A method and device for analyzing scene demand of an autonomous transportation system

Abstract

The application discloses a kind of autonomous traffic system scene demand analysis method and device, method includes: using tree structure hierarchical method to the typical scene of autonomous traffic system is hierarchically abstracted, and the boundary of each level scene is defined;According to the triangular model of activity theory, the attribute elements involved in each level typical scene are obtained;The typical scene of each level is described in a standardized way, wherein the standardized description of the typical scene includes a plurality of attribute elements;The attribute elements of typical scene are matched with the text similarity of autonomous traffic system demand library, and the target scene demand is obtained.The application can more scientific and effective scene analysis method, to complex traffic system scene is hierarchically abstracted and attribute element analysis comprehensively, to realize the standardized description of traffic scene, and further study the demand and service contained in autonomous traffic system typical scene, can be widely applied in traffic data processing technical field.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic data processing, and in particular to a method and device for analyzing scenario requirements of an autonomous traffic system. Background Art

[0002] With the rapid growth of transportation volume, the orderly construction and utilization of comprehensive transportation infrastructure, and the mutual promotion of emerging technologies and transportation services, the demand for a transportation system that can achieve self-organization and provide autonomous services to users is gradually emerging to meet the surging transportation demand for passengers and freight. This is the Autonomous Transportation System (ATS).

[0003] Autonomous transportation systems, driven by emerging technologies, are based on the business logic of autonomous perception, learning, decision-making, and response, and transport people and goods through self-organizing operations and autonomous services. Their essence is to reduce human intervention in transportation systems and enhance their autonomy. Building an autonomous transportation system architecture is fundamental to effectively guiding the planning and construction of future autonomous transportation systems. Establishing a system architecture reference solution tailored to typical transportation application scenarios applies and validates the fundamental theories and methods of the ATS architecture. Furthermore, feedback from application scenarios can further refine the underlying theory. However, due to the numerous scenarios involved in autonomous transportation systems, studying each requirement individually is a significant undertaking. Therefore, a scientific approach is required to standardize the description of scenarios and extract key information. A common scenario research approach is to first abstract and layer the scenarios and then identify their attributes. Activity theory, as a tool for studying human activities, can play a key role in analyzing scenario attributes.

[0004] There are few existing studies that analyze traffic scenarios. Relevant technologies mention that risk scenarios are divided into two levels, namely accident influencing factors and violation influencing factors; they also mention that autonomous driving scenarios should be analyzed from three attribute dimensions: scenario elements, system structure, and system functions; relevant technologies also consider defining scenario elements into four, namely road attributes, traffic attributes, climate attributes, and interference attributes.

[0005] Current research focuses on analyzing specific issues after scenario establishment, while neglecting the fundamental research of analyzing the characteristic attributes of complex scenarios and forming standardized descriptions. This leads to a series of conceptual problems in subsequent scenario-based research, making it increasingly difficult to fully capture the needs of complex transportation system scenarios. Specifically,

[0006] 1. The basis for scenario stratification lacks sufficient theoretical support, and the distinction between scenarios at each level is not clear enough;

[0007] 2. Current research is mostly based on analysis of known scene attribute elements. The determination of scene attribute elements is mostly subjective analysis, lacking objective scene attribute element extraction methods as support;

[0008] 3. The scene attribute elements considered in existing studies are not comprehensive enough, and the description of the scene is not complete;

[0009] 4. Existing research lacks standardized definitions of scene attribute elements, and subsequent research has no unified scene basis.

[0010] At this time, a more scientific and effective scenario analysis method is needed to perform hierarchical abstraction and attribute element analysis of complex traffic system scenarios, so as to achieve a standardized description of traffic scenarios and further study the needs and services contained in typical scenarios of autonomous transportation systems. Summary of the Invention

[0011] In view of this, an embodiment of the present invention provides a more comprehensive autonomous traffic system scenario demand analysis method and device.

[0012] One aspect of the present invention provides a method for analyzing scenario requirements of an autonomous transportation system, comprising:

[0013] A tree-structured hierarchical approach is used to abstract typical scenarios of autonomous transportation systems and define the boundaries of each level of scenarios.

[0014] According to the triangular model of activity theory, obtain the attribute elements involved in typical scenarios at each level;

[0015] Performing standardized descriptions of typical scenarios at each level, wherein the standardized descriptions of the typical scenarios include a plurality of the attribute elements;

[0016] The attribute elements of typical scenarios are matched with the autonomous transportation system requirement library by text similarity to obtain the target scenario requirements.

[0017] Optionally, the tree-structured hierarchical method is used to perform hierarchical abstraction of typical scenarios of the autonomous transportation system and define the boundaries of each level of scenarios, including:

[0018] Describe coarse-grained scenarios of autonomous transportation systems at a high level of abstraction;

[0019] Use the decomposition idea to decompose and refine the high-level scene layer by layer to obtain macroscopic scenes, mesoscopic scenes, and microscopic scenes. Each macroscopic scene contains multiple mesoscopic scenes, and each mesoscopic scene contains multiple microscopic scenes.

[0020] The macro scenario is used to represent the overall description of a typical scenario of an autonomous transportation system, including but not limited to the operational characteristics of a traffic information collection platform and a road network management platform;

[0021] The meso-scenario is used to represent a refined description of the system elements in the macro-scenario, including but not limited to the characteristics of the traveler group;

[0022] The micro-scenario is used to characterize the specific scenarios in the meso-scenario, including but not limited to the behavioral characteristics of a single traveler before the trip, during the trip, and after the trip.

[0023] Optionally, the attribute elements involved in the step of obtaining the attribute elements involved in the typical scenes at each level according to the triangular model of activity theory include the attribute elements of the macro scene, the attribute elements of the meso scene and the attribute elements of the micro scene;

[0024] The attribute elements of the macro scene include concept elements, characteristic elements, and contrast elements;

[0025] The attribute elements of the meso-scenario include user group elements, environmental elements, group tool elements, group behavior elements, and group goals or expectations elements;

[0026] The attribute elements of the micro-scene include time elements, subject elements, individual tool elements, individual behavior elements, object elements, and individual goals or expectations elements.

[0027] Optionally, the method further includes:

[0028] Define the concepts of typical scene attribute elements at each level;

[0029] The conceptual elements are used to represent the conceptual explanations corresponding to the five typical scenarios of autonomous transportation systems;

[0030] The characteristic elements are used to represent the supplementary description of the macro-scenario concept under the autonomous transportation system;

[0031] The comparison factors are used to characterize the characteristics and advantages of typical scenarios of autonomous transportation systems compared to traditional scenarios;

[0032] The user group element and subject element are used to characterize the initiator of the traffic behavior;

[0033] The environmental elements are used to characterize the transportation services provided to the user group;

[0034] The time element is used to represent the time stage in which the subject's behavior occurs in the scene;

[0035] The object element is used to characterize the goal of the subject's role in traffic behavior;

[0036] The tool element is used to represent the medium through which the subject acts on the object, including but not limited to GPS positioning technology, communication technology, vehicle-road cooperative technology, and autonomous driving technology;

[0037] The behavioral elements are used to characterize the behavior of the subject in the traffic environment;

[0038] The goals or expected elements are used to represent the real needs of users.

[0039] Optionally, the standardized description of typical scenarios at each level includes:

[0040] The macro scenario is standardized as follows:

[0041] "The macro scenario under the autonomous transportation system is" + conceptual elements + "distinguished from traditional scenarios" + contrasting elements + "having" + characteristic elements;

[0042] The mesoscopic scenario is standardized as follows:

[0043] User group element + "can be provided by the autonomous transportation system" + environmental element + "with the help of" + tool element + "through" behavior element + "achieve" + goal or expectation element;

[0044] The microscopic scene is standardized as follows:

[0045] Time element + "under constraints" + subject element + "through the help of" + tool element + "in the process of micro-scenario travel under the autonomous transportation system" + object element + "generating travel" + behavior element + "to achieve" + goal or expectation element.

[0046] Optionally, performing text similarity matching on the attribute elements of the typical scenario and the autonomous transportation system requirement library to obtain the target scenario requirements includes:

[0047] Identify all documents in the corpus; segment each document in the corpus and remove stop words; scan all documents in the corpus and number each word to obtain a dictionary; count the number of occurrences of each word in the dictionary in the document, combine it with the word number to obtain a bigram, and then determine the vectorized corpus;

[0048] Training a text vector representation model based on the vectorized corpus; converting input text into a text vector based on the trained text vector representation model;

[0049] Determine the similarity of the key attribute texts corresponding to each text vector by using the cosine similarity calculation method, and perform weighted summation on the similarities to obtain a comprehensive similarity;

[0050] By comparing the magnitude relationship between the comprehensive similarity and a preset threshold, the determination result of the scene requirement is determined.

[0051] Another aspect of an embodiment of the present invention further provides an autonomous traffic system scenario demand analysis device, comprising:

[0052] The first module is used to abstract typical scenarios of autonomous transportation systems using a tree-structured hierarchical method and define the boundaries of each level of scenarios.

[0053] The second module is used to obtain the attribute elements involved in typical scenarios at each level based on the triangular model of activity theory;

[0054] The third module is used to perform a standardized description of typical scenes at each level, wherein the standardized description of the typical scenes includes a plurality of the attribute elements;

[0055] The fourth module is used to perform text similarity matching between the attribute elements of typical scenarios and the autonomous transportation system requirement library to obtain the target scenario requirements.

[0056] Another aspect of an embodiment of the present invention further provides an electronic device, including a processor and a memory;

[0057] The memory is used to store programs;

[0058] The processor executes the program to implement the method described above.

[0059] Another aspect of the embodiments of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the method described above.

[0060] Another aspect of an embodiment of the present invention further provides a computer program product, including a computer program, which implements the above-mentioned method when executed by a processor.

[0061] The embodiments of the present invention use a tree-structured hierarchical method to perform hierarchical abstraction of typical scenarios of autonomous transportation systems and define the boundaries of each level of scenarios; based on the triangular model of activity theory, the attribute elements involved in each level of typical scenarios are obtained; the typical scenarios at each level are standardizedly described, wherein the standardized description of the typical scenarios includes multiple attribute elements; the attribute elements of the typical scenarios are matched with the autonomous transportation system demand library for text similarity to obtain the target scenario requirements. The present invention can provide a more scientific and effective scenario analysis method to perform comprehensive hierarchical abstraction and attribute element analysis of complex transportation system scenarios, so as to achieve a standardized description of transportation scenarios and further study the requirements and services included in the typical scenarios of autonomous transportation systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present application, 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0063] Figure 1 A schematic diagram of a tree-like hierarchical structure provided by an embodiment of the present invention;

[0064] Figure 2 A flowchart of obtaining specific scenario requirements through similarity matching provided by an embodiment of the present invention;

[0065] Figure 3 The following is a flowchart of the overall steps provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solutions and advantages of this application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0067] In view of the problems existing in the prior art, one aspect of the present invention provides a scenario demand analysis method for an autonomous transportation system, comprising:

[0068] A tree-structured hierarchical approach is used to abstract typical scenarios of autonomous transportation systems and define the boundaries of each level of scenarios.

[0069] According to the triangular model of activity theory, obtain the attribute elements involved in typical scenarios at each level;

[0070] Performing standardized descriptions of typical scenarios at each level, wherein the standardized descriptions of the typical scenarios include a plurality of the attribute elements;

[0071] The attribute elements of typical scenarios are matched with the autonomous transportation system requirement library by text similarity to obtain the target scenario requirements.

[0072] Optionally, the tree-structured hierarchical method is used to perform hierarchical abstraction of typical scenarios of the autonomous transportation system and define the boundaries of each level of scenarios, including:

[0073] Describe coarse-grained scenarios of autonomous transportation systems at a high level of abstraction;

[0074] Use the decomposition idea to decompose and refine the high-level scene layer by layer to obtain macroscopic scenes, mesoscopic scenes, and microscopic scenes. Each macroscopic scene contains multiple mesoscopic scenes, and each mesoscopic scene contains multiple microscopic scenes.

[0075] The macro scenario is used to represent the overall description of a typical scenario of an autonomous transportation system, including but not limited to the operational characteristics of a traffic information collection platform and a road network management platform;

[0076] The meso-scenario is used to represent a refined description of the system elements in the macro-scenario, including but not limited to the characteristics of the traveler group;

[0077] The micro-scenario is used to characterize the specific scenarios in the meso-scenario, including but not limited to the behavioral characteristics of a single traveler before the trip, during the trip, and after the trip.

[0078] Optionally, the attribute elements involved in the step of obtaining the attribute elements involved in the typical scenes at each level according to the triangular model of activity theory include the attribute elements of the macro scene, the attribute elements of the meso scene and the attribute elements of the micro scene;

[0079] The attribute elements of the macro scene include concept elements, characteristic elements, and contrast elements;

[0080] The attribute elements of the meso-scenario include user group elements, environmental elements, group tool elements, group behavior elements, and group goals or expectations elements;

[0081] The attribute elements of the micro-scene include time elements, subject elements, individual tool elements, individual behavior elements, object elements, and individual goals or expectations elements.

[0082] Optionally, the method further includes:

[0083] Define the concepts of typical scene attribute elements at each level;

[0084] The conceptual elements are used to represent the conceptual explanations corresponding to the five typical scenarios of autonomous transportation systems;

[0085] The characteristic elements are used to represent the supplementary description of the macro-scenario concept under the autonomous transportation system;

[0086] The comparison factors are used to characterize the characteristics and advantages of typical scenarios of autonomous transportation systems compared to traditional scenarios;

[0087] The user group element and subject element are used to characterize the initiator of the traffic behavior;

[0088] The environmental elements are used to characterize the transportation services provided to the user group;

[0089] The time element is used to represent the time stage in which the subject's behavior occurs in the scene;

[0090] The object element is used to characterize the goal of the subject's role in traffic behavior;

[0091] The tool element is used to represent the medium through which the subject acts on the object, including but not limited to GPS (Global Positioning System, GPS) positioning technology, communication technology, vehicle-road cooperative technology, and autonomous driving technology;

[0092] The behavioral elements are used to characterize the behavior of the subject in the traffic environment;

[0093] The goals or expected elements are used to represent the real needs of users.

[0094] Optionally, the standardized description of typical scenarios at each level includes:

[0095] The macro scenario is standardized as follows:

[0096] "The macro scenario under the autonomous transportation system is" + conceptual elements + "distinguished from traditional scenarios" + contrasting elements + "having" + characteristic elements;

[0097] The mesoscopic scenario is standardized as follows:

[0098] User group element + "can be provided by the autonomous transportation system" + environmental element + "with the help of" + tool element + "through" behavior element + "achieve" + goal or expectation element;

[0099] The microscopic scene is standardized as follows:

[0100] Time element + "under constraints" + subject element + "through the help of" + tool element + "in the process of micro-scenario travel under the autonomous transportation system" + object element + "generating travel" + behavior element + "to achieve" + goal or expectation element.

[0101] Optionally, performing text similarity matching on the attribute elements of the typical scenario and the autonomous transportation system requirement library to obtain the target scenario requirements includes:

[0102] Identify all documents in the corpus; segment each document in the corpus and remove stop words; scan all documents in the corpus and number each word to obtain a dictionary; count the number of occurrences of each word in the dictionary in the document, combine it with the word number to obtain a bigram, and then determine the vectorized corpus;

[0103] Training a text vector representation model based on the vectorized corpus; converting input text into a text vector based on the trained text vector representation model;

[0104] Determine the similarity of the key attribute texts corresponding to each text vector by using the cosine similarity calculation method, and perform weighted summation on the similarities to obtain a comprehensive similarity;

[0105] By comparing the magnitude relationship between the comprehensive similarity and a preset threshold, the determination result of the scene requirement is determined.

[0106] Another aspect of an embodiment of the present invention further provides an autonomous traffic system scenario demand analysis device, comprising:

[0107] The first module is used to abstract typical scenarios of autonomous transportation systems using a tree-structured hierarchical method and define the boundaries of each level of scenarios.

[0108] The second module is used to obtain the attribute elements involved in typical scenarios at each level based on the triangular model of activity theory;

[0109] The third module is used to perform a standardized description of typical scenes at each level, wherein the standardized description of the typical scenes includes a plurality of the attribute elements;

[0110] The fourth module is used to perform text similarity matching between the attribute elements of typical scenarios and the autonomous transportation system requirement library to obtain the target scenario requirements.

[0111] Another aspect of an embodiment of the present invention further provides an electronic device, including a processor and a memory;

[0112] The memory is used to store programs;

[0113] The processor executes the program to implement the method described above.

[0114] Another aspect of the embodiments of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the method described above.

[0115] Another aspect of an embodiment of the present invention further provides a computer program product, including a computer program, which implements the above-mentioned method when executed by a processor.

[0116] The specific implementation principle of the present invention is described in detail below with reference to the accompanying drawings:

[0117] The present invention provides a method for analyzing typical scenario requirements of an autonomous transportation system based on activity theory, which includes the following steps:

[0118] (a) Using a tree-structured hierarchical approach, we abstract typical scenarios of autonomous transportation systems and define the boundaries of each level of scenarios.

[0119] (b) According to the triangular model provided by activity theory, obtain the attribute elements involved in typical scenarios at each level;

[0120] (c) Define the concept of typical scene attribute elements at each level;

[0121] (d) Standardize descriptions of typical scenes at each level, stipulating that scene descriptions include the above-mentioned multiple attribute elements;

[0122] (e) Perform similarity matching between the attribute elements of typical scenarios and the autonomous transportation system requirement library to obtain specific scenario requirements.

[0123] Preferably, in step (a), a tree structure hierarchical method is used to hierarchically abstract typical scenarios of the autonomous transportation system. First, the coarse-grained scenarios of the autonomous transportation system are described at a higher level of abstraction. Then, the high-level scenarios are decomposed and refined layer by layer using the decomposition idea, i.e., macroscopic scenarios, mesoscopic scenarios, and microscopic scenarios. The specific tree structure hierarchical method is as follows: Figure 1 shown.

[0124] Depend on Figure 1 It can be seen that the scenes at each level are mutually inclusive. For example, a mesoscopic scene contains multiple microscopic scenes, and the combination of multiple microscopic scenes can also express a mesoscopic scene. The specific definitions and characteristics are as follows:

[0125] 1) Macro scenario

[0126] The macro scenario is a holistic description of a typical scenario of an autonomous transportation system. It defines the boundaries of the entire system and describes the state at the system level with a large granularity, thereby analyzing the macro characteristics and requirements of the transportation system.

[0127] 2) Mesoscopic scenario

[0128] The meso-scenario is a refinement of the system elements in the macro-scenario. Taking the same type of elements as the research object, such as the traveler group, it can describe the traffic scenario in more detail and further explore the scenario needs.

[0129] 3) Microscopic scenes

[0130] The micro-scenario starts from the specific scenario in the meso-scenario and takes a certain individual as the research object, such as a traveler or a driver. The granularity involved is the smallest, and it can describe in detail the behavioral characteristics of each element in the scenario at different travel stages, making demand discussions easier.

[0131] Preferably, in step (b), the multi-dimensional attribute elements involved in each level of typical scenarios are obtained based on the triangular model provided by activity theory, namely, subject, object, community, rules, tools, division of labor, and results. Based on the boundary definition of each level of typical scenarios, the attribute elements involved in each level of scenarios are summarized and organized as shown in Table 1 below:

[0132] Table 1

[0133] Scene Hierarchy Scene attribute elements Macro scenario Concept, characteristics, and contrast Mesoscopic scene User groups, environments, tools, behaviors, goals, or expectations Microscopic scenes time, subject, tool, behavior, object, goal or expectation

[0134] Table 1 describes the attribute elements involved in typical scenarios at each level.

[0135] Preferably, in step (c), the concepts of typical scenario attribute elements at each level are defined based on the typical scenario attribute elements at each level summarized in step (b), namely, macro-level scenarios: concepts, characteristics, and comparisons; meso-level scenarios: user groups, environments, tools, behaviors, goals, or expectations; and micro-level scenarios: time, subjects, tools, behaviors, objects, goals, or expectations. The definitions of typical scenario attribute elements at each level are shown in Table 2 below.

[0136] Table 2

[0137]

[0138] Table 2 describes the typical scene attribute elements and their definitions at each level.

[0139] Preferably, in step (d), the typical scenes at each level are described in a standardized manner according to the attribute elements involved in the typical scenes at each level given in step (b), as shown in Table 3 below:

[0140] Table 3

[0141]

[0142] Table 3 describes the standardized description of typical scenarios at each level.

[0143] Preferably, in step (e), the attribute elements of the typical scene are matched with the autonomous transportation system demand library to obtain specific scene requirements. The specific implementation steps are as follows: Figure 2 As shown, the specific steps include:

[0144] 1) Create a vectorized corpus

[0145] First, determine all the documents contained in the corpus, that is, the input text. In match 1, the input text is the "subject" and "object" text of the scenario library and the "user" text of the requirement library; in match 2, the input text is the "scenario description" text of the scenario library and the "user need" text of the requirement library. Then, each document in the corpus is preprocessed by word segmentation and stop words are removed. After that, all documents in the corpus are scanned, each word is numbered, and a dictionary is formed. Finally, the number of times each word in the dictionary appears in the document is counted, and a two-tuple is formed with the word number to represent the corpus document in the form of a vector. At this time, the corpus is expressed as follows:

[0146]

[0147] Where: w xy : The number of word y in document x in the dictionary, w xy =0,1,...,n-1;

[0148] c xy : The number of times word y that makes up document x appears in the document, c xy ≥0;

[0149] m: the total number of documents in the corpus;

[0150] n: The total number of words in the corpus.

[0151] 2) Construct text vector

[0152] First, the input text is preprocessed with word segmentation, which is the same as the processing of documents in the corpus. Then, the preprocessed input text is preliminarily vectorized, that is, the text is represented as a vector form with the same document vector in the vectorized corpus. The vectorized corpus is then used to train the text vector representation model. Finally, the input text is converted from the preliminary vector form to the corresponding text vector using the trained text vector representation model. Match 1 uses the Term Frequency-Inverse Document Frequency (TF-IDF) model, and Match 2 uses the Latent Semantic Indexing (LSI) model. The text vector formed by the TF-IDF model is as follows:

[0153] text_vec=[(w1,TF-IDF1) … (w n ,TF-IDF n )]

[0154] Where: w y : The number of the word y in the dictionary;

[0155] TF-IDFy : TF-IDF value of word y in the text.

[0156] The text vector formed by the LSI model is as follows:

[0157] text_vec=[(t1,U1) … (t k ,U k )]

[0158] Where: t p : The number of the topic p, t p =0,1,...,k-1;

[0159] U p : The relevance of the text to the topic p.

[0160] 3) Calculate text similarity

[0161] In Match 1, the cosine similarity calculation is performed on the "subject" and "object" texts of a certain micro-scenario and all the "user" text vectors in the demand library. In Match 2, the cosine similarity calculation is performed on the other key attribute texts of a certain micro-scenario (each micro-scenario has 6 key attributes, in addition to the two attributes of "subject" and "object" used in Match 1, there are 4 key attributes: "time", "goal or expectation", "tool" and "behavior") and all the "user needs" text vectors of the candidate demand set obtained in Match 1. The similarity corresponding to each key attribute text is obtained, and then the weighted sum of the similarities of each key attribute text is performed to obtain the comprehensive similarity. For a text of the form [(0,a1) … (L-1,a L )] and [(0,b1) … (L-1,b L )], the cosine similarity calculation formula is as follows:

[0162]

[0163] The comprehensive similarity calculation formula in Match 2 is as follows:

[0164]

[0165] Among them: wi i : The weight of the i-th key attribute;

[0166] cos_sim i : Cosine similarity of the i-th key attribute.

[0167] 4) Select scenario requirements

[0168] For a specific micro-scenario, in Match 1, a threshold is set. If the similarity between the "user" text in the requirement library and the "subject" and "object" texts exceeds the threshold, the requirements corresponding to these "users" are considered candidate requirements. In Match 2, a threshold is set. If the similarity between the "user needs" text in the candidate requirement set and the text of other key attributes (such as "time") exceeds the threshold, the corresponding requirement is considered as the requirement of the micro-scenario.

[0169] The scenario analysis steps of the present invention are further described in detail below with reference to a Mobility as a Service (MaaS) scenario in a typical scenario of an autonomous transportation system.

[0170] The MaaS scenario here refers to a one-stop travel service approach based on autonomous transportation system technology, using one or more modes of transportation to help passengers move around in space, taking into account the time, money, and environmental impact of their travel. Unlike traditional transportation systems, MaaS in this scenario incorporates the characteristics of an autonomous transportation system for both people and goods, encompassing nine key components: traffic status information, route planning, shared travel management, route navigation, parking management, transfers, integrated payment, dynamic cargo transportation planning, and data storage.

[0171] like Figure 3 As shown in the figure, the present invention provides a method for analyzing the typical scenarios of autonomous transportation systems based on activity theory. Taking the "MaaS" scenario as an example, the demand analysis of this scenario is achieved through the following steps:

[0172] (a) A tree-structured hierarchical approach is used to abstract typical scenarios for autonomous transportation systems, defining the boundaries of each layer. The MaaS travel scenario is defined as a macro-scenario; the integrated payment scenario for a group of travelers during a MaaS trip is defined as a meso-scenario; and the specific travel behavior of travelers at a certain stage within the integrated payment scenario is defined as a micro-scenario. The three layers of scenarios are targeted at the system, the user group, and the specific user, respectively. Each layer has distinct boundaries, and the granularity of the scenarios decreases.

[0173] (b) According to the triangular model provided by activity theory, obtain the attribute elements involved in typical scenarios at each level.

[0174] Among them, the macro-scenario attribute elements taking the MaaS travel scenario as an example are: concept, characteristics, and comparison; the meso-scenario attribute elements taking the integrated payment scenario of the traveler group during the MaaS travel process as an example are: user group, environment, tool, behavior, goal or expectation; the micro-scenario attribute elements taking the specific travel behavior of travelers at a certain stage under the integrated payment scenario as an example are: time, subject, tool, behavior, object, goal or expectation.

[0175] (c) Define the concepts of typical scene attribute elements at each level.

[0176] Based on the attribute elements of each level of MaaS travel scenario determined above, the specific content of its attribute elements is determined. The content of the scenario attribute elements involved is shown in Table 4 below:

[0177] Table 4

[0178]

[0179]

[0180] Table 4 describes the attribute elements and their definitions in the MaaS scenario.

[0181] (d) Standardize descriptions of typical scenarios at each level, stipulating that scenario descriptions include the aforementioned multiple attribute elements, specifically including the following aspects:

[0182] 1. Standardize the description structure based on the macro-scenario: The macro-scenario of an autonomous transportation system is a <concept>, which is distinguished from the traditional scenario <contrast> and has <characteristics>. Describe the MaaS travel scenario.

[0183] Specifically, the MaaS travel scenario, based on autonomous transportation system technology, is a one-stop travel service that uses one or more modes of transportation to facilitate passenger mobility, taking into account the time, financial, and environmental impact of passenger travel. Unlike traditional transportation systems, MaaS travel for people and goods in this scenario features autonomous perception, learning, decision-making, and response. This includes nine key components: traffic status information, route planning, shared travel management, route navigation, parking management, transfers, integrated payment, dynamic cargo transportation planning, and data storage. This makes it more convenient, intelligent, efficient, and economical.

[0184] 2. Standardize the description structure based on the meso-scenario: In the meso-scenario within the context of autonomous transportation system technology, <user group> can achieve <goal or expectation> through <behavior> using <tool 1, tool 2, etc.> within the <environment> of the autonomous transportation system. Describe the integrated payment scenario for this group of travelers during MaaS travel.

[0185] The specific description is: In the integrated payment scenario under the background of autonomous transportation system technology, travelers can use payment integration, ticket integration and customized personalized service technologies in the integrated payment, one-platform management and one-time security check environment provided by transportation operators, and make one-account payment operations on the mobile platform to achieve seamless personalized travel without the need for multiple scan codes or cash payments.

[0186] 3. Standardize the description structure based on micro-scenarios: Under the constraints of <time>, the <subject> uses <tool 1, tool 2, etc.> to generate travel <behavior> on the <object> in a micro-scenarios of autonomous transportation systems to achieve <goal or expectation>. Describe the specific travel behaviors of travelers at a specific stage in the integrated payment scenario for the traveler group.

[0187] The specific description is: In the integrated payment scenario of the traveler group during the MaaS travel process, a traveler is preparing to take an integrated payment method to complete the trip. Before making the integrated payment, the traveler uses a mobile device to enter the official software through the use of payment integration, ticketing integration and customized personalized service technologies. After determining the starting point and end point, the traveler chooses a personalized travel service that integrates multiple modes of transportation, confirms the itinerary and order amount, and enters the payment interface after identity authentication, so as to realize the user's personalized requirements for this trip and confirm the amount before payment.

[0188] After completing the payment process, travelers can obtain the order number and invoice information through the official travel app through the integrated payment, ticketing and after-sales service, thus completing the order after payment. If the traveler has any questions about the order at this time, they can contact the after-sales service and file a complaint on the after-sales platform to get their questions answered.

[0189] (e) Perform similarity matching between the attribute elements of typical scenarios and the autonomous transportation system requirement library to obtain specific scenario requirements.

[0190] In summary, this paper proposes an activity-based approach for analyzing the requirements of typical scenarios for autonomous transportation systems. Compared to traditional scenarios for intelligent transportation systems, this method provides an effective methodology for rationally classifying and stratifying typical scenarios for autonomous transportation systems. It then describes and analyzes these scenarios from multiple dimensions, forming standardized descriptions of typical scenarios at each level, ultimately identifying the requirements within these scenarios.

[0191] Furthermore, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise indicated, one or more of the functions and / or features described may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It will also be understood that a detailed discussion of the actual implementation of each module is not necessary for understanding the present invention. More specifically, given the properties, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the module will be understood within the ordinary skill of an engineer. Therefore, a person skilled in the art using ordinary skill will be able to implement the present invention set forth in the claims without undue experimentation. It will also be understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0192] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0193] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0194] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0195] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0196] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0197] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

[0198] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A scenario demand analysis method for an autonomous transportation system, characterized in that: include: A tree-structured hierarchical approach is used to abstract typical scenarios of autonomous transportation systems and define the boundaries of each level of scenarios. According to the triangular model of activity theory, obtain the attribute elements involved in typical scenarios at each level; Performing standardized descriptions of typical scenarios at each level, wherein the standardized descriptions of the typical scenarios include a plurality of the attribute elements; Perform text similarity matching between the attribute elements of typical scenarios and the autonomous transportation system requirement database to obtain the target scenario requirements; The process of performing text similarity matching on the attribute elements of the typical scenario and the autonomous transportation system requirement library to obtain the target scenario requirements includes: Determine all documents in the corpus, i.e., the input text; perform word segmentation on each document in the corpus and remove stop words; scan all documents in the corpus and number each word to obtain a dictionary; count the number of occurrences of each word in the dictionary in the document, combine it with the word number to obtain a bigram, and then determine the vectorized corpus; Training a text vector representation model based on the vectorized corpus; converting input text into a text vector based on the trained text vector representation model; Determine the similarity of the key attribute texts corresponding to each text vector by using the cosine similarity calculation method, and perform weighted summation on the similarities to obtain a comprehensive similarity; Determining the result of the scene requirement determination by comparing the magnitude relationship between the comprehensive similarity and a preset threshold; In Match 1, the input text is the subject text and object text of the scenario library and the user text of the requirement library. The cosine similarity calculation is performed between the subject text and object text of the micro-scenario and all the user text vectors of the requirement library. If the similarity between the user text of the requirement library and the subject text and object text is greater than the threshold, the requirement corresponding to the user text is selected as a candidate requirement. In matching 2, the input text is the scene description text of the scene library and the user need text of the requirement library. The cosine similarity calculation is performed on the other key attribute texts of the micro scene except the subject text and object text and all the user need text vectors of the candidate requirement set obtained in matching 1 to obtain the similarity corresponding to each key attribute text. If the similarity between the user need text of the candidate requirement set and other key attribute texts is greater than the threshold, the corresponding requirement will be taken as the requirement of the micro scene.

2. The method for analyzing scenario requirements of an autonomous transportation system according to claim 1, characterized in that: The tree-structured hierarchical approach is used to abstract typical scenarios of autonomous transportation systems in layers, and the boundaries of each layer of scenarios are defined, including: Describe coarse-grained scenarios of autonomous transportation systems at a high level of abstraction; Use the decomposition idea to decompose and refine the high-level scene layer by layer to obtain macroscopic scenes, mesoscopic scenes, and microscopic scenes. Each macroscopic scene contains multiple mesoscopic scenes, and each mesoscopic scene contains multiple microscopic scenes. The macro scenario is used to represent the overall description of a typical scenario of an autonomous transportation system, including but not limited to the operational characteristics of a traffic information collection platform and a road network management platform; The meso-scenario is used to represent a refined description of the system elements in the macro-scenario, including but not limited to the characteristics of the traveler group; The micro-scenario is used to characterize the specific scenarios in the meso-scenario, including but not limited to the behavioral characteristics of a single traveler before the trip, during the trip, and after the trip.

3. The method for analyzing scenario requirements of an autonomous transportation system according to claim 2, characterized in that: The attribute elements involved in the step of obtaining the attribute elements involved in the typical scenes at each level according to the triangular model of activity theory include the attribute elements of the macro scene, the attribute elements of the meso scene and the attribute elements of the micro scene; The attribute elements of the macro scene include concept elements, characteristic elements, and contrast elements; The attribute elements of the meso-scenario include user group elements, environmental elements, group tool elements, group behavior elements, and group goals or expectations elements; The attribute elements of the micro-scene include time elements, subject elements, individual tool elements, individual behavior elements, object elements, and individual goals or expectations elements.

4. The method for analyzing scenario requirements of an autonomous transportation system according to claim 3, characterized in that: The method further comprises: Define the concepts of typical scene attribute elements at each level; The conceptual elements are used to represent the conceptual explanations corresponding to the five typical scenarios of autonomous transportation systems; The characteristic elements are used to represent the supplementary description of the macro-scenario concept under the autonomous transportation system; The comparison factors are used to characterize the characteristics and advantages of typical scenarios of autonomous transportation systems compared to traditional scenarios; The user group element and subject element are used to characterize the initiator of the traffic behavior; The environmental elements are used to characterize the transportation services provided to the user group; The time element is used to represent the time stage in which the subject's behavior occurs in the scene; The object element is used to characterize the goal of the subject's role in traffic behavior; The tool element is used to represent the medium through which the subject acts on the object, including but not limited to GPS positioning technology, communication technology, vehicle-road cooperative technology, and autonomous driving technology; The behavioral elements are used to characterize the behavior of the subject in the traffic environment; The goals or expected elements are used to represent the real needs of users.

5. The method for analyzing scenario requirements of an autonomous transportation system according to claim 4, characterized in that: The above-mentioned standardized description of typical scenarios at each level includes: The macro scenario is standardized as follows: The macro scenario under the autonomous transportation system is "+conceptual elements+" distinguished from the traditional scenario "+contrast elements+" has"+characteristic elements; The mesoscopic scenario is standardized as follows: User group element + "can use" + tool element + "through" behavior element + "achieve" + goal or expectation element under the "environmental element" + provided by the autonomous transportation system; The microscopic scene is standardized as follows: Time element + "under constraints" + subject element + "through the help of" + tool element + "in the micro-scenario travel process under the autonomous transportation system" + object element + "produce travel" + behavior element + "to achieve" + goal or expectation element.

6. An autonomous traffic system scenario demand analysis device, characterized in that: The method for analyzing scenario requirements of an autonomous transportation system according to any one of claims 1 to 5, wherein the device comprises: The first module is used to abstract typical scenarios of autonomous transportation systems using a tree-structured hierarchical method and define the boundaries of each level of scenarios. The second module is used to obtain the attribute elements involved in typical scenarios at each level based on the triangular model of activity theory; The third module is used to perform a standardized description of typical scenes at each level, wherein the standardized description of the typical scenes includes a plurality of the attribute elements; The fourth module is used to perform text similarity matching between the attribute elements of typical scenarios and the autonomous transportation system requirement library to obtain the target scenario requirements.

7. An electronic device, characterized in that: including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that The storage medium stores a program, and the program is executed by a processor to implement the method according to any one of claims 1 to 5.

9. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images