Intelligent logistics management method and system based on big data

Abstract

The embodiment of the invention provides an intelligent logistics management method and system based on big data, and belongs to the technical field of logistics information. The method comprises the following steps: performing data classification on first logistics information of a target logistics vehicle to obtain a target cargo type of the first logistics information; performing attention target screening on the first logistics information according to the target cargo type to obtain second logistics information; target space information of the second logistics information is obtained according to the target three-dimensional data, and initial internal environment parameters are obtained by measuring environment information of a target logistics vehicle according to a target sensor; adjusting the initial internal environment parameters according to the target space information to obtain target internal environment parameters; performing data clustering on the second logistics information according to the target internal environment parameters to obtain a target logistics class cluster; performing state prediction on the target logistics class cluster according to the target internal environment parameters to obtain a target logistics state; and performing logistics strategy adjustment on the target logistics vehicle according to the target logistics state to obtain a target logistics strategy.

Description

Technical Field

[0001] The present invention relates to the field of logistics information technology, and in particular to a smart logistics management method and system based on big data. Background Art

[0002] With the development of the Internet, the logistics industry has ushered in unprecedented opportunities and challenges. The Internet has not only greatly promoted the vigorous development of e-commerce, but also made logistics services an indispensable part of people's daily lives. People can transport goods through logistics and enjoy unprecedented convenience. However, in this process, the lack of effective protection measures for easily damaged items not only directly affects the customer experience, but also significantly increases the workload of delivery personnel. For example, for easily damaged items such as agricultural products, minerals, equipment, etc., if there is a lack of effective control and preservation measures in the logistics process, the items may be damaged during transportation, resulting in the goods received by customers being unusable. This increases the abnormal handling costs of logistics companies, while also extending the waiting time for customers and reducing customer satisfaction. Summary of the invention

[0003] The main purpose of the embodiments of the present invention is to provide a smart logistics management method and system based on big data, aiming to solve the problem in the related technology that there is a lack of effective protection measures for easily damaged items in the logistics service process, which not only directly affects the customer experience, but also significantly increases the workload of delivery personnel.

[0004] In a first aspect, an embodiment of the present invention provides a smart logistics management method based on big data, comprising: Obtaining first logistics information corresponding to a target logistics vehicle, and performing data classification on the first logistics information to obtain a target cargo type corresponding to the first logistics information; Performing a focus target screening on the first logistics information according to the target cargo type to obtain second logistics information corresponding to the target logistics vehicle; Obtaining target space information corresponding to the second logistics information according to the target three-dimensional data, and measuring the internal environment information of the target logistics vehicle according to the target sensor to obtain corresponding initial internal environment parameters; Adjusting the initial internal environment parameters according to the target space information to obtain the target internal environment parameters corresponding to the second logistics information; Performing data clustering on the second logistics information according to the target internal environment parameters to obtain a target logistics cluster; Predicting the state of the target logistics cluster according to the target internal environment parameters to obtain the target logistics state corresponding to the target logistics cluster; The logistics strategy of the target logistics vehicle is adjusted according to the target logistics status to obtain the target logistics strategy corresponding to the target logistics vehicle.

[0005] In a second aspect, an embodiment of the present invention provides a smart logistics management system based on big data, including: A data classification module, used to obtain first logistics information corresponding to a target logistics vehicle, and to perform data classification on the first logistics information to obtain a target cargo type corresponding to the first logistics information; A data screening module, used for screening the first logistics information according to the target cargo type to obtain the second logistics information corresponding to the target logistics vehicle; A data acquisition module, used to obtain target space information corresponding to the second logistics information according to the target three-dimensional data, and to measure the internal environment information of the target logistics vehicle according to the target sensor to obtain the corresponding initial internal environment parameters; a parameter adjustment module, configured to adjust the initial internal environment parameters according to the target space information to obtain the target internal environment parameters corresponding to the second logistics information; A data clustering module, used for performing data clustering on the second logistics information according to the target internal environment parameters to obtain a target logistics cluster; A state prediction module, used to predict the state of the target logistics cluster according to the target internal environment parameters, and obtain the target logistics state corresponding to the target logistics cluster; The logistics management module is used to adjust the logistics strategy of the target logistics vehicle according to the target logistics status to obtain the target logistics strategy corresponding to the target logistics vehicle.

[0006] The embodiment of the present invention provides a smart logistics management method and system based on big data, the method comprising: obtaining first logistics information corresponding to a target logistics vehicle, and classifying the first logistics information to obtain the target cargo type corresponding to the first logistics information; screening the first logistics information according to the target cargo type to obtain second logistics information corresponding to the target logistics vehicle, so as to obtain the items that need attention in the target logistics vehicle; obtaining target space information corresponding to the second logistics information according to the target three-dimensional data, and measuring the internal environmental information of the target logistics vehicle according to the target sensor to obtain the corresponding initial internal environmental parameters; adjusting the initial internal environmental parameters according to the target space information to obtain The target internal environmental parameters corresponding to the second logistics information are obtained, and then the accurate environmental parameters of the second logistics information can be accurately obtained according to the target spatial information, thereby providing good support for the subsequent logistics state judgment; the second logistics information is clustered according to the target internal environmental parameters to obtain the target logistics cluster; the state of the target logistics cluster is predicted according to the target internal environmental parameters, and the target logistics state corresponding to the target logistics cluster is obtained, so that the state prediction based on the target logistics cluster with similar characteristics can improve the accuracy of the state prediction of the single logistics information and reduce the risk; finally, the logistics strategy of the target logistics vehicle is adjusted according to the target logistics state, and the target logistics strategy corresponding to the target logistics vehicle is obtained. Thereby ensuring that the target items corresponding to the second logistics information are fully protected during the transportation process and improving the transportation quality. This method not only improves customer satisfaction, but also reduces the workload of the delivery staff. In addition, it also solves the problem in the related technology that there is a lack of effective protection measures for easily damaged items during the logistics service process, which not only directly affects the customer experience, but also significantly increases the workload of the delivery staff. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0008] Figure 1 A schematic diagram of a flow chart of a smart logistics management method based on big data provided by an embodiment of the present invention; Figure 2 A schematic diagram of the module structure of a big data-based intelligent logistics management system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0009] 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 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.

[0010] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0011] It should be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0012] The embodiment of the present invention provides a smart logistics management method and system based on big data. The smart logistics management method based on big data can be applied to a terminal device, which can be an electronic device such as a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device. The terminal device can be a server or a server cluster.

[0013] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0014] Please refer to Figure 1 , Figure 1 A flowchart of a smart logistics management method based on big data is provided in an embodiment of the present invention.

[0015] like Figure 1 As shown, the smart logistics management method based on big data includes steps S101 to S107.

[0016] Step S101: obtain first logistics information corresponding to a target logistics vehicle, and perform data classification on the first logistics information to obtain a target cargo type corresponding to the first logistics information.

[0017] Exemplarily, the target logistics vehicles refer to those vehicles that are performing transportation tasks, and the first logistics information refers to the information of the goods loaded in the target logistics vehicles. The first logistics information includes but is not limited to the origin, destination, type, quantity, weight, volume, etc. of each commodity. Thus, the first logistics information is classified according to the type in the first logistics information to obtain the corresponding target goods type, and the target goods type is one of the fragile type, the easily damaged type, the non-fragile type, etc. Among them, the goods corresponding to the easily damaged type usually have a short shelf life, are sensitive to environmental conditions such as temperature and humidity, and are easily damaged.

[0018] Step S102: screening the first logistics information for a target according to the target cargo type to obtain second logistics information corresponding to the target logistics vehicle.

[0019] For example, when the target cargo type is a fragile type or a cargo type that is easily affected by the external environment, the first logistics information corresponding to the target cargo type is determined as the second logistics information. That is, the second logistics information is the goods or articles that are affected by environmental parameters during transportation.

[0020] Step S103: obtaining target space information corresponding to the second logistics information according to the target three-dimensional data, and measuring the internal environmental information of the target logistics vehicle according to the target sensor to obtain corresponding initial internal environmental parameters.

[0021] For example, high-precision 3D scanning equipment, such as laser scanners, structured light scanners or portable 3D scanners, are installed in key locations such as loading areas, such as warehouses and loading and unloading platforms. The position and angle of the scanning equipment are reasonably planned to ensure that it can fully cover the entire loading area. Strategies such as multi-point scanning or scanning path planning are adopted to ensure that each commodity is scanned in all directions without blind spots. For example, fixed scanning equipment can be installed in the four corners of the loading area, and mobile scanners can be set up at key loading points to achieve seamless coverage. During the cargo loading process, each commodity is scanned in real time using a 3D scanning device to obtain its precise target 3D data, which is then transmitted to the database in real time through the network for storage and processing.

[0022] Exemplarily, in the database, the target three-dimensional data will be stored in association with the unique identifier of each commodity (such as commodity barcode, QR code, RFID tag, etc.). Thus, according to the unique identifier of each commodity in the second logistics information, the target spatial information corresponding to the second logistics information is extracted from the target three-dimensional data. The target spatial information is used to characterize the spatial information presented after the second logistics information is loaded in the target logistics vehicle.

[0023] Exemplarily, the target sensor includes but is not limited to a temperature sensor, a humidity sensor, an air pressure sensor, a light sensor, etc. Thus, the target sensor measures the internal environmental information of the target logistics vehicle to obtain the corresponding initial internal environmental parameters, which include but are not limited to temperature information, humidity information, air pressure information, light intensity information, etc.

[0024] Step S104: adjusting the initial internal environment parameters according to the target space information to obtain the target internal environment parameters corresponding to the second logistics information.

[0025] Exemplarily, the specific installation position of the target sensor inside the target logistics vehicle is determined, and the distance information between the target space information corresponding to each second logistics information and the specific installation position of the target sensor is calculated according to the Euclidean distance formula, and then the environmental parameters (such as temperature, humidity, etc.) of the target space information may be affected according to the distance information. For example: if the target space information is close to the target sensor, it may mean that the environmental parameters corresponding to the second logistics information are slightly different from the measurement results of the target sensor, otherwise the difference is large.

[0026] Exemplarily, the initial internal environment parameters are adjusted using preset parameter adjustment rules according to the calculated distance information to obtain the target internal environment parameters corresponding to the second logistics information.

[0027] For example, the preset parameter adjustment rules include temperature adjustment rules: for every additional 1 meter of distance information, the temperature should be increased by 0.5°C; humidity adjustment rules: the humidity adjustment value can be set as a percentage change of the distance information, such as for every additional 1 meter of distance, the humidity increases by 10 percentage points, and so on. After obtaining the distance information, the preset parameter adjustment rules are used to adjust the initial internal environment parameters to obtain the target internal environment parameters corresponding to the second logistics information.

[0028] In some embodiments, the adjusting the initial internal environment parameters according to the target spatial information to obtain the target internal environment parameters corresponding to the second logistics information includes: obtaining the surrounding logistics information corresponding to the second logistics information according to the target spatial information, and obtaining the first spatial information corresponding to the surrounding logistics information and the second spatial information corresponding to the second logistics information from a database; superimposing the surrounding logistics information according to the first spatial information to obtain the third spatial information; obtaining the current spatial information corresponding to the surrounding logistics information from the target three-dimensional data, calculating the similarity between the current spatial information and the third spatial information, and obtaining the first extrusion information corresponding to the surrounding logistics information; calculating the similarity between the second spatial information and the target spatial information, and obtaining the second extrusion information corresponding to the second logistics information; fusing the first extrusion information and the second extrusion information to determine the target closed information corresponding to the second logistics information; adjusting the initial internal environment parameters according to the target closed information to obtain the target internal environment parameters corresponding to the second logistics information.

[0029] Exemplarily, the database is accessed according to the target spatial information, all logistics information adjacent to the target spatial information is extracted and determined as the surrounding logistics information corresponding to the second logistics information, and then the first spatial information corresponding to the surrounding logistics information and the second spatial information corresponding to the second logistics information are obtained from the database. The first spatial information is used to represent the spatial information required to be occupied by the surrounding logistics information when it is not loaded in the target logistics vehicle. The second spatial information is used to represent the space required to be occupied by the second logistics information when it is not loaded in the target logistics vehicle.

[0030] Exemplarily, the first spatial information corresponding to the surrounding logistics information is merged to obtain the spatial information that all the surrounding logistics information needs to occupy when it is not squeezed in the target logistics vehicle, that is, to obtain the third spatial information. The third spatial information is used to represent the spatial information that all the surrounding logistics information needs to occupy when it is not squeezed and loaded in the target logistics vehicle.

[0031] Exemplarily, the target three-dimensional data collected previously is used to obtain current spatial information associated with the surrounding logistics information, that is, the current spatial information is the real spatial information formed by the surrounding logistics information near the second logistics information.

[0032] Exemplarily, a similarity measurement method (such as cosine similarity, Euclidean distance, etc.) is used to calculate the similarity between the current spatial information and the third spatial information. The actual state of the surrounding logistics information is evaluated by the similarity value to obtain the first squeezing information corresponding to the surrounding logistics information after loading. Similarly, the similarity between the second spatial information and the target spatial information is calculated, and the second squeezing information is obtained by the similarity result. The first squeezing information is used to characterize the squeezing degree of the surrounding logistics information after loading. The greater the similarity, the smaller the squeezing degree, and the smaller the similarity, the greater the squeezing degree. The second squeezing information is used to characterize the squeezing degree of the second logistics information after loading. The greater the similarity, the smaller the squeezing degree, and the smaller the similarity, the greater the squeezing degree.

[0033] Exemplarily, weighted average, logistic regression and other methods are used to fuse the first squeeze information and the second squeeze information to obtain the target closed information between the second logistics information and the surrounding logistics information. The target closed information is used to characterize the environmental circulation degree of the second logistics information in the target logistics vehicle.

[0034] Exemplarily, the initial environmental parameters are adjusted accordingly using preset rules according to the target sealing information to obtain the target internal environmental parameters corresponding to the second logistics information under the target space information.

[0035] Specifically, by adjusting the initial environmental parameters according to the target sealing information, the target internal environmental parameters corresponding to the second logistics information under the target space information are obtained, which provides good support for subsequently improving the accuracy of the second logistics information state prediction.

[0036] Step S105: clustering the second logistics information according to the target internal environment parameters to obtain a target logistics cluster.

[0037] Exemplarily, a clustering algorithm is used to perform data clustering according to the target internal environment parameters and the attribute information corresponding to the second logistics information, so as to obtain a target logistics cluster, wherein each cluster in the target logistics cluster has the same state change trend.

[0038] In some embodiments, data clustering of the second logistics information according to the target internal environment parameters to obtain target logistics clusters includes: performing similarity calculation on the second logistics information according to the target internal environment parameters to obtain target association information corresponding to the second logistics information; data clustering of the second logistics information according to the target association information to obtain the target logistics clusters.

[0039] Exemplarily, a suitable similarity calculation method is selected, such as cosine similarity, Euclidean distance or Pearson correlation coefficient, to measure the similarity between the target internal environment parameters corresponding to each logistics information in the second logistics information, and obtain a similarity value. When the similarity value is greater than a preset value, the target association information corresponding to the second logistics information is determined to have a high degree of association; when the similarity value is less than or equal to the preset value, the target association information corresponding to the second logistics information is determined to have a low degree of association.

[0040] Exemplarily, data clustering is performed on the second logistics information according to the target association information, and when the target association information has a high degree of association, it is determined to be the same cluster, thereby obtaining a target logistics cluster.

[0041] In some embodiments, the second logistics information includes at least first sub-logistics information and second sub-logistics information, the target internal environmental parameters include a first environmental parameter corresponding to the first sub-logistics information and a second environmental parameter corresponding to the second sub-logistics information, and the similarity calculation of the second logistics information according to the target internal environmental parameters to obtain the target association information corresponding to the second logistics information includes: obtaining first attribute information corresponding to the first sub-logistics information and second attribute information corresponding to the second sub-logistics information; determining a first change trend corresponding to the first sub-logistics information according to the first attribute information and the first environmental parameter; determining a second change trend corresponding to the second sub-logistics information according to the second attribute information and the second environmental parameter; and calculating the similarity between the first change trend and the second change trend to determine the target association information corresponding to the first sub-logistics information and the second sub-logistics information.

[0042] Exemplarily, the second logistics information includes at least first sub-logistics information and second sub-logistics information, and the target internal environmental parameters include first environmental parameters corresponding to the first sub-logistics information and second environmental parameters corresponding to the second sub-logistics information.

[0043] Exemplarily, a first item type corresponding to the first sub-logistics information is obtained, thereby determining first attribute information corresponding to the first sub-logistics information based on the first item type, and a second item type corresponding to the second sub-logistics information is obtained, thereby determining second attribute information corresponding to the second sub-logistics information based on the second item type.

[0044] Exemplarily, the first attribute information and the first environmental parameter are used to perform data statistics and trend analysis. For example, the destruction trend of the goods corresponding to the first sub-logistics information, that is, the first change trend, is determined by combining the first attribute information and the first environmental parameter through a time series model. The first change trend is used to characterize the destruction speed corresponding to the first sub-logistics information under the first environmental parameter. For example, the temperature in the first environmental parameter changes the destruction speed of the goods corresponding to the first sub-logistics information under the first attribute information.

[0045] Similarly, the second attribute information and the second environmental parameter are used to perform data statistics and trend analysis. For example, the destruction trend of the goods corresponding to the second sub-logistics information, that is, the second change trend, is determined by combining the second attribute information and the second environmental parameter through a time series model. The second change trend is used to characterize the destruction speed corresponding to the second sub-logistics information under the second environmental parameter. For example, the temperature in the second environmental parameter changes the destruction speed of the goods corresponding to the second sub-logistics information under the second attribute information.

[0046] Exemplarily, a suitable similarity calculation method is determined, such as cosine similarity, Euclidean distance or correlation analysis. The first change trend and the second change trend are input into the similarity calculation method, and the similarity value between them is calculated. This similarity value reflects the degree of correlation between the quality change of the first sub-logistics information and the second sub-logistics information. Thus, based on the calculated similarity result, the degree of correlation between the first sub-logistics information and the second sub-logistics information is analyzed. A higher similarity value indicates that the target correlation information between the first sub-logistics information and the second sub-logistics information is highly correlated. A lower similarity value indicates that the target correlation information between the first sub-logistics information and the second sub-logistics information is less correlated.

[0047] In some embodiments, determining a first change trend corresponding to the first sub-logistics information based on the first attribute information and the first environmental parameter and determining a second change trend corresponding to the second sub-logistics information based on the second attribute information and the second environmental parameter include: using the attribute representation layer of the trend prediction model to represent the first attribute information to obtain a first representation vector; using the parameter representation layer of the trend prediction model to represent the first environmental parameter to obtain a second representation vector; using the information combination layer of the trend prediction model to match the first attribute information and the first environmental parameter using the first representation vector and the second representation vector to obtain multiple first combination information corresponding to the first sub-logistics information; using the trend prediction layer of the trend prediction model to respectively predict changes in the multiple first combination information to obtain multiple first combination information. a first prediction trend; using the trend fusion layer of the trend prediction model to fuse multiple first prediction trends to obtain the first change trend corresponding to the first sub-logistics information; using the attribute representation layer to represent the second attribute information to obtain a third representation vector; using the parameter representation layer to represent the second environmental parameter to obtain a fourth representation vector; using the information combination layer to match the second attribute information and the second environmental parameter using the third representation vector and the fourth representation vector to obtain multiple second combination information corresponding to the second sub-logistics information; using the trend prediction layer to respectively predict the changes of multiple second combination information to obtain multiple second prediction trends; using the trend fusion layer to fuse multiple second prediction trends to obtain the second change trend corresponding to the second sub-logistics information.

[0048] Exemplarily, the trend prediction model includes an attribute representation layer, a parameter representation layer, an information combination layer, a trend prediction layer, and a trend fusion layer.

[0049] Exemplarily, the attribute representation layer is used to process and convert the first attribute information, extract features from the first attribute information, and generate a first representation vector. The first representation vector represents the essential features of the first attribute information and can better support subsequent calculations.

[0050] For example, in the parameter representation layer, a one-hot representation algorithm is used to convert the first environmental parameter into a vector form, and then feature extraction is performed on the first environmental parameter to generate a second representation vector. The second representation vector can effectively capture the key features of the environmental parameter and help with subsequent parameter matching and trend prediction.

[0051] Exemplarily, the first attribute information and the first environmental parameter are effectively combined in the information combination layer by means of principal component analysis or key feature extraction, thereby generating a plurality of first combination information. Then, in the trend prediction layer, a classification network is used to perform change prediction on each first combination information to obtain a plurality of first prediction trends. The first prediction trend reflects the change direction and magnitude under a specific combination of attribute information and environmental parameters.

[0052] For example, in the trend fusion layer, a fusion algorithm such as weighted average or Bayesian fusion is used to fuse multiple first prediction trends to obtain a comprehensive first change trend. The first change trend can more comprehensively reflect the change law of the first sub-logistics information under various combination data.

[0053] Exemplarily, the attribute representation layer is used to process and convert the second attribute information, extract features from the second attribute information, and generate a third representation vector. The third representation vector represents the essential features of the second attribute information and can better support subsequent calculations.

[0054] Exemplarily, in the parameter representation layer, the second environmental parameter is converted into a vector form using a one-hot representation algorithm, and then the second environmental parameter is feature extracted to generate a fourth representation vector. The fourth representation vector can effectively capture the key features of the environmental parameter and help with subsequent parameter matching and trend prediction.

[0055] Exemplarily, the second attribute information and the second environmental parameter are effectively combined in the information combination layer by means of principal component analysis or key feature extraction, thereby generating a plurality of second combination information. Then, in the trend prediction layer, a classification network is used to perform change prediction on each second combination information to obtain a plurality of second prediction trends. The second prediction trend reflects the change direction and magnitude under the combination of specific attribute information and environmental parameters.

[0056] For example, in the trend fusion layer, a fusion algorithm such as weighted average or Bayesian fusion is used to fuse multiple second prediction trends to obtain a comprehensive second change trend. The second change trend can more comprehensively reflect the change law of the second sub-logistics information under various combination data.

[0057] Step S106: predict the state of the target logistics cluster according to the target internal environment parameters to obtain the target logistics state corresponding to the target logistics cluster.

[0058] Exemplarily, a subclass cluster corresponding to a target logistics class cluster is obtained, and then the sub-environment parameters corresponding to each sub-logistics information in the subclass cluster are obtained from the target internal environment parameters, so that the item status of the sub-logistics information is predicted using the sub-environment parameters according to the neural network model to obtain the sub-logistics status corresponding to each sub-logistics information, and then the sub-logistics status corresponding to each sub-logistics information in the subclass cluster is counted according to the voting mechanism to obtain the most predicted logistics status in the subclass cluster, and then the most predicted logistics status in the subclass cluster is determined as the final logistics status corresponding to the subclass cluster, so that the above steps are performed on each subclass cluster in the target logistics class cluster to obtain the final logistics status corresponding to each subclass cluster in the target logistics class cluster, and thus the target logistics status corresponding to the target logistics class cluster is obtained.

[0059] In some embodiments, the target logistics cluster includes at least one target sub-class cluster, and the target sub-class cluster includes at least third sub-logistics information and fourth sub-logistics information. The state prediction of the target logistics cluster according to the target internal environmental parameters to obtain the target logistics state corresponding to the target logistics cluster includes: obtaining third attribute information corresponding to the third sub-logistics information and fourth attribute information corresponding to the fourth sub-logistics information; obtaining the third environmental parameters corresponding to the third sub-logistics information and the fourth environmental parameters corresponding to the fourth sub-logistics information from the target internal environmental parameters; performing information prediction on the third attribute information and the third environmental parameters according to the state prediction model to obtain a first prediction result corresponding to the third sub-logistics information; performing information prediction on the fourth attribute information and the fourth environmental parameters according to the state prediction model to obtain a second prediction result corresponding to the fourth sub-logistics information; and fusing the first prediction result and the second prediction result to obtain the target logistics state corresponding to the target logistics cluster.

[0060] Exemplarily, the target logistics class cluster includes at least one target sub-class cluster, and the target sub-class cluster includes at least third sub-logistics information and fourth sub-logistics information, so as to obtain a third item type corresponding to the third sub-logistics information, thereby determining the third attribute information corresponding to the third sub-logistics information according to the third item type, and obtain a fourth item type corresponding to the fourth sub-logistics information, thereby determining the fourth attribute information corresponding to the fourth sub-logistics information according to the fourth item type.

[0061] Exemplarily, the third environmental parameters corresponding to the third sub-logistics information are obtained from the target internal environmental parameters according to the unique identifier of the third sub-logistics information, and the fourth environmental parameters corresponding to the fourth sub-logistics information are obtained from the target internal environmental parameters according to the unique identifier of the fourth sub-logistics information.

[0062] For example, a suitable prediction model is selected, such as a time series analysis model, a machine learning model (such as a random forest, a support vector machine, etc.), or a deep learning model (such as a long short-term memory network, LSTM), etc. The selected state prediction model is trained using a historical data set to optimize the model parameters so that it can accurately predict the logistics state.

[0063] Exemplarily, the third attribute information and the third environmental parameter are input into the trained state prediction model for state prediction, and the first prediction result corresponding to the third sub-logistics information is obtained. And the fourth attribute information and the fourth environmental parameter are input into the trained state prediction model to obtain the second prediction result corresponding to the fourth sub-logistics information. Thus, the first prediction result and the second prediction result are probabilistically fused using evidence theory to obtain the target prediction result, and then the logistics state corresponding to the maximum probability in the target prediction result is determined as the sub-logistics state corresponding to the target sub-class cluster. Thus, the sub-logistics state corresponding to each target sub-class cluster in the target logistics class cluster is obtained, and then the sub-logistics state corresponding to each target sub-class cluster is combined into the target logistics state corresponding to the target logistics class cluster. Thus, the logistics state is fused and analyzed according to each sub-logistics information in the target sub-class cluster, which can not only improve the accuracy and reliability of the prediction, but also provide a more scientific basis for subsequent logistics management and decision-making.

[0064] In some embodiments, the fusion of the first prediction result and the second prediction result to obtain the target logistics state corresponding to the target logistics cluster includes: quantifying the third environmental parameter to obtain a first quantification result, and performing a reliability calculation based on the first quantification result to obtain first reliable information corresponding to the third environmental parameter; determining first weight information corresponding to the first prediction result based on the first reliable information; quantifying the fourth environmental parameter to obtain a second quantification result, and performing a reliability calculation based on the second quantification result to obtain second reliable information corresponding to the fourth environmental parameter; determining second weight information corresponding to the second prediction result based on the second reliable information; predictively fusion the first prediction result and the second prediction result based on the first weight information and the second weight information to obtain the target logistics state corresponding to the target logistics cluster; wherein the first weight information and the second weight information are obtained according to the following formula: ; ; ; ; in, represents the i-th first quantization result corresponding to the j-th third environmental parameter, represents the first reliable information corresponding to the j-th third environmental parameter, m represents the quantity information corresponding to the first quantization result or the second quantization result, and n represents the number of parameter types corresponding to the third environmental parameter or the fourth environmental parameter; represents the i-th second quantization result corresponding to the j-th fourth environmental parameter, represents the second reliable information corresponding to the j-th fourth environmental parameter; represents the first weight information, represents the second weight information, and ln represents the natural logarithm.

[0065] Exemplarily, the parameter data of each type parameter in the third environmental parameter is normalized to obtain the first quantization result. For example, the third environmental parameter includes multiple type parameters such as temperature, humidity, and air pressure, so that the parameter data when the type parameter is temperature, the parameter data when the type parameter is humidity, and the parameter data when the type parameter is air pressure in the third environmental parameter are normalized respectively, so that multiple temperature parameters in the third environmental parameter are at the same scale, multiple humidity parameters are at the same scale, and multiple air pressure parameters are at the same scale, providing support for the subsequent measurement of the stability of the parameter data corresponding to the type parameters in the third environmental parameter.

[0066] Exemplarily, the reliability is calculated using the first quantization result according to the following formula to obtain first reliable information corresponding to the third environmental parameter.

[0067] ; in, represents the i-th first quantization result corresponding to the j-th third environmental parameter, represents the first reliable information corresponding to the j-th third environmental parameter, m represents the quantity information corresponding to the first quantization result, n represents the number of parameter types corresponding to the third environmental parameter, and ln represents the natural logarithm.

[0068] Exemplarily, the above formula can more accurately reflect the amount of information of each environmental parameter by comprehensively considering multiple quantitative results of the third environmental parameter by using ln to represent the natural logarithm. The greater the amount of information, the greater the reliability of the corresponding prediction result.

[0069] Exemplarily, the parameter data of each type parameter in the fourth environmental parameter is normalized to obtain the second quantization result. For example, the fourth environmental parameter includes multiple type parameters such as temperature, humidity, and air pressure, so that the parameter data when the type parameter is temperature, the parameter data when the type parameter is humidity, and the parameter data when the type parameter is air pressure in the fourth environmental parameter are normalized respectively, so that multiple temperature parameters in the fourth environmental parameter are at the same scale, multiple humidity parameters are at the same scale, and multiple air pressure parameters are at the same scale, providing support for the subsequent measurement of the stability of the parameter data corresponding to the type parameters in the fourth environmental parameter.

[0070] Exemplarily, the reliability is calculated using the second quantization result according to the following formula to obtain second reliable information corresponding to the fourth environmental parameter.

[0071] ; Wherein m represents the quantity information corresponding to the second quantization result, and n represents the number of parameter types corresponding to the fourth environmental parameter; represents the i-th second quantization result corresponding to the j-th fourth environmental parameter, represents the second reliable information corresponding to the j-th fourth environmental parameter; ln represents the natural logarithm.

[0072] Exemplarily, the above formula can more accurately reflect the amount of information of each environmental parameter by comprehensively considering multiple quantified results of the fourth environmental parameter by using ln to represent the natural logarithm. The greater the amount of information, the greater the reliability of the corresponding prediction result.

[0073] Exemplarily, after obtaining the first reliable information and the second reliable information, first weight information of the first prediction result and second weight information corresponding to the second prediction result are obtained according to the following formula.

[0074] ; ; in, represents the first reliable information corresponding to the j-th third environmental parameter, and n represents the number of parameter types corresponding to the third environmental parameter or the fourth environmental parameter; represents the second reliable information corresponding to the j-th fourth environmental parameter; represents the first weight information, Indicates the second weight information.

[0075] Exemplarily, the first prediction result and the second prediction result are weightedly fused according to the first weight information and the second weight information to obtain the target prediction result, and then the logistics state corresponding to the maximum probability in the target prediction result is determined as the sub-logistics state corresponding to the target sub-class cluster. In this way, the sub-logistics state corresponding to each target sub-class cluster in the target logistics class cluster is obtained, and then the sub-logistics state corresponding to each target sub-class cluster is combined into the target logistics state corresponding to the target logistics class cluster. Therefore, the logistics state is fused and analyzed according to each sub-logistics information in the target sub-class cluster, which can not only improve the accuracy and reliability of the prediction, but also provide a more scientific basis for subsequent logistics management and decision-making.

[0076] Step S107: adjusting the logistics strategy of the target logistics vehicle according to the target logistics status to obtain the target logistics strategy corresponding to the target logistics vehicle.

[0077] Exemplarily, the abnormal state is set to damage or destruction. The sub-logistics state corresponding to each target sub-cluster in the target logistics cluster is obtained from the target logistics state. When the sub-logistics state is an abnormal state, the sub-logistics information contained in the target sub-cluster is obtained, and then the target logistics strategy corresponding to the target logistics vehicle is obtained from the preset strategy. For example, the target logistics strategy is to increase air circulation in the area specified by the target space information to reduce temperature and humidity and prevent further damage. Or if weather conditions permit, open the vehicle's tarpaulin to increase ventilation while preventing excessive direct sunlight from causing temperature increases. The target logistics strategy can also be to suggest adjusting the transportation route and choosing a more suitable transportation environment if the temperature and humidity conditions of the current route are not conducive to the preservation of the goods, etc.

[0078] In some embodiments, after obtaining the target logistics strategy corresponding to the target logistics vehicle, the method further includes: obtaining the first internal environmental parameter by the target sensor measuring the environmental information inside the target logistics vehicle after applying the target logistics strategy; adjusting the first internal environmental parameter according to the target space information to obtain the second internal environmental parameter corresponding to the second logistics information; and performing state prediction on the target logistics cluster according to the second internal environmental parameter to obtain the latest logistics state corresponding to the target logistics cluster.

[0079] Exemplarily, after applying the target logistics strategy for a period of time, the target sensor is reused to measure the parameters of the internal environmental information of the target logistics vehicle to obtain the first internal environmental parameters corresponding to the target logistics vehicle, and then the first internal environmental parameters are further adjusted according to the target space information to obtain the second internal environmental parameters corresponding to the second logistics information.

[0080] Exemplarily, the state of each target sub-cluster in the target logistics cluster is re-predicted based on the second internal environmental parameter to obtain the current logistics state corresponding to each target sub-cluster, and then the latest logistics state corresponding to the target logistics cluster is formed according to the current logistics state corresponding to each target sub-cluster.

[0081] In some embodiments, after obtaining the latest logistics status, the method also includes: when the target logistics vehicle arrives at the target location, comparing the latest logistics status with a preset status to obtain a target comparison result; determining a target distribution strategy corresponding to the target logistics cluster from a target mapping table according to the target comparison result; performing logistics processing on the target logistics cluster according to the target distribution strategy to obtain a logistics processing result corresponding to the target logistics cluster.

[0082] Exemplarily, the preset status is damage or destruction. When the target logistics vehicle arrives at the target location, the latest logistics status is compared with the preset status to obtain a target comparison result. When the target comparison result is equal, that is, the latest logistics status is damage or destruction, the corresponding sub-class cluster is obtained from the target logistics cluster according to the latest logistics status, and then the associated logistics information corresponding to the sub-class cluster is obtained.

[0083] Exemplarily, the target mapping table is used to determine the target distribution strategy corresponding to the associated logistics information. The target distribution strategy is a predefined strategy set, which includes specific operations to be taken in different situations, such as obtaining the first information of the target user from the associated logistics information and obtaining the second information of the target merchant, and then sending a notification to the target user and the target merchant to inform them of the current logistics status and potential problems. This notification not only contains the status information of damage or destruction, but also may make the following requirements: for the target user, confirm the receiving status and ask whether he wants to continue to receive the goods or choose to refuse to receive them; for the target merchant, ask whether there is an emergency solution, such as replacement of goods, refund or re-delivery options. After the notification is sent, wait for feedback from the target merchant and the target user. If the target user and the target merchant decide to continue delivery, the delivery level corresponding to the associated logistics information is set to the highest, so as to give priority to delivery. Thus, the corresponding logistics processing result is obtained.

[0084] Specifically, the logistics status of the second logistics information in the target logistics vehicle is predicted to adjust the logistics strategy, thereby ensuring that the target items corresponding to the second logistics information are adequately protected during transportation and improving the transportation quality. Furthermore, by predicting the latest logistics status of the second logistics information, the status of the second logistics information can be promptly informed to merchants and users, which can reduce user waiting time and reduce the workload of delivery personnel.

[0085] See also Figure 2 , Figure 2 A smart logistics management system 200 for big data is provided in an embodiment of the present application. The smart logistics management system 200 for big data includes a data classification module 201, a data screening module 202, a data acquisition module 203, a parameter adjustment module 204, a data clustering module 205, a state prediction module 206, and a logistics management module 207, wherein the data classification module 201 is used to obtain first logistics information corresponding to a target logistics vehicle, and to perform data classification on the first logistics information to obtain a target cargo type corresponding to the first logistics information; the data screening module 202 is used to perform target screening on the first logistics information according to the target cargo type to obtain second logistics information corresponding to the target logistics vehicle; the data acquisition module 203 is used to obtain the second logistics information according to the target three-dimensional data. The target space information is obtained by measuring the internal environment information of the target logistics vehicle according to the target sensor to obtain the corresponding initial internal environment parameters; the parameter adjustment module 204 is used to adjust the initial internal environment parameters according to the target space information to obtain the target internal environment parameters corresponding to the second logistics information; the data clustering module 205 is used to perform data clustering on the second logistics information according to the target internal environment parameters to obtain the target logistics cluster; the state prediction module 206 is used to perform state prediction on the target logistics cluster according to the target internal environment parameters to obtain the target logistics state corresponding to the target logistics cluster; the logistics management module 207 is used to adjust the logistics strategy of the target logistics vehicle according to the target logistics state to obtain the target logistics strategy corresponding to the target logistics vehicle.

[0086] In some implementations, the parameter adjustment module 204, in the process of adjusting the initial internal environment parameters according to the target space information to obtain the target internal environment parameters corresponding to the second logistics information, performs: Obtaining peripheral logistics information corresponding to the second logistics information according to the target spatial information, and obtaining first spatial information corresponding to the peripheral logistics information and second spatial information corresponding to the second logistics information from a database; Superimposing the surrounding logistics information on the first spatial information to obtain third spatial information; Obtaining current spatial information corresponding to the surrounding logistics information from the target three-dimensional data, calculating the similarity between the current spatial information and the third spatial information, and obtaining first extrusion information corresponding to the surrounding logistics information; Calculating the similarity between the second spatial information and the target spatial information to obtain second extrusion information corresponding to the second logistics information; The first extrusion information and the second extrusion information are integrated to determine the target sealing information corresponding to the second logistics information; The initial internal environment parameters are adjusted according to the target sealing information to obtain the target internal environment parameters corresponding to the second logistics information.

[0087] In some implementations, the data clustering module 205 performs, during the process of clustering the second logistics information according to the target internal environment parameters to obtain the target logistics cluster: Performing similarity calculation on the second logistics information according to the target internal environment parameter to obtain target association information corresponding to the second logistics information; The second logistics information is clustered according to the target association information to obtain the target logistics cluster.

[0088] In some embodiments, the second logistics information includes at least first sub-logistics information and second sub-logistics information, and the target internal environment parameter includes a first environment parameter corresponding to the first sub-logistics information and a second environment parameter corresponding to the second sub-logistics information. In the process of performing similarity calculation on the second logistics information according to the target internal environment parameter to obtain the target association information corresponding to the second logistics information, the data clustering module 205 executes: Obtaining first attribute information corresponding to the first sub-logistics information and second attribute information corresponding to the second sub-logistics information; Determine a first change trend corresponding to the first sub-logistics information according to the first attribute information and the first environmental parameter; Determine a second change trend corresponding to the second sub-logistics information according to the second attribute information and the second environmental parameter; The similarity between the first change trend and the second change trend is calculated to determine the target association information corresponding to the first sub-logistics information and the second sub-logistics information.

[0089] In some implementations, the data clustering module 205 performs, during the process of determining the first change trend corresponding to the first sub-logistics information according to the first attribute information and the first environmental parameter and determining the second change trend corresponding to the second sub-logistics information according to the second attribute information and the second environmental parameter: Using the attribute representation layer of the trend prediction model to represent the first attribute information, obtaining a first representation vector; Using the parameter representation layer of the trend prediction model to represent the first environmental parameter, obtaining a second representation vector; Using the information combination layer of the trend prediction model, using the first characterization vector and the second characterization vector, to match the first attribute information and the first environmental parameter, to obtain a plurality of first combination information corresponding to the first sub-logistics information; Using the trend prediction layer of the trend prediction model to respectively predict changes of the plurality of first combination information, to obtain a plurality of first prediction trends; Using the trend fusion layer of the trend prediction model to fuse the first prediction trends, the first change trend corresponding to the first sub-logistics information is obtained; Using the attribute representation layer to represent the second attribute information to obtain a third representation vector; Using the parameter characterization layer to characterize the second environmental parameter to obtain a fourth characterization vector; Using the information combination layer, using the third characterization vector and the fourth characterization vector, to match the second attribute information and the second environmental parameter to obtain a plurality of second combination information corresponding to the second sub-logistics information; Using the trend prediction layer to respectively predict changes of the plurality of second combination information to obtain a plurality of second predicted trends; The trend fusion layer is used to fuse the information of the plurality of the second prediction trends to obtain the second change trend corresponding to the second sub-logistics information.

[0090] In some embodiments, the target logistics cluster includes at least one target sub-cluster, and the target sub-cluster includes at least third sub-logistics information and fourth sub-logistics information. In the process of performing state prediction on the target logistics cluster according to the target internal environment parameters to obtain the target logistics state corresponding to the target logistics cluster, the state prediction module 206 executes: Obtain third attribute information corresponding to the third sub-logistics information and fourth attribute information corresponding to the fourth sub-logistics information; Obtaining a third environmental parameter corresponding to the third sub-logistics information and a fourth environmental parameter corresponding to the fourth sub-logistics information from the target internal environmental parameter; Performing information prediction on the third attribute information and the third environmental parameter according to the state prediction model to obtain a first prediction result corresponding to the third sub-logistics information; Performing information prediction on the fourth attribute information and the fourth environmental parameter according to the state prediction model to obtain a second prediction result corresponding to the fourth sub-logistics information; The first prediction result and the second prediction result are integrated to obtain the target logistics state corresponding to the target logistics cluster.

[0091] In some implementations, the state prediction module 206 performs, during the process of fusing the first prediction result and the second prediction result to obtain the target logistics state corresponding to the target logistics cluster: quantifying the third environmental parameter to obtain a first quantification result, and calculating the reliability according to the first quantification result to obtain first reliable information corresponding to the third environmental parameter; Determine first weight information corresponding to the first prediction result according to the first reliable information; quantifying the fourth environmental parameter to obtain a second quantification result, and calculating the reliability according to the second quantification result to obtain second reliable information corresponding to the fourth environmental parameter; Determine second weight information corresponding to the second prediction result according to the second reliable information; Perform prediction fusion on the first prediction result and the second prediction result according to the first weight information and the second weight information to obtain the target logistics state corresponding to the target logistics cluster; The first weight information and the second weight information are obtained according to the following formula: ; ; ; ; in, represents the i-th first quantization result corresponding to the j-th third environmental parameter, represents the first reliable information corresponding to the j-th third environmental parameter, m represents the quantity information corresponding to the first quantization result or the second quantization result, and n represents the number of parameter types corresponding to the third environmental parameter or the fourth environmental parameter; represents the i-th second quantization result corresponding to the j-th fourth environmental parameter, represents the second reliable information corresponding to the j-th fourth environmental parameter; represents the first weight information, represents the second weight information, and ln represents the natural logarithm.

[0092] In some implementations, after obtaining the target logistics strategy corresponding to the target logistics vehicle, the logistics management module 207 further executes: After obtaining and applying the target logistics strategy, the target sensor measures the environmental information inside the target logistics vehicle to obtain a corresponding first internal environmental parameter; Adjusting the first internal environment parameter according to the target space information to obtain a second internal environment parameter corresponding to the second logistics information; The state of the target logistics cluster is predicted according to the second internal environment parameter to obtain the latest logistics state corresponding to the target logistics cluster.

[0093] In some implementations, after obtaining the latest logistics status, the logistics management module 207 further executes: When the target logistics vehicle arrives at the target location, the latest logistics status is compared with the preset status to obtain a target comparison result; Determine the target distribution strategy corresponding to the target logistics cluster from the target mapping table according to the target comparison result; Perform logistics processing on the target logistics cluster according to the target distribution strategy to obtain a logistics processing result corresponding to the target logistics cluster.

[0094] In some embodiments, the smart logistics management system 200 for big data can be applied to terminal devices.

[0095] It should be noted that technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working process of the smart logistics management system 200 for big data described above can refer to the corresponding process in the aforementioned smart logistics management method based on big data embodiment, and will not be repeated here.

[0096] An embodiment of the present invention also provides a storage medium for computer-readable storage, wherein the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement any step of the smart logistics management method based on big data provided in the description of the embodiment of the present invention.

[0097] The storage medium may be an internal storage unit of the terminal device in the aforementioned embodiment, such as a hard disk or memory of the terminal device. The storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the terminal device.

[0098] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware embodiment, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or transient medium). As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0099] It should be understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0100] The serial numbers of the embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A smart logistics management method based on big data, characterized in that: The method comprises: Obtaining first logistics information corresponding to a target logistics vehicle, and performing data classification on the first logistics information to obtain a target cargo type corresponding to the first logistics information; Performing a focus target screening on the first logistics information according to the target cargo type to obtain second logistics information corresponding to the target logistics vehicle; Obtaining target space information corresponding to the second logistics information according to the target three-dimensional data, and measuring the internal environment information of the target logistics vehicle according to the target sensor to obtain corresponding initial internal environment parameters; Adjusting the initial internal environment parameters according to the target space information to obtain the target internal environment parameters corresponding to the second logistics information; Performing data clustering on the second logistics information according to the target internal environment parameters to obtain a target logistics cluster; Predicting the state of the target logistics cluster according to the target internal environment parameters to obtain the target logistics state corresponding to the target logistics cluster; The logistics strategy of the target logistics vehicle is adjusted according to the target logistics status to obtain the target logistics strategy corresponding to the target logistics vehicle.

2. The method according to claim 1, characterized in that The adjusting the initial internal environment parameters according to the target space information to obtain the target internal environment parameters corresponding to the second logistics information includes: Obtaining peripheral logistics information corresponding to the second logistics information according to the target spatial information, and obtaining first spatial information corresponding to the peripheral logistics information and second spatial information corresponding to the second logistics information from a database; Superimposing the surrounding logistics information on the first spatial information to obtain third spatial information; Obtaining current spatial information corresponding to the surrounding logistics information from the target three-dimensional data, calculating the similarity between the current spatial information and the third spatial information, and obtaining first extrusion information corresponding to the surrounding logistics information; Calculating the similarity between the second spatial information and the target spatial information to obtain second extrusion information corresponding to the second logistics information; The first extrusion information and the second extrusion information are integrated to determine the target sealing information corresponding to the second logistics information; The initial internal environment parameters are adjusted according to the target sealing information to obtain the target internal environment parameters corresponding to the second logistics information.

3. The method according to claim 1, characterized in that The step of clustering the second logistics information according to the target internal environment parameter to obtain a target logistics cluster includes: Performing similarity calculation on the second logistics information according to the target internal environment parameter to obtain target association information corresponding to the second logistics information; The second logistics information is clustered according to the target association information to obtain the target logistics cluster.

4. The method according to claim 3, characterized in that The second logistics information at least includes first sub-logistics information and second sub-logistics information, the target internal environment parameter includes a first environment parameter corresponding to the first sub-logistics information and a second environment parameter corresponding to the second sub-logistics information, and the target association information corresponding to the second logistics information is obtained by performing similarity calculation on the second logistics information according to the target internal environment parameter, including: Obtaining first attribute information corresponding to the first sub-logistics information and second attribute information corresponding to the second sub-logistics information; Determine a first change trend corresponding to the first sub-logistics information according to the first attribute information and the first environmental parameter; Determine a second change trend corresponding to the second sub-logistics information according to the second attribute information and the second environmental parameter; The similarity between the first change trend and the second change trend is calculated to determine the target association information corresponding to the first sub-logistics information and the second sub-logistics information.

5. The method according to claim 4, characterized in that Determining a first change trend corresponding to the first sub-logistics information according to the first attribute information and the first environmental parameter and determining a second change trend corresponding to the second sub-logistics information according to the second attribute information and the second environmental parameter, includes: Using the attribute representation layer of the trend prediction model to represent the first attribute information, obtaining a first representation vector; Using the parameter representation layer of the trend prediction model to represent the first environmental parameter, obtaining a second representation vector; Using the information combination layer of the trend prediction model, using the first characterization vector and the second characterization vector, to match the first attribute information and the first environmental parameter, to obtain a plurality of first combination information corresponding to the first sub-logistics information; Using the trend prediction layer of the trend prediction model to respectively predict changes of the plurality of first combination information, to obtain a plurality of first prediction trends; Using the trend fusion layer of the trend prediction model to fuse the first prediction trends, the first change trend corresponding to the first sub-logistics information is obtained; Using the attribute representation layer to represent the second attribute information to obtain a third representation vector; Using the parameter characterization layer to characterize the second environmental parameter to obtain a fourth characterization vector; Using the information combination layer, using the third characterization vector and the fourth characterization vector, to match the second attribute information and the second environmental parameter to obtain a plurality of second combination information corresponding to the second sub-logistics information; Using the trend prediction layer to respectively predict changes of the plurality of second combination information to obtain a plurality of second predicted trends; The trend fusion layer is used to fuse the information of the plurality of the second prediction trends to obtain the second change trend corresponding to the second sub-logistics information.

6. The method according to claim 1, characterized in that The target logistics cluster includes at least one target sub-cluster, and the target sub-cluster includes at least third sub-logistics information and fourth sub-logistics information. The state prediction of the target logistics cluster according to the target internal environment parameter to obtain the target logistics state corresponding to the target logistics cluster includes: Obtain third attribute information corresponding to the third sub-logistics information and fourth attribute information corresponding to the fourth sub-logistics information; Obtaining a third environmental parameter corresponding to the third sub-logistics information and a fourth environmental parameter corresponding to the fourth sub-logistics information from the target internal environmental parameter; Performing information prediction on the third attribute information and the third environmental parameter according to the state prediction model to obtain a first prediction result corresponding to the third sub-logistics information; Performing information prediction on the fourth attribute information and the fourth environmental parameter according to the state prediction model to obtain a second prediction result corresponding to the fourth sub-logistics information; The first prediction result and the second prediction result are integrated to obtain the target logistics state corresponding to the target logistics cluster.

7. The method according to claim 6, characterized in that The fusing the first prediction result and the second prediction result to obtain the target logistics state corresponding to the target logistics cluster includes: quantifying the third environmental parameter to obtain a first quantification result, and calculating the reliability according to the first quantification result to obtain first reliable information corresponding to the third environmental parameter; Determine first weight information corresponding to the first prediction result according to the first reliable information; quantifying the fourth environmental parameter to obtain a second quantification result, and calculating the reliability according to the second quantification result to obtain second reliable information corresponding to the fourth environmental parameter; Determine second weight information corresponding to the second prediction result according to the second reliable information; Perform prediction fusion on the first prediction result and the second prediction result according to the first weight information and the second weight information to obtain the target logistics state corresponding to the target logistics cluster; The first weight information and the second weight information are obtained according to the following formula: ； ； ； ； in, represents the i-th first quantization result corresponding to the j-th third environmental parameter, represents the first reliable information corresponding to the j-th third environmental parameter, m represents the quantity information corresponding to the first quantization result or the second quantization result, and n represents the number of parameter types corresponding to the third environmental parameter or the fourth environmental parameter; represents the i-th second quantization result corresponding to the j-th fourth environmental parameter, represents the second reliable information corresponding to the j-th fourth environmental parameter; represents the first weight information, represents the second weight information, and ln represents the natural logarithm.

8. The method according to any one of claims 1 to 7, characterized in that After obtaining the target logistics strategy corresponding to the target logistics vehicle, the method further includes: After obtaining and applying the target logistics strategy, the target sensor measures the environmental information inside the target logistics vehicle to obtain a corresponding first internal environmental parameter; Adjusting the first internal environment parameter according to the target space information to obtain a second internal environment parameter corresponding to the second logistics information; The state of the target logistics cluster is predicted according to the second internal environment parameter to obtain the latest logistics state corresponding to the target logistics cluster.

9. The method according to claim 8, characterized in that After obtaining the latest logistics status, the method further includes: When the target logistics vehicle arrives at the target location, the latest logistics status is compared with the preset status to obtain a target comparison result; Determine the target distribution strategy corresponding to the target logistics cluster from the target mapping table according to the target comparison result; Perform logistics processing on the target logistics cluster according to the target distribution strategy to obtain a logistics processing result corresponding to the target logistics cluster.

10. A smart logistics management system based on big data, characterized in that: include: A data classification module, used to obtain first logistics information corresponding to a target logistics vehicle, and to perform data classification on the first logistics information to obtain a target cargo type corresponding to the first logistics information; A data screening module, used for screening the first logistics information according to the target cargo type to obtain the second logistics information corresponding to the target logistics vehicle; A data acquisition module, used to obtain target space information corresponding to the second logistics information according to the target three-dimensional data, and to measure the internal environment information of the target logistics vehicle according to the target sensor to obtain the corresponding initial internal environment parameters; a parameter adjustment module, configured to adjust the initial internal environment parameters according to the target space information to obtain the target internal environment parameters corresponding to the second logistics information; A data clustering module, used for performing data clustering on the second logistics information according to the target internal environment parameters to obtain a target logistics cluster; A state prediction module, used to predict the state of the target logistics cluster according to the target internal environment parameters, and obtain the target logistics state corresponding to the target logistics cluster; The logistics management module is used to adjust the logistics strategy of the target logistics vehicle according to the target logistics status to obtain the target logistics strategy corresponding to the target logistics vehicle.

Images