Smart city distribution monitoring system based on Internet of Things

Abstract

The invention relates to the technical field of temperature monitoring, in particular to a smart city distribution monitoring system based on the Internet of Things. The system comprises a historical data acquisition module for acquiring a historical temperature time sequence data segment; the to-be-detected data segment acquisition module is used for acquiring the abnormality of the data points and determining suspected abnormal points through the fluctuation change degree of the data fluctuation in the historical data segment in combination with the distribution deviation condition of the data points in the fluctuation, and determining the abnormal points according to the abnormality distribution condition of the data points in the preset moving average window; updating the data value of the suspected abnormal point to obtain a to-be-detected data segment; and the temperature monitoring module is used for obtaining a predicted value at each moment for temperature monitoring according to the abnormality of the data points in the data segment to be detected in combination with the data value and the abnormality distribution condition at each moment. According to the method, the more accurate temperature prediction value is obtained by adjusting the abnormal condition in the historical data, so that the temperature monitoring process is more reliable, and the distribution safety is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature monitoring, and particularly to an intelligent city distribution monitoring system based on the Internet of Things. Background Art

[0002] The central kitchen in an intelligent city is a model of the catering manufacturing industry. It adopts a huge operation room, and each link such as procurement, vegetable selection, cutting, and seasoning is responsible by a dedicated person. The semi-finished products and the prepared seasonings are transported in a unified way and delivered to the branch stores within the specified time. With the increasing demand in the central kitchen industry, how to reduce the possibility of deterioration of the manufactured dishes during the delivery process and ensure food safety is an important research direction.

[0003] Since the delivery has a unified transportation method, the temperature of the refrigerated truck during the future dish delivery can be predicted by analyzing the relationship between the historical delivery temperature and the delivery time. However, due to the possible existence of certain abnormal temperature data in the historical time period, these abnormal data will affect the prediction. The commonly used SMA (Simple Moving Average) moving average method smooths the abnormal data according to the trend. However, the SMA moving average method uses the same weight for all data in the moving average window for averaging. When the abnormality is relatively complex, it cannot effectively smooth the data in the historical time period, resulting in a low accuracy of the obtained temperature prediction value and insufficient reliability for monitoring, and further unable to guarantee the delivery safety. Summary of the Invention

[0004] In order to solve the technical problems in the prior art that the accuracy of the obtained temperature prediction value is relatively low, the reliability of monitoring is insufficient, and further the delivery safety cannot be guaranteed, the purpose of the present invention is to provide an intelligent city distribution monitoring system based on the Internet of Things, and the specific technical solution adopted is as follows:

[0005] The present invention provides an intelligent city distribution monitoring system based on the Internet of Things, and the system includes:

[0006] A historical data acquisition module, configured to acquire a preset number of historical temperature time series data segments;

[0007] A data segment to be detected acquisition module, configured to obtain the abnormality degree of each data point in each historical temperature time series data segment according to the fluctuation change distribution of each data fluctuation and the distribution deviation of each data point in the corresponding data fluctuation; determine the suspected abnormal points through the abnormality degree of the data points in each historical temperature time series data segment; update the data value of each suspected abnormal point by combining the moving average method according to the abnormal degree distribution ratio of all data points in the corresponding preset moving average window for each suspected abnormal point in each historical temperature time series data segment, and obtain the data segment to be detected;

[0008] A temperature monitoring module, which is used to obtain the abnormality degree of each data point in each data segment to be detected; obtain the predicted value of each moment according to the data values and the abnormality degree distribution of the data points in all data segments to be detected corresponding to each moment; and perform temperature monitoring according to the predicted value of each moment.

[0009] Further, the obtaining of the abnormality degree of each data point includes:

[0010] Successively take each historical temperature time series data segment as the target data segment, and obtain the temperature data curve in the target data segment; obtain the extreme points in the temperature data curve, and take the curve between every two adjacent extreme points as the data fluctuation.

[0011] According to the change degree of the data points in each data fluctuation, obtain the fluctuation degree of each data fluctuation; calculate the average value of the fluctuation degrees of all data fluctuations in the target data segment to obtain the average fluctuation degree of the target data segment; normalize the difference between the fluctuation degree of each data fluctuation and the average fluctuation degree to obtain the abnormality index of each data fluctuation.

[0012] Calculate the average value of the data values of all data points in the target data segment to obtain the average data value of the target data segment; for any data point in the target data segment, normalize the difference between the data value of this data point and the average data value to obtain the abnormality possibility of this data point.

[0013] Multiply the abnormality possibility of this data point by the abnormality index of the data fluctuation where this data point is located to obtain the abnormality degree of this data point.

[0014] Further, the obtaining of the fluctuation degree of each data fluctuation according to the change degree of the data points in each data fluctuation includes:

[0015] For any data fluctuation, calculate the difference between the data values between the two extreme points corresponding to this data fluctuation to obtain the extreme value difference of this data fluctuation; calculate the difference between the times between the two extreme points corresponding to this data fluctuation to obtain the time difference of this data fluctuation.

[0016] Take the ratio of the extreme value difference of this data fluctuation to the time difference as the fluctuation degree of this data fluctuation.

[0017] Further, the method for obtaining the suspected abnormal points includes:

[0018] Take the average value of all the abnormality degrees in each historical temperature time series data segment as the abnormality evaluation index of each historical temperature time series data segment.

[0019] When the difference between the abnormality degree of a data point and the abnormality evaluation index of the historical temperature time series data where it is located is greater than a preset abnormality threshold, the corresponding data point is regarded as a suspected abnormal point.

[0020] Further, the method for obtaining the data segment to be detected includes:

[0021] For any suspected abnormal point in any historical temperature time series data segment, the preset moving average window corresponding to the suspected abnormal point is used as the detection window;

[0022] Calculate the sum value of the cumulative value of the abnormality degrees of all data points in the detection window and the abnormality degree of the suspected abnormal point to obtain the total abnormality value of the suspected abnormal point; calculate the ratio of the abnormality degree of each data point in the detection window to the total abnormality value, perform negative correlation mapping and normalization processing to obtain the allocation weight of each data point in the detection window;

[0023] In the detection window, according to the allocation weight of each data point, use the SMA moving average method to obtain a new data value for the suspected abnormal point; the historical temperature time series data segment with the data values of all suspected abnormal points updated is used as the data segment to be detected.

[0024] Further, the step of using the SMA moving average method according to the allocation weight of each data point in the detection window to obtain a new data value for the suspected abnormal point includes:

[0025] Based on the SMA moving average method, according to the allocation weight and data value of each data point in the detection window, obtain the moving average value in the detection window; calculate the average value of the difference between the data value of the data point in the detection window and the moving average value to obtain the adjustment value of the detection window;

[0026] Take the sum value of the moving average value and the adjustment value as the new data value of the corresponding suspected abnormal point.

[0027] Further, the method for obtaining the predicted value includes:

[0028] For any moment, calculate the sum value of the abnormality degrees of the data points corresponding to all data segments to be detected at this moment as the detection sum value; calculate the ratio of the abnormality degree of the data point corresponding to each data segment to be detected at this moment to the detection sum value, perform negative correlation mapping and normalization processing to obtain the prediction weight of the data point corresponding to each data segment to be detected at this moment;

[0029] Calculate the product of the prediction weight of the data point corresponding to each data segment to be detected at this moment and the corresponding data value to obtain the adjusted prediction value of the data point corresponding to each data segment to be detected at this moment; calculate the average value of all adjusted prediction values at this moment to obtain the predicted value corresponding to this moment.

[0030] Further, the temperature monitoring based on the predicted values at each moment includes:

[0031] Obtain the actual value corresponding to the temperature data at the current moment, and use the numerical difference between the actual value at the current moment and the predicted value at the current moment as the monitoring evaluation value;

[0032] When the monitoring evaluation values at a continuous preset number of moments before the current moment are greater than the preset monitoring threshold, record the monitoring status at the current moment as an abnormal state; otherwise, the monitoring status is a normal state.

[0033] Further, the obtaining of the temperature data curve in the target data segment includes:

[0034] Perform polynomial fitting on the target data segment using the least squares method to obtain the temperature data curve.

[0035] Further, the method for obtaining the extreme points in the temperature data curve uses Newton's method.

[0036] The present invention has the following beneficial effects:

[0037] The present invention analyzes the abnormality of each fluctuation through the degree of fluctuation change of the data fluctuations in the historical data segment, and combines the distribution deviation of each data point in the fluctuation. The abnormality degree of each data point is comprehensively obtained through the deviation of the data point itself and the abnormality of the fluctuation where it is located, and the suspected abnormal points where abnormal situations may occur are determined for more accurate smoothing in the future. Further, smooth the data values of each suspected abnormal point. Through the distribution of the abnormality degrees of the data points in the preset moving average window, that is, taking the abnormality situation of each data point in the window as the weight to analyze the trend situation, predict the data value at the suspected abnormal point, update the data value of the suspected abnormal point, and obtain a more accurate data segment to be detected representing the historical relationship between the distribution temperature and the distribution time, making the predicted value for subsequent prediction more accurate. Further, obtain the abnormality degree of each data point in each data segment to be detected. At this time, the abnormality degree represents the credibility of each data point in the corresponding data segment to be detected. Combining the data values and the distribution of the abnormality degrees corresponding to all data segments to be detected at each moment, finally obtain a more accurate predicted value corresponding to each moment for temperature monitoring. The present invention adjusts the abnormal data situation in the historical data, combines the abnormal situation to obtain a more accurate temperature prediction value, makes the process of temperature monitoring more reliable, and thus improves the safety of distribution. Description of the Drawings

[0038] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0039] Figure 1 The structure diagram of a smart city distribution monitoring system based on the Internet of Things provided by an embodiment of the present invention. Detailed implementation manners

[0040] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following, in combination with the drawings and preferred embodiments, will describe in detail the specific implementation manners, structures, features and effects of a smart city distribution monitoring system based on the Internet of Things proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0041] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0042] The following will specifically describe the specific solution of a smart city distribution monitoring system based on the Internet of Things provided by the present invention in conjunction with the drawings.

[0043] Please refer to Figure 1 , which shows the structure diagram of a smart city distribution monitoring system based on the Internet of Things provided by an embodiment of the present invention. The system includes: a historical data acquisition module 101, a data segment to be detected acquisition module 102, and a temperature monitoring module 103.

[0044] The historical data acquisition module 101 is used to acquire a preset number of historical temperature time series data segments.

[0045] The meals produced in the central kitchen are delivered by refrigerated trucks. During monitoring, the monitoring is also based on the temperature obtained in the refrigerated trucks to prevent problems such as bacterial growth and food spoilage caused by abnormal temperature control, which brings potential quality and safety hazards. In the embodiment of the present invention, the temperature time series data of the refrigerated truck during the entire transportation process is collected by an in-vehicle temperature sensor, and the collection frequency is set to once every 3 minutes. Among them, the temperature time series data is to map all the collected temperature data into the time series space, and the time series space is a time series coordinate system, where the horizontal axis represents time and the vertical axis represents the data value corresponding to the temperature. It should be noted that the specific data collection process is a data means well-known to those skilled in the art and will not be elaborated here.

[0046] Since in the embodiments of the present invention, the daily distribution process of the refrigerated truck is a unified distribution process, the temperature time series data within the corresponding time period of a day is used as a historical temperature time series data segment, and a preset number of historical temperature time series data segments are obtained. In the embodiments of the present invention, the preset number is set to 7, that is, the temperature time series data for 7 days is obtained from the day to be predicted for prediction. The specific sampling frequency, preset number, and time period selection can be adjusted by the implementer according to the specific implementation situation and are not limited herein.

[0047] The data segment to be detected acquisition module 102 is configured to obtain the abnormality degree of each data point in each historical temperature time series data segment according to the fluctuation change distribution of each data fluctuation and the distribution deviation of each data point in the corresponding data fluctuation; determine suspected abnormal points through the abnormality degree of the data points in each historical temperature time series data segment; and update the data value of each suspected abnormal point according to the abnormality degree distribution ratio of all data points in the corresponding preset moving average window in each historical temperature time series data segment, and combine the moving average method to obtain the data segment to be detected.

[0048] Since the temperature time series data of the refrigerated truck may have some abnormal low or high temperature data due to reasons such as changes in the external temperature. For example, during the actual distribution process, the opening and closing of the door during unloading, changes in the external temperature, or refrigeration machine failures can all cause abnormal temperatures. Therefore, it is necessary to correct the data in the historical temperature time series data segment. First, it is obtained by analyzing the abnormality degree of the data points in the historical temperature time series data segment.

[0049] In each historical temperature time series data segment, the abnormality degree of each data point is obtained according to the fluctuation change distribution of each data fluctuation and the distribution deviation of each data point in the corresponding data fluctuation. Preferably, each historical temperature time series data segment is sequentially used as the target data segment, and the same analysis is performed on each historical temperature time series data to obtain the temperature data curve in the target data segment. In the embodiments of the present invention, the least squares method can be used to perform polynomial fitting on the target data segment to obtain the temperature data curve. The method of performing polynomial fitting curve by the least squares method is a well-known technical means to those skilled in the art and will not be elaborated herein.

[0050] Further, the Newton method is used to obtain the extreme points in the temperature data curve. In other embodiments of the present invention, the gradient descent method or the method of taking derivatives can also be used to obtain the extreme points. The Newton method, the gradient descent method, or the method of taking derivatives are all well-known technical means to those skilled in the art and are not limited herein. The curve between every two adjacent extreme points is used as the data fluctuation, and the abnormal situation of the data change is reflected through the data fluctuation.

[0051] Under normal circumstances, the temperature in the refrigerated truck is usually stable and will also show relatively stable fluctuations in the curve. Abnormal data will cause more changes in the data fluctuations. For example, during the process of opening and closing the door, when the door opening time is short, the temperature rise caused by heat exchange may not be particularly obvious, and the fluctuation change shown in the curve has a relatively small change compared to the normal fluctuation. However, when the door opening time is long, the heat exchange may be more intense, resulting in a significant increase in the temperature inside the refrigerated truck, and the fluctuation change shown in the curve has a relatively large change compared to the normal fluctuation. In addition, if the refrigeration unit is running during the door opening period of the refrigerated truck, then due to the loss of cold air, the temperature inside the carriage may rise even higher, and the fluctuation change shown in the curve will also have a large change compared to the normal fluctuation.

[0052] Furthermore, according to the degree of change of the data points in each data fluctuation, the fluctuation degree of each data fluctuation is obtained, and the fluctuation change degree of each data fluctuation is reflected through the fluctuation degree. In an embodiment of the present invention, for any data fluctuation, the difference in data values between the two extreme points corresponding to the data fluctuation is calculated to obtain the extreme value difference of the data fluctuation, and the difference in time between the two extreme points corresponding to the data fluctuation is calculated to obtain the time difference of the data fluctuation. The overall change degree is reflected by the difference between the data values and the time change difference, and the ratio of the extreme value difference of the data fluctuation to the time difference is used as the fluctuation degree of the data fluctuation. In the embodiment of the present invention, the specific expression of the fluctuation degree is:

[0053]

[0054] In the formula, μ n represents the fluctuation degree of the nth data fluctuation, h n1 represents the data value of the first extreme point corresponding to the nth data fluctuation, h n2 represents the data value of the second extreme point corresponding to the nth data fluctuation, t n1 represents the time of the first extreme point corresponding to the nth data fluctuation, t n2 represents the time of the second extreme point corresponding to the nth data fluctuation, and || represents the absolute value extraction function.

[0055] Among them, |h n1 -h n2 | represents the extreme value difference of the nth data fluctuation, |t n1 -t n2|Denoted as the time difference of the nth data fluctuation, since the time difference must exist, the ratio will not have a situation where the denominator is zero and the formula becomes meaningless. When the degree of fluctuation is larger, it indicates that the overall data change degree in the data fluctuation is larger. In other embodiments of the present invention, the average value of the slopes corresponding to all data points in each data fluctuation can also be calculated as the degree of fluctuation to reflect the data change situation in the data fluctuation, which is not limited herein.

[0056] Further, calculate the average value of the degrees of fluctuation of all data fluctuations in the target data segment to obtain the average degree of fluctuation of the target data segment. The average degree of fluctuation reflects the overall fluctuation change situation in the target data segment. Normalize the difference between the degree of fluctuation of each data fluctuation and the average degree of fluctuation to obtain the anomaly index of each data fluctuation. When the difference is larger, it indicates that the degree of fluctuation corresponding to the data fluctuation has a larger difference relative to the overall fluctuation change situation, and the anomaly of this data fluctuation is higher.

[0057] Further, calculate the average value of the data values of all data points in the target data segment to obtain the average data value of the target data segment, and analyze each data point through the average data value. For any data point in the target data segment, the analysis method for each data point is the same. Normalize the difference between the data value of this data point and the average data value to obtain the anomaly possibility of this data point. When the difference is larger, it indicates that the data value of the data point is less similar to the overall data value, and the possibility that it may be abnormal itself is larger. Therefore, the anomaly possibility is larger.

[0058] Considering the anomaly of the data fluctuation where the data point itself is located, multiply the anomaly possibility of this data point by the anomaly index of the data fluctuation where this data point is located to obtain the anomaly degree of this data point. In the embodiments of the present invention, the specific expression of the anomaly degree is:

[0059]

[0060] In the formula, P i Denotes the anomaly degree of the ith data point, h i Denotes the data value of the ith data point, M denotes the total number of data points in the target data segment, μ i,n Denotes the degree of fluctuation of the nth data fluctuation where the ith data point is located, μ n Denotes the degree of fluctuation of the nth data fluctuation, N denotes the total number of data fluctuations in the target data segment, || denotes the absolute value extraction function, norm() denotes the normalization function. It should be noted that normalization is a well-known technical means in the art, and the selection of the normalization function can be linear normalization or standard normalization, etc. The specific normalization method is not limited herein.

[0061] Among them, Represented as the average data value of the target data segment, Represented as the anomaly possibility of the i-th data point, Represented as the average fluctuation degree of the target data segment, Represented as the anomaly index of the n-th data fluctuation where the i-th data point is located. When the anomaly index of the data fluctuation where the data point is located is larger, the anomaly possibility of the data point is greater, and the data point is more likely to be an abnormal data point. Therefore, the anomaly degree is greater.

[0062] After obtaining the anomaly degree of each data point, the data points with a larger anomaly degree are screened out for smoothing processing, that is, the suspected anomaly points are determined through the anomaly degree of the data points in each historical temperature time series data segment. Preferably, the average value of all anomaly degrees in each historical temperature time series data segment is used as the anomaly evaluation index of each historical temperature time series data segment. Since abnormal fluctuations will cause a certain abnormal impact on all data points, the data points with a large anomaly degree are screened out through the anomaly evaluation index. When the difference between the anomaly degree of the data point and the anomaly evaluation index of the historical temperature time series data where it is located is greater than the preset anomaly threshold, it indicates that the abnormal change of the data point in the historical temperature time series data is more obvious, and the corresponding data point is used as a suspected anomaly point. In the embodiment of the present invention, the preset anomaly threshold is set to 0.5, and the specific value can be screened by the implementer according to the specific implementation situation, which will not be elaborated here.

[0063] In other embodiments of the present invention, the suspected anomaly points can also be directly screened out by only comparing the anomaly degree of the data point with the threshold, which is not limited here.

[0064] Furthermore, the suspected anomaly points can be smoothed by the SMA moving average method according to the data trend. The SMA moving average method belongs to the method of analyzing data trends and can also be used for data prediction, that is, the true data value of the suspected anomaly point can be predicted according to the change situation of the previous data points of the suspected anomaly point. The specific process of using the SMA moving average method for prediction includes: calculating the moving average value, that is, obtaining the moving average value in the moving average window using the SMA moving average method. Calculating the deviation, that is, calculating the difference between the data value of each data point in the moving average window and the moving average value. Calculating the average deviation, that is, calculating the average value of all deviations in the moving average window. Obtaining the predicted value, that is, adding the average deviation to the moving average value to obtain the predicted value of the current data point. It should be noted that the SMA moving average method is a well-known technical means for those skilled in the art and will not be elaborated here.

[0065] Among them, since the SMA moving average method uses the same weight for all data points during calculation and does not take into account the certain abnormal conditions of the data points, the greater the degree of abnormality of a data point, the lower its credibility. Therefore, by obtaining the degree of abnormality to adjust the weights of different data points during calculation, a more accurate predicted value of each suspected abnormal point is obtained, and then a data segment to be detected for temperature prediction is formed. That is, according to the proportion of the degree of abnormality distribution of all data points in the corresponding preset moving average window for each suspected abnormal point in each historical temperature time series data segment, the data value of each suspected abnormal point is updated in combination with the moving average method to obtain the data segment to be detected. In the embodiment of the present invention, the preset moving average window is set to a window size composed of the first 7 data points in the time series of data points. Specifically, the implementer can adjust the window size according to the specific implementation situation.

[0066] Preferably, for any suspected abnormal point in any historical temperature time series data segment, the corresponding preset moving average window of the suspected abnormal point is used as the detection window. Calculate the sum value of the cumulative value of the degree of abnormality of all data points in the detection window and the degree of abnormality of the suspected abnormal point to obtain the total degree of abnormality of the suspected abnormal point. Calculate the ratio of the degree of abnormality of each data point in the detection window to the total degree of abnormality, and perform negative correlation mapping and normalization processing to obtain the allocation weight of each data point in the detection window. The credibility is reflected by the proportion degree of the degree of abnormality. In the embodiment of the present invention, the expression of the allocation weight is:

[0067]

[0068] In the formula, Q t,h represents the allocation weight of the h-th data point in the preset moving average window corresponding to the t-th suspected abnormal point, P h represents the degree of abnormality of the h-th data point, H t represents the total number of data points in the preset moving average window corresponding to the t-th suspected abnormal point, P t represents the degree of abnormality of the t-th suspected abnormal point, and exp represents the exponential function with the natural constant as the base.

[0069] Among them, represents the total degree of abnormality corresponding to the t-th suspected abnormal point. When the proportion of the degree of abnormality of a data point is larger, it indicates that the possible abnormal situation of the data point is larger compared with other data points, and its credibility is lower than that of other data points. Therefore, a smaller allocation weight is given.

[0070] In the detection window, according to the assigned weight of each data point, the SMA moving average method is used to obtain a new data value for the suspected abnormal point. In an embodiment of the present invention, based on the SMA moving average method, according to the assigned weight and data value of each data point in the detection window, the moving average value in the detection window is obtained. The moving average value represents the data trend situation corresponding to the suspected abnormal point. The average value of the difference between the data value of the data point in the detection window and the moving average value is calculated to obtain the adjustment value of the detection window. The sum value of the moving average value and the adjustment value is used as the new data value corresponding to the suspected abnormal point. It should be noted that the calculation of the moving average value is a well-known calculation method in the SMA moving average method, and the process of obtaining the new data value is the above-mentioned prediction process according to the SMA moving average method, which will not be specifically described here.

[0071] The historical temperature time series data segment with the data values of all suspected abnormal points updated is used as the data segment to be detected, and a preset number of data segments to be detected are obtained. At this time, the abnormal data in the data segment to be detected has been smoothed, and its credibility and the accuracy of reflecting the relationship between temperature and time change are relatively high, and further data prediction and monitoring are carried out.

[0072] The temperature monitoring module 103 is used to obtain the abnormality degree of each data point in each data segment to be detected; according to the data value and abnormality degree distribution of the data points in all data segments to be detected corresponding to each moment, the predicted value of each moment is obtained; temperature monitoring is carried out according to the predicted value of each moment.

[0073] Since the data value of the data point in the data point to be detected has been updated, the abnormality degree of each data point is recalculated. The calculation method is the same as the method for obtaining the abnormality degree of each data point in the data segment acquisition module 102. At this time, the abnormality degree of the data point reflects the credibility of each data point. The greater the abnormality degree, the lower the credibility of the data point.

[0074] According to the data value and abnormality degree distribution of the data points in all data segments to be detected corresponding to each moment, the predicted value of each moment is obtained. Since the distribution link is unified during the distribution process, the data values corresponding to the same moment in each data segment have the same distribution situation, and the data values at the same moment in all data segments to be detected are combined for prediction.

[0075] Preferably, for any moment, the sum value of the abnormality degrees of the data points corresponding to all data segments to be detected at this moment is calculated as the detection sum value. The ratio of the abnormality degree of the data point corresponding to each data segment to be detected at this moment to the detection sum value is subjected to negative correlation mapping and normalization processing to obtain the prediction weight of the data point corresponding to each data segment to be detected at this moment. That is, at the same moment, the prediction weight is obtained according to the proportion of the abnormality degree corresponding to the data point. The smaller the abnormality degree, the greater the credibility, and the greater the corresponding prediction weight.

[0076] Calculate the product of the predicted weight and the corresponding data value of each data point corresponding to the data segment to be detected at this moment, obtain the adjusted predicted value of each data point corresponding to the data segment to be detected at this moment, calculate the average value of all adjusted predicted values at this moment, obtain the predicted value corresponding to this moment, that is, perform weighted averaging on the data values of the data points at the same moment according to the predicted weight, and obtain the predicted value of each moment. In the embodiment of the present invention, the expression of the predicted value is:

[0077]

[0078] In the formula, Y v represents the predicted value corresponding to the v-th moment, S represents the total number of data segments to be detected, h c,v represents the data value of the data point corresponding to the c-th data segment to be detected at the v-th moment, P c,v represents the abnormality degree of the data point corresponding to the c-th data segment to be detected at the v-th moment, and exp represents the exponential function with the natural constant as the base.

[0079] Among them, represents the detection sum value corresponding to the v-th moment, represents the predicted weight of the data point corresponding to the c-th data segment to be detected at the v-th moment, represents the adjusted predicted value of the data point corresponding to the c-th data segment to be detected at the v-th moment. Combining different weights and considering the influence of the abnormality degree of each data point at the same moment, a more accurate predicted value corresponding to each moment is finally obtained.

[0080] Since the monitoring is timely, the temperature is monitored through the predicted values of each moment after prediction. Preferably, the actual value corresponding to the temperature data at the current moment is obtained, that is, the temperature data collected by the in-vehicle temperature sensor at the current moment, and the numerical difference between the actual value at the current moment and the predicted value at the current moment is used as the monitoring evaluation value, and the monitoring is carried out through the difference between the actually collected value and the predicted value.

[0081] In the embodiment of the present invention, the preset monitoring quantity is set to 3, and the preset monitoring threshold is set to 5. The specific values can be adjusted by the implementer according to the specific implementation situation. When the monitoring evaluation values of the continuous preset monitoring quantity of moments before the current moment are greater than the preset monitoring threshold, that is, when the monitoring evaluation values of the 3 consecutive moments before the current moment are greater than 5, it indicates that the temperature is abnormal, and the monitoring status at the current moment is recorded as the abnormal status. When in the abnormal status, a warning is given to the monitoring personnel for temperature control to ensure the quality and safety of the delivered meals. Otherwise, the monitoring status is the normal status, and the monitoring can continue.

[0082] In summary, the present invention analyzes the abnormality of each fluctuation through the degree of fluctuation change of the data in the historical data segment, and combines the distribution deviation of each data point in the fluctuation. The abnormality degree of each data point is obtained by comprehensively considering the deviation of the data point itself and the abnormality of the fluctuation where it is located, and the suspected abnormal points where abnormal situations may occur are determined for more accurate smoothing later. Further, the data values of each suspected abnormal point are smoothed. By analyzing the distribution of the abnormality degrees of the data points in the preset moving average window, that is, using the abnormality situations of each data point in the window as weights to analyze the trend, the data values at the suspected abnormal points are predicted, and the data values of the suspected abnormal points are updated, obtaining a data segment to be detected that more accurately represents the historical relationship between the delivery temperature and the delivery time, making the predicted values for subsequent prediction more accurate. Further, the abnormality degree of each data point in each data segment to be detected is obtained. At this time, the abnormality degree represents the credibility of each data point in the corresponding data segment to be detected. By combining the data values and the distribution of the abnormality degrees corresponding to all the data segments to be detected at each moment, finally, more accurate predicted values corresponding to each moment are obtained for temperature monitoring. The present invention adjusts the abnormal data situation in the historical data, combines the abnormal situations to obtain more accurate temperature predicted values, makes the process of temperature monitoring more reliable, and thus improves the safety of delivery.

[0083] It should be noted that the above sequence of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0084] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key points of each embodiment are the differences from other embodiments.

Claims

1. A smart city distribution monitoring system based on the Internet of Things, characterized in that: The system comprises: A historical data acquisition module is used to acquire a preset number of historical temperature time series data segments; The module for acquiring the data segment to be detected is used to obtain the abnormality of each data point in each historical temperature time series data segment according to the fluctuation change distribution of each data fluctuation and the distribution deviation of each data point in the corresponding data fluctuation; determine the suspected abnormal point by the abnormality of the data point in each historical temperature time series data segment; update the data value of each suspected abnormal point in combination with the moving average method according to the abnormality distribution proportion of all data points in the corresponding preset moving average window in each historical temperature time series data segment, and obtain the data segment to be detected; The temperature monitoring module is used to obtain the abnormality of each data point in each data segment to be detected; obtain the predicted value at each moment according to the data value and abnormality distribution of the data points in all the data segments to be detected at each moment; and perform temperature monitoring according to the predicted value at each moment.

2. According to the smart city distribution monitoring system based on the Internet of Things as claimed in claim 1, it is characterized in that: The step of obtaining the abnormality of each data point includes: Taking each historical temperature time series data segment as the target data segment in turn, obtaining the temperature data curve in the target data segment; obtaining the extreme value points in the temperature data curve, and taking the curve between each two adjacent extreme value points as the data fluctuation; According to the degree of change of the data points in each data fluctuation, the fluctuation degree of each data fluctuation is obtained; the average value of the fluctuation degrees of all data fluctuations in the target data segment is calculated to obtain the average fluctuation degree of the target data segment; the difference between the fluctuation degree of each data fluctuation and the average fluctuation degree is normalized to obtain the abnormal index of each data fluctuation; Calculate the average value of the data values ​​of all data points in the target data segment to obtain the average data value of the target data segment; for any data point in the target data segment, normalize the difference between the data value of the data point and the average data value to obtain the abnormal possibility of the data point; The abnormal probability of the data point is multiplied by the abnormal index of the data fluctuation where the data point is located to obtain the abnormal degree of the data point.

3. According to claim 2, a smart city distribution monitoring system based on the Internet of Things is characterized in that: The step of obtaining the fluctuation degree of each data fluctuation according to the variation degree of the data points in each data fluctuation comprises: For any data fluctuation, the difference in data values ​​between two extreme value points corresponding to the data fluctuation is calculated to obtain the extreme value difference of the data fluctuation; the difference in time between two extreme value points corresponding to the data fluctuation is calculated to obtain the time difference of the data fluctuation; The ratio of the extreme value difference of the data fluctuation to the time difference is taken as the volatility of the data fluctuation.

4. According to the smart city distribution monitoring system based on the Internet of Things as claimed in claim 1, it is characterized in that: The method for obtaining the suspected abnormal point includes: The average value of all abnormalities in each historical temperature time series data segment is used as the abnormality evaluation index of each historical temperature time series data segment; When the difference between the abnormality of a data point and the abnormal evaluation index of the historical temperature time series data is greater than the preset abnormal threshold, the corresponding data point is regarded as a suspected abnormal point.

5. According to the smart city distribution monitoring system based on the Internet of Things as claimed in claim 1, it is characterized in that: The method for acquiring the data segment to be detected includes: For any suspected abnormal point in any historical temperature time series data segment, the preset moving average window corresponding to the suspected abnormal point is used as the detection window; Calculate the cumulative value of the abnormality of all data points in the detection window and the sum of the abnormality of the suspected abnormal point to obtain the total abnormal value of the suspected abnormal point; calculate the ratio of the abnormality of each data point in the detection window to the total abnormal value, perform negative correlation mapping and normalization processing to obtain the distribution weight of each data point in the detection window; In the detection window, according to the assigned weight of each data point, the SMA moving average method is used to obtain the new data value of the suspected abnormal point; the historical temperature time series data segment in which the data values ​​of all suspected abnormal points are updated is used as the data segment to be detected.

6. According to claim 5, a smart city distribution monitoring system based on the Internet of Things is characterized in that: The method of performing the SMA moving average method according to the assigned weight of each data point in the detection window to obtain a new data value of the suspected abnormal point includes: Based on the SMA moving average method, the moving average value in the detection window is obtained according to the assigned weight and data value of each data point in the detection window; the average value of the difference between the data value of the data point in the detection window and the moving average value is calculated to obtain the adjustment value of the detection window; The sum of the moving average value and the adjusted value is used as the new data value of the corresponding suspected abnormal point.

7. According to the smart city distribution monitoring system based on the Internet of Things as claimed in claim 1, it is characterized in that: The method for obtaining the predicted value includes: For any moment, the sum of the abnormality of all the data points corresponding to the data segments to be detected at that moment is calculated as the detection sum value; the ratio of the abnormality of the data point corresponding to each data segment to be detected at that moment to the detection sum value is negatively correlated and normalized to obtain the prediction weight of each data point corresponding to the data segment to be detected at that moment; Calculate the product of the prediction weight and the corresponding data value of each data point corresponding to each data segment to be detected at this moment, and obtain the adjusted prediction value of each data point corresponding to each data segment to be detected at this moment; calculate the average of all adjusted prediction values ​​at this moment, and obtain the corresponding prediction value at this moment.

8. According to the IoT-based smart city distribution monitoring system of claim 1, it is characterized in that: The temperature monitoring according to the predicted value at each moment includes: Obtain the actual value corresponding to the temperature data at the current moment, and use the numerical difference between the actual value at the current moment and the predicted value at the current moment as the monitoring evaluation value; When the monitoring evaluation value of a preset number of monitoring moments before the current moment is greater than the preset monitoring threshold, the monitoring state at the current moment is recorded as an abnormal state, otherwise, the monitoring state is a normal state.

9. According to claim 2, a smart city distribution monitoring system based on the Internet of Things is characterized in that: The step of obtaining a temperature data curve in a target data segment includes: The least square method is used to perform polynomial fitting on the target data segment to obtain the temperature data curve.

10. The smart city distribution monitoring system based on the Internet of Things according to claim 2 is characterized in that: The method for obtaining the extreme value points in the temperature data curve adopts Newton's method.

Images