CN117474427B - Intelligent pallet cold chain tracing method based on Internet of things technology - Google Patents
Intelligent pallet cold chain tracing method based on Internet of things technology Download PDFInfo
- Publication number
- CN117474427B CN117474427B CN202311810803.9A CN202311810803A CN117474427B CN 117474427 B CN117474427 B CN 117474427B CN 202311810803 A CN202311810803 A CN 202311810803A CN 117474427 B CN117474427 B CN 117474427B
- Authority
- CN
- China
- Prior art keywords
- data
- monitoring
- monitoring data
- parameters
- intelligent
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000005516 engineering process Methods 0.000 title claims abstract description 16
- 238000012544 monitoring process Methods 0.000 claims abstract description 388
- 238000001914 filtration Methods 0.000 claims abstract description 19
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 9
- 230000002159 abnormal effect Effects 0.000 claims description 82
- 230000035945 sensitivity Effects 0.000 claims description 41
- 238000004364 calculation method Methods 0.000 claims description 27
- 238000013507 mapping Methods 0.000 claims description 20
- 238000012216 screening Methods 0.000 claims description 16
- 238000010606 normalization Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 description 12
- 230000005856 abnormality Effects 0.000 description 8
- 230000003044 adaptive effect Effects 0.000 description 6
- 238000012937 correction Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000009499 grossing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000010206 sensitivity analysis Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0832—Special goods or special handling procedures, e.g. handling of hazardous or fragile goods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
- G06F16/2379—Updates performed during online database operations; commit processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/64—Protecting data integrity, e.g. using checksums, certificates or signatures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0833—Tracking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0838—Historical data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
- G06Q10/0875—Itemisation or classification of parts, supplies or services, e.g. bill of materials
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Computer Security & Cryptography (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Bioethics (AREA)
- General Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of data processing of intelligent tray monitoring data, in particular to an intelligent tray cold chain tracing method based on the internet of things technology. According to the invention, the integral fluctuation characteristics of the monitoring data, the distribution differences among different monitoring data in the same intelligent tray and the local difference characteristics of the monitoring data corresponding to the same monitoring parameter in different intelligent trays are synthesized, the self-adaptive weight of each data point in each monitoring data is obtained, the monitoring data is accurately denoised by utilizing a filtering algorithm based on the self-adaptive weight, the denoised monitoring data is uplink, the accurate monitoring data is stored, and the tracing of related personnel is facilitated.
Description
Technical Field
The invention relates to the technical field of data processing of intelligent tray monitoring data, in particular to an intelligent tray cold chain tracing method based on the internet of things technology.
Background
Tracing typically records the traced and analyzed data in a non-tamperable block in the blockchain, thereby ensuring the security of the data. When the state of the cold chain goods is monitored in real time, the sensors in the intelligent tray are used for monitoring, so that partial noise data inevitably exist in the collected data, and meanwhile, due to the non-tamper-resistant property of the blockchain, the data must be preprocessed before being uplinked, so that the data seen by the subsequent user during tracing is real data.
The most common filtering smoothing treatment is adopted for the monitoring data, but in the actual situation, the characteristics of the data and noise in the monitoring data are similar, so that the denoising effect of the original data is poor due to fixed parameters in the filtering process, the authenticity of the processed data is influenced, and the tracing effect is influenced.
Disclosure of Invention
In order to solve the technical problems that the existing method is not ideal in denoising effect on intelligent tray monitoring data and affects the tracing effect, the invention aims to provide an intelligent tray cold chain tracing method based on the internet of things technology, and the adopted technical scheme is as follows:
acquiring monitoring data of all monitoring parameters of all intelligent trays; the monitoring data is composed of data points arranged according to time sequence;
analyzing the overall fluctuation characteristics of the monitoring data to obtain the sensitivity coefficient of each monitoring data; analyzing the difference characteristics of data distribution among the monitoring data of different monitoring parameters of the intelligent tray to obtain abnormal distribution factors of each monitoring data; analyzing local difference characteristics of the monitoring data of the same monitoring parameters in different intelligent trays, and combining the abnormal distribution factors to obtain abnormal factors of each data point in each monitoring data; correcting the abnormal factor of each data point according to the sensitivity coefficient and the abnormal distribution factor of the monitoring data to which each data point belongs, and obtaining the self-adaptive weight of each data point in each monitoring data;
denoising the monitoring data by using a filtering algorithm based on the self-adaptive weight;
and (5) carrying out uplink operation on the denoised monitoring data.
Further, the method for acquiring the sensitivity coefficient comprises the following steps:
establishing a data window with a preset window size by taking each data point of the monitoring data as a center; acquiring the sensitivity coefficient of each monitoring data by using a sensitivity coefficient calculation formula; the sensitivity coefficient calculation formula comprises:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Indicate->The intelligent tray->The sensitivity coefficient of the monitoring data corresponding to the monitoring parameters; />Indicate->The intelligent tray->The +.f. of the monitoring data corresponding to the monitoring parameters>A value of a data point; />Indicate->The intelligent tray->The average value of all data points in the monitoring data corresponding to the monitoring parameters; />Indicate->The intelligent tray->The +.f. of the monitoring data corresponding to the monitoring parameters>A mean of data points within a data window of data points; />Indicate->The intelligent tray->The +.f. of the monitoring data corresponding to the monitoring parameters>Standard deviation of data points within a data window of data points; />Indicate->The intelligent tray->The number of data points of the monitoring data corresponding to the monitoring parameters; />Representing the normalization function.
Further, the method for acquiring the abnormal distribution factor comprises the following steps:
acquiring extreme points of the monitoring data of each monitoring parameter; analyzing fluctuation characteristics of extreme points in the monitoring data, screening the extreme points, and obtaining extreme points to be analyzed of each monitoring data; acquiring the difference of the number of the extreme points to be analyzed among different monitoring parameters of the intelligent tray as an extreme value difference parameter;
taking a curve formed by extreme points to be analyzed in the monitoring data as a curve to be analyzed, combining any two curves to be analyzed, and processing by using a DTW algorithm to obtain the cost value of each extreme point to be analyzed corresponding to each combination; combining the cost value of the extreme point to be analyzed and the fluctuation characteristic of the extreme point to be analyzed to obtain the distribution difference parameters among different monitoring parameters of the intelligent tray;
selecting any monitoring data as target monitoring data, respectively obtaining products of the distribution difference parameters of the target monitoring data and the monitoring data of all other monitoring parameters in the intelligent tray to which the target monitoring data belong and the corresponding extreme value difference parameters, and taking the average value of all the products as an abnormal distribution factor of the target monitoring data; and changing target monitoring data, and acquiring an abnormal distribution factor of each monitoring data.
Further, the method for obtaining the distribution difference parameter comprises the following steps:
obtaining a distribution difference parameter by using a distribution difference parameter calculation formula; the distribution difference parameter calculation formula comprises:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Indicating +.>Monitoring data of species monitoring parameters and +.>Distribution difference parameters corresponding to monitoring data of the monitoring parameters; />Represent the firstMonitoring data of species monitoring parameters and +.>When comparing the monitoring data of the monitoring parameters, the first ∈>Within the monitoring data of the species monitoring parameter +.>The cost value of each extreme point to be analyzed; />Representing a normalization function; />Indicate->Within the monitoring data of the species monitoring parameter +.>Data values of the extreme points to be analyzed; />Indicate->The average value of the data values of all extreme points to be analyzed in the monitoring data of the monitoring parameters; />Indicate->The number of extreme points to be analyzed in the monitoring data of the monitoring parameters.
Further, the method for obtaining the abnormal factor includes:
obtaining an abnormal factor of each data point by using an abnormal factor calculation formula; the anomaly factor calculation formula comprises:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Indicate->The intelligent tray->The +.f. of the monitoring data corresponding to the monitoring parameters>An anomaly factor for the data point; />Indicating removal of->The total number of other intelligent trays except the intelligent trays; />Indicate->The intelligent tray->The first monitoring data corresponding to the monitoring parametersStandard deviation of data within a data window of data points; />Indicating removal of->Other than the intelligent tray +.>The intelligent tray->The +.f. of the monitoring data corresponding to the monitoring parameters>Standard deviation of data within a data window of data points; />Indicating removal of->Other than the intelligent tray +.>The intelligent tray->Abnormal distribution factors of monitoring data corresponding to the monitoring parameters; />Representing the normalization function.
Further, the method for acquiring the adaptive weight comprises the following steps:
mapping the sensitivity coefficient of the monitoring data to which the data point belongs in a negative correlation manner, multiplying the sensitivity coefficient by the anomaly factor of the data point and the anomaly distribution factor of the monitoring data to which the data point belongs, and mapping the product in the negative correlation manner to obtain an adjustment coefficient of the data point; and correcting the adjustment coefficient of the data point through a preset mapping function to obtain the self-adaptive weight of each data point.
Further, the preset mapping function is thatA function.
Further, the method for acquiring the extreme point to be analyzed comprises the following steps:
acquiring the absolute value of the difference value between the extreme point in the monitoring data and the mean value of all data points in the monitoring data, and normalizing the absolute value of the difference value to be used as a screening factor of each extreme point; and taking the extreme point of which the screening factor is larger than a preset screening threshold value as the extreme point to be analyzed.
Further, the preset screening threshold is 0.2.
Further, the preset window size is 11.
The invention has the following beneficial effects:
firstly, acquiring monitoring data of all monitoring parameters of all intelligent trays, and providing an analysis basis for analyzing specific characteristics of the monitoring data; further analyzing the overall fluctuation characteristics of the monitoring data, obtaining the sensitivity coefficient of each monitoring data, providing a basis for the subsequent correction of abnormal factors of data points, improving the accuracy of the obtained self-adaptive weights, and further accurately denoising the monitoring data to obtain and store real data; further analyzing the difference characteristics of data distribution among the monitoring data of different monitoring parameters of the intelligent tray, obtaining an abnormal distribution factor of each monitoring data, providing more basis for correcting the abnormal factors of the data points, and preparing for obtaining the abnormal factors; further analyzing local difference characteristics of the monitoring data of the same monitoring parameters in different intelligent trays, and acquiring an abnormal factor of each data point in each monitoring data by combining with an abnormal distribution factor, and performing preliminary evaluation on the abnormal degree of the data point to provide a correction basis for subsequent correction operation; correcting the abnormal factors of each data point according to the sensitivity coefficient and the abnormal distribution factors of the monitoring data to which each data point belongs, and acquiring the self-adaptive weight of each data point in each monitoring data, so as to prepare for accurately denoising the monitoring data and acquiring real and effective monitoring data; and finally, denoising the monitoring data by utilizing a filtering algorithm based on the self-adaptive weight, and performing uplink operation on the denoised monitoring data. According to the invention, the integral fluctuation characteristics of the monitoring data, the distribution differences among different monitoring data in the same intelligent tray and the local difference characteristics of the monitoring data corresponding to the same monitoring parameter in different intelligent trays are synthesized, the self-adaptive weight of each data point in each monitoring data is obtained, the monitoring data is accurately denoised by utilizing a filtering algorithm based on the self-adaptive weight, the denoised monitoring data is uplink, the accurate monitoring data is stored, and the tracing of related personnel is facilitated.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of an intelligent pallet cold chain tracing method based on the internet of things technology according to an embodiment of the present invention.
Detailed Description
In order to further explain the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of specific implementation, structure, characteristics and effects thereof of the intelligent pallet cold chain tracing method based on the internet of things technology according to the invention by combining the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a specific scheme of an intelligent pallet cold chain tracing method based on the internet of things technology, which is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of an intelligent pallet cold chain tracing method based on the internet of things technology according to an embodiment of the present invention is shown, which specifically includes:
step S1: acquiring monitoring data of all monitoring parameters of all intelligent trays; the monitoring data is composed of data points arranged according to time sequence.
In the embodiment of the invention, the vibration, humidity and temperature sensor assembly is additionally arranged in the intelligent tray sensor assembly to acquire real-time monitoring data of the intelligent tray. When the monitored data is in the uplink operation in the cold chain transportation process, a transfer station or an end point is usually taken as a segmentation point, for example, the monitoring is started from a place A, and the data is stored in a warehouse to be a transportation process, so the data processed by the invention is the monitored data of a transportation vehicle in a certain time period in the whole logistics process; meanwhile, the unit and order difference of parameters among the sensors are considered, so that the monitoring data are standardized.
It should be noted that the sensor of the intelligent tray can be customized and adjusted according to the requirements of different enterprises so as to monitor various transported objects.
Step S2: analyzing the integral fluctuation characteristics of the monitoring data to obtain the sensitivity coefficient of each monitoring data; analyzing the difference characteristics of data distribution among the monitoring data of different monitoring parameters of the intelligent tray to obtain abnormal distribution factors of each monitoring data; analyzing local difference characteristics of monitoring data of the same monitoring parameters in different intelligent trays, and acquiring abnormal factors of each data point in each monitoring data by combining the abnormal distribution factors; and correcting the abnormal factor of each data point according to the sensitivity coefficient and the abnormal distribution factor of the monitoring data to which each data point belongs, and obtaining the self-adaptive weight of each data point in each monitoring data.
The fluctuation of the transportation environment randomly occurs, and a certain degree of fluctuation can occur in the sensor data; the sensor noise also appears randomly and disturbs the monitoring data, and the fluctuation caused by the sensor noise and the monitoring data is similar, so that when a conventional filtering means is adopted, the weight of the data point is difficult to control, and a better effect is often not achieved, so that the authenticity of the monitoring data stored in the uplink is influenced.
In the embodiment of the invention, considering that in cold chain logistics transportation, a plurality of intelligent trays are loaded by a transport vehicle, and each intelligent tray records part of cold chain cargo information respectively, so that in the transportation process, various conditions such as vehicle body vibration, temperature and humidity changes caused by operations such as loading and unloading after reaching a certain destination, and the like are generated, the same conditions can occur in sensors loaded by the plurality of trays, and the fluctuation time range is the same, so that the abnormal degree of data points in the monitoring data can be analyzed according to the local difference of the monitoring data of the same monitoring parameters in different intelligent trays, and abnormal factors can be obtained; however, the loading states of different intelligent trays are different, and the sensitivity degree of different monitoring parameters to fluctuation changes of the transportation environment is different, so that the sensitivity analysis is required to be carried out on the monitoring data of each monitoring parameter of each intelligent tray so as to improve the accuracy of the analysis processing of the monitoring data; in addition, the fact that the fluctuation of the monitoring data presented by the environmental fluctuation received by the same intelligent tray is more concentrated is considered, if the sensor is aged, malfunctions, damage to a sensing element and the like, which can cause abnormal working state of the sensor, the characteristic of the fluctuation of the data can be influenced, the distribution characteristic of the corresponding monitoring data is abnormal compared with other monitoring data, so that abnormal distribution factors of the monitoring data are obtained, and analysis basis of abnormal degree of data points is supplemented; therefore, the self-adaptive weight of each data point in each monitoring data is obtained by integrating the integral fluctuation characteristics of the monitoring data, the distribution differences among different monitoring data in the same intelligent tray and the local difference characteristics of the monitoring data corresponding to the same monitoring parameter in different intelligent trays.
In the embodiment of the invention, the fluctuation characteristics presented by different types of monitoring parameters for different changes of the transportation environment are considered, and certain differences exist in the working states among the intelligent trays, for example, the weight sensor is insensitive to the temperature in the transportation environment, and the differences exist in various parameters such as the type, weight, volume, shape and the like of cargoes loaded by different intelligent trays, so that the integral fluctuation characteristics of the monitoring data are analyzed, and the sensitivity coefficient of each monitoring data is obtained, so that the abnormal factors of data points are corrected later, and the real characteristics are more met.
Preferably, in one embodiment of the present invention, a data window is established at each data point, considering that establishing a data window facilitates extraction of data characteristic information, capturing key features of the data; considering that when the local fluctuation of the data is stable and the deviation degree of the data points is large, the data points are possibly abnormal isolated values, the greater the possibility of being influenced by random noise is, the lower the reference value of the data points is, and based on the reference value, each data point of the monitored data is taken as the center, and a data window is established by taking the preset window size; acquiring the sensitivity coefficient of each monitoring data by using a sensitivity coefficient calculation formula; the sensitivity coefficient calculation formula comprises:
wherein,indicate->The intelligent tray->The sensitivity coefficient of the monitoring data corresponding to the monitoring parameters; />Indicate->The intelligent tray->Monitoring data corresponding to the monitoring parametersFirst->A value of a data point; />Indicate->The intelligent tray->The average value of all data points in the monitoring data corresponding to the monitoring parameters; />Indicate->The intelligent tray->The +.f. of the monitoring data corresponding to the monitoring parameters>A mean of data points within a data window of data points; />Indicate->The intelligent tray->The +.f. of the monitoring data corresponding to the monitoring parameters>Standard deviation of data points within a data window of data points; />Indicate->The intelligent tray->The number of data points of the monitoring data corresponding to the monitoring parameters;representing the normalization function.
In the sensitivity coefficient calculation formula, the greater the deviation degree of the data points is, the greater the discrete degree is, which shows that the higher the sensitivity degree of the monitoring data to the change of the transportation environment is, the greater the sensitivity coefficient is; the smaller the standard deviation of the data point in the local range, the more stable the fluctuation in the local range is, and the larger the mean value difference between the data point and the local range is, the larger the fluctuation of the data point is,the larger the data point is more likely to be an isolated outlier, the lower the credibility and reference value of the data point, and the lower the bias degree pair weight is given to the data point; the fluctuation characteristic of the square amplified monitoring data is utilized, the sensitivity of the difference of the monitoring data is improved, the change and abnormal conditions in the data can be captured more accurately, the denoising accuracy of the data is improved, and therefore accurate and real monitoring data can be stored.
It should be noted that, in one embodiment of the present invention, the size of the data window is 11, that is, each data point is taken as the center, 5 neighborhood data points are respectively obtained from the left side and the right side of the center data point, if the number of data points on one side is insufficient, enough neighborhood data points are obtained from the other side, so as to form the data window; in other embodiments of the present invention, an implementer may construct data windows with other sizes, and other basic mathematical operations or function mapping may be used to implement the relevant mapping when calculating the sensitivity coefficient, which are all technical means known to those skilled in the art, and are not described herein.
In the whole transportation process, the influence degree of the loading and unloading stages on the monitoring data is large, at the moment, data fluctuation can occur on various monitoring parameters of the same intelligent tray, and the characteristic of concentrated fluctuation is presented; when the fluctuation of the monitoring data of a certain monitoring parameter is not accumulated with the rest monitoring parameters and the fluctuation of the monitoring data is relatively more, the abnormal degree of the corresponding monitoring data is larger, and the noise influence degree is larger, so that the difference characteristics of data distribution among different monitoring parameters in one intelligent tray can be analyzed, and the abnormal distribution factor of each monitoring data can be obtained.
Preferably, in one embodiment of the present invention, analyzing the distribution characteristics of the extreme points can provide important information about the characteristics of the monitored data fluctuations, considering that the occurrence of the extreme points generally represents fluctuations or anomalies occurring in the data; meanwhile, the adjacency of larger fluctuation often accompanies some small fluctuation, and the small fluctuation is not helpful to the analysis of the overall abnormal difference, so that extreme points need to be screened; considering that the DTW algorithm can acquire the similarity between two data curves, and further can acquire the shortest path of the extreme point as the cost value, so as to measure the similarity characteristics of different monitoring data; because the number of the extreme points of the monitoring data of different monitoring parameters is different, the fluctuation characteristic difference between the monitoring data with larger difference is larger, so that the similarity of the monitoring data and the fluctuation characteristic difference is lower, the reference value for obtaining the distribution difference parameter is lower, and the obtained distribution difference parameter is constrained by the number difference of the extreme points to be analyzed; based on the extreme points of the monitoring data of each monitoring parameter are obtained; analyzing fluctuation characteristics of extreme points in the monitoring data, screening the extreme points, and obtaining extreme points to be analyzed of each monitoring data; acquiring the difference of the number of extreme points to be analyzed among different monitoring parameters of the intelligent tray, and taking the difference as an extreme value difference parameter;
taking a curve formed by extreme points to be analyzed in the monitoring data as a curve to be analyzed, combining any two curves to be analyzed, and processing by using a DTW algorithm to obtain the cost value of each extreme point to be analyzed corresponding to each combination; combining the cost value of the extreme point to be analyzed and the fluctuation characteristic of the extreme point to be analyzed to obtain the distribution difference parameters among different monitoring parameters of the intelligent tray;
selecting any monitoring data as target monitoring data, respectively acquiring products of distribution difference parameters and corresponding extreme value difference parameters of the target monitoring data and monitoring data of all other monitoring parameters in the intelligent tray to which the target monitoring data belongs, and taking the average value of all the products as an abnormal distribution factor of the target monitoring data; and changing target monitoring data, and acquiring an abnormal distribution factor of each monitoring data. The calculation formula of the abnormality distribution factor is expressed as:
wherein,indicate->The intelligent tray->Abnormal distribution factors of the individual target monitoring data; />Indicating removal of->The number of monitoring data other than the individual target monitoring data; />Indicate->The intelligent tray->Target monitoring data and removal->The other +.>Distribution difference parameters of the individual monitoring data; />Indicate->The intelligent tray->Target monitoring data and removal->The other +.>Extreme value difference parameters of the individual monitoring data; />Representing natural constants.
In the calculation formula of the abnormal distribution factor, the larger the distribution difference parameter is, the larger the distribution difference of extreme points between the monitoring data is, the higher the abnormal possibility of the target monitoring data is, the larger the average value of the distribution difference parameter of the target monitoring data and the monitoring data in other same intelligent trays is, and the larger the abnormal distribution factor is; the larger the extremum difference parameter is, the larger the difference of fluctuation characteristics among the monitoring data is, the lower the similarity among the monitoring data is, the lower the reference value is, and the lower the weight is given.
When the similarity between curves formed by the extreme points to be analyzed is obtained by using a DTW algorithm, the shortest path distance between the two curves can be obtained, and the shortest path distance matched with the data points is used as the cost value of the extreme points to be analyzed; the DTW algorithm is a well known technical means for those skilled in the art, and will not be described in detail herein.
In one embodiment of the invention, a data point with zero first derivative in the monitoring data is taken as an extreme point, then the absolute value of the difference value between the extreme point in the monitoring data and the average value of all the data points in the monitoring data is obtained, and the absolute value of the difference value is normalized and then taken as a screening factor of each extreme point; taking an extreme point with a screening factor larger than a preset screening threshold value as an extreme point to be analyzed, wherein the preset screening threshold value takes an empirical value of 0.2; in other embodiments of the present invention, the extremum points may be obtained by adopting a mode that the data points are simultaneously greater than or simultaneously less than the data points on both sides, other screening thresholds may be set when the extremum points to be analyzed are screened, other basic mathematical operations or function mapping may be selected to implement related mapping when calculating the abnormal distribution factor, and other modes such as fitting distribution may be utilized to analyze the data distribution difference characteristics between different monitoring data, which are all technical means well known to those skilled in the art, and are not described herein.
Preferably, in one embodiment of the present invention, considering that the greater the deviation degree of the extreme point to be analyzed, the more obvious the fluctuation occurs in the monitored data, and the higher the attention degree should be, the more the deviation degree of the extreme point to be analyzed is used as the weight to correct the cost value, based on this, a distribution difference parameter calculation formula is constructed, and the distribution difference parameter is obtained by using the distribution difference parameter calculation formula; the distribution difference parameter calculation formula includes:
wherein,indicating +.>Monitoring data of species monitoring parameters and +.>Distribution difference parameters corresponding to monitoring data of the monitoring parameters; />Indicate->Monitoring data of species monitoring parameters and +.>When comparing the monitoring data of the monitoring parameters, the first ∈>Within the monitoring data of the species monitoring parameter +.>The cost value of each extreme point to be analyzed; />Representing a normalization function; />Indicate->Within the monitoring data of the species monitoring parameter +.>Data values of the extreme points to be analyzed; />Indicate->The average value of the data values of all extreme points to be analyzed in the monitoring data of the monitoring parameters; />Indicate->The number of extreme points to be analyzed in the monitoring data of the monitoring parameters.
In the distribution difference parameter calculation formula, the larger the cost value of the extreme point to be analyzed is, the larger the distribution difference of the extreme point to be analyzed is, and the larger the distribution difference parameter is; the greater the deviation degree of the extreme points to be analyzed, the more obvious the fluctuation features appear in the monitoring data, and the higher the attention degree is, the greater the weight is given.
It should be noted that, in other embodiments of the present invention, other basic mathematical operations or function mapping may be used to implement the related mapping, which are all technical means known to those skilled in the art, and are not described herein.
In the embodiment of the invention, the influence degree of the change of the internal environment of the carriage of the vehicle on each intelligent tray is considered to be similar in the transportation process, so that the local difference characteristics of the monitoring data of the same monitoring parameters on different intelligent trays are analyzed, and meanwhile, the abnormal factors of each data point in each monitoring data are obtained by combining the abnormal distribution factors while the possibility of abnormal operation of the sensor is considered.
Preferably, in one embodiment of the present invention, the smaller the standard deviation is, the smaller the data fluctuation is, the smaller the standard deviation difference between the data windows is, and the less the abnormality possibility of the data is, considering that the standard deviation in the data window can reflect the local fluctuation characteristics of the monitored data; the abnormal distribution factor represents the abnormal degree of data distribution in the monitoring data, and the larger the abnormal degree of the data distribution is, the more abnormal the fluctuation of the monitoring data is, and the lower the reference value is; constructing an abnormal factor calculation formula according to the standard deviation difference and the abnormal distribution factor, and acquiring an abnormal factor of each data point by using the abnormal factor calculation formula; the anomaly factor calculation formula includes:
wherein,indicate->The intelligent tray->The +.f. of the monitoring data corresponding to the monitoring parameters>An anomaly factor for the data point; />Indicating removal of->The total number of other intelligent trays except the intelligent trays; />Indicate->The intelligent tray->The +.f. of the monitoring data corresponding to the monitoring parameters>Standard deviation of data within a data window of data points; />Indicating removal of->Other than the intelligent tray +.>The intelligent tray->The +.f. of the monitoring data corresponding to the monitoring parameters>Standard deviation of data within a data window of data points; />Indicating removal of->Other than the intelligent tray +.>The intelligent tray->Abnormal distribution factors of monitoring data corresponding to the monitoring parameters; />Representing the normalization function.
In the anomaly factor calculation formula, the smaller the standard deviation difference is, the more similar the local fluctuation characteristics of different monitoring data are, the smaller the anomaly possibility of the data points is, and the smaller the anomaly factor is; the larger the abnormality distribution factor, the larger the data distribution in the monitoring data, the more abnormal the fluctuation of the monitoring data, the lower the reference value, and the smaller the weight given to the standard deviation difference.
It should be noted that, in other embodiments of the present invention, other basic mathematical operations or function mapping may be used to implement the related mapping, which are all technical means known to those skilled in the art, and are not described herein.
After the abnormal factors of the data points and the sensitivity coefficient and the abnormal distribution factor of the monitoring data are obtained, the abnormal factors of each data point can be corrected by using the sensitivity coefficient and the abnormal distribution factor of the monitoring data to which each data point belongs, and the self-adaptive weight of each data point is obtained, so that the monitoring data can be accurately noise reduced according to the self-adaptive weight of the data point.
Preferably, in one embodiment of the present invention, the range of values of the adjustment coefficient obtained by the difficult-to-control correction is taken into consideration when the correction is performed on the abnormality factor by a plurality of parametersThe function can map data between 0-1, soThe function is used as a preset mapping function to adjust the self-adaptive weight value range, based on the self-adaptive weight value range, the sensitivity coefficient of the monitoring data of the data point is mapped in a negative correlation manner, and then the sensitivity coefficient of the monitoring data of the data point is different from the abnormality factor of the data point and the monitoring data of the data pointMultiplying the constant distribution factors, and mapping the product negative correlation to obtain the adjustment coefficient of the data point; and correcting the adjustment coefficient of the data point through a preset mapping function to obtain the self-adaptive weight of each data point. The calculation formula of the adaptive weight comprises:
wherein,indicate->The intelligent tray->The +.f. of the monitoring data corresponding to the monitoring parameters>Adaptive weights for data points; />Representing a preset mapping function; />Indicate->The intelligent tray->The sensitivity coefficient of the monitoring data corresponding to the monitoring parameters; />Indicate->The intelligent tray->Monitoring corresponding to species monitoring parametersData->An anomaly factor for the data point; />Indicate->The intelligent tray->Abnormal distribution factors of the monitoring data corresponding to the monitoring parameters.
In the calculation formula of the self-adaptive weight, the greater the abnormality factor is, the greater the abnormality degree of the data point is, the greater the influence degree of noise is, the smaller the reference value and the contribution degree of the self-adaptive weight in the filtering process are, and the smaller the self-adaptive weight is; the larger the abnormal distribution factor is, the greater the possibility of abnormal working state of the sensor is, the smaller the reference value of the monitoring data is, and the smaller the self-adaptive weight is; the larger the sensitivity coefficient is, the more sensitive the monitoring data is to the change of the transportation environment, and the more likely the fluctuation of the data points is caused by the transportation environment, so the data points are corrected in the direction of reducing the degree of abnormality, and the accuracy of the self-adaptive weight is improved.
Step S3: and denoising the monitoring data by using a filtering algorithm based on the adaptive weight.
And (3) through the processing of the steps S1 to S2, integrating the integral fluctuation characteristics of the monitoring data, the distribution differences among different monitoring data in the same intelligent tray and the local difference characteristics of the monitoring data corresponding to the same monitoring parameter in different intelligent trays, acquiring the self-adaptive weight of each data point in each monitoring data, and preparing for accurately processing the monitoring data.
Preferably, in one embodiment of the present invention, the average filtering algorithm based on adaptive weights is used to denoise the monitored data, considering that the average filtering can suppress random noise in the data, better preserve the overall characteristics and details of the data, and have lower computational complexity.
It should be noted that, the mean filtering algorithm is a technical means well known to those skilled in the art, and will not be described herein again; in other embodiments of the invention, the practitioner may employ other filtering algorithms to process the monitored data.
Step S4: and (5) carrying out uplink operation on the denoised monitoring data.
The uplink is typically the recording of data or information into the blockchain. Blockchains are a distributed ledger technique that uses encryption to link blocks of data together to form a non-tamperable, de-centralised database, and the chaining of data means writing data into the blockchain to make it an unalterable record in the blockchain network. The uplink monitoring data may provide a complete cold chain transportation history. In the whole process of product delivery, transportation and warehousing, the monitoring data of each step are recorded, so that the whole transportation process of the product is traced more feasible, potential problems can be rapidly located, and the product tracing capability is improved.
Therefore, in the embodiment of the invention, the denoised monitoring data is subjected to the uplink operation and stored in the blockchain so that the transportation monitoring data can be conveniently called by the subsequent related personnel, the related model is built by utilizing the monitoring data, and the cold chain transportation process is analyzed and optimized, or the monitoring data in the blockchain is used as a certificate of the transportation process, thereby avoiding the data from being tampered, improving the transparency of the monitoring data and meeting the related supervision requirements.
It should be noted that the uplink operation is a technical means well known to those skilled in the art, and will not be described herein.
In summary, the invention provides an intelligent pallet cold chain tracing method based on the internet of things technology, aiming at the technical problems that the denoising effect of the intelligent pallet monitoring data is not ideal and the tracing effect is affected in the existing method: the method comprises the steps of integrating integral fluctuation characteristics of monitoring data, distribution differences among different monitoring data in the same intelligent tray and local difference characteristics of monitoring data corresponding to the same monitoring parameter in different intelligent trays, acquiring self-adaptive weights of each data point in each monitoring data, accurately denoising the monitoring data by utilizing a filtering algorithm based on the self-adaptive weights, and uplink the denoised monitoring data, storing the accurate monitoring data, and is convenient for related personnel to trace.
An embodiment of a denoising method for intelligent tray monitoring data comprises the following steps:
the most common filtering smoothing treatment is adopted for the monitoring data, but in the actual situation, the characteristics of the data and noise in the monitoring data are similar, so that the denoising effect of the original data is poor due to fixed parameters in the filtering process, and the authenticity of the processed data is affected.
In order to solve the technical problem that the denoising effect of the existing method on the intelligent tray monitoring data is not ideal, the embodiment provides a denoising method of the intelligent tray monitoring data, which comprises the following steps:
step S1: acquiring monitoring data of all monitoring parameters of all intelligent trays; the monitoring data is composed of data points arranged according to time sequence.
Step S2: analyzing the integral fluctuation characteristics of the monitoring data to obtain the sensitivity coefficient of each monitoring data; analyzing the difference characteristics of data distribution among the monitoring data of different monitoring parameters of the intelligent tray to obtain abnormal distribution factors of each monitoring data; analyzing local difference characteristics of monitoring data of the same monitoring parameters in different intelligent trays, and acquiring abnormal factors of each data point in each monitoring data by combining the abnormal distribution factors; and correcting the abnormal factor of each data point according to the sensitivity coefficient and the abnormal distribution factor of the monitoring data to which each data point belongs, and obtaining the self-adaptive weight of each data point in each monitoring data.
Step S3: and denoising the monitoring data by using a filtering algorithm based on the adaptive weight.
Because the specific implementation process of steps S1 to S3 is already described in detail in the intelligent pallet cold chain tracing method based on the internet of things technology, a detailed description is omitted.
In summary, the invention provides a denoising method for intelligent tray monitoring data, aiming at the technical problem that the denoising effect of the existing method on the intelligent tray monitoring data is not ideal: and (3) integrating the integral fluctuation characteristics of the monitoring data, the distribution differences among different monitoring data in the same intelligent tray and the local difference characteristics of the monitoring data corresponding to the same monitoring parameter in different intelligent trays, acquiring the self-adaptive weight of each data point in each monitoring data, and accurately denoising the monitoring data by utilizing a filtering algorithm based on the self-adaptive weight.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings 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.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (5)
1. An intelligent pallet cold chain tracing method based on the internet of things technology is characterized by comprising the following steps:
acquiring monitoring data of all monitoring parameters of all intelligent trays; the monitoring data is composed of data points arranged according to time sequence;
analyzing the overall fluctuation characteristics of the monitoring data to obtain the sensitivity coefficient of each monitoring data; analyzing the difference characteristics of data distribution among the monitoring data of different monitoring parameters of the intelligent tray to obtain abnormal distribution factors of each monitoring data; analyzing local difference characteristics of the monitoring data of the same monitoring parameters in different intelligent trays, and combining the abnormal distribution factors to obtain abnormal factors of each data point in each monitoring data; correcting the abnormal factor of each data point according to the sensitivity coefficient and the abnormal distribution factor of the monitoring data to which each data point belongs, and obtaining the self-adaptive weight of each data point in each monitoring data;
denoising the monitoring data by using a filtering algorithm based on the self-adaptive weight;
carrying out uplink operation on the denoised monitoring data; building a correlation model by using the denoised monitoring data, and tracing by using the correlation model;
the method for acquiring the sensitivity coefficient comprises the following steps:
establishing a data window with a preset window size by taking each data point of the monitoring data as a center; acquiring the sensitivity coefficient of each monitoring data by using a sensitivity coefficient calculation formula; the sensitivity coefficient calculation formula comprises:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Indicate->The intelligent tray->The sensitivity coefficient of the monitoring data corresponding to the monitoring parameters; />Indicate->The intelligent tray->The +.f. of the monitoring data corresponding to the monitoring parameters>A value of a data point; />Indicate->The intelligent tray->The average value of all data points in the monitoring data corresponding to the monitoring parameters; />Indicate->The intelligent tray->The first monitoring data corresponding to the monitoring parametersA mean of data points within a data window of data points; />Indicate->The intelligent tray->The +.f. of the monitoring data corresponding to the monitoring parameters>Standard deviation of data points within a data window of data points; />Indicate->The intelligent tray->The number of data points of the monitoring data corresponding to the monitoring parameters; />Representing a normalization function;
the method for acquiring the abnormal distribution factor comprises the following steps:
acquiring extreme points of the monitoring data of each monitoring parameter; analyzing fluctuation characteristics of extreme points in the monitoring data, screening the extreme points, and obtaining extreme points to be analyzed of each monitoring data; acquiring the difference of the number of the extreme points to be analyzed among different monitoring parameters of the intelligent tray as an extreme value difference parameter;
taking a curve formed by extreme points to be analyzed in the monitoring data as a curve to be analyzed, combining any two curves to be analyzed, and processing by using a DTW algorithm to obtain the shortest path of each extreme point to be analyzed corresponding to each combination, and taking the shortest path as the cost value of each extreme point to be analyzed corresponding to each combination; combining the cost value of the extreme point to be analyzed and the fluctuation characteristic of the extreme point to be analyzed to obtain the distribution difference parameters among different monitoring parameters of the intelligent tray;
selecting any monitoring data as target monitoring data, respectively obtaining products of the distribution difference parameters of the target monitoring data and the monitoring data of all other monitoring parameters in the intelligent tray to which the target monitoring data belong and the corresponding extreme value difference parameters, and taking the average value of all the products as an abnormal distribution factor of the target monitoring data; changing target monitoring data, and acquiring an abnormal distribution factor of each monitoring data;
the method for acquiring the distribution difference parameters comprises the following steps:
obtaining a distribution difference parameter by using a distribution difference parameter calculation formula; the distribution difference parameter calculation formula comprises:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Indicating +.>Monitoring data of species monitoring parameters and +.>Distribution difference parameters corresponding to monitoring data of the monitoring parameters; />Indicate->Monitoring data of species monitoring parameters and +.>When comparing the monitoring data of the monitoring parameters, the first ∈>Within the monitoring data of the species monitoring parameter +.>The cost value of each extreme point to be analyzed; />Representing a normalization function; />Indicate->Within the monitoring data of the species monitoring parameter +.>Data values of the extreme points to be analyzed; />Indicate->The average value of the data values of all extreme points to be analyzed in the monitoring data of the monitoring parameters; />Indicate->The number of extreme points to be analyzed in the monitoring data of the monitoring parameters;
the method for acquiring the abnormal factors comprises the following steps:
obtaining an abnormal factor of each data point by using an abnormal factor calculation formula; the anomaly factor calculation formula comprises:
the method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>Indicate->The intelligent tray->The +.f. of the monitoring data corresponding to the monitoring parameters>An anomaly factor for the data point; />Indicating removal of->The total number of other intelligent trays except the intelligent trays; />Indicate->The intelligent tray->The +.f. of the monitoring data corresponding to the monitoring parameters>Standard deviation of data within a data window of data points; />Indicating removal of->Other than the intelligent tray +.>The intelligent tray->The +.f. of the monitoring data corresponding to the monitoring parameters>Standard deviation of data within a data window of data points; />Indicating removal of->Other than the intelligent tray +.>The intelligent tray->Species monitoringMeasuring abnormal distribution factors of monitoring data corresponding to parameters; />Representing a normalization function;
the method for acquiring the self-adaptive weight comprises the following steps:
mapping the sensitivity coefficient of the monitoring data to which the data point belongs in a negative correlation manner, multiplying the sensitivity coefficient by the anomaly factor of the data point and the anomaly distribution factor of the monitoring data to which the data point belongs, and mapping the product in the negative correlation manner to obtain an adjustment coefficient of the data point; and correcting the adjustment coefficient of the data point through a preset mapping function to obtain the self-adaptive weight of each data point.
2. The intelligent pallet cold chain tracing method based on the internet of things technology as set forth in claim 1, wherein the preset mapping function isA function.
3. The intelligent pallet cold chain tracing method based on the internet of things technology as set forth in claim 1, wherein the method for acquiring the extreme point to be analyzed comprises the following steps:
acquiring the absolute value of the difference value between the extreme point in the monitoring data and the mean value of all data points in the monitoring data, and normalizing the absolute value of the difference value to be used as a screening factor of each extreme point; and taking the extreme point of which the screening factor is larger than a preset screening threshold value as the extreme point to be analyzed.
4. The intelligent pallet cold chain tracing method based on the internet of things technology according to claim 3, wherein the preset screening threshold is 0.2.
5. The intelligent pallet cold chain tracing method based on the internet of things technology according to claim 1, wherein the preset window size is 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311810803.9A CN117474427B (en) | 2023-12-27 | 2023-12-27 | Intelligent pallet cold chain tracing method based on Internet of things technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311810803.9A CN117474427B (en) | 2023-12-27 | 2023-12-27 | Intelligent pallet cold chain tracing method based on Internet of things technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117474427A CN117474427A (en) | 2024-01-30 |
| CN117474427B true CN117474427B (en) | 2024-03-26 |
Family
ID=89627810
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311810803.9A Active CN117474427B (en) | 2023-12-27 | 2023-12-27 | Intelligent pallet cold chain tracing method based on Internet of things technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117474427B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117829381B (en) * | 2024-03-05 | 2024-05-14 | 成都农业科技职业学院 | Agricultural greenhouse data optimization acquisition system based on Internet of things |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110377447A (en) * | 2019-07-17 | 2019-10-25 | 腾讯科技（深圳）有限公司 | A kind of abnormal deviation data examination method, device and server |
| CN112550892A (en) * | 2020-11-26 | 2021-03-26 | 河北交通职业技术学院 | Intelligent logistics tray and management system thereof |
| CN112561250A (en) * | 2020-11-30 | 2021-03-26 | 深圳技术大学 | Cold chain logistics management system based on block chain |
| CN113592050A (en) * | 2021-08-04 | 2021-11-02 | 无锡感知金服物联网科技有限公司 | Internet of things storage pledge supervision intelligent tray equipment and system |
| CN114912852A (en) * | 2022-07-18 | 2022-08-16 | 山东鑫亚装备制造有限公司 | Abnormity monitoring and early warning system for storage tank of refrigeration bin |
| WO2022252505A1 (en) * | 2021-06-02 | 2022-12-08 | 杭州安脉盛智能技术有限公司 | Device state monitoring method based on multi-index cluster analysis |
| CN115496344A (en) * | 2022-09-06 | 2022-12-20 | 苏州凌归物流科技有限公司 | Logistics data-based supervision and early warning management method |
| CN116183058A (en) * | 2023-04-21 | 2023-05-30 | 实德电气集团有限公司 | Monitoring method of intelligent capacitor |
| CN116237817A (en) * | 2023-05-06 | 2023-06-09 | 济南章力机械有限公司 | Five-axis linkage numerical control machine intelligent monitoring system based on Internet of things |
| CN116304962A (en) * | 2023-05-25 | 2023-06-23 | 湖南东润智能仪表有限公司 | Intelligent anomaly monitoring method for water meter metering data |
| CN116701983A (en) * | 2023-08-03 | 2023-09-05 | 青岛冠成软件有限公司 | Cold-chain logistics real-time monitoring data processing method and system |
| CN117093879A (en) * | 2023-10-19 | 2023-11-21 | 无锡尚航数据有限公司 | Intelligent operation management method and system for data center |
| CN117094611A (en) * | 2023-10-20 | 2023-11-21 | 济南优谷生物技术有限公司 | Quality safety traceability management method and system for food processing |
| CN117151570A (en) * | 2023-10-31 | 2023-12-01 | 南通百源制冷设备有限公司 | Cold source pipeline monitoring method of box body for cold chain transportation |
-
2023
- 2023-12-27 CN CN202311810803.9A patent/CN117474427B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110377447A (en) * | 2019-07-17 | 2019-10-25 | 腾讯科技（深圳）有限公司 | A kind of abnormal deviation data examination method, device and server |
| CN112550892A (en) * | 2020-11-26 | 2021-03-26 | 河北交通职业技术学院 | Intelligent logistics tray and management system thereof |
| CN112561250A (en) * | 2020-11-30 | 2021-03-26 | 深圳技术大学 | Cold chain logistics management system based on block chain |
| WO2022252505A1 (en) * | 2021-06-02 | 2022-12-08 | 杭州安脉盛智能技术有限公司 | Device state monitoring method based on multi-index cluster analysis |
| CN113592050A (en) * | 2021-08-04 | 2021-11-02 | 无锡感知金服物联网科技有限公司 | Internet of things storage pledge supervision intelligent tray equipment and system |
| CN114912852A (en) * | 2022-07-18 | 2022-08-16 | 山东鑫亚装备制造有限公司 | Abnormity monitoring and early warning system for storage tank of refrigeration bin |
| CN115496344A (en) * | 2022-09-06 | 2022-12-20 | 苏州凌归物流科技有限公司 | Logistics data-based supervision and early warning management method |
| CN116183058A (en) * | 2023-04-21 | 2023-05-30 | 实德电气集团有限公司 | Monitoring method of intelligent capacitor |
| CN116237817A (en) * | 2023-05-06 | 2023-06-09 | 济南章力机械有限公司 | Five-axis linkage numerical control machine intelligent monitoring system based on Internet of things |
| CN116304962A (en) * | 2023-05-25 | 2023-06-23 | 湖南东润智能仪表有限公司 | Intelligent anomaly monitoring method for water meter metering data |
| CN116701983A (en) * | 2023-08-03 | 2023-09-05 | 青岛冠成软件有限公司 | Cold-chain logistics real-time monitoring data processing method and system |
| CN117093879A (en) * | 2023-10-19 | 2023-11-21 | 无锡尚航数据有限公司 | Intelligent operation management method and system for data center |
| CN117094611A (en) * | 2023-10-20 | 2023-11-21 | 济南优谷生物技术有限公司 | Quality safety traceability management method and system for food processing |
| CN117151570A (en) * | 2023-10-31 | 2023-12-01 | 南通百源制冷设备有限公司 | Cold source pipeline monitoring method of box body for cold chain transportation |
Non-Patent Citations (1)
| Title |
|---|
| 基于区块链的农产品安全可信溯源应用研究;高阳阳;吕相文;袁柳;李勐;;计算机应用与软件;20200712(第07期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117474427A (en) | 2024-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117474427B (en) | Intelligent pallet cold chain tracing method based on Internet of things technology | |
| US11151679B2 (en) | Systems and methods for monitoring packaging quality issues | |
| TWI581213B (en) | Method, image processing system and computer-readable recording medium for item defect inspection | |
| CN109345513B (en) | Cigarette package defect detection method with cigarette package posture calculation function | |
| CN115578780A (en) | Agricultural product and food cold chain traceability management system based on big data | |
| CN110991493B (en) | Hyperspectral anomaly detection method for collaborative representation and anomaly rejection | |
| CN110363626B (en) | Behavior mode monitoring method for unmanned container, electronic equipment and unmanned container | |
| CN104680138B (en) | Satellite image automated interpretation system and method based on characterisitic parameter correlation | |
| CN111415339B (en) | Image defect detection method for complex texture industrial product | |
| CN117094611B (en) | Quality safety traceability management method and system for food processing | |
| US20200175142A1 (en) | Electronic device with fingerprint sensing function and fingerprint image processing method | |
| CN111461101A (en) | Method, device and equipment for identifying work clothes mark and storage medium | |
| CN117151595A (en) | Commodity inventory management method, equipment and storage medium | |
| CN117314901A (en) | Scale-adaptive chip detection neural network system | |
| CN110751623A (en) | Joint feature-based defect detection method, device, equipment and storage medium | |
| Wendelberger et al. | Monitoring Deforestation Using Multivariate Bayesian Online Changepoint Detection with Outliers | |
| CN113747270B (en) | Cloud data center thing allies oneself with management and control system | |
| CN114972234A (en) | Edible mushroom quality monitoring method and system | |
| US20220137018A1 (en) | Method for identifying an item by olfactory signature | |
| CN114596033A (en) | Intelligent logistics planning monitoring method and system based on deep learning | |
| CN114359287A (en) | Image data processing method and device | |
| CA2965218A1 (en) | Systems and methods for monitoring packaging quality issues | |
| Molina et al. | A robotic vision system using a modified Hough transform to perform weld line detection on storage tanks | |
| CN114359945A (en) | Method and device for generating express delivery abnormal bill, computer equipment and storage medium | |
| CN116812590B (en) | Visual-based unloading method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |