Cold chain vehicle temperature anomaly identification method and device
By processing cold chain vehicle temperature data through wavelet decomposition and pattern sequence generation, the method addresses the challenge of analyzing large volumes of temperature data, achieving efficient abnormal temperature recognition.
Patent Information
- Application Number
- CN202411287067.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-13
- Publication Date
- 2024-12-13
AI Technical Summary
The large volume of temperature data generated in cold chain logistics is difficult to analyze due to environmental and sensor accuracy factors, making it challenging to identify abnormal temperature patterns.
A method involving time series data processing, including wavelet decomposition, polynomial interpolation, and pattern sequence generation to identify abnormal temperature patterns in cold chain vehicles.
The method effectively processes and classifies massive data into pattern sequences, reducing analysis burden and enabling efficient recognition of abnormal temperatures in cold chain vehicles.
Smart Images
Figure CN119130303A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing technology, and in particular to a method and device for identifying abnormal temperature of a cold chain vehicle. Background Art
[0002] At present, in the field of logistics, cold chain logistics continues to develop and become a form of logistics with broad prospects. In recent years, with the continuous introduction of vehicle GPS positioning tracking, temperature sensors, the Internet of Things, big data and other technologies, real-time collection and monitoring of temperature data has been widely used in the field of cold chain logistics.
[0003] Since the temperature data generated in the cold chain logistics process is easily affected by factors such as the environment and sensor accuracy, these data suffer from large data volumes and are difficult to conduct overall analysis. Summary of the invention
[0004] The present invention provides a method and device for identifying abnormal temperature of cold chain vehicles, which are used to solve the problem that the temperature data generated in the cold chain logistics link in the prior art presents a large amount of data and is difficult to perform overall analysis.
[0005] The present invention provides a method for identifying abnormal temperature of a cold chain vehicle, the method comprising: Obtain the time series data of the compartment temperature of the cold chain vehicle and the time series data of the external environment temperature; Acquire target compartment high-frequency temperature time series data corresponding to the compartment temperature time series data, wherein the target compartment high-frequency temperature time series data is a high-frequency component corresponding to the compartment temperature time series data, and the temperature conversion range and data volume of the target compartment high-frequency temperature time series data are equal to those of the compartment temperature time series data; Generate a pattern sequence of cold chain vehicles based on the target compartment high-frequency temperature time series data, the compartment temperature time series data, and the external environment temperature time series data, wherein the pattern sequence includes temperature patterns under multiple consecutive target time periods; Based on the pattern sequence of the cold chain vehicle, abnormal temperature patterns of the cold chain vehicle are identified.
[0006] According to the method for identifying abnormal temperature of cold chain vehicles provided by the present invention, the time series data of the compartment temperature of the cold chain vehicle and the time series data of the external environment temperature are obtained in the following manner: Acquire original cold chain data of the cold chain vehicle, wherein the original cold chain data includes the first vehicle longitude and latitude and the first compartment temperature of the cold chain vehicle at each data recording time point; Based on the preset time window, the vehicle longitude and latitude and the compartment temperature of the cold chain vehicle at each data recording time point are downsampled and linearly interpolated to obtain the second vehicle longitude and latitude and the second compartment temperature of the cold chain vehicle in each time window; Based on the latitude and longitude of the second vehicle and historical weather data of the cold chain vehicle in each time window, obtaining the external environment temperature of the cold chain vehicle in each time window; Based on the compartment temperature of the cold chain vehicle in each time window, obtaining the compartment temperature time series data of the cold chain vehicle; Based on the external ambient temperature of the cold chain vehicle in each time window, the external ambient temperature time series data of the cold chain vehicle is obtained.
[0007] According to the method for identifying abnormal temperature of cold chain vehicles provided by the present invention, the step of obtaining high-frequency temperature time series data of the compartment corresponding to the compartment temperature time series data includes: Performing 4-level wavelet decomposition on the cabin temperature time series data, and using the decomposed high-frequency components as the first cabin high-frequency temperature time series data; Shifting and scaling the first compartment high-frequency temperature time series data to obtain second compartment temperature time series data having a temperature conversion range equal to that of the compartment temperature time series data; Polynomial interpolation is performed on the second compartment high-frequency temperature time series data to obtain target compartment high-frequency temperature time series data having the same data volume as the compartment temperature time series data.
[0008] According to the method for identifying abnormal temperature of cold chain vehicles provided by the present invention, the pattern sequence of cold chain vehicles is generated based on the target compartment high-frequency temperature time series data, the compartment temperature time series data and the external environment temperature time series data, including: Segmenting the target compartment high-frequency temperature time series data to obtain target compartment high-frequency temperature data in multiple initial time periods; Merging the target compartment high-frequency temperature data in the multiple initial time periods based on the characteristic vectors of the target compartment high-frequency temperature data in each initial time period to obtain the target compartment high-frequency temperature data in the multiple target time periods; Determining the cabin temperature data and the ambient temperature data in each target time period based on the cabin temperature time series data and the ambient temperature time series data; Determining a temperature mode in each time period based on the target compartment high-frequency temperature data, the compartment temperature data, and the external environment temperature data in each target time period; Based on the temperature patterns in each time period, a pattern sequence of cold chain vehicles is generated.
[0009] According to the method for identifying abnormal temperature of cold chain vehicles provided by the present invention, the high-frequency temperature time series data of the target compartment is segmented to obtain the high-frequency temperature data of the target compartment in multiple initial time periods, including: Performing a second-order derivative on the target compartment high-frequency temperature time series data to determine the peaks and troughs after the second-order derivative; Based on the peaks and troughs, the first target compartment high-frequency temperature time series data is segmented to obtain target compartment high-frequency temperature data in multiple initial time periods.
[0010] According to the method for identifying temperature anomalies in cold chain vehicles provided by the present invention, the temperature mode includes at least one of a normal temperature stable state mode, a power-on stable state mode, a refrigeration shutdown mode, a refrigeration door-open mode, a heating shutdown mode, a heating door-open mode, a refrigeration startup mode, a refrigeration door-closed mode, a heating startup mode, a heating door-closed mode, and a horizontal temperature state mode.
[0011] The present invention also provides a device for identifying abnormal temperature of a cold chain vehicle, comprising: The first identification module is used to obtain the time series data of the compartment temperature of the cold chain vehicle and the time series data of the external environment temperature; A second identification module is used to obtain target compartment high-frequency temperature time series data corresponding to the compartment temperature time series data, wherein the target compartment high-frequency temperature time series data is a high-frequency component corresponding to the compartment temperature time series data, and the temperature conversion range and data volume of the target compartment high-frequency temperature time series data are equal to those of the compartment temperature time series data; A third identification module is used to generate a pattern sequence of cold chain vehicles based on the target compartment high-frequency temperature time series data, the compartment temperature time series data and the external environment temperature time series data, wherein the pattern sequence includes temperature patterns under multiple consecutive target time periods; The fourth recognition module is used to identify abnormal temperature patterns of cold chain vehicles based on the pattern sequence of the cold chain vehicles.
[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for identifying abnormal temperature of a cold chain vehicle as described in any one of the above is implemented.
[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for identifying abnormal temperature of a cold chain vehicle as described in any one of the above.
[0014] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the method for identifying abnormal temperature of a cold chain vehicle as described in any one of the above.
[0015] The method for identifying abnormal temperature of cold chain vehicles provided by the present invention first obtains the compartment temperature time series data and the external environment temperature time series data of the cold chain vehicle; then obtains the target compartment high-frequency temperature time series data corresponding to the compartment temperature time series data; finally, based on the target compartment high-frequency temperature time series data, the compartment temperature time series data and the external environment temperature time series data, a pattern sequence of the cold chain vehicle is generated, and the pattern sequence includes temperature patterns under multiple consecutive target time periods; based on the pattern sequence of the cold chain vehicle, abnormal temperature pattern recognition is performed on the cold chain vehicle. The present invention automatically processes and classifies the original cold chain vehicle data, compresses the massive original data into a pattern sequence, effectively reduces the burden of subsequent data analysis, and finally analyzes the pattern sequence to achieve efficient recognition of abnormal temperature of cold chain vehicles. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0017] Figure 1 It is a flow chart of the method for identifying abnormal temperature of cold chain vehicles provided by the present invention.
[0018] Figure 2 It is a structural schematic diagram of the temperature anomaly identification device for cold chain vehicles provided by the present invention.
[0019] Figure 3 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION
[0020] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0021] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way are interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first" and "second" are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally represents that the objects associated with each other are in an "or" relationship.
[0022] The embodiment of the present invention provides a method for identifying abnormal temperature of a cold chain vehicle. Figure 1 As shown, the steps 110 to 150 are included.
[0023] Step 110, obtaining the time series data of the compartment temperature of the cold chain vehicle and the time series data of the external environment temperature; Here, the compartment temperature time series data of the cold chain vehicle refers to the continuous record of the changes in the compartment temperature of the cold chain vehicle over time. These data exist in the form of a time series, and each time point corresponds to a compartment temperature value. For example, the compartment temperature value of the cold chain vehicle compartment temperature every 1 minute.
[0024] The external environment temperature time series data refers to the continuous record of the external environment temperature of the cold chain vehicle over time. These data exist in the form of a time series, and each time point corresponds to an external environment temperature value. For example, the external environment temperature value of the cold chain vehicle every 1 minute.
[0025] Step 120, obtaining target compartment high-frequency temperature time series data corresponding to the compartment temperature time series data, wherein the target compartment high-frequency temperature time series data is a high-frequency component corresponding to the compartment temperature time series data, and the temperature conversion range and data volume of the target compartment high-frequency temperature time series data are equal to those of the compartment temperature time series data; Here, the target compartment high-frequency temperature time series data refers to the high-frequency component part extracted from the compartment temperature time series data, which retains the high-frequency change information (rapid temperature change or fluctuation) in the original data, but removes the low-frequency (or slowly changing temperature) components.
[0026] In the present embodiment, after the high-frequency component part is extracted from the cabin temperature time series data, since the high-frequency component part usually only contains the rapidly changing part in the original cabin temperature time series data, its temperature change range may be smaller than the temperature change range of the original data, and the data volume is also smaller than the amount of the original data. Therefore, in the present embodiment, the extracted high-frequency component part is further processed, such as scaling, resampling, waveform replication and adjustment, so that the processed temperature change range and data volume are consistent with the original cabin temperature time series data.
[0027] Step 130, generating a pattern sequence of cold chain vehicles based on the target compartment high-frequency temperature time series data, the compartment temperature time series data, and the external environment temperature time series data, wherein the pattern sequence includes temperature patterns in a plurality of consecutive target time periods; Specifically, the target compartment high-frequency temperature time series data, compartment temperature time series data and external environment temperature time series data are integrated together to ensure that they are aligned on the time axis, that is, each time point has a corresponding high-frequency compartment temperature, compartment temperature and external environment temperature. Then, according to the high-frequency compartment temperature, compartment temperature and external environment temperature at each time point, the temperature mode in a time period (such as stable mode, fluctuating mode, rising mode, falling mode, etc.) is analyzed, and finally the temperature modes in continuous time periods are arranged into a mode sequence in chronological order, such as: mode A, mode B, mode C, mode B, mode D, mode A...
[0028] It should be noted here that these time periods may be of equal length, or may be dynamically determined based on certain rules (such as temperature change rate, changes in external environmental conditions, etc.), and there is no limitation to this.
[0029] Step 140: Based on the pattern sequence of the cold chain vehicle, abnormal temperature pattern recognition is performed on the cold chain vehicle.
[0030] It can be understood that the pattern sequence is composed of a series of continuous temperature patterns. In this embodiment, the pattern subsequence strings in the pattern sequence can be analyzed one by one and compared with the predefined normal pattern library and abnormal pattern library to identify inconsistent abnormal patterns.
[0031] for example,<N、D、C> (Power on),<C、A0、N> (Power off),<C、A1、D、C> (Normal door opening and closing) belongs to the normal mode,<D、A0、D、A0> (continuous on / off),<A1、D、A1、D> (Continuous opening and closing of doors), <e>(Temperature probe abnormality) belongs to abnormal mode. Then the pattern subsequence strings in the pattern sequence are analyzed one by one to identify<D、A0、D、A0> (continuous on / off),<A1、D、A1、D> (Continuous opening and closing of doors), <e>(Temperature probe abnormality) abnormal mode.
[0032] The method for identifying abnormal temperature of cold chain vehicles provided by the present invention first obtains the compartment temperature time series data and the external environment temperature time series data of the cold chain vehicle; then obtains the target compartment high-frequency temperature time series data corresponding to the compartment temperature time series data; finally, based on the target compartment high-frequency temperature time series data, the compartment temperature time series data and the external environment temperature time series data, a pattern sequence of the cold chain vehicle is generated, and the pattern sequence includes temperature patterns under multiple consecutive target time periods; based on the pattern sequence of the cold chain vehicle, abnormal temperature pattern recognition is performed on the cold chain vehicle. The present invention automatically processes and classifies the original cold chain vehicle data, compresses the massive original data into a pattern sequence, effectively reduces the burden of subsequent data analysis, and finally analyzes the pattern sequence to achieve efficient recognition of abnormal temperature of cold chain vehicles.
[0033] In some embodiments, the compartment temperature time series data of the cold chain vehicle and the external environment temperature time series data are obtained in the following manner: Acquire original cold chain data of the cold chain vehicle, wherein the original cold chain data includes the first vehicle longitude and latitude and the first compartment temperature of the cold chain vehicle at each data recording time point; Based on the preset time window, the vehicle longitude and latitude and the compartment temperature of the cold chain vehicle at each data recording time point are downsampled and linearly interpolated to obtain the second vehicle longitude and latitude and the second compartment temperature of the cold chain vehicle in each time window; Based on the latitude and longitude of the second vehicle and historical weather data of the cold chain vehicle in each time window, obtaining the external environment temperature of the cold chain vehicle in each time window; Based on the compartment temperature of the cold chain vehicle in each time window, obtaining the compartment temperature time series data of the cold chain vehicle; Based on the external ambient temperature of the cold chain vehicle in each time window, the external ambient temperature time series data of the cold chain vehicle is obtained.
[0034] First, the original cold chain data is extracted from the monitoring system of the cold chain vehicle, which includes the longitude and latitude of the first vehicle (latitude lat and longitude lng), timestamp and the temperature of the first compartment at each data recording time point.
[0035] Since the original data may be very dense (i.e., the recording frequency is very high, such as once per second or every few minutes), in this embodiment, a preset time window (such as every minute, every 5 minutes, etc.) is used to downsample the data. Specifically, the average of the longitude and latitude of the first vehicle and the temperature of the first compartment in each time window is calculated to obtain the longitude and latitude of the second vehicle and the temperature of the second compartment.
[0036] Here, for some time windows, no data may be reported due to equipment failure, signal loss or other reasons. In order to maintain the continuity and integrity of the data, the second vehicle longitude and latitude and the second cabin temperature in these missing time windows are further linearly interpolated in this embodiment.
[0037] Then, the latitude and longitude and timestamp of the second vehicle of the cold chain vehicle in each time window are used to query or associate the historical weather database to obtain the ambient temperature of the vehicle's location in the current time window.
[0038] Finally, filter out the original longitude and latitude data, and then sort the second compartment temperature and the outside ambient temperature by time. The sorted data sequence can be expressed as data=[d1,d2,...,dn], where each element dn is a tuple or record containing a timestamp (trigger_time), the second compartment temperature (t_truck), and the outside ambient temperature (t_weather). Based on the sorted data sequence, the compartment temperature time series data and the outside ambient temperature time series data of the cold chain vehicle can be generated respectively.
[0039] The method for identifying temperature anomalies in cold chain vehicles provided by the present invention reduces the amount of data by downsampling and performs linear interpolation on missing data points to ensure the continuity and integrity of the data. It also associates historical weather data based on the latitude and longitude and timestamp of the vehicle to obtain the ambient temperature of the vehicle's location at the current moment for subsequent abnormal temperature pattern recognition.
[0040] In some embodiments, the step of obtaining the high-frequency temperature time series data of the vehicle compartment corresponding to the vehicle compartment temperature time series data includes: Performing 4-level wavelet decomposition on the cabin temperature time series data, and using the decomposed high-frequency components as the first cabin high-frequency temperature time series data; Shifting and scaling the first compartment high-frequency temperature time series data to obtain second compartment temperature time series data having a temperature conversion range equal to that of the compartment temperature time series data; Polynomial interpolation is performed on the second compartment high-frequency temperature time series data to obtain target compartment high-frequency temperature time series data having the same data volume as the compartment temperature time series data.
[0041] In this embodiment, the cabin temperature time series data is subjected to 4-level wavelet decomposition to separate the high-frequency components in the cabin temperature data as the first cabin high-frequency temperature time series data. The high-frequency components usually include the fast-changing parts in the temperature data, such as short-term temperature fluctuations.
[0042] The first compartment high-frequency temperature time series data obtained after wavelet decomposition may have a temperature range and fluctuation amplitude different from those of the original temperature data. Therefore, in this embodiment, in order to maintain data consistency, it is necessary to translate and scale the first compartment high-frequency temperature time series data to obtain the second compartment temperature time series data so that its temperature variation range is consistent with the original compartment temperature time series data. For example, by calculating the extreme values (maximum and minimum values) of the original compartment temperature time series data and the first compartment high-frequency temperature time series data, the scaling and translation factors can be determined. The scaling factor is used to adjust the fluctuation amplitude of the first compartment high-frequency temperature time series data, and the translation factor is used to adjust the overall position of the first compartment high-frequency temperature time series data.
[0043] It can be understood that the second cabin temperature time series data is the high-frequency component part extracted from the original cabin temperature time series data, and the data volume may be smaller than the data volume of the original cabin temperature time series data. Therefore, in this embodiment, polynomial interpolation is used to increase the data volume of the second cabin temperature time series data to make it consistent with the data volume of the original cabin temperature time series data, thereby obtaining the target cabin high-frequency temperature time series data.
[0044] In some embodiments, the generating of the pattern sequence of the cold chain vehicle based on the target compartment high-frequency temperature time series data, the compartment temperature time series data and the external environment temperature time series data includes: Segmenting the target compartment high-frequency temperature time series data to obtain target compartment high-frequency temperature data in multiple initial time periods; Merging the target compartment high-frequency temperature data in the multiple initial time periods based on the characteristic vectors of the target compartment high-frequency temperature data in each initial time period to obtain the target compartment high-frequency temperature data in the multiple target time periods; Determining the cabin temperature data and the ambient temperature data in each target time period based on the cabin temperature time series data and the ambient temperature time series data; Determining a temperature mode in each time period based on the target compartment high-frequency temperature data, the compartment temperature data, and the external environment temperature data in each target time period; Based on the temperature patterns in each time period, a pattern sequence of cold chain vehicles is generated.
[0045] Here, the target compartment high-frequency temperature time series data can be divided into multiple initial time periods according to preset time intervals or according to natural change points of the data (such as points where the temperature change rate changes significantly). Then, feature vectors are calculated for each initial time period. These feature vectors may include average temperature, temperature change rate, duration, etc. Then, the weighted distance between the feature vectors between adjacent initial time periods is calculated. If the weighted distance is less than the threshold, the adjacent initial time periods are merged into a longer target time period. Finally, based on the analysis of the target compartment high-frequency temperature data, external ambient temperature, and compartment temperature data of consecutive target time periods, the temperature change pattern in each time period is identified. Finally, the temperature patterns in each time period are combined in chronological order to form a complete pattern sequence in the cold chain vehicle transportation process.
[0046] In some examples, the target cabin high-frequency temperature time series data can be first subjected to a second-order derivative to determine the peaks and troughs after the second-order derivative; then, based on the peaks and troughs, the first target cabin high-frequency temperature time series data can be segmented to obtain the target cabin high-frequency temperature data in multiple initial time periods.
[0047] Here, the temperature modes in this embodiment can be divided into: normal temperature stable state mode, power-on stable state mode, cooling off mode, cooling door open mode, heating off mode, heating door open mode, cooling on mode, cooling door closed mode, heating on mode, heating door closed mode, and horizontal temperature state mode. Specifically, refer to the following table 1.
[0048] The cooling and heating modes in each target time period in this embodiment can be determined by the temperature difference parameter t_diff at each time point in each target time period.
[0049] Specifically, the calculation formula of the temperature difference parameter t_diff refers to the following formula: ; Among them, t_weather is the external environment temperature, and t_truck is the high-frequency temperature data of the target vehicle compartment (or vehicle compartment temperature data).
[0050] Here, the average of t_diff in each target time period is calculated. If the average is less than 0, it is a heating mode. If it is greater than 0, it is a cooling mode. If the average is equal to 0, thresh_diff is reduced. This judgment process is continued until the mode judgment is successful.
[0051] Table 1 Temperature modes and their judgment conditions
[0052] The method for identifying temperature anomalies in cold chain vehicles provided by the present invention automatically processes and classifies patterns of original cold chain vehicle data, compresses massive original data into pattern sequences, effectively reduces the burden of subsequent data analysis, and finally analyzes the pattern sequences to achieve efficient identification of temperature anomalies in cold chain vehicles.
[0053] The cold chain vehicle temperature anomaly identification device provided by the present invention is described below. The cold chain vehicle temperature anomaly identification device described below and the cold chain vehicle temperature anomaly identification method described above can be referenced to each other.
[0054] Figure 2 : is a schematic diagram of the structure of the device for identifying abnormal temperature of cold chain vehicles provided by the present invention, such as Figure 2 As shown, the device for identifying abnormal temperature of cold chain vehicles includes the following.
[0055] The first identification module 210 is used to obtain the time series data of the compartment temperature of the cold chain vehicle and the time series data of the external environment temperature; The second identification module 220 is used to obtain target compartment high-frequency temperature time series data corresponding to the compartment temperature time series data, wherein the target compartment high-frequency temperature time series data is a high-frequency component corresponding to the compartment temperature time series data, and the temperature conversion range and data volume of the target compartment high-frequency temperature time series data are equal to those of the compartment temperature time series data; The third identification module 230 is used to generate a pattern sequence of cold chain vehicles based on the target compartment high-frequency temperature time series data, the compartment temperature time series data and the external environment temperature time series data, wherein the pattern sequence includes temperature patterns in a plurality of consecutive target time periods; The fourth recognition module 240 is used to identify abnormal temperature patterns of cold chain vehicles based on the pattern sequence of the cold chain vehicles.
[0056] The device for identifying abnormal temperature of cold chain vehicles provided by the present invention first obtains the compartment temperature time series data and the external environment temperature time series data of the cold chain vehicle; then obtains the target compartment high-frequency temperature time series data corresponding to the compartment temperature time series data; finally, based on the target compartment high-frequency temperature time series data, the compartment temperature time series data and the external environment temperature time series data, generates a pattern sequence of the cold chain vehicle, the pattern sequence includes temperature patterns under multiple consecutive target time periods; based on the pattern sequence of the cold chain vehicle, performs abnormal temperature pattern recognition on the cold chain vehicle. The present invention automatically processes and classifies the original cold chain vehicle data, compresses the massive original data into a pattern sequence, effectively reduces the burden of subsequent data analysis, and finally analyzes the pattern sequence to achieve efficient recognition of abnormal temperature of cold chain vehicles.
[0057] Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3 As shown, the electronic device may include: a processor 310, a communications interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communications interface 320 and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the cold chain vehicle temperature abnormality identification method, which includes the following steps: Obtain the time series data of the compartment temperature of the cold chain vehicle and the time series data of the external environment temperature; Acquire target compartment high-frequency temperature time series data corresponding to the compartment temperature time series data, wherein the target compartment high-frequency temperature time series data is a high-frequency component corresponding to the compartment temperature time series data, and the temperature conversion range and data volume of the target compartment high-frequency temperature time series data are equal to those of the compartment temperature time series data; Generate a pattern sequence of cold chain vehicles based on the target compartment high-frequency temperature time series data, the compartment temperature time series data, and the external environment temperature time series data, wherein the pattern sequence includes temperature patterns under multiple consecutive target time periods; Based on the pattern sequence of the cold chain vehicle, abnormal temperature patterns of the cold chain vehicle are identified.
[0058] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.
[0059] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the method for identifying abnormal temperature of cold chain vehicles provided by the above-mentioned methods. The method includes the following steps.
[0060] Obtain the time series data of the compartment temperature of the cold chain vehicle and the time series data of the external environment temperature; Acquire target compartment high-frequency temperature time series data corresponding to the compartment temperature time series data, wherein the target compartment high-frequency temperature time series data is a high-frequency component corresponding to the compartment temperature time series data, and the temperature conversion range and data volume of the target compartment high-frequency temperature time series data are equal to those of the compartment temperature time series data; Generate a pattern sequence of cold chain vehicles based on the target compartment high-frequency temperature time series data, the compartment temperature time series data, and the external environment temperature time series data, wherein the pattern sequence includes temperature patterns under multiple consecutive target time periods; Based on the pattern sequence of the cold chain vehicle, abnormal temperature patterns of the cold chain vehicle are identified.
[0061] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for identifying abnormal temperature of cold chain vehicles provided by the above-mentioned methods is implemented, and the method includes the following steps.
[0062] Obtain the time series data of the compartment temperature of the cold chain vehicle and the time series data of the external environment temperature; Acquire target compartment high-frequency temperature time series data corresponding to the compartment temperature time series data, wherein the target compartment high-frequency temperature time series data is a high-frequency component corresponding to the compartment temperature time series data, and the temperature conversion range and data volume of the target compartment high-frequency temperature time series data are equal to those of the compartment temperature time series data; Generate a pattern sequence of cold chain vehicles based on the target compartment high-frequency temperature time series data, the compartment temperature time series data, and the external environment temperature time series data, wherein the pattern sequence includes temperature patterns under multiple consecutive target time periods; Based on the pattern sequence of the cold chain vehicle, abnormal temperature patterns of the cold chain vehicle are identified.
[0063] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.
[0064] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0065] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.< / e> < / e>
Claims
1. A method for identifying abnormal temperature of cold chain vehicles, characterized in that: The method comprises: Obtain the time series data of the compartment temperature of the cold chain vehicle and the time series data of the external environment temperature; Acquire target compartment high-frequency temperature time series data corresponding to the compartment temperature time series data, wherein the target compartment high-frequency temperature time series data is a high-frequency component corresponding to the compartment temperature time series data, and the temperature conversion range and data volume of the target compartment high-frequency temperature time series data are equal to those of the compartment temperature time series data; Generate a pattern sequence of cold chain vehicles based on the target compartment high-frequency temperature time series data, the compartment temperature time series data, and the external environment temperature time series data, wherein the pattern sequence includes temperature patterns under multiple consecutive target time periods; Based on the pattern sequence of the cold chain vehicle, abnormal temperature patterns of the cold chain vehicle are identified.
2. The method for identifying abnormal temperature of cold chain vehicles according to claim 1, characterized in that: The time series data of the compartment temperature of the cold chain vehicle and the time series data of the external environment temperature are obtained in the following manner: Acquire original cold chain data of the cold chain vehicle, wherein the original cold chain data includes the first vehicle longitude and latitude and the first compartment temperature of the cold chain vehicle at each data recording time point; Based on the preset time window, the vehicle longitude and latitude and the compartment temperature of the cold chain vehicle at each data recording time point are downsampled and linearly interpolated to obtain the second vehicle longitude and latitude and the second compartment temperature of the cold chain vehicle in each time window; Based on the latitude and longitude of the second vehicle and historical weather data of the cold chain vehicle in each time window, obtaining the external environment temperature of the cold chain vehicle in each time window; Based on the compartment temperature of the cold chain vehicle in each time window, obtaining the compartment temperature time series data of the cold chain vehicle; Based on the external ambient temperature of the cold chain vehicle in each time window, the external ambient temperature time series data of the cold chain vehicle is obtained.
3. The method for identifying abnormal temperature of cold chain vehicles according to claim 1, characterized in that: The step of obtaining the high-frequency temperature time series data of the vehicle compartment corresponding to the vehicle compartment temperature time series data includes: Performing 4-level wavelet decomposition on the cabin temperature time series data, and using the decomposed high-frequency components as the first cabin high-frequency temperature time series data; Shifting and scaling the first compartment high-frequency temperature time series data to obtain second compartment temperature time series data having a temperature conversion range equal to that of the compartment temperature time series data; Polynomial interpolation is performed on the second compartment high-frequency temperature time series data to obtain target compartment high-frequency temperature time series data having the same data volume as the compartment temperature time series data.
4. The method for identifying abnormal temperature of cold chain vehicles according to claim 1, characterized in that: The generating of the pattern sequence of the cold chain vehicle based on the target compartment high-frequency temperature time series data, the compartment temperature time series data and the external environment temperature time series data includes: Segmenting the target compartment high-frequency temperature time series data to obtain target compartment high-frequency temperature data in multiple initial time periods; Merging the target compartment high-frequency temperature data in the multiple initial time periods based on the characteristic vectors of the target compartment high-frequency temperature data in each initial time period to obtain the target compartment high-frequency temperature data in the multiple target time periods; Determining the cabin temperature data and the ambient temperature data in each target time period based on the cabin temperature time series data and the ambient temperature time series data; Determining a temperature mode in each time period based on the target compartment high-frequency temperature data, the compartment temperature data, and the external environment temperature data in each target time period; Based on the temperature patterns in each time period, a pattern sequence of cold chain vehicles is generated.
5. The method for identifying abnormal temperature of cold chain vehicles according to claim 4, characterized in that: The step of segmenting the target compartment high-frequency temperature time series data to obtain target compartment high-frequency temperature data in multiple initial time periods includes: Performing a second-order derivative on the target compartment high-frequency temperature time series data to determine the peaks and troughs after the second-order derivative; Based on the peaks and troughs, the first target compartment high-frequency temperature time series data is segmented to obtain target compartment high-frequency temperature data in multiple initial time periods.
6. The method for identifying abnormal temperature of cold chain vehicles according to any one of claims 1 to 5, characterized in that: The temperature mode includes at least one of a normal temperature stable state mode, a power-on stable state mode, a cooling shutdown mode, a cooling door-open mode, a heating shutdown mode, a heating door-open mode, a cooling startup mode, a cooling door-closed mode, a heating startup mode, a heating door-closed mode, and a horizontal temperature state mode.
7. A device for identifying abnormal temperature of cold chain vehicles, characterized in that: include: The first identification module is used to obtain the time series data of the compartment temperature of the cold chain vehicle and the time series data of the external environment temperature; A second identification module is used to obtain target compartment high-frequency temperature time series data corresponding to the compartment temperature time series data, wherein the target compartment high-frequency temperature time series data is a high-frequency component corresponding to the compartment temperature time series data, and the temperature conversion range and data volume of the target compartment high-frequency temperature time series data are equal to those of the compartment temperature time series data; A third identification module is used to generate a pattern sequence of cold chain vehicles based on the target compartment high-frequency temperature time series data, the compartment temperature time series data and the external environment temperature time series data, wherein the pattern sequence includes temperature patterns under multiple consecutive target time periods; The fourth recognition module is used to identify abnormal temperature patterns of cold chain vehicles based on the pattern sequence of the cold chain vehicles.
8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, it implements the method for identifying abnormal temperature of a cold chain vehicle as described in any one of claims 1 to 6.
9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for identifying abnormal temperature of a cold chain vehicle as described in any one of claims 1 to 6 is implemented.
10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for identifying abnormal temperature of a cold chain vehicle as described in any one of claims 1 to 6 is implemented.