A sensor data error correction method and system based on big data

Abstract

This application provides a sensor data processing method and system based on big data, belonging to the field of data processing technology. In this method, when the target sensor cluster meets the security conditions, abnormal data in the original dataset uploaded by the target sensor cluster can be automatically identified and repaired to obtain a data-repaired target dataset, thereby ensuring data integrity and accuracy. Simultaneously, based on the update time of the sensor data in each target dataset, newly added sensor data in each target dataset can be stored in appropriate target leaf nodes in a Merkle tree. This achieves orderly storage of newly added sensor data while effectively reducing storage overhead. Furthermore, by achieving consensus on the newly added sensor data in a blockchain, it effectively prevents sensors from being illegally controlled or their data from being illegally tampered with, thus ensuring the security of data storage.

Description

Technical Field

[0001] This disclosure relates to the field of sensor technology, and more specifically, to a sensor data error correction method and system based on big data. Background Technology

[0002] With the development of sensor technology, the applications of sensors are becoming increasingly widespread. A temperature sensor is a sensor that senses temperature and converts it into a usable output signal. Temperature sensors are the core component of temperature measuring instruments, and there are many different types.

[0003] When temperature sensors collect temperature data, they are affected by many factors, which can lead to errors in the data. Therefore, error correction is necessary for the temperature data collected by the sensors. Currently, temperature sensor data correction suffers from low efficiency and difficulty in guaranteeing accuracy. Summary of the Invention

[0004] The purpose of this disclosure is to provide a sensor data error correction method and system based on big data, which can achieve effective and accurate correction of temperature sensor data.

[0005] To achieve the above objectives, in a first aspect, this disclosure provides a sensor data error correction method based on big data, comprising: acquiring sensor data to be corrected, temperature sensor information corresponding to the sensor data to be corrected, and measurement object information corresponding to the sensor data to be corrected; determining an error type based on the temperature sensor information and the measurement object information, wherein the error type characterizes the relationship between the error influence weight of the temperature sensor information and the error influence weight of the measurement object information; determining error correction parameters based on the error type, the sensor data to be corrected, and a pre-trained first prediction model; and correcting the sensor data to be corrected based on the error correction parameters to obtain corrected sensor data.

[0006] Optionally, the temperature sensor information includes: protective tube information, temperature sensing element information, and measurement information, wherein the measurement information characterizes the measurement method of the temperature sensor; the measurement object information includes: measurement object shape, measurement object state, and measurement object size; determining the error type based on the temperature sensor information and the measurement object information includes: if the measurement information characterizes the temperature sensor measurement method as insertion measurement, determining the error influence weight of the temperature sensor information based on the insertion depth in the measurement information and the protective tube information, and determining the error influence weight of the measurement object information based on the measurement object shape and the measurement object state; if the measurement information characterizes the temperature sensor measurement method as contact measurement, determining the error influence weight of the temperature sensor information based on the protective tube information and the temperature sensing element information, and determining the error influence weight of the measurement object information based on the measurement object shape and the measurement object size; and determining the error type based on the error influence weight of the temperature sensor information and the error influence weight of the measurement object information.

[0007] Optionally, determining the error type based on the error influence weight of the temperature sensor information and the error influence weight of the measured object information includes: if the error influence weight of the temperature sensor information is equal to the error influence weight of the measured object information, the error type is determined as a first error type; if the error influence weight of the temperature sensor information is greater than the error influence weight of the measured object information, the error type is determined as a second error type; and if the error influence weight of the temperature sensor information is less than the error influence weight of the measured object information, the error type is determined as a third error type.

[0008] Optionally, the big data-based sensor data error correction method further includes: determining an error correction evaluation result based on the error type, the error correction parameters, the corrected sensor data, and the pre-trained second prediction model, wherein the error correction evaluation result is used to characterize the error correction effect of the error correction parameters; and feeding back the corrected sensor data and the error correction evaluation result.

[0009] Optionally, the pre-trained first prediction model is used to output the error correction parameters based on the input error type and the sensor data to be corrected. The sensor data error correction method based on big data further includes: obtaining a first training dataset, the first training dataset including: first sample sensor data, error correction parameters corresponding to the first sample sensor data, and error type corresponding to the first sample sensor data; training the first prediction model to be trained based on the first training dataset to obtain the pre-trained first prediction model.

[0010] Optionally, the pre-trained second prediction model is used to output the error correction evaluation result based on the input error type, the error correction parameters, and the corrected sensor data. The sensor data error correction method based on big data further includes: obtaining a second training dataset, the second training dataset including: second sample sensor data, error type, target error parameters, and error correction evaluation labels of the original sample sensor data corresponding to the second sample sensor data, wherein the original sample sensor data is sensor data selected from the first sample sensor data; training the second prediction model to be trained based on the second training dataset to obtain the pre-trained second prediction model.

[0011] Optionally, obtaining the second training dataset includes: determining the original sample sensor data from the first sample sensor data; inputting the original sample sensor data and the error type corresponding to the original sample sensor data into the pre-trained first prediction model to obtain the prediction error correction parameters output by the pre-trained first prediction model; determining a target error correction parameter and a first error correction evaluation label based on the error correction parameters corresponding to the original sample sensor data and the prediction error correction parameters; determining the second sample sensor data based on the target error correction parameter and the original sample sensor data; determining the error correction evaluation label based on the first error correction evaluation label; and generating the second training dataset based on the second sample sensor data, the error type of the original sample sensor data corresponding to the second sample sensor data, the target error correction parameter, and the error correction evaluation label.

[0012] Optionally, determining the error correction evaluation label based on the first error correction evaluation label includes: feeding back the target error correction parameter and the original sample sensor data; receiving a second error correction evaluation label input by the user based on the fed-back target error correction parameter, the original sample sensor data, and a preset error correction parameter range; and determining the error correction evaluation label based on the first error correction evaluation label and the second error correction evaluation label.

[0013] Optionally, the error types include a first error type, a second error type, and a third error type. The first error type indicates that the error influence weight of the temperature sensor information is equal to the error influence weight of the measured object information. The second error type indicates that the error influence weight of the temperature sensor information is greater than the error influence weight of the measured object information. The third error type indicates that the error influence weight of the temperature sensor information is less than the error influence weight of the measured object information. Determining the error correction parameters based on the error type, the sensor data to be corrected, and the pre-trained first prediction model includes: if the error type is the first error type, inputting the sensor data to be corrected and the error type into the pre-trained first prediction model to obtain the pre-trained first prediction model. The model outputs error correction parameters; if the error type is the second error type, a first sensor data to be corrected is determined from the sensor data to be corrected, and the first sensor data to be corrected and the error type are input into the pre-trained first prediction model to obtain the error correction parameters output by the pre-trained first prediction model, wherein the acquisition time of the first sensor data to be corrected covers the target acquisition period; if the error type is the third error type, a second sensor data to be corrected is determined from the sensor data to be corrected, and the second sensor data to be corrected and the error type are input into the pre-trained first prediction model to obtain the error correction parameters output by the pre-trained first prediction model, wherein the acquisition time of the second sensor data to be corrected covers multiple acquisition periods.

[0014] Secondly, embodiments of this disclosure provide a sensor data error correction system based on big data, comprising: a temperature sensor for collecting temperature data of a measured object; and a terminal connected to the temperature sensor; wherein the temperature sensor is used to transmit the temperature data of the measured object as the sensor data to be corrected to the terminal, and the terminal is used to execute the sensor data error correction method based on big data as described in the first aspect.

[0015] The above technical solution first determines the error type using temperature sensor information and the measured object information. Then, it uses the error type, the sensor data to be corrected, and a pre-trained first prediction model to determine the error correction parameters. Finally, the sensor data to be corrected is adjusted according to these parameters to obtain the corrected sensor data. Since the error type can characterize the relationship between the error influence weight of the temperature sensor information and the error influence weight of the measured object information, the error type can be considered as an influence weight of the sensor data to be corrected. Based on this error type, the error correction parameters determined by the pre-trained first prediction model have high accuracy. Furthermore, the pre-trained first prediction model can quickly determine the error correction parameters. Therefore, this technical solution can achieve effective and accurate correction of temperature sensor data.

[0016] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0017] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings:

[0018] Figure 1 This is a structural block diagram of a sensor data error correction system based on big data, according to an exemplary embodiment.

[0019] Figure 2 This is a flowchart illustrating a sensor data error correction method based on big data, according to an exemplary embodiment.

[0020] Figure 3 This is a flowchart illustrating the training process of a first prediction model and a second prediction model according to an exemplary embodiment.

[0021] Figure 4 This is a structural block diagram illustrating a sensor data error correction device based on big data, according to an exemplary embodiment.

[0022] Figure 5 This is a block diagram illustrating an electronic device according to an exemplary embodiment. Detailed Implementation

[0023] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0024] The technical solutions of this disclosure can be applied to various application scenarios involving temperature sensors, in which temperature sensors are used to collect temperature data.

[0025] In some applications, after acquiring a batch of temperature sensor data, the data is corrected based on that batch of data. In other applications, after acquiring real-time temperature sensor data, the data is corrected based on that real-time data.

[0026] It is understandable that temperature sensors are affected by many factors when collecting temperature data, which can lead to errors in the data. Therefore, error correction is necessary for the temperature data collected by the sensors. Currently, temperature sensor data correction suffers from low efficiency and difficulty in guaranteeing accuracy.

[0027] Based on this, the present disclosure provides a technical solution in which, based on the error type representing the relationship between the error influence weight of temperature sensor information and the error influence weight of the measured object information, a pre-trained first prediction model is used to quickly and accurately determine the error correction parameters, thereby achieving effective and accurate correction of temperature sensor data.

[0028] Figure 1 This is a structural block diagram illustrating a sensor data error correction system based on big data, according to an exemplary embodiment. Figure 1 As shown, the system includes a temperature sensor and a terminal.

[0029] The temperature sensor is connected to the terminal. The temperature sensor is used to collect the temperature data of the object being measured and transmits the temperature data of the object being measured as the sensor data to be corrected to the terminal. The terminal corrects the sensor data to be corrected and applies the corrected sensor data.

[0030] Regarding the object of measurement, it can be of different types, such as objects of different shapes, states, and sizes.

[0031] Regarding temperature sensors, the number can be one or more, and there is no limitation here. Furthermore, temperature sensors can be of different types, for example, using different protective tubes, different sensing elements, and different temperature measurement methods.

[0032] In some embodiments, the system may be part of an Internet of Things (IoT) system, serving as a data acquisition component of the IoT system to achieve accurate data acquisition within the IoT system.

[0033] Examples include some scenarios involving temperature acquisition: equipment monitoring scenarios, where the temperature of the equipment needs to be detected to determine its safety; and feedback control scenarios, where temperature data needs to be detected to perform feedback control based on the temperature data.

[0034] Regarding the terminal, it can be any type of electronic device with data processing capabilities.

[0035] Figure 2 This is a flowchart illustrating a sensor data error correction method based on big data, according to an exemplary embodiment. Figure 2 As shown, the method includes the following steps:

[0036] Step 201: Obtain the sensor data to be corrected, the temperature sensor information corresponding to the sensor data to be corrected, and the measurement object information corresponding to the sensor data to be corrected.

[0037] Step 202: Determine the error type based on the temperature sensor information and the measurement object information. The error type is used to characterize the relationship between the error influence weight of the temperature sensor information and the error influence weight of the measurement object information.

[0038] Step 203: Determine the error correction parameters based on the error type, the sensor data to be corrected, and the pre-trained first prediction model.

[0039] Step 204: Correct the sensor data to be corrected according to the error correction parameters to obtain the corrected sensor data.

[0040] In step 201, the sensor data to be corrected is temperature sensor data. This sensor data can be real-time or non-real-time temperature sensor data. It can include one or more temperature sensor data points; if multiple, each temperature sensor data point can be corrected using the same error correction method.

[0041] Information about the temperature sensor can be understood as information related to the temperature sensor itself. Information about the object being measured can be understood as information about the object being measured by the temperature sensor.

[0042] As an optional implementation, the temperature sensor information includes: protection tube information, temperature sensing element information, and measurement information, wherein the measurement information is used to characterize the measurement method of the temperature sensor; the measurement object information includes: the shape of the measurement object, the state of the measurement object, and the size of the measurement object.

[0043] For example, the protective tube information may include: protective tube material, protective tube attachments, and protective tube thickness. The temperature sensing element information may include: the diameter of the temperature sensing element's measuring end. Measurement information is used to characterize the temperature sensor's measurement method, such as insertion measurement, contact measurement, and non-contact measurement.

[0044] The material and thickness of the protective tube are fixed parameters and can be directly obtained. The deposits on the protective tube can be detected using methods such as image detection. It is understandable that this information about the protective tube will affect its thermal conductivity and cause measurement errors. For example, a thicker deposit will increase the overall thickness of the protective tube, reducing its thermal conductivity and leading to measurement errors.

[0045] Both the temperature sensing element information and the measurement information are fixed and can be directly obtained. It's understood that the smaller the diameter of the temperature sensing element, the shorter the thermal response time, and the lower the possibility of error. Different measurement methods can lead to different errors. For example, insertion-type measurements may cause errors due to improper insertion depth; contact-type measurements may cause errors due to excessively slow thermal response; and non-contact-type measurements may cause errors due to relative positional relationships. Therefore, both the temperature sensing element information and the measurement information can contribute to errors in the temperature sensor data.

[0046] For example, the form of the object being measured can include gaseous, liquid, and solid states. The state of the object being measured can include static and dynamic states. The dimensions of the object being measured can be represented by different parameters depending on the object being measured, such as diameter, length, width, and area.

[0047] It is understandable that different shapes and states of the object being measured may lead to inconsistencies between the object's temperature and that of the temperature sensor, thus causing measurement errors. Furthermore, different dimensions of the object being measured may affect the thermal response time of the temperature sensor, further contributing to measurement errors.

[0048] Therefore, in this embodiment of the present disclosure, the temperature sensor information and the measurement object information are first quantified to determine the error type. This error type can serve as indicative information for the first prediction model to help the first prediction model determine the error correction parameters more quickly and accurately.

[0049] Therefore, in step 202, based on the temperature sensor information and the measurement object information, the error type characterizing the error influence weight of the temperature sensor information and the error influence weight of the measurement object information is determined.

[0050] As an optional implementation, step 202 includes: if the measurement information indicates that the temperature sensor's measurement method is insertion measurement, determining the error influence weight of the temperature sensor information based on the insertion depth and protective tube information in the measurement information, and determining the error influence weight of the measured object information based on the shape and state of the measured object; if the measurement information indicates that the temperature sensor's measurement method is contact measurement, determining the error influence weight of the temperature sensor information based on the protective tube information and the temperature sensing element information, and determining the error influence weight of the measured object information based on the shape and size of the measured object; and determining the error type based on the error influence weight of the temperature sensor information and the error influence weight of the measured object information.

[0051] In this implementation, the error influence weights of temperature sensor information and measurement object information are first determined, and then the error type is determined based on the relationship between the error influence weights of temperature sensor information and measurement object information.

[0052] It's understandable that the selection of the temperature measurement point is crucial when using common insertion-type temperature sensors. For a manufacturing process, the location for temperature measurement must be typical and representative; otherwise, the measurement is meaningless. When the temperature sensor is inserted into the object being measured, some heat flow will occur along the length of the sensor. When the ambient temperature is low, heat loss will occur, causing a temperature discrepancy between the temperature sensor and the measured object, thus resulting in measurement errors.

[0053] Therefore, the measurement error caused by heat conduction is related to the insertion depth, which in turn is related to the material of the protective tube.

[0054] Depending on the material, metal protective tubes, due to their superior thermal conductivity, should be inserted deeper, while ceramic materials, with their better thermal insulation, can be inserted shallower. In some applications of engineering temperature measurement, the insertion depth also depends on whether the object being measured is stationary or flowing. For example, the temperature measurement of flowing liquids or high-speed airflows is not subject to these limitations, and the insertion depth can be shallower. Specific values ​​can be determined experimentally.

[0055] Therefore, when the measurement information characterizes the temperature sensor's measurement method as an insertion measurement, the error influence weight of the temperature sensor information can be determined based on the insertion depth and protection tube information in the measurement information.

[0056] In some embodiments, an error influence weighting table can be generated in advance through experiments. This table includes the influence weights corresponding to different insertion depths and different protective tube information. By looking up the table, the error influence weights corresponding to the insertion depth and protective tube information can be determined. Then, the error influence weights corresponding to the insertion depth and protective tube information are weighted and summed to determine the error influence weight of the temperature sensor information. The weights for the insertion depth and protective tube information can be determined based on actual conditions, and their sum can be 1.

[0057] Regarding the error impact weight of the measured object information, an error impact weight table can be generated in advance through experiments, and then the error impact weight of the measured object information can be determined by looking up the table.

[0058] In some embodiments, temperature sensor information and measurement object information can correspond to different error influence weight tables, or they can be integrated into the same error influence weight table, the latter being more accurate than the former.

[0059] Therefore, in order to determine the weight of the error impact, it is necessary to analyze a large amount of data, i.e., based on big data.

[0060] The basic principle of contact temperature measurement in temperature sensors is that the sensing element and the object being measured must reach a thermal equilibrium. Therefore, during temperature measurement, the two need to be kept in contact for a certain period to achieve this equilibrium. The length of this contact time is related to the thermal response time of the sensing element. The thermal response time depends significantly on the structure of the temperature sensor and the measurement conditions. Consequently, the temperature sensor may lag behind the rate of temperature change of the object being measured, or it may introduce measurement errors due to failure to reach thermal equilibrium.

[0061] In addition to the influence of the protective tube, the diameter of the measuring end of the temperature sensing element is also a major factor for temperature sensors. That is, the thinner the temperature sensing element and the smaller the diameter of the measuring end, the shorter its thermal response time will be.

[0062] Furthermore, in temperature sensors used at high temperatures, if the medium being measured is gaseous, some dust deposited on the surface of the protective tube will melt and melt onto the surface of the protective tube, making the protective tube thicker and increasing its thermal resistance.

[0063] If the object being measured is a molten substance, slag will accumulate on it during use, which not only increases the response time of the temperature sensor but also causes the indicated temperature to be lower, resulting in deviation.

[0064] Therefore, when the temperature sensor uses contact measurement to characterize the measured information, the error influence weight of the temperature sensor information is determined based on the information from the protective tube and the temperature sensing element. Furthermore, the error influence weight of the measured object information is determined based on the shape and size of the measured object.

[0065] The implementation method for determining the error influence weights of temperature sensor information and measurement object information can refer to the above embodiments, that is, it can also be determined by looking up a table.

[0066] In some embodiments, if the measurement information characterizes the temperature sensor's measurement method as non-contact measurement, the error influence weight of the measured object information can be 0. The error influence weight of the temperature sensor information can be determined based on the distance between the temperature sensor and the measured object. Specifically, the error influence weight can be determined according to the aforementioned error influence weight table, which will not be repeated here.

[0067] Furthermore, determining the error type based on the error influence weights of the temperature sensor information and the measurement object information can include: if the error influence weights of the temperature sensor information and the measurement object information are equal, the error type is determined as the first error type; if the error influence weights of the temperature sensor information are greater than the error influence weights of the measurement object information, the error type is determined as the second error type; and if the error influence weights of the temperature sensor information are less than the error influence weights of the measurement object information, the error type is determined as the third error type.

[0068] In this implementation, three error types are defined. The first error type indicates that the weights of the two errors are equal. The second error type indicates that the weight of the error influence of the temperature sensor information is greater than the weight of the error influence of the measured object information. The third error type indicates that the weight of the error influence of the temperature sensor information is less than the weight of the error influence of the measured object information.

[0069] In some embodiments, the three error types can be represented by corresponding identifiers, which can be vectors or characters. For example, the first error type is represented as 0, the second error type as 1, and the third error type as 2. As another example, the first error type is represented as [0,0,0], the second error type as [1,1,1], and the third error type as [2,2,2].

[0070] In step 203, error correction parameters are determined based on the error type, the sensor data to be corrected, and the pre-trained first prediction model.

[0071] In some embodiments, a pre-trained first prediction model is used to output error correction parameters based on the input error type and the sensor data to be corrected.

[0072] In some embodiments, the sensor data to be corrected can be first converted into vector form before being input into the first prediction model.

[0073] In some embodiments, the first prediction model may be a large language model or a neural network model, etc.

[0074] In some embodiments, the training process of the first prediction model may include: obtaining a first training dataset, the first training dataset including: first sample sensor data, error correction parameters corresponding to the first sample sensor data, and error types corresponding to the first sample sensor data; training the first prediction model to be trained according to the first training dataset to obtain a pre-trained first prediction model.

[0075] In this implementation, the first sample sensor data can be historically collected temperature sensor data. This historically collected temperature sensor data is corrected using an error correction parameter corresponding to the first sample sensor data. This error correction parameter can be determined manually or through other established error correction parameter determination methods. Furthermore, the error type corresponding to the first sample sensor data can be determined according to the error type determination method described in the aforementioned embodiments, or it can be determined manually or through other established determination methods.

[0076] Then, the first prediction model to be trained is trained using the first training dataset to obtain the pre-trained first prediction model, so that the first prediction model can output the pre-trained first prediction model based on the sensor data to be corrected under the indication of the error type.

[0077] Furthermore, in step 204, the sensor data to be corrected is corrected according to the error correction parameters to obtain the corrected sensor data.

[0078] In some embodiments, the correction method for the error correction parameter can be the default, for example: adding the error correction parameter to the sensor data to be corrected, or multiplying it by the error correction parameter to complete the correction.

[0079] In this embodiment of the disclosure, the correction effect of the error correction parameters can also be evaluated. Therefore, as an optional implementation, the method further includes: determining an error correction evaluation result based on the error type, error correction parameters, corrected sensor data, and a pre-trained second prediction model, wherein the error correction evaluation result is used to characterize the error correction effect of the error correction parameters; and feeding back the corrected sensor data and the error correction evaluation result.

[0080] In this implementation, the error correction effect is evaluated at the level of the corrected sensor data by combining the error type and error correction parameters.

[0081] In some embodiments, the first prediction model and the second prediction model may take different model types; or they may take the same model type.

[0082] Regarding the second prediction model, the corresponding training dataset may include: the second sample sensor data, the error type of the original sample sensor data corresponding to the second sample sensor data, the target error parameters, and the error correction evaluation labels.

[0083] In some embodiments, the second sample sensor data is corrected data corresponding to historically collected temperature sensor data.

[0084] In this embodiment of the disclosure, since a first prediction model and a second prediction model are used, in order to improve the training efficiency of the model and reduce the amount of data collected in the early stage, the training dataset of the second prediction model can be obtained based on the training dataset of the first prediction model.

[0085] Therefore, as an optional implementation, the training process of the second prediction model includes: obtaining a second training dataset, which includes: second sample sensor data, error type, target error parameter, and error correction evaluation label of the original sample sensor data corresponding to the second sample sensor data, wherein the original sample sensor data is sensor data selected from the first sample sensor data; and training the second prediction model to be trained according to the second training dataset to obtain a pre-trained second prediction model.

[0086] In this implementation, the original sample sensor data is sensor data selected from the first sample sensor data. Correspondingly, the error type, target error parameter, and error correction evaluation label of the original sample sensor data corresponding to the second sample sensor data can be determined in conjunction with the first prediction model.

[0087] Therefore, as an optional implementation, obtaining the second training dataset includes: determining the original sample sensor data from the first sample sensor data; inputting the original sample sensor data and the error type corresponding to the original sample sensor data into a pre-trained first prediction model to obtain the prediction error correction parameters output by the pre-trained first prediction model; determining the target error correction parameters and the first error correction evaluation label based on the error correction parameters corresponding to the original sample sensor data and the prediction error correction parameters; determining the second sample sensor data based on the target error correction parameters and the original sample sensor data; determining the error correction evaluation label based on the first error correction evaluation label; and generating the second training dataset based on the second sample sensor data, the error type of the original sample sensor data corresponding to the second sample sensor data, the target error correction parameters, and the error correction evaluation label.

[0088] Regarding the original sample sensor data, it can be obtained by sampling from the first sample sensor data, and the sampling method can refer to mature technologies in this field.

[0089] After obtaining the original sample sensor data, the original sample sensor data and the corresponding error type can be input into the pre-trained first prediction model to obtain the prediction error correction parameters output by the pre-trained first prediction model.

[0090] Therefore, in this embodiment, the first prediction model needs to be trained first, and then the second prediction model needs to be trained. Furthermore, it can be understood that since the original sample sensor data is determined from the first sample sensor data, the error type corresponding to the original sample sensor data is also known and can be directly obtained.

[0091] Based on the error correction parameters and prediction error correction parameters corresponding to the original sample sensor data, the target error correction parameters and the first error correction evaluation label can be determined.

[0092] For example, if the difference between the error correction parameter corresponding to the original sample sensor data and the predicted error correction parameter is large, then the error correction parameter corresponding to the original sample sensor data is determined as the target error correction parameter. If the difference between the error correction parameter corresponding to the original sample sensor data and the predicted error correction parameter is small, then the predicted error parameter is determined as the target error correction parameter. If they are equal, then the target error correction parameter can be any error correction parameter.

[0093] Specifically, if the absolute value of the difference between the error correction parameter corresponding to the original sample sensor data and the prediction error correction parameter is greater than a preset difference, it is considered a large difference. Otherwise, it is considered a small difference. The preset difference can be determined based on the accuracy of the temperature sensor. For example, if the sensor accuracy is ±1, the preset difference can be 1.

[0094] In some embodiments, a first error correction evaluation label is determined based on the difference between the error correction parameter corresponding to the original sample sensor data and the predicted error correction parameter.

[0095] For example, the accuracy of a sensor can be further subdivided. For instance, an accuracy of +1 can be divided into 0–0.5, 0.5–0.8, 0.8–1, and 1–∞. Then, the first error correction evaluation label corresponding to 0–0.5 could be 3, the first error correction evaluation label corresponding to 0.5–0.8 could be 2, the first error correction evaluation label corresponding to 0.8–1 could be 1, and the first error correction evaluation label corresponding to 1–∞ could be 0. Furthermore, a larger first error correction evaluation label indicates a better error correction evaluation effect.

[0096] In some embodiments, the first error correction evaluation label can be directly determined as the error correction evaluation label.

[0097] In other embodiments, determining the error correction evaluation label based on the first error correction evaluation label includes: feeding back the target error correction parameter and the original sample sensor data; receiving a second error correction evaluation label input by the user based on the fed-back target error correction parameter, the original sample sensor data and the preset error correction parameter range; and determining the error correction evaluation label based on the first error correction evaluation label and the second error correction evaluation label.

[0098] In this implementation, the target error correction parameters and the original sample sensor data can also be fed back to the user, who can then input a second error correction evaluation label based on the fed-back target error correction parameters, the original sample sensor data, and the preset error correction parameter range.

[0099] The preset error correction parameter range is a pre-defined range of error correction parameters that meets the requirements, which can constrain error correction. For example, if the error correction parameter is too large or too small, the error correction will be meaningless.

[0100] Therefore, users can evaluate the error correction effect based on experience and the preset error correction parameter range, and input a second error correction evaluation label.

[0101] Then, by weighted summing the first error correction evaluation label and the second error correction evaluation label, the final error correction evaluation label can be determined. The weight of the second error correction evaluation label is greater than the weight of the first error correction evaluation label.

[0102] Furthermore, based on the second sample sensor data, the error type of the original sample sensor data corresponding to the second sample sensor data, the target error correction parameters, and the error correction evaluation labels, a second training dataset can be generated.

[0103] Furthermore, the first prediction model can be optimized based on the error correction parameters and prediction error correction parameters corresponding to the original sample sensor data. For example, the differences between the error correction parameters and prediction error correction parameters corresponding to multiple original sample sensor data can be determined, resulting in multiple differences. If the average of these differences is less than a preset difference, no optimization is needed. If the average is greater than or equal to the preset difference, the first prediction model needs optimization. Optimization methods could include: training with a new training dataset; adjusting model parameters, etc.

[0104] Figure 3 This is a flowchart illustrating the training process of a first prediction model and a second prediction model according to an exemplary embodiment, such as... Figure 3 As shown, the first prediction model is trained based on the first training dataset.

[0105] For the first prediction model, a second training dataset is used for training, and this second training dataset is generated based on the first training dataset. Specifically, a portion of the training data is selected from the first training dataset, and then the target error correction parameters and error correction evaluation labels are determined. The determination of the error correction evaluation labels also incorporates manual annotation. Furthermore, the manual annotation is based on the target error correction parameters and the original sample sensor data.

[0106] Furthermore, the first prediction model can be optimized based on the prediction error correction parameters.

[0107] In this way, not only can the training of the first and second prediction models be completed, but the accuracy of the two models can also be guaranteed, and the amount of external data acquired can be reduced, thereby reducing the difficulty of model training.

[0108] In this embodiment of the disclosure, another implementation method for determining error correction parameters is also provided, in which the data input to the first prediction model needs to be determined first according to the error type.

[0109] Therefore, as an optional implementation, step 203 includes: if the error type is a first error type, inputting the sensor data to be corrected and the error type into a pre-trained first prediction model to obtain the error correction parameters output by the pre-trained first prediction model; if the error type is a second error type, determining the first sensor data to be corrected from the sensor data to be corrected, inputting the first sensor data to be corrected and the error type into the pre-trained first prediction model to obtain the error correction parameters output by the pre-trained first prediction model, wherein the acquisition time of the first sensor data to be corrected covers the target acquisition period; if the error type is a third error type, determining the second sensor data to be corrected from the sensor data to be corrected, inputting the second sensor data to be corrected and the error type into the pre-trained first prediction model to obtain the error correction parameters output by the pre-trained first prediction model, wherein the acquisition time of the second sensor data to be corrected covers multiple acquisition periods.

[0110] In this implementation, if the error type is the first error type, the sensor data to be corrected can be input into the first prediction model to obtain the error correction parameters.

[0111] If the error type is the second error type, then the sensor data to be corrected, whose acquisition time covers the target acquisition period, can be input into the first prediction model. The target acquisition period can be the first acquisition period, or both the first and second acquisition periods.

[0112] It's understandable that if the error from the temperature sensor has a greater weight than the error from the measured object, it means the error caused by the temperature sensor has a larger impact. Since the error caused by the temperature sensor typically only applies to the data collected initially, the error in later data collection is very small. Therefore, it's only necessary to determine the error correction parameters for the sensor data collected in the earlier acquisition cycles.

[0113] If the error type is the third type, then the sensor data to be corrected, covering multiple acquisition cycles, can be input into the first prediction model. Covering multiple acquisition cycles can be understood as acquiring a portion of the sensor data in each acquisition cycle.

[0114] It's understandable that if the error impact weight of temperature sensor information is less than that of the error impact weight of the measured object information, it indicates that the error caused by the measured object has a greater impact. Furthermore, errors caused by the measured object typically persist throughout the entire data acquisition cycle. Therefore, it's necessary to cover sensor data from multiple acquisition cycles to determine the error correction parameters.

[0115] Understandably, this implementation method is more suitable for non-real-time temperature sensor data because it may involve multiple acquisition cycles.

[0116] As can be seen from the embodiments described in this disclosure, the error type is first determined using temperature sensor information and the measurement object. Then, error correction parameters are determined using the error type, the sensor data to be corrected, and a pre-trained first prediction model. Finally, the sensor data to be corrected is corrected according to the error correction parameters to obtain the corrected sensor data. Since the error type can characterize the relationship between the error influence weight of the temperature sensor information and the error influence weight of the measurement object information, the error type can be regarded as an influence weight of the sensor data to be corrected. Based on this error type, the error correction parameters determined by the pre-trained first prediction model have high accuracy. Furthermore, the error correction parameters can be quickly determined through the pre-trained first prediction model. Therefore, this technical solution can achieve effective and accurate correction of temperature sensor data.

[0117] Figure 4 This is a structural block diagram of a sensor data error correction device 400 based on big data, as shown in an exemplary embodiment. Figure 4 As shown, the device includes:

[0118] The acquisition module 401 is used to acquire the sensor data to be corrected, the temperature sensor information corresponding to the sensor data to be corrected, and the measurement object information corresponding to the sensor data to be corrected.

[0119] The correction module 402 is used to determine the error type based on the temperature sensor information and the measurement object information, wherein the error type is used to characterize the relationship between the error influence weight of the temperature sensor information and the error influence weight of the measurement object information; determine the error correction parameters based on the error type, the sensor data to be corrected and the pre-trained first prediction model; and correct the sensor data to be corrected based on the error correction parameters to obtain the corrected sensor data.

[0120] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0121] Figure 5 This is a block diagram illustrating an electronic device 500 according to an exemplary embodiment. For example... Figure 5 As shown, the electronic device 500 may include a processor 501 and a memory 502. The electronic device 500 may also include one or more of a multimedia component 503, an input / output (I / O) interface 504, and a communication component 505.

[0122] The processor 501 controls the overall operation of the electronic device 500 to complete all or part of the steps in the aforementioned big data-based sensor data error correction method. The memory 502 stores various types of data to support the operation of the electronic device 500. This data may include, for example, instructions for any application or method operating on the electronic device 500, and application-related data such as contact data, sent and received messages, images, audio, video, etc. The memory 502 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. Multimedia component 503 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 502 or transmitted via communication component 505. The audio component also includes at least one speaker for outputting audio signals. I / O interface 504 provides an interface between processor 501 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical buttons. Communication component 505 is used for wired or wireless communication between the electronic device 500 and other devices. Wireless communication may include Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination of these. Therefore, the corresponding communication component 505 may include a Wi-Fi module, a Bluetooth module, or an NFC module.

[0123] In an exemplary embodiment, the electronic device 500 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described big data-based sensor data error correction method.

[0124] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided. When executed by a processor, these program instructions implement the steps of the above-described big data-based sensor data error correction method. For example, the computer-readable storage medium may be the memory 502 including the program instructions, which may be executed by the processor 501 of the electronic device 500 to complete the above-described big data-based sensor data error correction method.

[0125] In another exemplary embodiment, a computer program product is also provided, which includes a computer program executable by a processor, which, when executed by the processor, implements the steps of the above-described big data-based sensor data error correction method.

[0126] The preferred embodiments of this disclosure have been described in detail above with reference to the accompanying drawings. However, this disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this disclosure, various simple modifications can be made to the technical solutions of this disclosure, and these simple modifications all fall within the protection scope of this disclosure.

[0127] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

[0128] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.

Claims

1. A sensor data error correction method based on big data, characterized in that, include: Acquire the sensor data to be corrected, the temperature sensor information corresponding to the sensor data to be corrected, and the measurement object information corresponding to the sensor data to be corrected; Based on the temperature sensor information and the measurement object information, the error type is determined. The error type is used to characterize the relationship between the error influence weight of the temperature sensor information and the error influence weight of the measurement object information. Based on the error type, the sensor data to be corrected, and the pre-trained first prediction model, the error correction parameters are determined; The sensor data to be corrected is corrected according to the error correction parameters to obtain the corrected sensor data; The temperature sensor information includes: protective tube information, temperature sensing element information, and measurement information, wherein the measurement information characterizes the measurement method of the temperature sensor; the measurement object information includes: measurement object shape, measurement object state, and measurement object size; determining the error type based on the temperature sensor information and the measurement object information includes: if the measurement information characterizes the temperature sensor measurement method as insertion measurement, determining the error influence weight of the temperature sensor information based on the insertion depth in the measurement information and the protective tube information, and determining the error influence weight of the measurement object information based on the measurement object shape and the measurement object state; if the measurement information characterizes the temperature sensor measurement method as contact measurement, determining the error influence weight of the temperature sensor information based on the protective tube information and the temperature sensing element information, and determining the error influence weight of the measurement object information based on the measurement object shape and the measurement object size; and determining the error type based on the error influence weights of the temperature sensor information and the measurement object information. The error types include a first error type, a second error type, and a third error type. The first error type indicates that the error influence weight of the temperature sensor information is equal to the error influence weight of the measured object information. The second error type indicates that the error influence weight of the temperature sensor information is greater than the error influence weight of the measured object information. The third error type indicates that the error influence weight of the temperature sensor information is less than the error influence weight of the measured object information. Determining the error correction parameters based on the error type, the sensor data to be corrected, and the pre-trained first prediction model includes: if the error type is the first error type, inputting the sensor data to be corrected and the error type into the pre-trained first prediction model to obtain the error output by the pre-trained first prediction model. Correction parameters: If the error type is the second error type, determine the first sensor data to be corrected from the sensor data to be corrected, input the first sensor data to be corrected and the error type into the pre-trained first prediction model, and obtain the error correction parameters output by the pre-trained first prediction model, wherein the acquisition time of the first sensor data to be corrected covers the target acquisition period in multiple acquisition periods; If the error type is the third error type, determine the second sensor data to be corrected from the sensor data to be corrected, input the second sensor data to be corrected and the error type into the pre-trained first prediction model, and obtain the error correction parameters output by the pre-trained first prediction model, wherein the acquisition time of the second sensor data to be corrected covers the multiple acquisition periods.

2. The sensor data error correction method based on big data according to claim 1, characterized in that, The step of determining the error type based on the error influence weight of the temperature sensor information and the error influence weight of the measured object information includes: If the error influence weight of the temperature sensor information is equal to the error influence weight of the measured object information, the error type is determined as the first error type; If the error influence weight of the temperature sensor information is greater than the error influence weight of the measured object information, the error type is determined as the second error type. If the error influence weight of the temperature sensor information is less than the error influence weight of the measured object information, the error type is determined as the third error type.

3. The sensor data error correction method based on big data according to claim 1, characterized in that, The big data-based sensor data error correction method also includes: Based on the error type, the error correction parameters, the corrected sensor data, and the pre-trained second prediction model, an error correction evaluation result is determined, which is used to characterize the error correction effect of the error correction parameters. The corrected sensor data and the error correction evaluation results are fed back.

4. The sensor data error correction method based on big data according to claim 3, wherein the pre-trained first prediction model is used to output the error correction parameters according to the input error type and the sensor data to be corrected, and the sensor data error correction method based on big data further includes: Obtain a first training dataset, which includes: first sample sensor data, error correction parameters corresponding to the first sample sensor data, and error type corresponding to the first sample sensor data; The first prediction model to be trained is trained based on the first training dataset to obtain the pre-trained first prediction model.

5. The sensor data error correction method based on big data according to claim 4, wherein the pre-trained second prediction model is used to output the error correction evaluation result based on the input error type, the error correction parameters, and the corrected sensor data, and the sensor data error correction method based on big data further includes: Obtain a second training dataset, which includes: second sample sensor data, error type, target error parameter, and error correction evaluation label of the original sample sensor data corresponding to the second sample sensor data, wherein the original sample sensor data is sensor data selected from the first sample sensor data; The second prediction model to be trained is trained based on the second training dataset to obtain the pre-trained second prediction model.

6. The sensor data error correction method based on big data according to claim 5, characterized in that, The process of obtaining the second training dataset includes: The original sample sensor data is determined from the first sample sensor data; The original sample sensor data and the error type corresponding to the original sample sensor data are input into the pre-trained first prediction model to obtain the prediction error correction parameters output by the pre-trained first prediction model. Based on the error correction parameters corresponding to the original sample sensor data and the prediction error correction parameters, the target error correction parameters and the first error correction evaluation label are determined; The second sample sensor data is determined based on the target error correction parameters and the original sample sensor data; The error correction evaluation label is determined based on the first error correction evaluation label; The second training dataset is generated based on the second sample sensor data, the error type of the original sample sensor data corresponding to the second sample sensor data, the target error correction parameter, and the error correction evaluation label.

7. The sensor data error correction method based on big data according to claim 6, characterized in that, The step of determining the error correction evaluation label based on the first error correction evaluation label includes: Feedback of the target error correction parameters and the original sample sensor data; Receive a second error correction evaluation label input by the user based on the target error correction parameters, the original sample sensor data, and the preset error correction parameter range; The error correction evaluation label is determined based on the first error correction evaluation label and the second error correction evaluation label.

8. A sensor data error correction system based on big data, characterized in that, include: Temperature sensor, the temperature sensor being used to collect temperature data of the object being measured; A terminal, which is connected to the temperature sensor; The temperature sensor is used to transmit the temperature data of the measured object as the sensor data to be corrected to the terminal, and the terminal is used to execute the sensor data error correction method based on big data as described in any one of claims 1 to 7.

Images