Block chain-based bulk commodity logistics tracking and monitoring method and system

Abstract

The invention discloses a bulk commodity logistics tracking and monitoring method and system based on a block chain, and relates to the field of commodity logistics monitoring. The method comprises the following steps: acquiring logistics node information recorded on a block chain, extracting influence factor information, including commodity feature information, logistics feature information and objective feature information, of a circulation period Ti of a current logistics node i, and determining an influence coefficient of each influence factor on the circulation period Ti; constructing a prediction model of the circulation period Ti of the current logistics node i according to the obtained influence coefficient and influence factor information, calculating and obtaining the circulation period Ti of the current logistics node i through the prediction model, and analyzing the multi-source data influencing the circulation transition period of the logistics node in the cross-border e-commerce logistics process. And the predicted circulation period of the circulation link in the logistics process is obtained, so that a logistics blind area caused by difficulty in tracking the cross-border commodity logistics information data is effectively prevented, and effective control, tracking and monitoring of the logistics and commodity flow information of the cross-border commodities are realized.

Description

Technical Field

[0001] The present invention relates to the field of commodity logistics monitoring, and in particular to a method and system for tracking and monitoring bulk commodity logistics based on blockchain. Background Art

[0002] In traditional logistics and distribution, commodity logistics information tracking relies on intermediaries or third-party platforms, and logistics data needs to be forwarded and processed multiple times, resulting in increased inaccuracy of information and decreased timeliness of tracking. Due to the isolated storage and non-uniform standards of logistics information, information sharing between different participants is difficult, and there is a lack of overall visibility and transparency. Traditional logistics tracking is also vulnerable to the risk of data tampering and illegal access, and there are problems with information security and trustworthiness. With the continuous development of blockchain technology, the use of blockchain technology can provide more advanced logistics tracking visibility and transparency. The decentralized nature of blockchain eliminates the reliance on a single intermediary agency and enables direct communication and data sharing between participants in all links. Blockchain can ensure the timeliness and accuracy of data by recording logistics data in real time. Participants can update and view logistics data in real time through the blockchain network, realize real-time monitoring and traceability in the logistics process, and reduce information lags and errors.

[0003] For cross-border e-commerce logistics platforms, although the traceability characteristics of blockchain technology can record the date, location, mode of transportation and other data information of each link from warehouse out, transportation, warehousing to terminal distribution in a complete chronological order, cross-border goods are limited by various influencing factors such as commodity type, weather reasons, and differences in departmental handover procedures during the long-term transportation process. During the transition period of adjacent logistics nodes, logistics blind spots are prone to occur, resulting in reduced timeliness in obtaining real-time information on goods. To this end, we propose a method and system for tracking and monitoring bulk commodity logistics based on blockchain. Summary of the invention

[0004] The main purpose of the present invention is to provide a method and system for tracking and monitoring bulk commodity logistics based on blockchain, which can effectively solve the problems in the background technology.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is:

[0006] The blockchain-based commodity logistics tracking and monitoring method includes:

[0007] Obtain the logistics node information recorded on the blockchain and extract the circulation cycle T of the current logistics node i i The influencing factor information is used to determine the influence of each influencing factor on the circulation period T iThe influencing factor information includes commodity feature information, logistics feature information, and objective feature information; wherein the commodity feature information includes at least one of commodity category information, commodity quantity information, and commodity quality grade information; the logistics feature information includes at least one of transportation mode information, transportation capacity information, and transportation efficiency information; the objective feature information includes at least one of environmental delay time, average circulation time, and average review cycle;

[0008] According to the acquired influence coefficient and influencing factor information, the circulation cycle T of the current logistics node i is constructed. i The prediction model is used to calculate the turnover period T of the current logistics node i. i ;

[0009] The expression of the prediction model is:

[0010]

[0011] In the formula, β 1u Expressed as the influence coefficient of the u-th commodity feature; Represented as the characteristic information of the u-th commodity at logistics node i; β 2v It is expressed as the influence coefficient of the vth logistics characteristic; Represented as the vth item of logistics characteristic information of logistics node i; β 3w Expressed as the influence coefficient of the wth environmental characteristic; It is represented as the w-th environmental characteristic information of logistics node i; ε is a constant coefficient.

[0012] The influence coefficient acquisition process includes the following steps:

[0013] Get the circulation cycle T of the current logistics node i in the logistics node information recorded on the blockchain i and historical data of information on influencing factors;

[0014] To obtain the turnover period T i The historical data constructs the data sequence E = {T i}, construct a data sequence F = {F1, F2, ..., F n}, where F n It is represented as the data set of the nth influencing factor; n is the number of influencing factors;

[0015] Calculate the correlation coefficient ξ between each data point in data sequence F and data sequence E jk ,ξ jk It is expressed as the correlation coefficient between the kth data point of the jth influencing factor and the data sequence E, j∈n, according to the calculated correlation coefficient ξ jkDetermine the correlation R between the jth influencing factor and the circulation cycle j , the calculation formula is: Among them, Q is the total amount of data;

[0016] According to the calculated correlation R j Determine the jth influencing factor for the turnover period T i The influence coefficient The calculation formula is:

[0017] Correlation coefficient ξ jk The calculation formula is:

[0018]

[0019] Where, Δmin=min[min(|T ik '-F jk |)], where min[min(|T ik '-F jk |)] is to take |T ik '-F jk |Calculate the minimum value of the result, and then take the minimum value of all calculated minimum values; Δmax=max[max(|T ik '-F jk |)], where max[max(|T ik '-F jk |)] is to take |T ik '-F jk |Calculate the maximum value of the result, and then take the maximum value of all calculated maximum values; T ik ' is the standardized value of the kth circulation cycle data point in the data sequence E, and T ik is the kth circulation cycle data value in the data sequence E, is the mean value of the turnover cycle data in the data sequence E, F jk is the normalized value of the kth data point of the jth influencing factor, and Among them, f jk is the kth data value of the jth influencing factor, is the data mean of the jth influencing factor, ρ is the resolution coefficient, and its value range is (0,1].

[0020] The blockchain-based commodity logistics tracking and monitoring system includes a logistics node information acquisition module, an influence coefficient acquisition module, and a prediction model construction module;

[0021] The logistics node information acquisition module is used to obtain the logistics node information recorded on the blockchain and extract the circulation period T of the current logistics node i. i and influencing factor information, wherein the influencing factor information includes commodity feature information, logistics feature information, and objective feature information;

[0022] The influence coefficient acquisition module is used to obtain the current logistics node i according to the circulation period T i The influencing factor information is used to determine the influence of each influencing factor on the circulation period T i The influence coefficient of

[0023] The prediction model building module is used to build the circulation cycle T of the current logistics node i according to the acquired influence coefficient and influence factor information. i The prediction model is used to calculate the turnover period T of the current logistics node i. i ;

[0024] The system further includes a memory, a processor, and an electronic program stored in the memory and capable of running on the processor.

[0025] The present invention has the following beneficial effects:

[0026] Compared with the existing technology, by obtaining the logistics node information recorded on the blockchain, the circulation cycle T of the current logistics node i is extracted. i Including commodity feature information, logistics feature information, and influencing factor information of objective feature information, and determining the influence of each of the influencing factors on the circulation period T i The influence coefficient of the current logistics node i is constructed based on the obtained influence coefficient and influencing factor information. i The prediction model is used to calculate the turnover period T of the current logistics node i. i , analyze the multi-source data that affects the transition period of logistics nodes in the cross-border e-commerce logistics process, and obtain the predicted circulation cycle of the turnover links in the logistics process, so as to effectively prevent the occurrence of logistics blind spots caused by the difficulty in tracking cross-border commodity logistics information data, and realize the effective control and tracking monitoring of cross-border commodity logistics and commodity flow information. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 This is a flow chart of the method for tracking and monitoring bulk commodity logistics based on blockchain of the present invention;

[0028] Figure 2 This is a structural block diagram of the bulk commodity logistics tracking and monitoring system based on blockchain of the present invention. DETAILED DESCRIPTION

[0029] The present invention will be further described below in conjunction with specific implementation methods, wherein the accompanying drawings are only used for exemplary descriptions and represent only schematic diagrams rather than actual drawings, and should not be understood as limiting the present invention. In order to better illustrate the specific implementation methods of the present invention, some parts of the accompanying drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product.

[0030] The specific implementation process of the technical solution of the present invention includes the following steps:

[0031] Step 1: Obtain the logistics node information recorded on the blockchain;

[0032] Generally speaking, the logistics process of cross-border e-commerce imports includes foreign outbound customs clearance, international logistics, inbound customs clearance, domestic logistics, etc. Each step of the process can be further subdivided into distribution, warehousing, customs declaration, customs clearance, delivery and other links. These turnover links may make the cross-border e-commerce logistics span longer and the logistics node data more. Problems or delays in any link or step will affect the follow-up. From the above-mentioned cross-border e-commerce logistics process, the amount of information collected by different cross-border e-commerce participants and various links is large and complicated, involving consumers, sellers, cross-border e-commerce platforms, logistics parties, payment intermediaries, tax departments, etc., and these cross-border e-commerce participants are often not in the same region, making information data collection, tracking and auditing difficult. By applying blockchain technology to cross-border e-commerce supervision, cross-border enterprises, consumers, payment institutions, customs, taxation and other participants are effectively connected as chain members; in the blockchain system, all parties store the product information on the chain, and the input information is open and transparent. Members can share data information and cross-verify each other to ensure that the information is equal to the transaction facts. Applying blockchain technology to the cross-border e-commerce logistics platform can make the logistics information of the goods correspond to the actual flow in real time, and realize the traceability of the entire logistics process. According to the traceability characteristics of blockchain technology, the date, location, mode of transportation and other data information of each link of each commodity from shipment, transportation, warehousing to terminal delivery are recorded in the blockchain in a complete chronological order. The information of each link is seamlessly connected and interconnected, ensuring that cross-border commodities are tracked during long-term transportation. Any party in the logistics process can obtain the logistics node information recorded on the blockchain through the legal identity that has been authenticated on the chain.

[0033] Step 2: Extract the circulation period T of the current logistics node i i Information on influencing factors;

[0034] The influencing factor information includes commodity feature information, logistics feature information, and objective feature information; the commodity feature information includes at least one of commodity category information, commodity quantity information, and commodity quality grade information; the logistics feature information includes at least one of transportation mode information, transportation capacity information, and transportation efficiency information; the objective feature information includes at least one of environmental delay time, average circulation time, and average review cycle;

[0035] It should be noted that for qualitative data, such as commodity category information data, after extraction, subjective assignment method can be used for quantitative processing, and commodity category information data can be scored by formulating assignment standards. In addition, at different logistics nodes, different assignment standards are formulated. For example, for loading nodes, the commodity category can be processed based on the loading difficulty as the assignment standard. The easier the commodity category is to load, the smaller the impact on the node's circulation cycle, and the lower the quantitative score after assignment. On the contrary, the more difficult the commodity category is to load, the greater the impact on the node's circulation cycle, and the higher the quantitative score after assignment. For warehousing nodes, the commodity category can be processed based on the storage difficulty as the assignment standard. The easier the commodity category is to store, the smaller the impact on the node's circulation cycle, and the lower the quantitative score after assignment. On the contrary, the more difficult the commodity category is to store, the greater the impact on the node's circulation cycle, and the higher the quantitative score after assignment.

[0036] Step 3: Determine the impact of various factors on the turnover period T i The influence coefficient of

[0037] The specific process is:

[0038] Step 31: Obtain the circulation period T of the current logistics node i in the logistics node information recorded on the blockchain i and historical data of information on influencing factors;

[0039] Step 32: To obtain the circulation period T i The historical data constructs the data sequence E = {T i}, construct a data sequence F = {F1, F2, ..., F n}, where F n It is represented as the data set of the nth influencing factor; n is the number of influencing factors;

[0040] Step 33: Calculate the correlation coefficient ξ between each data point in data sequence F and data sequence E jk ,ξ jk It is expressed as the correlation coefficient between the kth data point of the jth influencing factor and the data sequence E, j∈n, according to the calculated correlation coefficient ξ jk Determine the correlation R between the jth influencing factor and the circulation cycle j , the calculation formula is: Among them, Q is the total amount of data;

[0041] Step 34: According to the calculated correlation R j Determine the jth influencing factor for the turnover period T i The influence coefficient The calculation formula is:

[0042] Among them, the correlation coefficient ξ jk The calculation formula is:

[0043]

[0044] Where, Δmin=min[min(|T ik '-F jk |)], where min[min(|T ik '-F jk |)] is to take |T ik '-F jk |Calculate the minimum value of the result, and then take the minimum value of all calculated minimum values; Δmax=max[max(|T ik '-F jk |)], where max[max(|T ik '-F jk |)] is to take |T ik '-F jk |Calculate the maximum value of the result, and then take the maximum value of all calculated maximum values; T ik ' is the standardized value of the kth circulation cycle data point in the data sequence E, and T ik is the kth circulation cycle data value in the data sequence E, is the mean value of the turnover cycle data in the data sequence E, F jk is the normalized value of the kth data point of the jth influencing factor, and Among them, f jk is the kth data value of the jth influencing factor, is the data mean of the jth influencing factor, ρ is the resolution coefficient, and its value range is (0,1].

[0045] Step 4: Construct the circulation cycle T of the current logistics node i based on the obtained influence coefficient and influencing factor information i The prediction model is used to calculate the turnover period T of the current logistics node i. i ;

[0046] The expression of the prediction model is:

[0047]

[0048] In the formula, β 1u Expressed as the influence coefficient of the u-th commodity feature; Represented as the characteristic information of the u-th commodity at logistics node i; β 2v It is expressed as the influence coefficient of the vth logistics characteristic; Represented as the vth item of logistics characteristic information of logistics node i; β 3w Expressed as the influence coefficient of the wth environmental characteristic; It is represented as the w-th environmental characteristic information of logistics node i; ε is a constant coefficient.

[0049] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for tracking and monitoring bulk commodity logistics based on blockchain, characterized in that: include: Obtain the logistics node information recorded on the blockchain and extract the circulation cycle T of the current logistics node i i The influencing factor information is used to determine the influence of each influencing factor on the circulation period T i The influencing factor information includes commodity feature information, logistics feature information, and objective feature information; According to the acquired influence coefficient and influencing factor information, the circulation cycle T of the current logistics node i is constructed. i The prediction model is used to calculate the turnover period T of the current logistics node i. i ; The expression of the prediction model is: In the formula, β 1u Expressed as the influence coefficient of the u-th commodity feature; Represented as the characteristic information of the u-th item of goods at logistics node i; β 2v It is expressed as the influence coefficient of the vth logistics characteristic; It is represented as the vth item of logistics characteristic information of logistics node i; β 3w It is expressed as the influence coefficient of the wth environmental characteristic; It is represented as the w-th environmental characteristic information of logistics node i; ε is a constant coefficient.

2. The method for tracking and monitoring bulk commodity logistics based on blockchain according to claim 1 is characterized in that: The commodity characteristic information includes at least one of commodity category information, commodity quantity information, and commodity quality grade information; the logistics characteristic information includes at least one of transportation mode information, carrying capacity information, and transportation efficiency information; the objective characteristic information includes at least one of environmental delay duration, average circulation time, and average review cycle.

3. The method for tracking and monitoring bulk commodity logistics based on blockchain according to claim 1 is characterized in that: The influence coefficient acquisition process includes the following steps: Get the circulation cycle T of the current logistics node i in the logistics node information recorded on the blockchain i and historical data of information on influencing factors; To obtain the turnover period T i The historical data constructs the data sequence E = {T i }, construct a data sequence F = {F1, F2, ..., F n }, where F n It is represented as the data set of the nth influencing factor; n is the number of influencing factors; Calculate the correlation coefficient ξ between each data point in data sequence F and data sequence E jk ,ξ jk It is expressed as the correlation coefficient between the kth data point of the jth influencing factor and the data sequence E, j∈n, according to the calculated correlation coefficient ξ jk Determine the correlation R between the jth influencing factor and the circulation cycle j , the calculation formula is: Among them, Q is the total amount of data; According to the calculated correlation R j Determine the jth influencing factor for the turnover period T i The influence coefficient The calculation formula is:

4. The method for tracking and monitoring bulk commodity logistics based on blockchain according to claim 3 is characterized in that: Correlation coefficient ξ jk The calculation formula is: Where, Δmin=min[min(|T ik '-F jk |)], where min[min(|T ik '-F jk |)] is to take |T ik '-F jk |Calculate the minimum value of the result, and then take the minimum value of all calculated minimum values; Δmax=max[max(|T ik '-F jk |)], where max[max(|T ik '-F jk |)] is to take |T ik '-F jk |Calculate the maximum value of the result, and then take the maximum value of all calculated maximum values; T ik ' is the standardized value of the kth circulation cycle data point in the data sequence E, and T ik is the kth circulation cycle data value in the data sequence E, is the mean value of the turnover cycle data in the data sequence E, F jk is the normalized value of the kth data point of the jth influencing factor, and Among them, f jk is the kth data value of the jth influencing factor, is the data mean of the jth influencing factor, ρ is the resolution coefficient, and its value range is (0,1].

5. The blockchain-based commodity logistics tracking and monitoring system is characterized by: It includes logistics node information acquisition module, influence coefficient acquisition module and prediction model construction module; The logistics node information acquisition module is used to obtain the logistics node information recorded on the blockchain and extract the circulation period T of the current logistics node i. i The influencing factor information includes commodity feature information, logistics feature information, and objective feature information; the commodity feature information includes at least one of commodity category information, commodity quantity information, and commodity quality grade information; the logistics feature information includes at least one of transportation mode information, transportation capacity information, and transportation efficiency information; the objective feature information includes at least one of environmental delay duration, average circulation duration, and average review cycle; The influence coefficient acquisition module is used to obtain the current logistics node i according to the circulation period T i The influencing factor information is used to determine the influence of each influencing factor on the circulation period T i The influence coefficient of The influence coefficient acquisition process includes the following steps: Get the circulation cycle T of the current logistics node i in the logistics node information recorded on the blockchain i and historical data of information on influencing factors; To obtain the turnover period T i The historical data constructs the data sequence E = {T i }, construct a data sequence F = {F1, F2, ..., F n }, where F n It is represented as the data set of the nth influencing factor; n is the number of influencing factors; Calculate the correlation coefficient ξ between each data point in data sequence F and data sequence E jk ,ξ jk It is expressed as the correlation coefficient between the kth data point of the jth influencing factor and the data sequence E, j∈n, according to the calculated correlation coefficient ξ jk Determine the correlation R between the jth influencing factor and the circulation cycle j , the calculation formula is: Among them, Q is the total amount of data; According to the calculated correlation R j Determine the jth influencing factor for the turnover period T i The influence coefficient The calculation formula is: Among them, the correlation coefficient ξ jk The calculation formula is: Where, Δmin=min[min(|T ik '-F jk |)], where min[min(|T ik '-F jk |)] is to take |T ik '-F jk |Calculate the minimum value of the result, and then take the minimum value of all calculated minimum values; Δmax=max[max(|T ik '-F jk |)], where max[max(|T ik '-F jk |)] is to take |T ik '-F jk |Calculate the maximum value of the result, and then take the maximum value of all calculated maximum values; T ik ' is the standardized value of the kth circulation cycle data point in the data sequence E, and T ik is the kth circulation cycle data value in the data sequence E, is the mean value of the turnover cycle data in the data sequence E, F jk is the normalized value of the kth data point of the jth influencing factor, and Among them, f jk is the kth data value of the jth influencing factor, is the data mean of the jth influencing factor, ρ is the resolution coefficient, and its value range is (0,1]; The prediction model building module is used to build the circulation cycle T of the current logistics node i according to the acquired influence coefficient and influence factor information. i The prediction model is used to calculate the turnover period T of the current logistics node i. i ; The expression of the prediction model is: In the formula, β 1u Expressed as the influence coefficient of the u-th commodity feature; Represented as the characteristic information of the u-th commodity at logistics node i; β 2v It is expressed as the influence coefficient of the vth logistics characteristic; Represented as the vth item of logistics characteristic information of logistics node i; β 3w It is expressed as the influence coefficient of the wth environmental characteristic; It is represented as the w-th environmental characteristic information of logistics node i; ε is a constant coefficient.

6. The blockchain-based commodity logistics tracking and monitoring system according to claim 5 is characterized in that: The system also includes a memory, a processor, and an electronic program stored in the memory and capable of running on the processor, wherein the processor can implement the steps of the method according to any one of claims 1 to 4 when running the electronic program.

Images