Traffic transportation scheduling platform based on visual large model

Abstract

The invention relates to the field of traffic transportation scheduling, in particular to a traffic transportation scheduling platform based on a visual large model, an image recognition module receives matching qualification information sent by the visual large model, and a display module displays vehicle and cargo positioning information generated by the image recognition module. The display module receives information sent by the image recognition module, and the handheld display device receives the information of the display module and pushes the information to a cargo owner and a driver, so that the cargo owner and the driver compare the information of the handheld display device with the information of the big data matching model and the visual big model. And the matching precision of cargo vehicle types is further improved.

Description

Technical Field

[0001] The present disclosure relates to the field of transportation scheduling, and more particularly, to a transportation scheduling platform based on a visual large model. Background Art

[0002] Transportation is an engineering field that studies the layout and construction of railway, highway, waterway and air transportation infrastructure, vehicle operation engineering, traffic information engineering and control, and transportation operations and management; among these, highway transportation is one of the most complex usage scenarios.

[0003] In addition to relying on a system that matches vehicles and cargo, existing road transportation also requires a more accurate platform to achieve a balance and scheduling between the supply and demand of vehicles and cargo. However, the existing system platform only focuses on the preliminary work of matching vehicles and cargo, that is, consumers themselves evaluate the volume and weight of the cargo to measure the required vehicle model. This will undoubtedly lead to relatively large errors, which in turn leads to problems such as truck drivers making wasted trips and wasting consumers' time. In response to this, the present invention proposes a transportation scheduling platform based on a large visual model. Summary of the Invention

[0004] In view of this, the embodiments of the present application provide at least one transportation scheduling platform based on a visual large model, which includes: The vehicle information acquisition module is used to obtain vehicle information, real-time vehicle photos, and vehicle model and frame number generated by the information collection platform, and record relevant information about the vehicle driver; The address positioning module is used to receive the signal from the information collection platform. The address positioning module locates the driver's position based on the signal and the mobile phone positioning system, and combines the uploaded vehicle frame number and real-time vehicle photos to perform secondary calibration on the driver's position; An image recognition module is used to receive a real-time photo of the vehicle and the positioning information sent by the address positioning module, and to match and calibrate the road image content of the real-time photo with the road information content of the positioning information; a display module configured to receive the address information sent by the image recognition module, the information collection platform configured to receive the address information sent by the display module, the vehicle information collection platform transmitting the relevant address information to a handheld display device, and the handheld display device displaying the vehicle location and street information; The cargo information module is used to receive cargo information sent by the information collection platform. The information collected by the cargo owner includes cargo type, volume, weight, photo, origin location, and destination location. The big data matching model is used to receive relevant information from the cargo information module, the vehicle information acquisition module, and the display module, and match the appropriate cargo model based on the relevant information. The big data matching model sends the cargo model information results to the handheld display device, and the cargo owner and the driver conduct preliminary mutual evaluation based on the received display information; The visual big model is used to receive preliminary mutual evaluation information from the big data matching model. If the preliminary mutual evaluation information is qualified, the vehicle driver can choose to accept or reject the order based on the result. If the preliminary mutual evaluation information is unqualified, the big data matching model will re-intervene in the evaluation and further match the order based on the specific reasons for the failure until it passes. The image recognition module receives the matching qualified information sent by the visual large model, the display module displays the positioning information of the vehicle and cargo generated by the image recognition module, the display module receives the information sent by the image recognition module, and the handheld display device receives the information of the display module and pushes it to the cargo owner and the driver. Therefore, at this time, the cargo owner and the driver compare the information of the handheld display device with the big data matching model and the visual large model, thereby further improving the matching accuracy of the cargo model.

[0005] According to one aspect of an embodiment of the present disclosure, the vehicle information acquisition module includes a login unit, an information storage unit, and a face verification and recognition unit. The relevant information of the vehicle driver includes the driver's identity information, contact information, residential address, and vehicle storage location.

[0006] According to an example of an embodiment of the present disclosure, the cargo information module includes a cargo classification unit, an evaluation unit, an origin location unit, and a destination location unit.

[0007] According to an example of an embodiment of the present disclosure, the road image of the real-time photo in the image recognition module includes road information, and the road information content is generated based on the information collection system of the handheld external device. After the image recognition module receives the real-time photo of the vehicle for the first time and receives the positioning position information issued by the address positioning module, the image recognition module issues instructions for uploading the vehicle information for the second and multiple times based on the clarity of the photo and the accuracy of the positioning of the address positioning module.

[0008] According to an example of an embodiment of the present disclosure, the handheld display devices in the big data matching model are mobile phones and tablets, and there are multiple of them.

[0009] According to an example embodiment of the present disclosure, the method further includes: the vehicle models in the vehicle frame number are divided into small trucks, medium trucks, and large trucks based on load capacity, and are divided into 3.6 meters, 4.2 meters, and 6.8 meters based on size. The frame number is the vehicle identification code (VIN), which is the abbreviation of Vehicle Identification Number. Because the ASE standard stipulates that the VIN code consists of 17 characters, it is commonly known as the 17-digit code. Correctly interpreting the VIN code is very important for correctly identifying the vehicle model and performing correct diagnosis and repair. The vehicle identification code is the vehicle's ID number, which is determined according to national vehicle management standards and includes information such as the vehicle's manufacturer, year, model, body type and code, engine code, and assembly location. New driving licenses generally print the VIN code in the "Frame Number" column.

[0010] According to an example of an embodiment of the present disclosure, the cargo classification unit assumes that cargo is divided into n categories, each category has a corresponding number . Can be identified using a classification and coding system; The evaluation units include the volume compatibility and weight compatibility between the cargo and the vehicle type; Volume adaptability: Assuming the length, width, and height of the vehicle's cargo space are L1, W1, and H1 respectively, and the length, width, and height of the cargo are L2, W2, and H2 respectively, the vehicle's cargo space volume is V1=L1xW1xH1, and the cargo volume is V2=L2xW2xH2; Volume adaptation rate R1 = V2 / V1. When R1 ≤ 1, the cargo is compatible in terms of volume and can be loaded into the vehicle type. When R1 > 1, it indicates incompatibility. Weight adaptability: Assuming the rated load capacity of the vehicle model is W1 and the total weight of the cargo is W2, the weight adaptation rate R2=W2 / W1. When R2≤1, the cargo weight and vehicle load are compatible, otherwise they are not compatible.

[0011] The present application at least includes the following beneficial effects: the image recognition module provided by the present application receives the matching qualified information issued by the visual large model, the display module displays the positioning information of the vehicle and cargo generated by the image recognition module, the display module receives the information issued by the image recognition module, and the handheld display device receives the information of the display module and pushes it to the cargo owner and the driver. Therefore, at this time, the cargo owner and the driver compare the information of the handheld display device with the big data matching model and the information of the visual large model, thereby further improving the matching accuracy of the cargo model.

[0012] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory, and do not limit the technical solutions of the present application. DETAILED DESCRIPTION

[0013] The following will be combined with the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the embodiments described are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0014] Vision models use convolutional neural networks (CNNs), which are very good at recognizing images. Vision models have multiple layers that process visual information in a manner similar to how humans see. Each layer extracts different features from the image; during training, the model is fed a large dataset of labeled images, allowing it to learn and refine its parameters through backpropagation. This extensive training process enables the model to generalize well across a wide range of vision tasks, from object recognition to scene understanding. Vision models are structured in layers that gradually extract features, starting with simple ones like edges and textures and moving on to more complex shapes and patterns. They also use attention mechanisms to focus on important parts of an image, similar to how humans pay attention. Furthermore, they often employ transfer learning, in which a model trained on one task is adapted to perform on a related task. This results in faster training and better performance, making vision models highly efficient.

[0015] A transportation scheduling platform based on a large visual model, the platform comprising: The vehicle information acquisition module is used to obtain vehicle information, real-time vehicle photos, and vehicle model and frame number generated by the information collection platform, and record relevant information about the vehicle driver; The address positioning module is used to receive signals from the information collection platform. The address positioning module locates the driver's position based on the signals and the mobile phone positioning system, and combines the uploaded vehicle frame number and real-time vehicle photos to perform secondary calibration of the driver's position; An image recognition module is used to receive a real-time photo of the vehicle and the positioning information sent by the address positioning module, and to match and calibrate the road image content of the real-time photo with the road information content of the positioning information; The display module is used to receive the address information sent by the image recognition module. The information collection platform is used to receive the address information sent by the display module. The vehicle information collection platform transmits the relevant address information to the handheld display device, and the handheld display device displays the vehicle location and street information; The cargo information module is used to receive cargo information from the information collection platform. The information collected by the cargo owner includes cargo type, volume, weight, photos, origin and destination locations. The big data matching model is used to receive relevant information from the cargo information module, the vehicle information acquisition module, and the display module, and match the appropriate cargo model based on the relevant information. The big data matching model sends the cargo model information results to the handheld display device, and the cargo owner and the driver conduct preliminary mutual evaluation based on the received display information; The visual big model is used to receive preliminary mutual evaluation information from the big data matching model. If the preliminary mutual evaluation information is qualified, the vehicle driver can choose to accept or reject the order based on the result. If the preliminary mutual evaluation information is unqualified, the big data matching model will re-intervene in the evaluation and further match the order based on the specific reasons for the failure until it passes. The image recognition module receives the matching qualified information sent by the visual large model, and the display module displays the positioning information of the vehicle and cargo generated by the image recognition module. The display module receives the information sent by the image recognition module, and the handheld display device receives the information of the display module and pushes it to the cargo owner and the driver. Therefore, at this time, the cargo owner and the driver compare the information of the handheld display device with the big data matching model and the information of the visual large model to further improve the matching accuracy of the cargo model.

[0016] According to one aspect of an embodiment of the present disclosure, a vehicle information acquisition module is provided, including a login unit, an information storage unit, and a face verification and recognition unit. The relevant information of the vehicle driver includes the driver's identity information, contact information, residential address, and vehicle storage location.

[0017] According to an example of an embodiment of the present disclosure, the cargo information module includes a cargo classification unit, an evaluation unit, an origin location unit, and a destination location unit.

[0018] According to an example of an embodiment of the present disclosure, the road image of the real-time photo in the image recognition module includes road information, and the road information content is generated based on the information collection system of the handheld external device. After the image recognition module receives the real-time photo of the vehicle for the first time and receives the positioning position information issued by the address positioning module, the image recognition module issues instructions for uploading the vehicle information for the second and multiple times based on the clarity of the photo and the accuracy of the positioning of the address positioning module.

[0019] According to an example of an embodiment of the present disclosure, the handheld display devices in the big data matching model are mobile phones and tablets, and there are multiple of them.

[0020] According to an example of an embodiment of the present disclosure, the method further includes: the vehicle model in the vehicle frame number is divided into small trucks, medium trucks, and large trucks according to load capacity, and is divided into 3.6 meters, 4.2 meters, and 6.8 meters according to size. The frame number is the vehicle identification code (VIN), which is the abbreviation of Vehicle Identification Number in English. Because the ASE standard stipulates that the VIN code consists of 17 characters, it is commonly known as the 17-digit code. Correctly interpreting the VIN code is very important for us to correctly identify the vehicle model and perform correct diagnosis and repair. The vehicle identification code is the vehicle's ID number. It is determined according to national vehicle management standards and contains information such as the vehicle's manufacturer, year, model, body type and code, engine code, and assembly location. New driving licenses generally print the VIN code in the "Frame Number" column.

[0021] According to an example of an embodiment of the present disclosure, the cargo classification unit assumes that the cargo is divided into n categories, each category has a corresponding number . Can be identified using a classification and coding system; The evaluation units include the volume compatibility and weight compatibility between the cargo and the vehicle type; Volume adaptability: Assuming the length, width, and height of the vehicle's cargo space are L1, W1, and H1 respectively, and the length, width, and height of the cargo are L2, W2, and H2 respectively, the vehicle's cargo space volume is V1=L1xW1xH1, and the cargo volume is V2=L2xW2xH2; Volume adaptation rate R1 = V2 / V1. When R1 ≤ 1, the cargo is compatible in terms of volume and can be loaded into the vehicle type. When R1 > 1, it indicates incompatibility. Weight adaptability: Assuming the rated load capacity of the vehicle model is W1 and the total weight of the cargo is W2, the weight adaptation rate R2=W2 / W1. When R2≤1, the cargo weight and vehicle load are compatible, otherwise they are not compatible.

[0022] The present application at least includes the following beneficial effects: the image recognition module provided by the present application receives the matching qualified information sent by the visual large model, the display module displays the positioning information of the vehicle and cargo generated by the image recognition module, the display module receives the information sent by the image recognition module, the handheld display device receives the information of the display module and pushes it to the cargo owner and the driver. Therefore, at this time, the cargo owner and the driver compare the information of the handheld display device with the big data matching model and the information of the visual large model to further improve the matching accuracy of the cargo model.

[0023] In order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions of the present application are further elaborated in detail below in conjunction with the embodiments. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. In the following description, "optional implementation methods" are involved, which describe a subset of all possible embodiments, but it can be understood that "optional implementation methods" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first / second" involved are merely to distinguish similar objects and do not represent a specific order for the objects. It can be understood that "first / second" can be interchanged with a specific order or sequence where permitted. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of this application. The terms used herein are only for the purpose of describing the present application and are not intended to limit the present application.

[0024] It should be noted that the object information (including but not limited to the object's device information, corresponding personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the object or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0025] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0026] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification. The above-mentioned embodiments only express several implementation methods of the present application. The description is relatively specific and detailed, but it cannot be understood as a limitation on the scope of the patent of this application. It should be pointed out that for ordinary technicians in this field, without departing from the concept of this application, several variations and improvements can be made, which all fall within the scope of protection of this application. Therefore, the scope of protection of this application should be based on the attached claims.

Claims

1. A transportation scheduling platform based on a large visual model, characterized by: The platform includes: The vehicle information acquisition module is used to obtain vehicle information, real-time vehicle photos, and vehicle model and frame number generated by the information collection platform, and record relevant information about the vehicle driver; The address positioning module is used to receive the signal from the information collection platform. The address positioning module locates the driver's position based on the signal and the mobile phone positioning system, and combines the uploaded vehicle frame number and real-time vehicle photos to perform secondary calibration on the driver's position; An image recognition module is used to receive a real-time photo of the vehicle and the positioning information sent by the address positioning module, and to match and calibrate the road image content of the real-time photo with the road information content of the positioning information; a display module configured to receive the address information sent by the image recognition module, the information collection platform configured to receive the address information sent by the display module, the vehicle information collection platform transmitting the relevant address information to a handheld display device, and the handheld display device displaying the vehicle location and street information; The cargo information module is used to receive cargo information sent by the information collection platform. The information collected by the cargo owner includes cargo type, volume, weight, photo, origin location, and destination location. The big data matching model is used to receive relevant information from the cargo information module, the vehicle information acquisition module, and the display module, and match the appropriate cargo model based on the relevant information. The big data matching model sends the cargo model information results to the handheld display device, and the cargo owner and the driver conduct preliminary mutual evaluation based on the received display information; The visual big model is used to receive preliminary mutual evaluation information from the big data matching model. If the preliminary mutual evaluation information is qualified, the vehicle driver can choose to accept or reject the order based on the result. If the preliminary mutual evaluation information is unqualified, the big data matching model will re-intervene in the evaluation and further match the order based on the specific reasons for the failure until it passes. The image recognition module receives the matching qualified information sent by the visual large model, the display module displays the positioning information of the vehicle and cargo generated by the image recognition module, the display module receives the information sent by the image recognition module, and the handheld display device receives the information of the display module and pushes it to the cargo owner and the driver. Therefore, at this time, the cargo owner and the driver compare the information of the handheld display device with the big data matching model and the visual large model, thereby further improving the matching accuracy of the cargo model.

2. A transportation scheduling platform based on a visual large model according to claim 1, characterized in that: The vehicle information acquisition module includes a login unit, an information storage unit, and a face verification and recognition unit. The relevant information of the vehicle driver includes the driver's identity information, contact information, residential address, and vehicle storage location.

3. The transportation scheduling platform based on a visual large model according to claim 1 is characterized by: The cargo information module includes a cargo classification unit, an evaluation unit, a starting point positioning unit, and a destination positioning unit.

4. The transportation scheduling platform based on a visual large model according to claim 1 is characterized by: The road image of the real-time photo in the image recognition module includes road information, and the road information content is generated based on the information collection system of the handheld external device. After the image recognition module receives the real-time photo of the vehicle for the first time and the positioning position information sent by the address positioning module, the image recognition module issues instructions for uploading the vehicle information for the second and multiple times based on the clarity of the photo and the accuracy of the positioning by the address positioning module.

5. The transportation scheduling platform based on a visual large model according to claim 1 is characterized by: The handheld display devices in the big data matching model are mobile phones and tablets, and there are multiple of them.

6. The transportation scheduling platform based on a visual large model according to claim 1 is characterized by: The vehicle model frame number is divided into small trucks, medium trucks, and large trucks according to load capacity, and divided into 3.6 meters, 4.2 meters, and 6.8 meters according to size. The frame number is the vehicle identification code; The Vehicle Identification Number (VIN) is the vehicle's identification number. It's determined according to national vehicle management standards and includes information such as the vehicle's manufacturer, year, model, body type and code, engine code, and assembly location. New vehicle license plates typically have the VIN number printed in the "Vehicle Frame Number" column.

7. The transportation scheduling platform based on a visual large model according to claim 3 is characterized by: The cargo classification unit assumes that cargo is divided into n categories, each category has a corresponding number . Can be identified using a classification and coding system; The evaluation units include the volume compatibility and weight compatibility between the cargo and the vehicle type; Volume adaptability: Assuming the length, width, and height of the vehicle's cargo space are L1, W1, and H1 respectively, and the length, width, and height of the cargo are L2, W2, and H2 respectively, the vehicle's cargo space volume is V1=L1xW1xH1, and the cargo volume is V2=L2xW2xH2; Volume adaptation rate R1 = V2 / V1. When R1 ≤ 1, the cargo is compatible in terms of volume and can be loaded into the vehicle type. When R1 > 1, it indicates incompatibility. Weight adaptability: Assuming the rated load capacity of the vehicle model is W1 and the total weight of the cargo is W2, the weight adaptation rate R2=W2 / W1. When R2≤1, the cargo weight and vehicle load are compatible, otherwise they are not compatible.