Logistics freight forecasting method, system and equipment based on IoT AI technology

Abstract

The present application relates to the field of business management information processing technology, and provides a logistics freight forecasting method, system, computer-readable medium and electronic device based on the Internet of Things AI technology. The economic development data of the target area is obtained through the Internet of Things architecture, and the target industry is quantitatively evaluated based on the industrial data to determine the parameters representing the industry, and an industrial index model is constructed; the target goods are quantitatively evaluated based on the cargo data to determine the cargo attribute vector; based on the static characteristics corresponding to the cargo attribute vector, combined with the dynamic characteristics in the real-time cargo information obtained by the Internet of Things architecture, the cargo in the target area is graded to generate a cargo grading result; a freight forecasting model is constructed based on the industrial index model and the cargo grading result. It can reflect the industry and cargo status of the target area in real time and comprehensively, and the constructed freight forecasting model can comprehensively consider the industrial development trend and cargo market demand, and improve the accuracy and reliability of the forecast.

Description

Technical Field

[0001] The present application relates to the field of business management information processing technology, and specifically, to a logistics freight forecasting method, system, computer-readable medium and electronic device based on Internet of Things AI technology. Background Art

[0002] With the booming development of e-commerce and the accelerated advancement of globalization, the logistics industry is experiencing unprecedented development opportunities. The substantial increase in freight volume has resulted in a more complex transportation environment and higher management requirements for logistics companies. To improve transportation efficiency, reduce transportation costs, and enhance competitiveness, logistics companies need to leverage advanced technologies to achieve intelligent management and decision-making.

[0003] In current logistics and transportation management applications, commercial vehicle freight rate forecasting primarily relies on traditional factors such as transport distance, cargo weight, and volume. However, this approach often overlooks the significant impact of regional industries and cargo conditions on freight rates, resulting in inaccurate and subjective freight rate forecasting for commercial vehicle logistics. Summary of the Invention

[0004] The present application provides a logistics freight forecasting method, system, computer-readable medium and electronic device based on IoT AI technology, which can at least to some extent solve the problem of insufficient objectivity and accuracy in freight forecasting during commercial vehicle logistics transportation.

[0005] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by practice of the present application.

[0006] According to one aspect of the present application, a logistics freight prediction method based on IoT AI technology is provided, comprising: obtaining economic development data of a target area through an IoT architecture; quantitatively evaluating a target industry based on industry data in the economic development data, determining industry parameters representing the commercial attributes of the target industry, and constructing an industry index model based on the industry parameters; quantitatively evaluating a target cargo based on cargo data in the economic development data, and determining a cargo attribute vector representing the commercial attributes of the target cargo; grading cargo in the target area based on static features corresponding to the cargo attribute vector and dynamic features in real-time cargo information obtained by the IoT architecture to generate a cargo grading result; and constructing a freight prediction model based on the industry index model and the cargo grading result.

[0007] In the present application, based on the aforementioned scheme, the target industry is quantitatively evaluated according to the industrial data in the economic development data to determine the industrial parameters representing the commercial attributes of the target industry, including: determining the regional factor corresponding to the target area according to the population data in the economic development data; determining the distance factor between the enterprises in the target area according to the location information of each enterprise in the economic development data; determining the competition factor of the target area according to the scale data of each enterprise in the economic development data; and using the regional factor, the distance factor and the competition factor as the industrial parameters.

[0008] In the present application, based on the aforementioned solution, the industry index model is constructed based on the industry parameters, including: extracting features from the industry parameters according to the spatial correlation between the industry parameters to construct the industry index model.

[0009] In the present application, based on the aforementioned scheme, the target goods are quantitatively evaluated according to the goods data in the economic development data to determine the goods attribute vector representing the commercial attributes of the target goods, including: extracting feature information according to the goods data in the economic development data; and quantitatively evaluating the feature information to determine the goods attribute vector representing the commercial attributes of the target goods.

[0010] In the present application, based on the aforementioned scheme, the static features corresponding to the cargo attribute vectors are combined with the dynamic features in the real-time cargo information obtained by the Internet of Things architecture to grade the cargo in the target area and generate cargo grading results, including: dimensionality reduction of the cargo attribute vectors to generate static features; generating dynamic features based on the real-time cargo information obtained by the Internet of Things architecture; splicing the static features and the dynamic features, classifying the splicing results, and generating cargo grading results.

[0011] In the present application, based on the aforementioned scheme, a freight prediction model is constructed based on the industry index model and the cargo grading results, including: linearly processing the industry index model and the cargo grading results to generate linear results; performing deep cross-network-based splicing processing on the industry index model and the cargo grading results to generate nonlinear results; and generating a commercial vehicle freight prediction model based on the linear results and the nonlinear results.

[0012] In the present application, based on the aforementioned solution, after constructing the freight prediction model based on the industry index model and the cargo grading results, it also includes: displaying the commercial vehicle freight output by the commercial vehicle freight prediction model on the terminal interface.

[0013] According to one aspect of the present application, a logistics freight rate prediction system based on IoT AI technology is provided, comprising:

[0014] an acquisition unit, configured to acquire economic development data of a target area through an Internet of Things architecture;

[0015] An industry unit, configured to perform a quantitative assessment of a target industry based on the industry data in the economic development data, determine industry parameters representing the commercial attributes of the target industry, and construct an industry index model based on the industry parameters;

[0016] A cargo unit, performing a quantitative evaluation on target cargo based on cargo data in the economic development data, and determining a cargo attribute vector representing commercial attributes of the target cargo;

[0017] a grading unit, configured to grade the goods in the target area based on the static features corresponding to the goods attribute vector and in combination with the dynamic features in the real-time goods information acquired by the Internet of Things architecture, and generate a goods grading result;

[0018] A prediction unit is used to build a freight prediction model based on the industry index model and the cargo classification result.

[0019] In the present application, based on the aforementioned scheme, the target industry is quantitatively evaluated according to the industrial data in the economic development data to determine the industrial parameters representing the commercial attributes of the target industry, including: determining the regional factor corresponding to the target area according to the population data in the economic development data; determining the distance factor between the enterprises in the target area according to the location information of each enterprise in the economic development data; determining the competition factor of the target area according to the scale data of each enterprise in the economic development data; and using the regional factor, the distance factor and the competition factor as the industrial parameters.

[0020] In the present application, based on the aforementioned solution, the industry index model is constructed based on the industry parameters, including: extracting features from the industry parameters according to the spatial correlation between the industry parameters to construct the industry index model.

[0021] In the present application, based on the aforementioned scheme, the target goods are quantitatively evaluated according to the goods data in the economic development data to determine the goods attribute vector representing the commercial attributes of the target goods, including: extracting feature information according to the goods data in the economic development data; and quantitatively evaluating the feature information to determine the goods attribute vector representing the commercial attributes of the target goods.

[0022] In the present application, based on the aforementioned scheme, the static features corresponding to the cargo attribute vectors are combined with the dynamic features in the real-time cargo information obtained by the Internet of Things architecture to grade the cargo in the target area and generate cargo grading results, including: dimensionality reduction of the cargo attribute vectors to generate static features; generating dynamic features based on the real-time cargo information obtained by the Internet of Things architecture; splicing the static features and the dynamic features, classifying the splicing results, and generating cargo grading results.

[0023] In the present application, based on the aforementioned scheme, a freight prediction model is constructed based on the industry index model and the cargo grading results, including: linearly processing the industry index model and the cargo grading results to generate linear results; performing deep cross-network-based splicing processing on the industry index model and the cargo grading results to generate nonlinear results; and generating a commercial vehicle freight prediction model based on the linear results and the nonlinear results.

[0024] In the present application, based on the aforementioned solution, after constructing the freight prediction model based on the industry index model and the cargo grading results, it also includes: displaying the commercial vehicle freight output by the commercial vehicle freight prediction model on the terminal interface.

[0025] According to one aspect of the present application, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the logistics freight prediction method based on the Internet of Things AI technology as described in the above embodiment is implemented.

[0026] According to one aspect of the present application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the logistics freight prediction method based on the Internet of Things AI technology as described in the above embodiments.

[0027] According to one aspect of the present application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the logistics freight rate prediction method based on IoT AI technology provided in the various optional implementations described above.

[0028] The above process uses the IoT architecture to obtain economic development data for a target region. Based on the industry data in this economic development data, the target industry is quantitatively evaluated, and industry parameters representing the commercial attributes of the target industry are determined. Based on these industry parameters, an industry index model is constructed. Based on the cargo data in this economic development data, the target cargo is quantitatively evaluated, and a cargo attribute vector representing the commercial attributes of the target cargo is determined. Based on the static characteristics corresponding to the cargo attribute vector and the dynamic characteristics of the real-time cargo information obtained by the IoT architecture, cargo in the target region is graded and a cargo classification result is generated. A commercial vehicle freight rate forecasting model is constructed based on the industry index model and the cargo classification results. By integrating economic development data, classifying it, and quantitatively evaluating it through IoT technology, a real-time and comprehensive reflection of the industry and cargo status in the target region is achieved, providing an accurate data foundation for freight rate forecasting. Combining the industry index model with the cargo classification results allows the constructed freight rate forecasting model to comprehensively consider industry development trends and cargo market demand, improving the accuracy and reliability of forecasts.

[0029] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0031] Figure 1 The flowchart of the logistics freight prediction method based on the Internet of Things AI technology in one embodiment of the present application is schematically shown.

[0032] Figure 2 The flowchart for generating cargo classification results in one embodiment of the present application is schematically shown.

[0033] Figure 3 The following schematically shows a logistics freight forecasting system based on IoT AI technology in one embodiment of the present application.

[0034] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0035] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0036] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner.In the following description, many specific details are provided so as to provide a full understanding of the embodiments of the present application. However, it will be appreciated by those skilled in the art that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps etc. can be adopted. In other cases, known methods, systems, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0037] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0038] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0039] The implementation details of the technical solution of this application are described in detail below:

[0040] Figure 1 The flowchart of the method for predicting logistics freight based on the Internet of Things AI technology according to one embodiment of the present application is shown. Figure 1 As shown, the logistics freight prediction method based on IoT AI technology includes at least steps S110 to S150, which are described in detail as follows:

[0041] In step S110 , economic development data of the target area is obtained through the Internet of Things architecture.

[0042] In practical applications, the IoT architecture includes the perception layer, network layer, platform layer and application layer.

[0043] The perception layer is the bottom layer of the IoT architecture, like "touch" and "senses." It is composed of various sensors, such as temperature and humidity sensors. It interacts with the physical world to collect environmental or physical data, and converts non-electrical signals into digital signals. Its data collection characteristics are crucial to the effectiveness of the IoT system. Specifically, in this embodiment, in the IoT data acquisition module corresponding to the perception layer, IoT devices such as Global Positioning System (GPS) locators and sensors are deployed on commercial vehicles to collect information such as vehicle location, speed, and status in real time. By binding the GPS / Beidou positioning terminal with anti-disassembly function to the transport vehicle one by one, vehicle operation data is collected in real time, and the positioning terminal identifier and the transport vehicle frame number are associated and matched through the IoT platform.

[0044] The network layer is the "nerve center" that connects the upper and lower layers. Data is transmitted by building a network of wireless communication devices, such as routers and gateways. To ensure the accuracy, completeness, and timeliness of data transmission, a variety of communication technologies are used to meet the needs of different scenarios. Specifically, in this embodiment, the data transmission and processing module corresponding to the network layer transmits the collected data to the cloud server via mobile communication networks or satellite communications.

[0045] The platform layer is the "brain" of the IoT. The data processing center resides at this layer, responsible for data storage, processing (cleaning, denoising, etc.), conversion, and distribution. It may also perform device and security management functions to ensure system stability and data security. Specifically, the IoT platform cleans data reported by positioning terminals to ensure accuracy and performs physical model conversion to pre-process raw device data into business attribute indicators. Map matching is then performed, and the longitude and latitude reported by the positioning terminals are used to map the path and determine the vehicle's actual travel path.

[0046] The application layer is the top layer of the IoT architecture, where user interaction and value are realized. Based on platform layer data, various applications are developed, such as those related to smart homes and industrial fields, to provide intelligent solutions for life and industry. In this embodiment, in the mileage calculation module corresponding to the application layer, a map matching algorithm or path planning algorithm is used to construct a freight calculation model based on multi-dimensional factors. This model calculates the precise mileage of a vehicle's cycle based on real-time location information. Current transportation parameters are input into the freight calculation model, which instantly outputs the freight. Simultaneously, a prediction model is trained using historical data to output future freight forecasts. Based on the prediction results, strategic recommendations such as logistics route optimization and cost savings are then proposed.

[0047] This embodiment builds an IoT architecture within the target area, including deploying sensors, establishing a wireless communication network, and building facilities such as a data processing center. Specifically, when deploying sensors, various sensor devices are configured and managed to ensure they can accurately collect environmental or physical data within the target area. When building a wireless communication device network, wireless communication devices such as routers and gateways are set up to ensure that the data collected by the sensors can be efficiently and stably transmitted to the data processing center. The data processing center processes and analyzes the received data and is responsible for data storage, processing, conversion, and distribution, ultimately supporting the needs of various IoT application layers.

[0048] Specifically, in this embodiment, the target area may include the production and distribution area corresponding to a certain product, or the production and operation coverage area of ​​a certain type of enterprise, etc.

[0049] The sensor network is responsible for collecting various economic data related to physical quantities, such as traffic flow, cargo volume, and storage facility usage. Wireless communication equipment is responsible for transmitting this data in real time to the data processing center. After the data processing center receives the data from the sensor network, it undergoes preliminary processing and integration. The processing process includes steps such as data cleaning, data format unification, and data standardization. The integration process classifies and organizes data based on source and data type, integrating data from different sources and formats into a unified dataset for subsequent analysis.

[0050] From the integrated data set, data related to economic development are extracted as economic development data. Specifically, they may include indicator data such as industrial added value, fixed asset investment, and total retail sales of consumer goods in the target area. They may also include data that are indirectly related to economic development and directly related to the transportation industry, such as road freight volume and cargo turnover.

[0051] By implementing this step, economic development data of the target area can be effectively collected. These data not only reflect the economic status and development trends of the target area, but also provide rich input features for the commercial vehicle freight forecasting model, which helps to improve the accuracy and reliability of freight forecasting.

[0052] In step S120, a quantitative assessment is performed on the target industry based on the industry data in the economic development data, and industry parameters representing the commercial attributes of the target industry are determined. Based on the industry parameters, an industry index model is constructed.

[0053] In this embodiment, based on the industry data contained in the economic development data, a quantitative assessment algorithm is used to conduct an in-depth analysis of the target industry, thereby determining industry parameters that accurately represent the target industry's commercial attributes. Subsequently, based on these industry parameters, an industry index model is constructed that dynamically reflects the development status and trends of the target industry. This industry index model not only updates in real time to adapt to market changes, but also provides strong data support and decision-making basis for subsequent commercial vehicle freight rate forecasts.

[0054] In one embodiment of the present application, a quantitative assessment of a target industry is performed based on the industry data in the economic development data to determine industry parameters representing the commercial attributes of the target industry, including:

[0055] Determining a regional factor corresponding to the target area based on population data in the economic development data;

[0056] determining a distance factor between enterprises in the target area based on location information of each enterprise in the economic development data;

[0057] Determining the competition factor of the target area based on the scale data of each enterprise in the economic development data;

[0058] The regional factor, the distance factor, and the competition factor are used as the industry parameters.

[0059] In one embodiment of the present application, in determining the regional factor, first, based on the population data in the economic development data, the first number of employees corresponding to the target industry in the target region is obtained, and the total number of employees in the target industry nationwide is obtained; then, the quotient between the first number of employees and the total number of employees is used as a first parameter, the quotient between the total number of employees in the target region and the total number of employees nationwide is used as a second parameter, and the quotient between the first parameter and the second parameter is used as the regional factor. In this embodiment, the regional factor is used to measure the relationship between the target industry and population in the target region.

[0060] In one embodiment of the present application, in determining the distance factor, the first distance between each enterprise in the target industry and other similar enterprises in the target region is obtained based on the location information of each enterprise in the economic development data. The average distance between enterprises in the target industry nationwide is then determined. The quotient between the first distance and the average distance is used as a third parameter. The mean of the third parameter for all enterprises in the target industry is then determined, and the reciprocal of this mean is used as the distance factor. In this embodiment, the distance factor is used to characterize the distance attributes between enterprises in the same industry in the target region.

[0061] In one embodiment of the present application, in the process of determining the competitive factor, the Herfindahl index is determined based on the scale data of each enterprise in the economic development data. The calculation of the Herfindahl index is an existing public technology and is not described in detail in this application. The logarithm of the Herfindahl index is then taken as the competitive factor.

[0062] Finally, the regional factor, distance factor, and competition factor are used as industry parameters. This process is suitable for comparing the industrial agglomeration potential of regions of different sizes and economic levels, such as emerging industrial clusters in the central and western regions. This allows for a more comprehensive assessment of regional industrial attributes and captures their spatiotemporal dynamics.

[0063] After obtaining the industry parameters, we extract their features based on the spatial correlation between them to construct an industry index model. Specifically, the spatial correlation between industry parameters reflects the degree of spatial influence and dependence between different industries. Specifically, the degree of association (i.e., spatial correlation) between industry parameters can be determined by calculating the distance between corresponding vectors of these parameters. This spatial correlation stems from a variety of factors, such as resource sharing, market demand, and technological spillover effects.

[0064] Features that can reflect spatial correlation are extracted from industry parameters, including but not limited to: transaction volume between industries, which reflects the economic connection and degree of dependence between industries; technological similarity, which measures the technological connection between industries through indicators such as technology citations and R&D investment; geographical proximity, which is related to factors such as resource sharing and personnel flow; supply chain relationships, which are the upstream and downstream relationships of industries in the supply chain, and the impact of such relationships on the industry index.

[0065] After extracting the features, we use them to construct an industry index model to predict or explain changes in the industry index. Specifically, we can use methods such as multiple linear regression or logistic regression, using industry parameters as independent variables and the industry index as the dependent variable, to build an industry index model through regression analysis.

[0066] The above process uses industrial data in economic development data to conduct quantitative evaluation of target industries, and constructs an industrial index model by extracting the spatial correlation characteristics between industrial parameters, thereby enhancing the ability of the industrial index model to capture industrial development trends and market dynamics.

[0067] In step S130, a quantitative evaluation is performed on the target goods based on the goods data in the economic development data to determine a goods attribute vector representing the commercial attributes of the target goods.

[0068] In this example, a quantitative assessment of the goods data within the economic development data is conducted, and an in-depth analysis of the target goods is performed to determine a goods attribute vector that comprehensively reflects their commercial attributes. This vector encompasses multiple key indicators of the goods to more accurately describe the target goods' market performance and potential value.

[0069] In one embodiment of the present application, performing a quantitative assessment of target goods based on the goods data in the economic development data to determine a goods attribute vector representing the commercial attributes of the target goods includes:

[0070] extracting feature information based on the cargo data in the economic development data;

[0071] The characteristic information is quantitatively evaluated to determine a cargo attribute vector representing the commercial attributes of the target cargo.

[0072] In one embodiment of the present application, cargo data includes data such as cargo volume, weight, and material. Cargo attributes include physical properties (such as volume, weight, and density), chemical properties (such as perishability and hazardous material classification), and energy consumption during transportation (such as energy consumption coefficient). Cargo attribute quantification is the process of converting various cargo attributes into quantifiable mathematical indicators or feature vectors. The resulting cargo attribute vectors can include characteristic information such as volume-to-density ratio, weight distribution entropy, perishability index, hazardous material classification, and energy consumption coefficient.

[0073] The volume density ratio is the ratio of the volume of a cargo to its weight. It reflects the compactness or density of the cargo. For transportation, high-density cargo means higher transportation efficiency because more weight can be transported in a limited space.

[0074] Weight distribution entropy is a measure of the uniformity of cargo weight distribution. Uneven weight distribution can lead to instability or safety hazards during transportation. By quantifying this unevenness, weight distribution entropy provides an important reference for transportation planning.

[0075] The perishability index measures the likelihood that goods will deteriorate or be damaged during transportation. For perishable goods such as food and medicine, the perishability index directly impacts their preservation and safety during transportation.

[0076] Dangerous goods are classified into different levels based on the degree of danger they pose. This classification helps to take appropriate safety measures during transportation to ensure the safety of people and goods.

[0077] The energy efficiency factor (EIC) is a measure of the energy consumption efficiency of cargo transportation. It reflects the amount of energy required to transport a unit weight or volume of cargo. It is a key consideration for those pursuing green and energy-efficient transportation methods.

[0078] After determining the characteristic information, a quantitative assessment is performed based on it to determine the characteristic vectors corresponding to each vector indicator. This vector serves as the cargo attribute vector representing the commercial attributes of the target cargo. By quantifying the characteristic information, a cargo attribute vector is constructed. This vector is a multi-dimensional dataset that comprehensively and accurately depicts the commercial attributes of the target cargo. This quantitative assessment provides a solid data foundation and scientific basis for subsequent decision-making, market strategy planning, and commercial vehicle freight rate forecasting.

[0079] In step S140, based on the static features corresponding to the cargo attribute vector and combined with the dynamic features in the real-time cargo information obtained by the IoT architecture, the cargo in the target area is classified to generate a cargo classification result.

[0080] In this embodiment, a comprehensive analysis and assessment is performed based on static features in the cargo attribute vector, such as size, weight, and material, combined with dynamic features of cargo information captured in real time by the IoT architecture, such as current inventory levels (temperature, humidity), and real-time transportation status (location). Subsequently, these goods are meticulously graded using pre-set grading rules, generating a clear cargo classification result. This result not only reflects the comprehensive performance of the goods in the current market environment but also provides strong data support for subsequent decisions such as inventory management, logistics scheduling, and commercial vehicle freight pricing.

[0081] like Figure 2 As shown, in one embodiment of the present application, based on the static features corresponding to the cargo attribute vectors and combined with the dynamic features in the real-time cargo information obtained by the IoT architecture, the cargo in the target area is graded to generate a cargo grading result, including:

[0082] S210, performing dimensionality reduction on the cargo attribute vector to generate static features;

[0083] S220, generating dynamic features based on the real-time cargo information obtained by the IoT architecture;

[0084] S230: performing splicing processing on the static features and the dynamic features, classifying the splicing results, and generating a cargo classification result.

[0085] In practical applications, under the Internet of Things architecture, the classification of goods needs to comprehensively consider their static and dynamic characteristics. In order to accurately classify the goods, this application classifies them by combining static and dynamic characteristics.

[0086] In one embodiment of the present application, the process of reducing the dimension of the cargo attribute vector and generating static features includes the following steps: determining the covariance matrix corresponding to the cargo attribute vector; performing eigenvalue decomposition on the covariance matrix to generate multiple eigenvalues ​​and their corresponding eigenvectors; selecting the front k The eigenvalue vectors corresponding to the largest eigenvalues ​​are used to form a projection matrix; and static features are generated based on the product between the cargo attribute vector and the projection matrix.

[0087] Furthermore, for highly nonlinear data, the first correlation parameter between the elements in the cargo attribute vector is calculated. for:

[0088]

[0089] in, 、 as well as Represents the element value in the cargo attribute vector, m represents the number of elements in the cargo attribute vector, represents the vector factor obtained by training based on historical data, Represents an exponential function with the natural constant e as its base.

[0090] At the same time, in the low-dimensional space corresponding to the cargo attribute vector, the second correlation parameter between the elements in the cargo attribute vector is calculated for:

[0091]

[0092] in, 、 as well as express 、 as well as The corresponding low-dimensional coordinates respectively.

[0093] Generate an objective function based on the first correlation parameter and the second correlation parameter for:

[0094]

[0095] Here, log represents logarithmic operation.

[0096] The static characteristics of the cargo attribute vector are determined by minimizing the objective function. Specifically, the objective function is calculated, and when the objective function value is minimum, the corresponding and , as a static feature.

[0097] In one embodiment of the present application, a process of generating dynamic features based on real-time cargo information obtained by the Internet of Things architecture includes the following steps: obtaining real-time cargo information based on the Internet of Things architecture, and representing the real-time cargo information as time series data, wherein the real-time cargo information includes temperature, humidity, and location; extracting statistical features such as mean, variance, maximum value, minimum value, change trend, etc. from the time series data; and using the time series to extract trend information from the statistical features as the dynamic features.

[0098] In one embodiment of the present application, the static features and the dynamic features are spliced ​​together, the spliced ​​results are classified, and the process of generating a cargo grading result includes the following steps: splicing the static features and the dynamic features to form a complete feature vector, training the spliced ​​feature vector using a machine learning classification algorithm, and generating a cargo grading result.

[0099] This process quantitatively evaluates cargo data from economic development data to determine the commercial attribute vectors of target goods. Combined with real-time cargo information captured by the IoT architecture, this fully considers both static and dynamic characteristics of the goods. This categorized approach not only improves logistics management efficiency but also provides more refined data support for freight rate forecasting.

[0100] In step S150, a freight forecasting model is constructed based on the industry index model and the cargo classification result.

[0101] In one embodiment of this application, the established industry index model and cargo classification results are further integrated as key input features. Subsequently, a machine learning algorithm is used to conduct in-depth learning and pattern recognition on these input features to construct an accurate freight rate forecasting model. This model comprehensively considers multiple factors, including industry development trends, cargo market demand, and supply conditions, to efficiently and accurately forecast commercial vehicle freight rates, providing powerful decision-making support for logistics companies and transport providers.

[0102] In one embodiment of the present application, a freight rate prediction model is constructed based on the industry index model and the cargo classification results, including:

[0103] Performing linear processing on the industry index model and the goods classification result to generate a linear result;

[0104] Performing a deep cross-network-based splicing process on the industry index model and the goods classification results to generate a nonlinear result;

[0105] A commercial vehicle freight rate prediction model is generated based on the linear result and the nonlinear result.

[0106] In one embodiment of the present application, the industry index model and cargo classification results are linearly processed, that is, the original data are converted into linear results using a linear function (such as weighted sum) to capture the linear relationship in the data, that is, those freight changes that can be directly predicted by proportional changes.

[0107] The industry index model and cargo classification results are used as input and concatenated through a deep cross-layer network. The deep cross-layer network uses multiple layers of nonlinear activation functions and cross-layers to learn high-order feature interactions between the input data, generating nonlinear results that capture nonlinear relationships in the data, specifically freight rate fluctuations that cannot be predicted by simple linear models.

[0108] The linear and nonlinear results are then fused. This means that both results are written into the same training set. Using historical freight data as labels, the fused model is trained using the backpropagation algorithm. During training, model parameters, such as weights and biases, can be adjusted to minimize prediction error. Strategies such as regularization are employed to prevent overfitting, and model performance is evaluated using methods such as cross-validation. Model performance is evaluated on the validation set to ensure that the model maintains good predictive power even on unseen data. If model performance is poor, optimization can be sought by adjusting the model structure, increasing the amount of data, or improving feature engineering.

[0109] Deploy the trained commercial vehicle freight rate prediction model to real-world scenarios to predict freight rates in real time. Simultaneously, monitor the model's performance in real-world operation and perform regular updates and maintenance as needed.

[0110] Through the above steps, a commercial vehicle freight rate prediction model that combines linear and nonlinear characteristics can be constructed. This model can more accurately capture the patterns of freight rate changes, improve the model's prediction accuracy and generalization ability, and provide more accurate freight rate prediction services for the commercial vehicle transportation industry.

[0111] In one embodiment of the present application, after the commercial vehicle freight prediction model has been successfully run and can output the predicted freight results, the data format of the prediction results is checked to ensure that it can be correctly parsed and displayed by the terminal interface. If the model outputs raw data, it may need to be properly formatted, such as converted to currency format. The freight data output by the prediction model is bound to the display elements on the terminal interface (such as text boxes, labels, etc.), and the designed interface and prediction model are deployed to the target device. Through the above steps, the freight information output by the commercial vehicle freight prediction model can be displayed on the terminal interface, providing users with an intuitive and easy-to-use freight query service.

[0112] The above process uses the Internet of Things (IoT) architecture to obtain economic development data for a target region. Based on the industry data in this economic development data, a quantitative assessment of the target industry is performed, industry parameters representing the commercial attributes of the target industry are determined, and an industry index model is constructed based on these industry parameters. Based on the cargo data in the economic development data, a quantitative assessment of the target cargo is performed, and cargo attribute vectors representing the commercial attributes of the target cargo are determined. Based on the static characteristics corresponding to the cargo attribute vectors and the dynamic characteristics of the real-time cargo information obtained by the IoT architecture, cargo in the target region is graded to generate cargo classification results. A freight rate forecasting model is constructed based on the industry index model and the cargo classification results. By integrating and processing economic development data through IoT technology, this method can provide a real-time and comprehensive reflection of the industry and cargo status in the target region, providing an accurate data foundation for freight rate forecasting. Combining the industry index model with the cargo classification results, the constructed freight rate forecasting model comprehensively considers industry development trends and cargo market demand, improving the accuracy and reliability of forecasts.

[0113] The following describes an embodiment of a device of the present application, which can be used to implement the method for predicting logistics freight rates based on IoT AI technology described in the aforementioned embodiments of the present application. It is understood that the device can be a computer program (including program code) running on a computer device, such as an application software; the device can be used to execute the corresponding steps of the method provided in the embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the aforementioned embodiment of the method for predicting logistics freight rates based on IoT AI technology.

[0114] Figure 3 A block diagram of a logistics freight forecasting system based on IoT AI technology according to an embodiment of the present application is shown.

[0115] Reference Figure 3 As shown, according to one embodiment of the present application, a logistics freight forecasting system based on IoT AI technology includes:

[0116] An acquisition unit 310 is configured to acquire economic development data of a target area through an Internet of Things architecture;

[0117] An industry unit 320 is configured to perform a quantitative assessment of a target industry based on the industry data in the economic development data, determine industry parameters representing the commercial attributes of the target industry, and construct an industry index model based on the industry parameters;

[0118] The cargo unit 330 performs a quantitative evaluation on the target cargo based on the cargo data in the economic development data, and determines a cargo attribute vector representing the commercial attributes of the target cargo;

[0119] A grading unit 340 is configured to grade the goods in the target area based on the static features corresponding to the goods attribute vector and the dynamic features in the real-time goods information acquired by the IoT architecture, and generate a goods grading result;

[0120] The prediction unit 350 is configured to construct a freight prediction model based on the industry index model and the cargo classification result.

[0121] In the present application, based on the aforementioned scheme, the target industry is quantitatively evaluated according to the industrial data in the economic development data to determine the industrial parameters representing the commercial attributes of the target industry, including: determining the regional factor corresponding to the target area according to the population data in the economic development data; determining the distance factor between the enterprises in the target area according to the location information of each enterprise in the economic development data; determining the competition factor of the target area according to the scale data of each enterprise in the economic development data; and using the regional factor, the distance factor and the competition factor as the industrial parameters.

[0122] In the present application, based on the aforementioned solution, the industry index model is constructed based on the industry parameters, including: extracting features from the industry parameters according to the spatial correlation between the industry parameters to construct the industry index model.

[0123] In the present application, based on the aforementioned scheme, the target goods are quantitatively evaluated according to the goods data in the economic development data to determine the goods attribute vector representing the commercial attributes of the target goods, including: extracting feature information according to the goods data in the economic development data; and quantitatively evaluating the feature information to determine the goods attribute vector representing the commercial attributes of the target goods.

[0124] In the present application, based on the aforementioned scheme, the static features corresponding to the cargo attribute vectors are combined with the dynamic features in the real-time cargo information obtained by the Internet of Things architecture to grade the cargo in the target area and generate cargo grading results, including: dimensionality reduction of the cargo attribute vectors to generate static features; generating dynamic features based on the real-time cargo information obtained by the Internet of Things architecture; splicing the static features and the dynamic features, classifying the splicing results, and generating cargo grading results.

[0125] In the present application, based on the aforementioned scheme, a freight prediction model is constructed based on the industry index model and the cargo grading results, including: linearly processing the industry index model and the cargo grading results to generate linear results; performing deep cross-network-based splicing processing on the industry index model and the cargo grading results to generate nonlinear results; and generating a commercial vehicle freight prediction model based on the linear results and the nonlinear results.

[0126] In the present application, based on the aforementioned solution, after constructing the freight prediction model based on the industry index model and the cargo grading results, it also includes: displaying the commercial vehicle freight output by the commercial vehicle freight prediction model on the terminal interface.

[0127] The above process uses the Internet of Things (IoT) architecture to obtain economic development data for a target region. Based on the industry data in this economic development data, a quantitative assessment of the target industry is performed, industry parameters representing the commercial attributes of the target industry are determined, and an industry index model is constructed based on these industry parameters. Based on the cargo data in the economic development data, a quantitative assessment of the target cargo is performed, and cargo attribute vectors representing the commercial attributes of the target cargo are determined. Based on the static characteristics corresponding to the cargo attribute vectors and the dynamic characteristics of the real-time cargo information obtained by the IoT architecture, cargo in the target region is graded to generate cargo classification results. A freight rate forecasting model is constructed based on the industry index model and the cargo classification results. By integrating and processing economic development data through IoT technology, this method can provide a real-time and comprehensive reflection of the industry and cargo status in the target region, providing an accurate data foundation for freight rate forecasting. Combining the industry index model with the cargo classification results, the constructed freight rate forecasting model comprehensively considers industry development trends and cargo market demand, improving the accuracy and reliability of forecasts.

[0128] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device according to an embodiment of the present application is shown.

[0129] It should be noted that the computer system of the electronic device in this embodiment is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0130] In this embodiment, the computer system includes a central processing unit 401, which can perform various appropriate actions and processes based on programs stored in a read-only memory 402 or programs loaded from a storage unit 408 into a random access memory 403, such as executing the logistics freight forecasting method based on IoT AI technology described in the above embodiment. The random access memory 403 also stores various programs and data required for system operation. The central processing unit 401, the read-only memory 402, and the random access memory 403 are connected to each other via a bus 404. The input / output interface 405 is also connected to the bus 404.

[0131] The following components are connected to the input / output interface 405: an input section 406 including a keyboard, mouse, and the like; an output section 407 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and speakers; a storage section 408 including devices such as a hard disk; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the input / output interface 405 as needed. Removable media 411, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 410 as needed, so that computer programs read from the removable media can be installed in the storage section 408 as needed.

[0132] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product that includes a computer program carried on a computer-readable medium, the computer program including a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 409 and / or installed from a removable medium 411. When the computer program is executed by the central processing unit 401, the various functions defined in the system of the present application are performed.

[0133] It should be noted that the computer-readable medium described in the embodiments of the present application may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium may include a data signal transmitted in baseband or as part of a carrier wave, which carries a computer-readable computer program. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0134] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. Among them, each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0135] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. In some cases, the names of these units do not constitute limitations on the units themselves.

[0136] According to one aspect of the present application, a computer program product or computer program is provided, which includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above-mentioned various optional implementations. By integrating economic development data through Internet of Things technology and classifying and quantitatively evaluating it, it is possible to reflect the industry and cargo conditions of the target area in real time and comprehensively, providing an accurate data basis for freight forecasting. Combined with the industry index model and cargo classification results, the freight forecasting model constructed can comprehensively consider the industry development trend and cargo market demand, and improve the accuracy and reliability of the forecast.

[0137] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or it may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs. When the above one or more programs are executed by an electronic device, the electronic device implements the logistics freight forecasting method based on the Internet of Things AI technology described in the above embodiment. By integrating economic development data through the Internet of Things technology and classifying and quantitatively evaluating it, it can reflect the industry and cargo status of the target area in real time and comprehensively, and provide an accurate data basis for freight forecasting. Combined with the industry index model and cargo grading results, the constructed freight forecasting model can comprehensively consider the industry development trend and cargo market demand, and improve the accuracy and reliability of the forecast.

[0138] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiment of the application, the features and functions of two or more modules or units described above can be concretized in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0139] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes a number of instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.

[0140] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of this application and include common knowledge or customary techniques in the art that are not disclosed herein.

[0141] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A logistics freight forecasting method based on IoT AI technology, characterized in that: include: obtaining economic development data of a target area through an Internet of Things architecture, wherein the Internet of Things architecture includes a perception layer, a network layer, a platform layer, and an application layer; The perception layer interacts with the physical world to collect environmental or physical data and converts non-electrical signals into digital signals. IoT devices are deployed on commercial vehicles, including global positioning system locators and sensors. The perception layer is used to collect vehicle location, vehicle speed and vehicle status in real time, and to associate and match the positioning terminal identifier with the transport vehicle frame number through the IoT platform. The network layer transmits data to the cloud server by building a wireless communication device network. The platform layer cleans the data reported by the positioning terminal through the IoT platform, and performs physical model conversion to pre-process the original data of the device into business attribute indicators. After that, map matching is performed, and the longitude and latitude reported by the positioning terminal are used to draw a path to determine the actual driving path of the vehicle. In the mileage calculation module corresponding to the application layer, a map matching algorithm or a path planning algorithm is used to construct a freight calculation model based on multi-dimensional factors to calculate the precise mileage of the vehicle within a cycle based on real-time location information. Current transportation parameters are input into the freight calculation model, and the freight calculation model immediately outputs the freight. At the same time, the prediction model is trained using historical data to output future freight forecasts. Based on the forecast results, strategic recommendations for logistics route optimization and cost savings are then proposed. From the integrated data set, data related to economic development is extracted as economic development data. The economic development data includes the industrial added value, fixed asset investment, total retail sales of consumer goods, road freight volume, and cargo turnover of the target area. Performing a quantitative assessment of a target industry based on the industry data in the economic development data, determining industry parameters representing the commercial attributes of the target industry, and constructing an industry index model based on the industry parameters; Performing a quantitative assessment of target goods based on the goods data in the economic development data to determine a goods attribute vector representing the commercial attributes of the target goods; the goods data includes physical attributes, chemical attributes, and energy consumption attributes during transportation, physical attributes including volume, weight, and density, chemical attributes including perishability and hazardous material level, and energy consumption attributes including energy consumption coefficient. Cargo attribute vector quantification is the process of converting various attributes of goods into quantifiable mathematical indicators or characteristic vectors. The cargo attribute vector obtained through this process includes volume-to-density ratio, weight distribution entropy, perishability index, hazardous material level, and energy consumption coefficient. Based on the static features corresponding to the cargo attribute vectors and in combination with the dynamic features in the real-time cargo information acquired by the IoT architecture, the cargo in the target area is graded to generate a cargo classification result; Building a commercial vehicle freight rate prediction model based on the industry index model and the cargo classification results; The step of quantitatively evaluating the target goods based on the goods data in the economic development data to determine a goods attribute vector representing the commercial attributes of the target goods includes: extracting feature information based on the cargo data in the economic development data; Performing quantitative evaluation on the characteristic information to determine a goods attribute vector representing the commercial attributes of the target goods; The steps of grading the goods in the target area based on the static features corresponding to the goods attribute vector and combining the dynamic features in the real-time goods information obtained by the Internet of Things architecture to generate a goods grading result include: Performing dimensionality reduction on the cargo attribute vector to generate static features; Generating dynamic features based on real-time cargo information acquired by the IoT architecture; performing splicing processing on the static features and the dynamic features, classifying the splicing results, and generating a cargo classification result; The dimension of the cargo attribute vector is reduced to generate static features, including: Calculate the first correlation parameter between each element in the cargo attribute vector for: in, 、 as well as Represents the element value in the cargo attribute vector, m represents the number of elements in the cargo attribute vector, represents the vector factor obtained by training based on historical data, represents an exponential function with the natural constant e as the base; In the low-dimensional space corresponding to the cargo attribute vector, calculate the second correlation parameter between the elements in the cargo attribute vector for: in, 、 as well as express 、 as well as The corresponding low-dimensional coordinates respectively; Generate an objective function based on the first correlation parameter and the second correlation parameter for: Among them, log represents logarithmic operation; Calculate the objective function. When the objective function value is minimum, determine the corresponding and , as a static feature.

2. The method for predicting logistics freight rates based on IoT AI technology according to claim 1, characterized in that: The quantitative evaluation of the target industry based on the industry data in the economic development data to determine the industry parameters representing the commercial attributes of the target industry includes: Determining a regional factor corresponding to the target area based on population data in the economic development data; determining a distance factor between enterprises in the target area based on location information of each enterprise in the economic development data; Determining the competition factor of the target area based on the scale data of each enterprise in the economic development data; The regional factor, the distance factor, and the competition factor are used as the industry parameters.

3. The method for predicting logistics freight rates based on IoT AI technology according to claim 2, characterized in that: The constructing of an industry index model based on the industry parameters includes: According to the spatial correlation between the industrial parameters, features in the industrial parameters are extracted to construct an industrial index model.

4. The method for predicting logistics freight rates based on IoT AI technology according to claim 1, characterized in that: The commercial vehicle freight rate prediction model is constructed based on the industry index model and the cargo classification result, including: Performing linear processing on the industry index model and the goods classification result to generate a linear result; Performing a deep cross-network-based splicing process on the industry index model and the goods classification results to generate a nonlinear result; A commercial vehicle freight rate prediction model is generated based on the linear result and the nonlinear result.

5. The method for predicting logistics freight rates based on IoT AI technology according to claim 1, characterized in that: After constructing the freight rate prediction model based on the industry index model and the cargo classification result, the method further includes: The commercial vehicle freight rate output by the commercial vehicle freight rate prediction model is displayed on the terminal interface.

6. A logistics freight forecasting system based on IoT AI technology, characterized by: include: An acquisition unit is used to obtain real-time cargo information and economic development data of the target area through the Internet of Things architecture. The Internet of Things architecture includes a perception layer, a network layer, a platform layer and an application layer. The perception layer interacts with the physical world to collect environmental or physical data and converts non-electrical signals into digital signals. Internet of Things devices are deployed on commercial vehicles. The Internet of Things devices include global positioning system locators and sensors. The perception layer is used to collect vehicle position, vehicle speed and vehicle status in real time, and to achieve the association and matching of the positioning terminal identifier and the transport vehicle frame number through the Internet of Things platform. The network layer transmits data to the cloud server by building a wireless communication device network. The platform layer cleans the data reported by the positioning terminal through the Internet of Things platform, and performs physical model conversion to pre-process the original data of the device into business attribute indicators, and then performs map matching. The positioning terminal reports the longitude and latitude for path mapping to determine the actual driving path of the vehicle; in the mileage calculation module corresponding to the application layer, a map matching algorithm or a path planning algorithm is used to build a freight calculation model based on multi-dimensional factors to calculate the precise mileage of the vehicle within the cycle according to the real-time location information. The current transportation parameters are input into the freight calculation model, and the freight calculation model outputs the freight in real time; at the same time, the prediction model is trained using historical data to output the future freight forecast value, and then based on the forecast results, strategic suggestions for logistics path optimization and cost saving are proposed; in the integrated data set, data related to economic development are extracted as economic development data, and the economic development data include the industrial added value, fixed asset investment, total retail sales of consumer goods, road freight volume and cargo turnover of the target area; An industry unit, configured to perform a quantitative assessment of a target industry based on the industry data in the economic development data, determine industry parameters representing the commercial attributes of the target industry, and construct an industry index model based on the industry parameters; A cargo unit, performing a quantitative assessment of target cargo based on cargo data in the economic development data, and determining a cargo attribute vector representing the commercial attributes of the target cargo; the cargo data includes physical attributes, chemical attributes, and energy consumption attributes during transportation, the physical attributes including volume, weight, and density, the chemical attributes including perishability and hazardous material level, and the energy consumption attributes including an energy consumption coefficient. Cargo attribute vector quantification is a process of converting various cargo attributes into quantifiable mathematical indicators or characteristic vectors. The cargo attribute vector obtained through this process includes volume-to-density ratio, weight distribution entropy, perishability index, hazardous material level, and energy consumption coefficient. a grading unit, configured to grade the goods in the target area based on the static features corresponding to the goods attribute vector and in combination with the dynamic features in the real-time goods information acquired by the Internet of Things architecture, and generate a goods grading result; A prediction unit, configured to construct a commercial vehicle freight rate prediction model based on the industry index model and the cargo classification result; The step of quantitatively evaluating the target goods based on the goods data in the economic development data to determine a goods attribute vector representing the commercial attributes of the target goods includes: extracting feature information based on the cargo data in the economic development data; Performing quantitative evaluation on the characteristic information to determine a goods attribute vector representing the commercial attributes of the target goods; The steps of grading the goods in the target area based on the static features corresponding to the goods attribute vector and combining the dynamic features in the real-time goods information obtained by the Internet of Things architecture to generate a goods grading result include: Performing dimensionality reduction on the cargo attribute vector to generate static features; Generating dynamic features based on real-time cargo information acquired by the IoT architecture; performing splicing processing on the static features and the dynamic features, classifying the splicing results, and generating a cargo classification result; The dimension of the cargo attribute vector is reduced to generate static features, including: Calculate the first correlation parameter between each element in the cargo attribute vector for: in, 、 as well as Represents the element value in the cargo attribute vector, m represents the number of elements in the cargo attribute vector, represents the vector factor obtained by training based on historical data, represents an exponential function with the natural constant e as the base; In the low-dimensional space corresponding to the cargo attribute vector, calculate the second correlation parameter between the elements in the cargo attribute vector for: in, 、 as well as express 、 as well as The corresponding low-dimensional coordinates respectively; Generate an objective function based on the first correlation parameter and the second correlation parameter for: Among them, log represents logarithmic operation; Calculate the objective function. When the objective function value is minimum, determine the corresponding and , as a static feature.

7. A computer-readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the logistics freight forecasting method based on the Internet of Things AI technology as described in any one of claims 1 to 5 is implemented.

8. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the logistics freight forecasting method based on IoT AI technology as described in any one of claims 1 to 5.

Images