A method, system, and computer storage medium for detecting traffic command conflicts

Abstract

This specification discloses a traffic command conflict detection method, system, and computer storage medium. The traffic command conflict detection method includes: extracting core information of a received traffic command; querying command conflict rules in a command conflict database based on the core information to obtain query results; performing hierarchical command conflict detection based on the query results to obtain the command conflict type corresponding to the traffic command; performing conflict processing on the traffic command according to the command conflict type to obtain conflict processing results; and feeding back the conflict processing results to the command conflict database to update the command conflict rules.

Description

Technical Field

[0001] The embodiments in this specification relate to the field of traffic control technology, and in particular to a traffic command conflict detection method, system, and computer storage medium. Background Technology

[0002] With the rapid development of intelligent transportation systems, centralized management of heterogeneous traffic control equipment has become an important direction for improving traffic efficiency and safety. For example, centralized control architectures such as SDN-based traffic control systems can achieve collaborative scheduling of numerous traffic control applications by separating the application layer, control layer, and device layer. However, due to the parallel operation of multiple applications, traffic command conflicts are becoming increasingly prominent, such as a traffic light displaying green while a variable message sign indicates "No Entry." Traditional traffic control methods mainly rely on manual inspection or single-device log analysis to detect such conflicts, which cannot detect conflicts in real time. In addition, the lack of coordination mechanisms, such as emergency priority and green wave coordination strategies, leads to local optimization causing global deterioration. Therefore, for the problem of traffic control command conflicts under centralized control architecture, there is a lack of a method that can both ensure the efficiency and accuracy of traffic command conflict detection and resolve command conflicts to optimize traffic control efficiency. Summary of the Invention

[0003] In view of this, embodiments of this specification provide a traffic instruction conflict detection method, system, and computer storage medium to solve problems such as insufficient semantic parsing capability of traffic instructions, low efficiency of dynamic conflict detection, and global deterioration caused by local optimization in the prior art.

[0004] The embodiments in this specification adopt the following technical solutions:

[0005] This specification provides a traffic order conflict detection method, which includes:

[0006] Extract the core information of the received traffic instructions;

[0007] Based on the core instruction information, query the instruction conflict rules in the instruction conflict database to obtain the query results;

[0008] Based on the query results, hierarchical detection of instruction conflicts is performed to obtain the instruction conflict type corresponding to the traffic instruction;

[0009] Based on the type of instruction conflict, the traffic instruction is processed to obtain the conflict processing result;

[0010] The conflict resolution results are fed back to the instruction conflict database to update the instruction conflict rules.

[0011] This specification also provides a traffic order conflict detection system, which includes:

[0012] The extraction module extracts the core information of the received traffic instructions.

[0013] The query module queries the instruction conflict database for instruction conflict rules based on the core instruction information to obtain the query results;

[0014] The detection module performs hierarchical detection of instruction conflicts based on the query results to obtain the instruction conflict type corresponding to the traffic instruction;

[0015] The processing module performs conflict processing on the traffic command according to the command conflict type, and obtains the conflict processing result;

[0016] The feedback module sends the conflict handling results back to the instruction conflict database and updates the instruction conflict rules.

[0017] This specification also provides a computer storage medium including a program for use in conjunction with an electronic device, the program being executable by a processor to perform the following steps:

[0018] Extract the core information of the received traffic instructions;

[0019] Based on the core instruction information, query the instruction conflict rules in the instruction conflict database to obtain the query results;

[0020] Based on the query results, hierarchical detection of instruction conflicts is performed to obtain the instruction conflict type corresponding to the traffic instruction;

[0021] Based on the type of instruction conflict, the traffic instruction is processed to obtain the conflict processing result;

[0022] The conflict resolution results are fed back to the instruction conflict database to update the instruction conflict rules.

[0023] The above-described at least one technical solution adopted in the embodiments of this specification can achieve the following beneficial effects:

[0024] By constructing an intelligent, self-learning traffic command conflict management system, through innovative "static and dynamic combination" conflict classification, deep semantic parsing, comprehensive knowledge base-driven approach, optimization algorithm empowerment, closed-loop learning evolution, and modular collaborative design oriented towards a centralized architecture, the various modules work together to achieve static and dynamic conflict detection and optimization of traffic control commands, significantly surpassing traditional methods that rely on manual labor and simple rules.

[0025] This approach not only enables real-time and automatic detection and resolution of static threats to security, but also proactively predicts and globally optimizes the handling of dynamic conflicts affecting efficiency, thereby significantly improving the overall efficiency and security of traffic management under a centralized control architecture. Its application scenarios are clearly defined (e.g., urban signal control, vehicle-road cooperation, emergency priority, etc.), and the technical solution is highly systematic and possesses significant practical value. Attached Figure Description

[0026] The accompanying drawings, which are included to provide a further understanding of the embodiments of this specification and form part of the embodiments of this specification, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0027] Figure 1 A schematic flowchart illustrating a traffic command conflict detection method provided in an embodiment of this specification;

[0028] Figure 2 A diagram illustrating the parsing architecture of a semantic conflict pattern library corresponding to a traffic command conflict detection method provided in an embodiment of this specification.

[0029] Figure 3 This is a schematic diagram of the system architecture corresponding to a traffic command conflict detection method provided in the embodiments of this specification;

[0030] Figure 4 A schematic diagram of the conflict detection process corresponding to a traffic command conflict detection method provided in the embodiments of this specification;

[0031] Figure 5 A schematic diagram of a traffic command conflict detection system provided in the embodiments of this specification;

[0032] Figure 6 This is a schematic diagram of the structure of a computer storage medium corresponding to a traffic command conflict detection method provided in an embodiment of this specification. Detailed Implementation

[0033] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments in this specification, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments in this specification without creative effort are within the scope of protection of this application.

[0034] The technical solutions provided in the various embodiments of this specification are described in detail below with reference to the accompanying drawings.

[0035] like Figure 1The diagram shown is a flowchart illustrating a traffic command conflict detection method provided in an embodiment of this specification.

[0036] In the embodiments described in this specification, the traffic command conflict detection method may specifically include the following steps:

[0037] S101: Extract core information of the received traffic instructions;

[0038] S103: Based on the core instruction information, query the instruction conflict rules in the instruction conflict database to obtain the query results;

[0039] S105: Perform instruction conflict layer detection based on the query results to obtain the instruction conflict type corresponding to the traffic instruction;

[0040] S107: Based on the conflict type of the instruction, perform conflict processing on the traffic instruction to obtain the conflict processing result;

[0041] S109: Feed back the conflict handling result to the instruction conflict database and update the instruction conflict rules.

[0042] In the embodiments of this specification, traffic command conflicts can be specifically divided into the following two categories:

[0043] One type of conflict is a conflict that can be determined to conflict with the existing traffic control status or instructions after the instructions are issued, which may affect traffic safety and lead to risks such as vehicle collisions, pedestrian accidents or traffic paralysis. This is defined as a static conflict. Static conflicts are usually caused by phase competition, conflicting control instructions, or conflicting emergency responses.

[0044] Another type of conflict is a potential conflict. At the time the instruction is issued, it cannot be determined whether a conflict will definitely occur, but it can be determined that certain events may lead to a conflict during the execution of the instruction. This type of conflict is called a dynamic conflict. These conflicts do not directly endanger safety, but they reduce traffic efficiency and increase delays and congestion. They are commonly seen in scenarios such as green wave coordination failures, conflicts between sensor-based control and fixed timing, and conflicts between bus priority and private vehicle traffic.

[0045] As an application embodiment of this specification, step S101, extracting the core information of the received traffic instruction, may specifically include:

[0046] Identify ambiguous or polysemous expressions in the traffic instructions to obtain identification results;

[0047] The traffic instruction is disambiguated based on the recognition result;

[0048] The disambiguated traffic instructions are semantically parsed and standardized to obtain the parsing results;

[0049] Extract the core information of the instruction from the parsing results.

[0050] In the embodiments described in this specification, the core information of the instruction may specifically include information such as the target device, operation content, and time parameters, which are not specifically limited here.

[0051] Furthermore, identifying ambiguous expressions or ambiguities in the traffic instructions to obtain identification results can specifically include:

[0052] Using natural language processing technology, combined with a semantic conflict pattern library, the system identifies ambiguous expressions or ambiguities in the traffic instructions, and obtains the identification results.

[0053] Natural Language Processing (NLP) technology, through the cross-integration of computer science, linguistics, and machine learning, aims to build systems that can understand, interpret, and generate human language, enabling computers to understand, process, and generate human language, and to perform tasks such as human-computer interaction and information extraction.

[0054] The semantic conflict pattern library is constructed in the embodiments of this specification, and may specifically include a synonym instruction mapping table, polysemous word context matching rules, and fuzzy instruction default filling rules. For example... Figure 2 The diagram shown is a parsing architecture diagram of a semantic conflict pattern library corresponding to a traffic command conflict detection method provided in an embodiment of this specification.

[0055] Among them, the synonym instruction mapping table can be generated based on word vector clustering (for example, when Word2Vec is used to train traffic text, the vector distance between "prohibited" and "red light" is less than 0.2), which can be used to solve the differences in instruction expression across multiple applications.

[0056] Specifically, the synonym instruction mapping table can be constructed in the following ways:

[0057] Collect historical traffic instruction text corpora;

[0058] Train instruction word vectors using a word embedding model;

[0059] For vector space clustering, instruction words within a distance threshold are determined to be synonyms.

[0060] The context matching rules for polysemous words can be implemented by relying on syntactic analysis and scene tags. For example, when parsing the word "yield," if the subject is "bus," the action can be analyzed as extending the green light; if the subject is "accident," the action can be analyzed as closing the lane. This can overcome parsing errors caused by polysemy.

[0061] Specifically, the generation of polysemous context matching rules can include:

[0062] Extract the dependency syntactic features of polysemous words, such as subject / object / adverbial, etc.

[0063] Label the scenarios with tags, such as emergency priority / bus dispatch / accident handling, etc.

[0064] A mapping rule for semantic labels corresponding to <feature, scene> is established based on the random forest model.

[0065] The default filling rules for fuzzy instructions can be inferred based on the probabilities of Bayesian networks. For example, "optimized passage" defaults to "green wave coordination" with a confidence level of over 80%, which can be used to fill the semantic gaps in incomplete instructions.

[0066] Specifically, the default fill for fuzzy instructions can include:

[0067] Construct a Bayesian network where nodes include command keywords, time, location, weather, etc., without making specific limitations here;

[0068] Learn the conditional probability of nodes by using a historical instruction library;

[0069] Default operating parameters are generated based on the maximum a posteriori probability.

[0070] Furthermore, the traffic instruction is disambiguated based on the recognition result, which may specifically include:

[0071] Based on the polysemous word context matching rules, and combined with the instruction source scene tags, the true semantics of polysemous words are parsed to perform disambiguation processing on the traffic instructions.

[0072] In the embodiments of this specification, the instruction source scenario label may specifically originate from the identification result of the traffic instruction.

[0073] Furthermore, the disambiguated traffic instructions are semantically parsed and standardized to obtain the parsing results, which may specifically include:

[0074] The non-standard expressions in traffic instructions after disambiguation are converted into standard control instructions through a synonym instruction mapping table.

[0075] In the embodiments of this specification, after semantic parsing and standardization of the disambiguated traffic instructions, the method may further include:

[0076] The fuzzy instructions in the traffic instructions after disambiguation are used to generate default operation parameters based on the historical data probability model, so as to perform the default filling operation of the fuzzy instructions.

[0077] By performing a default fill operation on fuzzy instructions, the fuzzy instructions can be standardized and parameters can be automatically completed, making the expression of traffic instructions clearer and more concise.

[0078] Based on the above-described embodiments, the specific application of the semantic conflict pattern library in specific application embodiments will be described below.

[0079] For example, in a specific application scenario, the upper-level traffic control platform issues a traffic instruction: "During the morning rush hour, buses must give way at the intersection of Renmin Road and Jiefang Road."

[0080] Perform semantic disambiguation on this traffic instruction:

[0081] Extract keywords: <Action = "Give way", Location = "Renmin Road - Jiefang Road intersection", Scene = "Morning rush hour" + "Bus">;

[0082] According to the matching rule base, when the action = "yield" and the subject implicitly contains "bus", the semantic tag "extend the green light for bus phase" is executed.

[0083] Perform semantic standardization:

[0084] Query the synonym mapping table: "Yield" → standard command "Phase Lengthen".

[0085] Use default fill:

[0086] The fuzzy parameter “morning rush hour” triggers a Bayesian network, with P(extended duration = 8s | time period = morning rush hour, location = core area) = 92%;

[0087] Output the standardized command, "Traffic light ID123: Phase P2 extended by 8 seconds".

[0088] In the embodiments of this specification, natural language processing technology and a specialized semantic conflict pattern library are introduced to parse complex, potentially ambiguous or polysemous traffic instructions (e.g., text instructions from different applications). The process of resolving semantic conflicts is standardized into a computable rule engine, which breaks through the limitations of traditional keyword matching. This is the key to improving the accuracy of conflict detection in complex instruction environments, solves the parsing difficulties and potential ambiguities caused by diverse instruction sources and complex expressions, overcomes the limitations of existing technologies that mainly rely on structured parameter matching, and lays the foundation for subsequent accurate conflict detection.

[0089] As an application embodiment of this specification, for step S103, querying instruction conflict rules in the instruction conflict database based on the instruction core information to obtain the query results may specifically include:

[0090] Query the instruction conflict database for instruction conflict rules or historical conflict cases corresponding to the core information of the instruction.

[0091] In the embodiments described in this specification, the instruction conflict database may specifically store static conflict rules, dynamic conflict history data, and semantic conflict patterns to support conflict detection.

[0092] Specifically, the instruction conflict database may include: a device conflict rule base (defining physical conflict constraints between different device operations, such as a green traffic light and a "no entry" sign on an information board), a logical conflict rule base (defining logical constraint relationships between instructions, such as instruction A must be executed before instruction B), a dynamic conflict case base (recording historical conflict cases, including historical dynamic conflict scenarios and their characteristics and solutions), and a semantic conflict pattern base (storing parsing rules for resolving and eliminating ambiguous instructions).

[0093] In the embodiments of this specification, a structured instruction conflict database containing various rules and case types (device rules, logic rules, dynamic cases, semantic patterns) is constructed. It is not only a collection of rules, but also a comprehensive knowledge base containing historical experience (dynamic cases) and semantic knowledge (patterns). This provides strong multi-dimensional knowledge support for efficient and accurate conflict detection (especially rule-based static detection and case matching), avoiding the limitations of a single rule base.

[0094] As an application embodiment of this specification, for step S105, performing instruction conflict layer detection based on the query results to obtain the instruction conflict type corresponding to the traffic instruction may specifically include:

[0095] Based on the query results, static conflict detection is performed on the traffic instructions;

[0096] If no static conflict is detected, then dynamic conflict detection is performed on the traffic instruction.

[0097] Specifically, static conflict detection of the traffic instructions may include:

[0098] Based on the query results, a static conflict rule base is matched to determine whether the traffic instruction conflicts immediately with the current traffic status or existing instructions.

[0099] If so, then the traffic instruction is determined to have a static conflict;

[0100] If not, then continue with dynamic conflict detection for the traffic instructions.

[0101] Furthermore, dynamic conflict detection of the traffic instructions may specifically include:

[0102] The optimization algorithm is used to predict the probability of potential conflicts caused by event triggering during the execution of the traffic order;

[0103] If the probability exceeds a set threshold, it is determined that the traffic instruction has a dynamic conflict.

[0104] In the embodiments of this specification, traffic orders are dynamically conflict detected. The optimization algorithm can specifically adopt genetic algorithms or heuristic search, etc., without being specifically limited here, in order to simplify the dynamic conflict prediction process and improve detection efficiency. Alternatively, the probability of conflict occurrence can be calculated through a dynamic model, and when the probability exceeds a set threshold, it is determined to be a dynamic conflict.

[0105] The dynamic model can be pre-built using machine learning or other methods, and no specific limitations are made here.

[0106] As an application embodiment of this specification, step S107, which involves processing the traffic instruction according to the instruction conflict type to obtain a conflict processing result, may specifically include:

[0107] If the instruction conflict type is a static conflict, then the priority of the static conflicting instructions is determined, and the static conflicting instructions are merged according to the rule that higher priority instructions override lower priority instructions to generate a static conflict solution.

[0108] If the instruction conflict type is a dynamic conflict, a global optimization algorithm is used to adjust the instruction execution order.

[0109] In the embodiments of this specification, for static conflict instruction types, an instruction priority mechanism can be preset, and the priority of static conflict instructions can be determined based on the instruction priority mechanism.

[0110] Furthermore, a global optimization algorithm can be used to adjust the instruction execution order, which may specifically include:

[0111] Using genetic algorithms or reinforcement learning models, with global traffic efficiency as the optimization objective, green wave parameters, signal phase time, or downstream equipment startup timing are adjusted.

[0112] In the embodiments described in this specification, the global optimization algorithm may include genetic algorithms or reinforcement learning models, etc., and is not specifically limited here. Traffic efficiency is improved by adjusting the order of instruction execution through traffic control parameters. Specifically, traffic control parameters may include green wave parameters, signal phase timing, or downstream equipment startup sequence, etc., and are not specifically limited here.

[0113] By clearly distinguishing between immediately identified security risk conflicts (static conflicts) and potential future efficiency impact conflicts (dynamic conflicts), and designing different detection and handling strategies accordingly, this represents a significant extension and deepening of the traditional conflict concept. It directly solves the problems in existing technologies where conflicts cannot be detected in real time (relying on static detection) and where local optimization leads to global deterioration (relying on dynamic detection and handling).

[0114] In addition, the core applications of optimization algorithms (genetic algorithms, heuristic search, etc.) and global optimization algorithms (genetic algorithms, reinforcement learning, etc.) are used in dynamic conflict detection and handling.

[0115] In the detection phase, optimization algorithms are used to simplify the dynamic conflict detection process, solve the combinatorial explosion problem, and improve the efficiency of predicting potential conflicts in large-scale complex road networks.

[0116] At the dynamic conflict handling end, global optimization algorithms are used to find the overall optimal or suboptimal solution (such as adjusting phase time, signal period, green wave parameters, etc.) to resolve conflicts while optimizing global traffic flow efficiency (such as reducing total delay).

[0117] It efficiently solves the computational complexity problem of dynamic conflict detection and avoids global deterioration caused by local optimization through global optimization, thus achieving true collaborative optimization.

[0118] As an application embodiment of this specification, for step S109, by feeding back the results of conflict handling (especially successfully resolved dynamic conflict cases) to the instruction conflict database, the system can continuously learn new conflict patterns and effective solutions, update the rule base and optimize model parameters, realize the continuous evolution of the knowledge base and the self-improvement of system performance, and enable the system to adapt to the ever-changing traffic environment and new application requirements, overcoming the shortcomings of static rule bases being easily outdated and having poor adaptability.

[0119] The traffic command conflict detection method provided in this specification constructs an intelligent, self-learning traffic command conflict management system. Through innovative "static and dynamic combination" conflict classification, deep semantic parsing, comprehensive knowledge base driving, optimization algorithm empowerment, closed-loop learning evolution, and modular collaborative design oriented towards a centralized architecture, the various modules work together to realize the detection and optimization of static and dynamic conflicts of traffic control commands, significantly surpassing traditional methods that rely on manual labor and simple rules.

[0120] This approach not only enables real-time and automatic detection and resolution of static threats to security, but also proactively predicts and globally optimizes the handling of dynamic conflicts affecting efficiency, thereby significantly improving the overall efficiency and security of traffic management under a centralized control architecture. Its application scenarios are clearly defined (e.g., urban signal control, vehicle-road cooperation, emergency priority, etc.), and the technical solution is highly systematic and possesses significant practical value.

[0121] It should be noted that the above-described specific traffic command conflict detection method is merely a specific application example and does not limit the scope of the embodiments in this specification. Other specific embodiments may also be included, which will not be elaborated here.

[0122] Based on the same inventive concept, this specification also provides specific application examples of the above-described traffic command conflict detection method.

[0123] like Figure 3 The diagram shown is a system architecture diagram corresponding to a traffic command conflict detection method provided in an embodiment of this specification.

[0124] In the embodiments of this specification, the system architecture corresponding to the traffic command conflict detection method includes an application layer, a control layer, and a traffic equipment layer.

[0125] The application layer may specifically include traffic control application 1, traffic control application 2, traffic control application N, etc., and the specific number of traffic control applications is not limited here.

[0126] The control layer includes a conflict detection and processing system and a traffic central controller. Specifically, the conflict detection and processing system may include an instruction conflict database, a database query module, an instruction parsing module, a conflict detection module, and a conflict processing module.

[0127] The traffic equipment layer may specifically include traffic signals, variable message signs, and traffic detectors, etc., without being specifically limited here.

[0128] Specifically, the instruction parsing module performs semantic parsing and standardization on traffic instructions, extracting core information such as target equipment, operation content, and time parameters. Using Natural Language Processing (NLP) technology, combined with a semantic conflict pattern library, it identifies ambiguous expressions or ambiguities in the instructions and performs disambiguation.

[0129] The instruction conflict database stores static conflict rules, dynamic conflict history data, and semantic conflict patterns to support conflict detection. The database includes: a device conflict rule base (defining contradictory constraints on device operations), a logical conflict rule base (defining logical relationships between instructions), a dynamic conflict case base (recording historical conflict cases), and a semantic conflict pattern base (stores parsing rules for ambiguous instructions).

[0130] The database query module is responsible for receiving traffic instructions to be detected, querying data in the instruction conflict database, matching possible conflict rules or historical cases, optimizing query speed with indexes, and supporting fast retrieval.

[0131] The conflict detection module is used to detect potential dynamic conflicts. It uses optimization algorithms (such as genetic algorithms and heuristic search) to simplify the dynamic conflict detection process and improve detection efficiency.

[0132] The conflict resolution module addresses static conflicts by implementing a priority mechanism, where higher-priority instructions override lower-priority instructions, merging conflicting instructions, and generating a compromise optimization solution. For dynamic potential conflicts, it employs global optimization algorithms (such as genetic algorithms and reinforcement learning) to adjust the instruction execution order. It also dynamically adjusts parameters such as green wave bands and signal timing to improve traffic efficiency. Conflict resolution results are fed back to the instruction conflict database for updating the rule base and optimization model.

[0133] In the specific implementation process, the application layer sends the traffic command to be detected to the command parsing module. The module parses the traffic command, extracts its core information, and then uses a database query module to search for command conflict rules in the command conflict database. A conflict detection module detects the conflict type of the traffic command, and based on the detected conflict type, a conflict handling module processes the conflict to obtain an optimized traffic control command. This optimized traffic control command is then sent to the traffic equipment layer for execution. Simultaneously, conflict information is fed back to the command conflict database for data updates.

[0134] like Figure 4 The diagram shown is a flowchart illustrating the conflict detection process of a traffic command conflict detection method provided in an embodiment of this specification.

[0135] In the embodiments described in this specification, the collision detection process may specifically include the following steps:

[0136] S401: Start the testing process;

[0137] S402: The upper-level traffic control application issues traffic control instructions;

[0138] S403: The instruction parsing module extracts the core information of the instruction, which includes, for example, the target device, the operation content, and time parameters.

[0139] S404: The database query module receives the traffic instructions to be detected and queries the database for conflicting instructions;

[0140] S405: Determine if a traffic order is a static conflict;

[0141] S406: If it is a static conflict, then use the conflict handling module to handle the static conflict.

[0142] S407: If it is not a static conflict, send the detection result to the conflict detection module;

[0143] S408: Determine if a traffic order is a dynamic conflict;

[0144] S409: If it is a dynamic conflict, then use the conflict handling module to handle the dynamic conflict.

[0145] S410: If it is not a dynamic conflict, the detection result or the processing result of the conflict handling module will be sent to the central controller, which will then issue control commands.

[0146] S411: Feed back the processing results of the conflict handling module to the database, update the conflict rules, and submit the conflict query results of S404 to the database.

[0147] S412: End the conflict detection process.

[0148] Based on the above conflict detection process, the following are specific application examples of static conflict detection and dynamic conflict detection provided in this specification.

[0149] For static conflict detection.

[0150] The conflict scenario is: the traffic light shows a green light for going straight, but the variable message sign indicates "Traffic control ahead, straight ahead prohibited".

[0151] In this conflict scenario, the static conflict detection process should be performed according to the following steps:

[0152] 1. The instruction parsing module parses the instructions issued by the upper-layer application, sets the traffic light phase to green to allow straight-ahead movement, and displays text on the variable message sign to prohibit straight-ahead movement.

[0153] 2. The database query module queries the instruction conflict database for data;

[0154] 3. The instruction conflict database is used for rule matching to obtain static conflict conclusions;

[0155] 4. The conflict handling module performs static conflict handling, and according to the instruction priority rules, forces the traffic light to turn red, and updates the variable message sign to "go by signal".

[0156] For dynamic conflict detection.

[0157] The conflict scenario is: a bus requests an extension of the green light at a certain intersection, which may disrupt the coordination of the downstream green wave and affect traffic efficiency.

[0158] In this conflict scenario, the dynamic conflict detection process is carried out according to the following steps:

[0159] 1. The instruction parsing module parses the instructions issued by the upper-layer application. The traffic lights at this intersection will prioritize buses, and this road segment will be set to green wave traffic for trunk lines.

[0160] 2. The database query module queries the instruction conflict database for data;

[0161] 3. The instruction conflict database performs rule matching, which is not a static conflict;

[0162] 4. The conflict detection module performs potential conflict detection. Based on the dynamic model, it predicts that the probability of the green wave breaking caused by the bus priority instruction is greater than 85%, which is a dynamic conflict.

[0163] 5. The conflict handling module performs dynamic conflict handling, which shortens the bus phase by 5 seconds and simultaneously accelerates the start of the downstream green light.

[0164] As can be seen, the embodiments in this specification are specifically designed for centralized control architectures (such as SDN), where each module (parsing, querying, database, detection, processing, etc.) has clear functions, well-defined boundaries, and works collaboratively. This modular design facilitates system expansion (such as adding new conflict rules or detection algorithms) and upgrades and maintenance, meeting the needs of multi-application collaboration, complex instruction flows, and the requirement for efficient and reliable processing under a centralized control architecture.

[0165] The specific implementation process of the embodiments in this specification can be referred to the various implementation steps corresponding to the above embodiments, and will not be repeated here.

[0166] Based on the same inventive concept, embodiments of this specification also provide a traffic order conflict detection system. For example... Figure 5 The diagram shown is a structural schematic of a traffic command conflict detection system provided in an embodiment of this specification.

[0167] Specifically, the traffic command conflict detection system may include:

[0168] Extraction module 501 extracts the core information of the received traffic instructions;

[0169] The query module 502 queries the instruction conflict database for instruction conflict rules based on the instruction core information to obtain the query results;

[0170] The detection module 503 performs hierarchical detection of instruction conflicts based on the query results to obtain the instruction conflict type corresponding to the traffic instruction;

[0171] The processing module 504 performs conflict processing on the traffic command according to the command conflict type, and obtains the conflict processing result;

[0172] The feedback module 505 feeds back the conflict handling result to the instruction conflict database and updates the instruction conflict rules.

[0173] based on Figure 5 The system described in this specification also provides some specific implementation schemes of the system, which will be described below.

[0174] Furthermore, the core information of the received traffic instructions is extracted, including:

[0175] Identify ambiguous or polysemous expressions in the traffic instructions to obtain identification results;

[0176] The traffic instruction is disambiguated based on the recognition result;

[0177] The disambiguated traffic instructions are semantically parsed and standardized to obtain the parsing results;

[0178] Extract the core information of the instruction from the parsing results.

[0179] Furthermore, the system identifies ambiguous expressions or ambiguities in the traffic instructions to obtain identification results, including:

[0180] Using natural language processing technology, combined with a semantic conflict pattern library, the system identifies ambiguous expressions or ambiguities in the traffic instructions, and obtains the identification results.

[0181] Furthermore, the instruction conflict database includes the following stored content:

[0182] A device conflict rule base is used to define physical conflict constraints between the operations of different devices;

[0183] A logical conflict rule base is used to define logical constraint relationships between instructions;

[0184] A dynamic conflict case library is used to record historical conflict cases;

[0185] A semantic conflict pattern library that stores parsing rules for resolving and eliminating ambiguous instructions.

[0186] Furthermore, based on the query results, hierarchical detection of instruction conflicts is performed to obtain the instruction conflict type corresponding to the traffic instruction, including:

[0187] Based on the query results, static conflict detection is performed on the traffic instructions;

[0188] If no static conflict is detected, then dynamic conflict detection is performed on the traffic instruction.

[0189] Furthermore, static conflict detection is performed on the traffic instructions, including:

[0190] Based on the query results, a static conflict rule base is matched to determine whether the traffic instruction conflicts immediately with the current traffic status or existing instructions.

[0191] If so, then the traffic instruction is determined to have a static conflict;

[0192] If not, then continue with dynamic conflict detection for the traffic instructions.

[0193] Furthermore, dynamic conflict detection is performed on the traffic instructions, including:

[0194] The optimization algorithm is used to predict the probability of potential conflicts caused by event triggering during the execution of the traffic order;

[0195] If the probability exceeds a set threshold, it is determined that the traffic instruction has a dynamic conflict.

[0196] Furthermore, based on the specified conflict type, the traffic command is processed to obtain a conflict resolution result, including:

[0197] If the instruction conflict type is a static conflict, then the priority of the static conflicting instructions is determined, and the static conflicting instructions are merged according to the rule that higher priority instructions override lower priority instructions.

[0198] If the instruction conflict type is a dynamic conflict, a global optimization algorithm is used to adjust the instruction execution order.

[0199] The traffic command conflict detection system provided in this specification constructs an intelligent, self-learning traffic command conflict management system. Through innovative "static and dynamic combination" conflict classification, deep semantic parsing, comprehensive knowledge base driving, optimization algorithm empowerment, closed-loop learning evolution, and modular collaborative design oriented towards a centralized architecture, the various modules work together to realize the detection and optimization of static and dynamic conflicts of traffic control commands, significantly surpassing traditional methods that rely on manual labor and simple rules.

[0200] This approach not only enables real-time and automatic detection and resolution of static threats to security, but also proactively predicts and globally optimizes the handling of dynamic conflicts affecting efficiency, thereby significantly improving the overall efficiency and security of traffic management under a centralized control architecture. Its application scenarios are clearly defined (e.g., urban signal control, vehicle-road cooperation, emergency priority, etc.), and the technical solution is highly systematic and possesses significant practical value.

[0201] Based on the same inventive concept, embodiments of this specification also provide an electronic device, including at least one processor and a memory, wherein the memory stores a program and is configured to be executed by the at least one processor in the following steps:

[0202] Extract the core information of the received traffic instructions;

[0203] Based on the core instruction information, query the instruction conflict rules in the instruction conflict database to obtain the query results;

[0204] Based on the query results, hierarchical detection of instruction conflicts is performed to obtain the instruction conflict type corresponding to the traffic instruction;

[0205] Based on the type of instruction conflict, the traffic instruction is processed to obtain the conflict processing result;

[0206] The conflict resolution results are fed back to the instruction conflict database to update the instruction conflict rules.

[0207] Other functions of the processor can be found in the above embodiments, and will not be repeated here.

[0208] Based on the same inventive concept, embodiments of this specification also provide a computer-readable storage medium, including a program for use in conjunction with an electronic device, the program being executable by a processor to perform the following steps:

[0209] Extract the core information of the received traffic instructions;

[0210] Based on the core instruction information, query the instruction conflict rules in the instruction conflict database to obtain the query results;

[0211] Based on the query results, hierarchical detection of instruction conflicts is performed to obtain the instruction conflict type corresponding to the traffic instruction;

[0212] Based on the type of instruction conflict, the traffic instruction is processed to obtain the conflict processing result;

[0213] The conflict resolution results are fed back to the instruction conflict database to update the instruction conflict rules.

[0214] Other functions of the processor can be found in the above embodiments, and will not be repeated here.

[0215] like Figure 6 As shown in the figure, this specification also provides a schematic diagram of the structure of a computer storage medium.

[0216] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0217] For ease of description, the above devices are described separately by function as various units. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware.

[0218] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0219] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0220] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0221] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0222] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0223] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0224] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0225] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0226] This application can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0227] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0228] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of protection of the claims of this application.

Claims

1. A traffic order conflict detection method, characterized in that, The traffic command conflict detection method includes: Extract the core information of the received traffic instructions; Based on the core instruction information, query the instruction conflict rules in the instruction conflict database to obtain the query results; Based on the query results, hierarchical detection of command conflicts is performed to obtain the command conflict type corresponding to the traffic command; according to the command conflict type, conflict processing is performed on the traffic command to obtain the conflict processing result; and The conflict resolution results are fed back to the instruction conflict database to update the instruction conflict rules. Extract the core information of the received traffic instructions, including: Identify ambiguous or polysemous expressions in the traffic instructions to obtain identification results; The traffic instruction is disambiguated based on the recognition result; The disambiguated traffic instructions are semantically parsed and standardized to obtain the parsing results; and Extract the core information of the instruction from the parsing results. Based on the query results, hierarchical detection of instruction conflicts is performed to obtain the instruction conflict type corresponding to the traffic instruction, including: Based on the query results, static conflict detection is performed on the traffic instructions; If no static conflict is detected, then dynamic conflict detection is performed on the traffic instruction. The static conflict refers to a conflict that can be determined immediately after the instruction is issued, which conflicts with the existing traffic control status or instructions, thus affecting traffic safety. Static conflicts are caused by phase competition, conflicting control instructions, and conflicting emergency responses. The dynamic conflict refers to a potential conflict that can be determined to occur during the execution of the instruction due to events. Dynamic conflicts include scenarios such as green wave coordination failure, conflicts between sensor control and fixed timing, and conflicts between bus priority and private vehicles. Static conflict detection is performed on the traffic instructions, including: Based on the query results, a static conflict rule base is matched to determine whether the traffic instruction conflicts immediately with the current traffic status or existing instructions. If so, then the traffic instruction is determined to have a static conflict; If not, then continue with dynamic conflict detection for the traffic instructions. Dynamic conflict detection is performed on the traffic instructions, including: Genetic algorithms or heuristic search are used to predict the probability of potential conflicts caused by event triggering during the execution of the traffic order; If the probability exceeds a set threshold, then the traffic instruction is determined to have a dynamic conflict. Based on the specified conflict type, the traffic command is processed to obtain a conflict resolution result, including: If the instruction conflict type is a static conflict, then the priority of the static conflicting instructions is determined, and the static conflicting instructions are merged according to the rule that higher priority instructions override lower priority instructions. If the instruction conflict type is a dynamic conflict, a global optimization algorithm is used to adjust the instruction execution order. The method of adjusting the instruction execution order using a global optimization algorithm specifically includes: using a genetic algorithm or reinforcement learning model, with global traffic efficiency as the optimization objective, to adjust the green wave parameters, signal phase time, or the startup sequence of downstream equipment.

2. The method as described in claim 1, characterized in that, Identify ambiguous expressions or ambiguities in the traffic instructions to obtain identification results, including: Using natural language processing technology, combined with a semantic conflict pattern library, the system identifies ambiguous expressions or ambiguities in the traffic instructions, and obtains the identification results.

3. The method as described in claim 1, characterized in that, The instruction conflict database includes the following stored contents: A device conflict rule base is used to define physical conflict constraints between the operations of different devices; A logical conflict rule base is used to define logical constraint relationships between instructions; A dynamic conflict case library is used to record historical conflict cases; as well as A semantic conflict pattern library that stores parsing rules for resolving and eliminating ambiguous instructions.

4. A traffic command conflict detection system, characterized in that, The traffic command conflict detection system includes: The extraction module extracts the core information of the received traffic instructions. The query module queries the instruction conflict database for instruction conflict rules based on the core instruction information to obtain the query results; The detection module performs hierarchical detection of instruction conflicts based on the query results to obtain the instruction conflict type corresponding to the traffic instruction; The processing module performs conflict processing on the traffic command according to the command conflict type, and obtains the conflict processing result; and The feedback module sends the conflict resolution results back to the instruction conflict database to update the instruction conflict rules. The extraction module: Identify ambiguous or polysemous expressions in the traffic instructions to obtain identification results; The traffic instruction is disambiguated based on the recognition result; The disambiguated traffic instructions are semantically parsed and standardized to obtain the parsing results; and The detection module extracts the core instruction information from the parsing results. Based on the query results, static conflict detection is performed on the traffic instructions; If no static conflict is detected, then dynamic conflict detection is performed on the traffic instruction. The static conflict refers to a conflict that can be determined immediately after the instruction is issued, which conflicts with the existing traffic control status or instructions, thus affecting traffic safety. Static conflicts are caused by phase competition, conflicting control instructions, and emergency response conflicts. The dynamic conflict refers to a potential conflict that can be determined to occur during the execution of the instruction due to the occurrence of events. Dynamic conflicts include scenarios such as green wave coordination failure, conflicts between sensor control and fixed timing, and conflicts between bus priority and private vehicles. Static conflict detection is performed on the traffic instructions, including: Based on the query results, a static conflict rule base is matched to determine whether the traffic instruction conflicts immediately with the current traffic status or existing instructions. If so, then the traffic instruction is determined to have a static conflict; If not, then continue with dynamic conflict detection for the traffic instructions. Dynamic conflict detection is performed on the traffic instructions, including: Genetic algorithms or heuristic search are used to predict the probability of potential conflicts caused by event triggering during the execution of the traffic order; If the probability exceeds a set threshold, then the traffic instruction is determined to have a dynamic conflict. Based on the specified conflict type, the traffic command is processed to obtain a conflict resolution result, including: If the instruction conflict type is a static conflict, then the priority of the static conflicting instructions is determined, and the static conflicting instructions are merged according to the rule that higher priority instructions override lower priority instructions. If the instruction conflict type is a dynamic conflict, a global optimization algorithm is used to adjust the instruction execution order. The method of adjusting the instruction execution order using a global optimization algorithm specifically includes: using a genetic algorithm or reinforcement learning model, with global traffic efficiency as the optimization objective, to adjust the green wave parameters, signal phase time, or the startup sequence of downstream equipment.

5. A computer storage medium comprising a program for use in conjunction with an electronic device, the program being executable by a processor to perform the steps of the traffic order conflict detection method according to any one of claims 1-3.

Images