Logistics electronic lock distributed autonomous decision-making system and method

Abstract

The invention relates to the technical field of logistics, and particularly discloses a logistics electronic lock distributed autonomous decision-making system and method, and the method comprises the following steps: obtaining local state parameter data of an electronic lock node; processing the state parameter data to obtain a multi-dimensional risk assessment sub-item, and calculating an obtained comprehensive risk score based on the risk assessment sub-item; comparing the comprehensive risk score with a risk threshold to obtain an abnormal signal, and sending the abnormal signal to an adjacent node; on the basis of the abnormal signal, score data of a plurality of adjacent nodes are obtained, a neighborhood average score is calculated, a collaborative risk signal is obtained, collaborative consensus adjustment is carried out, and an alarm mechanism of linkage lock control and distributed calculation is adopted, so that on one hand, the situation of misjudgment and false alarm of independent electronic lock nodes is avoided; on the other hand, linkage judgment can be conducted on the electronic lock nodes in the neighborhood, the recognition decision-making capacity of the distributed electronic lock is improved, and meanwhile the recognition and judgment accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the field of logistics technology, and in particular to a distributed autonomous decision-making system and method for logistics electronic locks. Background Art

[0002] With the rapid development of the logistics industry, the safety of goods during transportation is receiving increasing attention. To prevent loss, tampering, and theft during transportation, electronic locks are gradually replacing traditional mechanical locks and becoming a key means of ensuring logistics transportation safety. Existing electronic lock systems in logistics primarily rely on centralized control and scheduled information uploads, with remote servers centrally determining the lock's open status, abnormal vibration, or abnormal displacement.

[0003] However, in practical applications, traditional electronic lock systems face the following significant problems:

[0004] When a lock is abnormal, it is necessary to wait for communication with the central platform for confirmation, which affects the efficiency of emergency response;

[0005] Single-point judgment mechanism, high misjudgment rate: Some electronic locks may be misjudged as abnormal due to non-abnormal factors such as GPS drift, vibration false touch, short-term signal loss, etc.

[0006] Therefore, there is an urgent need to provide a logistics electronic lock system and method with distributed autonomous decision-making capabilities, so that each electronic lock node can combine local perception information, neighboring node judgment results and comprehensive scoring mechanism to achieve high-reliability judgment and response to abnormal behavior, thereby greatly improving the safety, real-time and intelligence level of logistics transportation. Summary of the Invention

[0007] The purpose of the present invention is to provide a distributed autonomous decision-making system and method for logistics electronic locks to solve the problems in the above background.

[0008] The purpose of the present invention can be achieved through the following technical solutions:

[0009] A distributed autonomous decision-making method for logistics electronic locks includes the following steps:

[0010] Step 1: Obtain local status parameter data of the electronic lock node;

[0011] Step 2: Process the state parameter data to obtain multidimensional risk score sub-items, and calculate the comprehensive risk score based on the risk score sub-items;

[0012] Step 3: Compare the comprehensive risk score with the risk threshold to obtain an abnormal signal, and send the abnormal signal to the adjacent node;

[0013] Step 4: Based on the abnormal signal, obtain the score data of several nearby nodes, calculate the average score of the neighborhood, obtain the collaborative risk signal, and then perform collaborative consensus adjustment.

[0014] As a further solution of the present invention: the state parameter data includes position offset data, vibration data, state data and abnormality data;

[0015] The position offset data is the maximum offset distance d of the GPS position of the electronic lock during the monitoring period;

[0016] The vibration data is the current acceleration value a periodically read by the vibration sensor on the electronic lock;

[0017] Status data includes electronic lock locked status, normal authorized opening status, unauthorized opening status and detection of destructive unlocking status;

[0018] Abnormal data refers to the time period during which the abnormality lasts and is recorded by the system when the electronic lock has abnormal indicators and is monitored.

[0019] As a further solution of the present invention: the multidimensional risk score sub-items include an offset risk score, a vibration risk score, a state risk score and an abnormality duration score.

[0020] As a further solution of the present invention: the state parameter data is processed to obtain multidimensional risk score sub-items, including:

[0021] S1: Normalize the position offset data, specifically:

[0022] Get the maximum allowable offset displacement value D of the electronic lock in logistics transportation max ;

[0023] Then pass Calculate the bias risk score R d , the range value is [0,1];

[0024] S2: Normalize the vibration data, including:

[0025] Get the maximum acceleration value A allowed during the use of the electronic lock max ;

[0026] Then pass Calculate the vibration risk score R a , the range value is [0,1];

[0027] S3: Automatically assign a score to the electronic lock status based on the status data to obtain the status risk score R x Specific:

[0028] S4: The steps for processing abnormal data include:

[0029] Get the duration of the current abnormality, recorded as Δt;

[0030] Then obtain the maximum duration of abnormality residual value set by the system, recorded as T max ;

[0031] pass The abnormal duration score is calculated and ranges from [0,1].

[0032] As a further solution of the present invention: based on the multidimensional risk scoring sub-items, a comprehensive score value Rto is obtained by calculation, with a range of [0,1];

[0033] Specifically: Rto=α×R d +β×R a +γ×R x +θ×R t

[0034] Among them, α, β, γ, and θ are weighted coefficients of the multidimensional risk scoring sub-items, and α+β+γ+θ=1.

[0035] As a further solution of the present invention: the risk threshold includes a warning threshold RY and an abnormality threshold RC.

[0036] As a further solution of the present invention: the comprehensive risk score Rto is compared with the risk threshold:

[0037] If Rto ≥ RY, a warning signal is generated;

[0038] If RY>Rto≥RC, an abnormal signal is generated;

[0039] If RC>Rto, a normal signal is generated.

[0040] As a further solution of the present invention: in step 4, the calculation process of the neighborhood average score is as follows;

[0041] Obtain the electronic lock node under the abnormal signal, denoted as i; simultaneously obtain the set of nodes adjacent to the electronic lock node under the abnormal signal, denoted as j, where j is 1, 2, 3, etc.;

[0042] Calculate the comprehensive risk score Rto of the electronic lock node j in the adjacent node set j ;

[0043] Then, by Calculate the neighborhood average score Ravg i .

[0044] As a further solution of the present invention: in the step 4:

[0045] The neighborhood average score Ravg i Compare with the consensus risk threshold RT;

[0046] If Ravg i ≥RT, a collaborative risk signal is generated;

[0047] If RT>Ravg i , an abnormality detection signal is generated.

[0048] As a further solution of the present invention: a distributed autonomous decision-making system for logistics electronic locks, comprising:

[0049] Data acquisition module: obtains local status parameter data of the electronic lock node, including position offset data, vibration data, status data and abnormal data;

[0050] Node scoring module: It processes the state parameter data to obtain multi-dimensional risk scoring sub-items and calculates the comprehensive risk score based on the risk scoring sub-items;

[0051] Abnormal judgment module: compares the comprehensive risk score with the risk threshold, obtains abnormal signals, and sends the abnormal signals to nearby nodes;

[0052] Collaborative processing module: Based on abnormal signals, it obtains the scoring data of several nearby nodes, makes collaborative risk judgments, and performs collaborative consensus adjustments when collaborative risk signals are obtained.

[0053] Beneficial effects of the present invention:

[0054] Through the distributed deployment of edge electronic locks, based on the GPS, vibration and other sensors installed inside the electronic locks, and based on the electronic lock status, independent data is collected for each electronic lock node, and then a risk score is determined. The electronic lock nodes are then shared through short-distance information transmission to monitor the status of the electronic locks. This enables each electronic lock node to have the ability to make decisions, and when risks arise, early warnings can be issued quickly and effectively.

[0055] At the same time, the alarm mechanism of linked lock control and distributed computing is adopted. On the one hand, it can avoid the misjudgment and false alarm of independent electronic lock nodes. On the other hand, it can make linked judgments on the electronic lock nodes in its neighborhood, improve the recognition and decision-making capabilities of distributed electronic locks, and at the same time improve the accuracy of recognition and judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The present invention will be further described below with reference to the accompanying drawings.

[0057] Figure 1 It is a schematic flow chart of the method of the present invention;

[0058] Figure 2 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0059] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making any creative efforts shall fall within the scope of protection of the present invention.

[0060] Example 1

[0061] See also Figure 1 As shown, the present invention is a distributed autonomous decision-making method for logistics electronic locks, comprising the following steps:

[0062] Step 1: Obtain local status parameter data of the electronic lock node, including position offset data, vibration data, status data, and abnormal data;

[0063] The position offset data is the maximum offset distance d of the GPS position of the electronic lock during the monitoring period;

[0064] Vibration data is the current acceleration value a periodically read by the vibration sensor on the electronic lock. By measuring the vibration acceleration, it can be used to determine whether the electronic lock has been hit, shaken violently, or disassembled.

[0065] Status data includes the electronic lock's locked state, normal authorized opening state, unauthorized opening state, and unlocked state after detection of destructive conditions. Classifying and quantifying the electronic lock's status can facilitate subsequent overall risk assessment.

[0066] Abnormal data refers to the duration of abnormality recorded by the system when the electronic lock has abnormal indicators and is monitored. The longer the abnormal period, the higher the risk.

[0067] Step 2: Process the state parameter data to obtain multidimensional risk score sub-items, and calculate the comprehensive risk score based on the risk score sub-items;

[0068] Among them, the multidimensional risk score sub-items include offset risk score, vibration risk score, state risk score and abnormality duration score;

[0069] The state parameter data is processed to obtain multi-dimensional risk score sub-items, including:

[0070] S1: Normalize the position offset data, specifically:

[0071] Get the maximum allowable offset displacement value D of the electronic lock in logistics transportationmax ;

[0072] Then pass Calculate the bias risk score R d , the range value is [0,1];

[0073] S2: Normalize the vibration data, including:

[0074] Get the maximum acceleration value A allowed during the use of the electronic lock max ;

[0075] Then pass Calculate the vibration risk score R a , the range value is [0,1];

[0076] S3: Automatically assign a score to the electronic lock status based on the status data to obtain the status risk score R x Directly assigning a score to the electronic lock status can facilitate subsequent overall risk assessment. The scoring mechanism categorizes and quantifies the electronic lock status, guiding the system to perceive abnormal unlocking behavior. A score of 1 indicates a high risk.

[0077] Specifically:

[0078] S4: The steps for processing abnormal data include:

[0079] Get the duration of the current abnormality, recorded as Δt;

[0080] Then obtain the maximum duration of abnormality residual value set by the system, recorded as T max ;

[0081] pass Calculate the abnormal duration score, ranging from [0,1];

[0082] Based on the multidimensional risk scoring sub-items, the comprehensive score value Rto is obtained by calculation, ranging from [0,1];

[0083] Specifically: Rto=α×R d +β×R a +γ×R x +θ×R t

[0084] Among them, α, β, γ, θ are the weighting coefficients of the multidimensional risk score sub-items, and α+β+

[0085] γ+θ=1;

[0086] Step 3: Compare the comprehensive risk score with the risk threshold to obtain an abnormal signal, and send the abnormal signal to the adjacent node;

[0087] Among them, the risk threshold includes the warning threshold RY and the abnormal threshold RC;

[0088] Specifically: Compare the comprehensive risk score Rto with the risk threshold:

[0089] If Rto≥RY, an early warning signal is generated. At this time, an early warning prompt is issued directly, indicating that the current electronic lock node has a greater risk and needs to be checked. If the electronic lock is in the open state, it can be automatically locked directly.

[0090] If RY>Rto≥RC, an abnormal signal is generated. At this time, it means that there is an abnormality in the electronic lock, but the abnormality risk is low and there may be a misjudgment. At this time, the electronic lock node is subjected to collaborative risk detection, which can reduce the misjudgment and improve the system fault tolerance.

[0091] If RC>Rto, a normal signal is generated; this indicates that the electronic lock node is in a normal state, and the risk scores of all data are in a normal state, and no operation is required;

[0092] Step 4: Based on the abnormal signal, obtain the score data of several nearby nodes, calculate the average score of the neighborhood, obtain the collaborative risk signal, and then perform collaborative consensus adjustment.

[0093] Specifically, the calculation process of the neighborhood average score is as follows;

[0094] Obtain the electronic lock node under the abnormal signal, denoted as i; simultaneously obtain the set of nodes adjacent to the electronic lock node under the abnormal signal, denoted as j, where j is 1, 2, 3, etc.;

[0095] Calculate the comprehensive risk score Rto of the electronic lock node j in the adjacent node set j ;

[0096] Then, by Calculate the neighborhood average score Ravg i ;

[0097] The neighborhood average score Ravg i Compare with the consensus risk threshold RT;

[0098] If Ravg i ≥RT, a collaborative risk signal is generated. In this case, it means that after an abnormal signal appears at electronic lock node i, the adjacent average score of the further judgment is higher, that is, the adjacent electronic lock node also has an abnormality. In this case, the probability of misjudgment of the electronic lock node can be ignored, and an early warning is issued directly. In addition, an early warning reminder is also issued to its adjacent electronic lock nodes.

[0099] If RT>Ravgi , an abnormal detection signal is generated; indicating that the electronic lock of the abnormal signal, its adjacent electronic locks are in a stable state, and the electronic lock node can be continuously monitored;

[0100] Through the distributed deployment of edge electronic locks, based on the GPS, vibration and other sensors installed inside the electronic locks, and based on the electronic lock status, independent data is collected for each electronic lock node, and then a risk score is determined. The electronic lock nodes are then shared through short-distance information transmission to monitor the status of the electronic locks. This enables each electronic lock node to have the ability to make decisions, and when risks arise, early warnings can be issued quickly and effectively.

[0101] At the same time, the alarm mechanism of linked lock control and distributed computing is adopted. On the one hand, it can avoid the misjudgment and false alarm of independent electronic lock nodes. On the other hand, it can make linked judgments on the electronic lock nodes in its neighborhood, improve the recognition and decision-making capabilities of distributed electronic locks, and at the same time improve the accuracy of recognition and judgment.

[0102] Example 2

[0103] Reference Figure 2 As shown, based on the above embodiment, this embodiment provides a distributed autonomous decision-making system for logistics electronic locks, including:

[0104] Data acquisition module: obtains local status parameter data of the electronic lock node, including position offset data, vibration data, status data and abnormal data;

[0105] Node scoring module: It processes the state parameter data to obtain multi-dimensional risk scoring sub-items and calculates the comprehensive risk score based on the risk scoring sub-items;

[0106] Abnormal judgment module: compares the comprehensive risk score with the risk threshold, obtains abnormal signals, and sends the abnormal signals to nearby nodes;

[0107] Collaborative processing module: Based on abnormal signals, it obtains the scoring data of several nearby nodes, makes collaborative risk judgments, and performs collaborative consensus adjustments when collaborative risk signals are obtained.

[0108] Through the distributed deployment of edge electronic locks, based on the GPS, vibration and other sensors installed inside the electronic locks, and based on the electronic lock status, independent data is collected for each electronic lock node, and then a risk score is determined. The electronic lock nodes are then shared through short-distance information transmission to monitor the status of the electronic locks. This enables each electronic lock node to have the ability to make decisions, and when risks arise, early warnings can be issued quickly and effectively.

[0109] At the same time, the alarm mechanism of linked lock control and distributed computing is adopted. On the one hand, it can avoid the misjudgment and false alarm of independent electronic lock nodes. On the other hand, it can make linked judgments on the electronic lock nodes in its neighborhood, improve the recognition and decision-making capabilities of distributed electronic locks, and at the same time improve the accuracy of recognition and judgment.

[0110] The above is a detailed description of an embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A distributed autonomous decision-making method for logistics electronic locks, characterized in that: The following steps are involved: Step 1: Obtain local status parameter data of the electronic lock node; Step 2: Process the state parameter data to obtain multidimensional risk score sub-items, and calculate the comprehensive risk score based on the risk score sub-items; Step 3: Compare the comprehensive risk score with the risk threshold to obtain an abnormal signal, and send the abnormal signal to the adjacent node; Step 4: Based on the abnormal signal, obtain the score data of several nearby nodes, calculate the average score of the neighborhood, obtain the collaborative risk signal, and then perform collaborative consensus adjustment.

2. A distributed autonomous decision-making method for logistics electronic locks according to claim 1, characterized in that: The state parameter data includes position offset data, vibration data, state data and abnormal data; The position offset data is the maximum offset distance d of the GPS position of the electronic lock during the monitoring period; The vibration data is the current acceleration value a periodically read by the vibration sensor on the electronic lock; Status data includes electronic lock locked status, normal authorized opening status, unauthorized opening status and detection of destructive unlocking status; Abnormal data refers to the time period during which the abnormality lasts and is recorded by the system when the electronic lock has abnormal indicators and is monitored.

3. A distributed autonomous decision-making method for logistics electronic locks according to claim 1, characterized in that: The multidimensional risk score sub-items include a deviation risk score, a vibration risk score, a state risk score, and an abnormality duration score.

4. A distributed autonomous decision-making method for logistics electronic locks according to claim 3, characterized in that: The state parameter data is processed to obtain multi-dimensional risk score sub-items, including: S1: Normalize the position offset data, specifically: Get the maximum allowable offset displacement value D of the electronic lock in logistics transportation max ; Then pass Calculate the bias risk score R d , the range value is [0,1]; S2: Normalize the vibration data, including: Get the maximum acceleration value A allowed during the use of the electronic lock max ; Then pass Calculate the vibration risk score R a , the range value is [0,1]; S3: Automatically assign a score to the electronic lock status based on the status data to obtain the status risk score R x Specific: S4: The steps for processing abnormal data include: Get the duration of the current abnormality, recorded as Δt; Then obtain the maximum duration of abnormality residual value set by the system, recorded as T max ; pass The abnormal duration score is calculated and ranges from [0,1].

5. A distributed autonomous decision-making method for logistics electronic locks according to claim 1, characterized in that: Based on the multidimensional risk scoring sub-items, the comprehensive score value Rto is obtained by calculation, ranging from [0,1]; Specifically: Rto=α×R d +β×R a +γ×R x +θ×R t Among them, α, β, γ, and θ are weighted coefficients of the multidimensional risk scoring sub-items, and α+β+γ+θ=1.

6. A distributed autonomous decision-making method for logistics electronic locks according to claim 1, characterized in that: The risk threshold includes a warning threshold RY and an abnormality threshold RC.

7. A distributed autonomous decision-making method for logistics electronic locks according to claim 1, characterized in that: Compare the composite risk score Rto with the risk threshold: If Rto ≥ RY, a warning signal is generated; If RY>Rto≥RC, an abnormal signal is generated; If RC>Rto, a normal signal is generated.

8. A distributed autonomous decision-making method for logistics electronic locks according to claim 1, characterized in that: In step 4, the calculation process of the neighborhood average score is as follows: Obtain the electronic lock node under the abnormal signal, denoted as i; simultaneously obtain the set of nodes adjacent to the electronic lock node under the abnormal signal, denoted as j, where j is 1, 2, 3, etc.; Calculate the comprehensive risk score Rto of the electronic lock node j in the adjacent node set j ; Then, by Calculate the neighborhood average score Ravg i .

9. A distributed autonomous decision-making method for logistics electronic locks according to claim 8, characterized in that: In the step 4: The neighborhood average score Ravg i Compare with the consensus risk threshold RT; If Ravg i ≥RT, a collaborative risk signal is generated; If RT>Ravg i , an abnormality detection signal is generated.

10. A distributed autonomous decision-making system for logistics electronic locks, characterized by: The system is used to execute the distributed autonomous decision-making method for logistics electronic locks according to any one of claims 1 to 9, comprising: Data acquisition module: obtains local status parameter data of the electronic lock node, including position offset data, vibration data, status data and abnormal data; Node scoring module: It processes the state parameter data to obtain multi-dimensional risk scoring sub-items and calculates the comprehensive risk score based on the risk scoring sub-items; Abnormal judgment module: compares the comprehensive risk score with the risk threshold, obtains abnormal signals, and sends the abnormal signals to nearby nodes; Collaborative processing module: Based on abnormal signals, it obtains the scoring data of several nearby nodes, makes collaborative risk judgments, and performs collaborative consensus adjustments when collaborative risk signals are obtained.

Images