confidence scores of historical detection task rounds are assigned progressively lower weights in the time dimension from recent to distant. The weighted historical confidence scores are then compared with the upper limit of the scores to obtain the historical correction value.

[0012] In an optional embodiment of this application, calculating the dynamic weight of each sensor node based on the corrected confidence score includes: The corrected confidence scores are normalized to calculate the dynamic weight of each sensor node.

[0013] In an optional embodiment of this application, it further includes: Based on the difference between the final detected temperature and the reported temperature of each sensor node, the confidence score of each node in this round of detection task is calculated, and the confidence score record is updated.

[0014] Secondly, this application provides a temperature detection system, the system including a central control node and multiple distributed sensor nodes, wherein the central control node executes a temperature detection process according to the method described in any embodiment of the first aspect.

[0015] Thirdly, this application provides an air conditioner, including an air conditioning device and a temperature detection system as described in the second aspect embodiment, wherein the air conditioning device is used to dynamically adjust its working state based on the temperature data detected by the temperature detection system.

[0016] Fourthly, this application provides a temperature detection device applied to the central control node of a temperature detection system, wherein multiple distributed sensor nodes are deployed in the temperature detection system, and the device includes: The acquisition module is used to acquire the confidence scores and collected temperature data uploaded by each distributed sensor node in the same round of detection task; wherein, the confidence scores are used to characterize the reliability of the temperature detection by the sensor node; A correction module is used to correct the confidence score to obtain a corrected confidence score; The first calculation module is used to calculate the dynamic weight of each sensor node based on the corrected confidence score; The second calculation module is used to perform weighted calculations on the temperature data using the dynamic weights to obtain the final detected temperature.

[0017] In an optional embodiment of this application, the confidence score is calculated by the sensor node based on the environmental data it collects and the communication data with neighboring sensor nodes.

[0018] In an optional embodiment of this application, the confidence score is obtained by weighted calculation of any one or more of the following scores: Human activity detection score, used to characterize the strength and stability of human activity signals detected by the sensor node; The carbon dioxide concentration detection score is used to characterize whether the current carbon dioxide concentration detected by the sensor node is within the range of human activity. Spatial consistency score is used to characterize the degree of difference between the temperature data collected by the sensor node and the average temperature of neighboring sensor nodes; The stability score is used to characterize the fluctuation of the temperature values ​​measured historically by the sensor node.

[0019] In an optional embodiment of this application, the correction module specifically includes: A global correction unit is used to globally correct the confidence score based on the performance of all sensor nodes in the global network to obtain a global correction value. The history correction unit is used to perform historical correction on the confidence score based on the historical detection data of this sensor node to obtain a historical correction value. The calculation unit is used to combine the global correction value and the historical correction value to calculate the corrected confidence score of the sensor node.

[0020] In an optional embodiment of this application, the global correction unit is specifically used for: Calculate the mean confidence score for all sensor nodes; The confidence score of this sensor node is compared with the mean, and a global correction value is obtained based on the comparison result.

[0021] In an optional embodiment of this application, the history correction unit is specifically used for: Based on the time decay mechanism, the confidence scores of historical detection task rounds are assigned progressively lower weights in the time dimension from recent to distant. The weighted historical confidence scores are then compared with the upper limit of the scores to obtain the historical correction value.

[0022] In an optional embodiment of this application, the first computing module specifically includes: The normalization processing unit is used to normalize the corrected confidence scores and calculate the dynamic weight of each sensor node.

[0023] In an optional embodiment of this application, the apparatus further includes: The update module is used to calculate the confidence score of each node in this round of detection task based on the difference between the final detected temperature and the reported temperature of each sensor node, and update the confidence score record.

[0024] Fifthly, this application provides a temperature detection device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, communication interface, and memory communicate with each other via the communication bus. Memory, used to store computer programs; When a processor executes a program stored in memory, it implements the steps of the method as described in any embodiment of the first aspect.

[0025] In a sixth aspect, this application also provides a computer-readable storage medium, characterized in that it stores a computer program thereon, which, when executed by a processor, implements the steps of the method as described in any embodiment of the first aspect.

[0026] The advantages of the technical solution provided in this application compared with the prior art are described in detail below: This temperature detection method is applied to the central control node of a temperature detection system. This system deploys multiple distributed sensor nodes. The central control node acquires the confidence scores and collected temperature data uploaded by each distributed sensor node in the same detection task. The confidence score characterizes the reliability of the temperature detection by the sensor node and is calculated by the sensor node itself. The central control node corrects the received confidence score to obtain a corrected confidence score. Then, based on the corrected confidence score, it calculates the dynamic weight of each sensor node. Finally, the central control node uses the calculated dynamic weight to perform a weighted calculation on the temperature data to obtain the final detected temperature. Therefore, in this embodiment, the confidence score of temperature detection is first calculated by the multimodal sensor nodes and uploaded to the central control node, so that the central control can initially assess the current reliability of each sensor; the central control node further corrects the confidence score; and the dynamic weight of each sensor node is calculated by comprehensively considering the confidence score and the correction value. Based on the dynamic weight, the final detected temperature is calculated, which enables the overall temperature detection system to more scientifically and comprehensively integrate multiple influencing factors, achieving a more accurate, stable and reliable temperature detection effect. Attached Figure Description

[0027] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0028] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0029] One or more embodiments are illustrated by way of example with reference numerals in the accompanying drawings. These illustrations do not constitute a limitation on the embodiments. Elements with the same reference numerals in the drawings are denoted as similar elements. Unless otherwise stated, the figures in the drawings are not to be limited by scale.

[0030] Figure 1 A schematic flowchart of a temperature detection method provided in an embodiment of this application; Figure 2 A flowchart illustrating a method for correcting confidence scores provided in an embodiment of this application; Figure 3 A schematic flowchart of another temperature detection method provided in an embodiment of this application; Figure 4A schematic diagram of the node arrangement scenario for a temperature detection method provided in a specific embodiment of this application; Figure 5 This is a schematic diagram of a scenario for an air conditioning and temperature detection system provided in a specific embodiment of this application; Figure 6 This is a schematic diagram of the structure of a temperature detection device provided in an embodiment of this application; Figure 7 This is a schematic diagram of the structure of a temperature detection device provided in an embodiment of this application. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0032] The following disclosure provides numerous different embodiments or examples for implementing various structures of the invention. To simplify the disclosure, specific examples of components and arrangements are described below. These are merely examples and are not intended to limit the scope of the invention. Furthermore, reference numerals and / or letters may be repeated in different examples. Such repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed.

[0033] In modern intelligent air conditioning systems, the accuracy of temperature detection and control directly affects indoor comfort and energy efficiency. Existing indoor temperature detection systems use multiple temperature sensors with statically set weights, failing to dynamically adjust temperature data based on historical sensor performance or environmental changes. This results in significant system errors and reduces overall system stability and reliability. Therefore, this application provides a temperature detection method, system, air conditioner, device, and storage medium. By offering a distributed temperature detection method capable of dynamically evaluating sensor temperature detection confidence and adjusting their weights, the accuracy and reliability of temperature detection are comprehensively improved.

[0034] The present application solution will be described in detail below through specific embodiments.

[0035] Figure 1 A schematic flowchart of a temperature detection method provided in this application embodiment; see reference Figure 1As shown, this method is applied to the central control node of a temperature detection system, which deploys multiple distributed sensor nodes. The method includes the following steps S10-S40: S10. The central control node acquires the confidence scores and collected temperature data uploaded by each distributed sensor node in the same round of detection task; wherein, the confidence scores are used to characterize the reliability of the temperature detection by the sensor nodes.

[0036] The temperature detection system in this embodiment includes a central control node and multiple distributed sensor nodes, which interact with the central control node. When detecting the indoor temperature, the sensor nodes are configured to be distributed at different locations to collect environmental data, including temperature data, from various indoor locations.

[0037] In one embodiment of this application, the confidence score is calculated by the sensor node based on its own collected environmental data and communication data with neighboring sensor nodes. For example, the sensor node communicates with neighboring sensor nodes via Bluetooth, and the proximity can be determined by the strength of the Bluetooth communication signal. This confidence score is essentially a self-assessment by the sensor node of the reliability of its collected temperature data.

[0038] In this embodiment, the central control node sends an instruction to each sensor node to start the current round of detection tasks. After receiving the start instruction, each sensor node calculates the confidence score and then uploads the data to the central control node.

[0039] Each sensor node uses multimodal sensors to collect data on the surrounding environment, such as temperature, human activity, and carbon dioxide concentration. During system operation, the sensor nodes continuously record current environmental data and monitor the entire network, awaiting instructions to begin detection tasks.

[0040] S20. The confidence score is corrected to obtain the corrected confidence score.

[0041] Since the central control node aggregates the confidence scores uploaded by all distributed sensor nodes and records the confidence scores of each sensor node in past detection tasks, it can perform global and historical corrections on the uploaded confidence scores based on the performance of each sensor node compared to other sensor nodes and its own historical detection data.

[0042] It should be noted that the process of the central control node correcting the confidence score here can be either a global correction or a historical correction only.

[0043] To further enhance detection accuracy, in a preferred embodiment of this application, the central control node performs global correction and historical correction on each sensor node.

[0044] Figure 2 This application provides a flowchart illustrating a method for correcting confidence scores in an embodiment of the present application; see also... Figure 2 As shown, in step S20 above, the central control node corrects the confidence score uploaded by the sensor node to obtain the corrected confidence score, specifically including the following steps S201-S203: S201. Based on the performance of all sensor nodes in the global network, the confidence score is globally corrected to obtain a globally corrected value.

[0045] Since the confidence score can be regarded as the performance of a single sensor node in the detection task, and the average confidence score of all sensor nodes can represent the average level of detection of each sensor node, in this embodiment, the confidence score of each sensor node is compared with the average score to obtain a global correction value that takes into account the performance of each sensor node in the global network.

[0046] Furthermore, in a specific embodiment of this application, in step S201 above, the confidence score is globally corrected based on the performance of all sensor nodes in the global network to obtain a globally corrected value, specifically including the following steps A10-A20: Step A10: Calculate the mean confidence score of all sensor nodes in the global network; Step A20: Compare the confidence score of this sensor node with the mean value, and obtain the global correction value based on the comparison result.

[0047] In this embodiment, a global correction value is obtained by comparing the confidence score of the current sensor node with the average confidence score uploaded by all sensor nodes in the system.

[0048] S202. Based on the sensor node's own historical detection data, the confidence score is historically corrected to obtain a historically corrected value.

[0049] Since the historical detection confidence scores of each sensor node can be considered a measure of its reliability, and considering that the more recent detection task rounds have higher timeliness, the effect of time decay can be introduced. The confidence scores of rounds from most recent to oldest are assigned progressively decreasing weights. By comparing the weighted scores with the upper limit of the score, the correction value for each sensor node based on the historical detection records is obtained. Therefore, in a specific embodiment of this application, step S202 above, which involves historically correcting the confidence score based on the sensor node's own historical detection data to obtain a historically corrected value, specifically includes step B10: Step B10: Based on the time decay mechanism, assign gradually decreasing weights to the confidence scores of historical detection task rounds from recent to distant in the time dimension, compare the weighted historical confidence scores with the upper limit of the scores, and obtain the historical correction value.

[0050] S203. Combine the global correction value and the historical correction value to calculate the corrected confidence score of the sensor node.

[0051] In summary, in one specific embodiment of this application, the central control node calculates the confidence score of each sensor node based on the confidence score submitted by each sensor node in this instance and the performance of each sensor node in historical detection tasks. Specifically, this can be achieved through the following operational relationship:

[0052]

[0053] in, This represents the sigmoid function, used for normalization after comparison with the global confidence score; This represents the confidence score of the j-th sensor in the i-th round of detection; This represents the average confidence score submitted by each sensor in the i-th round of detection. For example, the time decay factor. Set fixed values ​​based on experience; for example... , , , Take values ​​of 0.4, 0.3, 0.2, and 0.1 respectively; Let be the confidence score obtained by the j-th sensor in round ir; This represents the maximum score, and the experience value; for example, the maximum score is set to 10.

[0054] S30. Based on the corrected confidence score, calculate the dynamic weight of each sensor node.

[0055] In a specific embodiment of this application, step S30 above, which calculates the dynamic weight of each sensor node based on the corrected confidence score, specifically includes the following step C10: Step C10: Normalize the corrected confidence scores to calculate the dynamic weight of each sensor node.

[0056] In this embodiment, the central control node performs a normalization process again on the corrected confidence score to calculate the dynamic weight of each sensor node.

[0057] In one specific implementation, the final normalized dynamic contribution weight of a single sensor node to the detected temperature is... It can be obtained through the following operational relationship:

[0058] Where N is the total number of sensor nodes participating in the i-th round of detection.

[0059] S40. The temperature data is weighted using the dynamic weights to obtain the final detected temperature.

[0060] In this embodiment, the central control node normalizes the corrected confidence score, calculates the dynamic weight of each sensor node, and then uses the weight to perform a weighted calculation on the temperature data uploaded by each sensor node to obtain the final detected temperature.

[0061] In the above embodiments of this application, a dynamic weight adjustment mechanism based on the combination of distributed sensor node confidence scores and central control node confidence correction is provided. Through information collaborative detection among multiple sensor nodes, evaluation of the confidence scores of each sensor node, and further correction by the central control node, high-precision and high-reliability detection of indoor temperature in air conditioning is achieved.

[0062] In one specific embodiment of this application, after receiving the detection task start instruction, each of the above-mentioned distributed sensor nodes will calculate the current confidence score of the node based on the collected environmental data and the data communicated with surrounding nodes, and upload it to the central control node together with the currently detected temperature value.

[0063] The confidence score uploaded by each sensor node can measure the reliability of the temperature detected by a single distributed node. For example, the confidence score may take into account the following influencing factors: human activity, carbon dioxide concentration, spatial consistency and the performance stability of the sensor itself.

[0064] Therefore, in one embodiment of this application, the confidence score uploaded by the sensor node to the central control node is obtained by weighted calculation of any one or more of the following scores: Human activity detection score, used to characterize the strength and stability of human activity signals detected by the sensor node; The carbon dioxide concentration detection score is used to characterize whether the current carbon dioxide concentration detected by the sensor node is within the range of human activity. Spatial consistency score is used to characterize the degree of difference between the temperature data collected by this sensor node and the average temperature of neighboring sensor nodes; The stability score is used to characterize the fluctuation of the temperature values ​​measured historically by the sensor node.

[0065] In this embodiment of the application, the above four scores will be described separately: Human activity detection score: This score measures the strength and stability of human activity signals detected by the infrared sensor in the sensor node, reflecting whether the sensor "senses a real heat source". When human activity is detected and remains stable, the score increases; when there is no activity or the signal is weak, the score decreases.

[0066] For example, for the first The sensor at the first Human activity detection score in round detection task In practice, the following operational relationship can be used to calculate it:

[0067] in, Indicates the effective human body threshold. Indicates the sensor's maximum received signal strength. This indicates the test results.

[0068] This embodiment is particularly suitable for scenarios where people are unevenly distributed or frequently changing. Because the detection results of fixed sensors are prone to deviate from the actual temperature of the area in use, the air conditioning system may not adjust accurately, thus affecting the user experience.

[0069] Carbon dioxide detection score: This score is used to determine whether the current carbon dioxide concentration is within a reasonable range for human activity. A carbon dioxide concentration within a reasonable range indicates that there is human activity in the area, and the sensor data is more reliable; if the concentration is abnormal, the score will be lowered.

[0070] For example, for the first The sensor at the first In the round detection task Detection score When the detected concentration is greater than the lower limit of normal human activity =800 and less than the upper limit of high-density human activity. When the value is 2500, the score is 100; at other times, the score is 0.

[0071] Spatial consistency score: This measures whether the temperature reading of this sensor node is within an acceptable range compared to the average temperature of its neighboring sensors, reflecting spatial consistency. If the sensor temperature deviates significantly from that of neighboring sensors, it indicates potential local interference, reducing confidence. For selecting nearby sensors, Bluetooth signal strength can be used as a criterion. Generally, in unobstructed conditions, a stronger received signal indicates a closer relative distance between the two sensors.

[0072] For example, for the first The sensor at the first Spatial consistency score in round detection task Specifically, it can be calculated using the following operational relationships:

[0073] in, Indicates the round of testing. This indicates the results of this round of testing. This indicates that the sensor's Bluetooth module detected the average temperature of the two surrounding sensors with the strongest signals. This indicates the maximum permissible deviation threshold.

[0074] Stability Score: This score is used to evaluate the volatility of the sensor's historical data and prevent anomalies caused by equipment aging, drift, or noise. Sensors with small fluctuations in historical temperature values ​​have high stability and a high score; large fluctuations result in a lower score.

[0075] For example, for the first The sensor at the first Stability score in round detection task ,

[0076] in, Indicates the round of testing; The attenuation coefficient (0.5) is used to control the fluctuation sensitivity. This represents the standard deviation of the sensor's temperature readings over the past m sampling periods.

[0077] Finally, in the i-th round of detection, the confidence scores submitted by each sensor node to the central control node are... It can be calculated based on the weighted values ​​set by experience and the four scores mentioned above.

[0078] It is particularly important to note that when the temperature collected by the sensor node experiences a sudden error or serious anomaly, such as a temperature jump, exceeding the reasonable range, or no change for a long time, the sensor node will directly set the confidence score to zero because the detected temperature value has obvious problems.

[0079] Figure 3 A schematic flowchart of another temperature detection method provided in this application embodiment; see reference Figure 3 As shown, the method provided in this application embodiment further includes the following arrangement S50: S50. Based on the difference between the final detected temperature and the reported temperature of each sensor node, calculate the confidence score of each node in this round of detection task, and update the confidence score record.

[0080] The central control node calculates the confidence score of each sensor node in this detection task, collects the corrected confidence scores, and updates the confidence score records to provide a reference for the next detection task.

[0081] For example, in the i-th round of the detection task, the temperature submitted by the j-th sensor is The final temperature output by the central control unit is Then the confidence score obtained by the sensor in this round of tasks. It can be represented as:

[0082] in, This represents the maximum temperature interval, which is 2℃.

[0083] In this embodiment of the system, the correction value is adaptively adjusted by continuously updating the confidence score of each sensor node, ensuring that the detected scene can still maintain high temperature detection accuracy when the distribution of people changes or the performance of sensors fluctuates.

[0084] The embodiments described above address the problems of inaccurate temperature detection and delayed system response caused by changes in personnel distribution and sensor errors in air-conditioned indoor environments. By using multimodal data to calculate the confidence score of the temperature collected by distributed sensor nodes at the sensor node side, and simultaneously performing global / historical correction on the confidence score, intelligent fusion of node-detected temperature data is dynamically achieved. By introducing a dual evaluation mechanism of confidence score and correction value to dynamically adjust the weight of each sensor, the final detected temperature is ensured to be closer to the actual temperature at the user's location, effectively improving the air conditioning system's ability to sense and respond to indoor temperature, and enhancing the user experience.

[0085] Figure 4 A schematic diagram of the node arrangement scenario for a temperature detection method provided in a specific embodiment of this application; refer to Figure 4 As shown, the temperature detection system provided in this embodiment includes a central control node and multiple distributed sensor nodes. The central control node performs temperature detection according to the method described in any of the above method embodiments.

[0086] The temperature detection system provided in this implementation is achieved by deploying a distributed temperature detection sensor network in the air-conditioned room. For example... Figure 2 As shown, multiple distributed sensor nodes and one central control node are deployed in different locations indoors. Each sensor node is responsible for collecting environmental data from different locations, while the central control node is responsible for summarizing the data from each location and calculating the final detected temperature.

[0087] To ensure communication range, communication between sensor nodes and between sensor nodes and the central control node can be achieved via flooded Bluetooth Mesh. For example, each sensor node includes a temperature sensor, an infrared sensor, and a carbon dioxide sensor to detect the temperature, human activity levels, and air quality of its area.

[0088] This system, by deploying a multimodal distributed sensor network, can acquire data from different environmental locations within a space, providing precise data for intelligent environmental control. Based on multi-dimensional information such as temperature and human activity, the system achieves precise temperature control and dynamic adjustment, thereby significantly improving indoor comfort and creating a healthy and intelligent indoor environmental management system.

[0089] During system operation, sensor nodes continuously record current environmental data and monitor the entire network, waiting for the central control node to issue an instruction to start the detection task.

[0090] At regular intervals, the central control node sends a detection task start command to each sensor node in the network. Upon receiving the command, each distributed sensor node responds, processes the collected data, and then sends the corresponding data back to the central control node.

[0091] In this system embodiment, the aforementioned central control node is used for: The confidence scores and collected temperature data uploaded by each distributed sensor node in the same round of detection task are obtained; wherein, the confidence scores are used to characterize the reliability of the temperature detection by the sensor node. The confidence score is then corrected to obtain the corrected confidence score; Based on the corrected confidence score, the dynamic weight of each sensor node is calculated; The temperature data is weighted using the dynamic weights to obtain the final detected temperature.

[0092] In an optional embodiment of this application, the confidence score is calculated by the sensor node based on the environmental data it collects and the communication data with neighboring sensor nodes.

[0093] In an optional embodiment of this application, the confidence score is obtained by weighted calculation of any one or more of the following scores: Human activity detection score, used to characterize the strength and stability of human activity signals detected by the sensor node; The carbon dioxide concentration detection score is used to characterize whether the current carbon dioxide concentration detected by the sensor node is within the range of human activity. Spatial consistency score is used to characterize the degree of difference between the temperature data collected by the sensor node and the average temperature of neighboring sensor nodes; The stability score is used to characterize the fluctuation of the temperature values ​​measured historically by the sensor node.

[0094] In an optional embodiment of this application, the aforementioned central control node is used to correct the confidence score to obtain a corrected confidence score, specifically including: Based on the performance of all sensor nodes in the global network, the confidence score is globally corrected to obtain a globally corrected value. Based on the historical detection data of this sensor node, the confidence score is historically corrected to obtain a historically corrected value; The corrected confidence score of the sensor node is calculated by combining the global correction value and the historical correction value.

[0095] In an optional embodiment of this application, the aforementioned central control node is used to globally correct the confidence score based on the performance of all sensor nodes in the global network, obtaining a globally corrected value, specifically including: Calculate the mean confidence score for all sensor nodes; The confidence score of this sensor node is compared with the mean, and a global correction value is obtained based on the comparison result.

[0096] In an optional embodiment of this application, the aforementioned central control node is used to perform historical correction on the confidence score based on the historical detection data of the sensor node, obtaining a historical correction value, specifically including: Based on the time decay mechanism, the weights of historical detection task rounds are gradually reduced from recent to distant in the time dimension. The weighted historical confidence score is compared with the upper limit of the score to obtain the historical correction value.

[0097] In an optional embodiment of this application, the central control node is used to calculate the dynamic weight of each sensor node based on the corrected confidence score, including: The corrected confidence scores are normalized to calculate the dynamic weight of each sensor node.

[0098] In an optional embodiment of this application, the aforementioned central control node is further used for: Based on the difference between the final detected temperature and the reported temperature of each sensor node, the confidence score of each node in this round of detection task is calculated, and the confidence score record is updated.

[0099] Figure 5 This is a schematic diagram of a scenario for an air conditioning and temperature detection system provided in a specific embodiment of this application; see reference. Figure 5As shown in the illustration, this application provides an air conditioner, including an air conditioning unit and a temperature detection system as described in the above embodiments. The temperature detection unit detects temperature data according to the steps described in the above temperature detection method embodiments. The air conditioning unit is used to dynamically adjust its operating state based on the temperature data detected by the temperature detection system.

[0100] For example, embodiments of this application are applied to temperature control in smart homes or smart commercial settings, such as office buildings and hotels. A temperature detection system detects multiple temperature points according to the steps described in the temperature detection method embodiments. A central control node transmits the final data to the air conditioning unit. Alternatively, the central control node can perform an algorithmic decision based on the final data and send the final decision instruction data to the air conditioning unit. Upon receiving the data, the air conditioning unit dynamically adjusts its operating status, including adjusting the operating mode (cooling or heating), and regulating compressor power and fan speed. This allows the air conditioning unit to make real-time corrections based on the monitoring results of the temperature detection system, avoiding localized temperature differences and achieving a balance between energy saving and comfort.

[0101] Figure 6 This is a schematic diagram of the structure of a temperature detection device provided in an embodiment of this application; see reference. Figure 6 As shown, the temperature detection device is applied to the central control node of a temperature detection system, which deploys multiple distributed sensor nodes. The device includes: The acquisition module 501 is used to acquire the confidence scores and collected temperature data uploaded by each distributed sensor node in the same round of detection task; wherein, the confidence scores are used to characterize the reliability of the temperature detection by the sensor node; Correction module 502 is used to correct the confidence score to obtain the corrected confidence score; The first calculation module 503 is used to calculate the dynamic weight of each sensor node based on the corrected confidence score. The second calculation module 504 is used to perform weighted calculations on the temperature data using the dynamic weights to obtain the final detection temperature.

[0102] In an optional embodiment of this application, the confidence score is calculated by the sensor node based on the environmental data it collects and the communication data with neighboring sensor nodes.

[0103] In an optional embodiment of this application, the confidence score is obtained by weighted calculation of any one or more of the following scores: Human activity detection score, used to characterize the strength and stability of human activity signals detected by the sensor node; The carbon dioxide concentration detection score is used to characterize whether the current carbon dioxide concentration detected by the sensor node is within the range of human activity. Spatial consistency score is used to characterize the degree of difference between the temperature data collected by the sensor node and the average temperature of neighboring sensor nodes; The stability score is used to characterize the fluctuation of the temperature values ​​measured historically by the sensor node.

[0104] In an optional embodiment of this application, the above-mentioned correction module 502 specifically includes: A global correction unit is used to globally correct the confidence score based on the performance of all sensor nodes in the global network to obtain a global correction value. The history correction unit is used to perform historical correction on the confidence score based on the historical detection data of this sensor node to obtain a historical correction value. The calculation unit is used to combine the global correction value and the historical correction value to calculate the corrected confidence score of the sensor node.

[0105] In an optional embodiment of this application, the aforementioned global correction unit is specifically used for: Calculate the mean confidence score for all sensor nodes; The confidence score of this sensor node is compared with the mean, and a global correction value is obtained based on the comparison result.

[0106] In an optional embodiment of this application, the aforementioned history correction unit is specifically used for: Based on the time decay mechanism, the weights of historical detection task rounds are gradually reduced from recent to distant in the time dimension. The weighted historical confidence score is compared with the upper limit of the score to obtain the historical correction value.

[0107] In an optional embodiment of this application, the first computing module 503 specifically includes: The normalization processing unit is used to normalize the corrected confidence scores and calculate the dynamic weight of each sensor node.

[0108] In an optional embodiment of this application, the apparatus further includes: The update module (not shown in the figure) is used to calculate the confidence score of each node in this round of detection task based on the difference between the final detected temperature and the reported temperature of each sensor node, and update the confidence score record.

[0109] Figure 7A schematic diagram of a temperature detection device provided in this application embodiment includes a processor 111, a communication interface 112, a memory 113, and a communication bus 114, wherein the processor 111, the communication interface 112, and the memory 113 communicate with each other through the communication bus 114. Memory 113 is used to store computer programs; In one embodiment of this application, the processor 111, when executing a program stored in the memory 113, implements a method for locating communication faults in home appliances provided in any of the foregoing method embodiments, including: The confidence scores and collected temperature data uploaded by each distributed sensor node in the same round of detection task are obtained; wherein, the confidence scores are used to characterize the reliability of the temperature detection by the sensor node. The confidence score is then corrected to obtain the corrected confidence score; Based on the corrected confidence score, the dynamic weight of each sensor node is calculated; The temperature data is weighted using the dynamic weights to obtain the final detected temperature.

[0110] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of a temperature detection method as provided in any of the foregoing method embodiments.

[0111] In the above embodiments, the confidence scores and collected temperature data uploaded by each distributed sensor node in the same round of detection task are obtained; wherein, the confidence scores are used to characterize the reliability of the temperature detected by the sensor nodes; the confidence scores are corrected to obtain corrected confidence scores; based on the corrected confidence scores, the dynamic weight of each sensor node is calculated; the dynamic weights are used to perform weighted calculations on the temperature data to obtain the final detected temperature.

[0112] Furthermore, in this embodiment, the central control node can initially assess the current reliability of each sensor node by uploading the calculated confidence scores from the multimodal sensor nodes; the central control node further corrects the confidence scores; and simultaneously, the dynamic weights of the sensor nodes are calculated by comprehensively considering the confidence scores and correction values, and the final detected temperature is calculated based on these dynamic weights. This enables the system to more scientifically and comprehensively integrate multiple influencing factors for temperature detection, achieving a more accurate, stable, and reliable technical effect.

[0113] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0114] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented using software plus a general-purpose hardware platform, or of course, using hardware. Based on this understanding, the above technical solutions, in essence or the parts that contribute to the related technology, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0115] It should be understood that the terminology used herein is for the purpose of describing particular exemplary embodiments only and is not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “described” as used herein may also include the plural forms. The terms “comprising,” “including,” “containing,” and “having” are inclusive and therefore indicate the presence of the stated features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or combinations thereof. The method steps, processes, and operations described herein are not construed as requiring them to be performed in a particular order described or illustrated unless the order of performance is explicitly indicated. It should also be understood that additional or alternative steps may be used.

[0116] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A temperature detection method, characterized in that, The method is applied to the central control node of a temperature detection system, wherein multiple distributed sensor nodes are deployed in the temperature detection system, and the method includes: The confidence scores and collected temperature data uploaded by each distributed sensor node in the same round of detection task are obtained; wherein, the confidence scores are used to characterize the reliability of the temperature detection by the sensor node. The confidence score is then corrected to obtain the corrected confidence score; Based on the corrected confidence score, the dynamic weight of each sensor node is calculated; The temperature data is weighted using the dynamic weights to obtain the final detected temperature.

2. The method according to claim 1, characterized in that, The confidence score is calculated by the sensor node based on the environmental data it collects and the communication data with neighboring sensor nodes.

3. The method according to claim 2, characterized in that, The confidence score is obtained by weighting one or more of the following scores: Human activity detection score, used to characterize the strength and stability of human activity signals detected by the sensor node; The carbon dioxide concentration detection score is used to characterize whether the current carbon dioxide concentration detected by the sensor node is within the range of human activity. Spatial consistency score is used to characterize the degree of difference between the temperature data collected by the sensor node and the average temperature of neighboring sensor nodes; The stability score is used to characterize the fluctuation of the temperature values ​​measured historically by the sensor node.

4. The method according to claim 1, characterized in that, The step of correcting the confidence score to obtain the corrected confidence score includes: Based on the performance of all sensor nodes in the global network, the confidence score is globally corrected to obtain a globally corrected value. The confidence score is historically corrected based on the sensor node's own historical detection data to obtain a historically corrected value; The corrected confidence score of the sensor node is calculated by combining the global correction value and the historical correction value.

5. The method according to claim 4, characterized in that, The confidence score is globally corrected based on the performance of all sensor nodes in the global network to obtain a globally corrected value, including: Calculate the mean confidence score for all sensor nodes; The confidence score of this sensor node is compared with the mean, and a global correction value is obtained based on the comparison result.

6. The method according to claim 4, characterized in that, The process of historically correcting the confidence score based on the sensor node's own historical detection data to obtain a historically corrected value includes: Based on the time decay mechanism, the confidence scores of historical detection task rounds are assigned progressively lower weights in the time dimension from recent to distant. The weighted historical confidence scores are then compared with the upper limit of the scores to obtain the historical correction value.

7. The method according to claim 1, characterized in that, The calculation of the dynamic weight of each sensor node based on the corrected confidence score includes: The corrected confidence scores are normalized to calculate the dynamic weight of each sensor node.

8. The method according to claim 1, characterized in that, The method further includes: Based on the difference between the final detected temperature and the reported temperature of each sensor node, the confidence score of each node in this round of detection task is calculated, and the confidence score record is updated.

9. A temperature detection system, characterized in that, The system includes a central control node and multiple distributed sensor nodes, wherein the central control node performs temperature detection in accordance with the method described in any one of claims 1-8.

10. An air conditioner, characterized in that, The system includes an air conditioning unit and the temperature detection system as described in claim 9, wherein the air conditioning unit is used to dynamically adjust its operating state based on the temperature data detected by the temperature detection system.

11. A temperature detection device, characterized in that, A central control node for a temperature detection system, wherein multiple distributed sensor nodes are deployed in the temperature detection system, the device comprising: The acquisition module is used to acquire the confidence scores and collected temperature data uploaded by each distributed sensor node in the same round of detection task; wherein, the confidence scores are used to characterize the reliability of the temperature detection by the sensor node; The correction module is used to correct the confidence score to obtain the corrected confidence score; The first calculation module is used to calculate the dynamic weight of each sensor node based on the corrected confidence score; The second calculation module is used to perform weighted calculations on the temperature data using the dynamic weights to obtain the final detected temperature.

12. A temperature detection device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus. The processor, communication interface, and memory communicate with each other through the communication bus. Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the steps of the method as described in any one of claims 1-8.

13. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the steps of the method as described in any one of claims 1-8.

Images