Personalized travel scheme pushing method and system based on artificial intelligence

Through a personalized travel solution push system based on artificial intelligence, deep learning models are used to predict traffic conditions and user demands, and optimize travel solution push, solving the problem of inefficient data sharing and utilization in the existing traffic management system and improving transportation resources The efficient allocation and utilization of urban transportation systems has enhanced the intelligence and adaptability of urban transportation systems.

CN118967412APending Publication Date: 2024-11-15QINGDAO ZHIHUICHENGSHI IND DEV
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411085353.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-08
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

The existing traffic management system cannot effectively share and utilize data, resulting in inefficient allocation and utilization of traffic resources, slow response when handling emergencies, and lack effective prediction and response mechanisms.

Method used

Adopt a personalized travel solution push system based on artificial intelligence, collect and integrate traffic data and user location information, use deep learning models to predict traffic conditions and user demands, optimize and generate personalized travel solutions, and push them in real time, considering traffic capacity , environmental impact and safety regulations.

Benefits of technology

It improves the efficient allocation and utilization of transportation resources, reduces traffic pressure, enhances the intelligence and adaptability of urban transportation systems, provides personalized travel suggestions, and ensures that users receive the best travel suggestions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118967412A_ABST
    Figure CN118967412A_ABST
Patent Text Reader

Abstract

The invention discloses a personalized travel scheme pushing method and system based on artificial intelligence, and the method comprises the following steps: S1, collecting original data, and carrying out the cleaning and classification of the original data, and obtaining integrated data; s2, analyzing the integrated data by using a deep learning model to obtain traffic condition prediction and user demand prediction; and S3, optimizing the traffic condition prediction and the user demand prediction in the step S2 to generate a personalized travel scheme, and pushing the personalized travel scheme in real time. According to the invention, the traffic condition prediction and the user demand prediction generated by the deep learning model are optimized to obtain a personalized travel scheme, so that the traffic pressure is effectively reduced, and efficient distribution and utilization of traffic resources are ensured; and the intelligentization and the self-adaptive capability of the urban traffic system are enhanced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of traffic management and information technology, and in particular to a method and system for pushing personalized travel plans using artificial intelligence technology. Background Art

[0002] At present, urban traffic monitoring mainly relies on hardware equipment such as surveillance cameras and traffic flow detectors. Although these devices can provide real-time traffic flow data, the problem of data islands is serious, and there is a lack of effective data sharing and communication mechanisms between different systems. In addition, most of the existing traffic management solutions focus on monitoring and controlling traffic flow, and rarely involve the prediction and satisfaction of individual travel needs, and cannot provide personalized travel suggestions, resulting in inefficient allocation and utilization of traffic resources.

[0003] With the popularization of smart phones and mobile Internet, people's demand for travel services is becoming increasingly diversified and personalized. Travel tools such as taxi apps, shared bicycles, and public transportation apps have emerged, providing citizens with convenient travel options. However, there is a lack of effective coordination and data sharing between these independently running applications, and their role in alleviating traffic pressure and optimizing traffic resource allocation is limited. For example, taxi apps may recommend a certain route in a certain period of time without considering the actual traffic conditions of this route, thereby exacerbating traffic congestion on a specific section of the road.

[0004] In addition, existing technologies are slow to respond to sudden traffic incidents and lack effective prediction and response mechanisms. How to predict traffic flow changes based on historical data and real-time conditions and take measures in advance has become an urgent problem to be solved.

[0005] In summary, it is now necessary to design a personalized travel plan push system and method based on artificial intelligence to solve the above problems in the prior art. Summary of the invention

[0006] The present invention provides a system and method for pushing personalized travel plans based on artificial intelligence, which solves the problem of low efficiency in configuration and utilization of traffic resources in the prior art.

[0007] In order to achieve the purpose of solving the above technical problems, the present invention adopts the following technical solutions: A method for pushing a personalized travel plan based on artificial intelligence includes the following steps: S1. Collect raw data, clean and classify the raw data to obtain integrated data; S2. Analyze the integrated data using a deep learning model to obtain traffic condition prediction and user demand prediction; S3, optimizing the traffic condition prediction and user demand prediction in step S2 to generate a personalized travel plan and push it in real time; The optimization of prediction in step S3 includes: Defining an objective function: The objective function includes a primary objective and a secondary objective; Setting constraints: The constraints include at least traffic capacity restrictions, environmental factors, and safety regulations; After selecting the optimization algorithm, iterative calculation is performed to determine the personalized travel plan based on the optimized objective function value.

[0008] In some embodiments of the present invention, step S2 also includes using the integrated data to train the deep learning model, and the deep learning model adopts a convolutional neural network, which includes an input layer, multiple convolutional layers and pooling layers, a fully connected layer and an output layer.

[0009] In some embodiments of the present invention, the deep learning model training process also includes adopting a dynamic learning rate adjustment mechanism, parameter initialization, and optimizing parameters in the neural network training process.

[0010] In some embodiments of the present invention, the traffic condition prediction includes at least traffic flow prediction, congestion point analysis and vehicle distribution prediction; the user demand prediction is based on user travel records, current location and social media information data.

[0011] In some embodiments of the present invention, collecting raw data includes: Use urban monitoring systems, sensors and IoT devices to collect traffic data and user location information in real time.

[0012] In some embodiments of the present invention, the step S1 further comprises integrating the original data: Firstly, the raw data is synchronized, and then the raw data from different sources are formatted in a unified manner; The data with unified format are merged and abnormal data are deleted to obtain improved data; Finally, the improved data is saved in a database and indexes are created for key attributes and fields of the improved data.

[0013] In some embodiments of the present invention, the cleaning of the raw data in step S1 includes: Identify and remove duplicate entries in the database; Check the data for errors or illogical values ​​and make corrections. For missing data, fill in the missing data based on the context or use statistical methods. Format standardization and removal of data fields not relevant to the analysis goal; The classification of the original data in step S1 includes: Determine the basis for classification based on the analysis objectives; Group the data according to the defined classification criteria and aggregate each group of data; Label the categorized data and encode the categories.

[0014] In some embodiments of the present invention, a system for pushing personalized travel plans based on artificial intelligence includes: A data collection module, which is used to collect traffic data and user location data; A data processing module, which is in communication with the data acquisition module and is used to clean and classify the data to obtain integrated data; An intelligent analysis module, which is used to analyze the integrated data according to a deep learning model to obtain traffic condition prediction and user demand prediction; Decision support module, which is used to optimize traffic condition forecasts and user demand forecasts and output personalized travel plans; The communication module is used to communicate with external devices to push personalized travel plans.

[0015] In some embodiments of the present invention, there is provided an electronic device, comprising: A processor, and a memory and a transceiver communicatively connected to the processor; The memory stores computer-executable instructions; the transceiver is used to send and receive data; The processor executes the computer-executable instructions stored in the memory to implement the above-mentioned calculation method.

[0016] In some embodiments of the present invention, a computer-readable storage medium is provided, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the above-mentioned calculation method when executed by a processor.

[0017] The technical solution of the present invention has the following technical effects compared with the prior art: The present invention obtains personalized travel plans after optimization by using the traffic condition prediction and user demand prediction generated by the deep learning model, which not only takes into account the overall traffic conditions, but also focuses on meeting individual travel needs, ensuring that users can receive the best travel suggestions, effectively reducing traffic pressure, and ensuring the efficient allocation and utilization of traffic resources; enhancing the intelligence and adaptability of urban transportation systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0019] Figure 1 This is a schematic diagram of the structure of a system for pushing personalized travel plans based on artificial intelligence.

[0020] Figure 2 It is a structural schematic diagram of the electronic device.

[0021] Figure numerals: 100, push system; 110, data acquisition module; 120, data processing module; 130, intelligent analysis module; 140, decision support module; 150, communication module; 200, electronic device; 210, processor; 220, memory; 230, transceiver. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner. Embodiment 1

[0024] A method for pushing a personalized travel plan based on artificial intelligence includes the following steps: S1. Collect raw data, clean and classify the raw data to obtain integrated data; Specifically, collecting raw data includes: Use urban monitoring systems, sensors and IoT devices to collect traffic data and user location information in real time.

[0025] Data collection can be represented by the following data collection function: f collect(t,x,y), where t represents time, and x and y represent geographic coordinates; For example, the data collection function can be expressed as: f collect (t,x,y)=SensorsData(t,x,y)+IOTDevices (t,x,y)+ UserData(t,x,y) Among them, SensorsData(t,x,y) represents the data collected by the sensor, IOTDevices (t,x,y) represents the data collected by the IoT device, and UserData(t,x,y) represents the data of the user's location.

[0026] In some embodiments of the present invention, the raw data includes traffic data and user location data; Traffic data includes the following: - Traffic volume: refers to the number of vehicles passing through a point or area within a specific period of time.

[0027] - Pedestrian flow: refers to the number of pedestrians in a specific area and is used to help analyze and predict the use of pedestrian areas or crosswalks.

[0028] - Bus operation status: including bus operation time, frequency, delays, etc., to evaluate the efficiency and reliability of public transportation services.

[0029] - Taxi Distribution: reflects the distribution and availability of taxis in the city, which helps to understand the coverage and demand satisfaction of taxi services.

[0030] The above data is collected through sensor networks deployed at key nodes in the city, surveillance cameras, public transportation systems and personal mobile devices, thereby achieving comprehensive monitoring of urban traffic conditions.

[0031] In some embodiments of the present invention, the step S1 further comprises integrating the original data: Firstly, the raw data is synchronized, and then the raw data from different sources are formatted in a unified manner; The data with unified format are merged and abnormal data are deleted to obtain improved data; Finally, the improved data is saved in a database and indexes are created for key attributes and fields of the improved data.

[0032] Specifically, the integration includes the following steps: 1. Data synchronization: Temporal and spatial alignment: Ensure that data from all sources are based on the same temporal and geographic coordinate systems. Standardization of timestamps and uniform encoding of geographic locations can be used.

[0033] 2. Unified data format: Formatting: Convert data from different sources into a unified format (such as CSV, JSON, etc.) for easy processing and analysis.

[0034] Coding uniformity: For categorical data, ensure that all sources use the same coding system, such as uniformly representing traffic signal status as "red", "yellow", "green", etc.

[0035] 3. Data Fusion: Association analysis: Linking data about the same geographic location or event from different data sources through key identifiers (such as road segment number, intersection name, etc.).

[0036] Data fusion technology: Use data fusion algorithms (such as weighted average, maximum / minimum selection, model fusion, etc.) to integrate information from different data sources to improve the accuracy and representativeness of the data.

[0037] 4. Exception and error handling: Anomaly detection: Identifying and correcting outliers or obvious errors in data, such as unreasonable speed readings or position information, detected through statistical analysis methods.

[0038] Data quality improvement: Improve data quality through cross-validation and data cleaning methods, such as using other data sources for comparison and correction.

[0039] 5. Data storage and indexing: Efficient storage: The consolidated data is stored in a database or databases, which enables fast access and retrieval.

[0040] Index building: Build indexes on key attributes and fields to optimize query performance and data retrieval speed.

[0041] Through the above steps, traffic data and user location information from different devices and data sources can be effectively integrated into a set of structured, unified and high-quality data sets, providing a reliable foundation for subsequent data processing, analysis and decision support.

[0042] In some embodiments of the present invention, data cleaning includes removing erroneous, incomplete, inconsistent or irrelevant parts of data to improve the quality and consistency of the data, in order to ensure that the data is accurate and reliable before in-depth analysis.

[0043] The cleaning of the original data in step S1 specifically includes the following steps: Identify and remove duplicate entries in the database to avoid over-computation of data during analysis; Check the data for errors or illogical values ​​and make corrections. For missing data, fill in the missing data based on the context or use statistical methods (such as mean or median filling); Ensure that all data follows the same format and unit, for example, the date and time format is unified as "YYYY-MM-DD HH:MM:SS"; remove data fields that are not related to the analysis objectives and focus on information that affects the results.

[0044] In some embodiments of the present invention, the classification of data involves organizing the data into meaningful categories or groups so that the data can be processed and analyzed more efficiently. This may include grouping or labeling the data so that it can be analyzed according to specific standards or characteristics.

[0045] The classification of the original data in step S1 specifically includes the following steps: Determine the classification basis based on the analysis objectives; for example, classification by geographic location, time period or event type; Group the data according to the defined classification criteria and aggregate each group of data; such as calculating the total number, average value, etc.; Label the classified data, such as classifying traffic conditions into "peak", "off-peak" and "low-peak", and encode these categories for easy processing and analysis; Build hierarchies: If necessary, further stratify or sub-categorize the data to support more detailed analysis.

[0046] After cleaning and classification, the integrated data is usually in an actionable format and needs to have the following characteristics: 1. Structured: Data should be organized according to a certain pattern or structure, such as a table, where each row represents a record and each column represents a data field. This structured format helps the database management system (DBMS) process the data efficiently.

[0047] 2. Standardization: Data values ​​should follow a unified standard or format. For example, dates and times should follow the ISO 8601 standard (such as "YYYY-MM-DD HH:MM:SS"), and address information should be standardized.

[0048] 3. Coding consistency: Data should be encoded in a unified way, such as UTF-8, to ensure compatibility between different data sources or systems.

[0049] 4. Metadata definition: There should be a clear metadata definition, that is, the descriptive information about the data, such as the data type of each field (string, integer, floating point number, date, etc.), length, whether it can be empty, etc.

[0050] 5. Accessibility: The data format should support easy access and retrieval, for example, using standard query languages ​​(such as SQL) to easily retrieve and analyze data.

[0051] 6. Compatibility: The format should be compatible with different data analysis and processing tools and can be easily imported into various data processing software and platforms for further analysis.

[0052] For example, the processed data can be in one of the following formats: - Relational Database Tables: In a relational database, data is organized in rows and columns, and each table has its defined schema, including field names and data types.

[0053] - CSV or Excel files: For file-level data exchange, the CSV or Excel format provides a widely accepted method to structure and standardize data.

[0054] - JSON or XML: For situations where hierarchical data representation is required, JSON or XML provides flexibility and scalability, supporting complex data structures and nesting.

[0055] By converting to these formats, the data becomes easier to analyze and process, meeting the needs of the subsequent intelligent analysis layer.

[0056] S2. Analyze the integrated data using a deep learning model to obtain traffic condition prediction and user demand prediction; The deep learning model is mainly used to analyze data and generate prediction results. The specific deep learning analysis process can be expressed as: P traffic , P user =M DL (Integrated Data) = NeuralNetwork(Integrated Data) Among them, NeuralNetwork is a convolutional neural network (CNN) or recurrent neural network (RNN) used to process large-scale traffic data.

[0057] For traffic condition prediction: predict traffic flow changes, expressed as P traffic .

[0058] Specifically, it includes traffic flow prediction, congestion point analysis, and vehicle distribution prediction, etc. This can be achieved by training deep learning models and learning traffic patterns from historical data and real-time data.

[0059] For user demand prediction: Identify and predict the user's personalized travel needs, expressed as P user .

[0060] Specifically, it predicts user needs based on data such as user travel history, current location, social media information, etc. Relevant information can be extracted from social media and news through natural language processing (NLP).

[0061] In some embodiments of the present invention, step S2 also includes using the integrated data to train the deep learning model, and the deep learning model adopts a convolutional neural network, which includes an input layer, multiple convolutional layers and pooling layers, a fully connected layer and an output layer.

[0062] The model formula of this embodiment includes multiple convolution and pooling layers, which are specially designed to extract spatiotemporal correlation features in traffic data. This structure enables the model to effectively identify and utilize the temporal and spatial dependencies of traffic flow, providing highly accurate input for prediction.

[0063] The fully connected layers in the model use composite activation functions to process the complex features passed from the convolutional layers and perform nonlinear transformations to generate the final traffic flow forecast. This design enhances the model's ability to express itself when dealing with nonlinear problems, thereby more accurately simulating and predicting traffic flow.

[0064] The output layer is custom designed according to the specific needs of urban traffic management and can provide a variety of forecast outputs, including short-term and long-term traffic flow forecasts, user travel demand forecasts, etc. In addition, the output layer can adjust its parameters according to different traffic scenarios and conditions to adapt to different forecasting needs.

[0065] Specifically, the deep learning model is a convolutional neural network (CNN) suitable for processing spatiotemporal data, which is particularly important in traffic flow prediction because traffic data usually has a high degree of spatiotemporal correlation.

[0066] 1. Input layer - Input: X t Represents the input data at time t, which may include vehicle flow, pedestrian flow, weather conditions, time tags (such as weekdays or weekends), historical traffic conditions, etc.

[0067] - Formula: X t =[x 1,t , x 2,t ,…, x n,t ] Among them, x i,t represents the value of the i-th feature at time t.

[0068] 2. Convolutional Layer - Function: Extract spatiotemporal features from input data.

[0069] - Formula: C t =f(W c *X t +b c ) Among them, W c represents the weight of the convolution layer, * represents the convolution operation, b c is the bias and f is the activation function, such as ReLU.

[0070] 3. Pooling Layer - Function: Reduce feature dimension and enhance the generalization ability of the model.

[0071] - Formula: P t =MaxPool(C t ) Use the maximum pooling operation to reduce the spatial dimension of the data, thereby reducing the number of parameters and the amount of calculation.

[0072] 4. Fully connected layer - Function: Perform nonlinear combination of features.

[0073] - Formula: F t =g(W f ·P t +b f ) Among them, W f and b f are the weights and biases of the fully connected layer, respectively, and g is another activation function, which may be Sigmoid or Tanh.

[0074] 5. Output Layer - Function: Generate the final prediction results, such as traffic flow in the future.

[0075] - Formula: Y t =h(W o ·F t +b o ) Among them, W o and b o are the weights and biases of the output layer, and h may be a linear activation function, suitable for regression tasks.

[0076] In some embodiments of the present invention, the deep learning model training process also includes adopting a dynamic learning rate adjustment mechanism, parameter initialization, and optimizing parameters in the neural network training process.

[0077] By adopting a dynamic learning rate adjustment mechanism, the parameter update during the neural network training process is optimized. This method not only improves the stability of training, but also speeds up the convergence speed, especially when processing large-scale and complex urban traffic data.

[0078] By designing a loss function tailored to specific urban traffic forecasting needs (e.g., weighted MSE, where errors in different time periods and traffic conditions are weighted differently), the accuracy and reliability of the forecast are significantly improved.

[0079] Using advanced parameter initialization methods, such as He or Xavier initialization, to ensure that the network can maintain appropriate activation levels and gradient flow in the early stages of training is critical for training deep networks.

[0080] Specifically, the parameters for deep learning model training include: - Weights and Biases: These are the basis of any neural network model. Weights control how much the input variables affect the output, while biases are constants added to the weight calculations to adjust the output.

[0081] - Learning Rate: determines the magnitude of the model parameter update in each iteration. A learning rate that is too high may cause the model to oscillate around the optimal solution, while a learning rate that is too low will result in a slow training process.

[0082] - Loss Function: Mean square error (MSE) or root mean square error (RMSE) is usually used in traffic flow prediction to measure the difference between the predicted value and the true value.

[0083] - Optimizer: Such as SGD (Stochastic Gradient Descent), Adam or RMSprop, which is used to update the weights and biases in the network to minimize the loss function.

[0084] In this embodiment, the loss function of the model training is usually the mean square error (MSE). The optimization algorithm is Adam or SGD to optimize the weights and biases and reduce the loss function value.

[0085] S3, optimizing the traffic condition prediction and user demand prediction in step S2 to generate a personalized travel plan and push it in real time; The optimization of prediction in step S3 includes: 1. Define the objective function: The objective function includes the primary objective and the secondary objective; Main goals: Minimize traffic congestion and optimize traffic flow; Secondary goal: maximize user satisfaction, such as reducing users' expected travel time and cost.

[0086] 2. Setting constraints includes: Transport capacity constraints: ensuring that any recommended route or mode does not exceed its carrying capacity; Environmental impact considerations: Consider environmental protection in route and mode recommendations, such as giving priority to public transportation and non-motorized routes; Safety regulations: All recommended solutions must comply with local traffic safety regulations and standards; Real-time: The optimization plan must take into account real-time traffic data and emergency response.

[0087] 3. After selecting the optimization algorithm, perform iterative calculations and determine the personalized travel plan based on the optimized objective function value.

[0088] Specifically, the optimization algorithm includes a heuristic algorithm and a deterministic algorithm; the heuristic algorithm adopts, for example, a genetic algorithm, simulated annealing or particle swarm optimization, which is suitable for processing such large-scale and complex optimization problems; The deterministic algorithm uses linear programming or integer programming to find an exact solution under specific conditions.

[0089] The iterative process specifically includes: - Initialization: Set the initial solution based on historical data and preset conditions; - Iterative optimization: The traffic plan is continuously adjusted through an iterative process. The objective function value is evaluated after each iteration, and the solution is adjusted to move towards a better solution according to the set optimization strategy; - Termination condition: Iteration stops when the maximum number of iterations is reached or the improvement of the solution is less than a predefined threshold.

[0090] By applying this optimization algorithm, this embodiment can improve user travel efficiency and satisfaction while ensuring smooth urban traffic, optimize the allocation of urban traffic resources, and significantly enhance the intelligence and adaptability of the entire urban traffic system.

[0091] In some embodiments of the present invention, the push process of personalized travel plans is implemented through real-time communication with user terminal devices. This mainly involves the following aspects: - Real-time: It can instantly push personalized travel suggestions and traffic management information to ensure the timeliness and accuracy of the information.

[0092] - Dynamic adjustment: According to the real-time traffic conditions, the pushed content can be dynamically adjusted to adapt to the current traffic environment and user needs.

[0093] - Collaboration: Collaborate closely with the city traffic management center to adjust traffic light control, optimize bus routes, etc. based on the analysis results, effectively alleviate traffic pressure and improve the operating efficiency of the entire urban transportation system.

[0094] The technical solution of the present invention has the following technical effects compared with the prior art: The present invention generates traffic condition predictions and user demand predictions through deep learning models, and obtains personalized travel plans after optimization, which can provide more accurate and personalized traffic management services. It not only takes into account the overall traffic conditions, but also focuses on meeting individual travel needs, ensuring that users can receive the best travel suggestions, effectively reducing traffic pressure, and ensuring the efficient allocation and utilization of traffic resources; enhancing the intelligence and adaptability of urban transportation systems. Embodiment 2

[0095] This embodiment will be based on Figure 1 and Figure 2 A system 100 and an electronic device 200 for pushing personalized travel plans based on artificial intelligence are described.

[0096] For the push system 100, refer to Figure 1 As shown, including: A data collection module 110, which is used to collect traffic data and user location data; A data processing module 120, which is in communication with the data acquisition module and is used to clean and classify the data to obtain integrated data; An intelligent analysis module 130, which is used to analyze the integrated data according to a deep learning model to obtain a traffic condition prediction and a user demand prediction; A decision support module 140, which is used to optimize traffic condition prediction and user demand prediction and output a personalized travel plan; The communication module 150 is used to communicate with external devices to push personalized travel plans.

[0097] It should be understood that the push system 100 here is embodied in the form of a functional module. The term "module" here may refer to an application specific integrated circuit (ASIC), an electronic circuit, a processor (such as a shared processor, a proprietary processor or a group processor, etc.) and a memory for executing one or more software or firmware programs, a merged logic circuit and / or other suitable components that support the described functions. In an optional example, those skilled in the art may understand that the push system 100 may be specifically the electronic device 200 in the above embodiment, or the functions of the electronic device 200 in the above embodiment may be integrated in the push system 100, and the push system 100 may be used to execute the various processes and / or steps corresponding to the electronic device 200 in the above method embodiment. To avoid repetition, it will not be repeated here.

[0098] The push system 100 has the function of implementing the corresponding steps performed by the electronic device 200 of the calculation method in Example 1; the above functions can be implemented by hardware, or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions. For example, the above acquisition module can be a communication interface, such as a transceiver interface.

[0099] In the embodiments of the present application, Figure 1 The prediction device 100 may also be a chip or a chip system, such as a system on chip (SoC).

[0100] Reference Figure 2 As shown, in this embodiment, an electronic device 200 is provided, including: A processor 210, and a memory 220 and a transceiver 230 communicatively connected to the processor; The memory 220 stores computer-executable instructions; the transceiver 230 is used to send and receive data; The processor 210 executes the computer-executable instructions stored in the memory 220 to implement the calculation method in Example 1.

[0101] It should be understood that the electronic device 200 can be used to execute the corresponding steps and / or processes in the above method embodiments. Optionally, the memory 220 may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory 220 may also include a non-volatile random access memory. For example, the memory 220 may also store information about the device type. The processor 210 may be used to execute the instructions stored in the memory 220, and when the processor 210 executes the instructions, the processor 210 may execute the corresponding steps and / or processes in the above method embodiments.

[0102] It should be understood that in the embodiment of the present application, the processor 210 may be a central processing unit (CPU), and the processor 210 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0103] In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor 210 or an instruction in the form of software. The steps of the method disclosed in conjunction with the embodiment of the present application can be directly embodied as a hardware processor for execution, or a combination of hardware and software modules in the processor 210 for execution. The software module can be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor executes the instructions in the memory, and completes the steps of the above method in conjunction with its hardware. To avoid repetition, it is not described in detail here. Embodiment 3

[0104] In this embodiment, a computer-readable storage medium is provided, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the calculation method in Example 1 when executed by a processor.

[0105] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0106] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0107] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0108] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0109] In the description of the above embodiments, specific features, structures, materials or characteristics may be combined in a suitable manner in any one or more embodiments or examples.

[0110] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for pushing personalized travel plans based on artificial intelligence, characterized in that: The following steps are involved: S1. Collect raw data, clean and classify the raw data to obtain integrated data; S2. Analyze the integrated data using a deep learning model to obtain traffic condition prediction and user demand prediction; S3, optimizing the traffic condition prediction and user demand prediction in step S2 to generate a personalized travel plan and push it in real time; The optimization of prediction in step S3 includes: Defining an objective function: The objective function includes a primary objective and a secondary objective; Setting constraints: The constraints include at least traffic capacity restrictions, environmental factors, and safety regulations; After selecting the optimization algorithm, iterative calculation is performed to determine the personalized travel plan based on the optimized objective function value.

2. The push method according to claim 1, characterized in that: Step S2 also includes using the integrated data to train the deep learning model, where the deep learning model uses a convolutional neural network, which includes an input layer, multiple convolutional layers and pooling layers, a fully connected layer and an output layer.

3. The push method according to claim 1, characterized in that: The deep learning model training process also includes adopting a dynamic learning rate adjustment mechanism, parameter initialization, and optimizing parameters in the neural network training process.

4. The push method according to claim 1, characterized in that: The traffic condition prediction includes at least traffic flow prediction, congestion point analysis and vehicle distribution prediction; the user demand prediction is based on user travel records, current location and social media information data.

5. The push method according to claim 1, characterized in that: The raw data collection includes: Use urban monitoring systems, sensors and IoT devices to collect traffic data and user location information in real time.

6. The push method according to claim 1, characterized in that: The step S1 also includes integrating the original data: Firstly, the raw data is synchronized, and then the raw data from different sources are formatted in a unified manner; The data with unified format are merged and abnormal data are deleted to obtain improved data; Finally, the improved data is saved in a database and indexes are created for key attributes and fields of the improved data.

7. The push method according to claim 1, characterized in that: The cleaning of the original data in step S1 includes: Identify and remove duplicate entries in the database; Check the data for errors or illogical values ​​and make corrections. For missing data, fill in the missing data based on the context or use statistical methods. Format standardization and removal of data fields not relevant to the analysis goal; The classification of the original data in step S1 includes: Determine the basis for classification based on the analysis objectives; Group the data according to the defined classification criteria and aggregate each group of data; Label the categorized data and encode the categories.

8. A personalized travel plan push system based on artificial intelligence, characterized in that: include: A data collection module, which is used to collect traffic data and user location data; A data processing module, which is in communication with the data acquisition module and is used to clean and classify the data to obtain integrated data; An intelligent analysis module, which is used to analyze the integrated data according to a deep learning model to obtain traffic condition prediction and user demand prediction; Decision support module, which is used to optimize traffic condition forecasts and user demand forecasts and output personalized travel plans; The communication module is used to communicate with external devices to push personalized travel plans.

9. An electronic device, characterized in that: include: A processor, and a memory and a transceiver communicatively connected to the processor; The memory stores computer-executable instructions; the transceiver is used to send and receive data; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

Citation Information

Cited By

  • Engineering truck intelligent scheduling method based on artificial intelligence

    CN120410015A