Travel task allocation method, electronic device and storage medium based on user portrait

Abstract

The present invention provides a travel task allocation method based on user portraits, an electronic device and a storage medium, and relates to the technical field of travel task allocation. The method includes: obtaining several portraits corresponding to the users of each idle vehicle; determining several main influencing external factors and the main external influencing factor values ​​corresponding to each portrait of each user; if the current external influencing factor value of each preset external influencing factor corresponding to the travel task to be allocated and the main external influencing factor value corresponding to the specified portrait meet the preset matching conditions, then the specified portrait is determined as the pending portrait; according to the number of pending portraits, the travel task characteristics corresponding to the travel task to be allocated and the historical travel task characteristics of all historical travel tasks corresponding to each pending portrait, a target portrait is determined from the pending portraits; and the travel task to be allocated is allocated to the idle vehicle corresponding to the target portrait. The present invention can improve the matching of travel task allocation.

Description

Technical Field

[0001] The present invention relates to the technical field of travel task allocation, and in particular to a travel task allocation method based on user portraits, an electronic device, and a storage medium. Background Art

[0002] In the field of smart travel, allocating taxi orders based on user portraits is of great significance. Dispatching vehicles in advance according to travel patterns can significantly reduce passenger waiting time, making travel more efficient and convenient. Vehicle deployment can be reasonably arranged based on demand distribution, thereby improving overall vehicle utilization. In existing technologies, driver or passenger portraits are usually portrayed based on the historical order information of taxis and the historical order information of users. However, for people, their corresponding user portraits are not static. In some scenarios, user portraits may be affected by many factors, resulting in relatively large changes in user portraits. At this time, if travel tasks are still matched with user portraits portrayed based on historical data, the assigned travel tasks will not match the user portraits. Therefore, how to improve the matching of travel task allocation has become a technical problem that needs to be solved urgently. Summary of the Invention

[0003] In view of the above technical problems, the technical solution adopted by the present invention is:

[0004] According to a first aspect of the present application, a method for allocating travel tasks based on user profiles is provided, the method comprising the following steps:

[0005] S100, clustering a number of historical travel tasks corresponding to any idle vehicle to obtain a number of profiles corresponding to the user of each idle vehicle;

[0006] S200, determining a number of main influencing external factors and main external influencing factor values ​​corresponding to each user's profile based on the external influencing factor value corresponding to each preset external influencing factor corresponding to each historical travel task included in each user's profile and the external influencing factor value corresponding to each historical travel task of each user;

[0007] S300, obtaining the current external influencing factor value and travel task characteristics of each preset external influencing factor corresponding to the to-be-assigned travel task;

[0008] S400, if the current external influencing factor value of each preset external influencing factor corresponding to the to-be-assigned travel task and the main external influencing factor value corresponding to the designated portrait meet a preset matching condition, then determining the designated portrait as a pending portrait; wherein the designated portrait is any portrait;

[0009] S500, determining a target portrait from the pending portraits based on the number of pending portraits, the travel task characteristics corresponding to the to-be-assigned travel task, and the historical travel task characteristics of all historical travel tasks corresponding to each pending portrait;

[0010] S600: Allocate the travel task to be assigned to the idle vehicle corresponding to the target profile.

[0011] According to another aspect of the present application, a non-transitory computer-readable storage medium is also provided, in which at least one instruction or at least one program is stored, and the at least one instruction or at least one program is loaded and executed by a processor to implement the above-mentioned travel task allocation method based on user portraits.

[0012] According to another aspect of the present application, an electronic device is provided, including a processor and the above-mentioned non-transitory computer-readable storage medium.

[0013] The present invention has at least the following beneficial effects:

[0014] The travel task allocation method based on user portrait of the present invention significantly improves the matching and efficiency of travel task allocation by dynamically constructing a multi-dimensional portrait of the driver and matching external influencing factors in real time; specifically, cluster analysis is performed on the driver's historical travel tasks to generate dynamic portraits reflecting behavioral patterns in different scenarios, overcoming the rigidity of static portraits; by analyzing the correlation between historical data and real-time external factors (such as traffic and weather), the main influencing factors and their thresholds of each portrait are extracted to ensure that the current environmental changes are accurately matched when the task is allocated; combined with the real-time characteristics of the task to be assigned and the similarity of the historical task characteristics of the portrait to be determined, the execution density and other comprehensive weight evaluations, the most suitable vehicle is selected first, which not only reduces the waiting time of passengers but also improves the utilization rate of vehicles; at the same time, invalid scheduling is avoided through geographical location constraint screening; the method of the present invention realizes the upgrade from static experience-driven to dynamic data-driven, solves the core problem of mismatch between user portraits and real-time needs, improves the matching of travel task allocation, and makes travel task allocation more intelligent and precise. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 A flowchart of a travel task allocation method based on user profiles provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] 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 the embodiments. 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.

[0018] It should be noted that, based on this disclosure, those skilled in the art will appreciate that an aspect described herein can be implemented independently of any other aspect, and that two or more of these aspects can be combined in various ways. For example, any number of the aspects described herein can be used to implement an apparatus and / or practice a method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement such an apparatus and / or practice such a method.

[0019] The following will refer to Figure 1 The flowchart of the travel task allocation method based on user portrait is shown, which introduces a travel task allocation method based on user portrait.

[0020] The travel task allocation method based on user profile may include the following steps:

[0021] 1. A travel task allocation method based on user profile, characterized by comprising the following steps:

[0022] S100 , clustering a number of historical travel tasks corresponding to any idle vehicle to obtain a number of portraits corresponding to the user of each idle vehicle.

[0023] In this embodiment, the user of each idle vehicle is the driver of each idle vehicle; the idle status of the vehicle can be obtained through image recognition, for example: the on-board camera is installed in the front of the vehicle (such as near the rearview mirror), which can clearly capture the situation of the passengers in the back seat; a deep learning (DNN) target detection model is used to analyze the status of the passengers in the vehicle in real time, including complete face recognition and partially occluded human body detection, to improve the detection recall rate; the current number of passengers in the vehicle is identified and the data is transmitted to the on-board control unit (ECU); when it is detected that the number of people in the vehicle is greater than or equal to 1, the system automatically controls the dome light to display "occupied", that is, the vehicle is in a non-idle state; when it is detected that the number of people in the vehicle is equal to 0, the system automatically controls the dome light to display "empty vehicle", that is, the vehicle is in an idle state.

[0024] Since camera detection may result in short-term misjudgments (such as a passenger lowering their head or blocking the view), a Kalman filter or exponential moving average (EMA) is used to smooth the detection data. The dome light status change is triggered only when a passenger is detected to have boarded the vehicle for more than a set time (such as 3 seconds) to prevent instantaneous false alarms. When a brief change in the passenger status is detected (such as a passenger adjusting their posture or blocking the view), the system will not immediately switch the dome light, but will wait for continuous and stable detection results before making a decision.

[0025] Furthermore, the distance between the position of the idle vehicle and the position to be assigned the travel task is within a preset distance range.

[0026] In this embodiment, there are several idle vehicles in the target area, for example, a city area. When the travel task to be assigned is published by the user, there is corresponding location information. It is only necessary to process the idle vehicles within a certain range corresponding to the location where the travel task to be assigned is published, thereby reducing the driver's pick-up time and idle driving distance, and improving the passenger waiting experience.

[0027] For each idle vehicle, several historical travel tasks, i.e., travel orders, have been executed within a preset historical time period. Each historical travel task executed by each idle vehicle can be obtained, and each historical travel task corresponds to the time, starting / ending location, travel distance, duration, cost, passenger rating, etc. The above data can be preprocessed and normalized to generate a feature vector corresponding to each historical travel task, and then clustered to obtain several profiles corresponding to the driver of each idle vehicle. Different categories of portraits for the same driver reflect differences in the driver's working hours, service preferences, income model, driving behavior, etc. It should be noted that those skilled in the art can use existing clustering methods to generate several profiles corresponding to the driver of each idle vehicle according to actual needs, and this will not be elaborated here.

[0028] S200, based on the external influencing factor value corresponding to each preset external influencing factor corresponding to each historical travel task contained in each portrait of each user and the external influencing factor value corresponding to each historical travel task of each driver, determine several main influencing external factors and main external influencing factor values ​​corresponding to each portrait of each user.

[0029] Furthermore, the preset external influencing factors include: traffic congestion factors, weather factors, road construction factors, time factors and hot event factors.

[0030] In this embodiment, when a driver is performing a certain historical travel task, the historical travel task corresponds to each preset external influencing factor at that time and the corresponding external influencing factor value; for example: when performing a certain historical travel task, the corresponding traffic is very congested, the weather factor is rainy, there is road construction, the time is eight o'clock in the morning, and there is no hot event; each preset external influencing factor corresponding to each historical travel task can be obtained, and then each external influencing factor is assigned a corresponding external influencing factor value.

[0031] Furthermore, the external influencing factor value is obtained by normalizing the external influencing factor.

[0032] In this embodiment, all external influencing factor values ​​can be processed as values ​​between 0 and 1. For example, each external influencing factor is first uniquely encoded and then normalized. It should be noted that those skilled in the art can use existing methods to normalize external influencing factors according to actual needs, which will not be elaborated here.

[0033] Furthermore, step S200 may include the following steps:

[0034] S210, obtaining the external influencing factor value corresponding to each preset external influencing factor corresponding to each historical travel task included in the specified portrait, so as to obtain a list set of external influencing factor values ​​corresponding to the specified portrait η = (η1, η2, ..., η i ,…,η f（i） ), i=1, 2,…, f(i); η i is a list of external influencing factor values ​​corresponding to the i-th historical travel task contained in the specified portrait, f(i) is the number of historical travel tasks contained in the specified portrait; η i =(η i，1 , η i，2 ,…,η i，p ,…,η i，q ), p = 1, 2, …, q; η i，p is the external influencing factor value of the pth preset external influencing factor corresponding to the i-th historical travel task contained in the specified portrait, and q is the number of preset external influencing factors.

[0035] In this embodiment, all historical travel tasks of a specified portrait (a clustered portrait of a certain driver) are collected; the preset external influencing factor values ​​corresponding to each historical travel task are extracted to form a structured data set; it can be understood that since the number of historical travel tasks corresponding to each portrait is different in this embodiment, f(i) does not refer to a specific function or function result value in this embodiment, but refers to a possible value that varies with the specific value of i. For example, when i=1, f(i)=300; when i=2, f(i)=400; when i=3, f(i)=300.

[0036] For example, a driver profile contains three historical tasks. The preset external factors are traffic congestion (factor 1), weather (factor 2), and time (factor 3). The normalized values ​​are as follows: Task 1: η1=(0.8, 0.5, 0.3); Task 2: η1=(0.7, 0.6, 0.4); Task 3: η1=(0.9, 0.4, 0.2); the corresponding external influencing factor value list set η=((0.8, 0.5, 0.3), (0.7, 0.6, 0.4), (0.9, 0.4, 0.2)).

[0037] S220, according to η, determine the deviation of each preset external influencing factor corresponding to the specified portrait, so as to obtain a list of external influencing factor deviations corresponding to the specified portrait λ = (λ1, λ2, ..., λ p ,…,λ q ); where λ p is the deviation of the pth preset external influencing factor corresponding to the specified portrait; p =((1 / f(i))∑ f(i) i=1 η i，p ) / γ p , γ p The average external influence factor value of the pth external influence factor corresponding to several historical travel tasks completed by the idle vehicle corresponding to the specified portrait.

[0038] In this embodiment, (1 / f(i))∑ f(i) i=1 η i，p It represents the mean value of the p-th preset external influencing factor value of all historical travel tasks corresponding to the specified portrait, γ p is the average external influence factor value of the pth external influence factor corresponding to several historical travel tasks completed by the idle vehicle corresponding to the specified portrait. Therefore, λ p It represents the degree of deviation between the value of the pth external influencing factor corresponding to the specified portrait and the overall value.

[0039] S230, traverse λ i , if |1-γp | / γ p >θ p , then the pth preset external influencing factor is determined as the main influencing external factor corresponding to the specified portrait, and the pth external influencing factor value μ corresponding to the specified portrait is determined p =(1 / f(i))∑ f(i) i=1 η i，p ; where θ p is the deviation threshold corresponding to the preset pth preset external influencing factor.

[0040] In this embodiment, if |1-γ p | / γ p >θ p , indicating that the pth external influencing factor of the specified portrait has a more significant impact on the specified portrait, and it is determined as the main influencing external factor; thus, all the main external influencing factors corresponding to each portrait can be determined, thereby clearly depicting the driver's travel task preferences under certain main external influencing factors, and improving the accuracy of subsequent matching.

[0041] The above method has at least the following technical effects:

[0042] 1. Dynamically capture key factors: Through deviation calculation, the system automatically identifies drivers' sensitive factors in different scenarios (such as a driver's sudden increase in orders on rainy days), avoiding manually preset deviations.

[0043] 2. Quantitative analysis improves accuracy: Normalization and mathematical formulas transform abstract factors into comparable numerical values, ensuring that decisions are based on objective data rather than subjective experience.

[0044] 3. Adapt to environmental changes: When external factors (such as sudden traffic control) cause drivers' behavior patterns to change, the system can quickly identify the new main factors and update the profile to avoid the invalidation of static profiles.

[0045] 4. Reduce computational redundancy: Perform subsequent matching only on key factors (such as step S400 ), avoiding meaningless computation on non-critical factors and improving system efficiency.

[0046] Steps S210-S230 dynamically identify the primary external factors influencing driver profiles through structured data collection, deviation analysis, and threshold determination. This process extracts key information from massive amounts of historical data, ensuring precise matching of task assignments to the current environment (e.g., prioritizing drivers skilled in inclement weather during rainy days). This significantly improves the matching of travel task assignments and system response efficiency.

[0047] S300: Obtain the current external influencing factor value and travel task characteristics of each preset external influencing factor corresponding to the travel task to be assigned.

[0048] In this embodiment, after the user distributes a travel task to be assigned, the location time corresponding to the travel task to be assigned can be obtained. Based on this, the current external influencing factor value of each preset external influencing factor and the travel task characteristics can be obtained; the travel task characteristics include travel distance, travel time, route preference, etc.

[0049] S400, if the current external influencing factor value of each preset external influencing factor corresponding to the travel task to be assigned and the main external influencing factor value corresponding to the designated portrait meet the preset matching conditions, the designated portrait is determined as the pending portrait; wherein the designated portrait is any portrait.

[0050] Furthermore, step S400 may include the following steps:

[0051] S410, obtaining the current external influencing factor value of each preset external influencing factor corresponding to the to-be-assigned travel task, so as to obtain a current external influencing factor value list B corresponding to the to-be-assigned travel task = (B1, B2, ..., B p ,…,B q ); Among them, B p The current external influencing factor value of the pth preset external influencing factor corresponding to the travel task to be assigned.

[0052] In this embodiment, based on the real-time data of the travel task to be assigned, the current values ​​of all preset external influencing factors corresponding to the task are extracted to generate List B; for example, assuming that the preset external factors are:

[0053] Traffic congestion (factor 1, value range 0 to 1, 1 indicates severe congestion);

[0054] Weather (factor 2, 0 = sunny, 1 = heavy rain);

[0055] time (factor 3, 0 = off-peak, 1 = morning and evening peak);

[0056] The environment of the current task is: traffic congestion index 0.8, heavy rain (weather value 0.9), non-peak period (time value 0.1), then: B=(0.8,0.9,0.1).

[0057] S420, determining the portraits whose differences between the corresponding values ​​of each main external influencing factor and the corresponding current external influencing factor value in B are within a preset range as intermediate portraits, so as to obtain an intermediate portrait list C = (C1, C2, ..., C x ,…,C y ), x=1, 2,…, y; where C xis the xth intermediate image determined, and y is the number of intermediate images determined.

[0058] In this embodiment, the portraits of all drivers and their main influencing factor values ​​(from step S230) are obtained; each portrait is traversed to check whether the difference between each of its main external influencing factor values ​​and the corresponding current external influencing factor value in B is within a preset range; if all conditions are met, the portrait is added to the intermediate portrait list C.

[0059] For example, there is only one main external influencing factor value for portrait 1, which is 0.75 for traffic congestion. There are three current external influencing factors, including 0.6 for traffic congestion. Therefore, we only need to find the difference between 0.75 and 0.6.

[0060] S430, traverse C, if C x If the corresponding user is different from the user corresponding to any other intermediate portrait in C, then C x Determined as pending portrait.

[0061] Traverse C. If the driver corresponding to a certain portrait does not overlap with other drivers in the list, then keep it. Finally, generate a list of unique pending portraits for the driver. In this way, only one portrait of the selected driver matches the travel task to be assigned, thereby improving the driver's success rate in accepting orders.

[0062] The method in the above steps has at least the following beneficial effects:

[0063] 1. Accurate environment matching:

[0064] By determining the difference between real-time external factors (such as heavy rain) and key profile factors (such as Driver X is good at driving in the rain), we ensure that task allocation is adapted to the current scenario and reduce matching failures caused by sudden environmental changes.

[0065] 2. Efficient screening mechanism:

[0066] Only key factors are matched (rather than all factors), significantly reducing computational effort. For example, if a profile only needs to match two key factors instead of all five, computational efficiency is increased by 60%.

[0067] 3. Optimization of driver resource deduplication:

[0068] Avoid the same driver being assigned tasks repeatedly because multiple profiles meet the requirements, and prevent resource waste (for example, driver X receives multiple orders at the same time, resulting in order conflicts).

[0069] Through real-time factor matching and driver profile deduplication, we ensure that task allocation is accurately adapted to the current environment (for example, orders are given priority to drivers who are good at bad weather on rainy days), while avoiding the same driver from receiving repeated orders, thereby improving the allocation success rate and the overall efficiency of the system.

[0070] S500 , determining a target portrait from the pending portraits according to the number of pending portraits, travel task features corresponding to the travel task to be assigned, and historical travel task features of all historical travel tasks corresponding to each pending portrait.

[0071] Furthermore, step S500 may include the following steps:

[0072] S510: If the number of pending portraits is greater than 1, obtain the average feature vector of the historical travel tasks corresponding to each pending portrait to obtain an average feature vector list D = (D1, D2, ..., D a ,…,D b ), a=1, 2, …, b; where D a is the average feature vector of the historical travel tasks corresponding to the a-th pending portrait, and b is the number of pending portraits.

[0073] In this embodiment, the historical task features of each pending portrait are averaged to generate an average feature vector.

[0074] S511, obtain the similarity between the feature vector DL ​​of the to-be-assigned travel task and each average feature vector in D, so as to obtain the similarity list ω=(ω1, ω2, ..., ω a ,…,ω b ); where ω a DL and D a The similarity between them.

[0075] In this embodiment, the cosine similarity may be used to determine the similarity between the feature vector DL ​​of the to-be-assigned travel task and each average feature vector in D.

[0076] S512, obtain the historical travel task execution density corresponding to each pending portrait, the historical travel task execution density list E = (E1, E2, ..., E a ,…,E b ); where E a is the historical travel task execution density corresponding to the a-th pending portrait; E a =NUM a / T a ;NUM a is the number of historical travel tasks corresponding to the a-th pending portrait, T a is the time interval between the earliest historical travel task and the latest historical travel task corresponding to the a-th pending portrait.

[0077] In this embodiment, through E a =NUM a / T a Quantify the driver's activity level in the corresponding scenarios of the portraits; for example: the first pending portrait: completed 30 tasks within 10 days, E1=30 / 10=3 tasks / day; the second pending portrait: completed 8 tasks within 5 days, E2=8 / 5=1.6 tasks / day; this can represent the willingness of different drivers to accept orders under the corresponding portraits.

[0078] S513, according to ω and E, determine the comprehensive weight corresponding to each pending portrait to obtain a comprehensive weight list ψ = (ψ1, ψ2, ..., ψ a ,…,ψ b ); where ψ a is the comprehensive weight corresponding to the a-th pending portrait; ψ a =α×ω a +β×E a / MAX(E); α is the first preset weight, β is the second preset weight; MAX() is the preset maximum value function; α+β=1.

[0079] In this embodiment, α and β are empirical values, which can be obtained through a large amount of data analysis, or dynamically optimized and adjusted through a preset model.

[0080] S514, traverse ψ, if ψ a ≥ψ', the idle vehicle corresponding to the a-th pending portrait is determined as the target idle vehicle; where ψ' is the preset comprehensive weight threshold.

[0081] In this embodiment, if ψ a ≥ψ', indicating that the driver corresponding to the a-th pending portrait has a strong willingness to accept the order in this scenario. Therefore, the corresponding idle vehicle is determined as the target idle vehicle; ψ' can be set according to actual needs.

[0082] S515: Push the order to be assigned to the target idle vehicle.

[0083] The above method has at least the following beneficial effects:

[0084] Accurate matching of task features: By averaging feature vectors (step S510) and calculating similarity (step S511), tasks are ensured to be assigned to drivers with the best historical performance (e.g., morning rush hour orders are given priority to drivers who excel at this time), thus reducing passenger waiting time.

[0085] Execution density assessment activity: High density (step S512) reflects the driver's efficient response ability in specific scenarios (e.g., high density on rainy days means drivers are familiar with the route and avoid waterlogging), which improves the task completion rate.

[0086] Multi-dimensional weight balance: The comprehensive weight formula (step S513) avoids relying solely on similarity or density. For example, α=0.6 focuses on task matching, and β=0.4 ensures driver activity and prevents inefficient drivers from being selected due to accidental high similarity.

[0087] Dynamic threshold control: The preset threshold ψ' (step S514) can be adjusted according to the system load (e.g., lowering the threshold during peak hours to expand the matching range), thereby enhancing system flexibility.

[0088] Resource utilization optimization: Combine historical data (feature vectors) with real-time density to reduce idle vehicle rates and improve overall operational efficiency.

[0089] Furthermore, step S500 further includes the following steps:

[0090] S520: If the number of pending portraits is 1, the pending order is allocated to the idle vehicle corresponding to the pending portrait.

[0091] In this embodiment, if the number of pending portraits is 1, it means that a unique match is found with one idle vehicle, and therefore the order to be assigned is assigned to the idle vehicle corresponding to the pending portrait.

[0092] S600: Allocate the travel task to be assigned to the idle vehicle corresponding to the target profile.

[0093] In this embodiment, there may be a situation where a travel task to be assigned is assigned to multiple idle vehicles. At this time, the driver can selectively accept the order according to his wishes, avoiding the situation where the travel task to be assigned cannot be assigned. At the same time, it can also improve the driver's order-taking experience.

[0094] In this embodiment, the travel task allocation method based on user portraits significantly improves the matching and efficiency of travel task allocation by dynamically constructing a multi-dimensional portrait of the driver and matching external influencing factors in real time. Specifically, cluster analysis is performed on the driver's historical travel tasks to generate dynamic portraits reflecting behavioral patterns in different scenarios, overcoming the rigidity of static portraits. By analyzing the correlation between historical data and real-time external factors (such as traffic and weather), the main influencing factors and their thresholds of each portrait are extracted to ensure that the current environmental changes are accurately matched when the task is allocated. Combined with the real-time characteristics of the task to be assigned and the similarity of the historical task characteristics of the portrait to be determined, the execution density and other comprehensive weight evaluations are combined to give priority to the most suitable vehicle, which not only reduces passenger waiting time but also improves vehicle utilization. At the same time, invalid scheduling is avoided through geographical location constraint screening. The method of the present invention realizes the upgrade from static experience-driven to dynamic data-driven, solves the core problem of mismatch between user profiles and real-time needs, improves the matching of travel task allocation, and makes travel task allocation more intelligent and precise.

[0095] Furthermore, although the steps of the method of the present disclosure are described in a particular order in the accompanying drawings, this does not require or imply that the steps must be performed in this particular order, or that all steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0096] An embodiment of the present invention also provides a non-transitory computer-readable storage medium, which can be set in an electronic device to store at least one instruction or at least one program related to implementing a method in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement the method provided in the above embodiment.

[0097] The program product may utilize any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0098] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0099] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0100] The program code for performing the operations of the present application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0101] An embodiment of the present invention further provides an electronic device including a processor and the aforementioned non-transitory computer-readable storage medium.

[0102] The electronic device is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0103] The electronic device is implemented as a general-purpose computing device. Components of the electronic device may include, but are not limited to, the aforementioned at least one processor, the aforementioned at least one memory, and a bus connecting different system components (including the memory and the processor).

[0104] The memory stores program codes, which can be executed by the processor, so that the processor performs the steps of various embodiments described in this specification.

[0105] The memory may include readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory, and may further include read-only memory (ROM).

[0106] The memory may also include a program / utility having a set (at least one) of program modules, such program modules including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0107] The bus may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

[0108] The electronic device may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface. Furthermore, the electronic device may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter. The network adapter communicates with other modules of the electronic device via a bus. It should be understood that, although not shown in the figures, other hardware and / or software modules may be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0109] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

[0110] An embodiment of the present invention further provides a computer program product comprising program code. When the program product is run on an electronic device, the program code is used to enable the electronic device to execute the steps of the method according to various exemplary embodiments of the present invention described above in this specification.

[0111] Although some specific embodiments of the present invention have been described in detail by way of examples, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It should also be understood by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the present invention.

Claims

1. A travel task allocation method based on user portrait, characterized in that: The following steps are involved: S100, clustering a number of historical travel tasks corresponding to any idle vehicle to obtain a number of profiles corresponding to the user of each idle vehicle; S200, determining a number of primary influencing external factors and their values ​​corresponding to each user's profile based on the external influencing factor value corresponding to each preset external influencing factor corresponding to each historical travel task included in each user's profile and the external influencing factor value corresponding to each historical travel task of each user; the preset external influencing factors include: traffic congestion factors, weather factors, road construction factors, time factors, and hot event factors; S300, obtaining the current external influencing factor value and travel task characteristics of each preset external influencing factor corresponding to the to-be-assigned travel task; S400, if the current external influencing factor value of each preset external influencing factor corresponding to the to-be-assigned travel task and the main external influencing factor value corresponding to the designated portrait meet a preset matching condition, then determining the designated portrait as a pending portrait; wherein the designated portrait is any portrait; S500, determining a target portrait from the pending portraits based on the number of pending portraits, the travel task characteristics corresponding to the to-be-assigned travel task, and the historical travel task characteristics of all historical travel tasks corresponding to each pending portrait; S600: Allocate the travel task to be assigned to the idle vehicle corresponding to the target profile.

2. The travel task allocation method based on user profile according to claim 1 is characterized in that: Step S200 includes the following steps: S210, obtaining the external influencing factor value corresponding to each preset external influencing factor corresponding to each historical travel task included in the specified portrait, so as to obtain a list set of external influencing factor values ​​corresponding to the specified portrait η = (η1, η2, ..., η i ,…,η f（i） ), i=1, 2,…, f(i); η i is a list of external influencing factor values ​​corresponding to the i-th historical travel task contained in the specified portrait, f(i) is the number of historical travel tasks contained in the specified portrait; η i =(η i，1 , η i，2 ,…,η i，p ,…,η i，q ), p = 1, 2, …, q; η i，p is the external influencing factor value of the pth preset external influencing factor corresponding to the i-th historical travel task contained in the specified portrait, and q is the number of preset external influencing factors; S220, according to η, determine the deviation of each preset external influencing factor corresponding to the specified portrait, so as to obtain a list of external influencing factor deviations corresponding to the specified portrait λ = (λ1, λ2, ..., λ p ,…,λ q ); where λ p is the deviation of the pth preset external influencing factor corresponding to the specified portrait; p =((1 / f(i))∑ f(i) i=1 η i，p ) / γ p , γ p The average external influence factor value of the pth external influence factor corresponding to several historical travel tasks completed by the idle vehicle corresponding to the specified portrait; S230, traverse λ i , if |1-γ p | / γ p >θ p , then the pth preset external influencing factor is determined as the main influencing external factor corresponding to the specified portrait, and the pth external influencing factor value μ corresponding to the specified portrait is determined p =(1 / f(i))∑ f(i) i=1 η i，p ; where θ p is the deviation threshold corresponding to the preset pth preset external influencing factor.

3. The travel task allocation method based on user profile according to claim 2 is characterized in that: Step S400 includes the following steps: S410, obtaining the current external influencing factor value of each preset external influencing factor corresponding to the to-be-assigned travel task, so as to obtain a current external influencing factor value list B corresponding to the to-be-assigned travel task = (B1, B2, ..., B p ,…,B q ); Among them, B p The current external influencing factor value of the pth preset external influencing factor corresponding to the travel task to be assigned; S420, determining the portraits whose differences between the corresponding values ​​of each main external influencing factor and the corresponding current external influencing factor value in B are within a preset range as intermediate portraits, so as to obtain an intermediate portrait list C = (C1, C2, ..., C x ,…,C y ), x=1, 2,…, y; where C x is the xth intermediate image determined, and y is the number of intermediate images determined; S430, traverse C, if C x If the corresponding user is different from the user corresponding to any other intermediate portrait in C, then C x Determined as pending portrait.

4. The method for allocating travel tasks based on user profiles according to claim 3, characterized in that: Step S500 includes the following steps: S510: If the number of pending portraits is greater than 1, obtain the average feature vector of the historical travel tasks corresponding to each pending portrait to obtain an average feature vector list D = (D1, D2, ..., D a ,…,D b ), a=1, 2, …, b; where D a is the average feature vector of the historical travel tasks corresponding to the a-th pending portrait, and b is the number of pending portraits; S511, obtain the similarity between the feature vector DL ​​of the to-be-assigned travel task and each average feature vector in D, so as to obtain the similarity list ω=(ω1, ω2, ..., ω a ,…,ω b ); where ω a DL and D a similarity between S512, obtain the historical travel task execution density corresponding to each pending portrait, the historical travel task execution density list E = (E1, E2, ..., E a ,…,E b ); where E a is the historical travel task execution density corresponding to the a-th pending portrait; E a =NUM a / T a ;NUM a is the number of historical travel tasks corresponding to the a-th pending portrait, T a is the time interval between the earliest historical travel task and the latest historical travel task corresponding to the a-th pending portrait; S513, according to ω and E, determine the comprehensive weight corresponding to each pending portrait to obtain a comprehensive weight list ψ = (ψ1, ψ2, ..., ψ a ,…,ψ b ); where ψ a is the comprehensive weight corresponding to the a-th pending portrait; ψ a =α×ω a +β×E a / MAX(E); α is the first preset weight, β is the second preset weight; MAX() is the preset maximum value function; α+β=1; S514, traverse ψ, if ψ a ≥ψ', the idle vehicle corresponding to the a-th pending portrait is determined as the target idle vehicle; where ψ' is the preset comprehensive weight threshold; S515: Push the travel task to be assigned to the target idle vehicle.

5. The method for allocating travel tasks based on user profiles according to claim 3, characterized in that: Step S500 further includes the following steps: S520: If the number of pending portraits is 1, the pending travel task is assigned to the idle vehicle corresponding to the pending portrait.

6. The method for allocating travel tasks based on user profiles according to claim 1, characterized in that: The distance between the position of the idle vehicle and the position to be assigned the travel task is within a preset distance range.

7. The travel task allocation method based on user portrait according to claim 1 is characterized in that: The external influencing factor value is obtained by normalizing the external influencing factor.

8. A non-transitory computer-readable storage medium, wherein at least one instruction or at least one program is stored in the storage medium, characterized in that: The at least one instruction or the at least one program is loaded and executed by the processor to implement the travel task allocation method based on user portrait as described in any one of claims 1-7.

9. An electronic device, characterized in that: The device comprises a processor and the non-transitory computer-readable storage medium of claim 8.

Images