Description rule training method and device, electronic equipment, medium and program product

Abstract

The invention discloses a commentary rule training method and device, electronic equipment, a medium and a program product, and the method comprises the steps: obtaining historical traffic data and traffic signs corresponding to a to-be-trained person; determining importance indexes and correlation indexes of the traffic signs according to the historical traffic data; and obtaining a sign explanation rule corresponding to each traffic sign, and determining a target rule explanation sequence of each sign explanation rule based on the importance index and the correlation index of each traffic sign. According to the invention, for each to-be-trained person, the traffic sign contacted by the to-be-trained person is obtained, so that the training method is more suitable for the driving characteristics of the to-be-trained person, and the pertinence of the training method is improved; the importance indexes and the correlation indexes are used as constraint conditions to determine the optimal rule commentary sequence, so that the reliability of the training method can be improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method, apparatus, electronic device, medium, and program product for interpreting rules training. Background Technology

[0002] Traffic safety is an important component of public safety, and traffic safety education and training serve as a core means to enhance drivers' safety awareness, standardize driving behavior, and reduce road traffic accidents.

[0003] With the rapid development of extended reality technology, virtual reality, augmented reality and other technologies are gradually being integrated into the field of safety education and training. By constructing immersive virtual traffic scenarios, learners can intuitively experience various road environments, providing a new technical approach for traffic safety training.

[0004] Existing traffic safety education and training systems based on extended reality technology primarily use high-resolution cameras and sensors to collect images of traffic signs and surrounding environment data. This traffic sign information is then overlaid onto the user's real-world view, simulating complex traffic scenarios such as multi-sign road sections to help learners identify traffic signs. However, these systems neglect the varying degrees of impact different signs have on safe driving and fail to establish a clear explanation order for the overlaid signs. This prevents users from gaining a comprehensive understanding of the traffic signs, thus limiting the effectiveness of safety education and training. Summary of the Invention

[0005] This invention provides a method, apparatus, electronic device, medium, and program product for explaining rules training, in order to avoid confusion in the explanation order when multiple symbols are superimposed, thereby improving the training experience for trainees.

[0006] In one aspect, the present invention provides a method for training interpretation rules, comprising:

[0007] Obtain historical traffic data and traffic signs corresponding to the personnel to be trained;

[0008] Determine the importance and relevance indicators of traffic signs based on historical traffic data;

[0009] Obtain the interpretation rules for each traffic sign, and determine the target rule interpretation order for each traffic sign based on its importance and relevance indicators.

[0010] In another aspect of the present invention, an explanation rule training device is provided, comprising:

[0011] The data acquisition module is used to acquire historical traffic data and traffic signs corresponding to the trainees;

[0012] The indicator acquisition module is used to determine the importance and relevance indicators of traffic signs based on historical traffic data.

[0013] The sequence determination module is used to obtain the sign interpretation rules corresponding to each traffic sign, and determine the target rule interpretation order of each sign interpretation rule based on the importance index and relevance index of each traffic sign.

[0014] In another aspect of the present invention, an electronic device is provided, comprising:

[0015] At least one processor; and

[0016] Memory that is communicatively connected to at least one processor;

[0017] The memory stores a computer program that can be executed by at least one processor, which enables the at least one processor to perform the explanation rule training method of any embodiment of the present invention.

[0018] In another aspect, the present invention provides a computer-readable storage medium comprising: computer instructions that enable a processor to execute the interpretation rule training method of any embodiment of the present invention when executed.

[0019] In another aspect of the present invention, a computer program product is provided, comprising: a computer program that, when executed by a processor, performs the explanation rule training method of any embodiment of the present invention.

[0020] This invention acquires historical traffic data and traffic signs corresponding to trainees; determines the importance and relevance indicators of traffic signs based on the historical traffic data; acquires the sign interpretation rules corresponding to each traffic sign; and determines the target rule interpretation order for each sign interpretation rule based on the importance and relevance indicators of each traffic sign. This invention, by acquiring the traffic signs encountered by each trainee, makes the training method more aligned with the trainee's driving characteristics, improving the relevance of the training method; by using importance and relevance indicators, the impact of different traffic signs on safe driving can be clearly defined, improving the accuracy of determining the rule interpretation order; by using importance and relevance indicators as constraints to determine the optimal rule interpretation order, the reliability of the training method can be improved; this invention can also explain the sign interpretation rules of each traffic sign to trainees based on the target rule interpretation order, avoiding confusion in the interpretation order when multiple signs are superimposed, and allowing trainees to prioritize mastering the key sign rules, thus improving the training experience for trainees.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of a rule-explanation training method provided according to Embodiment 1 of the present invention;

[0024] Figure 2 This is a flowchart of another explanation rule training method provided according to Embodiment 2 of the present invention;

[0025] Figure 3 This is a flowchart of another explanation rule training method provided according to Embodiment 3 of the present invention;

[0026] Figure 4 This is a flowchart of another explanation rule training method provided according to Embodiment 4 of the present invention;

[0027] Figure 5 This is a schematic diagram of the structure of an explanation rule training device provided in Embodiment 5 of the present invention;

[0028] Figure 6 A block diagram of an electronic device for implementing an explanation rule training method according to Embodiment Six of the present invention. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, apparatus, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0031] Example 1

[0032] Figure 1 This invention provides a flowchart of a method for training interpretation rules. This invention is applicable to scenarios involving the interpretation of rules for multiple traffic signs. The method can be executed by an interpretation rule training device, which can be implemented in hardware and / or software. This device can be configured in electronic devices such as a semiconductor testing server or a distributed computing cluster composed of multiple servers. Figure 1 As shown, the method includes:

[0033] S110. Obtain historical traffic data and traffic signs corresponding to the personnel to be trained.

[0034] Historical traffic data can be understood as behavioral data generated by trainees during their past driving experiences. Furthermore, historical traffic data may also include the attribute information of various traffic signs. For example, historical traffic data may include: the total number of traffic signs encountered by the trainee during their past driving experiences, the number of violations or accidents incurred while encountering traffic signs, and attribute information such as the color, size, and shape of the traffic signs. Historical traffic data serves as foundational data for determining traffic sign importance and similarity indicators in subsequent steps.

[0035] Traffic signs can be understood as visual symbols used to regulate, warn, and / or instruct drivers' traffic behavior. Examples of traffic signs include speed limit signs, no left turn signs, and / or no U-turn signs. Traffic signs use graphics, symbols, and text to convey specific traffic information to drivers, thus regulating their traffic behavior.

[0036] Furthermore, in this embodiment of the invention, historical traffic data can be obtained from traffic survey and statistics databases, traffic accident statistics databases, or records from relevant traffic enforcement departments. When extracting historical traffic data, a time period can be preset, and only historical traffic data within that preset time period can be obtained. For example, the preset time period can be the most recent 10 days or the most recent 72 hours. The specific data collection time period can be set according to the actual situation, and will not be analyzed or limited in detail here.

[0037] Specifically, historical traffic data of trainees within a preset time period can be obtained from traffic survey and statistics databases, traffic accident statistics databases, or records of relevant traffic law enforcement departments. Traffic signs encountered by drivers during the preset time period can be extracted from the historical traffic data.

[0038] S120. Determine the importance and relevance indicators of traffic signs based on historical traffic data.

[0039] The importance index can be understood as a quantitative value that measures the importance of traffic signs to traffic safety. It can be used to clarify the priority of traffic signs and determine which traffic signs should be explained in the order of rule interpretation. A higher importance index indicates that the traffic sign is more important in the traffic scenario and has a significant impact on determining the order of rule interpretation; a lower importance index indicates that the traffic sign is less important in the traffic scenario and has a less significant impact on determining the order of rule interpretation.

[0040] The relevance index can be understood as a quantitative value that measures the degree of correlation between two or more traffic signs. It is used to determine whether traffic signs need to be explained in a coordinated manner and to avoid the repeated explanation of the same traffic signs. Understandably, a higher relevance index indicates that the two traffic signs are more similar. When determining the order of explanation for the target rule, this index should be considered to determine whether coordinated explanation is needed. When the relevance index is 1, it means that the two signs are exactly the same, and either sign can be removed to avoid the repeated explanation of similar signs.

[0041] Specifically, historical traffic data can include behavioral data generated by trainees during their past driving and sign attribute information of various traffic signs they pass. Based on the behavioral data generated during past driving, importance indicators for measuring the importance of traffic signs to traffic safety can be determined, and correlation indicators for measuring the similarity between different traffic signs can be determined based on the sign attribute information of various traffic signs.

[0042] S130. Obtain the sign interpretation rules corresponding to each traffic sign, and determine the target rule interpretation order of each sign interpretation rule based on the importance index and relevance index of each traffic sign.

[0043] The sign interpretation rules can be understood as a set of standards that clearly define the meaning, applicable scenarios, and / or enforcement requirements of traffic signs. When training trainees on traffic signs, simply showing them the signs directly may not be sufficient for them to understand their meaning. In such cases, the corresponding sign interpretation rules can be used to explain the meaning of the traffic signs, thus achieving the training objective. It is understood that each traffic sign corresponds to a unique sign interpretation rule.

[0044] The target rule explanation order can be understood as the rule explanation order that best meets training needs among all rule explanation orders. The target rule explanation order is the optimal order determined after a series of calculations and comparisons. The target rule explanation order directly serves the safety education and training of the trainees.

[0045] Specifically, the system retrieves the sign interpretation rules for each traffic sign from the preset rule base based on the preset sign codes. For traffic signs without preset rules, it can also generate corresponding sign interpretation rules by providing textual descriptions of their functions, applicable scenarios, and execution requirements. Importance and relevance indicators can be used as constraints. The optimal rule interpretation scheme, i.e., the target rule interpretation order, can be selected from multiple sets of rule interpretation orders through multi-objective optimization algorithms or Bayesian inference. The sign interpretation rules for each traffic sign can be explained to the trainees according to the order of the sign interpretation rules in the target rule interpretation order through application graphics or extended reality technology.

[0046] This invention provides an embodiment that acquires historical traffic data and traffic signs corresponding to trainees; determines the importance and relevance indicators of traffic signs based on the historical traffic data; acquires the sign interpretation rules corresponding to each traffic sign; and determines the target rule interpretation order for each sign interpretation rule based on the importance and relevance indicators. This invention, by acquiring the traffic signs encountered by each trainee, makes the training method more aligned with their driving characteristics, improving its relevance. The importance and relevance indicators clarify the impact of different traffic signs on safe driving, improving the accuracy of determining the rule interpretation order. By using the importance and relevance indicators as constraints, the optimal rule interpretation order is selected, improving the reliability of the training method. Furthermore, this invention can explain the sign interpretation rules of each traffic sign to trainees based on the target rule interpretation order, avoiding confusion in the interpretation order when multiple signs are superimposed, and allowing trainees to prioritize mastering key sign rules, thus enhancing the training experience.

[0047] Example 2

[0048] Figure 2 This invention provides another flowchart for a rule training method in embodiment two. This embodiment is a refinement of the above embodiment, specifically refining the steps for determining the importance indicators and relevance indicators, as well as the steps for determining the order of explaining the target rules.

[0049] like Figure 2 As shown, another method for training interpretation rules may include the following specific steps:

[0050] S210. Obtain historical traffic data and traffic signs corresponding to the personnel to be trained.

[0051] S220. Determine the scene statistics of each traffic sign based on historical traffic data, and determine the importance index of each traffic sign based on the scene statistics of each traffic sign.

[0052] Scenario statistics can be understood as statistical data on the occurrence of traffic signs in different traffic scenarios, used to quantify the impact of a specific traffic sign on the driving experience of trainees. For example, traffic scenarios may include: regular driving, illegal driving, and accident driving, and the corresponding scenario statistics may include: the total number of traffic signs encountered by the trainee during regular driving, the number of violations or accidents occurring when encountering a particular traffic sign, etc.

[0053] Specifically, information such as the total number of traffic signs encountered by the trainee during regular driving, and the number of violations or accidents occurring when encountering a particular traffic sign, can be extracted from historical traffic data. The total number of traffic signs encountered and the number of violations or accidents occurring when encountering a particular traffic sign can be used as scenario statistics for traffic signs. The weighted cumulative value of the total number of traffic signs encountered, the number of violations, and / or the number of accidents can be used as an importance indicator for traffic signs. Furthermore, in this embodiment of the invention, the weighted cumulative value can be normalized.

[0054] S230. Extract the sign attribute information of each traffic sign from historical traffic data, and determine the relevance index of the traffic signs based on the sign attribute information of each traffic sign.

[0055] Traffic sign attribute information can be understood as a set of information describing the characteristics of a traffic sign itself, such as sign shape, sign color, sign content, sign size, and sign location. By analyzing sign attribute information, we can understand the correlation between traffic signs and use it to calculate correlation indices between different signs.

[0056] Specifically, the sign attribute information, such as sign shape, sign color, sign content, sign size, and sign location, can be extracted from historical traffic data for the traffic signs corresponding to the trainees. The sign attribute information of the traffic signs can be converted into vectors, and the correlation between each traffic sign can be determined by calculating the Euclidean distance between the vectors. For example, the reciprocal of the Euclidean distance can be used as the correlation between each traffic sign.

[0057] S240. Obtain at least one set of rule interpretation order for each identifier interpretation rule.

[0058] The rule explanation order can be understood as the sequence in which multiple sign explanation rules are arranged and combined. A rule explanation order contains a set of sign explanation rules in a specific order. Different rule explanation orders result in different order of the sign explanation rules corresponding to traffic signs.

[0059] Specifically, once all the rules for interpreting traffic signs are determined, the rules can be sorted according to a preset logic to form at least one set of sign interpretation sequences.

[0060] S250. Count the total number of rules for explaining signs included in each rule explanation sequence; wherein the total number of rules is equal to the total number of traffic signs included in the corresponding rule explanation sequence.

[0061] The total number of rules can be understood as the total number of sign interpretation rules included in a specific rule interpretation order. The total number of rules is equal to the total number of traffic signs included in that rule interpretation order, and is used for subsequent marginal probability calculations.

[0062] Specifically, obtain the total number of traffic signs included in the rule explanation sequence, and use this total number of traffic signs as the total number of rules for the sign explanation rules included in each rule explanation sequence.

[0063] S260. In the order of rule explanation, count the first and second number of sign explanation rules; wherein, the first number is the number of sign explanation rules corresponding to the traffic sign's importance index being a specific importance index; and the second number is the number of sign explanation rules corresponding to the traffic sign's relevance index being a specific relevance index.

[0064] The first quantity can be understood as the number of rule interpretation rules whose importance index reaches a specific standard in a certain rule interpretation order, and is used to calculate the first marginal probability.

[0065] The second quantity can be understood as the number of rule interpretation rules that reach a specific standard in a certain rule interpretation order, and is used to calculate the second marginal probability.

[0066] Specifically, for each rule explanation sequence, the importance index of each traffic sign in the rule explanation sequence is obtained. The number of sign explanation rules when the importance index is a specific importance index is counted in each rule explanation sequence, and this number is taken as the first number. The number of sign explanation rules when the relevance index is a specific relevance index is counted in each rule explanation sequence, and this number is taken as the second number.

[0067] For example, a specific importance index can be set to 0.2. When the total number of traffic signs included in the rule explanation sequence is 5, the importance index of each traffic sign in the rule explanation sequence can be 0.2, 0.2, 0.3, 0.1, and 0.5 respectively. In this case, the first quantity is the number of traffic signs with an importance index of 0.2, which is 2. It should be noted that this example is for illustrative purposes only. The setting of the specific importance index can be obtained based on factors such as preset training objectives, analysis of users' historical learning behavior, or quantitative assessment of risks in complex traffic scenarios. The total number of traffic signs in the rule explanation sequence can also be obtained based on factors such as the design of the training method, the assessment of the knowledge level of the trainees, and the evaluation of learning progress.

[0068] S270. Obtain the preset prior probability of each rule explanation order, and use the product of the first marginal probability, the second marginal probability and the preset prior probability as the conditional probability of each rule explanation order; wherein, the first marginal probability is the first ratio of the first quantity to the total number of traffic signs; the second marginal probability is the second ratio of the second quantity to the total number of traffic signs.

[0069] Among them, the preset prior probability can be understood as the initial probability of the rule explanation order pre-set based on historical data, historical experience or industry standards. The preset prior probability is the probability of the rule explanation order appearing before considering the specific characteristics of the rule explanation order. The preset prior probability corresponds one-to-one with the rule explanation order.

[0070] The first marginal probability is the ratio of the first quantity to the total number of rules. It can be understood as the probability that an important indicator is a specific important indicator in a certain rule explanation order, reflecting the proportion of important indicators that are specific important indicators in that rule explanation order.

[0071] The second marginal probability is the ratio of the second quantity to the total number of rules. It can be understood as the probability that a certain relevance indicator is a specific relevance indicator in a certain rule explanation order, reflecting the proportion of relevance indicators that are specific relevance indicators in that rule explanation order. The first marginal probability and the first marginal probability can be used as intermediate data for calculating conditional probability and posterior probability.

[0072] Conditional probability can be understood as the probability that, given a preset prior probability, a certain rule interpretation order simultaneously satisfies the first marginal probability and the second marginal probability. It reflects the probability of a certain rule interpretation order occurring under the constraints of importance indicators, relevance indicators, and prior probabilities.

[0073] Specifically, based on historical data, historical experience, or industry standards, the preset prior probabilities of the rule explanation order can be multiplied by the first marginal probability, the second marginal probability, and the preset prior probabilities to obtain the product value of the multiplication operation. This product value can be used as the conditional probability of each rule explanation order.

[0074] S280. Determine the target rule interpretation order in each rule interpretation order based on the first marginal probability, the second marginal probability, the conditional probability, and the prior probability.

[0075] Specifically, Bayesian inference can be performed based on the first marginal probability, the second marginal probability, the conditional probability, and the prior probability to obtain the posterior probability of the rule interpretation order. The rule interpretation order with the highest posterior probability can be used as the target rule interpretation order.

[0076] In this embodiment of the invention, historical traffic data and traffic signs corresponding to the trainees are obtained. Scenario statistics for each traffic sign are determined based on the historical traffic data, and importance indicators for each traffic sign are determined based on the scenario statistics. Sign attribute information for each traffic sign is extracted from the historical traffic data, and relevance indicators for each traffic sign are determined based on the sign attribute information. At least one set of rule explanation sequences for each sign interpretation rule is obtained, and the total number of rule explanation rules included in each rule explanation sequence is counted. The total number of rules is equal to the total number of traffic signs included in the corresponding rule explanation sequence. Within each rule explanation sequence, the first and second number of sign explanation rules are counted. The quantity; where the first quantity is the number of sign interpretation rules corresponding to the importance index of a traffic sign being a specific importance index; the second quantity is the number of sign interpretation rules corresponding to the relevance index of a traffic sign being a specific relevance index; the preset prior probability of each rule interpretation order is obtained; the product of the first marginal probability, the second marginal probability, and the preset prior probability is used as the conditional probability of each rule interpretation order; where the first marginal probability is the first ratio of the first quantity to the total number of traffic signs; the second marginal probability is the second ratio of the second quantity to the total number of traffic signs; the target rule interpretation order in each rule interpretation order is determined based on the first marginal probability, the second marginal probability, the conditional probability, and the prior probability. This invention, through its embodiments, determines scenario statistics based on historical traffic data and generates importance indicators. It quantifies the safety impact of traffic signs on trainees through statistical information such as the frequency of sign occurrences, violations, and / or accidents. By extracting sign attribute information to generate correlation indicators, the training method can determine the relevance based on attributes such as sign shape and color, allowing related traffic signs to be explained in conjunction with each other, thus improving the coherence and logic of traffic sign explanations. By acquiring sign explanation rules and determining at least one set of rule explanation orders, the explanation content can be clearly defined, and multiple sorting options can be provided, breaking the limitations of a single explanation order and improving the flexibility of rule explanation order in adapting to different training scenarios and learners' cognitive habits. By determining the target rule explanation order through posterior probability, the optimal explanation order can be selected, prioritizing high-importance and highly correlated signs, ensuring training effectiveness and improving user experience.

[0077] Optionally, in this embodiment of the invention, step S280 is further refined, specifically detailing the steps for determining the order of interpreting the target rule based on the first marginal probability, the second marginal probability, the conditional probability, and the prior probability.

[0078] S281. Multiply each first marginal probability by each second marginal probability to obtain the joint probability of the corresponding rule interpretation order.

[0079] The joint probability is the product of the first marginal probability and the second marginal probability. It is the intermediate data for calculating the posterior probability and is used to quantify the synergistic proportion of the explanatory rules of specific importance indicators and correlation indicators in the rule explanation order. It reflects the probability of a certain rule explanation order appearing under the simultaneous influence of specific importance indicators and specific correlation indicators.

[0080] Specifically, for each rule explanation order, the first marginal probability corresponding to each rule explanation order is multiplied by the second marginal probability to obtain the product value of the first marginal probability and the second marginal probability corresponding to each rule explanation order. This product value is used as the joint probability of each rule explanation order.

[0081] S282. Obtain the product of the conditional probability and the prior probability, and use the ratio of the product to the joint probability as the posterior probability of the order of rule interpretation.

[0082] The posterior probability is the ratio of the product of the conditional probability and the prior probability to the joint probability, and it is used to measure the priority of the order in which rules are interpreted. For example, the higher the posterior probability, the greater the probability that the order in which the rules are interpreted will be the target order. Therefore, the order in which the rules are interpreted with the highest posterior probability can be used as the target order.

[0083] Specifically, for each rule explanation order, the conditional probability corresponding to each rule explanation order is multiplied by the prior probability to obtain the product of the conditional probability and the prior probability corresponding to each rule explanation order. This product is then compared with the joint probability to obtain the ratio of the product to the joint probability. This ratio is then used as the posterior probability of each rule explanation order.

[0084] S283. Among the order of rule interpretation, the order of rule interpretation with the highest posterior probability shall be taken as the order of target rule interpretation.

[0085] Specifically, the posterior probabilities of each rule explanation order are compared, and the rule explanation order with the highest posterior probability is taken as the target rule explanation order.

[0086] Example 3

[0087] Figure 3 This invention provides another flowchart for a rule training method in embodiment three. This embodiment is a refinement of the above embodiment, specifically refining the steps for determining the importance indicators and relevance indicators, as well as the steps for determining the order of explaining the target rules.

[0088] S310. Obtain historical traffic data and traffic signs corresponding to the personnel to be trained.

[0089] S320. Extract the total number of traffic signs, the number of violations, and the number of accidents corresponding to the traffic signs from the scene statistics information.

[0090] Specifically, for each traffic sign, the preset sign code can be used to retrieve the scene statistics information to extract the total number of traffic signs, the number of violations, and the number of accidents corresponding to each traffic sign.

[0091] S330. The sum of the total number of traffic signs, the number of violations, and the number of accidents, after normalization, shall be used as the importance indicator of traffic signs.

[0092] Specifically, the total number of traffic signs, the number of violations, and the number of accidents are summed or weighted to obtain the sum of the total number of traffic signs, the number of violations, and the number of accidents. This sum is then normalized, and the normalized result is used as the importance indicator of the traffic signs.

[0093] S340. Perform vector transformation processing on each traffic sign according to the sign attribute information to obtain the sign transformation vector of each traffic sign; wherein, the number of vector elements in the sign transformation vector is equal to the number of information dimensions of the sign attribute information.

[0094] The sign transformation vector can be understood as a numerical vector obtained by transforming the sign attribute information of traffic signs through mathematical methods, such as encoding or feature extraction. The number of elements in the sign transformation vector is consistent with the number of information dimensions of the sign attribute information, and each element of the sign transformation vector corresponds to a sign attribute. The sign transformation vector transforms non-numerical sign attribute information into a numerical form that facilitates the calculation of relevance.

[0095] The marker transformation vector can transform abstract attribute features into a computable mathematical form, and can calculate Euclidean distance to determine correlation indicators.

[0096] Specifically, the sign attributes of each traffic sign are converted into vectors, and the vectors converted from the sign attribute information of each traffic sign are concatenated to obtain the sign conversion vector.

[0097] S350. Take any one of the flag transformation vectors as the reference flag transformation vector.

[0098] The benchmark indicator transformation vector can be understood as a vector randomly selected from all indicator transformation vectors and used as a reference standard for correlation calculation. The benchmark indicator transformation vector can provide a unified comparison benchmark, making the correlation calculation of other indicator transformation vectors consistent and comparable.

[0099] Specifically, among the sign conversion vectors corresponding to each traffic sign, one can be randomly selected as a reference standard for calculating the correlation, and the vector used as the reference standard can be determined as the baseline sign conversion vector.

[0100] S360. The reciprocal of the Euclidean distance between each sign transformation vector and the baseline sign transformation vector, after normalization, is used as the correlation index of the traffic sign corresponding to each sign transformation vector.

[0101] Specifically, the Euclidean distance between each sign transformation vector and the baseline sign transformation vector is calculated, and the reciprocal of the Euclidean distance is used as the relevance index of the traffic sign corresponding to each sign transformation vector. For example, in this embodiment of the invention, the reciprocal of the Euclidean distance can also be normalized, and the result of the normalization process can be used as the relevance index of the traffic sign corresponding to each sign transformation vector.

[0102] S370. Obtain the sign interpretation rules corresponding to each traffic sign, and determine the target rule interpretation order of each sign interpretation rule based on the importance index and relevance index of each traffic sign.

[0103] This invention, in its embodiments, acquires historical traffic data and traffic signs corresponding to trainees. It extracts the total number of traffic signs, the number of violations, and the number of accidents corresponding to each traffic sign from the scene statistics. The sum of these three values, after normalization, is used as the importance index of the traffic sign. Each traffic sign is then vectorized according to its attribute information to obtain its transformation vector. Any one of these transformation vectors is used as the baseline transformation vector. The reciprocal of the Euclidean distance between each transformation vector and the baseline transformation vector, after normalization, is used as the relevance index of the traffic sign corresponding to each transformation vector. The interpretation rules for each traffic sign are then obtained, and the target rule interpretation order is determined based on the importance and relevance indices. This invention, by normalizing the extracted total number of traffic signs, the number of violations, and the number of accidents to obtain the importance index, can accurately quantify the impact of traffic signs on traffic safety. Furthermore, by vectorizing each traffic sign, abstract attribute information such as shape, color, and pattern can be transformed into quantifiable numerical vectors, improving the accuracy and efficiency of data processing when calculating the relevance index.

[0104] Example 4

[0105] Figure 4 This is a flowchart illustrating another method for training traffic sign interpretation rules, provided in Embodiment 4 of the present invention. This embodiment of the present invention is an optimization of the above embodiment; specifically, it adds another step for determining the similarity between traffic signs. For example... Figure 4 As shown, another method for training interpretation rules includes the following process:

[0106] Step 1: Determine the historical traffic data to be used for analyzing the order of the rules. Preprocessing steps can be performed on the historical traffic data.

[0107] Step 2: Calculate the importance index and relevance index of traffic signs using the preprocessed data.

[0108] Step 3: Convert the obtained importance and relevance indicators into data and input them into the Bayesian formula.

[0109] Step 4: Determine the relevance of the input data. If it is irrelevant, analyze the importance of the markers; if it is relevant, conduct a comprehensive analysis of both marker importance and marker relevance.

[0110] Step 5: Output the order of the explanation rules.

[0111] We can define the importance index of traffic signs as I and the correlation index between traffic signs as C.

[0112] The importance index of a traffic sign indicates its degree of importance, assessed based on its safety impact. The safety impact of a traffic sign is primarily influenced by the frequency of its appearance, the number of violations committed by users related to that sign, and the number of traffic accidents that occur associated with it. The importance index reflects the significance of a traffic sign in traffic management. Generally, signs with higher importance indices have higher priority in traffic rules, and their corresponding rules may be given priority in the order of enforcement. If a sign has a high importance index, it means its role in traffic management is more significant, and its rules may be placed earlier or in a more prominent position in the explanation of rules.

[0113] Traffic sign correlation refers to the relationship between two or more signs, primarily related to the sign's type and characteristics. Sign correlation reflects the degree of correlation between traffic signs. If two signs have a high correlation, it indicates they may be related or mutually influential in traffic rules. If two highly correlated signs appear simultaneously in a traffic situation, a more detailed explanation of their relationship may be needed to ensure drivers correctly understand and comply with traffic rules.

[0114] The following are the specific steps for calculating importance indicators and correlation indicators.

[0115] Calculating the importance index of traffic signs involves the following steps:

[0116] S1: Data Collection and Processing. Historical traffic data for a period of time is obtained through surveys, statistics on traffic accidents, or records from relevant traffic enforcement departments, including the number of times traffic signs appear, the number of violations, and the number of accidents.

[0117] S2: Calculate the number of occurrences. For each type of traffic sign, obtain scenario statistics, namely the total number of occurrences of the traffic sign, the total number of violations, and the total number of accidents.

[0118] S3: Define and calculate the importance index. Let η be the importance index, and let a be the number of times a traffic sign appears, b be the number of times a traffic sign is violated, and c be the number of times a traffic sign is involved in an accident.

[0119] S4: Calculate the importance index. This is achieved by weighting and summing the frequency of traffic sign occurrences, violations, accidents, and the total number of occurrences. The specific formula is as follows: In the formula The weighting coefficients and Weighting coefficient The specific value is set by those skilled in the art based on the specific circumstances, and is not limited here. η represents the safety impact coefficient importance index of the mark. The larger η is, the greater the importance index of the mark, and the more important the mark is; the smaller η is, the smaller the importance index of the mark, and the less important the mark is. By comparing the safety impact coefficients of two different marks, the importance of these two marks is determined, further resolving the order of priority interpretation rules.

[0120] It's important to note that the collected data is a summary of data within the specific time period set. For example, setting the data collection period to the last 10 days means collecting the number of traffic sign occurrences, violations, and accidents over the last 10 days. The specific data collection period should be set according to the actual situation, and will not be analyzed in detail here.

[0121] Extended Reality (XR) systems use high-resolution cameras and sensors to capture images of traffic signs and their surrounding environment. This data includes high-resolution images of the signs, 3D environmental data of the surrounding environment, and the sign's geolocation information (GPS data). The processed traffic sign data is then overlaid onto the user's real-world view using XR devices such as AR glasses or VR headsets, providing an enhanced display of traffic information.

[0122] Calculating the correlation index between traffic signs involves the following steps:

[0123] D1: Data Preparation. Collect data on different traffic signs, including their characteristics. This data can include the sign's shape, color, pattern, etc.

[0124] D2: Select the features used to describe the traffic signs. Assume that m sign attribute information is selected to describe each traffic sign.

[0125] For example: Color: Red border, white background, black numbers; Shape: Circle; Pattern: A capital number, such as "car icon"; Text: No additional text; Size: 60cm in diameter; Material: Reflective metallic material; As an example, the sign attribute information may also include: text describing the traffic sign, or traffic rules for the traffic sign.

[0126] D3: Data Representation. Each traffic sign is represented as an m-dimensional vector, where each dimension corresponds to a feature. Assume there are n traffic signs, represented as a matrix X of size n×m.

[0127] D4: k-means clustering algorithm. This algorithm uses k-means clustering to divide traffic signs into k groups, represented by a matrix Y of size n×1. Each element represents the group to which the corresponding traffic sign belongs.

[0128] D5: Calculate the similarity metric. The reciprocal of the Euclidean distance is used as the similarity metric, represented as a matrix Z of size n×n, where... This represents the Euclidean distance between traffic sign i and traffic sign j. The formula is: In the formula, p is the vector of one identification attribute information of the traffic sign after conversion and q is the vector of another identification attribute information of the traffic sign after conversion. The Euclidean distance between traffic sign i and traffic sign j is obtained by summing the squared differences of each dimension and taking the square root.

[0129] D6: Calculate the K-means cluster centers. Cluster centers represent the center point of each cluster in a clustering algorithm; they represent the average value of all data points in the cluster. The specific formula is: In the formula, Let represent the cluster center of the k-th group, which is the average of the eigenvectors of all traffic signs in that group. This represents the number of traffic signs in the k-th group. Let represent the sign transformation vector of the i-th traffic sign.

[0130] D7: Calculate the relevance score. The relevance score represents the degree of relevance between traffic signs. The similarity matrix Z is used to calculate the relevance score between traffic signs. Define the relevance score matrix R as k×k. The specific formula is as follows: In the formula, It is the group center and Similarity metrics between traffic signs. Relevance scores can help us discover patterns and regularities in the correlation between traffic signs, thus providing a better understanding of the relationships between them.

[0131] The relevance score between traffic signs depends directly on the similarity between the centers of their respective groups. The higher the similarity between two group centers, the higher the relevance score; conversely, the lower the similarity, the lower the relevance score.

[0132] To further explain the above matrix, suppose there are n traffic signs and m features. Then matrix X can be represented as: ;in, This represents the vector after converting the m-th identifier attribute information of the n-th traffic sign.

[0133] The Euclidean distance matrix Z can be represented as: ;in, Let μ represent the Euclidean distance between traffic signs i and j. For example, in this invention, assuming k cluster centers and m features, the cluster center matrix μ can be expressed as: ;in, This represents the m-th value of the k-th cluster center.

[0134] The correlation score matrix can be represented as: ;in, The correlation score represents the correlation between the kth cluster center and the kth cluster center. This correlation score is the correlation index.

[0135] When traffic signs show no correlation, the specific analysis of sign importance is as follows:

[0136] Traffic signs are assessed and graded based on a safety impact coefficient, which ranges from 0 to 1, with 1 indicating the most important and 0 indicating the least important. The order of interpretation rules is determined by the importance of the traffic signs, with the most important signs explained first and the least important signs explained last. For example, if the importance of Y1, Y2, and Y3 is 0.3, 0.8, and 0.5 respectively, then the order of importance is Y2 > Y3 > Y1. Therefore, the order of interpretation rules is: first Y2, then Y3, and finally Y1.

[0137] When traffic signs show a correlation, the comprehensive analysis process is as follows:

[0138] T1: Input Data. Input a set of importance indicators and relevance data for each traffic sign. Each sign can be described as a dataset (Ii, Ci), with each sample corresponding to one traffic sign. This data can be represented using a two-dimensional array: , where Ii represents the importance index of the i-th indicator and Ci represents the relevance of the i-th indicator.

[0139] T2: Building a Bayesian Network. Construct a Bayesian network where nodes include indicators of label importance, label relevance, and the order of interpretation rules. The structure of the Bayesian network can be determined based on the specific circumstances of the problem and the assumptions made.

[0140] T3: Setting the preset prior probabilities. This sets a preset prior probability for the interpretation rule sequence of each node, representing the prior probability of each node. This can be set based on the specific analysis of the data; no limitation is made here.

[0141] T4: Setting up the conditional probability table. This section sets up a conditional probability table for each node, representing the conditional dependencies between them. Assuming the order of interpretation rules is influenced by the importance and relevance of the markers, the conditional probability table is as follows:

[0142]

[0143] T5: Inference and Update. The posterior probability is updated using Bayesian inference methods based on observed marker importance coefficients and marker relevance information. The expression for Bayes' theorem is: ,in, It explains the posterior probability of rule order O after observing specific I and C. P(O) is the probability of observing specific I and C given the explanatory order O, where P(O) is the prior probability of the explanatory rule order, and P(I,C) is the marginal probability of observing I and C.

[0144] T6: Output order representation. The obtained posterior probabilities This can be represented as a probability distribution to reflect the likelihood of different orderings of interpretation rules. Generally, a normalized posterior probability can be used to represent this probability distribution to ensure that the sum of all probabilities is 1. The resulting probability distribution contains the probabilities of different orderings of interpretation rules. ;in, This represents the posterior probability of the rule order being Oi. A higher posterior probability indicates the highest probability of the rule order being that flag, and vice versa.

[0145] To further explain, for example, if the calculated posterior probability vector is [0.3, 0.5, 0.2], it means that the posterior probability of the rule order O1 is 0.3, the posterior probability of O2 is 0.5, and the posterior probability of O3 is 0.2. Then, based on the importance coefficient I and the correlation C, the order of the rule order is O2, followed by O1, and finally O3.

[0146] It is important to note that during the comprehensive analysis, the selection of prior probabilities and the setting of conditional probability tables must ensure that they express the true relationship between historical data and variables, and be as objective and reasonable as possible.

[0147] This embodiment of a safety education and training system based on XR technology solves the problem of the order of explaining rules when traffic signs overlap by considering their importance and relevance. The system determines the priority of signs based on their importance and relevance, and explains the signs with high importance and strong relevance first, so as to ensure that users can understand the most critical traffic rules first.

[0148] Example 5

[0149] Figure 5 This is a schematic diagram of the structure of an explanation rule training device provided for Embodiment 5 of the present invention. (See diagram below.) Figure 5 As shown, the explanation rule training device includes: a data acquisition module 410, an indicator acquisition module 420, and a sequence determination module 430;

[0150] Data acquisition module 410 is used to acquire historical traffic data and traffic signs corresponding to the trainees;

[0151] The indicator acquisition module 420 is used to determine the importance and relevance indicators of traffic signs based on historical traffic data.

[0152] The sequence determination module 430 obtains the sign interpretation rules corresponding to each traffic sign, and determines the target rule interpretation order of each sign interpretation rule based on the importance index and relevance index of each traffic sign.

[0153] Optionally, the indicator acquisition module 420 includes: a first indicator determination unit, used to determine the scene statistics of each traffic sign based on historical traffic data, and to determine the importance indicator of each traffic sign based on the scene statistics of each traffic sign; and a second indicator determination unit, used to extract the sign attribute information of each traffic sign from historical traffic data, and to determine the relevance indicator of each traffic sign based on the sign attribute information of each traffic sign.

[0154] Optionally, the first indicator determination unit is specifically used to extract the total number of traffic signs, the number of violations, and the number of accidents corresponding to traffic signs from the scene statistics information; and the sum of the total number of traffic signs, the number of violations, and the number of accidents, after normalization, is used as the importance indicator of traffic signs.

[0155] Optionally, the second indicator determination unit is specifically used to perform vector transformation processing on each traffic sign according to the sign attribute information to obtain the sign transformation vector of each traffic sign; wherein, the number of vector elements in the sign transformation vector is equal to the number of information dimensions of the sign attribute information; any one of the sign transformation vectors is used as the reference sign transformation vector; and the reciprocal of the Euclidean distance between each sign transformation vector and the reference sign transformation vector, after normalization, is used as the relevance index of the traffic sign corresponding to each sign transformation vector.

[0156] Optionally, the sequence determination module 430 includes: a sequence acquisition module, used to acquire at least one set of rule interpretation sequences for each sign interpretation rule; a total quantity acquisition unit, used to count the total number of sign interpretation rules included in each rule interpretation sequence; wherein the total number of rules is equal to the total number of traffic signs included in the corresponding rule interpretation sequence; and a first quantity acquisition unit, used to count the first quantity and the second quantity of sign interpretation rules in each rule interpretation sequence; wherein the first quantity is the number of sign interpretation rules corresponding to when the importance index of a traffic sign is a specific importance index; and the second quantity is the number of traffic signs... The correlation index is the number of sign interpretation rules corresponding to a specific correlation index; the first probability determination unit is used to obtain the preset prior probability of each rule interpretation order, and use the product of the first marginal probability, the second marginal probability and the preset prior probability as the conditional probability of each rule interpretation order; wherein, the first marginal probability is the first ratio of the first quantity to the total number of traffic signs; the second marginal probability is the second ratio of the second quantity to the total number of traffic signs; the order determination unit is used to determine the target rule interpretation order in each rule interpretation order based on the first marginal probability, the second marginal probability, the conditional probability and the prior probability.

[0157] Optionally, the order determination unit is specifically used to multiply each first marginal probability and each second marginal probability to obtain the joint probability of each rule interpretation order; obtain the product value of the conditional probability and the prior probability, and use the ratio of the product value to the joint probability as the posterior probability of each rule interpretation order; and in each rule interpretation order, use the rule interpretation order with the highest posterior probability as the target rule interpretation order.

[0158] The explanation rule training device provided in the embodiments of the present invention can execute the explanation rule training method provided in the embodiments of the present invention, and has the corresponding beneficial effects of the execution method.

[0159] Example 6

[0160] Embodiment 6 of the present invention provides an electronic device for performing an explanation rule training method, a computer-readable medium, and a computer program product.

[0161] Figure 6A schematic diagram of an electronic device is shown that can be used to implement the rule-explaining training method of any embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown in the embodiments of the present invention, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the embodiments of the present invention described and / or claimed herein.

[0162] like Figure 6 As shown, the electronic device includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from the storage unit 18. The RAM 13 can also store various programs and data required for device operation. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0163] Multiple components in the electronic device are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, optical disk, etc.; and a communication unit 19, such as a network card, modem, wireless transceiver, etc. The communication unit 19 allows the electronic device to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0164] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing units, graphics processing units, various special-purpose artificial intelligence computing chips, various processors running machine learning model algorithms, digital signal processors, and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as rule interpretation training methods.

[0165] In some embodiments, the rule-of-fact training method may be implemented as a computer program tangibly contained in a computer-readable medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on an electronic device via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the rule-of-fact training method may be performed. Alternatively, in other embodiments, processor 11 may be configured as the rule-of-fact training method by any other suitable means (e.g., by means of firmware).

[0166] Various embodiments of the systems and technologies described above in these embodiments of the present invention can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays, application-specific integrated circuits (ASICs), application-specific standard products (ASICs), systems-on-a-chip (SoCs), payload programmable logic devices, computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input system, and at least one output system, and transmitting data and instructions to the storage system, the at least one input system, and the at least one output system.

[0167] Computer programs for implementing the methods of embodiments of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing system, such that when executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0168] In the context of embodiments of the present invention, a computer-readable medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, system, or device. A computer-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable medium may be a machine-readable signal medium. More specific examples of machine-readable media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, erasable programmable read-only memory (EPROM or flash memory), optical fibers, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0169] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display system (e.g., a cathode ray tube or liquid crystal display monitor) for displaying information to the user; and a keyboard and pointing system (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of systems can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including: sound input, voice input, or tactile input).

[0170] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0171] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product within the cloud computing service system. This addresses the shortcomings of traditional physical hosts and virtual private servers, such as high management difficulty and weak business scalability.

[0172] It should be understood that the various forms of procedures shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and no limitation is imposed herein.

[0173] The specific embodiments described above do not constitute a limitation on the scope of protection of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for training students on interpretation rules, characterized in that, Applied to extended reality systems, the method includes: Obtain historical traffic data and traffic signs corresponding to the personnel to be trained; The importance and relevance indicators of the traffic signs are determined based on the historical traffic data. Obtain the sign interpretation rules corresponding to each traffic sign, and determine the target rule interpretation order of each sign interpretation rule based on the importance index and the relevance index of each traffic sign.

2. The method according to claim 1, characterized in that, The step of determining the importance and relevance indicators of the traffic signs based on the historical traffic data includes: Based on the historical traffic data, the scene statistics of each traffic sign are determined, and the importance index of each traffic sign is determined based on the scene statistics of each traffic sign. The sign attribute information of each traffic sign is extracted from the historical traffic data, and the relevance index of each traffic sign is determined based on the sign attribute information of each traffic sign.

3. The method according to claim 2, characterized in that, The determination of the importance index of each traffic sign based on the scene statistical information of each traffic sign includes: The total number of traffic signs, the number of violations, and the number of accidents corresponding to the traffic signs are extracted from the statistical information of the scenario. The sum of the total number of traffic signs, the number of violations, and the number of accidents, after being normalized, is used as the importance index of the traffic signs.

4. The method according to claim 2, characterized in that, The determination of the relevance index of the traffic sign based on the sign attribute information of each traffic sign includes: The traffic signs are vectorized according to the sign attribute information to obtain the sign transformation vector of each traffic sign; wherein the number of vector elements in the sign transformation vector is equal to the number of information dimensions of the sign attribute information; Take any one of the aforementioned flag transformation vectors as the base flag transformation vector; The reciprocal of the Euclidean distance between each of the sign transformation vectors and the baseline sign transformation vector, after normalization, is used as the correlation index of the traffic sign corresponding to each of the sign transformation vectors.

5. The method according to claim 1, characterized in that, The determination of the target rule interpretation order for each traffic sign interpretation rule based on the importance index and the relevance index of each traffic sign includes: Obtain at least one set of rule interpretation order for each of the aforementioned flag interpretation rules; The total number of sign explanation rules included in each rule explanation sequence is counted; wherein the total number of rules is equal to the total number of traffic signs included in the corresponding rule explanation sequence; In each of the rule explanation sequences, the first number and the second number of the sign explanation rules are counted; wherein, the first number is the number of sign explanation rules corresponding to when the importance index of the traffic sign is a specific importance index; and the second number is the number of sign explanation rules corresponding to when the relevance index of the traffic sign is a specific relevance index. Obtain the preset prior probability of each rule explanation order, and use the product of the first marginal probability, the second marginal probability and the preset prior probability as the conditional probability of each rule explanation order; wherein, the first marginal probability is the first ratio of the first quantity to the total number of traffic signs; the second marginal probability is the second ratio of the second quantity to the total number of traffic signs; The target rule interpretation order in each rule interpretation order is determined based on the first marginal probability, the second marginal probability, the conditional probability, and the prior probability.

6. The method according to claim 5, characterized in that, The step of determining the target rule interpretation order in each rule interpretation order based on the first marginal probability, the second marginal probability, the conditional probability, and the prior probability includes: Multiply each of the first marginal probabilities and each of the second marginal probabilities to obtain the joint probability corresponding to each of the rule interpretation orders; Obtain the product of the conditional probability and the prior probability, and use the ratio of the product to the joint probability as the posterior probability of each rule interpretation order; Among the various rule interpretation orders, the rule interpretation order with the highest posterior probability is taken as the target rule interpretation order.

7. A training device for explaining rules, characterized in that, The device includes: The data acquisition module is used to acquire historical traffic data and traffic signs corresponding to the trainees; The indicator acquisition module is used to determine the importance and relevance indicators of the traffic signs based on the historical traffic data. The sequence determination module is used to obtain the sign interpretation rules corresponding to each of the traffic signs, and determine the target rule interpretation order of each of the sign interpretation rules based on the importance index and the relevance index of each of the traffic signs.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the explanation rule training method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the explanation rule training method according to any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the explanation rule training method according to any one of claims 1-6.

Images