An environmental data acquisition method and system for a vehicle-mounted refrigerator

Abstract

The present invention belongs to the technical field of data processing, and particularly relates to a method and system for collecting environmental data of a vehicle-mounted refrigerator. The method includes: dividing the environmental data of the vehicle-mounted refrigerator into intervals, and respectively determining the membership degrees of the target environmental data belonging to its own interval, the previous interval, and the subsequent interval; determining the probability density of the target interval according to the membership degree of each environmental data belonging to the target interval; determining the anomaly score of the target environmental data according to the membership degrees of the target environmental data belonging to the three intervals and the probability densities of the three intervals, and then screening out the abnormal environmental data, and correcting the abnormal environmental data according to the data within the local range of the abnormal environmental data, so as to realize the denoising of the environmental data of the vehicle-mounted refrigerator. The denoising effect of the environmental data of the vehicle-mounted refrigerator in the present invention is excellent, which is beneficial to improving the accuracy of monitoring and adjusting the operating state of the vehicle-mounted refrigerator.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing. More specifically, the present invention relates to a method and system for collecting environmental data for a vehicle-mounted refrigerator. Background Art

[0002] With the continuous development of vehicle-mounted refrigerator technology, the accuracy and reliability of environmental data collection for vehicle-mounted refrigerators have become increasingly important. The environmental data of vehicle-mounted refrigerators are often interfered by various external factors during vehicle driving, such as vehicle jolts, electromagnetic interference, etc. These factors may cause noise in the collected environmental data. These noises will seriously affect the accuracy of environmental data, thus affecting the monitoring and adjustment of the operating state of the vehicle-mounted refrigerator, and may even cause damage to the items in the vehicle-mounted refrigerator.

[0003] The paper (Goldstein M, Dengel A. Histogram-based Outlier Score (HBOS): A fast Unsupervised Anomaly Detection Algorithm[C] / / KI-2012: Poster and Demo Track. 2012.) proposes a histogram-based outlier detection algorithm, which can be used to detect the noise in the environmental data of vehicle-mounted refrigerators. This algorithm divides the same number of environmental data into different intervals, and the lengths of the obtained intervals are different. The density of the interval is used to reflect the outlier score of the environmental data in the interval. When the density of the interval is smaller, the outlier score of the corresponding environmental data is larger, and the environmental data is more likely to be noise.

[0004] However, when the HBOS algorithm divides the intervals, it may divide similar environmental data into different intervals, affecting the accuracy of the outlier score of environmental data, resulting in missed detection or false detection of noise, affecting the denoising effect of environmental data, and further affecting the monitoring and adjustment of the operating state of the vehicle-mounted refrigerator. Summary of the Invention

[0005] To solve the above technical problem that the HBOS algorithm may divide similar environmental data into different intervals, affecting the accuracy of the outlier score of environmental data and resulting in missed detection or false detection of noise, the present invention provides solutions in the following aspects.

[0006] In a first aspect, the present invention provides a method for collecting environmental data for a vehicle-mounted refrigerator, including:

[0007] Collecting the environmental data of the vehicle-mounted refrigerator in real time; dividing all the environmental data into intervals; taking the environmental data at any moment as the target environmental data, and denoting the interval where the target environmental data is located as and taking The previous interval and the subsequent interval are respectively denoted as , ; respectively determine the membership degrees of the target environmental data belonging to the intervals , and ; take any one of the intervals as the target interval, and determine the probability density of the target interval according to the membership degrees of each environmental data belonging to the target interval; according to the membership degrees of the target environmental data belonging to the intervals , and , and the probability densities of the intervals , and , determine the anomaly score of the target environmental data; screen the abnormal environmental data according to the magnitudes of the anomaly scores of the environmental data, and correct the abnormal environmental data according to all the environmental data within the local range of the abnormal environmental data to obtain the corrected value of the abnormal environmental data, so as to realize the denoising process of the environmental data of the vehicle-mounted refrigerator.

[0008] In the present invention, the environmental data is divided into multiple intervals. By obtaining the membership degrees of the environmental data belonging to its own interval and the adjacent intervals, the similarity between the target environmental data and the surrounding environmental data can be quantified, and the distribution characteristics of the environmental data can be better reflected; in the present invention, by combining the membership degrees of the environmental data belonging to different intervals and the probability densities of the intervals, it is possible to more accurately evaluate whether the environmental data is located in an unlikely area, so as to more precisely calculate the anomaly score of the environmental data and avoid missed detection or false detection of noise; in the present invention, the abnormal environmental data is corrected and denoised according to the anomaly scores of the environmental data around the abnormal environmental data, making the environmental data of the vehicle-mounted refrigerator more accurate, reducing misjudgment or unnecessary reactions caused by abnormal data such as noise, and thus improving the accuracy of monitoring and intelligent adjustment of the operating state of the refrigerator.

[0009] Preferably, the dividing of all the environmental data into intervals includes: arranging all the environmental data in ascending order of numerical values, and dividing the sorted environmental data into one interval every F, and during the dividing process, if the number of environmental data in the current interval has reached F, but the next environmental data has the same numerical value as the largest environmental data in the current interval, then add the next environmental data to the current interval, and at this time, the number of environmental data in the current interval can exceed F, where F is a preset first quantity.

[0010] Preferably, the membership degrees of the target environmental data belonging to the intervals , and respectively satisfy the expressions: ; ; ; where , and respectively represent the membership degrees that the target environmental data belong to the intervals , and ; represents the target environmental data; represents the mean value of all environmental data in the interval ; represents the membership degree that the maximum environmental data in the interval belongs to the interval ; represents the membership degree that the minimum environmental data in the interval belongs to the interval ; , respectively represent the maximum environmental data and the minimum environmental data in the interval ; represents the maximum environmental data in the interval ; represents the minimum environmental data in the interval ; represents the length of the longest interval among all intervals.

[0011] By calculating the membership degrees that the target environmental data belong to different intervals, the present invention can more accurately reflect the adaptability and attribution degree of the target environmental data relative to different intervals, and further provides a quantitative basis for obtaining the anomaly score of the target environmental data according to the probability density of the intervals subsequently.

[0012] Preferably, the probability density of the target interval satisfies the expression:

[0013] ; where represents the probability density of the target interval; , and respectively represent the membership degrees that the th environmental data in the target interval, the th environmental data in the interval before the target interval, and the th environmental data in the interval after the target interval belong to the target interval; represents the number of environmental data in the target interval; represents the number of environmental data in the interval before the target interval; represents the number of environmental data in the interval after the target interval; represents the maximum environmental data in the target interval, represents the minimum environmental data in the target interval; is the minimum value function.

[0014] The present invention comprehensively considers the membership degrees of the environmental data in the target interval and the environmental data in the adjacent intervals before and after to the target interval, and evaluates the probability density of the target interval, which can accurately reflect the overall characteristics of the target interval and make the probability density of the target interval more accurate.

[0015] Preferably, the anomaly score of the target environmental data satisfies the expression:

[0016] ; where represents the anomaly score of the target environmental data; , and respectively represent the membership degrees of the target environmental data belonging to the intervals , and ; , and respectively represent the probability densities of the intervals , and .

[0017] The present invention calculates the anomaly score of the target environmental data by combining the membership degrees of the target environmental data in different intervals and the probability densities of each interval, which can effectively reflect the distribution deviation of the target environmental data relative to other environmental data, provides a basis for subsequent screening of abnormal environmental data, and improves the accuracy of subsequent correction of abnormal environmental data.

[0018] Preferably, screening abnormal environmental data according to the magnitude of the anomaly score of the environmental data includes: in response to the anomaly score of the environmental data being greater than a preset anomaly threshold, taking the corresponding environmental data as abnormal environmental data.

[0019] Preferably, correcting the abnormal environmental data according to all the environmental data within the local range of the abnormal environmental data includes: performing weighted summation on all the environmental data within the local range of the abnormal environmental data according to the anomaly scores of all the environmental data within the local range of the abnormal environmental data to obtain a correction value of the abnormal environmental data, where the weight during weighted summation is negatively correlated with the anomaly scores of all the environmental data within the local range.

[0020] The effect is that: the present invention performs weighted summation on all the environmental data within the local range of the abnormal environmental data in combination with the anomaly score, sets a smaller weight for the environmental data with a large anomaly score, and sets a smaller weight for the environmental data with a small anomaly score, ensuring the correction accuracy of the abnormal environmental data and improving the denoising effect of the environmental data.

[0021] Preferably, the correction value of the abnormal environmental data satisfies the expression:

[0022] ; wherein, represents the correction value of the th abnormal environment data; represents the number of environmental data within the local range of the th abnormal environment data; represents the th environmental data within the local range of the th abnormal environment data; represents the abnormal score of the th environmental data within the local range of the th abnormal environment data; is the exponential function with the natural constant as the base.

[0023] In a second aspect, the present invention provides an environmental data acquisition system for a vehicle-mounted refrigerator, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned environmental data acquisition method for a vehicle-mounted refrigerator is implemented.

[0024] By adopting the above technical solution, the above-mentioned environmental data acquisition method for a vehicle-mounted refrigerator is generated into a computer program and stored in the memory to be loaded and executed by the processor, so as to manufacture a terminal device according to the memory and the processor, which is convenient to use.

[0025] The beneficial effects of the present invention are as follows:

[0026] The present invention divides environmental data into multiple intervals. By obtaining the membership degrees of environmental data belonging to its own interval and adjacent intervals, the similarity between target environmental data and surrounding environmental data can be quantified, and the distribution characteristics of environmental data can be better reflected; the present invention combines the membership degrees of environmental data belonging to different intervals and the probability density of the intervals, and can more accurately evaluate whether environmental data is located in an unlikely area, so as to more precisely calculate the abnormal score of environmental data and avoid missed detection or false detection of noise; the present invention corrects and denoises abnormal environmental data according to the abnormal scores of the surrounding environmental data of the abnormal environmental data, making the environmental data of the vehicle-mounted refrigerator more accurate, reducing misjudgment or unnecessary reactions caused by abnormal data such as noise, and thus improving the accuracy of monitoring and intelligent adjustment of the refrigerator operation state. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the drawings, several embodiments of the present invention are shown in an exemplary rather than restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0028] Figure 1 is a flow chart schematically illustrating a method for collecting environmental data for a vehicle refrigerator in the present invention;

[0029] Figure 2 is a schematic diagram schematically showing the deployment of an ambient temperature sensor and an ambient humidity sensor in a vehicle refrigerator;

[0030] Figure 3 1 is a flow chart schematically showing step S2 of a method for collecting environmental data for a vehicle refrigerator in the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0032] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0033] The embodiment of the present invention discloses a method for collecting environmental data for a vehicle refrigerator. Figure 1 , comprising steps S1 to S4:

[0034] S1. Collect environmental data of the vehicle refrigerator.

[0035] The environmental data of the vehicle refrigerator, such as temperature and humidity, are collected in real time through the sensors on the vehicle refrigerator. The collection frequency is set by the implementer according to the actual implementation situation and is not limited to a specific frequency, for example, once per second. Figure 2 The figure is a deployment diagram of the ambient temperature sensor and the ambient humidity sensor in the car refrigerator. The ambient temperature sensor can be used to collect the temperature of the environment in which the car refrigerator is located, and the ambient humidity sensor can be used to collect the humidity of the environment in which the car refrigerator is located.

[0036] S2. Divide all environmental data into intervals, and determine the membership of the target environmental data to its interval, the previous interval, and the next interval respectively. Determine the probability density of the target interval based on the membership of each environmental data to the target interval. Determine the abnormal score of the target environmental data based on the membership of the target environmental data to its interval, the previous interval, and the next interval, and the probability density of the corresponding intervals.

[0037] It should be noted that the sensors deployed on the in-vehicle refrigerator may be affected by other factors such as bumps during vehicle driving, resulting in noise in the collected environmental data. Therefore, the present invention removes the noise in the collected environmental data. The HBOS algorithm can be used to detect the noise in the environmental data. The HBOS algorithm divides the data into intervals. The number of data in each divided interval is the same, but the length of the interval is different, so that the data density in different intervals is different. The data with a small density has a large anomaly score, and the data with a large density has a small anomaly score. However, the HBOS algorithm may divide similar data into different intervals, affecting the accuracy of the data anomaly score. Therefore, the present invention considers the membership degree of the environmental data belonging to different intervals, thereby obtaining a more accurate probability density for each interval, and combining the membership degree and the probability density to obtain the anomaly score of the environmental data, improving the accuracy of the anomaly score.

[0038] Specifically, the flowchart of step S2 is referred to Figure 3 , including steps S201 to S204:

[0039] S201. Divide all environmental data into intervals.

[0040] Specifically, all environmental data are sorted in ascending order of values. Every F environmental data after sorting are divided into one interval. During the division process, if the environmental data in the current interval have reached F, but the next environmental data has the same value as the largest environmental data in the current interval, then the next environmental data is added to the current interval. At this time, the number of environmental data in the current interval can exceed F. The interval boundary of each finally obtained interval is the smallest environmental data and the largest environmental data in the interval. Among them, F is a preset first quantity, used to limit the number of environmental data in each interval, and the implementer can set it according to the actual implementation situation. For example, F = 100.

[0041] For example, when the environmental data is temperature, and the sequence of real-time collected temperatures is {8°C, 9°C, 10°C, 8°C, 9°C, 9°C, 10°C, 11°C, 12°C, 13°C, 12°C, 13°C, 14°C, 15°C}, the temperatures are sorted in ascending order, and the result is {8°C, 8°C, 9°C, 9°C, 9°C, 10°C, 10°C, 11°C, 12°C, 12°C, 13°C, 13°C, 14°C, 15°C}. If , then {8°C, 8°C, 9°C, 9°C, 9°C} belongs to one interval, which is [8°C, 9°C], {10°C, 10°C, 11°C} belongs to one interval, which is [10°C, 11°C], {12°C, 12°C, 13°C, 13°C} belongs to one interval, which is [12°C, 13°C], and {14°C, 15°C} belongs to one interval, which is [14°C, 15°C].

[0042] So far, the interval division of environmental data has been achieved.

[0043] S202. Determine the membership degrees of the target environmental data belonging to its corresponding interval, the previous interval, and the next interval respectively.

[0044] Specifically, take any environmental data as the target environmental data, and represent the interval where the target environmental data is located with respectively represent the previous interval and the next interval of the interval where the target environmental data is located with 、 respectively.

[0045] Determine the membership degrees of the target environmental data belonging to the intervals 、 、 respectively:

[0046] ;

[0047] ;

[0048] ;

[0049] Among them, represents the membership degree of the target environmental data belonging to the interval ; represents the membership degree of the target environmental data belonging to the interval ; represents the membership degree of the target environmental data belonging to the interval ; represents the target environmental data; represents the mean value of all environmental data in the interval ; represents the membership degree of the largest environmental data in the interval belonging to the interval ; represents the membership degree of the smallest environmental data in the interval belonging to the interval ; represents the largest environmental data in the interval ; represents the smallest environmental data in the interval ; represents the largest environmental data in the interval ; represents the smallest environmental data in the interval ; represents the length of the longest interval among all intervals, and the length of each interval is determined by the difference between the largest environmental data and the smallest environmental data in each interval. For normalizing ; represents the absolute value symbol.

[0050] When the difference between the target environmental data and the mean value of all environmental data within the interval where it is located is smaller, the membership degree of the target environmental data belonging to the interval is larger; when the difference between the target environmental data and the maximum environmental data in the previous interval of the interval where it is located is smaller, and the membership degree of belonging to the interval is larger, the value of the target environmental data is closer to the value of the environmental data in the previous interval , and the membership degree of the target environmental data belonging to the previous interval is larger; when the difference between the target environmental data and the minimum environmental data in the next interval of the interval where it is located is smaller, and the membership degree of belonging to the interval is larger, the value of the target environmental data is closer to the value of the environmental data in the next interval , and the membership degree of the target environmental data belonging to the next interval is larger. It should be noted that when there is no previous interval

[0051] for the interval where the target environmental data is located , the membership degree of the target environmental data belonging to the interval is not calculated; when there is no next interval for the interval where the target environmental data is located , the membership degree of the target environmental data belonging to the interval is not calculated. At this point, the membership degrees of the target environmental data belonging to its own interval, the previous interval, and the next interval are obtained.

[0052] S203. Determine the probability density of the target interval according to the membership degrees of each environmental data belonging to the target interval.

[0053] Specifically, take any interval as the target interval, and determine the probability density of the target interval according to the membership degrees of each environmental data belonging to the target interval:

[0054]

[0055] ;

[0056] wherein represents the probability density of the target interval; Denote the membership degree of the th environmental data in the target interval belonging to the target interval; Denote the membership degree of the th environmental data in the previous interval of the target interval belonging to the target interval; Denote the membership degree of the th environmental data in the next interval of the target interval belonging to the target interval; Denote the number of environmental data in the target interval; Denote the number of environmental data in the previous interval of the target interval; Denote the number of environmental data in the next interval of the target interval; Denote the maximum environmental data in the target interval, Denote the minimum environmental data in the target interval; is the minimum value function, used to select the minimum value between

[0057] is the length of the target interval. When is smaller, the distribution of environmental data in the target interval is more concentrated. When is larger, the distribution of environmental data in the target interval is more dispersed; when the membership degrees of each environmental data in the target interval, the previous interval of the target interval, and the next interval of the target interval belonging to the target interval are larger, and the distribution of environmental data in the target interval is more concentrated, the probability density of the target interval is larger; conversely, when the membership degrees of each environmental data in the target interval, the previous interval of the target interval, and the next interval of the target interval belonging to the target interval are smaller, or the distribution of environmental data in the target interval is more dispersed, the probability density of the target interval is smaller.

[0058] It should be noted that when there is no previous interval for the target interval, when calculating the probability density of the target interval, is not considered, that is , when there is no next interval for the target interval, when calculating the probability density of the target interval, is not considered, that is .

[0059] S204. Determine the anomaly score of the target environmental data according to the membership degrees of the target environmental data belonging to its current interval, the previous interval, and the next interval, as well as the probability densities of the corresponding intervals.

[0060] Specifically, according to the membership degrees of the target environmental data belonging to the intervals , , , as well as the intervals , , Determine the anomaly score of the target environmental data based on the probability density:

[0061] ;

[0062] where represents the anomaly score of the target environmental data; represents the membership degree of the target environmental data belonging to the interval ; represents the membership degree of the target environmental data belonging to the interval ; represents the membership degree of the target environmental data belonging to the interval ; represents the interval where the target environmental data is located, and its probability density; represents the probability density of the interval ; represents the probability density of the interval ;

[0063] When the membership degree of the target environmental data belonging to its interval is larger, and the probability density of the interval is larger, the distribution of the target environmental data is closer to the distribution of the remaining environmental data within the interval , and the anomaly score of the target environmental data is smaller; or when the membership degree of the target environmental data belonging to the previous interval is larger, and the probability density of the interval is larger, the distribution of the target environmental data is closer to the distribution of the environmental data within the interval , and the anomaly score of the target environmental data is smaller; or when the membership degree of the target environmental data belonging to the next interval is larger, and the probability density of the interval is larger, the distribution of the target environmental data is closer to the distribution of the environmental data within the interval , and the anomaly score of the target environmental data is smaller; when the probability density of the interval , or is larger, but the membership degree of the target environmental data belonging to the corresponding interval is smaller, the distribution difference between the target environmental data and the environmental data within the corresponding interval is larger, the anomaly score of the target environmental data is larger, and the target environmental data is more likely to be noise; when the probability density of the interval , and is smaller, the distribution difference between the target environmental data and the environmental data within the intervals , and is larger. At this time, regardless of whether the target environmental data belongs to the intervals , and The larger the membership degree of, the larger the anomaly score of the target environmental data, and the more likely the target environmental data is noise.

[0064] It should be noted that when the interval where the target environmental data is located there is no previous interval when calculating the anomaly score of the target environmental data, do not consider That is, the anomaly score of the target environmental data is ; when the interval where the target environmental data is located there is no subsequent interval when calculating the anomaly score of the target environmental data, do not consider That is, the anomaly score of the target environmental data is .

[0065] Similarly, obtain the anomaly scores of all environmental data.

[0066] S3. Screen out abnormal environmental data according to the magnitude of the anomaly scores of the environmental data.

[0067] Specifically, in response to the anomaly score being greater than a preset anomaly threshold, the corresponding environmental data is regarded as abnormal environmental data. The anomaly threshold is set by the implementer according to the actual implementation situation, and is not specifically limited. For example, 0.8.

[0068] S4. Correct the abnormal environmental data according to all the environmental data within the local range of the abnormal environmental data to achieve noise reduction of the in-vehicle refrigerator environmental data.

[0069] For the abnormal environmental data, the environmental data at the moments before and after the abnormal environmental data are used as the environmental data within the local range of the abnormal environmental data, where is a preset second quantity used to limit the size of the local range, and is set by the implementer according to the actual implementation situation, and is not specifically limited. For example .

[0070] Correct the abnormal environmental data according to the environmental data within the local range of the abnormal environmental data:

[0071] ;

[0072] Among them, represents the correction value of the th abnormal environmental data; represents the number of environmental data within the local range of the th abnormal environmental data; represents the th within the local range of the An environmental data; indicating the abnormal score of the nth environmental data within the local range of the is the exponential function with the natural constant as the base.

[0073] is the reference weight of the nth environmental data within the local range of the nth abnormal environmental data. When the abnormal score of the nth environmental data within the local range of the nth abnormal environmental data is larger, the nth environmental data may also be affected by vehicle bumps or other factors, resulting in poor numerical accuracy. At this time, the reference weight of the nth environmental data is smaller, and when correcting the nth abnormal environmental data, the reference degree of the nth environmental data is smaller; when the abnormal score of the nth environmental data within the local range of the

[0074] Replace the data values of all abnormal environmental data in all the collected environmental data with their corrected values, so as to achieve denoising of the environmental data.

[0075] An embodiment of the present invention also discloses an environmental data acquisition system for a vehicle-mounted refrigerator, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, an environmental data acquisition method for a vehicle-mounted refrigerator according to the present invention is implemented.

[0076] The above system further includes a communication bus, a communication interface and other components well known to those skilled in the art. Their settings and functions are known in the art, so they will not be described in detail here.

[0077] In the description of this specification, the meanings of "a plurality of" and "several" are at least two, such as two, three or more, etc., unless otherwise specifically defined.

[0078] Although this specification has shown and described several embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many variations, modifications, and alternative means will occur to those skilled in the art without departing from the spirit and scope of the present invention. It should be understood that alternative embodiments to those described herein may be employed in practicing the present invention.

Claims

1. An environmental data acquisition method for a vehicle-mounted refrigerator, characterized in that, Including: Collecting the environmental data of the in-vehicle refrigerator in real time; dividing all the environmental data into intervals; Take the environmental data at any moment as the target environmental data, and denote the interval where the target environmental data is located as , and denote the interval before and the interval after as and respectively; determine the membership degrees of the target environmental data belonging to the intervals , and respectively, and they respectively satisfy the expressions: ； ； ； Among them, , and respectively represent the membership degrees that the target environmental data belong to the intervals , and ; represents the target environmental data; represents the mean value of all environmental data in the interval ; represents the membership degree that the largest environmental data in the interval belongs to the interval ; represents the membership degree that the smallest environmental data in the interval belongs to the interval ; , respectively represent the largest environmental data and the smallest environmental data in the interval ; represents the largest environmental data in the interval ; represents the smallest environmental data in the interval ; represents the length of the longest interval among all intervals; Taking any one of the intervals as the target interval, and determining the probability density of the target interval according to the membership degree of each environmental data belonging to the target interval; According to the membership degrees of the target environmental data belonging to the intervals , and , and the probability densities of the intervals , and , determine the anomaly score of the target environmental data; Screening out the abnormal environmental data according to the magnitude of the abnormal score of the environmental data, and correcting the abnormal environmental data according to all the environmental data within the local range of the abnormal environmental data to obtain the corrected value of the abnormal environmental data, so as to realize the denoising processing of the environmental data of the in-vehicle refrigerator.

2. The environmental data acquisition method for a vehicle-mounted refrigerator according to claim 1, wherein The dividing all the environmental data into intervals includes: Sorting all the environmental data in ascending order of numerical value, dividing every F pieces of the sorted environmental data into one interval. During the dividing process, if the number of environmental data in the current interval has reached F, but the next environmental data has the same numerical value as the largest environmental data in the current interval, then add the next environmental data to the current interval. At this time, the number of environmental data in the current interval can exceed F, where F is a preset first quantity.

3. A method for collecting environmental data for a vehicle-mounted refrigerator according to claim 1, characterized in that, The probability density of the target interval satisfies the expression: ； Among them, represents the probability density of the target interval; , and respectively represent the membership degrees of the -th environmental data in the target interval, the -th environmental data in the previous interval of the target interval, and the -th environmental data in the next interval of the target interval belonging to the target interval; represents the number of environmental data in the target interval; represents the number of environmental data in the previous interval of the target interval; represents the number of environmental data in the next interval of the target interval; represents the largest environmental data in the target interval, represents the smallest environmental data in the target interval; is the minimum value function.

4. A method for collecting environmental data for a vehicle-mounted refrigerator according to claim 1, characterized in that, The abnormal score of the target environmental data satisfies the expression: ； Among them, represents the anomaly score of the target environment data; , and respectively represent the membership degrees of the target environment data belonging to the intervals , and ; , and respectively represent the probability densities of the intervals , and .

5. A method for collecting environmental data for a vehicle-mounted refrigerator according to claim 1, characterized in that, The screening out the abnormal environmental data according to the magnitude of the abnormal score of the environmental data includes: In response to the abnormal score of the environmental data being greater than a preset abnormal threshold, taking the corresponding environmental data as the abnormal environmental data.

6. The environmental data acquisition method for a vehicle-mounted refrigerator according to claim 1, characterized in that, The correcting the abnormal environmental data according to all the environmental data within the local range of the abnormal environmental data includes: Performing weighted summation on all the environmental data within the local range of the abnormal environmental data according to the abnormal scores of all the environmental data within the local range of the abnormal environmental data to obtain the corrected value of the abnormal environmental data, where the weight during the weighted summation is negatively correlated with the abnormal scores of all the environmental data within the local range.

7. A method for collecting environmental data for a vehicle-mounted refrigerator according to claim 6, characterized in that, The corrected value of the abnormal environmental data satisfies the expression: ； Among them, represents the correction value of the th abnormal environment data; represents the number of environmental data within the local range of the th abnormal environment data; represents the th environmental data within the local range of the th abnormal environment data; represents the abnormal score of the th environmental data within the local range of the th abnormal environment data; is the exponential function with the natural constant as the base.

8. An environmental data acquisition system for a vehicle-mounted refrigerator, characterized in that, Including: A processor and a memory, the memory stores computer program instructions, and when the computer program instructions are executed by the processor, it realizes an environmental data collection method for an in-vehicle refrigerator according to any one of claims 1-7.

Images