Environment data acquisition method and system for vehicle-mounted refrigerator

Abstract

The invention belongs to the technical field of data processing, and particularly relates to an environment data acquisition method and system for a vehicle-mounted refrigerator, and the method comprises the steps: carrying out the interval division of the environment data of the vehicle-mounted refrigerator, and determining the membership degrees of the target environment data belonging to the interval, the previous interval and the next interval; determining the probability density of the target interval according to the membership degree of the environment data belonging to the target interval; according to the membership degree of the target environment data belonging to the three intervals and the probability density of the three intervals, the abnormal score of the target environment data is determined, then the abnormal environment data is screened, the abnormal environment data is corrected according to the data in the local range of the abnormal environment data, and therefore denoising of the vehicle-mounted refrigerator environment data is achieved. The denoising effect of the environment data of the vehicle-mounted refrigerator is excellent, and the accuracy of monitoring and adjusting the running state of the vehicle-mounted refrigerator can be improved.

Description

Technical Field

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

[0002] With the continuous development of car refrigerator technology, the accuracy and reliability of car refrigerator environmental data collection are becoming more and more important. The environmental data of car refrigerators are often interfered by various external factors during the driving process, such as vehicle bumps, electromagnetic interference, etc. These factors may cause noise in the collected environmental data. These noises will seriously affect the accuracy of environmental data, thereby affecting the monitoring and adjustment of the operating status of the car refrigerator, and may even cause damage to the items in the car refrigerator.

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

[0004] However, when dividing the intervals, the HBOS algorithm may divide similar environmental data into different intervals, affecting the accuracy of the environmental data anomaly score, resulting in noise omission or false detection, affecting the denoising effect of the environmental data, and further affecting the monitoring and adjustment of the operating status of the car refrigerator. Summary of the invention

[0005] In order to solve the technical problem that the above-mentioned HBOS algorithm may divide similar environmental data into different intervals, affect the accuracy of environmental data anomaly scores, and cause noise omissions or false detections, the present invention provides solutions in the following aspects.

[0006] In a first aspect, the present invention provides an environmental data collection method for a vehicle refrigerator, comprising: Collect the environmental data of the car refrigerator in real time; divide all environmental data into intervals; take the environmental data at any moment as the target environmental data, and record the interval where the target environmental data is located as ,Will The first interval and the second interval of , ; Determine the target environment data belongs to the interval , as well as membership degree; take any interval as the target interval, and determine 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 degree of the target environmental data belonging to the interval , as well as The membership degree and interval , as well as The probability density of the target environmental data is used to determine the abnormal score of the target environmental data; the abnormal environmental data is filtered according to the size of the abnormal score of the environmental data, and the abnormal environmental data is corrected according to all environmental data within the local range of the abnormal environmental data to obtain the correction value of the abnormal environmental data, thereby realizing the denoising of the environmental data of the vehicle refrigerator.

[0007] The present invention divides environmental data into multiple intervals, and by obtaining the degree of membership of the environmental data to the interval in which it is located and the adjacent intervals, it can quantify the similarity between the target environmental data and the surrounding environmental data, and can better reflect the distribution characteristics of the environmental data; the present invention combines the degree of membership of the environmental data to different intervals and the probability density of the intervals, and can more accurately evaluate whether the environmental data is located in an area that is unlikely to appear, thereby more accurately calculating the abnormal score of the environmental data and avoiding missed detection or false detection of noise; the present invention corrects and denoises the abnormal environmental data according to the abnormal score of the environmental data surrounding the abnormal environmental data, so that the environmental data of the vehicle refrigerator is more accurate, and the misjudgment or unnecessary reaction caused by abnormal data such as noise is reduced, thereby improving the accuracy of monitoring and intelligent adjustment of the refrigerator operation status.

[0008] Preferably, the interval division of all environmental data includes: arranging all environmental data in ascending order of numerical value, dividing every F pieces of the sorted environmental data into an interval, and during the division 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 the next environmental data is added to the current interval. At this time, the number of environmental data in the current interval may exceed F, where F is a preset first number.

[0009] Preferably, the target environment data belongs to the interval , as well as The membership degrees of satisfy the expressions: ; ; ;in, , as well as Respectively indicate that the target environment data belongs to the interval , as well as The degree of membership; Represents target environment data; Representation interval The mean of all environmental data in; Representation interval The largest environmental data belongs to the interval The degree of membership; Representation interval The smallest environmental data belongs to the interval The degree of membership; , Respectively represent the interval The largest environmental data and the smallest environmental data; Representation interval The largest environmental data in the world; Representation interval Minimum environmental data in Indicates the length of the longest interval among all intervals.

[0010] By calculating the membership of the target environmental data to different intervals, the present invention can more accurately reflect the adaptability and belongingness of the target environmental data to different intervals, thereby providing a quantitative basis for subsequently obtaining the abnormal score of the target environmental data according to the probability density of the interval.

[0011] Preferably, the probability density of the target interval satisfies the expression: ;in, represents the probability density of the target interval; , as well as Respectively represent the first environmental data, the first interval before the target interval The environmental data and the target interval in the next interval The degree of membership of each environmental data to the target interval; Indicates the number of environmental data in the target interval; Indicates the number of environmental data in the interval before the target interval; Indicates the number of environmental data in the interval following the target interval; Indicates the maximum environmental data in the target interval, Indicates the minimum environmental data in the target interval; is the minimum function.

[0012] The present invention comprehensively considers the degree of membership of the environmental data in the target interval and the environmental data in the preceding and following adjacent intervals to the target interval, evaluates the probability density of the target interval, and can accurately reflect the overall characteristics of the target interval, making the probability density of the target interval more accurate.

[0013] Preferably, the anomaly score of the target environment data satisfies the expression: ;in, Represents the anomaly score of the target environment data; , as well as Respectively indicate that the target environment data belongs to the interval , as well as The degree of membership; , as well as Respectively represent the interval , as well as The probability density of .

[0014] The present invention calculates the anomaly score of the target environmental data by combining the membership degree of the target environmental data in different intervals with the probability density of each interval, which can effectively reflect the distribution deviation of the target environmental data relative to other environmental data, provide a basis for the subsequent screening of abnormal environmental data, and improve the accuracy of subsequent correction of abnormal environmental data.

[0015] Preferably, the filtering of abnormal environmental data according to the magnitude of the abnormality score of the environmental data includes: in response to the abnormality score of the environmental data being greater than a preset abnormality threshold, treating the corresponding environmental data as abnormal environmental data.

[0016] Preferably, the correction of the abnormal environmental data based on all environmental data within the local range of the abnormal environmental data includes: performing weighted summation of all environmental data within the local range according to the abnormal scores of all environmental data within the local range of the abnormal environmental data to obtain a corrected value of the abnormal environmental data, wherein the weight in the weighted summation is negatively correlated with the abnormal scores of all environmental data within the local range.

[0017] The effect is that the present invention combines the anomaly score to perform weighted summation on all environmental data within the local range of the abnormal environmental data, sets a smaller weight for environmental data with a large anomaly score, and sets an even smaller weight for environmental data with a small anomaly score, thereby ensuring the accuracy of correction of the abnormal environmental data and improving the denoising effect of the environmental data.

[0018] Preferably, the correction value of the abnormal environment data satisfies the expression: ;in, Indicates Correction value of abnormal environmental data; Indicates The number of environmental data in the local area of ​​the abnormal environmental data; Indicates The local range of abnormal environmental data Environmental data; Indicates The local range of abnormal environmental data Anomaly score of environmental data; is an exponential function with a natural constant as its base.

[0019] In a second aspect, the present invention provides an environmental data collection system for a vehicle refrigerator, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned environmental data collection method for a vehicle refrigerator is implemented.

[0020] By adopting the above technical solution, the above-mentioned environmental data collection method for a vehicle refrigerator is generated into a computer program and stored in a memory to be loaded and executed by a processor, so that a terminal device is made according to the memory and the processor for easy use.

[0021] The beneficial effects of the present invention are: The present invention divides environmental data into multiple intervals, and by obtaining the degree of membership of the environmental data to the interval in which it is located and the adjacent intervals, it can quantify the similarity between the target environmental data and the surrounding environmental data, and can better reflect the distribution characteristics of the environmental data; the present invention combines the degree of membership of the environmental data to different intervals and the probability density of the intervals, and can more accurately evaluate whether the environmental data is located in an area that is unlikely to appear, thereby more accurately calculating the abnormal score of the environmental data and avoiding missed detection or false detection of noise; the present invention corrects and denoises the abnormal environmental data according to the abnormal score of the environmental data surrounding the abnormal environmental data, so that the environmental data of the vehicle refrigerator is more accurate, and the misjudgment or unnecessary reaction caused by abnormal data such as noise is reduced, thereby improving the accuracy of monitoring and intelligent adjustment of the refrigerator operation status. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] 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 accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 is a flow chart schematically illustrating a method for collecting environmental data for a vehicle refrigerator in the present invention; Figure 2 is a schematic diagram schematically showing the deployment of an ambient temperature sensor and an ambient humidity sensor in a vehicle refrigerator; 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

[0023] 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.

[0024] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0025] The embodiment of the present invention discloses a method for collecting environmental data for a vehicle refrigerator. Figure 1 , comprising steps S1 to S4: S1. Collect environmental data of the vehicle refrigerator.

[0026] 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.

[0027] 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.

[0028] It should be noted that the sensors deployed on the car 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 noise in environmental data. The HBOS algorithm divides the data into intervals. The number of data in the divided intervals is the same, and the length of the intervals is different, so that the data density of different intervals is different. The data with low density has a large abnormal score, and the data with high density has a small abnormal score. However, the HBOS algorithm may divide similar data into different intervals, affecting the accuracy of the data abnormal score. Therefore, the present invention takes into account the membership of environmental data belonging to different intervals, so as to obtain a more accurate probability density of each interval, and combines the membership and probability density to obtain the abnormal score of the environmental data, thereby improving the accuracy of the abnormal score.

[0029] Specifically, the flowchart of step S2 refers to Figure 3 , including steps S201 to S204: S201. Divide all environmental data into intervals.

[0030] Specifically, all environmental data are arranged in order from small to large values, and the sorted environmental data are divided into an interval for every F pieces. During the division process, if the environmental data in the current interval has reached F pieces, but the value of the next environmental data is the same 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 may exceed F. The interval boundary of each interval finally obtained is the smallest environmental data in the interval and the largest environmental data in the interval. Among them, F is a preset first number used to limit the number of environmental data in each interval. The implementer can set it according to the actual implementation situation, for example, F=100.

[0031] For example, when the environmental data is temperature, and the sequence of real-time collected temperatures is {8℃, 9℃, 10℃, 8℃, 9℃, 9℃, 10℃, 11℃, 12℃, 13℃, 12℃, 13℃, 14℃, 15℃}, the temperatures are sorted in ascending order, and the result is {8℃, 8℃, 9℃, 9℃, 9℃, 10℃, 10℃, 11℃, 12℃, 12℃, 13℃, 13℃, 14℃, 15℃}. If , then {8℃, 8℃, 9℃, 9℃, 9℃} belongs to an interval, which is [8℃, 9℃], {10℃, 10℃, 11℃} belongs to an interval, which is [10℃, 11℃], {12℃, 12℃, 13℃, 13℃} belongs to an interval, which is [12℃, 13℃], and {14℃, 15℃} belongs to an interval, which is [14℃, 15℃].

[0032] At this point, the interval division of environmental data has been achieved.

[0033] S202: Determine the membership of the target environment data to the interval in which it is located, the previous interval, and the next interval respectively.

[0034] Specifically, any environment data is used as the target environment data, and the interval where the target environment data is located is used as To indicate that the previous interval and the next interval of the interval where the target environment data is located are respectively used , To express.

[0035] Determine the target environment data belongs to the interval , , Membership degree: ; ; ; in, Indicates that the target environment data belongs to the interval The degree of membership; Indicates that the target environment data belongs to the interval The degree of membership; Indicates that the target environment data belongs to the interval The degree of membership; Represents target environment data; Representation interval The mean of all environmental data in; Representation interval The largest environmental data belongs to the interval The degree of membership; Representation interval The smallest environmental data belongs to the interval The degree of membership; Representation interval The largest environmental data in the world; Representation interval Minimum environmental data in Representation interval The largest environmental data in the world; Representation interval Minimum environmental data in Indicates the length of the longest interval among all intervals. The length of each interval is determined by the difference between the largest and smallest environmental data in each interval. Used for Perform normalization; Represents the absolute value symbol.

[0036] When the target environment data and the interval The mean of all environmental data in The difference between The smaller the value, the target environment data belongs to the interval The greater the membership degree, the greater the target environment data is compared with the previous interval of the interval in which it is located. The largest environmental data The smaller the difference, and Belong to the interval The greater the membership degree, the closer the value of the target environment data is to the previous interval The value of the environment data in the target environment data belongs to the previous interval The greater the membership degree, the greater the target environment data is. Minimum environmental data The smaller the difference, and Belong to the interval The greater the membership degree, the closer the value of the target environment data is to the latter interval The value of the environment data in the middle, the target environment data belongs to the latter interval The greater the degree of membership.

[0037] It should be noted that when the target environment data is in the interval There is no previous interval When the target environment data belongs to the interval The membership degree is when the target environment data is in the interval There is no subsequent interval When the target environment data belongs to the interval The degree of membership.

[0038] At this point, the membership of the target environment data to its interval, the previous interval, and the next interval is obtained.

[0039] S203: Determine the probability density of the target interval according to the degree of membership of each environmental data to the target interval.

[0040] Specifically, any interval is taken as the target interval, and the probability density of the target interval is determined according to the degree of membership of each environmental data to the target interval: ; in, represents the probability density of the target interval; Indicates the target interval The degree of membership of each environmental data to the target interval; Indicates the first interval before the target interval. The degree of membership of each environmental data to the target interval; Indicates the first interval after the target interval. The degree of membership of each environmental data to the target interval; Indicates the number of environmental data in the target interval; Indicates the number of environmental data in the interval before the target interval; Indicates the number of environmental data in the interval following the target interval; Indicates the maximum environmental data in the target interval, Indicates the minimum environmental data in the target interval; is the minimum function, used to select and 1, preventing the probability density from being greater than 1.

[0041] is the length of the target interval, when The smaller the value, the more concentrated the distribution of environmental data in the target interval. The larger it is, the more dispersed the distribution of environmental data in the target interval is; when the degree of membership of each environmental data in the target interval, the previous interval of the target interval, and the next interval of the target interval belongs to the target interval, and the more concentrated the distribution of environmental data in the target interval is, the greater the probability density of the target interval is; conversely, when the degree of membership of each environmental data in the target interval, the previous interval of the target interval, and the next interval of the target interval belongs to the target interval, or the distribution of environmental data in the target interval is more dispersed, the probability density of the target interval is smaller.

[0042] It should be noted that when the target interval does not have a previous interval, the probability density of the target interval is not considered. ,Right now , when the target interval does not exist in the next interval, the probability density of the target interval is calculated without considering ,Right now .

[0043] S204: Determine the abnormal score of the target environment data according to the degree of membership of the target environment data to the interval in which it is located, the previous interval, and the next interval, and the probability density of the corresponding interval.

[0044] Specifically, according to the target environment data belongs to the interval , , The membership degree and interval , , The probability density of , determines the abnormal score of the target environment data: ; in, Represents the anomaly score of the target environment data; Indicates that the target environment data belongs to the interval The degree of membership; Indicates that the target environment data belongs to the interval The degree of membership; Indicates that the target environment data belongs to the interval The degree of membership; Indicates the interval where the target environment data is located The probability density of Representation interval The probability density of Representation interval The probability density of .

[0045] When the target environment data belongs to its interval The greater the membership degree of The larger the probability density of The closer the distribution of the other environmental data is, the smaller the abnormal score of the target environmental data is; or when the target environmental data belongs to the previous interval The greater the membership degree of The larger the probability density of The closer the distribution of internal environment data is, the smaller the abnormal score of target environment data is; or when the target environment data belongs to the latter interval The greater the membership degree of The larger the probability density of The closer the distribution of internal environment data is, the smaller the abnormal score of target environment data is. , or The larger the probability density is, but the smaller the membership of the target environment data to the corresponding interval is, the greater the distribution difference between the target environment data and the environment data in the corresponding interval is, the greater the abnormal score of the target environment data is, and the target environment data is more likely to be noise; when the interval , as well as The smaller the probability density of , as well as The greater the distribution difference of the internal environment data, the greater the difference in the distribution of the internal environment data. , as well as The larger the membership degree is, the larger the abnormal score of the target environment data is, and the more likely the target environment data is noise.

[0046] It should be noted that when the target environment data is in the interval There is no previous interval When calculating the anomaly score of the target environment data, the , that is, the anomaly score of the target environment data is ; When the target environment data is in the interval There is no subsequent interval When calculating the anomaly score of the target environment data, the , that is, the anomaly score of the target environment data is .

[0047] Similarly, obtain the anomaly scores of all environmental data.

[0048] S3. Filter abnormal environmental data according to the size of the abnormal score of the environmental data.

[0049] Specifically, in response to the abnormality score being greater than a preset abnormality threshold, the corresponding environmental data is used as abnormal environmental data. The abnormality threshold is set by the implementer according to the actual implementation situation and is not specifically limited, for example, 0.8.

[0050] S4. Correct the abnormal environmental data according to all environmental data in the local range of the abnormal environmental data to achieve denoising of the vehicle refrigerator environmental data.

[0051] For abnormal environmental data, The environmental data at each moment is taken as the environmental data in the local range of the abnormal environmental data, where It is a preset second number used to limit the size of the local range. It is set by the implementer according to the actual implementation situation and is not limited to a specific number. For example, .

[0052] Correct the abnormal environmental data based on the environmental data in the local range of the abnormal environmental data: ; in, Indicates Correction value of abnormal environmental data; Indicates The number of environmental data in the local area of ​​the abnormal environmental data; Indicates The local range of abnormal environmental data Environmental data; Indicates The local range of abnormal environmental data Anomaly score of environmental data; is an exponential function with a natural constant as its base.

[0053] For the The local range of abnormal environmental data The reference weight of environmental data is The local range of abnormal environmental data The larger the anomaly score of the environmental data, the The environmental data may also be affected by vehicle bumps or other factors, resulting in poor numerical accuracy. The smaller the reference weight of the environmental data, the more When there is abnormal environmental data, The smaller the reference degree of each environmental data; The local range of abnormal environmental data The smaller the abnormal score of each environmental data is, the The more accurate the environmental data is, the The greater the reference weight of the environmental data, the more When there is abnormal environmental data, The greater the reference level of environmental data.

[0054] The data values ​​of all abnormal environmental data in all collected environmental data are replaced with their correction values, thereby achieving denoising of the environmental data.

[0055] An embodiment of the present invention also discloses an environmental data collection system for a vehicle refrigerator, including a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, an environmental data collection method for a vehicle refrigerator according to the present invention is implemented.

[0056] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0057] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0058] Although this specification has shown and described a number of 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. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A method for collecting environmental data for a vehicle refrigerator, characterized in that: include: Collect environmental data of the vehicle refrigerator in real time; divide all environmental data into intervals; The environmental data at any time is taken as the target environmental data, and the interval where the target environmental data is located is recorded as ,Will The first interval and the second interval of , ; Determine the target environment data belongs to the interval , as well as The degree of membership; Take any interval as the target interval, and determine the probability density of the target interval according to the degree of membership of each environmental data to the target interval; According to the target environment data belongs to the interval , as well as The membership degree and interval , as well as The probability density of , determines the abnormal score of the target environment data; The abnormal environmental data is filtered according to the size of the abnormal score of the environmental data, and the abnormal environmental data is corrected according to all environmental data within the local range of the abnormal environmental data to obtain the correction value of the abnormal environmental data, thereby realizing the denoising processing of the environmental data of the vehicle refrigerator.

2. The method for collecting environmental data for a vehicle refrigerator according to claim 1, characterized in that: The interval division of all environmental data includes: All environmental data are arranged in ascending order of numerical value, and every F pieces of sorted environmental data are divided into an interval. During the division process, if the number of environmental data in the current interval has reached F, but the value of the next environmental data is the same as the largest environmental data in the current interval, the next environmental data will be added to the current interval. At this time, the number of environmental data in the current interval may exceed F, where F is a preset first number.

3. The method for collecting environmental data for a vehicle refrigerator according to claim 1, characterized in that: The target environment data belongs to the interval , as well as The membership degrees of satisfy the expressions: ； ； ； in, , as well as Respectively indicate that the target environment data belongs to the interval , as well as The degree of membership; Represents target environment data; Representation interval The mean of all environmental data in; Representation interval The largest environmental data belongs to the interval The degree of membership; Representation interval The smallest environmental data belongs to the interval The degree of membership; , Respectively represent the interval The largest environmental data and the smallest environmental data; Representation interval The largest environmental data in the world; Representation interval Minimum environmental data in Indicates the length of the longest interval among all intervals.

4. The method for collecting environmental data for a vehicle refrigerator according to claim 1, characterized in that: The probability density of the target interval satisfies the expression: ； in, represents the probability density of the target interval; , as well as Respectively represent the first environmental data, the first interval before the target interval The environmental data and the target interval in the next interval The degree of membership of each environmental data to the target interval; Indicates the number of environmental data in the target interval; Indicates the number of environmental data in the interval before the target interval; Indicates the number of environmental data in the interval following the target interval; Indicates the maximum environmental data in the target interval, Indicates the minimum environmental data in the target interval; is the minimum function.

5. The method for collecting environmental data for a vehicle refrigerator according to claim 1, characterized in that: The anomaly score of the target environment data satisfies the expression: ； in, Represents the anomaly score of the target environment data; , as well as Respectively indicate that the target environment data belongs to the interval , as well as The degree of membership; , as well as Respectively represent the interval , as well as The probability density of .

6. The method for collecting environmental data for a vehicle refrigerator according to claim 1, characterized in that: The step of screening abnormal environmental data according to the abnormality score of the environmental data includes: In response to the abnormality score of the environmental data being greater than a preset abnormality threshold, the corresponding environmental data is regarded as abnormal environmental data.

7. The method for collecting environmental data for a vehicle refrigerator according to claim 1, characterized in that: The correcting of the abnormal environment data according to all environment data within the local range of the abnormal environment data includes: According to the abnormal scores of all environmental data in the local range of the abnormal environmental data, weighted summation is performed on all environmental data in the local range to obtain a corrected value of the abnormal environmental data, wherein the weight in the weighted summation is negatively correlated with the abnormal scores of all environmental data in the local range.

8. The method for collecting environmental data for a vehicle refrigerator according to claim 1 or 7, characterized in that: The correction value of the abnormal environment data satisfies the expression: ； in, Indicates Correction value of abnormal environmental data; Indicates The number of environmental data in the local area of ​​the abnormal environmental data; Indicates The local range of abnormal environmental data Environmental data; Indicates The local range of abnormal environmental data Anomaly score of environmental data; is an exponential function with a natural constant as its base.

9. An environmental data collection system for a vehicle refrigerator, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an environmental data collection method for a vehicle refrigerator according to any one of claims 1 to 8 is implemented.

Images