Data collaborative supervision system and method based on Internet of Things

Abstract

The invention relates to the technical field of data collaborative supervision, in particular to a data collaborative supervision system and method based on the Internet of Things, and the system is characterized in that a data collaborative analysis module obtains the abnormal transportation risk condition of each transportation article feature set in historical data based on a corresponding transportation state analysis model; and obtaining a transportation state risk prediction value of the to-be-transported article in the correlation analysis and evaluation model in real time. According to the invention, data collaboration among multiple parameters can be effectively realized, dynamic regulation and control of the article transportation state are realized by combining the transportation state in the article transportation process and the characteristic condition of the transported article, it is ensured that a logistics transportation user masters the article state to a certain extent in the transportation process, and meanwhile, the transportation efficiency is improved. And subsequent logistics transportation route alternative schemes can be intelligently provided for logistics transportation management and control personnel, the damage risk of the to-be-transported articles in the subsequent transportation process is reduced, and dynamic cooperative supervision of logistics transportation data is realized.

Description

Technical Field

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

[0002] Against the backdrop of the rapid development of IoT technology, the demands for data supervision face increasingly severe challenges. Traditional data supervision methods often have problems such as low level of informatization, data silos, and low supervision efficiency, making it difficult to meet the high requirements of modern enterprises for data security and business continuity.

[0003] For the logistics and transportation industry, the existing data supervision methods monitor content in a relatively one-sided manner, cannot achieve data coordination between multiple parameters, and cannot combine the transportation status of the goods during transportation and the characteristics of the transported goods to achieve dynamic regulation of the transportation status of the goods (existing damaged goods need to be confirmed by the recipient before they can be returned. During transportation, neither the sender nor the receiver can understand whether the status of the goods is intact or damaged. The sender cannot make corresponding response decisions during transportation, and the response efficiency is low). As a result, the existing technology has major defects. Summary of the invention

[0004] The purpose of the present invention is to provide a data collaborative supervision system and method based on the Internet of Things to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a data collaborative supervision method based on the Internet of Things, the method comprising the following steps:

[0006] The transportation status data of the logistics transportation process is collected in real time through sensors, and the collection results of each sensor in the logistics transportation process are summarized through the Internet of Things to build a transportation status analysis model;

[0007] Extract features of items to be transported by logistics transport users to obtain a feature set of items to be transported, bind the obtained feature set of items to be transported with the corresponding transport status analysis model, and obtain a correlation analysis evaluation model;

[0008] Obtain the abnormal transportation risk situation of each transport item feature set in the historical data based on the corresponding transportation status analysis model, and obtain the transportation status risk prediction value of the items to be transported in the association analysis and evaluation model in real time;

[0009] Based on the analysis results of the risk prediction value of the transportation status of the items to be transported in the association analysis evaluation model and the operation decisions of the logistics transportation users for the damaged items in the transportation in the historical data, a logistics operation warning decision based on the items to be transported is generated and fed back to the logistics transportation users;

[0010] Based on the operational decisions of logistics and transportation users regarding the items to be transported and the transportation destinations of the items to be transported, alternative routes for subsequent logistics and transportation are generated and fed back to logistics and transportation control personnel.

[0011] The present invention realizes dual-port early warning for logistics transportation users and logistics transportation control personnel to make decisions, which not only ensures that logistics transportation users can make response decisions in advance for the risk situations of transported items, but also provides auxiliary reference for logistics transportation control personnel in the subsequent transportation routes.

[0012] Preferably, the construction of the transport status analysis model includes: obtaining transport vehicles corresponding to different transport stages in the logistics transport process, wherein the different transport stages are different transport path intervals, and each transport path interval is preset in a database form,

[0013] The transport status data includes the transport time point, the vehicle bump amplitude value and the instantaneous change value of the vehicle speed;

[0014] Obtain a line graph showing how the vehicle bump amplitude value in the transport state data corresponding to different time points in the same transport stage by the sensor set on the same transport vehicle changes with the transport time, and record the function corresponding to the obtained line graph as the first state analysis function; obtain a line graph showing how the instantaneous change value of the vehicle speed in the transport state data corresponding to different time points in the same transport stage by the sensor set on the same transport vehicle changes with the transport time, and record the function corresponding to the obtained line graph as the second state analysis function;

[0015] A set of the first state analysis function and the second state analysis function in the same transport stage is used as a transport state analysis sub-model corresponding to the corresponding transport stage, wherein the transport state analysis sub-model includes transport state analysis sub-models corresponding to all executed transport stages in the logistics transport process;

[0016] Before the transported items arrive at the destination, the transport status analysis model is updated in real time as the transport stage changes.

[0017] Preferably, the feature set of the items to be transported includes the minimum value of the item type and the packaging thickness;

[0018] The obtained association analysis evaluation model is a binding association pair of the transport item feature set and the transport status analysis model.

[0019] Preferably, the real-time acquisition of the transportation status risk prediction value of the items to be transported in the association analysis and evaluation model includes:

[0020] Calculating the first state bias correlation value and the second state bias correlation value corresponding to the transportation state analysis model in the correlation analysis evaluation model,

[0021] CV1 bias =Intergral{SA1 function , CZ1}·[1+ε1·MD{SA1 function , CZ1}],

[0022] Among them, CV1 bias SA1 represents the first state bias correlation value corresponding to the transportation state analysis model in the correlation analysis evaluation model; function Indicates the first state analysis function in the transport state analysis submodel corresponding to the i-th executed transport stage in the transport state analysis model; CZ1 indicates the maximum value of the average function value corresponding to each first state analysis function in the transport state analysis model in each associated analysis evaluation model in which the feature set of the transported items bound in the historical data is the same as the feature set of the items to be transported and the transport result is normal; the transport result includes a normal state and an abnormal damage state; Intergral{SA1 function , CZ1} indicates SA1 function The function integral result in the interval where the corresponding function value is greater than CZ1; MD{SA1 function , CZ1} indicates SA1 function The difference between the maximum function value in and CZ1; ε1 represents the preset first conversion coefficient;

[0023] CV2 bias =Intergral{SA2 function , CZ2}·[1+ε2·MD{SA2 function , CZ2}],

[0024] Among them, CV2 bias SA2 represents the second state bias correlation value corresponding to the transportation state analysis model in the correlation analysis evaluation model; function Indicates the second state analysis function in the transport state analysis submodel corresponding to the i-th executed transport stage in the transport state analysis model; CZ2 indicates the maximum value of the average function value corresponding to each second state analysis function in the transport state analysis model in each associated analysis evaluation model in which the feature set of the transported items bound in the historical data is the same as the feature set of the items to be transported and the transport results are normal; Intergral{SA2 function , CZ2} represents SA2 function The function integral result in the interval where the corresponding function value is greater than CZ2; MD{SA2 function , CZ2} represents SA2 function The difference between the maximum function value in and CZ2; ε2 represents the preset second conversion coefficient;

[0025] Obtain the abnormal transportation risk situation of each transport item feature set in the historical data based on the corresponding transportation state analysis model, calculate the ratio of the number of association analysis evaluation models whose corresponding first state bias association values ​​are greater than the first state reference value in each association analysis evaluation model in which the transport item feature set bound in the historical data is the same as the feature set of the items to be transported and the transportation results are abnormal, and obtain the first bias weight, which is recorded as r1; the first state reference value represents the maximum value of the first state bias association values ​​corresponding to each association analysis evaluation model in which the transport item feature set bound in the historical data is the same as the feature set of the items to be transported and the transportation results are normal;

[0026] Calculate the ratio of the number of association analysis and evaluation models whose corresponding second state bias association values ​​are greater than the second state reference value in each association analysis and evaluation model in which the bound transported item feature set in the historical data is the same as the feature set of the item to be transported and the transportation result is abnormal, to the total number of corresponding association analysis and evaluation models, and obtain a second bias weight, recorded as r2; the second state reference value represents the maximum value of the second state bias association values ​​corresponding to each association analysis and evaluation model in which the bound transported item feature set in the historical data is the same as the feature set of the item to be transported and the transportation result is normal;

[0027] Get the transportation status evaluation value corresponding to the transportation items with the same feature set as the items to be transported in the historical data, recorded as EV, EV = r1 CV1 bias +r2·CV2 bias ;

[0028] The preset transport status evaluation value intervals of the transport status evaluation values ​​corresponding to the transport items with the same feature set as the transport items to be transported and abnormal transport results in the statistical historical data are the same, and the interval length of each preset transport status evaluation value interval is the same, which is recorded as L; construct the evaluation data pairs corresponding to each preset transport status evaluation value interval, and the first value of each evaluation data pair is the midpoint of the corresponding transport status evaluation value interval, and the second value is the quotient of the number of elements whose corresponding transport status evaluation values ​​belong to the corresponding transport status evaluation value interval divided by the product of L and the sum of the elements in the preset transport status evaluation value interval;

[0029] According to the normal distribution function model, a function is fitted to each evaluation data pair, and the obtained fitting function is recorded as F function (x);

[0030] The risk prediction value of the transportation status of the items to be transported in the association analysis evaluation model is recorded as RPV.

[0031]

[0032] Preferably, the generating of a logistics operation warning decision based on the items to be transported comprises:

[0033] When obtaining the transport items with the same feature set as the items to be transported in the historical data, the set of operation decisions of all logistics transportation users whose absolute value of the difference between the corresponding transportation status risk prediction value and the RPV is less than the preset transportation status risk prediction deviation is recorded as the logistics operation warning set;

[0034] The logistics operation warning decision based on the items to be transported is composed of RPV and logistics operation warning set;

[0035] The operational decisions include package return decisions, package reissue decisions, and package continued transportation decisions.

[0036] Preferably, the generating of the route alternatives for subsequent logistics transportation includes:

[0037] Obtain the operation decision of the logistics transportation user for the items to be transported. When the operation decision obtained is a decision to continue transporting the package, obtain the transportation destination of the items to be transported and the current decision execution location of the items to be transported.

[0038] If the current location of the item to be transported is on the transport vehicle, the current decision execution location of the item to be transported is the next transfer station; if the current location of the item to be transported is a transfer station, the current decision execution location of the item to be transported is the corresponding transfer station;

[0039] Obtain the corresponding routes from the current decision execution location of the item to be transported to the transportation destination of the item to be transported in the database,

[0040] The transport state analysis sub-models corresponding to each transport vehicle that passes through the kth pass route within the most recent preset time period based on the current time are added to the association analysis evaluation reference model, and the corresponding transport state risk prediction values ​​after the transport state analysis sub-models are added are calculated respectively; k is greater than or equal to 1 and less than or equal to the total number of corresponding pass routes in the database from the current decision execution place of the items to be transported to the transportation destination of the items to be transported;

[0041] The association analysis and evaluation reference model represents an association analysis and evaluation model composed of the transportation status data of the items to be transported from the starting transportation point to the current location of the items to be transported;

[0042] According to the average value of each transportation status risk prediction value corresponding to the same route, each route is sorted in ascending order to generate route alternatives for subsequent logistics transportation.

[0043] In the present invention, the route alternatives for subsequent logistics transportation are fed back to the logistics transportation control personnel by the system, providing data reference for the designation of subsequent logistics transportation routes. Its role is to serve as an auxiliary reference, but the actual transportation route is still decided by the logistics transportation control personnel based on comprehensive considerations of the actual situation.

[0044] A data collaborative supervision system based on the Internet of Things, comprising: a state analysis model construction module, a correlation evaluation model construction module, a data collaborative analysis module, a user decision warning feedback module and an adaptive decision feedback module.

[0045] The state analysis model building module collects the transportation state data in the logistics transportation process in real time through sensors, and summarizes the collection results of each sensor in the logistics transportation process through the Internet of Things to build a transportation state analysis model;

[0046] The association evaluation model construction module extracts features of items to be transported by logistics transportation users to obtain a feature set of items to be transported, and binds the obtained feature set of items to be transported with a corresponding transportation status analysis model to obtain an association analysis evaluation model;

[0047] The data collaborative analysis module obtains the abnormal transportation risk situation of each transport item feature set in the historical data based on the corresponding transportation status analysis model, and obtains the transportation status risk prediction value of the to-be-transported item in the association analysis evaluation model in real time;

[0048] The user decision warning feedback module generates a logistics operation warning decision based on the items to be transported based on the analysis results of the transportation status risk prediction value of the items to be transported in the association analysis evaluation model and the operation decision of the logistics transportation user for the damaged items to be transported in the historical data, and feeds back to the logistics transportation user;

[0049] The adaptive decision feedback module combines the operation decision of the logistics transportation user on the items to be transported and the transportation destination of the items to be transported, generates route alternatives for subsequent logistics transportation, and feeds back to the logistics transportation control personnel.

[0050] Preferably, the association evaluation model construction module includes a feature set construction unit and an analysis and evaluation unit.

[0051] The feature set construction unit extracts features of items to be transported by the logistics transportation user to obtain a feature set of items to be transported;

[0052] The analysis and evaluation unit binds the obtained feature set of the items to be transported with the corresponding transport status analysis model to obtain a correlation analysis and evaluation model.

[0053] Preferably, the user decision warning feedback module includes a historical decision collection unit and an operation warning decision generation unit.

[0054] The historical decision collection unit obtains the analysis results of the transportation status risk prediction value of the items to be transported in the association analysis evaluation model, and the operation decisions of the logistics transportation users for the damaged items to be transported in the historical data;

[0055] The operation warning decision generating unit generates a logistics operation warning decision based on the items to be transported according to the collection results of the historical decision collecting unit, and feeds back to the logistics transportation user.

[0056] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention can effectively realize data coordination among multiple parameters, realize dynamic regulation of the transportation status of items by combining the transportation status of items during transportation and the characteristics of the transported items, ensure that the logistics transportation users have control over the status of items to a certain extent during transportation, and ensure that when there is a risk of damage to the transported items, the logistics transportation users can make response decisions in advance. At the same time, it can also intelligently provide logistics transportation management and control personnel with alternative routes for subsequent logistics transportation, reduce the risk of damage to the items to be transported in the subsequent transportation process, and realize dynamic collaborative supervision between logistics transportation data. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0058] Figure 1 It is a schematic diagram of the system structure of the present invention;

[0059] Figure 2 It is a schematic flow chart of the method of the present invention. DETAILED DESCRIPTION

[0060] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] See also Figure 1 , the present invention provides a technical solution:

[0062] A data collaborative supervision system based on the Internet of Things, comprising: a state analysis model construction module, a correlation evaluation model construction module, a data collaborative analysis module, a user decision warning feedback module and an adaptive decision feedback module.

[0063] The state analysis model building module collects the transportation state data in the logistics transportation process in real time through sensors, and summarizes the collection results of each sensor in the logistics transportation process through the Internet of Things to build a transportation state analysis model;

[0064] The association evaluation model construction module includes a feature set construction unit and an analysis and evaluation unit.

[0065] The feature set construction unit extracts features of items to be transported by the logistics transportation user to obtain a feature set of items to be transported;

[0066] The analysis and evaluation unit binds the obtained feature set of the items to be transported with the corresponding transport status analysis model to obtain a correlation analysis and evaluation model;

[0067] The data collaborative analysis module obtains the abnormal transportation risk situation of each transport item feature set in the historical data based on the corresponding transportation status analysis model, and obtains the transportation status risk prediction value of the to-be-transported item in the association analysis evaluation model in real time;

[0068] The user decision warning feedback module includes a historical decision collection unit and an operation warning decision generation unit.

[0069] The historical decision collection unit obtains the analysis results of the transportation status risk prediction value of the items to be transported in the association analysis evaluation model, and the operation decisions of the logistics transportation users for the damaged items to be transported in the historical data;

[0070] The operation warning decision generation unit generates a logistics operation warning decision based on the items to be transported according to the collection results of the historical decision collection unit, and feeds back to the logistics transportation user;

[0071] The adaptive decision feedback module combines the operation decision of the logistics transportation user on the items to be transported and the transportation destination of the items to be transported, generates route alternatives for subsequent logistics transportation, and feeds back to the logistics transportation control personnel.

[0072] In this embodiment, the alternative routes for subsequent logistics transportation are fed back to the logistics transportation control personnel by the system, providing data reference for the designation of subsequent logistics transportation routes. Its role is to serve as an auxiliary reference. However, the actual transportation route is still decided by the logistics transportation control personnel based on comprehensive considerations of actual conditions. The final transportation route is determined by the logistics transportation control personnel.

[0073] like Figure 2 As shown, a data collaborative supervision method based on the Internet of Things includes the following steps:

[0074] The transportation status data of the logistics transportation process is collected in real time by sensors, and the collection results of each sensor in the logistics transportation process are summarized through the Internet of Things to build a transportation status analysis model; the construction of the transportation status analysis model includes: obtaining the transportation vehicles corresponding to different transportation stages in the logistics transportation process, the different transportation stages are different transportation path intervals, and each transportation path interval is preset in the database form,

[0075] The transport status data includes the transport time point, the vehicle bump amplitude value and the vehicle speed instantaneous change value;

[0076] In this embodiment, the two vehicle transportation states, the vehicle jolting amplitude value and the vehicle speed instantaneous change value, reflect different vehicle transportation risk situations. The vehicle jolting amplitude value reflects, to a certain extent, the route conditions (road surface flatness) traveled by the logistics transportation vehicle; while the vehicle speed instantaneous change value reflects, to a certain extent, the driving habits of the drivers of the logistics vehicles and the road congestion conditions of the logistics transportation vehicles when they are driving on the corresponding roads.

[0077] Obtain a line graph showing how the vehicle bump amplitude value in the transport state data corresponding to different time points in the same transport stage by the sensor set on the same transport vehicle changes with the transport time, and record the function corresponding to the obtained line graph as the first state analysis function; obtain a line graph showing how the instantaneous change value of the vehicle speed in the transport state data corresponding to different time points in the same transport stage by the sensor set on the same transport vehicle changes with the transport time, and record the function corresponding to the obtained line graph as the second state analysis function;

[0078] A set of the first state analysis function and the second state analysis function in the same transport stage is used as a transport state analysis sub-model corresponding to the corresponding transport stage, wherein the transport state analysis sub-model includes transport state analysis sub-models corresponding to all executed transport stages in the logistics transport process;

[0079] Before the transported items arrive at the destination, the transport status analysis model is updated in real time as the transport stage changes.

[0080] Extract features of items to be transported by logistics transport users to obtain a feature set of items to be transported, bind the obtained feature set of items to be transported with a corresponding transport status analysis model, and obtain a correlation analysis evaluation model; the feature set of items to be transported includes the type of items and the minimum value of packaging thickness;

[0081] The obtained association analysis evaluation model is a binding association pair of the transport item feature set and the transport status analysis model.

[0082] Obtain the abnormal transportation risk situation of each transport item feature set in the historical data based on the corresponding transportation status analysis model, and obtain the transportation status risk prediction value of the items to be transported in the association analysis and evaluation model in real time;

[0083] The real-time acquisition of the transportation status risk prediction value of the items to be transported in the association analysis and evaluation model includes:

[0084] Calculating the first state bias correlation value and the second state bias correlation value corresponding to the transportation state analysis model in the correlation analysis evaluation model,

[0085] CV1 bias =Intergral{SA1 function , CZ1}·[1+ε1·MD{SA1 function , CZ1}],

[0086] Among them, CV1 bias SA1 represents the first state bias correlation value corresponding to the transportation state analysis model in the correlation analysis evaluation model; function Indicates the first state analysis function in the transport state analysis submodel corresponding to the i-th executed transport stage in the transport state analysis model; CZ1 indicates the maximum value of the average function value corresponding to each first state analysis function in the transport state analysis model in each associated analysis evaluation model in which the feature set of the transported items bound in the historical data is the same as the feature set of the items to be transported and the transport result is normal; the transport result includes a normal state and an abnormal damage state; Intergral{SA1 function , CZ1} indicates SA1 function The function integral result in the interval where the corresponding function value is greater than CZ1; MD{SA1 function , CZ1} indicates SA1 function The difference between the maximum function value in and CZ1; ε1 represents the preset first conversion coefficient;

[0087] CV2 bias =Intergral{SA2 function , CZ2}·[1+ε2·MD{SA2 function , CZ2}],

[0088] Among them, CV2 bias SA2 represents the second state bias correlation value corresponding to the transportation state analysis model in the correlation analysis evaluation model; functionIndicates the second state analysis function in the transport state analysis submodel corresponding to the i-th executed transport stage in the transport state analysis model; CZ2 indicates the maximum value of the average function value corresponding to each second state analysis function in the transport state analysis model in each associated analysis evaluation model in which the feature set of the transported items bound in the historical data is the same as the feature set of the items to be transported and the transport results are normal; Intergral{SA2 function , CZ2} represents SA2 function The function integral result in the interval where the corresponding function value is greater than CZ2; MD{SA2 function , CZ2} represents SA2 function The difference between the maximum function value in and CZ2; ε2 represents the preset second conversion coefficient;

[0089] Obtain the abnormal transportation risk situation of each transport item feature set in the historical data based on the corresponding transportation state analysis model, calculate the ratio of the number of association analysis evaluation models whose corresponding first state bias association values ​​are greater than the first state reference value in each association analysis evaluation model in which the transport item feature set bound in the historical data is the same as the feature set of the items to be transported and the transportation results are abnormal, and obtain the first bias weight, which is recorded as r1; the first state reference value represents the maximum value of the first state bias association values ​​corresponding to each association analysis evaluation model in which the transport item feature set bound in the historical data is the same as the feature set of the items to be transported and the transportation results are normal;

[0090] Calculate the ratio of the number of association analysis and evaluation models whose corresponding second state bias association values ​​are greater than the second state reference value in each association analysis and evaluation model in which the bound transported item feature set in the historical data is the same as the feature set of the item to be transported and the transportation result is abnormal, to the total number of corresponding association analysis and evaluation models, and obtain a second bias weight, recorded as r2; the second state reference value represents the maximum value of the second state bias association values ​​corresponding to each association analysis and evaluation model in which the bound transported item feature set in the historical data is the same as the feature set of the item to be transported and the transportation result is normal;

[0091] Get the transportation status evaluation value corresponding to the transportation items with the same feature set as the items to be transported in the historical data, recorded as EV, EV = r1 CV1 bias +r2·CV2 bias ;

[0092] The preset transport status evaluation value intervals of the transport status evaluation values ​​corresponding to the transport items with the same feature set as the transport items to be transported and abnormal transport results in the statistical historical data are the same, and the interval length of each preset transport status evaluation value interval is the same, which is recorded as L; construct the evaluation data pairs corresponding to each preset transport status evaluation value interval, and the first value of each evaluation data pair is the midpoint of the corresponding transport status evaluation value interval, and the second value is the quotient of the number of elements whose corresponding transport status evaluation values ​​belong to the corresponding transport status evaluation value interval divided by the product of L and the sum of the elements in the preset transport status evaluation value interval;

[0093] According to the normal distribution function model, a function is fitted to each evaluation data pair, and the obtained fitting function is recorded as F function (x);

[0094] The risk prediction value of the transportation status of the items to be transported in the association analysis evaluation model is recorded as RPV.

[0095]

[0096] Based on the analysis results of the risk prediction value of the transportation status of the items to be transported in the association analysis evaluation model and the operation decisions of the logistics transportation users for the damaged items to be transported in the historical data, a logistics operation warning decision based on the items to be transported is generated and fed back to the logistics transportation users; the generation of the logistics operation warning decision based on the items to be transported includes:

[0097] When obtaining the transport items with the same feature set as the items to be transported in the historical data, the set of operation decisions of all logistics transportation users whose absolute value of the difference between the corresponding transportation status risk prediction value and the RPV is less than the preset transportation status risk prediction deviation is recorded as the logistics operation warning set;

[0098] The logistics operation warning decision based on the items to be transported is composed of RPV and logistics operation warning set;

[0099] The operational decisions include package return decisions, package reissue decisions, and package continued transportation decisions.

[0100] Combined with the operation decision of the logistics transportation user for the items to be transported and the transportation destination of the items to be transported, a route alternative plan for subsequent logistics transportation is generated and fed back to the logistics transportation control personnel; the generation of the route alternative plan for subsequent logistics transportation includes:

[0101] Obtain the operation decision of the logistics transportation user for the items to be transported. When the operation decision obtained is a decision to continue transporting the package, obtain the transportation destination of the items to be transported and the current decision execution location of the items to be transported.

[0102] If the current location of the item to be transported is on the transport vehicle, the current decision execution location of the item to be transported is the next transfer station; if the current location of the item to be transported is a transfer station, the current decision execution location of the item to be transported is the corresponding transfer station;

[0103] Obtain the corresponding routes from the current decision execution location of the item to be transported to the transportation destination of the item to be transported in the database,

[0104] The transport state analysis sub-models corresponding to each transport vehicle that passes through the kth pass route within the most recent preset time period based on the current time are added to the association analysis evaluation reference model, and the corresponding transport state risk prediction values ​​after the transport state analysis sub-models are added are calculated respectively; k is greater than or equal to 1 and less than or equal to the total number of corresponding pass routes in the database from the current decision execution place of the items to be transported to the transportation destination of the items to be transported;

[0105] In this embodiment, the transport status analysis sub-models corresponding to each transport vehicle passing through the kth route within the most recent preset time period based on the current time are added to the association analysis evaluation reference model respectively. Its essence is to update the association analysis evaluation reference model at the current time while predicting the transport status corresponding to subsequent transport vehicles, thereby realizing the prediction of the transport status risk under the overall transport process of the transported items.

[0106] The association analysis and evaluation reference model represents an association analysis and evaluation model composed of the transportation status data of the items to be transported from the starting transportation point to the current location of the items to be transported;

[0107] According to the average value of each transportation status risk prediction value corresponding to the same route, each route is sorted in ascending order to generate route alternatives for subsequent logistics transportation.

[0108] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0109] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A data collaborative supervision method based on the Internet of Things, characterized in that: The method comprises the following steps: The transportation status data of the logistics transportation process is collected in real time through sensors, and the collection results of each sensor in the logistics transportation process are summarized through the Internet of Things to build a transportation status analysis model; Extract features of items to be transported by logistics transport users to obtain a feature set of items to be transported, bind the obtained feature set of items to be transported with the corresponding transport status analysis model, and obtain a correlation analysis evaluation model; Obtain the abnormal transportation risk situation of each transport item feature set in the historical data based on the corresponding transportation status analysis model, and obtain the transportation status risk prediction value of the items to be transported in the association analysis and evaluation model in real time; Based on the analysis results of the risk prediction value of the transportation status of the items to be transported in the association analysis evaluation model and the operation decisions of the logistics transportation users for the damaged items in the transportation in the historical data, a logistics operation warning decision based on the items to be transported is generated and fed back to the logistics transportation users; Based on the operational decisions of logistics and transportation users regarding the items to be transported and the transportation destinations of the items to be transported, alternative routes for subsequent logistics and transportation are generated and fed back to logistics and transportation control personnel.

2. According to the method of data collaborative supervision based on the Internet of Things according to claim 1, it is characterized by: The construction of the transport status analysis model includes: obtaining transport vehicles corresponding to different transport stages in the logistics transport process, wherein the different transport stages are different transport path intervals, and each transport path interval is preset in a database form, The transport status data includes the transport time point, the vehicle bump amplitude value and the vehicle speed instantaneous change value; Obtain a line graph showing how the vehicle bump amplitude value in the transport state data corresponding to different time points in the same transport stage by the sensor set on the same transport vehicle changes with the transport time, and record the function corresponding to the obtained line graph as the first state analysis function; obtain a line graph showing how the instantaneous change value of the vehicle speed in the transport state data corresponding to different time points in the same transport stage by the sensor set on the same transport vehicle changes with the transport time, and record the function corresponding to the obtained line graph as the second state analysis function; A set of the first state analysis function and the second state analysis function in the same transport stage is used as a transport state analysis sub-model corresponding to the corresponding transport stage, wherein the transport state analysis sub-model includes transport state analysis sub-models corresponding to all executed transport stages in the logistics transport process; Before the transported items arrive at the destination, the transport status analysis model is updated in real time as the transport stage changes.

3. The data collaborative supervision method based on the Internet of Things according to claim 2 is characterized in that: The feature set of the items to be transported includes the type of items and the minimum value of the packaging thickness; The obtained association analysis evaluation model is a binding association pair of the transport item feature set and the transport status analysis model.

4. The data collaborative supervision method based on the Internet of Things according to claim 3 is characterized in that: The real-time acquisition of the transportation status risk prediction value of the items to be transported in the association analysis and evaluation model includes: Calculating the first state bias correlation value and the second state bias correlation value corresponding to the transportation state analysis model in the correlation analysis evaluation model, CV1 bias =Intergral{SA1 function ,CZ1}·[1+ε1·MD{SA1 function ,CZ1}], Among them, CV1 bias SA1 represents the first state bias correlation value corresponding to the transportation state analysis model in the correlation analysis evaluation model; function Indicates the first state analysis function in the transport state analysis submodel corresponding to the i-th executed transport stage in the transport state analysis model; CZ1 indicates the maximum value of the average function value corresponding to each first state analysis function in the transport state analysis model in each associated analysis evaluation model in which the feature set of the transported items bound in the historical data is the same as the feature set of the items to be transported and the transport result is normal; the transport result includes a normal state and an abnormal damage state; Intergral{SA1 function , CZ1} indicates SA1 function The function integral result in the interval where the corresponding function value is greater than CZ1; MD{SA1 function , CZ1} indicates SA1 function The difference between the maximum function value in and CZ1; ε1 represents the preset first conversion coefficient; CV2 bias =Intergral{SA2 function ,CZ2}·[1+ε2·MD{SA2 function ,CZ2}], Among them, CV2 bias SA2 represents the second state bias correlation value corresponding to the transportation state analysis model in the correlation analysis evaluation model; function Indicates the second state analysis function in the transport state analysis submodel corresponding to the i-th executed transport stage in the transport state analysis model; CZ2 indicates the maximum value of the average function value corresponding to each second state analysis function in the transport state analysis model in each associated analysis evaluation model in which the feature set of the transported items bound in the historical data is the same as the feature set of the items to be transported and the transport results are normal; Intergral{SA2 function , CZ2} represents SA2 function The function integral result in the interval where the corresponding function value is greater than CZ2; MD{SA2 function , CZ2} represents SA2 function The difference between the maximum function value in and CZ2; ε2 represents the preset second conversion coefficient; Obtain the abnormal transportation risk situation of each transport item feature set in the historical data based on the corresponding transportation state analysis model, calculate the ratio of the number of association analysis evaluation models whose corresponding first state bias association values ​​are greater than the first state reference value in each association analysis evaluation model in which the transport item feature set bound in the historical data is the same as the feature set of the items to be transported and the transportation results are abnormal, and obtain the first bias weight, which is recorded as r1; the first state reference value represents the maximum value of the first state bias association values ​​corresponding to each association analysis evaluation model in which the transport item feature set bound in the historical data is the same as the feature set of the items to be transported and the transportation results are normal; Calculate the ratio of the number of association analysis and evaluation models whose corresponding second state bias association values ​​are greater than the second state reference value in each association analysis and evaluation model in which the bound transported item feature set in the historical data is the same as the feature set of the item to be transported and the transportation result is abnormal, to the total number of corresponding association analysis and evaluation models, and obtain a second bias weight, recorded as r2; the second state reference value represents the maximum value of the second state bias association values ​​corresponding to each association analysis and evaluation model in which the bound transported item feature set in the historical data is the same as the feature set of the item to be transported and the transportation result is normal; Get the transportation status evaluation value corresponding to the transportation items with the same feature set as the items to be transported in the historical data, recorded as EV, EV = r1 CV1 bias +r2·CV2 bias ; The preset transport status evaluation value intervals of the transport status evaluation values ​​corresponding to the transport items with the same feature set as the transport items to be transported and abnormal transport results in the statistical historical data are the same, and the interval length of each preset transport status evaluation value interval is the same, which is recorded as L; construct the evaluation data pairs corresponding to each preset transport status evaluation value interval, and the first value of each evaluation data pair is the midpoint of the corresponding transport status evaluation value interval, and the second value is the quotient of the number of elements whose corresponding transport status evaluation values ​​belong to the corresponding transport status evaluation value interval divided by the product of L and the sum of the elements in the preset transport status evaluation value interval; According to the normal distribution function model, a function is fitted to each evaluation data pair, and the obtained fitting function is recorded as F function (x); The risk prediction value of the transportation status of the items to be transported in the association analysis evaluation model is recorded as RPV.

5. The method for data collaborative supervision based on the Internet of Things according to claim 4 is characterized in that: The generating of a logistics operation warning decision based on the items to be transported includes: When obtaining the transport items with the same feature set as the items to be transported in the historical data, the set of operation decisions of all logistics transportation users whose absolute value of the difference between the corresponding transportation status risk prediction value and the RPV is less than the preset transportation status risk prediction deviation is recorded as the logistics operation warning set; The logistics operation warning decision based on the items to be transported is composed of RPV and logistics operation warning set; The operational decisions include package return decisions, package reissue decisions, and package continued transportation decisions.

6. The method for collaborative data supervision based on the Internet of Things according to claim 5 is characterized in that: The generating of the route alternative plan for subsequent logistics transportation includes: Obtain the operation decision of the logistics transportation user for the items to be transported. When the operation decision obtained is a decision to continue transporting the package, obtain the transportation destination of the items to be transported and the current decision execution location of the items to be transported. If the current location of the item to be transported is on the transport vehicle, the current decision execution location of the item to be transported is the next transfer station; if the current location of the item to be transported is a transfer station, the current decision execution location of the item to be transported is the corresponding transfer station; Obtain the corresponding routes from the current decision execution location of the item to be transported to the transportation destination of the item to be transported in the database, The transport state analysis sub-models corresponding to each transport vehicle that passes through the kth pass route within the most recent preset time period based on the current time are added to the association analysis evaluation reference model, and the corresponding transport state risk prediction values ​​after the transport state analysis sub-models are added are calculated respectively; k is greater than or equal to 1 and less than or equal to the total number of corresponding pass routes in the database from the current decision execution place of the items to be transported to the transportation destination of the items to be transported; The association analysis and evaluation reference model represents an association analysis and evaluation model composed of the transportation status data of the items to be transported from the starting transportation point to the current location of the items to be transported; According to the average value of each transportation status risk prediction value corresponding to the same route, each route is sorted in ascending order to generate route alternatives for subsequent logistics transportation.

7. A data collaborative supervision system based on the Internet of Things, characterized in that: include: State analysis model building module, association evaluation model building module, data collaborative analysis module, user decision warning feedback module and adaptive decision feedback module, The state analysis model building module collects the transportation state data in the logistics transportation process in real time through sensors, and summarizes the collection results of each sensor in the logistics transportation process through the Internet of Things to build a transportation state analysis model; The association evaluation model construction module extracts features of items to be transported by logistics transportation users to obtain a feature set of items to be transported, and binds the obtained feature set of items to be transported with a corresponding transportation status analysis model to obtain an association analysis evaluation model; The data collaborative analysis module obtains the abnormal transportation risk situation of each transport item feature set in the historical data based on the corresponding transportation status analysis model, and obtains the transportation status risk prediction value of the to-be-transported item in the association analysis evaluation model in real time; The user decision warning feedback module generates a logistics operation warning decision based on the items to be transported based on the analysis results of the transportation status risk prediction value of the items to be transported in the association analysis evaluation model and the operation decision of the logistics transportation user for the damaged items to be transported in the historical data, and feeds back to the logistics transportation user; The adaptive decision feedback module combines the operation decision of the logistics transportation user on the items to be transported and the transportation destination of the items to be transported, generates route alternatives for subsequent logistics transportation, and feeds back to the logistics transportation control personnel.

8. The data collaborative supervision system based on the Internet of Things according to claim 7 is characterized in that: The association evaluation model construction module includes a feature set construction unit and an analysis and evaluation unit. The feature set construction unit extracts features of items to be transported by the logistics transportation user to obtain a feature set of items to be transported; The analysis and evaluation unit binds the obtained feature set of the items to be transported with the corresponding transport status analysis model to obtain a correlation analysis and evaluation model.

9. The data collaborative supervision system based on the Internet of Things according to claim 7 is characterized in that: The user decision warning feedback module includes a historical decision collection unit and an operation warning decision generation unit. The historical decision collection unit obtains the analysis results of the transportation status risk prediction value of the items to be transported in the association analysis evaluation model, and the operation decisions of the logistics transportation users for the damaged items to be transported in the historical data; The operation warning decision generating unit generates a logistics operation warning decision based on the items to be transported according to the collection results of the historical decision collecting unit, and feeds back to the logistics transportation user.

Images