Intelligent vehicle and goods matching method and system based on user feature attribute set

Abstract

The invention relates to the field of logistics matching, in particular to an intelligent vehicle and goods matching method and system based on a user feature attribute set, the method is used for vehicle and goods matching of dangerous chemicals, and specifically, the method comprises the steps of firstly defining goods labels of the dangerous chemicals, and binding corresponding first attribute vectors to the goods labels; the method comprises the following steps: firstly, defining a plurality of vehicle owners, then defining vehicle owner labels of the plurality of vehicle owners, binding corresponding second attribute vectors to the vehicle owner labels, then, calculating the similarity between the first attribute vectors and the second attribute vectors by adopting a cosine similarity algorithm, and finally, selecting a dangerous chemical with the highest similarity as the optimal transportation cargo of the corresponding vehicle owner. Compared with the prior art, a matching result obtained based on the method is more reliable, the safety is higher, and the method is more suitable for vehicle-cargo matching of dangerous chemicals.

Description

Technical Field

[0001] The present invention relates to the field of logistics matching. More specifically, the present invention relates to an intelligent vehicle-cargo matching method and system based on a user feature attribute set. Background Art

[0002] In the field of logistics and transportation, vehicle-cargo matching refers to the process of matching cargo characteristics to optimally match freight vehicles. This approach ensures that goods are delivered to their destinations as quickly or economically as possible. A Chinese patent application, publication number CN118863697A, discloses a method for intelligent management and monitoring of online freight transport. This method primarily achieves vehicle-cargo matching by calculating the matching degree between the cargo and the truck based on the matching weights between the cargo and the truck.

[0003] Hazardous chemicals are those listed in the "Catalogue of Hazardous Chemicals (2022 Edition)" and marked as "highly toxic." These chemicals must strictly adhere to relevant regulations throughout their production, storage, use, transportation, and sales. During transportation, multidimensional data, including the chemical's suitable storage temperature, humidity, pressure / air pressure, shelf life, and degree of hazard, must be considered. Generally, the aforementioned method cannot be used for vehicle-cargo matching. This is due to flaws in the algorithmic core for processing multidimensional data. The configuration of its weight parameters relies primarily on the local outlier factor (used to calculate vehicle-cargo distance). Consequently, the resulting matched vehicles often fail to meet the required qualifications, which can easily lead to safety incidents.

[0004] Therefore, the existing vehicle-cargo matching technology has the problem of poor safety when it comes to the transportation of highly toxic chemicals. Summary of the Invention

[0005] In order to solve the above-mentioned technical problem of poor security, the present invention discloses an intelligent vehicle-cargo matching method and system based on a user feature attribute set.

[0006] In a first aspect, the present invention discloses an intelligent vehicle-cargo matching method based on a user feature attribute set, which is used for vehicle-cargo matching of hazardous chemicals. The method of the present invention comprises: Define cargo labels for hazardous chemicals and bind the corresponding first attribute vector to the cargo labels; Define multiple owner tags for each car owner and bind the corresponding second attribute vector to each owner tag. Using the cosine similarity algorithm, calculate the similarity between the first attribute vector and the second attribute vector; The hazardous chemicals with the highest similarity are selected as the optimal transport cargo for the corresponding vehicle owner.

[0007] Beneficial Effects: By defining corresponding tags for hazardous chemicals and vehicle owners and binding corresponding vectors to these tags, data standardization of hazardous chemical and vehicle owner information is achieved, facilitating accurate matching in subsequent steps. A cosine similarity algorithm is used to calculate the similarity between the first attribute vector and the second attribute vector, which serves as a criterion for assessing the reliability of the vehicle owner in transporting the corresponding hazardous chemical. The hazardous chemical with the highest similarity is selected as the optimal transport cargo for the corresponding vehicle owner, thereby matching the vehicle owner with the most suitable transport cargo for the hazardous chemical. Compared to existing technologies, this method is more suitable for matching vehicles and cargo for hazardous chemical transportation and offers greater security.

[0008] Preferably, the hazardous chemicals with the highest similarity are selected as the optimal transport cargo, including: Based on multiple similarities, a similarity preference matrix is ​​constructed; Among them, the row attribute label of the similarity preference matrix is ​​the owner label, and the column attribute label of the similarity preference matrix is ​​the cargo label; Traverse the similarities between all vehicle owner labels and all cargo labels, and for each vehicle owner, select the hazardous chemicals with the highest similarity as the optimal transport cargo.

[0009] Beneficial Effect: By constructing a similarity preference matrix, vehicle-cargo matching can be achieved quickly. Compared with existing technologies, the matching method of this solution is simpler, more reliable, and faster.

[0010] Preferably, the cosine similarity algorithm is specifically:

[0011] Where, Represents the cosine similarity calculation function, Represents the first attribute vector corresponding to the cargo label, Represents the second attribute vector corresponding to the owner label, Indicates the L2 norm of the vector. Represents the first attribute vector and the second attribute vector similarity.

[0012] Beneficial effects: The above algorithm is more suitable for multi-dimensional feature matching and has stronger data expansion capabilities, and is suitable for hazardous chemicals with more attribute data.

[0013] Preferably, defining a cargo label for hazardous chemicals and binding the cargo label with a corresponding first attribute vector includes: Extract multidimensional features of cargo owners and hazardous chemicals and construct a multidimensional feature set; defining a cargo label in a multidimensional feature set, and extracting a first attribute vector from the multidimensional feature set; Bind the corresponding first attribute vector to the product label.

[0014] Furthermore, the cargo label uses the ID of the hazardous chemical, and the first attribute vector includes at least the type of hazardous chemical, refrigeration attribute, weight, volume and cargo owner's requirements.

[0015] Preferably, defining owner tags for multiple car owners and binding corresponding second attribute vectors to the owner tags includes: Extract multi-dimensional features of multiple car owners and construct a feature resource attribute set; Define a vehicle owner tag in the feature resource attribute set, and extract a second attribute vector from the feature resource attribute set; Bind the corresponding second attribute vector to the owner label.

[0016] Preferably, the vehicle owner tag adopts the vehicle type, and the second attribute vector includes at least load, volume and refrigeration coefficient.

[0017] Preferably, after selecting the hazardous chemical with the highest similarity as the optimal transport cargo for the corresponding vehicle owner, the method of the present invention further includes: Place hazardous chemicals that shippers need to transport into a free queue and send transportation requests to multiple vehicle owners; In response to receiving the transport request, push text information of the optimal transport cargo to the vehicle owner's preferred transport option; Determine whether the corresponding vehicle owner accepts the most preferred transportation option. If so, send a matching success message to the corresponding cargo owner.

[0018] Beneficial effect: During the process of confirming a vehicle and cargo transportation order, the method of the present invention will push the text information of the optimal transported goods to the corresponding vehicle owner, so as to encourage the optimal vehicle owner to go to the cargo owner to pick up the goods.

[0019] Preferably, after determining whether the corresponding vehicle owner accepts the most preferred transportation option, the method of the present invention further includes: If not, the vehicle owner's label refusing to transport the corresponding hazardous chemicals will be removed; Return to the steps for defining cargo labels for hazardous chemicals.

[0020] Beneficial effect: When a vehicle owner refuses to transport a certain hazardous chemical, the vehicle owner tag corresponding to the hazardous chemical will be removed so that it will no longer be matched with the refusing vehicle owner, thus avoiding repeated matching and repeated push in the subsequent process, thereby improving the matching efficiency of the method of the present invention and reducing the interference of repeated matching data on the vehicle owner.

[0021] In a second aspect, the present invention also discloses an intelligent vehicle-cargo matching system based on a user feature attribute set, comprising a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, the intelligent vehicle-cargo matching method based on a user feature attribute set recorded in the first aspect is implemented.

[0022] The beneficial effects of the present invention are: (1) The method of the present invention defines corresponding labels for hazardous chemicals and vehicle owners, and binds corresponding vectors to the labels, thereby achieving data standardization of hazardous chemical information and vehicle owner information, which is conducive to accurate matching in subsequent steps. The cosine similarity algorithm is used to calculate the similarity between the first attribute vector and the second attribute vector, which is used as a criterion for judging the reliability of the vehicle owner in transporting the corresponding hazardous chemicals. The hazardous chemical with the highest similarity is used as the optimal transport cargo for the corresponding vehicle owner, thereby achieving information matching between the vehicle owner and the most suitable transport cargo for hazardous chemicals. Compared with the existing technology, the method of the present invention is more suitable for matching vehicle and cargo transportation of hazardous chemicals, overcoming the poor safety problem of the existing technology.

[0023] (2) Compared with the existing technology, the method of the present invention constructs a similarity preference matrix to quickly achieve vehicle-cargo matching. This matching method is simpler, more reliable and faster.

[0024] (3) Compared with the existing technology, during the process of confirming the vehicle and cargo transportation order, the method of the present invention will push the text information of the optimal transported goods to the corresponding vehicle owner to encourage the optimal vehicle owner to go to the cargo owner to pick up the goods. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work shall fall within the scope of protection of the present invention.

[0026] Figure 1 This is a flow chart of an intelligent vehicle-cargo matching method based on a user feature attribute set in the first embodiment of the present invention; Figure 2 It is a structural diagram of the intelligent vehicle-cargo matching system based on user feature attribute sets in the second embodiment of the present invention. DETAILED DESCRIPTION

[0027] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0028] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0029] Example 1 like Figure 1 As shown, this embodiment discloses an intelligent vehicle-cargo matching method based on a user feature attribute set, which is used for vehicle-cargo matching of hazardous chemicals. The method of the present invention includes: S10: Define a cargo label for hazardous chemicals and bind the cargo label with a corresponding first attribute vector.

[0030] In this embodiment, the cargo tag can be a unique ID for the hazardous chemical or the consignor's ID. The data in the bound first attribute vector can include the hazardous chemical's name, type, refrigeration requirements, weight, volume, and consignor's requirements. This first attribute vector can be expanded based on actual conditions. Hazardous chemical types include Class I (explosives), Class II (compressed gases and liquefied gases), Class III (flammable liquids), Class IV (flammable solids, self-igniting materials, and materials that ignite when wet), Class V (oxidizers and organic peroxides), Class VI (toxic and infectious materials), Class VII (radioactive materials), Class VIII (corrosive materials), Class IX (miscellaneous items), other hazardous waste (hazardous waste), medical waste (medical waste), other hazardous materials, and general categories.

[0031] S20: Define owner tags for multiple car owners, and bind corresponding second attribute vectors to the owner tags.

[0032] In this embodiment, the owner tag can be the owner's license plate number or vehicle type, and the corresponding second attribute vector includes load capacity, volume, and refrigeration coefficient. The above second attribute vector can be expanded according to actual conditions.

[0033] S30: Calculate the similarity between the first attribute vector and the second attribute vector using a cosine similarity algorithm.

[0034] S40: Select the hazardous chemicals with the highest similarity as the optimal transport cargo for the corresponding vehicle owner.

[0035] Through the above steps S10 to S40, the method of the present invention performs similarity calculations by defining labels for hazardous chemicals and vehicle owners and configuring corresponding attribute vectors. This method is suitable for hazardous chemicals with higher dimensional attributes, and the vehicle-cargo matching results obtained are safer and more reliable.

[0036] Furthermore, the above step S10 is specifically as follows: S11: Extract multidimensional features of cargo owners and hazardous chemicals and construct a multidimensional feature set.

[0037] S12: Define a cargo label in the multidimensional feature set, and extract a first attribute vector from the multidimensional feature set.

[0038] S13: Bind the corresponding first attribute vector to the product label.

[0039] It should be noted that the multidimensional feature set in step S11 is a complex feature set that includes information about the shipper and hazardous chemicals. It includes both data strongly associated with vehicle-cargo matching and data less closely associated with vehicle-cargo matching. To improve matching reliability, step S12 can extract a first attribute vector from the multidimensional feature set based on pre-set filtering rules.

[0040] For example, after the above step S13, the data structure of the cargo label may be: Cargo cargoA=new Cargo(new HashMap<String, Double> () {{ put("load", 6.0); put("volume", 2.0); put("Refrigerated", 1.0); }}) It should be noted that after binding the corresponding first attribute vector to the cargo tag, the resulting data structure only uses numerical values ​​for data items, without units, for ease of calculation. The above example is intended only for hazardous chemical cargoA and does not represent all hazardous chemicals. This example only involves vector data for weight, volume, and refrigeration. In other embodiments, data expansion can be performed using the put() function.

[0041] Furthermore, the above step S20 is specifically as follows: S21: Extract multi-dimensional features of multiple car owners and construct a feature resource attribute set.

[0042] S22: defining a vehicle owner tag in the feature resource attribute set, and extracting a second attribute vector from the feature resource attribute set.

[0043] S23: Bind the corresponding second attribute vector to the owner label.

[0044] It should be noted that the feature resource attribute set in step S21 includes vehicle classification (e.g., flatbed truck, container truck, high-sided van, refrigerated truck, temperature-controlled wing truck, insulated tank truck, iron tank truck, aluminum tank truck, stainless steel tank truck, pressure tank truck, etc.), vehicle length, load capacity, route familiarity, owner location, quote, refrigeration temperature, reputation score, service score, and satisfaction score. It also includes relevant data strongly related to vehicle-cargo matching, as well as data weakly related to vehicle-cargo matching. Step S22 can extract a second attribute vector from the multidimensional feature set based on pre-set filtering rules.

[0045] For example, after the above step S23, the data structure of the owner tag may be: Vehicle truck1 = new Vehicle(new HashMap<String, Double> () {{ put("load", 5.0); put("volume", 3.0); put("Refrigerated", 1.0); }}) It should be noted that the above examples only involve vector data of three dimensions: weight, volume, and refrigeration. In other embodiments, the data dimensions of the cargo label can be adapted and data expansion can be performed through the put() function.

[0046] Furthermore, the cosine similarity algorithm in step S30 is specifically:

[0047] Where, Represents the cosine similarity calculation function, Represents the first attribute vector corresponding to the cargo label, Represents the second attribute vector corresponding to the owner label, Indicates the L2 norm of the vector. Represents the first attribute vector and the second attribute vector similarity.

[0048] For example, the routine may be: System.out.println("Preference Matrix (Vehicle x Cargo):"); System.out.println("\tCargoA\tCargoB\tCargoC"); List <vehicle>vehicles = Arrays.asList(truck1, truck2); List <cargo>cargos = Arrays.asList(cargoA, cargoB, cargoC); for (int i = 0; i <vehicles.size(); i++) { System.out.print("Truck" + (i+1) + "\t"); for (int j = 0; j <cargos.size(); j++) { double score = CosineSimilarity.calculate(vehicles.get(i), cargos.get(j)); System.out.printf("%.3f\t", score); } System.out.println(); } Through the above algorithm, the method of the present invention can quickly calculate the similarity of the shared features between the first attribute vector and the second attribute vector. Compared with existing technologies, the above operation method requires less computing power, has stronger scalability, and has higher data processing efficiency.

[0049] Furthermore, the above step S40 includes: S41: Construct a similarity preference matrix based on multiple similarities.

[0050] S42: Traverse the similarities between all vehicle owner tags and all cargo tags, and select the hazardous chemicals with the highest similarity as the optimal transport cargo for each vehicle owner.

[0051] Among them, the row attribute label of the similarity preference matrix is ​​the owner label, and the column attribute label of the similarity preference matrix is ​​the cargo label.

[0052] For example, the similarity preference matrix can be:

[0053] For example, the corresponding routine may be: for (int i = 0; i <vehicles.size(); i++) { double maxScore = -1; int bestIndex = -1; / / Traverse all goods and find the one with the highest similarity for (int j = 0; j <cargos.size(); j++) { double score = CosineSimilarity.calculate(vehicles.get(i), cargos.get(j)); if (score>maxScore) { maxScore = score; bestIndex = j; } } / / Output the best match System.out.println("Truck" + (i+1) + " Best for transport: " + (bestIndex>=0? cargos.get(bestIndex).getClass().getSimpleName() +(char)('A'+bestIndex) : "No suitable cargo")); } Through the above steps S41 and S42 and the corresponding algorithm improvements, the method of this embodiment can obtain a reliable matching relationship more quickly.

[0054] In order to implement the platform-side application of steps S10 to S40, after step S50, the method of this embodiment further includes: S60: The hazardous chemicals that the shipper needs to transport are placed in a free queue, and transportation requests are sent to multiple vehicle owners.

[0055] It should be explained that when a cargo owner has dangerous chemicals that need to be transported, he or she can input the relevant information of the dangerous chemicals into the platform. The platform will place the information in a free queue according to the order of input and the urgency of transportation, and send transportation requests to the vehicle owners around the cargo owner in chronological order.

[0056] S70: In response to receiving the transport request, push text information of the optimal transport cargo to the most preferred transport option of the corresponding vehicle owner.

[0057] It should be noted that in this implementation, vehicle owners are required to register on the platform in advance and provide relevant information about themselves and their freight vehicles. When a vehicle owner logs in and accepts an order on the platform, they will automatically receive a transport request and will be recommended the optimal transport option.

[0058] S80: Determine whether the corresponding vehicle owner accepts the most preferred transportation option. If so, send a matching success message to the corresponding cargo owner.

[0059] Through the above steps S60 to S80, during the process of confirming the vehicle and cargo transportation order, the method of this embodiment will push the text information of the optimal transported goods to the corresponding vehicle owner to encourage the optimal vehicle owner to go to the cargo owner to pick up the goods, thereby realizing safe and reliable transportation of hazardous chemicals.

[0060] Furthermore, after determining whether the vehicle owner accepts the most preferred transportation option in step S80, the method of this embodiment further includes: If not, the vehicle owner’s label refusing to transport the corresponding hazardous chemicals will be removed.

[0061] Return to the above step S10.

[0062] It should be explained that when a vehicle owner refuses to transport a certain hazardous chemical, the platform will remove the vehicle owner tag corresponding to the hazardous chemical so that it will no longer be matched with the refusing vehicle owner, thereby avoiding repeated matching and repeated push in subsequent processes, improving the matching efficiency of the method of this embodiment, and reducing the interference of repeated matching data on the vehicle owner.

[0063] Furthermore, if the optimal owner agrees to the transport, the information of the agreement can be sent to the cargo owner to confirm whether it is accepted. If so, the transport order is established and the GPS location of the optimal owner is sent to the cargo owner. If not, the owner tag of the rejected owner is removed and the process returns to step S10.

[0064] The above technical solution improvements are helpful for cargo owners to independently select freight vehicle owners and follow up in real time on the location of the vehicle owners they have selected, which effectively improves the flexibility of the method of this embodiment.

[0065] Based on the above technical descriptions, the method of this embodiment has at least the following technical advantages: First, the cosine similarity algorithm quantifies the compatibility of key features between vehicle owners and cargo, achieving the following: It enables multi-dimensional feature matching, overcoming the drawbacks of existing technologies that rely on simple distance and weight data matching (which is less secure). It also offers enhanced scalability; new vehicles or cargo only require updating the corresponding feature database. Similarity scores support priority sorting, enabling objective quantitative evaluation. Additional feature dimensions can be expanded based on actual business needs (such as timeliness requirements and route matching), and feature weights can be optimized through machine learning.

[0066] Secondly, it is more suitable for hazardous chemicals with higher dimensional attributes, and the vehicle-cargo matching results are safer and more reliable.

[0067] Third, the method of this embodiment requires less computing power and has higher data processing efficiency.

[0068] Example 2 like Figure 2 As shown, based on the first embodiment, this embodiment discloses an intelligent vehicle-cargo matching system based on a user feature attribute set. The system of this embodiment includes a processor and a memory. The memory stores computer program instructions. When the computer program instructions are executed by the processor, the intelligent vehicle-cargo matching method based on the user feature attribute set recorded in the first embodiment is implemented.

[0069] The above system also includes other components well known to those skilled in the art, such as a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.

[0070] In the present invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, the computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application, module, or both. Any such computer storage medium can be part of, accessible to, or connectable to a device. Any application or module described in the present invention can be implemented using computer-readable / executable instructions that can be stored or otherwise retained by such a computer-readable medium.

[0071] In the description of this specification, "a plurality of" means at least two, for example, two, three or more, etc., unless otherwise clearly defined.

[0072] While several embodiments of the present invention have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Numerous modifications, variations, and alternatives will occur to those skilled in the art without departing from the concept and spirit of the present invention. It should be understood that various alternatives to the embodiments of the present invention described herein may be employed in practicing the present invention.< / cargo> < / vehicle>

Claims

1. An intelligent vehicle-cargo matching method based on user feature attribute set, characterized in that: For vehicle-cargo matching of hazardous chemicals, the method includes: Defining a cargo label for hazardous chemicals and binding the corresponding first attribute vector to the cargo label; Defining owner tags for multiple car owners and binding corresponding second attribute vectors to the owner tags; Using a cosine similarity algorithm, calculate the similarity between the first attribute vector and the second attribute vector; The hazardous chemicals with the highest similarity are selected as the optimal transport cargo for the corresponding vehicle owner.

2. The intelligent vehicle-cargo matching method based on user feature attribute set according to claim 1 is characterized in that: Select the most similar hazardous chemicals as the optimal transport cargo, including: Based on multiple similarities, a similarity preference matrix is ​​constructed; The row attribute label of the similarity preference matrix is ​​the vehicle owner label, and the column attribute label of the similarity preference matrix is ​​the cargo label; Traverse the similarities between all vehicle owner labels and all cargo labels, and for each vehicle owner, select the hazardous chemicals with the highest similarity as the optimal transport cargo.

3. The intelligent vehicle-cargo matching method based on user feature attribute set according to claim 1 is characterized in that: The cosine similarity algorithm is specifically: Where, Represents the cosine similarity calculation function, Represents the first attribute vector corresponding to the cargo label, Represents the second attribute vector corresponding to the owner label, Indicates the L2 norm of the vector. Represents the first attribute vector and the second attribute vector similarity.

4. The intelligent vehicle-cargo matching method based on user feature attribute set according to claim 1 is characterized in that: Defining a cargo label for hazardous chemicals and binding the corresponding first attribute vector to the cargo label includes: Extract multidimensional features of cargo owners and hazardous chemicals and construct a multidimensional feature set; defining the cargo label in the multidimensional feature set, and extracting the first attribute vector from the multidimensional feature set; Bind the corresponding first attribute vector to the cargo label.

5. The intelligent vehicle-cargo matching method based on user feature attribute set according to claim 4 is characterized in that: The cargo label uses the ID of the hazardous chemical, and the first attribute vector includes at least the type of hazardous chemical, refrigeration attribute, weight, volume and cargo owner's requirements.

6. The intelligent vehicle-cargo matching method based on user feature attribute set according to claim 1 is characterized in that: Defining multiple owner tags for each car owner and binding the corresponding second attribute vector to the owner tags includes: Extract multi-dimensional features of multiple car owners and construct a feature resource attribute set; defining a vehicle owner tag in the feature resource attribute set, and extracting the second attribute vector from the feature resource attribute set; Bind the corresponding second attribute vector to the owner tag.

7. The intelligent vehicle-cargo matching method based on user feature attribute set according to claim 1 is characterized in that: The vehicle owner tag adopts the vehicle type, and the second attribute vector includes at least load, volume and refrigeration coefficient.

8. The intelligent vehicle-cargo matching method based on user feature attribute set according to claim 1 is characterized in that: After selecting the hazardous chemical with the highest similarity as the optimal transport cargo for the corresponding vehicle owner, the method further includes: Place hazardous chemicals that shippers need to transport into a free queue and send transportation requests to multiple vehicle owners; In response to receiving the transport request, pushing the text information of the optimal transport cargo to the most preferred transport options of the corresponding vehicle owner; Determine whether the corresponding vehicle owner accepts the most preferred transportation option, and if so, send a matching success message to the corresponding cargo owner.

9. The intelligent vehicle-cargo matching method based on user feature attribute set according to claim 1 is characterized in that: After determining whether the vehicle owner accepts the most preferred transportation option, the method further includes: If not, the vehicle owner's label refusing to transport the corresponding hazardous chemicals will be removed; Return to the steps for defining cargo labels for hazardous chemicals.

10. An intelligent vehicle-cargo matching system based on user feature attribute sets, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the method implements the intelligent vehicle-cargo matching method based on the user feature attribute set according to any one of claims 1 to 9.

Images