Commercial vehicle goods source searching method, device and equipment and storage medium

Abstract

The invention relates to the technical field of Internet of Vehicles, in particular to a commercial vehicle goods source searching method, device and equipment and a storage medium, and the method comprises the steps: responding to a goods source searching instruction sent by a commercial vehicle user, and collecting vehicle operation data, vehicle positioning data, user behavior data and environment data; determining a vehicle high-dimensional feature vector based on the vehicle operation data, the vehicle positioning data, the user behavior data and the environment data; based on the goods source searching instruction, the vehicle operation data, the vehicle positioning data and a preset goods source database, determining a goods source high-dimensional feature vector; and determining a target goods source based on the vehicle high-dimensional feature vector and the goods source high-dimensional feature vector. The goods source searching efficiency of the commercial vehicle user can be improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle networking technology, and in particular to a commercial vehicle cargo source search method, device, equipment and storage medium. Background Art

[0002] Internet of Vehicles (IoV) technology is becoming increasingly mature and increasingly accessible to users. It can provide users with services such as intelligent voice, online navigation, online entertainment, remote vehicle control, vehicle condition reporting, and vehicle positioning.

[0003] Currently, cargo sourcing remains a key focus for commercial vehicle users, particularly individual vehicle owners in the logistics sector. Real-time cargo information is crucial for efficient vehicle transport and maximized economic returns. Using IoV big model technology, cargo sourcing can be rapidly identified. Summary of the Invention

[0004] In order to improve the efficiency of commercial vehicle users in finding cargo sources, the present application provides a commercial vehicle cargo source finding method, device, equipment and storage medium.

[0005] In a first aspect, the present application provides a method for finding a source of commercial vehicle cargo, comprising:

[0006] In response to obtaining a supply search instruction issued by a commercial vehicle user, collecting vehicle operation data, vehicle positioning data, user behavior data, and environmental data;

[0007] Determining a vehicle high-dimensional feature vector based on the vehicle operation data, the vehicle positioning data, the user behavior data, and the environmental data;

[0008] Determining a high-dimensional feature vector of a cargo source based on the cargo source search instruction, the vehicle operation data, the vehicle positioning data, and a preset cargo source database;

[0009] A target source of cargo is determined based on the vehicle high-dimensional feature vector and the cargo source high-dimensional feature vector.

[0010] It should be noted that after a commercial vehicle owner issues a cargo source search instruction, the target cargo source required by the current commercial vehicle owner can be determined in a timely manner by processing the automatically collected vehicle operation data, vehicle positioning data, user behavior data, and environmental data, thereby facilitating the improvement of the efficiency of commercial vehicle users in finding cargo sources.

[0011] Preferably, determining the vehicle high-dimensional feature vector based on the vehicle operation data, the vehicle positioning data, the user behavior data, and the environmental data includes:

[0012] generating a low-dimensional feature of vehicle operation based on the remaining load, remaining cruising range, vehicle model, and historical failure rate in the vehicle operation data;

[0013] generating low-dimensional features for cargo source search based on the vehicle operation data and the vehicle positioning data;

[0014] Generate low-dimensional features of user preferences based on the high-frequency transportation routes, preferred cargo types, historical cooperating shipper scores, and common quotation strategies in the user behavior data;

[0015] Generate low-dimensional environmental features based on real-time weather, road conditions, and policy restrictions in the environmental data;

[0016] A vehicle high-dimensional feature vector is generated based on the vehicle operation low-dimensional features, the cargo source search low-dimensional features, the user preference low-dimensional features, and the environment low-dimensional features.

[0017] It should be noted that the vehicle's high-dimensional feature vector is determined through vehicle operation data, vehicle positioning data, user behavior data and environmental data, thereby realizing structured processing of vehicle operation data, vehicle positioning data, user behavior data and environmental data, and improving the convenience of subsequent calculation of target cargo sources.

[0018] Preferably, generating low-dimensional features for cargo source search based on the vehicle operation data and the vehicle positioning data includes:

[0019] Determining a maximum travel distance, a maximum reachable time, and a cargo source area attribute based on the vehicle operation data and the vehicle positioning data;

[0020] Based on the longest driving distance, the maximum reachable time and the supply source area attributes, a supply source search low-dimensional feature is generated.

[0021] It should be noted that by generating low-dimensional features for source search, it is convenient to subsequently integrate the low-dimensional features for source search with low-dimensional features corresponding to other data to generate a high-dimensional feature vector for source.

[0022] Preferably, determining the high-dimensional feature vector of the supply source based on the supply source search instruction, the vehicle operation data, the vehicle positioning data, and a preset supply source database includes:

[0023] Determine the type of supply based on the supply search instruction;

[0024] determining a search center based on the vehicle positioning data;

[0025] determining a maximum travel distance based on the vehicle operation data and the vehicle positioning data;

[0026] determining candidate supply sources based on the supply source type, the search center, the maximum travel distance, and a preset supply source database;

[0027] The candidate sources of goods are encoded based on a preset dimension to obtain a high-dimensional feature vector of the source of goods.

[0028] It should be noted that by generating a high-dimensional feature vector of the cargo source, structured processing of different dimensions of the cargo source is achieved, which facilitates subsequent matching with the high-dimensional feature vector of the vehicle.

[0029] Preferably, determining the target source of goods based on the vehicle high-dimensional feature vector and the source of goods high-dimensional feature vector includes:

[0030] Calculating the similarity between the vehicle high-dimensional feature vector and the cargo source high-dimensional feature vector;

[0031] A target source of goods is determined based on the similarity and a preset similarity threshold.

[0032] It should be noted that similarity is used to facilitate the determination of the degree of matching between the vehicle high-dimensional feature vector and the cargo source high-dimensional feature vector.

[0033] Preferably, after determining the target source of goods using the vehicle high-dimensional feature vector and the source of goods high-dimensional feature vector, the method further includes:

[0034] Determining a matching score for the target source of goods based on the high-dimensional characteristics of the target source of goods; the matching score includes at least one of a demand fit score, a user preference score, an environmental impact score, and an economic efficiency score;

[0035] Calculating a comprehensive score of the target supply source based on the matching score;

[0036] Arranging the target sources of goods based on the comprehensive scores to obtain a source display queue;

[0037] The supply display queue is displayed to commercial vehicle users.

[0038] It should be noted that by generating a cargo display queue, it is convenient for commercial vehicle users to improve the convenience of selecting target cargo sources.

[0039] In a second aspect, the present application provides a commercial vehicle cargo source search device, comprising:

[0040] A data collection module, configured to collect vehicle operation data, vehicle positioning data, user behavior data, and environmental data in response to a supply search instruction issued by a commercial vehicle user;

[0041] a vehicle calculation module, configured to determine a vehicle high-dimensional feature vector based on the vehicle operation data, the vehicle positioning data, the user behavior data, and the environmental data;

[0042] a cargo source calculation module, configured to determine a cargo source high-dimensional feature vector based on the cargo source search instruction, the vehicle operation data, the vehicle positioning data, and a preset cargo source database;

[0043] The cargo source determination module is used to determine the target cargo source based on the vehicle high-dimensional feature vector and the cargo source high-dimensional feature vector.

[0044] It should be noted that after a commercial vehicle owner issues a cargo source search instruction, the target cargo source required by the current commercial vehicle owner can be determined in a timely manner by processing the automatically collected vehicle operation data, vehicle positioning data, user behavior data, and environmental data, thereby facilitating the improvement of the efficiency of commercial vehicle users in finding cargo sources.

[0045] In a third aspect, the present application provides a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps in the above method when executing the computer program.

[0046] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the steps in the above-mentioned method when executed by a processor.

[0047] In a fifth aspect, the present application further provides a computer program product, which includes a computer program that implements the steps of any of the above method embodiments when executed by a processor.

[0048] The above-mentioned commercial vehicle cargo source search method, device, equipment and storage medium collect vehicle operation data, vehicle positioning data, user behavior data and environmental data in response to a cargo source search instruction issued by a commercial vehicle user; determine a vehicle high-dimensional feature vector based on the vehicle operation data, vehicle positioning data, user behavior data and environmental data; determine a cargo source high-dimensional feature vector based on the cargo source search instruction, the vehicle operation data, the vehicle positioning data and a preset cargo source database; and determine a target cargo source based on the vehicle high-dimensional feature vector and the cargo source high-dimensional feature vector. Through the above implementation, after a commercial vehicle owner issues a cargo source search instruction, the target cargo source required by the current commercial vehicle owner can be determined in a timely manner by processing the automatically collected vehicle operation data, vehicle positioning data, user behavior data and environmental data, thereby facilitating the improvement of the efficiency of commercial vehicle users in searching for cargo sources.

[0049] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0051] Figure 1 This is a flow chart of a commercial vehicle cargo source search method provided in an embodiment of the present application;

[0052] Figure 2 This is a schematic diagram of the structure of a commercial vehicle cargo source search system provided in an embodiment of the present application;

[0053] Figure 3 This is a schematic structural diagram of a commercial vehicle cargo source search device provided in an embodiment of the present application;

[0054] Figure 4 A schematic diagram of the structure of a computer device provided in an embodiment of the present application;

[0055] Figure 5 This is a diagram of the internal structure of a computer-readable storage medium provided in an embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solutions and advantages of the present disclosure more clearly understood, the present disclosure is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present disclosure and are not intended to limit the present disclosure.

[0057] It should be noted that the terms "first," "second," and the like in the specification and claims herein and in the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or device comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to these processes, methods, products, or devices.

[0058] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" could mean: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates an "or" relationship between the related objects.

[0059] Example 1

[0060] Figure 1 This is a flow chart of a commercial vehicle cargo source search method provided in Example 1 of this application, refer to Figure 1 The method may be performed by a device for performing the method, and the device may be implemented by software and / or hardware. The method includes:

[0061] S110 , in response to obtaining a cargo source search instruction issued by a commercial vehicle user, collecting vehicle operation data, vehicle positioning data, user behavior data, and environmental data.

[0062] The commercial vehicle shown in this embodiment is used for transporting goods, including but not limited to coal, building materials, food, etc. In order to facilitate the commercial vehicle users to transport goods, reference is made to Figure 2 A commercial vehicle cargo source search system is provided on the commercial vehicle, which includes: an on-board terminal, which is communicatively connected to a human-computer interaction system and a cloud service system, wherein the human-computer interaction system is used to receive a cargo source search instruction issued by a commercial vehicle user, and send the cargo source search instruction to the on-board terminal, and the on-board terminal is used to collect corresponding data according to the cargo source search.

[0063] Among them, the human-computer interaction system is provided with a touch module and a voice module, which is used for commercial vehicle users to send cargo source search instructions to the human-computer interaction system by touching the human-computer interaction system, and can also send cargo source search instructions to the human-computer interaction system in the form of voice; for example, the cargo source search instruction sent by the commercial vehicle user is "I want to haul coal."

[0064] In this embodiment, the corresponding data collected by the on-board terminal include: vehicle operation data, vehicle positioning data, user behavior data and environmental data. In other embodiments, there is no specific limitation; among them, vehicle operation data is used to reflect the operation status of the vehicle, vehicle positioning data is used to reflect the location information of the vehicle, user behavior data is used to reflect the transportation preference information of commercial vehicle users; environmental data is used to reflect the transportation environment information of the vehicle; after completing the corresponding data collection, the on-board terminal will further send the corresponding data to the cloud service system. The cloud service system is equipped with a large model, which is used to process the above-mentioned vehicle operation data, vehicle positioning data, user behavior data and environmental data, and output the cargo source information obtained after analysis, and then return the cargo source information to the on-board terminal. The on-board terminal displays the cargo source information to the commercial vehicle user on the human-computer interaction system.

[0065] S120: Determine a vehicle high-dimensional feature vector based on the vehicle operation data, the vehicle positioning data, the user behavior data, and the environmental data.

[0066] Among them, in order to facilitate matching suitable sources of goods for commercial vehicle users in the future, it is necessary to use a parameter to characterize the vehicle operation data, vehicle positioning data, user behavior data and environmental data collected by the on-board terminal; to facilitate obtaining this parameter, this embodiment adopts a method of structured processing of the acquired vehicle operation data, vehicle positioning data, user behavior data and environmental data.

[0067] Specifically, the large model in the cloud service system can perform structured processing on the vehicle operation data, vehicle positioning data, user behavior data, and environmental data uploaded by the vehicle terminal to obtain the above parameters, and record the parameters as the vehicle's high-dimensional feature vector.

[0068] S130. Determine a high-dimensional feature vector of a cargo source based on the cargo source search instruction, the vehicle operation data, the vehicle positioning data, and a preset cargo source database.

[0069] Among them, in order to facilitate matching suitable sources of goods for commercial vehicle users, the cloud service system of this embodiment is also preset with a source of goods database, which collects all possible source of goods information for commercial vehicle users within a certain geographical range; after the human-computer interaction system obtains the source of goods search instruction issued by the commercial vehicle user, it further sends the source of goods search instruction to the cloud service system through the on-board terminal, so that the big model in the cloud service system can subsequently process the source of goods search instruction; after obtaining the source of goods search instruction, as well as the vehicle operation data and vehicle positioning data, the big model can process the source of goods search instruction, vehicle operation data, vehicle positioning data and the preset source of goods database, thereby screening out a number of sources of goods corresponding to the source of goods search instruction, vehicle operation data and vehicle positioning data from the source of goods database. It should be noted that the screened sources of goods cannot be used as the sources of goods returned to the commercial vehicle user at this time, but the sources of goods returned to the commercial vehicle user subsequently can be generated from the above-mentioned screened sources of goods.

[0070] Among them, in order to facilitate the subsequent further determination of the source of goods returned to the commercial vehicle user from the screened sources of goods, each screened source of goods can be encoded to obtain a one-to-one corresponding feature vector of each screened source of goods, and the feature vector corresponding to the screened source of goods is recorded as a high-dimensional feature vector of the source of goods. The high-dimensional feature vector of the source of goods is used to reflect the characteristics of the corresponding source of goods in different dimensions; in this embodiment, the high-dimensional feature vector of the source of goods includes characteristics of four dimensions: first, the distance from the commercial vehicle; second, the time when the commercial vehicle arrives at the source of goods; third, the degree of matching with the transportation preference of the commercial vehicle user; fourth, the degree of influence of the environment on the commercial vehicle user's choice of source of goods.

[0071] S140: Determine a target cargo source based on the vehicle high-dimensional feature vector and the cargo source high-dimensional feature vector.

[0072] Among them, a vehicle high-dimensional feature vector corresponding to the commercial vehicle can be calculated through the vehicle operation data, vehicle positioning data, user behavior data and environmental data collected by the commercial vehicle; through step S130, a cargo source high-dimensional feature vector corresponding to each screened cargo source can be calculated; taking one of the cargo source high-dimensional feature vectors as an example, the cargo source high-dimensional feature vector is matched with the vehicle high-dimensional feature vector. If the matching degree is high, it means that the cargo source corresponding to the cargo source high-dimensional feature vector is more adapted to the needs of the commercial vehicle user corresponding to the vehicle high-dimensional feature vector. At this time, the cargo source corresponding to the cargo source high-dimensional feature vector is recorded as the target cargo source.

[0073] It should be noted that at least one target source of cargo can be determined through the above method, and the cloud service system can subsequently return all determined target sources of cargo to the human-computer interaction system through the on-board terminal; commercial vehicle users can select the target source of cargo they need from all returned target sources of cargo.

[0074] In an optional embodiment, in response to the commercial vehicle user selecting the desired target source of goods, the on-board terminal will further ask the commercial vehicle user through the human-computer interaction system whether to navigate to the target source of goods. If the commercial vehicle user confirms the navigation, the on-board terminal will start the navigation, thereby leading the commercial vehicle user to the target source of goods.

[0075] It should be noted that this embodiment collects vehicle operation data, vehicle positioning data, user behavior data, and environmental data in response to a cargo source search instruction issued by a commercial vehicle user; determines a vehicle high-dimensional feature vector based on the vehicle operation data, vehicle positioning data, user behavior data, and environmental data; determines a cargo source high-dimensional feature vector based on the cargo source search instruction, the vehicle operation data, the vehicle positioning data, and a preset cargo source database; and determines a target cargo source based on the vehicle high-dimensional feature vector and the cargo source high-dimensional feature vector. Through the above implementation, after a commercial vehicle owner issues a cargo source search instruction, the target cargo source required by the current commercial vehicle owner can be determined in a timely manner by processing the automatically collected vehicle operation data, vehicle positioning data, user behavior data, and environmental data, thereby facilitating the improvement of the efficiency of commercial vehicle users in searching for cargo sources.

[0076] Example 2

[0077] A commercial vehicle source search method is provided in a second embodiment of the present application. This method optimizes the "determining a vehicle high-dimensional feature vector based on the vehicle operation data, the vehicle positioning data, the user behavior data, and the environmental data" in the first embodiment. It should be noted that for portions not described in detail in this embodiment, reference may be made to the descriptions of other embodiments. This method includes:

[0078] S210 : In response to obtaining a cargo source search instruction issued by a commercial vehicle user, collecting vehicle operation data, vehicle positioning data, user behavior data, and environmental data.

[0079] S221. Generate low-dimensional features of vehicle operation based on the remaining load, remaining cruising range, vehicle model, and historical failure rate in the vehicle operation data.

[0080] Among them, in this embodiment, the vehicle operation data includes: remaining load, remaining cruising range, vehicle model and historical failure rate. In other embodiments, there is no specific limitation; among them, the remaining load represents the current remaining loadable weight of the commercial vehicle; the remaining cruising range represents the current remaining cruising range of the commercial vehicle; the vehicle model represents the type of commercial vehicle, for example, the vehicle includes but is not limited to vans, flatbed trucks, etc.; the historical failure rate represents the probability of historical failure of the commercial vehicle.

[0081] It should be noted that after obtaining each type of data in the vehicle operation data, the cloud service system will normalize each type of data one by one, so as to obtain a normalized value corresponding to each type of data in the vehicle operation data; and the normalized value for normalizing the remaining load is recorded as a1, the normalized value for normalizing the remaining cruising range is recorded as a2, the normalized value for normalizing the vehicle model is recorded as a3, and the normalized value for normalizing the historical failure rate is recorded as a4; further, a1, a2, a3, and a4 are also encoded to obtain the low-dimensional features A (a1, a2, a3, a4) of the vehicle operation.

[0082] S222: Generate low-dimensional features for cargo source search based on the vehicle operation data and the vehicle positioning data.

[0083] Among them, the cloud service system will also process the vehicle operation data and vehicle positioning data to generate the corresponding low-dimensional features B.

[0084] S223. Generate low-dimensional features of user preferences based on the high-frequency transportation routes, preferred cargo types, historical cooperative shipper scores, and common quotation strategies in the user behavior data.

[0085] Among them, in this embodiment, the user behavior data includes data such as high-frequency transportation routes, preferred cargo types, historical cooperative cargo owner scores and commonly used quotation strategies. In other embodiments, there is no specific limitation; among them, high-frequency transportation routes are used to characterize high-frequency transportation routes generated by commercial vehicles in the history; preferred cargo types are used to characterize the cargo types that commercial vehicle users have historically preferred to transport. For example, the preferred cargo type is coal; historical cooperative cargo owner scores are scores of cargo owners of cargo historically transported by commercial vehicle users, and this score is a comprehensive score for each commercial vehicle user; commonly used quotation strategies are quotation strategies commonly used by commercial vehicle users in the past. For example, the quotation strategy is an initial limit low quotation.

[0086] The cloud service system will also vectorize the various data contained in the user behavior data, thereby obtaining a one-to-one corresponding vector for each type of data in the user behavior data. For example, this embodiment specifically uses the Word2Vec vector model to vectorize the various data contained in the user behavior data one by one; and the vector obtained after the vectorization of high-frequency transportation routes is recorded as c1, the vector obtained after the vectorization of preferred cargo types is recorded as c2, and the vector obtained after the vectorization of historical cooperative cargo owner scores is recorded as c3; the vector obtained after the vectorization of commonly used quotation strategies is recorded as c4; further, the above c1, c2, c3 and c4 are also encoded to obtain the user preference low-dimensional feature C (c1, c2, c3, c4).

[0087] S224: Generate low-dimensional environmental features based on the real-time weather, road conditions, and policy restrictions in the environmental data.

[0088] In this embodiment, the environmental data includes real-time weather, road conditions, and policy restrictions. This is not specifically limited in other embodiments. Real-time weather represents the current day's weather information, and road conditions include congestion index and construction section information. The congestion index ranges from 1 to 10. Policy restrictions include regional traffic restrictions and overload control information.

[0089] The cloud service system will also perform binary conversion on various data in the environmental data one by one, thereby obtaining binary values corresponding to various data in the environmental data, and record the binary value corresponding to the real-time weather as d1, the binary value corresponding to the road condition as d2, and the binary value corresponding to the policy restriction as d3; further, the above d1, d2 and d3 are also encoded to obtain the low-dimensional environmental features D(d1, d2, d3).

[0090] S225 . Generate a vehicle high-dimensional feature vector based on the vehicle operation low-dimensional features, the cargo source search low-dimensional features, the user preference low-dimensional features, and the environment low-dimensional features.

[0091] Among them, the vehicle high-dimensional feature vector is obtained by encoding the vehicle operation low-dimensional feature A, the cargo source search low-dimensional feature B, the user preference low-dimensional feature C and the environment low-dimensional feature D, and the vehicle high-dimensional feature vector is recorded as [A, B, C, D].

[0092] S230: Determine a high-dimensional feature vector of a cargo source based on the cargo source search instruction, the vehicle operation data, the vehicle positioning data, and a preset cargo source database.

[0093] S240: Determine a target cargo source based on the vehicle high-dimensional feature vector and the cargo source high-dimensional feature vector.

[0094] Example 3

[0095] A method for finding cargo sources for commercial vehicles is provided in a third embodiment of the present application. This method optimizes the "generating low-dimensional features for cargo source search based on the vehicle operation data and the vehicle positioning data" in the second embodiment. It should be noted that for portions not described in detail in this embodiment, reference may be made to the descriptions of other embodiments. The method includes:

[0096] S310 : In response to obtaining a cargo source search instruction issued by a commercial vehicle user, collecting vehicle operation data, vehicle positioning data, user behavior data, and environmental data.

[0097] S321. Generate low-dimensional features of vehicle operation based on the remaining load, remaining cruising range, vehicle model, and historical failure rate in the vehicle operation data.

[0098] S322A. Determine the maximum driving distance, the maximum reachable time, and the cargo source area attributes based on the vehicle operation data and the vehicle positioning data.

[0099] Among them, the maximum driving distance is the maximum distance that the commercial vehicle can currently travel, the maximum reachable time is the time required for the commercial vehicle to currently travel to the maximum distance, and the cargo source area attributes include industrial areas and logistics parks, etc.; the cloud service system can calculate the maximum driving distance and maximum reachable time based on the acquired vehicle operation data and vehicle positioning data, and determine the cargo source area attributes corresponding to the commercial vehicle.

[0100] S322B: Generate low-dimensional features for source search based on the longest driving distance, the maximum reachable time, and the source area attributes.

[0101] Among them, the cloud service system can normalize the maximum driving distance, maximum reachable time and cargo source area attributes, so as to obtain normalized values corresponding to the maximum driving distance, maximum reachable time and cargo source area attributes, and record the normalized value corresponding to the maximum driving distance as b1, the normalized value corresponding to the maximum reachable time as b2, and the normalized value corresponding to the cargo source area attribute as b3; further, the above b1, b2 and b3 are also encoded to obtain the cargo source search low-dimensional feature B (b1, b2, b3).

[0102] S323. Generate user preference low-dimensional features based on the high-frequency transportation routes, preferred cargo types, historical cooperative shipper scores, and common quotation strategies in the user behavior data.

[0103] S324: Generate low-dimensional environmental features based on the real-time weather, road conditions, and policy restrictions in the environmental data.

[0104] S325 . Generate a vehicle high-dimensional feature vector based on the vehicle operation low-dimensional features, the cargo source search low-dimensional features, the user preference low-dimensional features, and the environment low-dimensional features.

[0105] S330: Determine a high-dimensional feature vector of a cargo source based on the cargo source search instruction, the vehicle operation data, the vehicle positioning data, and a preset cargo source database.

[0106] S340: Determine a target cargo source based on the vehicle high-dimensional feature vector and the cargo source high-dimensional feature vector.

[0107] Example 4

[0108] A fourth embodiment of the present application provides a method for searching cargo sources for commercial vehicles. This method optimizes the method of "determining a cargo source high-dimensional feature vector based on the cargo source search instruction, the vehicle operation data, the vehicle positioning data, and a preset cargo source database" in the first embodiment. It should be noted that for portions not described in detail in this embodiment, reference may be made to the descriptions of other embodiments. The method includes:

[0109] S410 : In response to obtaining a cargo source search instruction issued by a commercial vehicle user, collecting vehicle operation data, vehicle positioning data, user behavior data, and environmental data.

[0110] S420: Determine a vehicle high-dimensional feature vector based on the vehicle operation data, the vehicle positioning data, the user behavior data, and the environmental data.

[0111] S431. Determine the supply type based on the supply search instruction.

[0112] The supply source search instruction includes the supply source type.

[0113] Specifically, the supply source search instruction is segmented to obtain multiple initial segmented words, and then the stop words in the multiple segmented words are removed to obtain the target stop words. Then, based on the target stop words, a query is performed in the preset supply source type table. If the supply source type corresponding to the target stop word is queried, the supply source type is used as the supply source type corresponding to the supply source search instruction; for example, the supply source search instruction is "I want to do coal hauling work", and the supply source type corresponding to the supply source search instruction is "coal".

[0114] S432: Determine a search center based on the vehicle positioning data.

[0115] The vehicle positioning data is used to represent the position of the commercial vehicle in the geodetic coordinate system. The position of the commercial vehicle in the geodetic coordinate system is also the search center.

[0116] S433: Determine a maximum driving distance based on the vehicle operation data and the vehicle positioning data.

[0117] Among them, the vehicle positioning data can be used as the starting point of the longest driving distance, and the longest driving distance can be calculated based on the remaining cruising range in the vehicle operation data. In this implementation, 0.5*remaining cruising range is used as the value of the longest driving distance.

[0118] S434: Determine candidate supply sources based on the supply type, the search center, the longest travel distance, and a preset supply source database.

[0119] Among them, the search center is used as the center of the circle in the geodetic coordinate system, and the longest driving distance is used as the radius to draw a circle on the map, and the cargo sources in the cargo source database that correspond to the cargo source type and are located within the circle are taken as candidate cargo sources.

[0120] S435. Encode the candidate supply sources based on a preset dimension to obtain a high-dimensional feature vector of the supply source.

[0121] Among them, taking one of the candidate sources of cargo as an example, the cloud service system can encode the candidate source of cargo according to different dimensions; in this implementation, a total of four dimensions are designed, namely: first, the distance between the commercial vehicle; second, the time for the commercial vehicle to arrive at the source of cargo; third, the degree of matching with the transportation preference of the commercial vehicle user; fourth, the degree of influence of the environment on the commercial vehicle user's choice of cargo source; by encoding the candidate source of cargo in the above four dimensions respectively, a dimension code corresponding to each dimension can be obtained, and the dimension code corresponding to the first dimension is recorded as O, the dimension code corresponding to the second dimension is recorded as X, the dimension code corresponding to the third dimension is recorded as Y, and the dimension code corresponding to the fourth dimension is recorded as Z; further, the above O, X, Y and Z are further encoded to obtain a high-dimensional feature vector of the cargo source [O, X, Y, Z].

[0122] S440: Determine a target cargo source based on the vehicle high-dimensional feature vector and the cargo source high-dimensional feature vector.

[0123] Example 5

[0124] A fifth embodiment of the present application provides a method for finding a source of commercial vehicle cargo. This method optimizes the "determining a target source of cargo based on the vehicle high-dimensional feature vector and the cargo source high-dimensional feature vector" in the first embodiment. It should be noted that for portions not described in detail in this embodiment, reference may be made to the descriptions of other embodiments. The method includes:

[0125] S510 : In response to obtaining a cargo source search instruction issued by a commercial vehicle user, collecting vehicle operation data, vehicle positioning data, user behavior data, and environmental data.

[0126] S520: Determine a vehicle high-dimensional feature vector based on the vehicle operation data, the vehicle positioning data, the user behavior data, and the environmental data.

[0127] S530: Determine a high-dimensional feature vector of a cargo source based on the cargo source search instruction, the vehicle operation data, the vehicle positioning data, and a preset cargo source database.

[0128] S541. Calculate the similarity between the vehicle high-dimensional feature vector and the cargo source high-dimensional feature vector.

[0129] Among them, in order to determine whether the source of goods corresponding to the source of goods high-dimensional feature vector is suitable for the commercial vehicle user corresponding to the vehicle high-dimensional feature vector, this implementation needs to calculate the similarity between the vehicle high-dimensional feature vector and the source of goods high-dimensional feature vector; illustratively, this embodiment calculates the cosine similarity between the vehicle high-dimensional feature vector and the source of goods high-dimensional feature vector, and uses the cosine similarity as the similarity between the vehicle high-dimensional feature vector and the source of goods high-dimensional feature vector; in an optional embodiment, the Euclidean distance between the vehicle high-dimensional feature vector and the source of goods high-dimensional feature vector can also be used as the similarity between the vehicle high-dimensional feature vector and the source of goods high-dimensional feature vector; in another optional embodiment, the Pearson correlation coefficient between the vehicle high-dimensional feature vector and the source of goods high-dimensional feature vector can also be used as the similarity between the vehicle high-dimensional feature vector and the source of goods high-dimensional feature vector; in other embodiments, there is no specific limitation.

[0130] S542: Determine a target source of goods based on the similarity and a preset similarity threshold.

[0131] Among them, if the similarity corresponding to a candidate source of supply is greater than a preset similarity threshold, the candidate source of supply will be used as the target source of supply.

[0132] Example 6

[0133] A commercial vehicle cargo source search method is provided in Example 6 of the present application. This method supplements the steps after "determining a target cargo source by combining the vehicle high-dimensional feature vector and the cargo source high-dimensional feature vector" in Example 1. It should be noted that for portions not described in detail in this embodiment, reference may be made to the descriptions in other embodiments. The method includes:

[0134] S610 : In response to obtaining a cargo source search instruction issued by a commercial vehicle user, collecting vehicle operation data, vehicle positioning data, user behavior data, and environmental data.

[0135] S620: Determine a vehicle high-dimensional feature vector based on the vehicle operation data, the vehicle positioning data, the user behavior data, and the environmental data.

[0136] S630: Determine a high-dimensional feature vector of a cargo source based on the cargo source search instruction, the vehicle operation data, the vehicle positioning data, and a preset cargo source database.

[0137] S640: Determine a target cargo source based on the vehicle high-dimensional feature vector and the cargo source high-dimensional feature vector.

[0138] S650. Determine a matching score of the target source of supply based on the high-dimensional characteristics of the target source of supply; the matching score includes at least one of a demand fit score, a user preference score, an environmental impact score, and an economic score.

[0139] There may be multiple target sources identified. To facilitate display of these target sources to commercial vehicle users, they must be ranked, with those ranked higher being displayed first. To prioritize each target source, a large model within the cloud service system processes the high-dimensional features of the target sources to calculate a matching score for each target source. In this implementation, the matching score includes scores across four dimensions: compatibility, user preference, environmental impact, and economic efficiency. This is not a specific limitation in other embodiments.

[0140] S660: Calculate a comprehensive score of the target supply source based on the matching score.

[0141] In this embodiment, corresponding weights are preset for the scores of the four dimensions included in the matching score, namely: C1, C2, C3, and C4.

[0142] In this implementation, the comprehensive score of the target source of goods is the weighted sum of the scores of the four dimensions included in the matching score.

[0143] In an optional embodiment, the comprehensive score of the target source of goods is the sum of the scores of the four dimensions included in the matching score.

[0144] S670: Arrange the target sources of goods based on the comprehensive scores to obtain a source display queue.

[0145] Among them, in the supply display queue, the higher the comprehensive score corresponding to the target supply, the higher the position of the target supply in the supply display queue.

[0146] S680: Display the supply display queue to commercial vehicle users.

[0147] Among them, after determining the supply display queue, the cloud service system sends the supply display queue to the human-computer interaction system through the vehicle terminal to display it to the user.

[0148] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0149] Example 7

[0150] Based on the same inventive concept, this embodiment also provides a commercial vehicle cargo source search device for implementing the aforementioned commercial vehicle cargo source search method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more commercial vehicle cargo source search device embodiments provided below can be found in the aforementioned limitations of the commercial vehicle cargo source search method and will not be further elaborated here.

[0151] In this embodiment, Figure 3 As shown, a commercial vehicle cargo source search device is provided, comprising:

[0152] A data collection module, configured to collect vehicle operation data, vehicle positioning data, user behavior data, and environmental data in response to a supply search instruction issued by a commercial vehicle user;

[0153] a vehicle calculation module, configured to determine a vehicle high-dimensional feature vector based on the vehicle operation data, the vehicle positioning data, the user behavior data, and the environmental data;

[0154] a cargo source calculation module, configured to determine a cargo source high-dimensional feature vector based on the cargo source search instruction, the vehicle operation data, the vehicle positioning data, and a preset cargo source database;

[0155] The cargo source determination module is used to determine the target cargo source based on the vehicle high-dimensional feature vector and the cargo source high-dimensional feature vector.

[0156] Each module in the commercial vehicle cargo source search device described above can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0157] It should be noted that this embodiment collects vehicle operation data, vehicle positioning data, user behavior data, and environmental data in response to a cargo source search instruction issued by a commercial vehicle user; determines a vehicle high-dimensional feature vector based on the vehicle operation data, vehicle positioning data, user behavior data, and environmental data; determines a cargo source high-dimensional feature vector based on the cargo source search instruction, the vehicle operation data, the vehicle positioning data, and a preset cargo source database; and determines a target cargo source based on the vehicle high-dimensional feature vector and the cargo source high-dimensional feature vector. Through the above implementation, after a commercial vehicle owner issues a cargo source search instruction, the target cargo source required by the current commercial vehicle owner can be determined in a timely manner by processing the automatically collected vehicle operation data, vehicle positioning data, user behavior data, and environmental data, thereby facilitating the improvement of the efficiency of commercial vehicle users in searching for cargo sources.

[0158] In an optional embodiment, in determining the vehicle high-dimensional feature vector based on the vehicle operation data, the vehicle positioning data, the user behavior data, and the environmental data, the vehicle computing module is specifically configured to:

[0159] generating a low-dimensional feature of vehicle operation based on the remaining load, remaining cruising range, vehicle model, and historical failure rate in the vehicle operation data;

[0160] generating low-dimensional features for cargo source search based on the vehicle operation data and the vehicle positioning data;

[0161] Generate low-dimensional features of user preferences based on the high-frequency transportation routes, preferred cargo types, historical cooperating shipper scores, and common quotation strategies in the user behavior data;

[0162] Generate low-dimensional environmental features based on real-time weather, road conditions, and policy restrictions in the environmental data;

[0163] A vehicle high-dimensional feature vector is generated based on the vehicle operation low-dimensional features, the cargo source search low-dimensional features, the user preference low-dimensional features, and the environment low-dimensional features.

[0164] In an optional embodiment, in terms of generating low-dimensional features for cargo source search based on the vehicle operation data and the vehicle positioning data, the vehicle calculation module is specifically configured to:

[0165] Determining a maximum travel distance, a maximum reachable time, and a cargo source area attribute based on the vehicle operation data and the vehicle positioning data;

[0166] Based on the longest driving distance, the maximum reachable time and the supply source area attributes, a supply source search low-dimensional feature is generated.

[0167] In an optional embodiment, in determining the high-dimensional feature vector of a supply based on the supply search instruction, the vehicle operation data, the vehicle positioning data, and a preset supply database, the supply calculation module is specifically configured to:

[0168] Determine the type of supply based on the supply search instruction;

[0169] determining a search center based on the vehicle positioning data;

[0170] determining a maximum travel distance based on the vehicle operation data and the vehicle positioning data;

[0171] determining candidate supply sources based on the supply source type, the search center, the maximum travel distance, and a preset supply source database;

[0172] The candidate sources of goods are encoded based on a preset dimension to obtain a high-dimensional feature vector of the source of goods.

[0173] In an optional embodiment, in determining the target source of goods based on the vehicle high-dimensional feature vector and the source of goods high-dimensional feature vector, the source of goods determination module is specifically configured to:

[0174] Calculating the similarity between the vehicle high-dimensional feature vector and the cargo source high-dimensional feature vector;

[0175] A target source of goods is determined based on the similarity and a preset similarity threshold.

[0176] In an optional embodiment, the commercial vehicle cargo source search device further includes:

[0177] a matching score calculation module, configured to determine a matching score of the target source of goods based on the high-dimensional characteristics of the target source of goods; the matching score comprising at least one of a demand fit score, a user preference score, an environmental impact score, and an economic efficiency score;

[0178] A comprehensive score calculation module, configured to calculate a comprehensive score of the target source of goods based on the matching score;

[0179] a queue calculation module, configured to arrange the target supply sources based on the comprehensive scores to obtain a supply display queue;

[0180] The queue display module is used to display the supply display queue to commercial vehicle users.

[0181] Example 8

[0182] In this embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4As shown. The computer device includes a processor, a memory, and a network interface connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, it implements a method for finding a source of commercial vehicle cargo.

[0183] Those skilled in the art will understand that Figure 4 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present disclosure, and does not constitute a limitation on the computer device to which the solution of the present disclosure is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0184] Example 9

[0185] In this embodiment, a computer readable storage medium is provided. Figure 5 As shown, a computer program is stored thereon, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0186] Example 10

[0187] In this embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0188] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0189] 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 the present disclosure 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 each embodiment provided in this disclosure 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 each embodiment provided in this disclosure 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, etc.

[0190] The technical features of the above embodiments can be combined arbitrarily. 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.

[0191] The above-described embodiments merely represent several implementation methods of the present disclosure. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present disclosure. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present disclosure, all of which fall within the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure shall be determined by the appended claims.

Claims

1. A commercial vehicle source search method, characterized in that: include: In response to obtaining a supply search instruction issued by a commercial vehicle user, collecting vehicle operation data, vehicle positioning data, user behavior data, and environmental data; Determining a vehicle high-dimensional feature vector based on the vehicle operation data, the vehicle positioning data, the user behavior data, and the environmental data; Determining a high-dimensional feature vector of a cargo source based on the cargo source search instruction, the vehicle operation data, the vehicle positioning data, and a preset cargo source database; A target source of cargo is determined based on the vehicle high-dimensional feature vector and the cargo source high-dimensional feature vector.

2. The method according to claim 1, characterized in that The determining of a vehicle high-dimensional feature vector based on the vehicle operation data, the vehicle positioning data, the user behavior data, and the environmental data includes: generating a low-dimensional feature of vehicle operation based on the remaining load, remaining cruising range, vehicle model, and historical failure rate in the vehicle operation data; generating low-dimensional features for cargo source search based on the vehicle operation data and the vehicle positioning data; Generate low-dimensional features of user preferences based on the high-frequency transportation routes, preferred cargo types, historical cooperating shipper scores, and common quotation strategies in the user behavior data; Generate low-dimensional environmental features based on real-time weather, road conditions, and policy restrictions in the environmental data; A vehicle high-dimensional feature vector is generated based on the vehicle operation low-dimensional features, the cargo source search low-dimensional features, the user preference low-dimensional features, and the environment low-dimensional features.

3. The method according to claim 2, characterized in that The generating of low-dimensional features for cargo source search based on the vehicle operation data and the vehicle positioning data includes: Determining a maximum travel distance, a maximum reachable time, and a cargo source area attribute based on the vehicle operation data and the vehicle positioning data; Based on the longest driving distance, the maximum reachable time and the supply source area attributes, a supply source search low-dimensional feature is generated.

4. The method according to claim 1, wherein The determining of a high-dimensional feature vector of a supply source based on the supply source search instruction, the vehicle operation data, the vehicle positioning data, and a preset supply source database includes: Determine the type of supply based on the supply search instruction; determining a search center based on the vehicle positioning data; determining a maximum travel distance based on the vehicle operation data and the vehicle positioning data; determining candidate supply sources based on the supply source type, the search center, the maximum travel distance, and a preset supply source database; The candidate sources of goods are encoded based on a preset dimension to obtain a high-dimensional feature vector of the source of goods.

5. The method according to claim 1, wherein The determining of a target cargo source based on the vehicle high-dimensional feature vector and the cargo source high-dimensional feature vector includes: Calculating the similarity between the vehicle high-dimensional feature vector and the cargo source high-dimensional feature vector; A target source of goods is determined based on the similarity and a preset similarity threshold.

6. The method according to claim 1, characterized in that After the target source of goods is determined by the vehicle high-dimensional feature vector and the source of goods high-dimensional feature vector, the method further includes: Determining a matching score for the target source of goods based on the high-dimensional characteristics of the target source of goods; the matching score includes at least one of a demand fit score, a user preference score, an environmental impact score, and an economic efficiency score; Calculating a comprehensive score of the target supply source based on the matching score; Arranging the target sources of goods based on the comprehensive scores to obtain a source display queue; The supply display queue is displayed to commercial vehicle users.

7. A commercial vehicle cargo source search device, characterized in that: The device comprises: A data collection module, configured to collect vehicle operation data, vehicle positioning data, user behavior data, and environmental data in response to a supply search instruction issued by a commercial vehicle user; a vehicle calculation module, configured to determine a vehicle high-dimensional feature vector based on the vehicle operation data, the vehicle positioning data, the user behavior data, and the environmental data; a cargo source calculation module, configured to determine a cargo source high-dimensional feature vector based on the cargo source search instruction, the vehicle operation data, the vehicle positioning data, and a preset cargo source database; The cargo source determination module is used to determine the target cargo source based on the vehicle high-dimensional feature vector and the cargo source high-dimensional feature vector.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images