Logistics goods quality supervision system and method based on Internet of Things

Abstract

The invention discloses a logistics cargo quality supervision system and method based on the Internet of Things, and relates to the technical field of logistics supervision, and the supervision method comprises the following steps: analyzing the environmental data regulation condition of a cargo storage space in each logistics transportation process, and generating a corresponding regulation record; setting expected environment data of the goods; obtaining a quality inspection result of the goods after the goods are conveyed, carrying out abnormity identification on each regulation and control record, and extracting abnormal characteristic events influencing the goods quality to obtain the influence degree of each abnormal characteristic event; setting an abnormal occurrence node of each regulation and control record; performing abnormal feature event identification on the real-time regulation and control record, and predicting an abnormal occurrence node of the real-time regulation and control record; and when an abnormality occurrence node is triggered, carrying out risk early warning on the currently transported cargo, capturing the regulation duration of the real-time regulation record, and judging whether the regulation process is abnormal or not.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics supervision, and in particular to a logistics cargo quality supervision system and method based on the Internet of Things. Background Art

[0002] During the transportation of logistics goods, it is necessary to ensure the quality of the logistics goods. Especially for some fresh foods or drugs and other goods with very strict environmental requirements, quality assurance can effectively prevent deterioration and invalidation, and avoid risks and losses. Therefore, strict control of the quality of logistics goods is very important and necessary;

[0003] With the development of technology, it is now possible to monitor and automatically adjust the temperature and humidity of the space where the goods are located through Internet of Things technology; although the temperature and humidity can be maintained within a certain range, it often starts to adjust when it is out of the normal range. However, the change process of temperature and humidity is a slow process, and some goods are very sensitive to environmental changes. As long as the temperature and humidity are out of the normal range, it will already affect the quality of the goods. Therefore, it is unreasonable to adjust when the temperature and humidity are abnormal. Summary of the Invention

[0004] The purpose of the present invention is to provide a logistics cargo quality supervision system and method based on the Internet of Things to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solution: A logistics cargo quality supervision method based on the Internet of Things, the supervision method includes the following steps:

[0006] Step S100: Collect the environmental data of the cargo storage space during each logistics transportation process, analyze the regulation situation of the environmental data, and generate corresponding regulation records; based on the regulation results between each regulation record, set the expected environmental data of the cargo; the environmental data in the storage space includes temperature, humidity, etc., and various environmental data can be regulated;

[0007] Step S200: Obtain the quality inspection results of the cargo after transportation is completed, and identify abnormalities in each regulation record; analyze the differences in the regulation process between each regulation record, and extract abnormal characteristic events that affect the quality of the cargo;

[0008] Step S300: Analyze the influence of each abnormal characteristic event in each regulation record to obtain the influence degree of each abnormal characteristic event; based on the regulation situation of each regulation record and the included several abnormal characteristic events, set the abnormal occurrence nodes of each regulation record;

[0009] Step S400: Identify abnormal feature events in the real-time control records generated during the current transportation process, and predict the nodes where abnormalities occur in the real-time control records; when the abnormal occurrence nodes are triggered, issue a risk warning for the currently transported goods, and capture the control duration of the real-time control records to determine whether there are abnormalities in the control process.

[0010] Further, step S100 includes the following steps:

[0011] Step S101: Install a number of monitoring devices and control devices in the goods storage space. During the logistics transportation process, use the control devices to regulate the environmental data of the storage space, use the monitoring devices to collect the environmental data of the storage space in real time, sort the collected environmental data in the order of collection time, and generate a control record.

[0012] Step S102: Arbitrarily select a control record, and extract the environmental data of the storage space when the control device starts and stops running in the selected control record to obtain a number of target control data; the target control data refers to the environmental data that appears abnormal and the environmental data when it remains stable.

[0013] Step S103: Obtain the change situation of the environmental data of the control device from the start of operation to the stop of operation each time; if the environmental data is in an increasing state, set the target control data at the start of operation as the minimum expected data, and set the target control data at the stop of operation as the maximum expected data; if the environmental data is in a decreasing state, set the target control data at the start of operation as the maximum expected data, and set the target control data at the stop of operation as the minimum expected data.

[0014] Step S104: Divide each target control data to obtain a minimum expected data set and a maximum expected data set respectively, and extract the maximum value A max and the minimum value B min in the maximum expected data set to obtain the expected range of the environmental data of the goods (A max , B min ); By identifying the expected range of the goods, it can help analyze the abnormal situations that occur during the control process in the subsequent abnormal identification process.

[0015] Further, step S200 includes the following steps:

[0016] Step S201: Whenever the transportation is completed, preset quality assessment rules for several dimensions, conduct a quality assessment on the goods to obtain a quality inspection result, and use the quality inspection result as the accuracy of the control record corresponding to the logistics transportation; set the accuracy of any selected control record as Z, and preset an accuracy threshold Z min , if Z < Zmin , then the selected control record is set as the abnormal control record. If Z>Z min , then the selected control record is set as the normal control record;

[0017] Step S202: Acquire the control data recorded in any control record, extract a number of control features from the acquired control data, and extract features of the external environment where the cargo storage space is located to obtain a number of environmental features, and summarize the extracted control features and environmental features to obtain a feature set; the control features include the control duration, the fluctuation range of environmental data, etc.;

[0018] Step S203: randomly select a normal control record, extract corresponding data for each feature in the feature set of the selected normal control record, and obtain a feature value corresponding to each feature; for any feature, obtain the feature value of each normal control record, and obtain a normal value range of each feature;

[0019] Step S204: arbitrarily select an abnormal control record, obtain the characteristic value of each feature of the selected abnormal control record, if there is a characteristic value of a control feature that is not within the normal value range, extract the control data of the control feature in the selected abnormal control record, and generate an abnormal characteristic event of the abnormal control record, if there is a characteristic value of an environmental feature that is not within the normal value range, set the environmental feature as an abnormal characteristic event;

[0020] Step S205: Screen and summarize abnormal characteristic events for each abnormal control record to generate a set of abnormal characteristic events that affect the quality of the goods.

[0021] Further, step S300 includes the following steps:

[0022] Step S301: arbitrarily select an abnormal regulation record, obtain several abnormal characteristic events contained in the selected abnormal regulation record, select the ith abnormal characteristic event from them, and obtain the deviation degree between the ith abnormal characteristic event and the corresponding normal value range as P i ; Obtain the degree of deviation of each of several abnormal characteristic events according to the formula:

[0023]

[0024] Where c is the number of abnormal characteristic events contained in the selected abnormal regulation record; the characteristic proportion η of the i-th abnormal characteristic event in the selected abnormal regulation record is calculated i ;

[0025] Step S303: Obtain the accuracy of each normal regulation record, calculate the average value to obtain the expected accuracy Z ave ; Set the accuracy of the selected abnormal regulation record as Z', according to the formula:

[0026] γ i =(Z ave -Z')×η i ;

[0027] Calculate the influence degree γ of the i-th abnormal feature event i ; Calculating the influence degree of each abnormal feature event can help identify the subsequent expected range. Because the quality of the goods is affected during the regulation process due to the influence of the abnormal feature event, through the influence of the abnormal feature event, it is necessary to make a preliminary judgment to eliminate the abnormal situation that appears in the subsequent regulation process;

[0028] Step S304: Set the expected range of the environmental data of the goods (A max , B min ), according to the formula:

[0029]

[0030] Calculate the expected minimum value Min and the expected maximum value Max for the correction of the goods, and generate the actual expected range (Min, Max) after the correction of the goods;

[0031] Step S305: Extract all target regulation data from the selected abnormal regulation records, sort all the target regulation data according to the collection time, and arbitrarily select the target regulation data when a regulation device starts to run. If the next target regulation data of the selected target regulation data is the one collected when the regulation device stops running, then set the two target regulation data as a data group;

[0032] Step S306: Arbitrarily select a data group, obtain the target regulation data D2 of the data group when the regulation device stops running. If D2 ∈ (Min, Max), obtain the regulation duration T1 of the regulation device from the start of operation to the time when the environmental data meets the actual expected range (Min, Max) in the data group. At the same time, obtain the regulation duration T2 of the regulation device from the start of operation to the stop of operation in the data group and the environmental data change amount ΔD = D2 - D1, where D1 is the target regulation data of the data group when the regulation device starts to run;

[0033] Step S307: Obtain the regulation duration of each data group in each normal regulation record from the start of operation to the stop of operation of the regulation device, calculate the average value to obtain the average regulation duration T ave ; According to the formula:

[0034]

[0035] Calculate two abnormal occurrence nodes Y1 and Y2 of the selected abnormal regulation records; the abnormal occurrence node is a prediction of the regulation of the goods storage space. Since the change of environmental data in the actual regulation process is a slow-changing process, there is still a period of time in the abnormal state during the change process, and the setting of the abnormal occurrence node can effectively avoid this problem, make preparations for regulation in advance, and try to avoid the duration of the goods stored in the abnormal state.

[0036] Furthermore, step S400 includes the following steps:

[0037] Step S401: Obtain the regulation data recorded in the current real-time regulation record and the external environmental data of the goods storage space, extract several abnormal feature events, and set the influence degree of the jth abnormal feature event as γ j ; Obtain the expected range of environmental data of the goods (A max , B min ), and calculate the corrected actual expected range (Min’, Max’);

[0038] Step S402: Obtain each regulation record containing several extracted abnormal feature events, respectively obtain two abnormal occurrence nodes of each regulation record, and calculate the average value to obtain the abnormal occurrence node average value Y1 ave and Y2 ave ; According to the formula:

[0039] Y1′ = Y1 ave +Min′ - Min

[0040] Y2′ = Y2 ave +Max′ - Max;

[0041] Calculate that the predicted values of the two abnormal occurrence nodes of the real-time regulation record are Y1’ and Y2’ respectively;

[0042] Step S403: Collect environmental data of the storage space corresponding to the real-time regulation record through a monitoring device, and set the currently monitored environmental data as D now , if D now <Y1’ or D now >Y2’, then give a risk warning for the currently transported goods, and transfer the regulation device to regulate the storage space, and count the regulation duration T from the start to the stop of the regulation device now ;

[0043] Step S404: Obtain the regulation duration of each time in each abnormal regulation record, and select the regulation duration with the smallest value as the abnormal duration threshold T for judging abnormal regulation. th If T now > T th , an abnormal reminder for the regulation process will be given.

[0044] To better implement the above method, a logistics cargo quality supervision system is also proposed. The supervision system includes a regulation process analysis module, an abnormal regulation analysis module, a regulation optimization analysis module, and a real-time regulation analysis module.

[0045] The regulation process analysis module is used to collect the environmental data of the cargo storage space during each logistics transportation process, analyze the regulation situation of the environmental data, and generate corresponding regulation records; based on the regulation results between each regulation record, set the expected environmental data of the cargo.

[0046] The abnormal regulation analysis module is used to obtain the quality inspection results of the cargo after transportation, and identify abnormalities in each regulation record; analyze the differences in the regulation process between each regulation record, and extract abnormal characteristic events that affect the cargo quality.

[0047] The regulation optimization analysis module is used to analyze the influence of each abnormal characteristic event in each regulation record to obtain the influence degree of each abnormal characteristic event; based on the regulation situation of each regulation record and the included several abnormal characteristic events, set the abnormal occurrence nodes of each regulation record.

[0048] The real-time regulation analysis module is used to identify abnormal characteristic events in the real-time regulation record generated by the current transportation process, and predict the abnormal occurrence node of the real-time regulation record; when the abnormal occurrence node is triggered, give a risk warning for the currently transported cargo, and capture the regulation duration of the real-time regulation record to determine whether there is an abnormality in the regulation process.

[0049] Furthermore, the regulation process analysis module includes a regulation record establishment unit and an expected range setting unit.

[0050] The regulation record establishment unit is used to collect the environmental data of the cargo storage space during each logistics transportation process, analyze the regulation situation of the environmental data, and generate corresponding regulation records; the expected range setting unit is used to set the expected environmental data of the cargo based on the regulation results between each regulation record.

[0051] Furthermore, the abnormal regulation analysis module includes an abnormal regulation identification unit and an abnormal event extraction unit.

[0052] Anomaly regulation recognition unit, which is used to obtain the quality inspection results of goods after transportation completion and recognize anomalies in each regulation record; Anomaly event extraction unit, which is used to analyze the differences in the regulation process among each regulation record and extract anomaly feature events that affect the quality of goods.

[0053] Furthermore, the regulation optimization analysis module includes an event impact analysis unit and an anomaly node setting unit;

[0054] The event impact analysis unit is used to analyze the impact of each anomaly feature event in each regulation record to obtain the impact degree of each anomaly feature event; The anomaly node setting unit is used to set the anomaly occurrence nodes of each regulation record based on the regulation conditions of each regulation record and the included several anomaly feature events.

[0055] Furthermore, the real-time regulation analysis module includes an anomaly occurrence prediction unit and a risk anomaly judgment unit;

[0056] The anomaly occurrence prediction unit is used to identify anomaly feature events in the real-time regulation record generated during the current transportation process and predict the anomaly occurrence node of the real-time regulation record; The risk anomaly judgment unit is used to issue a risk warning for the currently transported goods when the anomaly occurrence node is triggered, capture the regulation duration of the real-time regulation record, and judge whether there is an anomaly in the regulation process.

[0057] Compared with the prior art, the beneficial effects of the present invention are:

[0058] 1. By monitoring the quality of goods during the transportation process, the present invention helps to maintain the stability of the storage space, can timely control the environmental stability when there are environmental fluctuations, and maximally guarantees the quality of goods;

[0059] 2. On the basis of the original automatic regulation, the present invention analyzes the regulation process during the entire transportation process, identifies and optimizes the anomalies generated due to environmental changes during the regulation process, helps to more accurately grasp the timing of environmental regulation during the transportation process, and effectively guarantees the quality of goods during the transportation process;

[0060] 3. By keeping the expected environmental data during the goods transportation process within a more accurate range, the present invention can timely adjust when the environmental data fluctuates, solves the problem that the quality of goods is affected due to large fluctuations in environmental data and too long regulation time, and performs anomaly recognition based on the regulation duration, helps the staff to timely identify anomalies, maximally guarantees the quality of goods, and reduces losses. Description of the Drawings

[0061] Figure 1Schematic diagram of the steps of a method for monitoring the quality of logistics goods based on the Internet of Things;

[0062] Figure 2 Schematic diagram of the structure of a system for monitoring the quality of logistics goods based on the Internet of Things. Detailed implementation manners

[0063] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0064] Embodiment: As Figures 1 to 2 shown, the present invention provides a method for monitoring the quality of logistics goods based on the Internet of Things. The monitoring method includes the following steps:

[0065] Step S100: Collect the environmental data of the goods storage space during each logistics transportation process, analyze the regulation situation of the environmental data, and generate corresponding regulation records; based on the regulation results between each regulation record, set the expected environmental data of the goods;

[0066] Among them, step S100 includes the following steps:

[0067] Step S101: Install a number of monitoring devices and regulation devices in the goods storage space. During the logistics transportation process, use the regulation devices to regulate the environmental data of the storage space, use the monitoring devices to collect the environmental data of the storage space in real time, sort the collected environmental data in the order of collection time, and generate a regulation record;

[0068] Step S102: Arbitrarily select a regulation record, and respectively extract the environmental data of the storage space when the regulation device starts to run and stops running in the selected regulation record to obtain a number of target regulation data;

[0069] Step S103: Obtain the change situation of the environmental data of the regulation device from the start of operation to the stop of operation each time; if the environmental data is in an increasing state, set the target regulation data at the start of operation as the minimum expected data, and set the target regulation data at the stop of operation as the maximum expected data; if the environmental data is in a decreasing state, set the target regulation data at the start of operation as the maximum expected data, and set the target regulation data at the stop of operation as the minimum expected data;

[0070] Step S104: Divide each target control data to obtain a minimum expected data set and a maximum expected data set respectively, and extract the maximum value A in the minimum expected data set max and the minimum value B in the maximum expected data set min , to obtain the expected range of the environmental data of the goods (A max , B min ).

[0071] Step S200: Obtain the quality inspection result of the goods after the transportation is completed, and identify abnormalities in each control record; analyze the differences in the control process between each control record, and extract abnormal characteristic events that affect the quality of the goods;

[0072] Among them, Step S200 includes the following steps:

[0073] Step S201: Whenever the transportation is completed, preset quality assessment rules for several dimensions, conduct a quality assessment on the goods to obtain a quality inspection result, and use the quality inspection result as the accuracy of the control record corresponding to the logistics transportation; set the accuracy of any selected control record as Z, and preset an accuracy threshold Z min , if Z < Z min , then set the selected control record as an abnormal control record, if Z > Z min , then set the selected control record as a normal control record;

[0074] Step S202: Obtain the control data recorded in any control record, extract several control features from the obtained control data, and at the same time extract the features of the external environment where the goods storage space is located to obtain several environmental features, and summarize the extracted control features and environmental features to obtain a feature set;

[0075] Step S203: Arbitrarily select a normal control record, extract the corresponding data of the selected normal control record according to each feature in the feature set to obtain the feature value corresponding to each feature; for any one feature, obtain the feature values of each normal control record to obtain the normal value range of each feature;

[0076] Step S204: Arbitrarily select an abnormal control record to obtain the feature values of the selected abnormal control record regarding each feature. If there is a feature value of a control feature that is not within the normal value range, then extract the control data of the control feature in the selected abnormal control record to generate the abnormal characteristic event of the selected abnormal control record. If there is a feature value of an environmental feature that is not within the normal value range, then set the environmental feature as an abnormal characteristic event;

[0077] Step S205: Screen and summarize abnormal feature events for each abnormal regulation record to generate a set of abnormal feature events affecting the quality of goods.

[0078] Step S300: Analyze the influence of each abnormal feature event in each regulation record to obtain the influence degree of each abnormal feature event; based on the regulation situation of each regulation record and the included several abnormal feature events, set the abnormal occurrence nodes of each regulation record;

[0079] Among them, step S300 includes the following steps:

[0080] Step S301: Arbitrarily select an abnormal regulation record, obtain several abnormal feature events included in the selected abnormal regulation record, select the i-th abnormal feature event from them, and obtain the deviation degree P between the i-th abnormal feature event and the corresponding normal value range i ; Obtain the deviation degree of each of the several abnormal feature events, according to the formula:

[0081]

[0082] Among them, c is the number of abnormal feature events included in the selected abnormal regulation record; calculate the feature proportion η of the i-th abnormal feature event in the selected abnormal regulation record i ;

[0083] Step S303: Obtain the accuracy of each normal regulation record, and calculate the average value to obtain the expected accuracy Z ave ; Set the accuracy of the selected abnormal regulation record as Z', according to the formula:

[0084] γ i =(Z ave -Z′)×η i ;

[0085] Calculate the influence degree γ of the i-th abnormal feature event i ;

[0086] Example 1: Assume there are two abnormal feature events, with deviation degrees of 10% and 20% respectively. Therefore, the feature proportions of the two abnormal feature events are 33.33% and 66.67% respectively; obtain the expected accuracy of 90%, but the accuracy of the selected abnormal regulation record is 88%. Calculate that the influence degrees of the two abnormal feature events are (90%-88%)×33.33% = 0.6666% and (90%-88%)×66.67% = 1.3334% respectively;

[0087] Step S304: Set the expected range of the environmental data of the goods (A max , Bmin ) According to the formula:

[0088]

[0089] The expected minimum value Min and the expected maximum value Max for correcting the goods are calculated, and the actual expected range (Min, Max) after correcting the goods is generated;

[0090] Embodiment 2: Set the expected range of the environmental data of the goods to (36°C, 40°C). Based on Embodiment 1, it is calculated that Min = 36×(1 + 0.6666%)×(1 + 1.3334%) = 36.723°C, Max = 39.212°C, and the actual expected range is obtained as (36.723°C, 39.212°C);

[0091] Step S305: Extract all target regulation data from the selected abnormal regulation records, sort all the target regulation data according to the collection time, and arbitrarily select the target regulation data when a regulation device starts to run. If the next target regulation data of the selected target regulation data is the one collected when the regulation device stops running, then set the two target regulation data as a data group;

[0092] Step S306: Arbitrarily select a data group, obtain the target regulation data D2 of the data group when the regulation device stops running. If D2 ∈ (Min, Max), obtain the regulation duration T1 of the regulation device from the start of operation to when the environmental data meets the actual expected range (Min, Max) in the data group. At the same time, obtain the regulation duration T2 of the regulation device from the start of operation to the stop of operation in the data group and the environmental data change amount ΔD = D2 - D1, where D1 is the target regulation data of the data group when the regulation device starts to run;

[0093] Step S307: Obtain the regulation duration of each data group in each normal regulation record from the start of operation to the stop of operation of the regulation device, and calculate the average value to obtain the average regulation duration T ave ; According to the formula:

[0094]

[0095] The two abnormal occurrence nodes Y1 and Y2 of the selected abnormal regulation record are calculated;

[0096] Embodiment 3: Set the average regulation duration to 1h, the environmental data change amount ΔD = 1°C, and the regulation duration T2 = 2h. Based on Embodiment 2, the actual expected range is (36.723°C, 39.212°C), and it is calculated that Y1 = 36.723 - 1×0.5 = 36.223°C, Y2 = 39.212 + 0.5 = 39.712°C.

[0097] Step S400: Identify abnormal feature events in the real-time regulation record generated during the current transportation process, and predict the abnormal occurrence nodes of the real-time regulation record; when an abnormal occurrence node is triggered, issue a risk warning for the currently transported goods, and capture the regulation duration of the real-time regulation record to determine whether there is an abnormality in the regulation process.

[0098] Among them, step S400 includes the following steps:

[0099] Step S401: Obtain the regulation data recorded in the current real-time regulation record and the external environment data of the goods storage space, extract several abnormal feature events, and set the influence degree of the jth abnormal feature event as γ j ; Obtain the expected range of the environmental data of the goods (A max , B min ), and calculate the corrected actual expected range (Min’, Max’);

[0100] Step S402: Obtain each regulation record containing several extracted abnormal feature events, respectively obtain two abnormal occurrence nodes of each regulation record, and calculate the average value to obtain the average abnormal occurrence node Y1 ave and Y2 ave ; According to the formula:

[0101] Y1′ = Y1 ave +Min′ - Min

[0102] Y2′ = Y2 ave +Max′ - Max;

[0103] Calculate the predicted values of the two abnormal occurrence nodes of the real-time regulation record to be Y1’ and Y2’ respectively;

[0104] Step S403: Collect environmental data of the storage space corresponding to the real-time regulation record through monitoring equipment, and set the currently monitored environmental data as D now , if D now < Y1’ or D now > Y2’, then issue a risk warning for the currently transported goods, and transfer the regulation equipment to regulate the storage space, and count the regulation duration T from the start to the stop of the regulation equipment now ;

[0105] Step S404: Obtain the regulation duration of each regulation in each abnormal regulation record, and select the minimum regulation duration as the abnormal duration threshold T for judging abnormal regulation th , if T now > T th, an abnormal reminder is given for the regulation process.

[0106] A logistics goods quality supervision system, the supervision system includes a regulation process analysis module, an abnormal regulation analysis module, a regulation optimization analysis module, and a real-time regulation analysis module;

[0107] The regulation process analysis module is used to collect the environmental data of the goods storage space during each logistics transportation process, analyze the regulation situation of the environmental data, and generate corresponding regulation records; based on the regulation results between each regulation record, set the expected environmental data of the goods;

[0108] The abnormal regulation analysis module is used to obtain the quality inspection results of the goods after transportation, and identify abnormalities in each regulation record; analyze the differences in the regulation process between each regulation record, and extract abnormal characteristic events that affect the quality of the goods;

[0109] The regulation optimization analysis module is used to analyze the influence of each abnormal characteristic event in each regulation record to obtain the influence degree of each abnormal characteristic event; based on the regulation situation of each regulation record and the included several abnormal characteristic events, set the abnormal occurrence nodes of each regulation record;

[0110] The real-time regulation analysis module is used to identify abnormal characteristic events in the real-time regulation record generated by the current transportation process, predict the abnormal occurrence node of the real-time regulation record; when the abnormal occurrence node is triggered, give a risk warning for the currently transported goods, and capture the regulation duration of the real-time regulation record to determine whether there is an abnormality in the regulation process.

[0111] Among them, the regulation process analysis module includes a regulation record establishment unit and an expected range setting unit;

[0112] The regulation record establishment unit is used to collect the environmental data of the goods storage space during each logistics transportation process, analyze the regulation situation of the environmental data, and generate corresponding regulation records; the expected range setting unit is used to set the expected environmental data of the goods based on the regulation results between each regulation record.

[0113] Among them, the abnormal regulation analysis module includes an abnormal regulation identification unit and an abnormal event extraction unit;

[0114] The abnormal regulation identification unit is used to obtain the quality inspection results of the goods after transportation, and identify abnormalities in each regulation record; the abnormal event extraction unit is used to analyze the differences in the regulation process between each regulation record, and extract abnormal characteristic events that affect the quality of the goods.

[0115] Among them, the regulation optimization analysis module includes an event impact analysis unit and an abnormal node setting unit;

[0116] The event impact analysis unit is used to analyze the impact of each abnormal feature event in each regulation record to obtain the impact degree of each abnormal feature event; the abnormal node setting unit is used to set the abnormal occurrence nodes of each regulation record based on the regulation situation of each regulation record and the included several abnormal feature events.

[0117] Among them, the real-time regulation analysis module includes an abnormal occurrence prediction unit and a risk abnormality judgment unit;

[0118] The abnormal occurrence prediction unit is used to identify abnormal feature events in the real-time regulation record generated by the current transportation process and predict the abnormal occurrence nodes of the real-time regulation record; the risk abnormality judgment unit is used to issue a risk warning for the current transported goods when the abnormal occurrence node is triggered, capture the regulation duration of the real-time regulation record, and judge whether there is an abnormality in the regulation process.

[0119] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present invention. Any reference signs in the claims should not be regarded as limiting the claims involved.

Claims

1. A method for monitoring the quality of logistics goods based on the Internet of Things, characterized by: The supervision method comprises the following steps: Step S100: Collect environmental data of the cargo storage space during each logistics transportation process, analyze the control status of the environmental data, and generate corresponding control records; based on the control results between each control record, set the expected environmental data of the cargo; Step S200: obtaining the quality inspection results of the goods after delivery, identifying abnormalities in each control record; analyzing the differences in the control process between each control record, and extracting abnormal characteristic events that affect the quality of the goods; Step S300: Analyze the impact of each abnormal characteristic event in each control record to obtain the impact degree of each abnormal characteristic event; based on the control situation of each control record and the number of abnormal characteristic events contained, set the abnormal occurrence node of each control record; Step S400: Identify abnormal characteristic events for the real-time control record generated in the current transportation process, and predict the abnormal occurrence node of the real-time control record; when the abnormal occurrence node is triggered, issue a risk warning for the current transported goods, capture the control duration of the real-time control record, and determine whether there is any abnormality in the control process.

2. According to the method for monitoring the quality of logistics goods based on the Internet of Things in claim 1, it is characterized by: The step S100 includes the following steps: Step S101: a plurality of monitoring devices and control devices are installed in the cargo storage space. The control devices are used to control the environmental data of the storage space during the logistics transportation process. The monitoring devices are used to collect the environmental data of the storage space in real time. The collected environmental data are sorted in the order of collection time to generate a control record. Step S102: randomly selecting a control record, respectively extracting environmental data of the storage space when the control device starts to run and stops running in the selected control record, to obtain a plurality of target control data; Step S103: Obtain the environmental data change of the control device from the start of operation to the stop of operation each time; if the environmental data is in an increasing state, the target control data when the operation starts is set to the minimum expected data, and the target control data when the operation stops is set to the maximum expected data; if the environmental data is in a decreasing state, the target control data when the operation starts is set to the maximum expected data, and the target control data when the operation stops is set to the minimum expected data; Step S104: Divide each target control data into a minimum expected data set and a maximum expected data set, and extract the maximum value A in the minimum expected data set. max and the minimum value B in the maximum expected data set min , get the expected range of environmental data for the goods (A max ,B min ).

3. The method for monitoring the quality of logistics goods based on the Internet of Things according to claim 1 is characterized in that: The step S200 includes the following steps: Step S201: Whenever the delivery is completed, several dimensions of quality assessment rules are preset to evaluate the quality of the goods, obtain a quality inspection result, and use the quality inspection result as the accuracy of the control record of the corresponding logistics delivery; set the accuracy of any selected control record as Z, and preset an accuracy threshold Z min , if Z<Z min , then the selected control record is set as the abnormal control record. If Z>Z min , then the selected control record is set as the normal control record; Step S202: acquiring the control data recorded in any control record, extracting a number of control features from the acquired control data, and extracting features of the external environment where the cargo storage space is located to obtain a number of environmental features, and summarizing the extracted control features and environmental features to obtain a feature set; Step S203: randomly select a normal control record, extract corresponding data for each feature in the feature set of the selected normal control record, and obtain a feature value corresponding to each feature; for any feature, obtain the feature value of each normal control record, and obtain a normal value range of each feature; Step S204: arbitrarily select an abnormal control record, obtain the characteristic value of each feature of the selected abnormal control record, if there is a characteristic value of a control feature that is not within the normal value range, extract the control data of the control feature in the selected abnormal control record, and generate an abnormal characteristic event of the abnormal control record, if there is a characteristic value of an environmental feature that is not within the normal value range, set the environmental feature as an abnormal characteristic event; Step S205: Screen and summarize abnormal characteristic events for each abnormal control record to generate a set of abnormal characteristic events that affect the quality of the goods.

4. The method for monitoring the quality of logistics goods based on the Internet of Things according to claim 3 is characterized by: The step S300 includes the following steps: Step S301: arbitrarily select an abnormal regulation record, obtain several abnormal characteristic events contained in the selected abnormal regulation record, select the ith abnormal characteristic event from them, and obtain the deviation degree between the ith abnormal characteristic event and the corresponding normal value range as P i ; Obtain the degree of deviation of each of several abnormal characteristic events according to the formula: Where c is the number of abnormal characteristic events contained in the selected abnormal regulation record; the characteristic proportion η of the i-th abnormal characteristic event in the selected abnormal regulation record is calculated i ; Step S303: Obtain the accuracy of each normal control record, calculate the average value and obtain the expected accuracy Z ave ; Set the accuracy of the selected abnormal control record to Z', according to the formula: γ i =(From ave -Z′)×η i ; Calculate the impact of the i-th abnormal characteristic event γ i ; Step S304: Set the expected range of environmental data for the goods (A max ,B min ), according to the formula: Calculate the expected minimum value Min and the expected maximum value Max of the goods to be corrected, and generate the actual expected range (Min, Max) of the goods after correction; Step S305: extract all target control data from the selected abnormal control record, sort all target control data according to the collection time, arbitrarily select a target control data when the control device starts to operate, and if the next target control data of the selected target control data is collected when the control device stops operating, the two target control data are set as one data group; Step S306: randomly select a data group, obtain the target control data D2 of the data group when the control device stops running, if D2∈(Min,Max), obtain the control time T1 of the control device in the data group from the start of operation to the time when the environmental data meets the actual expected range (Min,Max), and at the same time obtain the control time T2 and the environmental data change ΔD=D2-D1 from the start of operation to the stop of operation of the control device in the data group, where D1 is the target control data of the data group when the control device starts running; Step S307: Obtain the control time from the start of operation to the stop of operation of the control device in each data group in each normal control record, and calculate the average value to obtain the average control time T ave ; According to the formula: The two abnormal occurrence nodes Y1 and Y2 of the selected abnormal regulation record are calculated.

5. The method for monitoring the quality of logistics goods based on the Internet of Things according to claim 4 is characterized in that: The step S400 includes the following steps: Step S401: Obtain the control data recorded in the current real-time control record and the external environment data of the cargo storage space, and extract a number of abnormal characteristic events, setting the impact degree of the jth abnormal characteristic event as γ j ; Obtain the expected range of environmental data for goods (A max ,B min ), calculate the corrected actual expected range (Min', Max'); Step S402: Obtain each control record containing a number of extracted abnormal feature events, obtain two abnormal occurrence nodes of each control record, and calculate the average value to obtain the average value Y1 of the abnormal occurrence nodes ave and Y2 ave ; According to the formula: Y1′=Y1 ave +Min′-Min Y2′=Y2 ave +Max′-Max; The predicted values ​​of the two abnormal occurrence nodes of the real-time control record are calculated to be Y1' and Y2' respectively; Step S403: Collect environmental data from the storage space corresponding to the real-time control record through the monitoring device, and set the currently monitored environmental data as D now , if D now <Y1' or D now > Y2', then the risk warning is issued for the currently transported goods, and the control equipment is called to control the storage space, and the control time T of the control equipment from the start to the stop is counted now ; Step S404: Obtain the duration of each regulation in each abnormal regulation record, and select the regulation duration with the smallest value as the abnormal duration threshold T for judging abnormal regulation. th , if T now >T th , an abnormal reminder will be given for the control process.

6. A logistics cargo quality supervision system, used to implement a logistics cargo quality supervision method based on the Internet of Things as claimed in any one of claims 1 to 5, characterized in that: The supervision system includes a control process analysis module, an abnormal control analysis module, a control optimization analysis module and a real-time control analysis module; The control process analysis module is used to collect environmental data of the cargo storage space during each logistics transportation process, analyze the control status of the environmental data, and generate corresponding control records; based on the control results between each control record, the expected environmental data of the cargo is set; The abnormal control analysis module is used to obtain the quality inspection results of the goods after delivery, identify abnormalities in each control record, analyze the differences between the control records regarding the control process, and extract abnormal characteristic events that affect the quality of the goods; The control optimization analysis module is used to analyze the impact of each abnormal characteristic event in each control record to obtain the impact degree of each abnormal characteristic event; Based on the control situation of each control record and several abnormal characteristic events contained therein, the abnormal occurrence node of each control record is set; The real-time control analysis module is used to identify abnormal feature events of the real-time control records generated in the current transportation process and predict the abnormal occurrence nodes of the real-time control records; When the abnormality occurrence node is triggered, a risk warning is issued for the currently transported goods, and the control time of the real-time control record is captured to determine whether there is an abnormality in the control process.

7. A logistics cargo quality supervision system according to claim 6, characterized in that: The control process analysis module includes a control record establishment unit and an expected range setting unit; The control record establishment unit is used to collect the environmental data of the cargo storage space during each logistics transportation process, analyze the control status of the environmental data, and generate corresponding control records; the expected range setting unit is used to set the expected environmental data of the cargo based on the control results between each control record.

8. A logistics cargo quality supervision system according to claim 6, characterized in that: The abnormal regulation analysis module includes an abnormal regulation identification unit and an abnormal event extraction unit; The abnormal control identification unit is used to obtain the quality inspection results of the goods after the transportation is completed, and to identify the abnormalities of each control record; the abnormal event extraction unit is used to analyze the differences between the control records regarding the control process and to extract abnormal characteristic events that affect the quality of the goods.

9. A logistics cargo quality supervision system according to claim 6, characterized in that: The control optimization analysis module includes an event impact analysis unit and an abnormal node setting unit; The event impact analysis unit is used to analyze the impact of each abnormal characteristic event in each control record to obtain the impact degree of each abnormal characteristic event; The abnormal node setting unit is used to set the abnormal occurrence node of each control record based on the control situation of each control record and a number of abnormal characteristic events contained therein.

10. A logistics cargo quality supervision system according to claim 6, characterized in that: The real-time control and analysis module includes an abnormality occurrence prediction unit and a risk abnormality judgment unit; The abnormal occurrence prediction unit is used to identify abnormal characteristic events of the real-time control records generated in the current transportation process and predict the abnormal occurrence nodes of the real-time control records; The risk anomaly judgment unit is used to issue a risk warning for the currently transported goods when an abnormality occurrence node is triggered, and to capture the control time of the real-time control record to determine whether there is an abnormality in the control process.

Images