CN113091925B - Method and device for processing temperature breakpoints in cold chain logistics - Google Patents

Abstract

The present application provides a method and device for processing temperature breakpoints in cold chain logistics, wherein the method includes: collecting temperature data in cold chain logistics in real time; It is a temperature breakpoint; when it is determined as a temperature breakpoint, the category to which the temperature breakpoint belongs is determined through the neural network model identification; to be processed. The above solution solves the problem of temperature breakpoint false alarms in the existing cold chain logistics, and achieves the technical effect of effectively improving decision-making efficiency and accuracy.

Description

Method and device for processing temperature breakpoints in cold chain logistics

technical field

The present application belongs to the technical field of artificial intelligence, and in particular relates to a method and device for processing temperature breakpoints in cold chain logistics.

Background technique

The cold chain logistics of agricultural products is an effective way to reduce the loss and pollution of perishable fresh agricultural products and ensure their quality and safety by artificially refrigerating the production and circulation environment. By acquiring information and accurately controlling the environment of agricultural products in production, storage, transportation, sales and consumption, managers can greatly improve the market competitiveness of fresh agricultural products.

Temperature perception and control are the key elements for the efficiency of the cold chain. With the continuous development of information technology, the management and control of cold chain temperature has gradually shifted from operation control based on manual experience to intelligent real-time monitoring. Using intelligent sensor technology to monitor logistics and collect data, the cold chain environment can be restored to a certain extent by the management decision-making side and used as a basis for reasonable management and control.

The temperature breakpoint is the intersection of the temperature collection data curve and the temperature warning threshold caused by manual operation errors, equipment failures or monitoring errors. The appearance of temperature breakpoints not only reflects the failure of cold chain transportation from the side, which affects the quality of agricultural products, but also reduces the accuracy of temperature regulation to a certain extent. The control of temperature breakpoints in the cold chain has become an important part of ensuring the safety of agricultural product transportation.

In order to improve the management and control capabilities of cold chain logistics, the wireless temperature monitoring system will integrate temperature alarms to provide real-time early warning of the transportation environment, and provide managers with intuitive decision-making information to ensure the quality and safety of fresh agricultural products. The traditional cold chain temperature warning method is a threshold-triggered alarm. Once a temperature breakpoint occurs, an alarm is issued mechanically. However, not all temperature breakpoints indicate that the temperature of cold chain transportation is out of control. Therefore, using this method once the temperature breaks The method of mechanically issuing an alarm when a point appears, often there is a false alarm.

For the above problems, no effective solution has been proposed yet.

SUMMARY OF THE INVENTION

The purpose of the present application is to provide a method and a device for processing temperature breakpoints in cold chain logistics, which can solve the problem that false alarms of temperature breakpoints are prone to occur in existing cold chain logistics.

The present application provides a method and device for processing temperature breakpoints in cold chain logistics, which are realized as follows:

In one aspect, a method for processing temperature breakpoints in cold chain logistics is provided, the method comprising:

Real-time collection of temperature data in cold chain logistics;

Determine whether there is a temperature breakpoint in the temperature data collected in real time through the preset temperature threshold;

In the case of determining the temperature breakpoint, identify the category to which the temperature breakpoint belongs through the neural network model identification;

According to the category to which the determined temperature breakpoint belongs, the temperature breakpoint is processed in a manner associated with the determined category.

In one embodiment, the categories of temperature breakpoints include at least: long-period breakpoints, high-fluctuation breakpoints, and short-period low-fluctuation breakpoints.

In one embodiment, when the category to which the temperature breakpoint belongs is a long-period breakpoint or a high-fluctuation breakpoint, the temperature breakpoint is processed in a manner associated with the determined category, including:

Get the occurrence time of the temperature breakpoint;

Get where the temperature breakpoint occurs;

Determine the type of accident for temperature breakpoints;

Correlate the occurrence time, occurrence location and accident type to generate early warning information.

In one embodiment, when the category to which the temperature breakpoint belongs is a short-period low-fluctuation breakpoint, the temperature breakpoint is processed in a manner associated with the determined category, including:

Eliminate the temperature data of short-cycle and low-fluctuation breakpoints;

Through the Gaussian process model, the excluded temperature data is filled.

In one embodiment, the eliminated temperature data is filled by a Gaussian process model, including:

According to the Bayesian theory, the conditional probability distribution is obtained, wherein the conditional probability distribution obeys the Gaussian distribution;

Find the mean of the conditional probability distribution;

The average value obtained is used as the predicted complement value, and the excluded temperature data is complemented.

In one embodiment, determining whether the temperature data collected in real time is a temperature breakpoint is determined by a preset temperature threshold, including:

Determine whether the temperature data collected in real time satisfies the following formula:

|T _t,d -ε|≤μ

Among them, T _t,d represents the temperature data collected in real time at time t, μ represents the elastic setting value of the trigger temperature threshold, and ε represents the preset temperature threshold;

If the formula is satisfied, it is determined to be a temperature breakpoint, and if the formula is not satisfied, it is determined not to be a temperature breakpoint.

In one embodiment, the input data in the training data of the neural network model is feature information of each temperature breakpoint, wherein the feature information includes at least one of the following: breakpoint slope, upper threshold limit, lower threshold limit, fluctuation range, The fluctuation period; the output data in the training data of the neural network model is the category of temperature breakpoints.

In one embodiment, after the temperature breakpoint is processed in a manner associated with the determined category according to the category to which the determined temperature breakpoint belongs, the method further includes:

Statistics of temperature data and temperature breakpoints within a predetermined period of time;

generating an early warning curve for the predetermined time period according to the statistical temperature data and breakpoint data;

Visually display the warning curve.

In another aspect, a device for processing temperature breakpoints in cold chain logistics is provided, comprising:

The acquisition module is used for real-time acquisition of temperature data in cold chain logistics;

a first determination module, configured to determine whether the temperature data collected in real time is a temperature breakpoint through a preset temperature threshold;

The second determination module is used to identify and determine the category to which the temperature breakpoint belongs when it is determined to be a temperature breakpoint through a neural network model;

The processing module is configured to process the temperature breakpoint in a manner associated with the determined category according to the category to which the determined temperature breakpoint belongs.

In another aspect, a device for processing temperature breakpoints in cold chain logistics is provided, comprising:

The temperature data acquisition module is used to collect the temperature data in the cold chain logistics in real time;

The temperature breakpoint identification module is used to determine whether the temperature data collected in real time is a temperature breakpoint through a preset temperature threshold, and if it is determined to be a temperature breakpoint, the neural network model is used to identify and determine which temperature breakpoint belongs to. category;

The temperature breakpoint intelligent processing module is used to process the temperature breakpoint in a manner associated with the determined category according to the category to which the determined temperature breakpoint belongs.

In yet another aspect, an electronic device is provided, including a processor and a memory for storing instructions executable by the processor, and when the processor executes the instructions, the steps of the following method are implemented:

Real-time collection of temperature data in cold chain logistics;

Determine whether there is a temperature breakpoint in the temperature data collected in real time through the preset temperature threshold;

In the case of determining the temperature breakpoint, identify the category to which the temperature breakpoint belongs through the neural network model identification;

According to the category to which the determined temperature breakpoint belongs, the temperature breakpoint is processed in a manner associated with the determined category.

In yet another aspect, a computer-readable storage medium is provided on which computer instructions are stored, and when the instructions are executed, the steps of the following methods are implemented:

Real-time collection of temperature data in cold chain logistics;

Determine whether there is a temperature breakpoint in the temperature data collected in real time through the preset temperature threshold;

In the case of determining the temperature breakpoint, identify the category to which the temperature breakpoint belongs through the neural network model identification;

According to the category to which the determined temperature breakpoint belongs, the temperature breakpoint is processed in a manner associated with the determined category.

The method for processing temperature breakpoints in cold chain logistics provided by the present application collects temperature data in cold chain logistics in real time; then, through a preset temperature threshold, it is determined whether the temperature data collected in real time is a temperature breakpoint; In the case of a temperature breakpoint, the neural network model is used to identify and determine the category to which the temperature breakpoint belongs; and then according to the category to which the determined temperature breakpoint belongs, the temperature breakpoint is processed in a manner associated with the determined category. That is, it can classify and identify different types of temperature breakpoints, and make intelligent processing, thus solving the problem of temperature breakpoint false alarms that are prone to occur in the existing cold chain logistics, and effectively improving decision-making efficiency and accuracy. degree of technical effect.

Description of drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only These are some embodiments described in this application. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without any creative effort.

Fig. 1 is a method flow chart of an embodiment of a method for processing temperature breakpoints in cold chain logistics provided by the present application;

Fig. 2 is the module flow chart of the temperature breakpoint identification method of cold chain logistics provided by the application;

Fig. 3 is the temperature data acquisition module structure diagram provided by the application;

4 is a schematic diagram of a temperature breakpoint identification module provided by the present application;

Fig. 5 is the schematic diagram of missing data complement provided by this application;

6 is a block diagram of a hardware structure of an electronic device provided by the present application;

7 is a schematic structural diagram of an embodiment of a processing module for temperature breakpoints in cold chain logistics provided by the present application.

Detailed ways

In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described The embodiments are only a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the scope of protection of this application.

There will be false alarms in the existing temperature breakpoints, mainly because the existing temperature breakpoint alarms do not further excavate the characteristic information of the temperature breakpoints. False alarms caused by noise occur from time to time. If different types of temperature breakpoints can be classified and identified, and intelligent processing can be made, the decision-making efficiency and accuracy of managers can be effectively improved.

To this end, in this example, a method for processing temperature breakpoints in cold chain logistics is provided, and FIG. 1 is a method flowchart of an embodiment of the method for processing temperature breakpoints in cold chain logistics provided by the present application. Although the present application provides method operation steps or device structures as shown in the following embodiments or drawings, more or less operation steps or module units may be included in the method or device based on routine or without creative work. . In the steps or structures that logically do not have necessary causal relationship, the execution sequence of these steps or the module structure of the device are not limited to the execution sequence or module structure described in the embodiments of the present application and shown in the accompanying drawings. When the described method or module structure is applied in an actual device or terminal product, it can be executed sequentially or in parallel (for example, a parallel processor or multi-threaded processing method) according to the connection of the method or module structure shown in the embodiments or the accompanying drawings. environments, even distributed processing environments).

Specifically, as shown in FIG. 1 , the above-mentioned method for processing temperature breakpoints in cold chain logistics may include the following steps:

Step 101: collect temperature data in cold chain logistics in real time;

Step 102: Determine whether the temperature data collected in real time is a temperature breakpoint through a preset temperature threshold;

Step 103: In the case of determining the temperature breakpoint, identify and determine the category to which the temperature breakpoint belongs through the neural network model;

Specifically, the categories into which the above temperature breakpoints can be divided may include, but are not limited to, long-period breakpoints, high-fluctuation breakpoints, and short-period low-volatility breakpoints. Among them, the long-cycle breakpoints are mostly caused by intermittent human misoperation, and the high-fluctuation breakpoints are mainly caused by equipment failures or sudden temperature changes caused by the switch of the carriage. For short-period and low-fluctuation breakpoints, it is generally caused by system noise and has little impact on food quality.

Step 104: According to the category to which the determined temperature breakpoint belongs, the temperature breakpoint is processed in a manner associated with the determined category.

Different processing methods can be adopted for different types of temperature breakpoints. For example, if the category to which the temperature breakpoint belongs is a long-period breakpoint or a high-fluctuation breakpoint, the occurrence time of the temperature breakpoint can be obtained; the occurrence time of the temperature breakpoint can be obtained; Location; determine the accident type of the temperature breakpoint; associate the occurrence time, occurrence location and accident type to generate early warning information. If the category to which the temperature breakpoint belongs is a short-period and low-fluctuation breakpoint, the temperature data of the short-period and low-fluctuation breakpoint can be eliminated; the eliminated temperature data can be supplemented through the Gaussian process model.

Specifically, when the excluded temperature data is complemented by the Gaussian process model, the conditional probability distribution can be obtained according to Bayesian theory, wherein the conditional probability distribution obeys the Gaussian distribution; Mean value; the obtained mean value will be used as the predicted complement value, and the excluded temperature data will be complemented.

In the above example, the temperature data in the cold chain logistics is collected in real time; then, through the preset temperature threshold, it is determined whether the temperature data collected in real time is a temperature breakpoint; The network model identifies and determines the category to which the temperature breakpoint belongs; and then processes the temperature breakpoint in a manner associated with the determined category according to the category to which the determined temperature breakpoint belongs. That is, it can classify and identify different types of temperature breakpoints, and make intelligent processing, thus solving the problem of temperature breakpoint false alarms that are prone to occur in the existing cold chain logistics, and effectively improving decision-making efficiency and accuracy. degree of technical effect.

When the temperature breakpoint is determined based on the temperature data collected in real time, it may be determined whether the temperature data collected in real time is a temperature breakpoint through a preset temperature threshold. Specifically, it may be determined whether the temperature data collected in real time satisfies the following: formula:

|T _t,d -ε|≤μ

Among them, T _t,d represents the temperature data collected in real time at time t, μ represents the elastic setting value of the trigger temperature threshold, and ε represents the preset temperature threshold;

If the formula is satisfied, it is determined to be a temperature breakpoint, and if the formula is not satisfied, it is determined not to be a temperature breakpoint.

The input data in the training data of the above-mentioned neural network model can be the feature information of each temperature breakpoint, wherein the feature information can include but not limited to at least one of the following: breakpoint slope, upper threshold limit, lower threshold limit, fluctuation range, fluctuation Period; the output data in the training data of the above neural network model is the category of temperature breakpoints.

For the processed temperature data, it is possible to invert on the display screen and realize the early warning visualization of a specific scenario, that is, according to the category to which the determined temperature breakpoint belongs, after processing the temperature breakpoint in a manner associated with the determined category , the temperature data and temperature breakpoints within a predetermined period of time can be counted; an early warning curve of the predetermined period of time can be generated according to the statistical temperature data and breakpoint data; and the early warning curve can be visualized.

The above method will be described below with reference to a specific embodiment. However, it should be noted that the specific embodiment is only for better illustrating the present application, and does not constitute an improper limitation of the present application.

Considering that the existing temperature breakpoint alarms do not further excavate the characteristic information of temperature breakpoints, the occurrence of temperature breakpoints cannot fully characterize the runaway temperature of cold chain transportation, and false alarms caused by system noise occur from time to time. It can effectively improve the decision-making efficiency and accuracy of managers.

Based on this, in this example, a temperature breakpoint identification method and an intelligent monitoring device for cold chain logistics are provided to solve the problem of false alarms of cold chain temperature breakpoints, and to improve the accuracy of temperature regulation through intelligent processing. Visual human-computer interaction improves the credibility of the cold chain transportation process. Specifically, the monitoring device may be shown in Figure 2, including: a temperature data acquisition module, a temperature breakpoint identification module, and a temperature breakpoint intelligent processing module, wherein the temperature data acquisition module is used to realize the temperature perception and Storage, breakpoint identification module is used to identify temperature breakpoints in cold chain transportation and perform intelligent classification, and temperature breakpoint intelligent processing module is used to perform corresponding processing for different types of temperature breakpoints, including: data elimination and completion, intelligent alarm etc., and realize the continuous inversion and dynamic visualization of temperature.

The above three components are described in detail below:

1) A temperature data acquisition module, which utilizes NFC (Near Field Communication, short-range wireless communication) technology to realize real-time acquisition, storage and transmission of temperature data.

The NFC tag (1) may be provided with a temperature data acquisition module, and the temperature data acquisition module may include, as shown in FIG. 3: a temperature monitoring sensor (1-1) for continuous temperature sensing in the cold chain process; a memory (1-1) 2), connected with the temperature monitoring sensor, for storing the temperature data collected in real time; the first NFC sensor (1-3) is connected with the temperature monitoring module (1-1) for sending an instruction to drive the temperature monitoring module to collect temperature data; The first NFC sensor (1-3) is linked with the storage module (1-2) for acquiring temperature data stored in the storage module; The NFC sensor (2-1) is coupled to exchange data by means of wireless communication. The mobile device (2) may also be provided with an intelligent controller (2-2) and a display (2-3).

2) Temperature breakpoint identification module. This module is mainly divided into two steps to realize: identification and classification.

Step 1: By setting a certain temperature threshold ε, analyze the inversion relationship between temperature and time, and judge whether the real-time temperature data is a temperature breakpoint according to the following formula. If the following formula is satisfied, it means that it is a temperature breakpoint. If not, It means that it is not a temperature breakpoint:

|T _t,d -ε|≤μ

Among them, T _t,d represents the real-time temperature data at time t, and μ represents the elastic setting value of the trigger temperature threshold.

Step 2, use BP neural network algorithm to learn to realize the intelligent classification of temperature breakpoints, wherein, the input of this BP neural network is the characteristic information of each temperature breakpoint, for example: breakpoint slope, threshold upper and lower limit trigger, fluctuation amplitude, Fluctuation period, etc., the output can be shown in Figure 4, including: long-period breakpoints, high-volatility breakpoints, and short-period low-volatility breakpoints.

3) The temperature breakpoint intelligent processing module. This module can be divided into three parts: data early warning, data elimination and complementation, data inversion and visualization.

During data warning, according to the type of breakpoint, warning control can be performed as follows:

Specific scenario warnings for long-period breakpoints and high-volatility breakpoints. That is, associate the time when the temperature breakpoint occurs with the location of the accident, and associate the breakpoint type with the accident type. Among them, long-cycle breakpoints are mostly caused by intermittent human misoperation, and high-fluctuation breakpoints are mainly caused by equipment failures or carriage switches. sudden temperature change. Refine the warning rules according to the actual production process, and conduct multi-source information analysis, so as to improve the pertinence and accuracy of the warning;

For short-period and low-fluctuation breakpoints, since they are most likely to be caused by system noise and have little impact on food quality, in order to avoid frequent false alarms, the data in this type of breakpoint interval are eliminated, and the Gaussian process model is used to predict Complement, specifically, can be done as follows:

In the regression prediction, the implicit function of the undetermined cabin temperature change is set as f(x). The Gaussian process model assumes that f(x) obeys a Gaussian distribution, and the specific expression is:

f(x)～N(μ(x),k(x,x'))

Among them, μ(x) represents the Gaussian process mean function, and k(x, x') represents the covariance function. In regression prediction problems, the collected sequences usually contain Gaussian white noise as follows:

的噪声，则含噪温度序列y(x)可以表示为：If we consider that the above expectation is 0 and the variance is

noise, then the noisy temperature sequence y(x) can be expressed as:

y(x)=f(x)+ω(x)

And, y(x) still obeys the Gaussian distribution:

Among them, δ _ij is the Kronecker function, representing the element of the unit matrix; i, j are the free indexes, representing the coordinates of the matrix elements, and the value of δ _ij obeys the following rules:

where n represents the regression data dimension.

Usually, the mean function is normalized to μ(x)=0 to facilitate later data processing, and k(x,x') is expressed as a square exponential function as follows:

为核函数的方差，l为特征宽度，分别控制输入变量局部相关性和模型光滑程度。超参数向量Θ＝{l,σ_f,σ_v}可通过极大似然估计算法(Maximum LikelihoodEstimation， MLE)学习获取。给定观测数据Y＝{y_t1,y_t2,...,y_ti}，通过极大化似然函数估计参数如下：in,

is the variance of the kernel function, and l is the feature width, which respectively control the local correlation of the input variables and the smoothness of the model. The hyperparameter vector Θ={l, σ _f , σ _v } can be obtained by learning through the maximum likelihood estimation algorithm (Maximum Likelihood Estimation, MLE). Given observation data Y = {y _t1 , y _t2 ,..., y _ti }, the parameters are estimated by maximizing the likelihood function as follows:

表示超参数估计结果，似然函数极大化则可以通过如下公式对数似然函数lnL(Θ₀|Y)求偏导得到：Among them, L(Θ|Y)=∑lnp(Θ|Y) represents the likelihood function,

Represents the result of hyperparameter estimation, and the maximization of the likelihood function can be obtained by calculating the partial derivative of the log-likelihood function lnL(Θ ₀ |Y) by the following formula:

For the completion of the regression prediction of the temperature breakpoint elimination value, the conditional probability distribution P(y _t+1 |y _t ) can be obtained first according to Bayesian theory:

P(y _t+1 |y _t )=P(y _t+1 ,y _t )/P(y _t )

And take its mean as the final predicted padding value at sample x _t+1 . According to the Gaussian assumption, P(y _t+1 |y _t ) obeys the Gaussian distribution as follows:

Now suppose that the molecular expression P(y _t+1 |y _t ) is as follows:

表示低秩近似简化核矩阵，可以由学习样本训练得到。make

Represents a low-rank approximate reduced kernel matrix, which can be obtained by training with learning samples.

Among them, κ is the last value in the lower right corner of the matrix C _t+1 , and k and k ^T are the column vector and row vector for the last removal of κ, respectively. Then its inverse matrix is:

in,

将其作为剔除短周期低波动断点x_t+1处的预测补齐值。Therefore, the mean of the final conditional probability distribution P(y _t+1 |y _t ) is

Take it as the predicted padding value at x _t+1 , which eliminates short-period and low-volatility breakpoints.

As shown in Figure 5, it is a schematic diagram of an example of filling missing data in the temperature monitoring of the fruit cold chain process.

In the above example, the collection of circulation environment temperature data is performed at fixed time intervals, the training data is the temperature observations in the cold chain process, and the Gaussian process regression obtains the regression information in the form of Gaussian distribution, in which the mean value of the Gaussian distribution forms the regression curve, The standard deviation of the distribution provides a confidence interval, and at the same time, combined with Bayesian theory, the missing data that is excluded is predicted. For the processed temperature data, it is possible to invert on the display screen and realize early warning visualization of specific scenarios.

In the above example, a method for identifying temperature breakpoints in cold chain logistics and an intelligent monitoring device are provided, which are mainly used for intelligent early warning of temperature during cold chain transportation and visualization of actual transportation environment information. Intelligent classification processing can restore the environmental changes of cold chain transportation to a greater extent, and intelligently process temperature breakpoints to provide different early warning methods according to breakpoint categories, so as to improve the efficiency of management decision-making; use Gaussian process modeling to The short-period and low-fluctuation breakpoint data of temperature is eliminated and supplemented, which improves the reliability of the data and the control accuracy; the collected temperature data is inverted and visualized in the form of "time-temperature", which can be displayed to managers and consumers. Provide a more intuitive user-friendly interactive experience.

That is, intelligent perception, intelligent early warning and visual management of temperature information during cold chain transportation can be realized. Among them, intelligent perception can realize temperature collection, data processing and temperature breakpoint information extraction; intelligent early warning can realize scene-based alarm; visualization can provide human-computer interaction services. In this way, the cold chain transportation process can be restored more effectively, more humanized services can be provided for managers and consumers, the decision-making efficiency and regulation accuracy of managers can be improved, and the quality credibility of fresh agricultural products can be enhanced.

The method embodiments provided by the foregoing embodiments of the present application may be executed in a mobile terminal, a computer terminal, or a similar computing device. Taking the operation on an electronic device as an example, FIG. 6 is a block diagram of the hardware structure of the electronic device provided in the present application for a method for processing temperature breakpoints in cold chain logistics. As shown in FIG. 6 , the electronic device 10 may include one or more (only one is shown in the figure) processor 02 (the processor 02 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA) , a memory 04 for storing data, and a transmission module 06 for communication functions. Those of ordinary skill in the art can understand that the structure shown in FIG. 6 is only a schematic diagram, which does not limit the structure of the above electronic device. For example, the electronic device 10 may also include more or fewer components than shown in FIG. 6 , or have a different configuration than that shown in FIG. 6 .

The memory 04 can be used to store software programs and modules of application software, such as program instructions/modules corresponding to the method for processing temperature breakpoints in cold chain logistics in the embodiments of the present application, the processor 02 runs the software programs stored in the memory 04 by running the software program. and modules, so as to perform various functional applications and data processing, that is, to realize the processing method of temperature breakpoints in cold chain logistics of the above application programs. Memory 04 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 04 may further include memory located remotely from processor 02, which may be connected to electronic device 10 via a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

The transmission module 06 is used to receive or transmit data via a network. The specific example of the above-mentioned network may include the wireless network provided by the communication provider of the electronic device 10 . In one example, the transmission module 06 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through the base station so as to communicate with the Internet. In an example, the transmission module 06 may be a radio frequency (Radio Frequency, RF) module, which is used to communicate with the Internet in a wireless manner.

At the software level, the processing device for temperature breakpoints in the above-mentioned cold chain logistics can be as shown in Figure 7, and can include:

The collection module 701 is used for real-time collection of temperature data in cold chain logistics;

A determination module 702, configured to determine whether the temperature data collected in real time is a temperature breakpoint through a preset temperature threshold;

The identification module 703 is configured to identify and determine the category to which the temperature breakpoint belongs when it is determined to be a temperature breakpoint through a neural network model;

The processing module 704 is configured to process the temperature breakpoint in a manner associated with the determined category according to the category to which the determined temperature breakpoint belongs.

In one embodiment, the categories of temperature breakpoints may at least include: long-period breakpoints, high-fluctuation breakpoints, and short-period low-fluctuation breakpoints.

In one embodiment, the above-mentioned processing module 704 can be specifically used to obtain the occurrence time of the temperature breakpoint; obtain the occurrence location of the temperature breakpoint; determine the accident type of the temperature breakpoint; associate the occurrence time, the occurrence place and the accident type, Generate alert messages.

In one embodiment, the above-mentioned processing module 704 can specifically be used to eliminate the temperature data of short-period and low-fluctuation breakpoints; the eliminated temperature data is complemented by the Gaussian process model.

In one embodiment, using a Gaussian process model to complete the excluded temperature data may include: obtaining a conditional probability distribution according to Bayesian theory, wherein the conditional probability distribution obeys a Gaussian distribution; obtaining the conditional probability distribution The mean value; the obtained mean value is used as the predicted complement value, and the excluded temperature data is complemented.

In one embodiment, the determining module 702 may be specifically configured to determine whether the temperature data collected in real time satisfies the following formula:

|T _t,d -ε|≤μ

Among them, T _t,d represents the temperature data collected in real time at time t, μ represents the elastic setting value of the trigger temperature threshold, and ε represents the preset temperature threshold;

If the formula is satisfied, it is determined to be a temperature breakpoint, and if the formula is not satisfied, it is determined not to be a temperature breakpoint.

In one embodiment, the input data in the training data of the neural network model is feature information of each temperature breakpoint, wherein the feature information includes at least one of the following: breakpoint slope, upper threshold limit, lower threshold limit, fluctuation range, The fluctuation period; the output data in the training data of the neural network model is the category of temperature breakpoints.

In one embodiment, the device for processing temperature breakpoints in the cold chain logistics may, after processing the temperature breakpoints in a manner associated with the determined category according to the category to which the determined temperature breakpoints belong, may count a predetermined period of time. The temperature data and temperature breakpoints are obtained; according to the statistical temperature data and breakpoint data, an early warning curve of the predetermined time period is generated; and the early warning curve is visually displayed.

The embodiments of the present application also provide specific implementations of an electronic device that can realize all the steps in the method for processing temperature breakpoints in cold chain logistics in the above-mentioned embodiments. The electronic device specifically includes the following content: a processor ) memory (memory), communication interface (Communications Interface) and bus; wherein, described processor, memory, communication interface complete mutual communication through described bus; Described processor is used for invoking the computer program in described memory. When the processor executes the computer program, all steps in the method for processing temperature breakpoints in cold chain logistics in the above-mentioned embodiments are realized. For example, when the processor executes the computer program, the following steps are realized:

Step 1: Collect temperature data in cold chain logistics in real time;

Step 2: Determine whether the temperature data collected in real time is a temperature breakpoint through a preset temperature threshold;

Step 3: In the case of determining the temperature breakpoint, identify the category to which the temperature breakpoint belongs through the neural network model identification;

Step 4: According to the category to which the determined temperature breakpoint belongs, use the method associated with the determined category to carry out the analysis of the temperature breakpoint.

It can be seen from the above description that in the embodiment of the present application, the temperature data in the cold chain logistics is collected in real time; then, through the preset temperature threshold, it is determined whether the temperature data collected in real time is a temperature breakpoint; if it is determined to be a temperature breakpoint Then, the category to which the temperature breakpoint belongs is identified and determined by the neural network model; and then the temperature breakpoint is processed in a manner associated with the determined category according to the category to which the determined temperature breakpoint belongs. That is, it can classify and identify different types of temperature breakpoints, and make intelligent processing, thus solving the problem of temperature breakpoint false alarms that are prone to occur in the existing cold chain logistics, and effectively improving decision-making efficiency and accuracy. degree of technical effect.

The embodiments of the present application also provide a computer-readable storage medium capable of realizing all the steps in the method for processing temperature breakpoints in cold chain logistics in the above-mentioned embodiments, where a computer program is stored on the computer-readable storage medium. When the computer program is executed by the processor, all steps of the method for processing temperature breakpoints in cold chain logistics in the above-mentioned embodiment are realized. For example, when the processor executes the computer program, the following steps are realized:

Step 1: Collect temperature data in cold chain logistics in real time;

Step 2: Determine whether the temperature data collected in real time is a temperature breakpoint through a preset temperature threshold;

Step 3: In the case of determining the temperature breakpoint, identify the category to which the temperature breakpoint belongs through the neural network model identification;

Step 4: According to the category to which the determined temperature breakpoint belongs, use the method associated with the determined category to carry out the analysis of the temperature breakpoint.

It can be seen from the above description that in the embodiment of the present application, the temperature data in the cold chain logistics is collected in real time; then, through the preset temperature threshold, it is determined whether the temperature data collected in real time is a temperature breakpoint; if it is determined to be a temperature breakpoint Then, the category to which the temperature breakpoint belongs is identified and determined by the neural network model; and then the temperature breakpoint is processed in a manner associated with the determined category according to the category to which the determined temperature breakpoint belongs. That is, it can classify and identify different types of temperature breakpoints, and make intelligent processing, thus solving the problem of temperature breakpoint false alarms that are prone to occur in the existing cold chain logistics, and effectively improving decision-making efficiency and accuracy. degree of technical effect.

Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the hardware+program embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for related parts, please refer to the partial description of the method embodiment.

The foregoing describes specific embodiments of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that in the embodiments and still achieve desirable results. Additionally, the processes depicted in the figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Although the present application provides method operation steps as described in the embodiments or flow charts, more or less operation steps may be included based on routine or non-creative work. The sequence of steps enumerated in the embodiments is only one of the execution sequences of many steps, and does not represent the only execution sequence. When an actual device or client product is executed, the methods shown in the embodiments or the accompanying drawings may be executed sequentially or in parallel (for example, a parallel processor or a multi-threaded processing environment).

The systems, devices, modules or units described in the above embodiments may be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, an in-vehicle human-computer interaction device, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet A computer, wearable device, or a combination of any of these devices.

Although the embodiments of the present specification provide method operation steps as described in the embodiments or flow charts, more or less operation steps may be included based on conventional or non-creative means. The sequence of steps enumerated in the embodiments is only one of the execution sequences of many steps, and does not represent the only execution sequence. When an actual device or terminal product is executed, it can be executed sequentially or in parallel according to the methods shown in the embodiments or the drawings (eg, a parallel processor or multi-threaded processing environment, or even a distributed data processing environment). The terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, product or device comprising a list of elements includes not only those elements, but also others not expressly listed elements, or also include elements inherent to such a process, method, product or device. Without further limitation, it does not preclude the presence of additional identical or equivalent elements in a process, method, product or apparatus comprising the stated elements.

For the convenience of description, when describing the above device, the functions are divided into various modules and described respectively. Of course, when implementing the embodiments of this specification, the functions of each module may be implemented in the same one or more software and/or hardware, and the modules implementing the same function may be implemented by a combination of multiple sub-modules or sub-units. The apparatus embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated. to another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

Those skilled in the art also know that, in addition to implementing the controller in the form of pure computer-readable program code, the controller can be implemented as logic gates, switches, application-specific integrated circuits, programmable logic controllers and embedded devices by logically programming the method steps. The same function can be realized in the form of a microcontroller, etc. Therefore, such a controller can be regarded as a hardware component, and the devices included therein for realizing various functions can also be regarded as a structure within the hardware component. Or even, the means for implementing various functions can be regarded as both a software module implementing a method and a structure within a hardware component.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

Memory may include non-persistent memory in computer readable media, random access memory (RAM) and/or non-volatile memory in the form of, for example, read only memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media includes both persistent and non-permanent, removable and non-removable media, and storage of information may be implemented by any method or technology. Information may be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Flash Memory or other memory technology, Compact Disc Read Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media, such as modulated data signals and carrier waves.

As will be appreciated by one skilled in the art, the embodiments of the present specification may be provided as a method, a system or a computer program product. Accordingly, embodiments of this specification may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present specification may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

Embodiments of this specification may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. Embodiments of the description may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including storage devices.

Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, as for the system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and for related parts, please refer to the partial descriptions of the method embodiments. In the description of this specification, description with reference to the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples", etc., mean specific features described in connection with the embodiment or example , structures, materials, or features are included in at least one example or example of embodiments of this specification. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, those skilled in the art may combine and combine the different embodiments or examples described in this specification, as well as the features of the different embodiments or examples, without conflicting each other.

The above descriptions are merely examples of the embodiments of the present specification, and are not intended to limit the embodiments of the present specification. For those skilled in the art, various modifications and variations can be made to the embodiments of the present specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present specification shall be included within the scope of the claims of the embodiments of the present specification.

Claims (8)

1. a processing method of temperature breakpoint in cold chain logistics, is characterized in that, described method comprises: Real-time collection of temperature data in cold chain logistics; Determine whether there is a temperature breakpoint in the temperature data collected in real time through the preset temperature threshold; In the case of determining the temperature breakpoint, identify the category to which the temperature breakpoint belongs through the neural network model identification; According to the category to which the determined temperature breakpoint belongs, the temperature breakpoint is processed in a manner associated with the determined category; Among them, the categories of temperature breakpoints include at least: long-period breakpoints, high-fluctuation breakpoints, and short-period low-fluctuation breakpoints; if the category to which the temperature breakpoints belong is short-period low-fluctuation breakpoints, the category determined by The temperature breakpoints are processed in a correlated manner, including: eliminating the temperature data of short-period and low-fluctuation breakpoints; using the Gaussian process model to complement the eliminated temperature data; Complementing the excluded temperature data through the Gaussian process model includes: obtaining the conditional probability distribution according to Bayesian theory, wherein the conditional probability distribution obeys the Gaussian distribution; obtaining the mean value of the conditional probability distribution; The average value taken is used as the predicted complement value, and the excluded temperature data is complemented; Among them, through the preset temperature threshold, it is determined whether the temperature data collected in real time is a temperature breakpoint, including: Determine whether the temperature data collected in real time satisfies the following formula: |T _t,d -ε|≤μ Among them, T _t,d represents the temperature data collected in real time at time t, μ represents the elastic setting value of the trigger temperature threshold, and ε represents the preset temperature threshold; If the formula is satisfied, it is determined to be a temperature breakpoint, and if the formula is not satisfied, it is determined not to be a temperature breakpoint. 2 . The method according to claim 1 , wherein when the category to which the temperature breakpoint belongs is a long-period breakpoint or a high-fluctuation breakpoint, the temperature breakpoint is processed in a manner associated with the determined category. 3 . ,include: Get the occurrence time of the temperature breakpoint; Get where the temperature breakpoint occurs; Determine the type of accident for temperature breakpoints; Correlate the occurrence time, occurrence location and accident type to generate early warning information. 3. The method according to claim 1, wherein the input data in the training data of the neural network model is the characteristic information of each temperature breakpoint, wherein the characteristic information comprises at least one of the following: the breakpoint slope, Upper threshold, lower threshold, fluctuation range, fluctuation period; the output data in the training data of the neural network model is the category of temperature breakpoints. 4. The method according to any one of claims 1 to 3, characterized in that, after processing the temperature breakpoint in a manner associated with the determined category according to the category to which the determined temperature breakpoint belongs, further comprising: : Statistics of temperature data and temperature breakpoints within a predetermined period of time; generating an early warning curve for the predetermined time period according to the statistical temperature data and breakpoint data; Visually display the warning curve. 5. A processing device for temperature breakpoint in cold chain logistics, characterized in that, comprising: The acquisition module is used for real-time acquisition of temperature data in cold chain logistics; a first determination module, configured to determine whether the temperature data collected in real time is a temperature breakpoint through a preset temperature threshold; The second determination module is used to identify and determine the category to which the temperature breakpoint belongs when it is determined to be a temperature breakpoint through a neural network model; The processing module is used to process the temperature breakpoint in a manner associated with the determined category according to the category to which the determined temperature breakpoint belongs; Among them, the categories of temperature breakpoints include at least: long-period breakpoints, high-fluctuation breakpoints, and short-period low-fluctuation breakpoints; if the category to which the temperature breakpoints belong is short-period low-fluctuation breakpoints, the category determined by The temperature breakpoints are processed in a correlated manner, including: eliminating the temperature data of short-period and low-fluctuation breakpoints; using the Gaussian process model to complement the eliminated temperature data; Complementing the excluded temperature data through the Gaussian process model includes: obtaining the conditional probability distribution according to Bayesian theory, wherein the conditional probability distribution obeys the Gaussian distribution; obtaining the mean value of the conditional probability distribution; The average value taken is used as the predicted complement value, and the excluded temperature data is complemented; Among them, through the preset temperature threshold, it is determined whether the temperature data collected in real time is a temperature breakpoint, including: Determine whether the temperature data collected in real time satisfies the following formula: |T _t,d -ε|≤μ Among them, T _t,d represents the temperature data collected in real time at time t, μ represents the elastic setting value of the trigger temperature threshold, and ε represents the preset temperature threshold; If the formula is satisfied, it is determined to be a temperature breakpoint, and if the formula is not satisfied, it is determined not to be a temperature breakpoint. 6. A processing device for temperature breakpoint in cold chain logistics, characterized in that, comprising: The temperature data acquisition module is used to collect the temperature data in the cold chain logistics in real time; The temperature breakpoint identification module is used to determine whether the temperature data collected in real time is a temperature breakpoint through a preset temperature threshold, and if it is determined to be a temperature breakpoint, the neural network model is used to identify and determine which temperature breakpoint belongs to. category; The temperature breakpoint intelligent processing module is used to process the temperature breakpoint in a manner associated with the determined category according to the category to which the determined temperature breakpoint belongs. Among them, the categories of temperature breakpoints include at least: long-period breakpoints, high-fluctuation breakpoints, and short-period low-fluctuation breakpoints; if the category to which the temperature breakpoints belong is short-period low-fluctuation breakpoints, the category determined by The temperature breakpoints are processed in a correlated manner, including: eliminating the temperature data of short-period and low-fluctuation breakpoints; and filling the eliminated temperature data through the Gaussian process model. 7. An electronic device comprising a processor and a memory for storing processor-executable instructions that, when executed by the processor, implement the steps of the method of claim 1 . 8. A computer-readable storage medium having stored thereon computer instructions that, when executed, implement the steps of the method of claim 1 .

Images