Vehicle dispatching strategy evaluation method, device, electronic device and storage medium

Abstract

The present disclosure provides a vehicle scheduling strategy evaluation method, apparatus, electronic device, and storage medium. The vehicle scheduling strategy evaluation method includes: generating a vehicle operating state model for each section of the transport route based on the probability of a vehicle appearing on at least one section of the transport route; calculating a probability distribution of the vehicle operating state on each section of the transport route based on the vehicle scheduling strategy and the vehicle operating state model; and calculating performance parameters of the vehicle scheduling strategy based on the probability distribution of the vehicle operating state on each section of the transport route to evaluate the performance of the vehicle scheduling strategy.

Description

Technical Field

[0001] The present disclosure relates to the fields of artificial intelligence and vehicle scheduling. More specifically, the present disclosure provides an evaluation method, an optimization method, an evaluation device, an electronic device, and a storage medium for a vehicle scheduling strategy. Background Art

[0002] With the development of artificial intelligence (AI) technology, intelligent transportation systems are gaining increasing attention. These systems often require vehicles to operate along specific transportation routes (or roads). Vehicle scheduling is essential in these systems. The quality of vehicle scheduling strategies significantly impacts transportation efficiency. Current vehicle scheduling considerations often rely on deterministic factors to design and construct vehicle scheduling strategies. Summary of the Invention

[0003] An embodiment of the present disclosure provides a method for evaluating a vehicle scheduling strategy, comprising: generating a vehicle operating status model on each section of a transport route based on the probability of a vehicle appearing on at least one section of the transport route; calculating a probability distribution of the vehicle operating status on each section of the transport route based on the vehicle scheduling strategy and the vehicle operating status model; and calculating performance parameters of the vehicle scheduling strategy based on the probability distribution of the vehicle operating status on each section of the transport route to evaluate the performance of the vehicle scheduling strategy.

[0004] In some embodiments, the vehicle operating status model depends on the number of the vehicles and the number of segments of the transport route.

[0005] In some embodiments, the vehicle operating status model includes at least one of a single-vehicle route function for only a single vehicle operating on the same road segment, a multi-vehicle route function for multiple vehicles operating on the same road segment, and an abnormal event route function for abnormal events on the transportation route.

[0006] In some embodiments, the bicycle route function is f(o i-1 , o i )=p δt (o i |o i-1 ), where o i Indicates whether the vehicle appears on road section i, o i-1 Indicates whether the vehicle appears on road section i-1, p δt (o i |o i-1 =c) represents the probability that the vehicle will appear on road section i at time t+δt when the vehicle's appearance state on road section i-1 is c at time t, c∈{appeared, not appeared};

[0007] The multi-vehicle route function is in Indicates whether vehicle m appears on road section i, Indicates whether vehicle m appears on road section i-1, Indicates whether vehicle n appears on road section i-1, It means that at time t, vehicle m and vehicle n appear in the states of c on road section i-1 respectively. m and c n In the case of t+δt, the probability of vehicle m appearing on road section i is c m , c n ∈{appeared, not appeared};

[0008] The abnormal event circuit function is h(o i , e i-1 )=p δt (o i |e i-1 ), where o i Indicates whether the vehicle appears on road section i, e i-1 Indicates whether an abnormal situation occurs on road section i-1, where i is an integer greater than 1.

[0009] In some embodiments, when only a single vehicle is operating on the same road section, the probability distribution of the vehicle's operating time on the same road section is based on a Gaussian model, and / or when multiple vehicles are operating on the same road section, the probability distribution of the operating time of each of the multiple vehicles on the same road section is based on a Gaussian mixture model, and / or when an abnormal event occurs on a certain road section, the probability distribution of the vehicle's operating time on the road section is based on a Poisson distribution model.

[0010] In some embodiments, the calculation of the probability distribution of the vehicle's operating status on each section of the transportation route based on the vehicle scheduling strategy and the vehicle operating status model includes: initializing the operating status of the vehicle on each section at the first moment according to the vehicle scheduling strategy; and calculating the probability of the vehicle's operating status on each section at the first moment according to the vehicle operating status model.

[0011] In some embodiments, the calculation of the probability distribution of the vehicle's operating status on each section of the transportation route based on the vehicle scheduling strategy and the vehicle operating status model also includes: initializing the operating status of the vehicle on each section at the second or more moments according to the vehicle scheduling strategy; and calculating the probability of the vehicle's operating status on each section at the second or more moments according to the vehicle operating status model.

[0012] In some embodiments, the probability of a vehicle operating state on a road segment of a transportation route depends on the probability of an abnormal event occurring on a previous road segment of the road segment and the probability of a vehicle operating state on at least one road segment adjacent to the road segment.

[0013] In some embodiments, calculating the performance parameters of the vehicle scheduling strategy based on the probability distribution of the vehicle's operating status on each section of the transport route to evaluate the performance of the vehicle scheduling strategy includes: calculating the sum of the performance parameters of the vehicle scheduling strategy at multiple times based on the probability distribution of the vehicle's operating status on each section of the transport route at multiple times.

[0014] In some embodiments, the performance parameters of the vehicle scheduling strategy include: the transportation volume of the vehicle or the driving distance of the vehicle.

[0015] In some embodiments, the abnormal event includes a failure of a control unit inside the vehicle or a temporary obstacle that needs to be avoided on the road.

[0016] In some embodiments, the vehicle operating state model is directly established based on actual vehicle driving measurement data or is established by fitting parameters of a parameterized model according to the actual vehicle driving measurement data.

[0017] An embodiment of the present disclosure further provides a method for optimizing a vehicle scheduling strategy, comprising: evaluating a plurality of vehicle scheduling strategies using the method described in any of the aforementioned embodiments; and comparing the plurality of vehicle scheduling strategies to select a preferred strategy.

[0018] An embodiment of the present disclosure also provides an evaluation device for a vehicle scheduling strategy, comprising: a vehicle operating status generation module, for calculating the probability distribution of the vehicle's operating status on each section of the transport route based on the vehicle scheduling strategy and the vehicle operating status model on each section of the transport route, wherein the vehicle operating status model is generated based on the probability of the vehicle appearing on at least one section of the transport route; and a performance calculation module, for calculating the performance parameters of the vehicle scheduling strategy based on the probability distribution of the vehicle's operating status on each section of the transport route to evaluate the performance of the vehicle scheduling strategy.

[0019] In some embodiments, the vehicle operating status model includes at least one of a single-vehicle route function for only a single vehicle operating on the same road segment, a multi-vehicle route function for multiple vehicles operating on the same road segment, and an abnormal event route function for abnormal events on the transportation route.

[0020] In some embodiments, the vehicle operating status generation module includes: an initialization module for initializing the operating status of the vehicle on each road section at the first moment according to the vehicle scheduling strategy; and a probability calculation module for calculating the probability of the vehicle operating status on each road section at the first moment according to the vehicle operating status model.

[0021] In some embodiments, the initialization module is further configured to initialize the operating status of the vehicle on each road section at the second or more moments according to the vehicle scheduling strategy; and the probability calculation module is further configured to calculate the probability of the vehicle operating status on each road section at the second or more moments according to the vehicle operating status model.

[0022] In some embodiments, the probability of a vehicle operating state on a road segment of a transportation route depends on the probability of an abnormal event occurring on a previous road segment of the road segment and the probability of a vehicle operating state on at least one road segment adjacent to the road segment.

[0023] In some embodiments, the performance calculation module is configured to calculate the sum of performance parameters of the vehicle scheduling strategy at multiple times based on the probability distribution of the vehicle's operating status on each section of the transportation route at multiple times, and the performance parameter is the vehicle's transportation volume or the vehicle's driving distance.

[0024] In some embodiments, the vehicle scheduling strategy evaluation device further includes: a data acquisition module for acquiring actual vehicle driving measurement data for constructing the vehicle operation status model.

[0025] An embodiment of the present disclosure also provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method described in any one of the aforementioned embodiments.

[0026] An embodiment of the present disclosure further provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the method described in any one of the aforementioned embodiments.

[0027] An embodiment of the present disclosure further provides a computer program product, including a computer program, which implements the method described in any of the aforementioned embodiments when executed by a processor.

[0028] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0030] Figure 1 is a schematic diagram of a bicycle route probability graph model according to one embodiment of the present disclosure;

[0031] Figure 2 is a schematic diagram of a multi-vehicle route probability graph model according to one embodiment of the present disclosure;

[0032] Figure 3 is a schematic diagram of a bicycle route probability graph model taking abnormal events into consideration according to another embodiment of the present disclosure;

[0033] Figure 4 is a schematic diagram of a multi-vehicle route probability graph model taking abnormal events into consideration according to yet another embodiment of the present disclosure;

[0034] Figure 5 is a flow chart of a method for evaluating a vehicle scheduling strategy according to one embodiment of the present disclosure;

[0035] Figure 6 is a flow chart of a method for optimizing a vehicle scheduling strategy according to an embodiment of the present disclosure;

[0036] Figure 7 is a schematic diagram of a vehicle scheduling strategy evaluation device according to an embodiment of the present disclosure;

[0037] Figure 8 is a schematic diagram of a vehicle transportation route according to one embodiment of the present disclosure;

[0038] Figure 9 This is a first schematic diagram of calculating the vehicle appearance probability of each road section on a transportation route in a vehicle scheduling strategy evaluation method according to an embodiment of the present disclosure;

[0039] Figure 10 This is a second schematic diagram of calculating the vehicle appearance probability of each road section on a transportation route in the vehicle scheduling strategy evaluation method according to one embodiment of the present disclosure;

[0040] Figure 11 is a system block diagram for implementing remote control of a vehicle scheduling strategy evaluation method or optimization method according to another embodiment of the present disclosure; and

[0041] Figure 12 The present invention is a block diagram of an electronic device for implementing a vehicle dispatching strategy evaluation method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0042] To more clearly illustrate the objectives, technical solutions, and advantages of the present disclosure, embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the following description of the embodiments is intended to explain and illustrate the overall concept of the present disclosure and should not be construed as limiting the present disclosure. In the specification and drawings, the same or similar reference numerals refer to the same or similar parts or components. For the sake of clarity, the drawings are not necessarily drawn to scale, and some well-known parts and structures may be omitted in the drawings.

[0043] Unless otherwise defined, technical or scientific terms used in this disclosure should have the ordinary meaning understood by a person of ordinary skill in the art to which this disclosure belongs. The terms "first," "second," and similar terms used in this disclosure do not denote any order, quantity, or importance, but are simply used to distinguish different components. The terms "a" or "an" do not exclude a plurality. Terms such as "include" or "comprise" mean that the element or object preceding the term includes the elements or objects listed after the term and their equivalents, but do not exclude other elements or objects. Terms such as "connected" or "connected" are not limited to physical or mechanical connections but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," "right," "top," or "bottom" are used only to indicate relative positional relationships; if the absolute position of the described objects changes, the relative positional relationship may also change accordingly. When an element such as a layer, film, region, or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element, or intervening elements may be present.

[0044] In a transportation system, multiple vehicles are often required and multiple road sections are involved. Planning the vehicle's route and departure intervals, etc., requires a good vehicle scheduling strategy. The vehicle scheduling strategy is a design for when each vehicle appears on a certain section of the transportation route. A good vehicle scheduling strategy can make better use of transportation resources, improve transportation efficiency and reduce costs. However, the vehicle scheduling strategy not only needs to consider theoretical route planning, but also various complex situations of vehicle driving on the transportation section, such as vehicle speed fluctuations, vehicle breakdowns, obstacles on the road (such as people, other vehicles, fallen rocks, etc.), vehicle congestion, etc. For vehicle transportation systems in scenarios with more severe and complex road environments such as open-pit mines, the impact of uncertainty in vehicle driving on vehicle scheduling is more important. The embodiments of the present disclosure provide a method for evaluating a vehicle scheduling strategy, which can be used to evaluate the performance of a vehicle scheduling strategy. In this method, the uncertainty factors in vehicle driving are taken into account, and the performance of the vehicle scheduling strategy can be evaluated more accurately.

[0045] In one embodiment of the present disclosure, Figure 5 As shown, the evaluation method may include:

[0046] Step S1: generating a vehicle operation state model on each section of the transport route based on the appearance probability of the vehicle on at least one section of the transport route;

[0047] Step S2: Calculating the probability distribution of the vehicle's operating status on each section of the transport route based on the vehicle scheduling strategy and the vehicle operating status model; and

[0048] Step S3: Calculating performance parameters of the vehicle scheduling strategy based on the probability distribution of the vehicle's operating status on each section of the transport route to evaluate the performance of the vehicle scheduling strategy.

[0049] In the embodiments of the present disclosure, the transportation route may include only one or more independent roads, or may include roads that intersect with each other, for example, forming a transportation road network. Figure 8 Examples of transport routes are given. Figure 8 There are two roads, namely the first road R1 and the second road R2. The two roads intersect at point A. Each road is divided into corresponding sections. Figure 8 In the example shown, seven road sections are shown, namely, section 1, section 2, section 3, section 4, section 5, section 6, and section 7. In the embodiments of the present disclosure, the division of the transport route is not limited to the above examples, but may have one or more road sections of various shapes. Assuming the ideal situation, the travel time of a vehicle on each road section is fixed and there are no other uncertain factors, then it is possible to clearly arrange the vehicle to appear on that road section at each moment. However, as mentioned above, the influence of various uncertain factors (such as road obstacles, equipment failures, queues and traffic jams, etc.) during the vehicle's travel process cannot be ignored. In particular, when the vehicle travels a long distance or the road conditions are relatively complex, the vehicle's travel time on a certain road section is not completely certain. Therefore, in the above embodiments of the present disclosure, a vehicle operation status model for each road section of the transport route is introduced based on the probability of the vehicle appearing on the road section. The vehicle operation status model can be used to construct and evaluate vehicle scheduling strategies. The vehicle operation status model can be statistically modeled by random factors.

[0050] As an example, the vehicle operating state model described above may depend on the number of vehicles and the number of sections of the transport route. When multiple vehicles are present, there may be interactions between them, thereby changing the probability of a vehicle appearing on a particular section. Similarly, when the number of sections varies, this may also affect the probability of a vehicle appearing on different sections of the transport route.

[0051] In some embodiments, the vehicle operation state model can be established based on three situations. The first situation is single-vehicle driving, that is, only considering the situation of a single vehicle driving. In the case of single-vehicle driving, a statistical model of the operation time of each transport section can be constructed based on the historical operation data of each vehicle. According to the actual situation of different routes, the probability distribution function (such as Gaussian distribution function, etc.) is used to fit the data to complete the construction of the statistical model. The model is recorded as p 单车 (t), that is, the probability of completing the road section within t time under the condition of a single vehicle.

[0052] The following example uses the Gaussian distribution function as an example to give an example of a probability model for a single vehicle. When using the Gaussian distribution function to build a model, if the historical operating data of the vehicle is sufficient, the model parameters can be directly built based on the fitting of the historical operating data, that is, the mean and variance of the Gaussian distribution model can be solved. The following example illustrates that there are N historical data samples, and the data of a single vehicle running time on a certain road section is t i , where i∈{1,...,N}, calculate:

[0053]

[0054] is the mean of the Gaussian distribution, calculate

[0055]

[0056] is the variance of the Gaussian distribution.

[0057] From this we can get

[0058] When historical operating data is insufficient, the model can be constructed through attribution. For example, the mean of the Gaussian probability distribution is calculated based on the vehicle's calibrated operating speed and calibrated road section length, and the variance of the Gaussian probability distribution is calculated based on the time jitter caused by vehicle load deviation, vehicle control error, and road conditions. The probability distributions of these jitters can be fitted based on actual measurement data.

[0059] It should be noted that the probability model for single-vehicle travel is not limited to a Gaussian distribution; it can also be based on other probability distribution models, such as a uniform distribution, depending on the situation. For more complex situations, the probability model for single-vehicle travel can also include a series of sub-models. For example, the time jitter caused by road conditions can be divided into sub-models for straight sections, uphill routes, downhill routes, and curved routes.

[0060] The second situation is the meeting situation, that is, there are multiple vehicles driving on the same road section at the same time. This situation is more complicated than single-vehicle driving. In this case, the vehicle operation characteristics, road characteristics and meeting rules can be used to construct a meeting time statistical model for each vehicle in each transport section when a meeting occurs. As an example, based on the operating status of different vehicles (such as full / empty, manned / unmanned) and vehicle control information (such as speed limit, road rights), a mixed probability distribution function (such as a mixed Gaussian model, etc.) can be used to fit historical data to complete the construction of the statistical model. This model is denoted as p 会车 (t), that is, the probability of completing the driving of the road section within time t under the condition of meeting other vehicles.

[0061] The following example uses the Gaussian mixture probability model as an example to give an example of a probability model for a meeting situation. In the process of model construction using the Gaussian mixture probability model, when there is sufficient historical operating data, the model parameters can be directly constructed based on the fitting of the historical operating data, that is, the mean and variance of each Gaussian probability model in the Gaussian mixture probability model are solved, and the number of Gaussian models in the Gaussian mixture probability model is optimized; the following example illustrates that there are N historical data samples in total, and the time data for the vehicle to complete the driving of the road section in the meeting situation is t i , where i∈{1,...,N}, the parameterized Gaussian mixture model is constructed as:

[0062]

[0063] Among them, the parameter M represents the number of Gaussian probability models in the Gaussian mixture model, and the initialization parameter And complete the following P iterations in total, where the kth iteration step is calculated as follows:

[0064] For any sample t i calculate:

[0065]

[0066] Calculate the new parameters:

[0067]

[0068]

[0069]

[0070]

[0071] Starting from the initial value, repeat the above steps P times, or calculate until the function This is done until convergence is achieved. In this way, the various parameters in the above model are determined.

[0072] When historical operating data is insufficient, the model can be constructed by attribution, that is, a mixed Gaussian probability model is constructed based on the Gaussian probability model of a single vehicle, where the number of Gaussian probability models is the number of vehicles involved in the meeting.

[0073] The third situation is the abnormal event situation, that is, the situation where various abnormal events occur when the vehicle is driving on the road, such as falling rocks, people, other vehicles, vehicle control failure, communication failure, etc. These abnormal events may cause the time it takes for the vehicle to pass a certain section to be extended. In this case, the characteristics of abnormal events occurring in each transport section are used to construct a statistical model using a probability distribution function (such as the Poisson distribution model). This model is denoted as p 异常 (t), that is, the probability that the vehicle will complete the operation of the road section within t time when an abnormality occurs in the road section. The reasons for the abnormality occurring in each road section may be different. The time interval distribution of the occurrence of abnormal events can be, for example, a Poisson distribution, and its parameters are obtained by measuring historical data. As an example, the specific measurement method of the data is as follows: during the operation of the vehicle, abnormal events are captured based on the on-board perception unit, including but not limited to using cameras, lidars, millimeter-wave radars and other perception equipment to detect falling rocks, vehicles and personnel entering the lane, etc., and recording the time and place of the event, which is recorded as external abnormal event data; using the vehicle's internal control unit to capture events such as vehicle control failure and communication failure, and recording the time and place of the event, which is recorded as internal abnormal event data; using the Poisson distribution model to fit the external abnormal event data and the internal abnormal event data, respectively, to obtain the Poisson distribution model of the abnormal event. The following example illustrates that there are N historical data samplings, and the time delay caused by a single abnormal event is t i , where i∈{1,...,N}, the parameterized Poisson model is constructed as:

[0074]

[0075] in:

[0076]

[0077] Based on the analysis of the above three situations, the vehicle operation state model can be established for any of the above situations, or it can be established by considering two or three of the above situations simultaneously. As an example, the vehicle operation state model can include at least one of a single-vehicle route function for a single vehicle operating on the same road section, a multi-vehicle route function for multiple vehicles operating on the same road section, and an abnormal event route function for abnormal events on the transport route. The single-vehicle route function corresponds to the above-mentioned single-vehicle driving situation, the multi-vehicle route function corresponds to the above-mentioned meeting situation, and the abnormal event route function corresponds to the above-mentioned abnormal event situation.

[0078] Figure 1 A schematic diagram of a single-vehicle route probability graph model according to an embodiment of the present disclosure is shown. The complete transport route is divided into K sections, and the single-vehicle route probability graph model can represent the driving state of a single vehicle in the complete section. Constructing a single-vehicle route function f(o i-1 , o i )=p δt (o i |o i-1 ), where o i Indicates whether the vehicle appears on road section i, o i-1 Indicates whether the vehicle appears on road section i-1, p δt (o i |o i-1 =c) represents the probability that the vehicle will appear on road section i at time t+6t, given that the vehicle's appearance state on road section i-1 is c at time t, c∈{appeared, not appeared}. This probability distribution follows the following characteristics:

[0079] p δt (o i =appear|o i-1 = not present) = 0 (Formula 1)

[0080] p δt (o i =Not Appeared|o i-1 = not present) = 1 (Formula 2)

[0081]

[0082]

[0083] according to Figure 1 The probability of a vehicle appearing on each road section when a single vehicle is traveling can be calculated in sequence based on the single vehicle route function. Figure 1 o1, o2, o3, o K-1 、o KThey respectively indicate whether the vehicle appears on section 1, section 2, section 3, section K-1 and section K. Figure 1 The square in corresponds to the bicycle route function that reflects the relationship between the vehicle appearance probability between two adjacent road sections. Figure 1 The probability graph model shown and the probability model of the time it takes for a vehicle to pass through a road section in the aforementioned single-vehicle driving case can be used to derive a probability model of the complete vehicle operation route in the single-vehicle driving case.

[0084] Figure 2 A schematic diagram of a multi-vehicle route probability graph model according to an embodiment of the present disclosure is shown. The complete transport route is also divided into K road segments. The multi-vehicle route probability graph model can represent the driving status of multiple vehicles on a road segment when they are running together. Constructing a multi-vehicle route function in Indicates whether vehicle m appears on road section i, Indicates whether vehicle m appears on road section i-1, Indicates whether vehicle n appears on road section i-1, It means that at time t, vehicle m and vehicle n appear in the states of c on road section i-1 respectively. m and c n In the case of t+δt, the probability of vehicle m appearing on road section i is c m , c n ∈{appeared, not appeared}. This probability distribution follows the following characteristics:

[0085]

[0086]

[0087]

[0088]

[0089]

[0090]

[0091] As can be seen from Equations 5 through 10 above, when considering multi-vehicle routes, both single-vehicle and inter-vehicle scenarios may occur on a road segment. Therefore, when calculating the probability of vehicles being distributed on each road segment in a multi-vehicle scenario, it is necessary to consider the probability distribution models for both single-vehicle and inter-vehicle scenarios.

[0092] Figure 2 in They respectively indicate whether vehicle m appears on section 1, section 2, section K-1 and section K. They respectively indicate whether vehicle n appears on section 1, section 2, section K-1 and section K. Figure 2 The squares in correspond to the multi-vehicle route function that reflects the relationship between the vehicle appearance probabilities between two adjacent road sections.

[0093] exist Figure 2 In the above equation, we no longer consider the travel of a single vehicle, but consider the mutual influence of the probability of two vehicles (vehicle m and vehicle n) appearing on each road section. Figure 2 The probability graph of is more complicated. Figure 2 The probability graph model shown in the figure and the probability model of the time it takes for a vehicle to pass through a road section in the case of a single vehicle and the probability model of the time it takes for a vehicle to pass through a road section in the case of a vehicle passing through another vehicle can be used to derive a probability model of the complete vehicle route in the case of multiple vehicles. Figure 2 The above example only illustrates the case where the probability of occurrence of vehicle m and vehicle n on a road segment affects each other. Of course, the embodiments of the present disclosure are not limited to this. The multi-vehicle route function can also be used to represent more complex probability distributions where three or more vehicles may appear on the same road segment.

[0094] Figure 3 A schematic diagram of a bicycle route probability graph model taking abnormal events into consideration according to another embodiment of the present disclosure is shown, wherein the complete transportation route is also divided into K sections. Figure 3 is Figure 1 The probability model of abnormal events is combined with the probability diagram shown in the figure. The abnormal event circuit function h(o i , e i-1 )=p δt (o i |e i-1 ), where o i Indicates whether the vehicle appears on road section i, e i-1 Indicates whether an abnormal situation occurs in the road section i-1, i is an integer greater than 1. Figure 3 In the equation, e1 and e K-1 Respectively indicate whether abnormal events occur on section 1 and section K-1. Figure 3 As shown, whether an abnormal event occurs on the previous road segment, causing a vehicle delay, will affect the probability of vehicle appearance on the subsequent road segment. This influence can be represented by the abnormal event line function described above. For the probability model in the event of an abnormal event, please refer to the previous content and will not be repeated here.

[0095] Figure 4A schematic diagram of a multi-vehicle route probability graph model considering abnormal events according to another embodiment of the present disclosure is shown, wherein the complete transport route is also divided into K sections. Figure 4 is Figure 2 The probability diagram shown is based on the probability model of abnormal events. Figure 4 middle, and Indicates whether abnormal events related to vehicle n occur on road section 1 and road section K-1, and Respectively indicate whether abnormal events related to vehicle m occur on road section 1 and road section K-1. Figure 4 As shown, whether an abnormal event related to a particular vehicle on the previous road segment causes a travel delay will affect the probability of that vehicle appearing on the subsequent road segment. This influence can also be represented by the abnormal event circuit function described above. An abnormal event may be related only to a particular vehicle, such as a vehicle failure, or it may be related to all vehicles on a particular road segment, such as an obstacle such as a fallen rock. The probability model for abnormal events can be found in the previous section and will not be elaborated here.

[0096] In an embodiment of the present disclosure, the abnormal event includes, for example, a failure of a control unit inside the vehicle or a temporary obstacle that needs to be avoided on the road.

[0097] The vehicle operating state models under various circumstances have been discussed above. Figures 1 to 4 The illustrated probability graph models can be considered exemplary vehicle operating state models. However, the embodiments of the present disclosure are not limited thereto. Other probability models can also be used to construct a vehicle operating state model based on the actual transportation route and vehicle conditions.

[0098] In some embodiments, the vehicle operating state model is established directly based on actual vehicle travel measurement data or by fitting parameters of a parameterized model based on the actual vehicle travel measurement data. For example, onboard or remote information recording systems can be used to collect real-time time and location information during vehicle travel, and onboard cameras, lidar, millimeter-wave radar, and other sensing devices can be used to obtain warning information about abnormal events such as obstacles on the road section. As an example, the vehicle travel time for each road section can be calculated based on prior map information and time and location information provided by the onboard information collection module. A single vehicle travel time probability model can be constructed by repeatedly traveling on the same road section. This model can be constructed incrementally, with the accuracy of the model continuously adjusted as more samples are collected. As an example, a meeting travel time model can be constructed based on oncoming vehicle information obtained from the onboard information transmission module and time and location information provided by the onboard information collection module, and by repeated oncoming events on the same road section. This model can be constructed incrementally, with the accuracy of the model continuously adjusted as more samples are collected.

[0099] In some embodiments, the probability of a vehicle operating state on a segment of a transport route depends on the probability of an abnormal event occurring on the previous segment and the probability of a vehicle operating state on at least one adjacent segment. Figure 3 In the example shown, at node o2 (o2 indicates whether the vehicle appears on road section 2, i.e., the vehicle's operating status on road section 2), the probability p(o2) of the vehicle's operating status depends on the probability p(e1) of an abnormal event occurring on road section 1 and the probability p(o1) of the vehicle's operating status on road section 1. For another example, Figure 4 In the example shown, in the node ( Indicates whether vehicle m appears on road section 2, that is, the running state of vehicle m on road section 2), the probability of vehicle m's running state Depends on the probability of an abnormal event occurring on road segment 1 and the probability of vehicle m’s vehicle operation status on road section 1 and the probability of vehicle n’s vehicle operation status on road segment 1

[0100] The construction and evaluation of vehicle scheduling strategies are discussed below.

[0101] According to the variables involved in the probability diagram discussed above, the state of the entire transport line can be fully described, such as the state matrix O (t) And give it the following form.

[0102]

[0103] Each row represents the state of a vehicle on the transport road at time t, and the elements Represents whether vehicle m appears on road section i. This matrix has the following characteristics:

[0104] There is no more than one non-zero element in each row, which means that a vehicle will not appear on two road sections at the same time.

[0105] The vehicle scheduling strategy can be mapped to a specific state matrix O (t) , as planned at time t l If vehicle i is dispatched and enters the transport road from section k, then the state matrix Elements in is assigned a value of 1. l The vehicle scheduling policy executed at each moment is represented as a vector This vector specifies the road segment location where each vehicle is expected to appear at time t1. Where N represents the total number of road segments, Indicates that the i-th road segment is at t l By defining a vehicle scheduling strategy vector over a continuous time period, a pre-determined scheduling strategy for a specific vehicle can be given. The vehicle scheduling strategy corresponding to a certain moment reflects the distribution of vehicles on each road segment at that moment.

[0106] by Figure 8 As an example, the transport route shown in , which includes 7 sections, namely Section 1, Section 2, Section 3, Section 4, Section 5, Section 6 and Section 7. Based on this, the vehicle scheduling strategy vector can be defined as a vector with 7 elements. As an example, assuming that the vehicle scheduling strategy vectors at time 0, time 1, time 2, time 3, time 4 and time 5 can be s respectively. (0) =[1,0,0,0,0,0,0] T , s (1) =[0,1,0,0,0,0,0] T , s (2) =[0,0,1,0,2,0,0] T , s (3) =[0, 1, 0, 2, 0, 0, 0] T , s (4) =[1,0,0,0,0,2,0] T , s (5) =[0, 1, 0, 0, 0, 2] T. That is to say, vehicle 1 (represented by the number 1 in the vector) is located at section 1 at time 0, section 2 at time 1, section 3 at time 2, section 2 at time 3, section 2 at time 4, section 1 at time 4, and section 2 at time 5; while vehicle 2 (represented by the number 2 in the vector) does not appear in any section at time 0 and time 1, is located at section 5 at time 2, section 4 at time 3, section 6 at time 4, and section 7 at time 5. To summarize, the vehicle scheduling strategy vector at the above 6 moments represents the scheduling of vehicle 1 from time 0 to time 5 along the route: section 1 → section 2 → section 3 → section 2 → section 1 → section 2, while vehicle 2 starts to enter the running state at time 2, and runs from time 2 to time 5 along the route: section 5 → section 4 → section 6 → section 7. The impact of this scheduling strategy on the state matrix can be expressed as the conditional probability Consider the cutoff t l The scheduling strategy for all moments before the moment, then the impact of the overall scheduling strategy on the state matrix can be expressed as in is the set of scheduling policies at all times.

[0107] The state matrix O of the system at any time t+δt (t+δt) The probability distribution p(O (t+δt) |S (t+δt) ) can be represented by the state matrix O at time t (t) The conditional probability distribution p(O (t) |S (t) ), the latest vehicle scheduling strategy for the state matrix O (t+δt) The conditional probability p(O (t+δt) |s (t+δt) ) and bicycle route function f(o i-1 , o i ), multi-vehicle route function and abnormal event circuit function h(o i , e i-1 ) calculated.

[0108] In some embodiments, the calculation of the probability distribution of the vehicle's operating status on each section of the transport route based on the vehicle scheduling strategy and the vehicle operating status model in step S2 includes:

[0109] Step S21: Initializing the running status of the vehicles on each road section at the first moment according to the vehicle dispatching strategy; and

[0110] Step S22: Calculating the probability of the vehicle running state on each road section at the first moment according to the vehicle running state model.

[0111] For the calculation of the probability of the vehicle running state on each road section at the first moment, the nodes in the probability graph model can be used for iterative calculation. Figure 3 The specific calculation method is described by taking the bicycle route probability graph model taking abnormal events into consideration as an example.

[0112] First, perform step 1, that is, according to a certain vehicle scheduling strategy, each node o in the probability graph model is i Initialize. Then, the initial node function p(o i )(i.e. node o i The probability of abnormal events is initialized using the probability model of abnormal events. j (j>1) nodes, the node function p(e j )(i.e. node e j Using the initialization value, calculate the initial message (such as Figure 9 Indicated by the arrow in the middle. Figure 9 In the example, a function node f is set between node o1 and node o2. a , set the function node f between node o2 and node o3 b And set function node g between node o2 and node e1 u .by Figure 9 For example, the node o2 is connected to the function node f a Send message m 2，a (Can be recorded as m 2，a (o2)), to the function node f b Each sent message m 2，b (Can be recorded as m 2，b (o2)). In the initial state, that is, Figure 9 In the state shown, the message sent is calculated as follows:

[0113] m 2，a (o2) = p(o2) (Formula 12)

[0114] m 2，b (o2) = p(o2) (Formula 13)

[0115] Similarly, all o i The messages sent by a node are equal to the initial node function p(o i ), similarly, all e i The messages sent by a node are equal to the initial node function p(e i ),thus, Figure 9 All messages marked with arrows can be calculated.

[0116] Next, proceed to step 2 to calculate each function node f m (fm express Figure 9 As shown in the node o i-1 and node o i Function nodes between them such as f a 、f b ...f L etc.) nodes and g n (g n express Figure 9 As shown in the node e i-1 and node o i Function nodes between g u ...g v The message sent by the node is f a Node 1 receives message m from node o1. 1，a (Can be recorded as m 1，a (o1)), after the function f a (o1, o2)(here, f a (o1, o2) corresponds to the conditional probability p(o2|o1)) and the message sent to the o2 node is calculated as follows:

[0117]

[0118] Similarly, all f m Node and g n All messages sent by nodes can be calculated.

[0119] Then proceed to step 3 to update each o i The message at the node. Figure 10 Taking node o2 as an example, the neighboring nodes f a Node, f b Node and g n After receiving a new message, node o2 can update the message it sends. a The node receives message m a，2 (o2) and from g u The node receives message m u，2 After (o2), node o2 can update message m 2，b (o2), the message is calculated as follows:

[0120] m 2，b (o2)=m a，2 (o2)*m u，2 (o2) (Formula 15)

[0121] Similarly, all o i Each node can update messages sent to all its neighboring nodes.

[0122] After all oi nodes are updated with messages sent to all their adjacent nodes, each function node f is recalculated and updated. m Node and g n The message sent by the node. When updating each function node f m Node and g n After the message is sent by the node, all o i The node sends a message to all its neighboring nodes. Repeat steps 2 and 3 until all messages no longer change, or until the iteration (repeated execution of steps 2 and 3) reaches a certain number of times (for example, more than 100 times or more than 10,000 times).

[0123] After completing the above iterative operation, calculate each o i The posterior probability of the node, taking node o2 as an example:

[0124] p(o2)=m a，2 (o2)*m b，2 (o2)*m u，2 (o2) (Formula 16)

[0125] That is o i The posterior probability of a node is the product of the most recent messages received from all its neighboring nodes. Similarly, all o i The posterior probability of each node can be calculated, so as to obtain the probability value of the vehicle appearing on the road section, that is, the probability of the vehicle running state on each road section at a certain moment. i-1 The above message relationship can also be established between nodes and adjacent function nodes. For example, node e1 can send a u Node sends message m e1，u , from g u Node receives message m u，e1 The specific calculation method is the same as o i The nodes are similar and will not be described here.

[0126] The use of the above algorithm helps to reduce the complexity of system implementation and realize parallel computing.

[0127] It should be noted that for the sake of convenience, the above is only Figure 3 The single-vehicle route probability graph model considering abnormal events is used as an example for introduction. However, the embodiments of the present disclosure are not limited thereto. For other vehicle operation state models (e.g. Figure 4 ) can also be calculated according to the above method. The calculation method of the probability of the vehicle operating state according to the present disclosure is not limited to the above method. Other calculation methods known in the art can also be used to calculate the probability of the above vehicle operating state at a certain moment.

[0128] As mentioned above, in step S22, the probability of the vehicle operating state on each road section at the first moment can be calculated based on the vehicle operating state model, which can provide a basis for evaluating the performance of the vehicle scheduling strategy.

[0129] In some embodiments, when evaluating the performance of a vehicle scheduling strategy, the probability of vehicle operating states on each road segment at multiple moments is required. In this case, in addition to steps S21 and S22, step S2 may further include:

[0130] Step S23: Initializing the running status of the vehicles on each road section at the second or more time points according to the vehicle dispatching strategy; and

[0131] Step S24: Calculating the probability of the vehicle running state on each road section at the second or more time points according to the vehicle running state model.

[0132] The specific calculation method of steps S23 and S24 is similar to the calculation of the aforementioned steps S21 and S22, and will not be repeated here.

[0133] In some embodiments, as described above, in step S3, performance parameters of the vehicle scheduling strategy are calculated based on the probability distribution of the operating status of the vehicles on each section of the transportation route to evaluate the performance of the vehicle scheduling strategy. The performance parameters of the vehicle scheduling strategy can be any parameters that can be used to measure the transportation efficiency or cost of the vehicle. As an example, the performance parameters of the vehicle scheduling strategy may include the total distance traveled by the vehicle, the transportation volume of the vehicle, etc. In some embodiments, step S3 may include: calculating the sum of the performance parameters of the vehicle scheduling strategy at multiple times based on the probability distribution of the operating status of the vehicles on each section of the transportation route at multiple times.

[0134] When evaluating the performance of a vehicle scheduling strategy, it is often necessary to calculate the overall status of performance parameters within a certain period of time, such as calculating the sum of performance parameters at multiple moments. As an example, the state matrix O at time t mentioned above can be used. (t) (See formula 11) The conditional probability distribution p(O (t) |S (t) ) to complete the scheduling strategy S (t) The operation history of all dispatched vehicles under the conditions of the dispatched vehicle can be evaluated, so as to further calculate the performance parameters such as the travel distance and transportation volume of the dispatched vehicles.

[0135] The specific calculation method of vehicle driving distance is as follows:

[0136] Assume that the segment length vector is L = [l1 … l K ] T , where l1 … l KRepresent the lengths of sections 1 to K respectively, and calculate the travel distance vector:

[0137]

[0138] Then the total travel distance of vehicle m on K road segments is the mth element of vector d.

[0139] The specific calculation method of vehicle transport volume is as follows:

[0140] Assume that the transport volume vector is W = [w1 … w N ] T , where w1 … w N Represent the transport volume from vehicle 1 to vehicle N respectively, and calculate the transport volume vector of each road section at T time points:

[0141]

[0142] The total transport volume of all road sections can be obtained by summing up all elements in vector F.

[0143] Therefore, using the probability distribution p(O (t) |S (t) ) can complete the performance evaluation of vehicle group scheduling strategy, such as using p(O (t) |S (t) =S a ) and p(O (t) |S (t) =S b ) Calculate the expected value of transport volume to evaluate and compare two different vehicle scheduling strategies S a and S b The expected value can be calculated using Figures 1 to 4 The probability graph model in is combined with the aforementioned calculation method to achieve this.

[0144] The embodiment of the present disclosure also provides a method for optimizing vehicle scheduling strategy. Figure 6 As shown, the optimization method includes:

[0145] Step S0: Evaluate multiple vehicle scheduling strategies using the evaluation method of any of the above embodiments; and

[0146] Step S4: Compare the multiple vehicle dispatching strategies to select a preferred strategy.

[0147] Specifically, as an example, in step S4, the above probability distribution p(0 (t) |S (t)) to obtain the corresponding transportation performance indicators, and then compare these performance indicators (such as vehicle running distance, transportation volume, etc.) to select the optimal vehicle scheduling strategy. In some embodiments, an optimization algorithm can be used to solve the vehicle group scheduling strategy that maximizes the transportation volume within a specific time range. The solution to this optimization problem can be used as follows Figures 1 to 4 The probabilistic graphical model in is implemented in combination with any optimization algorithm known in the art.

[0148] The vehicle dispatch strategy evaluation and optimization methods according to the embodiments of the present disclosure can reduce vehicle waiting times caused by various factors and improve actual transportation efficiency. For example, they can reduce the number of vehicles waiting in line for tasks, reduce the number of vehicles stopping or slowing down due to passing vehicles on special road sections, and reduce the impact of abnormal situations such as falling rocks or equipment downtime on overall transportation, thereby improving actual transportation efficiency.

[0149] The evaluation method and optimization method of the vehicle scheduling strategy according to the embodiment of the present disclosure are based on the probability model of vehicles traveling on road sections, and are particularly suitable for road networks with fixed transportation routes, especially for scenarios such as open-pit mines, and can also be used in other road transportation scenarios.

[0150] The embodiment of the present disclosure also provides a vehicle dispatching strategy evaluation device 10. Figure 7 As shown, the evaluation device 10 may include:

[0151] A vehicle operation status generating module 11 is configured to calculate a probability distribution of the operation status of a vehicle on each section of the transport route based on a vehicle scheduling strategy and a vehicle operation status model on each section of the transport route, wherein the vehicle operation status model is generated based on the probability of a vehicle appearing on at least one section of the transport route; and

[0152] The performance calculation module 12 is used to calculate the performance parameters of the vehicle scheduling strategy based on the probability distribution of the vehicle's operating status on each section of the transportation route to evaluate the performance of the vehicle scheduling strategy.

[0153] In some embodiments, the vehicle operating status model includes at least one of a single-vehicle route function for only a single vehicle operating on the same road segment, a multi-vehicle route function for multiple vehicles operating on the same road segment, and an abnormal event route function for abnormal events on the transportation route.

[0154] In some embodiments, the vehicle operating status generating module 11 includes:

[0155] An initialization module 111 is used to initialize the running status of vehicles on each road section at a first moment according to a vehicle scheduling strategy; and

[0156] The probability calculation module 112 is configured to calculate the probability of the vehicle running state on each road section at the first moment according to the vehicle running state model.

[0157] In some embodiments, the initialization module 111 is further configured to initialize the operating status of the vehicles on each road segment at the second or more moments according to the vehicle scheduling strategy; and

[0158] The probability calculation module 112 is further configured to calculate the probability of the vehicle operating state on each road segment at the second or more time instants according to the vehicle operating state model.

[0159] In some embodiments, the performance calculation module 12 is configured to calculate the sum of performance parameters of the vehicle scheduling strategy at multiple times based on the probability distribution of the vehicle's operating status on each section of the transportation route at multiple times, and the performance parameters are, for example, the vehicle's transportation volume or the vehicle's driving distance.

[0160] In some embodiments, the evaluation device 10 may further include a data acquisition module 13 for acquiring actual vehicle driving measurement data for constructing the vehicle operating state model. The data acquisition module 13 may include, for example, various analog-digital collectors, cameras, radars, and the like.

[0161] The evaluation device 10 according to an embodiment of the present disclosure can be used to implement the above-mentioned vehicle scheduling strategy evaluation method or optimization method. The evaluation device 10 can be an on-site device or a remote device, for example, it can be set up in the cloud and communicate with the on-site vehicle and / or the control center through the cloud network.

[0162] In some embodiments, the various modules in the evaluation device 10 may be respectively provided in different devices, or may be partially or fully integrated into the same device.

[0163] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product. In some embodiments, the electronic device includes at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the vehicle scheduling strategy evaluation method or optimization method according to any of the above embodiments. In some embodiments, the readable storage medium may be a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable the computer to execute the vehicle scheduling strategy evaluation method or optimization method according to any of the above embodiments. In some embodiments, the computer program product includes a computer program, and when the computer program is executed by the processor, it implements the vehicle scheduling strategy evaluation method or optimization method according to any of the above embodiments.

[0164] Figure 11 This is a system block diagram for implementing remote control of an evaluation method or optimization method for vehicle scheduling strategy according to another embodiment of the present disclosure. It should be noted that Figure 11 The examples shown are merely examples of system architectures to which the embodiments of the present disclosure may be applied, to help those skilled in the art understand the technical content of the present disclosure, but do not mean that the embodiments of the present disclosure may not be used in other devices, systems, environments or scenarios.

[0165] like Figure 11 As shown, the system architecture 200 according to this embodiment may include a terminal device 201, a network 202, and a server 203. The network 202 is used to provide a medium for a communication link between the terminal device 201 and the server 203. The network 202 may include various connection types, such as wired and / or wireless communication links, etc.

[0166] A user can use a terminal device 201 to interact with a server 203 via a network 202 to receive or send messages, etc. The terminal device 201 can be any electronic device, including but not limited to a smartphone, a tablet computer, a laptop computer, etc. The terminal device 201 can also include a vehicle.

[0167] The vehicle dispatching strategy evaluation method or optimization method provided in the embodiments of the present disclosure may generally be executed by the server 203. The server 203 may be, for example, a cloud server.

[0168] Figure 12A schematic block diagram of an example electronic device 1100 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0169] like Figure 12 As shown, the electronic device 1100 includes a computing unit 1101, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1102 or a computer program loaded from a storage unit 1108 into a random access memory (RAM) 1103. Various programs and data required for the operation of the device 1100 can also be stored in the RAM 1103. The computing unit 1101, the ROM 1102, and the RAM 1103 are connected to each other via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0170] Various components in device 1100 are connected to I / O interface 1105, including an input unit 1106, such as a keyboard and mouse; an output unit 1107, such as various types of displays and speakers; a storage unit 1108, such as a magnetic disk and optical disk; and a communication unit 1109, such as a network card, a modem, a wireless communication transceiver, etc. Communication unit 1109 allows device 1100 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0171] The computing unit 1101 can be a variety of general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the computing unit 1101 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 1101 performs the various methods and processes described above, such as the method for predicting traffic flow. For example, in some embodiments, the method for predicting traffic flow can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 1108. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 1100 via the ROM 1102 and / or the communication unit 1109. When the computer program is loaded into the RAM 1103 and executed by the computing unit 1101, one or more steps of the method for predicting traffic flow described above can be performed. Alternatively, in other embodiments, the computing unit 1101 may be configured to execute the method for predicting traffic flow in any other appropriate manner (eg, by means of firmware).

[0172] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0173] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0174] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer 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 of the foregoing.

[0175] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0176] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0177] Computer systems may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The client and server relationship arises through computer programs running on the respective computers and having a client-server relationship to each other.

[0178] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0179] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A vehicle scheduling strategy evaluation method, comprising: generating a vehicle operating state model on each section of the transport route based on an appearance probability of the vehicle on at least one section of the transport route; Calculate the probability distribution of vehicle operation status on each section of the transport route based on the vehicle scheduling strategy and vehicle operation status model; as well as Calculating the performance parameters of the vehicle scheduling strategy for measuring the transportation efficiency or cost of the vehicle based on the probability distribution of the vehicle's operating status on each section of the transportation route to evaluate the performance of the vehicle scheduling strategy, The calculation of the probability distribution of the vehicle's operating status on each section of the transport route based on the vehicle scheduling strategy and the vehicle operating status model includes: Initializing the operating status of vehicles on each road section at the first moment according to the vehicle scheduling strategy; and Calculate the probability of the vehicle running state on each road section at the first moment according to the vehicle running state model, and The vehicle operation state model includes at least one of a single-vehicle route function for a single vehicle operating on the same road section, a multi-vehicle route function for multiple vehicles operating on the same road section, and an abnormal event route function for abnormal events on the transport route. The bicycle route function is: ,in Indicates that the vehicle is on the road Whether it appears, Indicates that the vehicle is on the road Whether it appears, Representatives in The vehicle is on the road at the moment The status appears In the case of The vehicle is on the road at the moment The probability of occurrence, ; The multi-vehicle route function is ,in Represents vehicle m on the road segment Whether it appears, Represents vehicle m on the road segment Whether it appears, Represents vehicle n on the road segment Whether it appears, Representatives in At the moment, vehicle m and vehicle n are on the road section The statuses are and In the case of At time moment vehicle m is on the road section The probability of occurrence, ; The abnormal event circuit function is: ,in Represents vehicles on the road Whether it appears, Representatives on the road -1 indicates whether an abnormal situation occurs, and i is an integer greater than 1.

2. The method according to claim 1, wherein The vehicle operating state model depends on the number of vehicles and the number of sections of the transport route.

3. The method according to claim 2, wherein: When only a single vehicle is running on the same road section, the probability distribution of the running time of the vehicle on the same road section is based on a Gaussian model, and / or when multiple vehicles are running on the same road section, the probability distribution of the running time of each of the multiple vehicles on the same road section is based on a Gaussian mixture model, and / or when an abnormal event occurs on a certain road section, the probability distribution of the running time of the vehicle on the road section is based on a Poisson distribution model.

4. The method according to any one of claims 1 to 3, wherein The method of calculating the probability distribution of the vehicle's operating status on each section of the transport route based on the vehicle scheduling strategy and the vehicle operating status model also includes: Initializing the operating status of the vehicles on each road section at a second or more time points according to the vehicle scheduling strategy; and The probability of the vehicle operating state on each road section at the second or more time instants is calculated according to the vehicle operating state model.

5. The method according to any one of claims 1 to 3, wherein The probability of a vehicle operating state on a road section of a transport route depends on the probability of an abnormal event occurring on a previous road section of the road section and the probability of a vehicle operating state on at least one road section adjacent to the road section.

6. The method according to any one of claims 1 to 3, wherein The calculating of the performance parameters of the vehicle scheduling strategy based on the probability distribution of the running status of the vehicles on each section of the transport route to evaluate the performance of the vehicle scheduling strategy includes: The sum of the performance parameters of the vehicle scheduling strategy at multiple moments is calculated based on the probability distribution of the vehicle's operating status on each section of the transportation route at multiple moments.

7. The method according to claim 6, wherein: The performance parameters of the vehicle scheduling strategy include: the transport volume of the vehicle or the travel distance of the vehicle.

8. The method according to any one of claims 1 to 3, wherein the abnormal event comprises a failure of a control unit inside the vehicle or a temporary obstacle that needs to be avoided on a road section. 9 . The method according to claim 1 , wherein the vehicle operating state model is directly established based on actual vehicle driving measurement data or is established by fitting parameters of a parameterized model according to the actual vehicle driving measurement data.

10. A method for optimizing a vehicle dispatching strategy, comprising: Evaluating a plurality of vehicle scheduling strategies using the method according to any one of claims 1 to 9; as well as The multiple vehicle scheduling strategies are compared to select a preferred strategy.

11. A vehicle dispatching strategy evaluation device, comprising: a vehicle operating status generation module, configured to calculate a probability distribution of a vehicle's operating status on each section of the transport route based on a vehicle scheduling strategy and a vehicle operating status model on each section of the transport route, wherein the vehicle operating status model is generated based on a probability of a vehicle appearing on at least one section of the transport route; and A performance calculation module is used to calculate the performance parameters of the vehicle scheduling strategy for measuring the transportation efficiency or cost of the vehicle based on the probability distribution of the vehicle's operating status on each section of the transportation route to evaluate the performance of the vehicle scheduling strategy. Wherein, the vehicle running status generation module includes: An initialization module, configured to initialize the operating status of vehicles on each road section at a first moment according to a vehicle scheduling strategy; and A probability calculation module is used to calculate the probability of the vehicle running state on each road section at the first moment according to the vehicle running state model, and The vehicle operation state model includes at least one of a single-vehicle route function for a single vehicle operating on the same road section, a multi-vehicle route function for multiple vehicles operating on the same road section, and an abnormal event route function for abnormal events on the transport route. The bicycle route function is ,in Indicates that the vehicle is on the road Whether it appears, Indicates that the vehicle is on the road Whether it appears, Representatives in The vehicle is on the road at the moment The status appears In the case of The vehicle is on the road at the moment The probability of occurrence, ; The multi-vehicle route function is ,in Represents vehicle m on the road segment Whether it appears, Represents vehicle m on the road segment Whether it appears, Represents vehicle n on the road segment Whether it appears, Representatives in At the moment, vehicle m and vehicle n are on the road section The statuses are and In the case of At time moment vehicle m is on the road section The probability of occurrence, ; The abnormal event circuit function is: ,in Represents vehicles on the road Whether it appears, Representatives on the road -1 indicates whether an abnormal situation occurs, and i is an integer greater than 1.

12. The vehicle dispatching strategy evaluation device according to claim 11, wherein: The initialization module is further configured to initialize the operating status of the vehicles on each road section at the second or more time points according to the vehicle scheduling strategy; and The probability calculation module is further configured to calculate the probability of the vehicle running state on each road segment at the second or more time instants according to the vehicle running state model.

13. The vehicle dispatching strategy evaluation device according to claim 11, wherein: The probability of a vehicle operating state on a road section of a transport route depends on the probability of an abnormal event occurring on a previous road section of the road section and the probability of a vehicle operating state on at least one road section adjacent to the road section.

14. The vehicle dispatching strategy evaluation device according to any one of claims 11 to 13, wherein: The performance calculation module is configured to calculate the sum of performance parameters of the vehicle scheduling strategy at multiple times based on the probability distribution of the vehicle's operating status on each section of the transportation route at multiple times. The performance parameter is the vehicle's transportation volume or the vehicle's driving distance.

15. The vehicle dispatching strategy evaluation device according to any one of claims 11 to 13, further comprising: The data acquisition module is used to collect actual vehicle driving measurement data for constructing the vehicle operation state model.

16. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 10.

17. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-10.

18. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 10.

Images