Digitized parking lot collaborative oversea truck reservation management system

Abstract

The invention discloses an oversea truck reservation management system based on digital parking lot cooperation, and the system comprises a judgment module which is used for obtaining a chat record of a truck driver, processing the chat record, and judging whether to generate truck oversea reservation information or not according to a processing result; the configuration module is used for configuring a multi-dimensional index and a cargo category index according to the truck sea-crossing reservation information, performing sea-crossing channel configuration according to the multi-dimensional index and the cargo category index, and distributing an optimal sea-crossing channel for the sea-crossing truck; the oversea truck dispatching module is used for distributing corresponding optimal parking spaces for the oversea trucks according to the positions of the oversea trucks; a plurality of index parameters can be considered, corresponding sea passing channels are dynamically distributed for sea passing trucks, and corresponding parking lots are distributed according to the sea passing channels; therefore, the utilization efficiency of sea passage resources is improved, and the turnover efficiency of ships is further improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of truck reservation, in particular to a digital yard cooperative cross-sea truck reservation management system. BACKGROUND

[0002] Cross-sea trucks refer to those cargo-carrying vehicles that need to be transported by ferry (ferry). These trucks are usually loaded with goods at a port or wharf and then transported to another port or wharf on the other side of the water to complete the cross-water transportation task. Cross-sea truck transportation combines the characteristics of road transportation and water transportation, and is suitable for connecting the transportation of goods between two land areas.

[0003] Different trucks differ in terms of cargo type, load capacity, etc., and have different requirements for cross-sea channels. However, the existing cross-sea trucks cannot reasonably allocate corresponding cross-sea channels when waiting to board the ship, which can lead to disorganized loading of trucks on the ship, failure to fully utilize the loading space of the ship, increased loading time, and reduced ship turnaround efficiency. SUMMARY

[0004] In view of the above prior art, the present application provides a digital yard cooperative cross-sea truck reservation management system, which mainly solves the technical problems existing in the background art.

[0005] To achieve the above purpose, the technical scheme of the embodiment of the present application is as follows: A digital yard cooperative cross-sea truck reservation management system, comprising: A judgment module for obtaining the chat records of truck drivers, processing the chat records, and determining whether to generate cross-sea truck reservation information according to the processing results; A configuration module for configuring multi-dimensional indicators and cargo category indicators according to the cross-sea truck reservation information, and configuring cross-sea channels according to the multi-dimensional indicators and the cargo category indicators, and allocating the optimal cross-sea channel for the cross-sea truck; A cross-sea truck dispatching module for allocating the corresponding optimal parking space for the cross-sea truck according to the position of the cross-sea truck.

[0006] Optionally, for obtaining the chat records of truck drivers, processing the chat records, and determining whether to generate cross-sea truck reservation information according to the processing results, comprising: Obtaining text messages in the WeChat group of the enterprise where the truck driver is located; Using large model entity recognition technology to extract and analyze the content of the text messages, determining whether the text messages contain basic information, and if so, generating cross-sea truck reservation information; If the text message does not contain basic information, the text message is determined as a casual message, and intent analysis is performed on the casual message.

[0007] Optionally, if the basic information is contained, truck crossing the sea reservation information is generated, further comprising: If the basic information is contained, it is further determined whether additional information is contained in the text message. If the text message contains the additional information, truck crossing the sea reservation information is generated. If the text message does not contain the additional information, the truck driver is reminded to supplement the additional information. After the truck driver supplements the additional information, truck crossing the sea reservation information is generated. The basic information includes: departure port, reservation time and license plate number; The additional information includes: driver's name, goods, truck type, accompanying personnel name and accompanying personnel ID information.

[0008] Optionally, if the text message does not contain basic information, the text message is determined as a casual message, and intent analysis is performed on the casual message, comprising: Setting a time window, for text messages within the time window, building an intent recognition model based on BERT; Input the text message into the intent recognition model, output the intent category and confidence corresponding to the text message, and determine the driver's intent; According to the driver's intent, the corresponding RPA processing flow is called. If the same RPA processing flow identifier appears within the time window, the calling is not repeated.

[0009] Optionally, the configuration module comprises a multi-dimensional index configuration unit, a goods configuration unit and a channel configuration unit. The multi-dimensional index configuration unit is configured to build multi-dimensional indexes according to the truck crossing the sea reservation information. The multi-dimensional indexes include the truck's approved load quality, truck height, truck category and goods category. The goods configuration unit is configured to configure the category of goods through a historical goods classification mapping table to build a goods category index. The channel configuration unit is configured to build a decision tree model and perform decision analysis according to the decision tree model to configure the crossing channel for the crossing truck.

[0010] Optionally, according to the decision tree model, decision analysis is performed to configure the crossing channel for the crossing truck, comprising: A hierarchical structure model is constructed by using the analytic hierarchy process to construct a judgment matrix. According to the judgment matrix, the weights of the multi-dimensional indexes and the goods category indexes are determined, consistency test is performed, and the optimal crossing channel for the crossing truck is obtained.

[0011] Optionally, according to the position of the cross-sea truck, a corresponding optimal parking space is allocated for the cross-sea truck, comprising: Obtaining an internal map of the parking lot, identifying the idle parking spaces of the internal map, and constructing an idle parking space dataset; According to the position of the cross-sea truck, analyzing the routes of the cross-sea truck and each idle parking space in the idle parking space dataset, screening to obtain the best navigation route, and according to the best navigation route, screening to obtain the optimal parking space; The best navigation route and the optimal parking space position are sent to the cross-sea truck driver.

[0012] Optionally, obtaining an internal map of the parking lot, identifying the idle parking spaces of the internal map, and constructing an idle parking space dataset, comprising: Obtaining an internal map of the parking lot; Collecting monitoring video data streams inside the parking lot, performing frame processing on the monitoring video data streams to obtain a monitoring image dataset, and using an image recognition model based on YOLO-V8 to perform image recognition on the monitoring image dataset to obtain idle parking space recognition results; According to the idle parking space recognition results, an idle parking space dataset is constructed.

[0013] Optionally, analyzing the routes of the cross-sea truck and each idle parking space in the idle parking space dataset, and screening to obtain the best navigation route, comprising: Calculate the distance between the cross-sea truck and each idle parking space in the idle parking space dataset to obtain a first route dataset; Sort all routes in the first route dataset according to distance to obtain a sorting result of all routes; According to the sorting result, the first route dataset is screened to obtain a second route dataset, and the time consumption results of all routes in the second route dataset are calculated; Analyzing the road congestion of the second route dataset to obtain a road congestion result; According to the time consumption results of all routes and the road congestion result, weighted calculation is performed, and according to the weighted calculation result, the best navigation route is screened.

[0014] Optionally, the analyzing the road congestion of the route dataset to obtain a road congestion result, comprising: Obtaining time sequence data information of the cross-sea truck, the time sequence data information including GPS position information, driving direction information, and vehicle state information of the cross-sea truck; Based on the timing data information, behavior of the cross-harbor truck is analyzed, and comprehensive behavior characteristics of the cross-harbor truck are established; Based on the comprehensive behavior characteristics of the cross-harbor truck, behavior correlation analysis is performed on the cross-harbor truck and adjacent cross-harbor trucks, and a correlation analysis result is obtained. According to the correlation result, a road congestion result is obtained.

[0015] The application provides a cross-harbor truck reservation management system based on digital yard cooperation, which can consider multiple index parameters, dynamically allocate corresponding cross-harbor channels to cross-harbor trucks, and allocate corresponding parking lot spaces according to the cross-harbor channels, thereby improving the utilization efficiency of cross-harbor channel resources and the turnover efficiency of ships. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 FIG. 1 is a structural schematic diagram of a cross-harbor truck reservation management system based on digital yard cooperation provided in an embodiment of the application. DETAILED DESCRIPTION

[0017] The technical solutions of the application are further described in detail below in combination with the drawings and specific embodiments. Unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art to which the application belongs. The terms used in the specification of the application are only for the purpose of describing specific embodiments and are not intended to limit the application. In the following description, the expression "some embodiments" describes a subset of all possible embodiments, but it should be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with each other without conflict.

[0018] In the following description, a large number of specific details are given in order to provide a more thorough understanding of the application. However, it is obvious to those skilled in the art that the application can be implemented without one or more of these details. In other cases, some technical features known in the art are not described in order to avoid obscuring the application.

[0019] It is to be understood that the application can assume various alternative embodiments, and should not be limited to the examples described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the application to those skilled in the art. Also, the terminology used here is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising", when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. As used herein the term "and / or" includes any and all combinations of associated items.

[0020] It is also to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising", when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. As used herein the term "and / or" includes any and all combinations of associated items.

[0021] For a thorough understanding of the application, reference will be made to the following detailed description, in which preferred embodiments of the application will be described, in order to explain the technical solutions presented by the application. The following detailed description of alternative embodiments of the application is provided, however, the application can have other embodiments in addition to these detailed descriptions.

[0022] Embodiments Please refer to the accompanying drawings Figure 1 The application provides a digital yard cooperative cross-harbor truck reservation management system, comprising: A judgment module is configured to obtain the chat records of truck drivers, process the chat records, and determine whether to generate cross-harbor truck reservation information according to the processing result; A configuration module is configured to configure multi-dimensional indexes and cargo category indexes according to the cross-harbor truck reservation information, and configure cross-harbor channels according to the multi-dimensional indexes and the cargo category indexes, and allocate the optimal cross-harbor channel for the cross-harbor truck. A cross-harbor truck scheduling module is configured to allocate the corresponding optimal parking space for the cross-harbor truck according to the position of the cross-harbor truck.

[0023] Specifically, the open interface of WeChat Enterprise is connected, the chat records of truck drivers in the WeChat Enterprise group are obtained at regular intervals, whether to generate reservation information is determined according to the analysis result by analyzing the chat records, if the cross-harbor truck reservation information is generated, the configuration module is used to configure the multi-dimensional indexes and the cargo category indexes according to the cross-harbor truck reservation information, the cross-harbor channels are configured according to the multi-dimensional indexes and the cargo category indexes, and the optimal cross-harbor channel is allocated for the cross-harbor truck. As an optional implementation, for obtaining the chat record of the truck driver, processing the chat record, and judging whether to generate the truck crossing the sea reservation information according to the processing result, comprising: Obtaining the text message in the enterprise WeChat group where the truck driver is located; Using a large model entity recognition technology to extract and analyze the content of the text message, judging whether the text message contains basic information, if it contains basic information, generating the truck crossing the sea reservation information; If the text message does not contain basic information, the text message is determined as a casual message, and the intent analysis is performed on the casual message.

[0024] If it contains basic information, the truck crossing the sea reservation information is generated, and further comprising: If the text message contains additional information, the truck crossing the sea reservation information is generated; if the text message does not contain the additional information, the truck driver is reminded to supplement the additional information, and then the truck crossing the sea reservation information is generated after the truck driver supplements the additional information; The basic information includes: departure port, reservation time and license plate number; The additional information includes: driver's name, goods, truck type, accompanying personnel name and accompanying personnel ID information.

[0025] As an optional implementation, if the text message does not contain basic information, the text message is determined as a casual message, and the intent analysis is performed on the casual message, comprising: Setting a time window, and based on BERT, constructing an intent recognition model for the text message in the time window; Inputting the text message into the intent recognition model, outputting the intent category and confidence corresponding to the text message, and determining the intent of the driver; According to the intent of the driver, the corresponding RPA processing flow is called; if the same RPA processing flow identifier appears in the time window, the calling is not repeated.

[0026] Specifically, the text message that does not contain basic information is determined as a casual message, avoiding unnecessary processing of irrelevant messages; As an optional implementation, the configuration module includes a multi-dimensional index configuration unit, a goods configuration unit and a channel configuration unit; The multi-dimensional index configuration unit is used to construct a multi-dimensional index according to the truck crossing the sea reservation information; the multi-dimensional index includes the approved load capacity of the truck, the height of the truck, the category of the truck and the category of the goods; The cargo configuration unit is configured to configure the category of the cargo by a historical cargo category mapping table, and to construct a cargo category index; The channel configuration unit is configured to construct a decision tree model, to perform decision analysis according to the decision tree model, and to configure a cross-sea channel for the cross-sea truck.

[0027] Specifically, the cross-sea truck type and the difference in the cargo cause the difference in the cross-sea channel selected by the cross-sea truck. According to the truck cross-sea reservation information, the rated load of the truck, the height of the truck, the type of the truck, and the category of the cargo can be obtained. Exemplarily, the type of the truck can be a mini truck, a light truck, a medium truck, or a heavy truck. The cargo configuration unit is configured to configure the category of the cargo by a historical cargo category mapping table, and to construct a cargo category index; The multi-dimensional index obtained by the multi-dimensional index configuration unit and the cargo category index obtained by the cargo configuration unit are subjected to decision analysis by the channel configuration unit, which is helpful to analyze the channel selection of different types of trucks and different categories of cargo, and to obtain a more reasonable decision.

[0028] It should be noted that the cargo type is involved in both the multi-dimensional index configuration unit and the cargo configuration unit, and the two are not in conflict. The cargo category information obtained by the multi-dimensional index configuration unit is relatively broad, while the cargo category index constructed by the cargo configuration unit is more specific and standardized. The two complement each other and provide more comprehensive and accurate cargo information support for subsequent links such as channel configuration.

[0029] As an optional implementation, the decision analysis according to the decision tree model and the configuration of the cross-sea channel for the cross-sea truck include: A hierarchical structure model is constructed by using the analytic hierarchy process, and a judgment matrix is constructed. The weights of the multi-dimensional index and the cargo category index are determined according to the judgment matrix, and consistency test is performed to obtain the optimal cross-sea channel for the cross-sea truck.

[0030] Specifically, a hierarchical structure model is constructed, which includes a target layer, a criterion layer, and a scheme layer. The target layer is used to select the optimal cross-sea channel, i.e., the problem to be solved is to allocate the most suitable channel to the truck. The criterion layer is used to obtain the multi-dimensional index configured by the multi-dimensional index configuration unit and the cargo category index obtained by the cargo configuration unit. These indexes are key factors affecting channel selection, for example, a truck with a large rated load may not be suitable for a channel with limited carrying capacity, and a truck with a high height may not be able to pass through some low channels. The scheme layer is used to provide selectable cross-sea channel schemes, exemplarily including channel A, channel B, and channel C. The complex channel configuration problem is decomposed into different levels. A judgment matrix is constructed, the indexes in the criterion layer are compared with each other according to the importance of each index to the selection of the over-sea passage, subjective judgment on the importance of the indexes is converted into quantified data, and basis is provided for subsequent calculation of the index weight; for example, it is considered that the rated load of the truck is slightly more important than the height of the truck, and therefore when the two indexes are compared, a judgment value a 12 = 3 (usually, a 1-9 scale method is adopted, 1 indicates that the two indexes are equally important, 3 indicates that one index is slightly more important than the other index, and so on) is given, and at the same time a 21 = ; in this way, the judgment matrix A of the indexes in the criterion layer is constructed:

[0031] The weight of each index in the criterion layer is determined according to the judgment matrix, and consistency check is performed; the relative importance weight of each index in the criterion layer is determined, and the rationality and consistency of the judgment is ensured through the consistency check, so as to avoid an incorrect judgment result; the comprehensive evaluation score of each over-sea passage is obtained by comprehensively considering the weight of each index, and the optimal over-sea passage is obtained.

[0032] As an optional implementation, according to the position of the over-sea truck, a corresponding optimal parking space is allocated for the over-sea truck, including: An internal map of the parking lot is acquired, and the idle parking spaces of the internal map are identified to construct an idle parking space data set; According to the position of the over-sea truck, the routes of the over-sea truck and each idle parking space in the idle parking space data set are analyzed, and the best navigation route is screened out, and the optimal parking space is screened out according to the best navigation route; The best navigation route and the position of the optimal parking space are sent to the driver of the over-sea truck.

[0033] Specifically, by acquiring the internal map of the parking lot, the overall layout of the inside of the parking lot can be understood, including the position of each parking space, the direction of the passage, the distribution of the parking spaces, the position of the entrance and exit, and the like; the idle parking spaces are identified and a data set is constructed; then the routes of the truck to each idle parking space are analyzed, and factors such as route length and time consumption can be considered to screen out the best navigation route, which can ensure that the truck reaches the parking space in the most efficient way; the optimal parking space is screened out according to the best navigation route, which further optimizes the result of the allocation of the parking space, so that the allocated parking space is not only idle, but also the truck can reach it conveniently and quickly; finally, the best navigation route and the position of the optimal parking space are sent to the driver, which improves the actual application efficiency of the allocation of the parking space.

[0034] As an optional implementation, an internal map of the parking lot is acquired, the idle parking spaces of the internal map are identified, and an idle parking space data set is constructed, including: obtaining an internal map of the parking lot; collecting a monitoring video data stream inside the parking lot, performing frame processing on the monitoring video data stream to obtain a monitoring image data set, and using an image recognition model constructed based on YOLO-V8 to perform image recognition on the monitoring image data set to obtain an idle parking space recognition result; constructing an idle parking space data set according to the idle parking space recognition result.

[0035] Specifically, the image recognition model constructed based on YOLO-V8 is used to recognize the monitoring image data set, which can quickly and accurately detect the idle parking space in the image. The idle parking space recognition result obtained by image recognition is used to construct an idle parking space data set, which contains detailed information of all idle parking spaces, such as parking space number and position coordinates.

[0036] As an optional implementation, routes of the cross-harbor truck and each idle parking space in the idle parking space data set are analyzed to obtain a best navigation route, including: calculating distances between the cross-harbor truck and each idle parking space in the idle parking space data set to obtain a first route data set; sorting all routes in the first route data set according to distance to obtain a sorting result of all routes; filtering the first route data set according to the sorting result to obtain a second route data set, and calculating time consumption results of all routes in the second route data set; analyzing road congestion of the second route data set to obtain a road congestion result; performing weighted calculation according to the time consumption results of all routes and the road congestion result, and filtering a best navigation route according to a weighted calculation result.

[0037] Specifically, the route distance between each idle parking space and the cross-harbor truck in the idle parking space data set can be obtained through the map of the area where the cross-harbor truck is located. Since there are multiple routes between each idle parking space and the cross-harbor truck, the idle parking space data set contains multiple idle parking spaces. The multiple routes of each idle parking space are sorted in ascending order of distance, and the three shortest routes of each idle parking space are selected according to the sorting result. The selected routes of each idle parking space are used to construct a second route data set, that is, each idle parking space in the second route data set includes three selected routes. According to the route information in the second route data set, combined with the road speed limit information, the theoretical time consumption of all routes in the second route data set is calculated. The road congestion situation in the second route data set is analyzed to obtain the road congestion result. By considering the route distance, route time consumption and road congestion situation, the advantages and disadvantages of each route can be evaluated comprehensively, and the best navigation route is finally selected.

[0038] As an optional implementation, the analyzing the road congestion situation in the route data set to obtain the road congestion result comprises: obtaining time sequence data information of the cross-harbor truck, the time sequence data information comprising GPS position information, driving direction information and vehicle state information of the cross-harbor truck; analyzing the behavior of the cross-harbor truck based on the time sequence data information to establish comprehensive behavior characteristics of the cross-harbor truck; analyzing the behavior correlation between the cross-harbor truck and adjacent cross-harbor trucks based on the comprehensive behavior characteristics of the cross-harbor truck to obtain a correlation result; obtaining the road congestion result according to the correlation result.

[0039] Specifically, vehicle data information recorded by the cross-harbor truck connected to the Internet of Vehicles in time sequence can be obtained through the Internet of Vehicles technology. The vehicle data information includes GPS position information, driving direction information and vehicle state information of the cross-harbor truck. The GPS position information of the cross-harbor truck can be obtained through GPS. The driving direction information can be determined by a direction sensor. The vehicle state data information includes speed information, acceleration information and brake state information, which can be collected by a vehicle-mounted sensor. The comprehensive behavior characteristics of the cross-harbor truck are constructed according to the time sequence data information. The comprehensive behavior characteristics include speed characteristics, acceleration characteristics, brake duration characteristics and driving direction characteristics. Then, adjacent trucks are identified. The spatial distance between the trucks is calculated using the Euclidean distance formula according to the GPS position information of the trucks. If the calculated spatial distance is less than a set distance threshold, they are considered to be adjacent trucks. The calculation formula of the Euclidean distance is:

[0040] wherein, and are the GPS coordinates of two over-sea trucks at a certain moment, respectively.

[0041] Then, the Pearson correlation coefficient is used to calculate the correlation of the comprehensive behavior characteristics between the adjacent trucks. The calculated correlation coefficient has a value range of [-1, 1], and when the calculated correlation coefficient is greater than 0, it indicates that the comprehensive behavior characteristics of the two trucks are positively correlated, that is, the change trends of the behavior characteristics such as speed, acceleration, brake duration and driving direction of the two trucks are similar; when the calculated correlation coefficient is less than 0, it indicates that the comprehensive behavior characteristics of the two trucks are negatively correlated, that is, the change trends of part of the behavior characteristics of the two trucks are opposite; the closer the absolute value is to 1, the stronger the correlation of the comprehensive behavior characteristics of the two trucks is; the closer the absolute value is to 0, the weaker the correlation is; and the congestion condition is judged according to the calculated correlation coefficient.

[0042] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application. The protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A digital vehicle depot collaborative reservation management system for cross-sea freight trucks, characterized in that, include: The judgment module is used to obtain the truck driver's chat history, process the chat history, and determine whether to generate truck crossing reservation information based on the processing result. The configuration module is used to configure multi-dimensional indicators and cargo category indicators based on the truck crossing reservation information, and to configure the crossing channel based on the multi-dimensional indicators and cargo category indicators, so as to allocate the optimal crossing channel for the truck crossing the sea. The cross-sea freight truck scheduling module allocates the corresponding optimal parking space to the cross-sea freight trucks based on their locations.

2. The digital vehicle depot collaborative cross-sea freight truck reservation management system according to claim 1, characterized in that, This process involves obtaining chat logs from truck drivers, processing these logs, and determining whether to generate a truck sea crossing reservation based on the processing result. The process includes: Retrieve text messages from the WeChat groups of companies where truck drivers are located; Large model entity recognition technology is used to extract and parse the content of the text message to determine whether the text message contains basic information. If it contains basic information, truck crossing reservation information is generated. If the text message does not contain basic information, the text message is determined to be a casual chat message, and intent analysis is performed on the casual chat message.

3. The digital vehicle depot collaborative cross-sea freight truck reservation management system according to claim 2, characterized in that, If basic information is included, truck crossing reservation information will be generated, which also includes: If the text message contains basic information, it is further determined whether it contains additional information. If the text message contains the additional information, a truck crossing reservation information is generated. If the text message does not contain the additional information, the truck driver is reminded to supplement the additional information. After the truck driver supplements the additional information, a truck crossing reservation information is generated. The basic information includes: departure port, reservation time, and vehicle license plate number; The additional information includes: driver's name, cargo, truck type, names of accompanying persons, and ID information of accompanying persons.

4. The digital vehicle depot collaborative cross-sea freight truck reservation management system according to claim 2, characterized in that, If the text message does not contain basic information, the text message is determined to be a casual chat message, and intent analysis is performed on the casual chat message, including: Set a time window, and build an intent recognition model based on BERT for text messages within the time window; The text message is input into the intent recognition model, which outputs the intent category and confidence level corresponding to the text message to determine the driver's intent. The corresponding RPA process is invoked according to the driver's intention; if the same RPA process identifier appears within the time window, it will not be invoked repeatedly.

5. The digital vehicle depot collaborative cross-sea freight truck reservation management system according to claim 3, characterized in that, The configuration module includes a multi-dimensional indicator configuration unit, a cargo configuration unit, and a channel configuration unit; The multi-dimensional indicator configuration unit is used to construct multi-dimensional indicators based on the truck crossing reservation information; the multi-dimensional indicators include the truck's rated load capacity, truck height, truck category, and cargo category; The cargo configuration unit is used to configure cargo categories through a historical cargo classification mapping table and construct cargo category indicators; The channel configuration unit is used to construct a decision tree model, perform decision analysis based on the decision tree model, and configure the sea crossing channel for the sea-crossing freight truck.

6. The digital vehicle depot collaborative cross-sea freight truck reservation management system according to claim 5, characterized in that, Decision analysis is performed based on the decision tree model to configure the sea-crossing channel for the freight trucks, including: A hierarchical structure model is constructed using the analytic hierarchy process (AHP) to generate a judgment matrix. The weights of the multidimensional indicators and the cargo category indicators are determined based on the judgment matrix, and a consistency check is performed to obtain the optimal sea crossing channel for the sea-crossing freight trucks.

7. The digital vehicle depot collaborative cross-sea freight truck reservation management system according to claim 1, characterized in that, Based on the location of the cross-sea freight trucks, allocate corresponding optimal parking spaces to them, including: Obtain an internal map of the parking lot, identify available parking spaces on the internal map, and construct an available parking space dataset; Based on the location of the cross-sea truck, the routes between the cross-sea truck and each available parking space in the available parking space dataset are analyzed, the best navigation route is selected, and the optimal parking space is selected based on the best navigation route. The optimal navigation route and the optimal parking space location are sent to the truck driver crossing the sea.

8. A digital vehicle depot collaborative cross-sea freight truck reservation management system according to claim 7, characterized in that, Obtain an internal map of the parking lot, identify available parking spaces on the internal map, and construct an available parking space dataset, including: Get the internal map of the parking lot; The system collects surveillance video data streams from inside the parking lot, performs frame-by-frame processing on the surveillance video data streams to obtain a surveillance image dataset, and uses an image recognition model based on YOLO-V8 to perform image recognition on the surveillance image dataset to obtain the vacant parking space recognition result. Based on the results of the vacant parking space identification, a dataset of vacant parking spaces is constructed.

9. A digital vehicle depot collaborative cross-sea freight truck reservation management system according to claim 7, characterized in that, The routes between the cross-sea freight trucks and each available parking space in the available parking space dataset are analyzed, and the optimal navigation routes are selected, including: Calculate the distance between the cross-sea freight truck and each available parking space in the available parking space dataset to obtain the first route dataset; Sort all routes in the first route dataset according to their distance to obtain the sorted results of all routes; The first route dataset is filtered according to the sorting results to obtain the second route dataset, and the time consumption results of all routes in the second route dataset are calculated. The road congestion situation in the second route dataset is analyzed to obtain the road congestion results; The optimal navigation route is obtained by weighting the time taken for all routes and the road congestion results, and then filtering based on the weighted calculation results.

10. A digital vehicle depot collaborative cross-sea freight truck reservation management system according to claim 7, characterized in that, The analysis of road congestion in the route dataset yields road congestion results, including: The time-series data information of the cross-sea freight truck is obtained, including the GPS location information, driving direction information, and vehicle status information of the cross-sea freight truck. The behavior of the cross-sea freight trucks is analyzed based on the time-series data information to establish comprehensive behavioral characteristics of the cross-sea freight trucks; Based on the comprehensive behavioral characteristics of the cross-sea freight trucks, a behavioral correlation analysis was conducted between the cross-sea freight trucks and adjacent cross-sea freight trucks to obtain the correlation analysis results. The road congestion results are obtained based on the correlation results.

Images