Method, device and equipment for selecting driving strategy based on human-computer interaction, and medium

Abstract

The application discloses a driving strategy selection method and device based on human-computer interaction, equipment and medium. The method comprises the following steps: generating the outflow of the strategy scheme according to the comprehensive priority of the strategy scheme relative to the reference scheme and the inflow generation model; generating the inflow of the strategy scheme according to the comprehensive priority of the strategy scheme relative to the reference scheme and the preset outflow generation model; determining the net flow corresponding to the strategy scheme according to the outflow and the inflow; and selecting the strategy scheme corresponding to the maximum net flow as the optimal driving strategy. The application collects and learns the decision characteristics and behavior patterns of people in various interactions of intelligent agents represented by intelligent vehicles by constructing a human behavior model, introduces the prospect theory in the traditional algorithm, improves the accuracy of evaluating and selecting driving decisions, helps to provide a driving strategy that is more in line with the decision-making preference of people in the intelligent driving process, and further improves the user experience in the whole human-computer interaction process.

Description

Technical Field

[0001] This application relates to the field of human-computer interaction technology, and in particular to a method, apparatus, device and medium for selecting driving strategies based on human-computer interaction. Background Technology

[0002] In recent years, the fields of artificial intelligence and human-computer interaction have risen rapidly, and digitalization and intelligence have become the core themes of future development in various industries. As cars owned by millions of households become increasingly intelligent, the era of a vehicle being a complete intelligent entity has arrived, and the interaction between the driver and the vehicle will become one of the most common human-computer interaction scenarios in the future.

[0003] However, existing driving strategy selection processes often overlook drivers' individual habits and behavioral patterns. Each driver develops a unique driving style and habits over a long period, and different drivers may make different decisions in similar traffic situations. This individual difference is often not taken into account in traditional decision-making methods. Therefore, existing driving strategy selection processes are not conducive to improving the efficiency of driving strategy selection, nor are they conducive to improving the reliability and accuracy of the selected driving strategy.

[0004] Therefore, there is an urgent need for a driving strategy that adapts to the human-computer interaction intelligent driving mode and meets the decision-maker's preferences, so as to improve the user experience of the entire human-computer interaction process and thus enhance the intelligence and personalization of driving decisions. Summary of the Invention

[0005] This application provides a driving strategy selection method, apparatus, device, and medium based on human-computer interaction to solve the technical problems mentioned above, which are that the existing driving strategy selection process is not conducive to improving the selection efficiency of driving strategies and the reliability and accuracy of the selected driving strategies.

[0006] In a first aspect, embodiments of this application provide a driving strategy selection method applied to an electronic device in a vehicle, the electronic device storing an autonomous driving system, the driving strategy selection method comprising:

[0007] Obtain the strategy scheme of the autonomous driving system, and obtain the attributes of the strategy scheme;

[0008] Based on the subjective weight corresponding to the attribute, the objective weight corresponding to the attribute, and the preset weight model, a comprehensive weight parameter corresponding to the attribute is generated.

[0009] Obtain the priority function, which includes the Gaussian criterion function and the hierarchical priority function;

[0010] Based on the evaluation value of the Gaussian criterion function on the attribute, the preference weight of the Gaussian criterion function is determined. Based on the evaluation value of the hierarchical priority function on the attribute, the preference weight of the hierarchical priority function is determined. Based on the preference weight of the Gaussian criterion function, the preference weight of the hierarchical priority function, and the comprehensive deviation generation model, the comprehensive deviation between the strategy scheme and the reference scheme regarding the attribute is generated.

[0011] Based on the comprehensive deviation, the comprehensive weight parameters, and the preset comprehensive priority value generation model, a comprehensive priority value of the strategy scheme relative to the reference scheme is generated;

[0012] Based on the overall priority value of the strategy scheme relative to the reference scheme and the preset inflow generation model, the outflow of the strategy scheme is generated, and based on the overall priority value of the strategy scheme relative to the reference scheme and the preset outflow generation model, the inflow of the strategy scheme is generated.

[0013] Based on the outflow and inflow, the net flow corresponding to the strategy scheme is determined, the net flow corresponding to multiple strategy schemes is sorted, and the strategy scheme corresponding to the largest net flow is selected as the optimal driving strategy.

[0014] In one possible implementation of the first aspect, before obtaining the strategy scheme of the autonomous driving system and the attributes of the strategy scheme, the driving strategy selection method includes:

[0015] Multiple alternative solutions for the autonomous driving system are obtained. Among the multiple alternative solutions, two alternative solutions are selected. One of the two alternative solutions is selected as the strategy solution, and the other of the two alternative solutions is selected as the reference solution.

[0016] In one possible implementation of the first aspect, obtaining the strategy scheme of the autonomous driving system and obtaining the attributes of the strategy scheme include:

[0017] Acquire the sensor data, vehicle logs, and vehicle monitoring data corresponding to the strategy scheme;

[0018] The sensor data, vehicle logs, and vehicle monitoring data are integrated into evaluation data, and the attribute values ​​of the strategy scheme are obtained from the evaluation data.

[0019] In one possible implementation of the first aspect, a comprehensive weight parameter corresponding to the attribute is generated based on the subjective weight corresponding to the attribute, the objective weight corresponding to the attribute, and a preset weight model, including:

[0020] Acquire language data, and determine the subjective weight corresponding to the attribute value based on the language data and a preset probabilistic language terminology set;

[0021] Based on the subjective weight corresponding to the attribute, the objective weight corresponding to the attribute, and the preset weight model, a comprehensive weight parameter corresponding to the attribute is generated.

[0022] In one possible implementation of the first aspect, after determining the net flow corresponding to the strategy scheme based on the outflow and the inflow, sorting the net flows corresponding to multiple strategy schemes, and selecting the strategy scheme corresponding to the largest net flow as the optimal driving strategy, the driving strategy selection method includes:

[0023] The driving strategy is transmitted to the preset autonomous driving system, and the autonomous driving system is controlled to execute the driving strategy.

[0024] In one possible implementation of the first aspect, after determining the net flow corresponding to the strategy scheme based on the outflow and the inflow, sorting the net flows corresponding to multiple strategy schemes, and selecting the strategy scheme corresponding to the largest net flow as the optimal driving strategy, the driving strategy selection method includes:

[0025] Read the preset upload time and determine whether the current time is the preset upload time;

[0026] If the current time is the upload time, then connect to the preset server and upload the driving strategy to the server.

[0027] In one possible implementation of the first aspect, after determining the net flow corresponding to the strategy scheme based on the outflow and the inflow, sorting the net flows corresponding to multiple strategy schemes, and selecting the strategy scheme corresponding to the largest net flow as the optimal driving strategy, the driving strategy selection method includes:

[0028] Obtain a preset storage area and store the driving strategy in the storage area.

[0029] Secondly, embodiments of this application provide a driving strategy selection device, applied to an electronic device in a vehicle, the electronic device storing an autonomous driving system, including:

[0030] The acquisition module is used to acquire the strategy scheme of the autonomous driving system and acquire the attributes of the strategy scheme;

[0031] The first generation module is used to generate a comprehensive weight parameter corresponding to the attribute based on the subjective weight corresponding to the attribute, the objective weight corresponding to the attribute, and a preset weight model.

[0032] The module is configured to obtain the priority function, which includes the Gaussian criterion function and the hierarchical priority function.

[0033] The second generation module is used to determine the preference weight of the Gaussian criterion function based on the evaluation value of the Gaussian criterion function on the attribute, determine the preference weight of the hierarchical priority function based on the evaluation value of the hierarchical priority function on the attribute, and generate the comprehensive deviation between the strategy scheme and the reference scheme regarding the attribute based on the preference weight of the Gaussian criterion function, the preference weight of the hierarchical priority function, and the comprehensive deviation generation model.

[0034] The third generation module is used to generate a comprehensive priority value of the strategy scheme relative to the reference scheme based on the comprehensive deviation, the comprehensive weight parameters and the preset comprehensive priority value generation model.

[0035] The fourth generation module is used to generate the outflow of the strategy scheme based on the comprehensive priority value of the strategy scheme relative to the reference scheme and the preset inflow generation model, and to generate the inflow of the strategy scheme based on the comprehensive priority value of the strategy scheme relative to the reference scheme and the preset outflow generation model.

[0036] The selection module is used to determine the net flow corresponding to the strategy scheme based on the outflow and inflow, sort the net flow corresponding to multiple strategy schemes, and select the strategy scheme corresponding to the largest net flow as the optimal driving strategy.

[0037] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the driving strategy selection method of the first aspect described above.

[0038] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the driving strategy selection method described in the first aspect above.

[0039] Fifthly, embodiments of this application provide a computer program product that, when run on an electronic device, causes the electronic device to execute the driving strategy selection method described in the first aspect.

[0040] The beneficial effects of this application embodiment are twofold. Firstly, based on the comprehensive priority value of the strategy scheme relative to the reference scheme and a preset inflow generation model, the outflow of the strategy scheme is generated, and based on the comprehensive priority value of the strategy scheme relative to the reference scheme and the preset outflow generation model, the inflow of the strategy scheme is generated. Based on the outflow and inflow, the net flow corresponding to the strategy scheme is determined. The net flows corresponding to multiple strategy schemes are sorted, and the strategy scheme corresponding to the largest net flow is selected as the optimal driving strategy. Since no manual selection is required, a large amount of human and time resources are saved, thus improving the efficiency of driving strategy selection. Secondly, through the comprehensive priority value generation model, the influence of human factors can be eliminated, which helps to improve the reliability and accuracy of the selected driving strategy. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of this application, 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 this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is an application scenario diagram of the driving strategy selection method provided in the embodiments of this application;

[0043] Figure 2 This is a flowchart illustrating the driving strategy selection method provided in an embodiment of this application;

[0044] Figure 3 A flowchart for obtaining evaluation data provided in the embodiments of this application;

[0045] Figure 4 A schematic block diagram of a driving strategy selection device provided in an embodiment of this application;

[0046] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0048] The technical solutions of the various embodiments can be combined with each other, but must be based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0049] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0050] The driving strategy selection method provided in this application can be applied to electronic devices such as mobile phones, tablets, wearable devices, in-vehicle devices, augmented reality (AR) / virtual reality (VR) devices, laptops, ultra-mobile personal computers (UMPCs), netbooks, and personal digital assistants (PDAs). This application does not impose any restrictions on the specific type of electronic device.

[0051] Please see Figure 1 , Figure 1 The application scenario diagram of the driving strategy selection method provided in the embodiments of this application is described in detail below:

[0052] The electronic device obtains the strategy scheme of the autonomous driving system and the attributes of the strategy scheme.

[0053] The multiple alternatives can come from a single file in the autonomous driving system or from multiple files in the autonomous driving system.

[0054] For ease of explanation, we will take the example of multiple alternative solutions coming from two documents, and elaborate as follows:

[0055] The two files consist of a first file and a second file. An electronic device connects to both the first and second files respectively, and retrieves multiple alternative solutions from both files.

[0056] In this embodiment of the application, the electronic device can connect to different files simultaneously, obtain the strategy scheme of the autonomous driving system from the different files, and obtain the attributes of the strategy scheme.

[0057] Please see Figure 2 , Figure 2This is a flowchart illustrating the driving strategy selection method provided in an embodiment of this application. This method can be applied to electronic devices on a vehicle, which store an autonomous driving system.

[0058] like Figure 2 As shown, the driving strategy selection method provided in this application includes the following steps, detailed below:

[0059] S201, Obtain the strategy scheme of the autonomous driving system and obtain the attributes of the strategy scheme;

[0060] The driving strategy selection method, prior to obtaining the strategy scheme of the autonomous driving system and its attributes, includes:

[0061] Multiple alternative solutions for the autonomous driving system are obtained. Among the multiple alternative solutions, two alternative solutions are selected. One of the two alternative solutions is selected as the strategy solution, and the other of the two alternative solutions is selected as the reference solution.

[0062] The step of obtaining the strategy scheme of the autonomous driving system and obtaining the attributes of the strategy scheme includes:

[0063] Acquire the sensor data, vehicle logs, and vehicle monitoring data corresponding to the strategy scheme;

[0064] The sensor data, vehicle logs, and vehicle monitoring data are integrated into evaluation data, and the attributes of the strategy scheme are obtained from the evaluation data.

[0065] The attributes include one or a combination of security data, stability data, congestion rate, and energy consumption.

[0066] For ease of explanation, the following example is provided:

[0067] There are n alternative solutions for autonomous driving systems. It has 4 attributes. The four attributes are safety data, stability data, congestion rate, and energy consumption. The solution is obtained based on sensor data, vehicle logs, and real-time monitoring. About attributes attribute values Attribute values ​​of all schemes This constitutes the decision matrix.

[0068] To scientifically determine the dominance of a solution, the attribute values ​​in the decision matrix need to be processed to obtain a standardized decision matrix. This involves considering attribute safety. and driving stability The standardized formula for this attribute value, which belongs to the benefit-type indicator, is:

[0069] ;

[0070] in, For the plan About attributes In the decision matrix The actual attribute value corresponding to it. This is the first result after standardization.

[0071] Similarly, for attribute congestion rate Fuel consumption The standardized formula for this attribute value, which belongs to the cost-type indicator, is:

[0072] ;

[0073] in, For the plan About attributes In the decision matrix The actual attribute value corresponding to it. The first and second results are then standardized. The standardized decision matrix is ​​obtained by merging the first and second results. ;

[0074] S202, Generate the comprehensive weight parameter corresponding to the attribute based on the subjective weight corresponding to the attribute, the objective weight corresponding to the attribute, and the preset weight model;

[0075] Specifically, based on the subjective weight corresponding to the attribute, the objective weight corresponding to the attribute, and a preset weight model, a comprehensive weight parameter corresponding to the attribute is generated, including:

[0076] Acquire language data, and determine the subjective weight corresponding to the attribute based on the language data and a preset probabilistic language terminology set;

[0077] Based on the subjective weight corresponding to the attribute, the objective weight corresponding to the attribute, and the preset weight model, a comprehensive weight parameter corresponding to the attribute is generated.

[0078] Since different attributes generally play different roles in the decision-making process, to overcome the limitations of traditional methods that rely solely on entropy weighting to obtain weights, we construct a probabilistic linguistic terminology set and build a human behavior model based on it to further collect and learn user decision preferences and behavioral patterns to obtain more reliable subjective weights. We combine these subjective weights with the objective weights obtained by entropy weighting to determine the comprehensive weight parameters for the four main attributes in four autonomous driving scenarios: safety data, stable data, congestion rate, and energy consumption.

[0079] The process of obtaining the objective weights corresponding to the attributes is detailed below:

[0080] Regarding the standardized decision matrix mentioned above Entropy can determine the relative importance of each attribute by quantifying the uncertainty of information about each attribute, thereby measuring the dispersion or variability of each attribute in the decision matrix. Entropy is defined as:

[0081] ;

[0082] in, ,when hour, .

[0083] Entropy is used to quantify the degree of uncertainty of an attribute. If the entropy value of an attribute is large, it means that the information of the attribute is more dispersed and the uncertainty is high. On the other hand, the smaller the entropy value, the more concentrated the information of the attribute is and the lower the uncertainty. This means that the attribute should be given higher weight in decision-making because it provides more certain information.

[0084] Therefore, for The objective weights of the aforementioned attributes are:

[0085] ;

[0086] for The objective weights of the aforementioned attributes, For the first The entropy value of each attribute. Reflects the first The distribution of the attribute across all options is uncertain. A larger entropy value for an attribute indicates a more dispersed information distribution and higher uncertainty; while a smaller entropy value indicates a more concentrated information distribution and lower uncertainty, meaning that this attribute should be given higher weight in decision-making because it provides more certain information.

[0087] The process of obtaining the subjective weights corresponding to the attributes is detailed below:

[0088] Step 1: Data collection.

[0089] Collecting data is a key step in building a model of human behavior. Multiple users of smart cars were invited to independently evaluate and judge the relative importance of two indicators in each subsystem and their driving habits.

[0090] Step 2: Data preprocessing.

[0091] The user ratings and judgments from the previous step are usually expressed in verbal form. Therefore, we need to preprocess and visually represent this verbal data. Specifically, we need to statistically analyze the verbal data and obtain the probability of each type of rating occurring. Next, the language evaluation is converted into language labels and then further converted into numerical values. The resulting numerical values ​​are then used to build a judgment matrix. Then, the judgment matrix will be used. The probability corresponding to each element in the matrix This combination yields a probabilistic linguistic terminology set, which is a direct reflection of the preferences implied in the user reviews collected in the previous step. The detailed process is as follows:

[0092] Define the following language terminology set S = { Extremely unimportant. It's not important at all. Not very important. It's not very important. Equally important Slightly more important More importantly, Very important. Extremely important;

[0093] Regulation With numerical values There is a mapping relationship; the larger the value, the greater the preference implied in the language data.

[0094] For a specific user evaluation, such as "Safety is more important than ride smoothness," "Safety is extremely important than fuel efficiency," or "Ride smoothness is more important than fuel consumption," mapping rules are used to map the user's language data to a set of language terms, and then the corresponding numerical values ​​are obtained. .

[0095] The probabilistic linguistic term set quantifies users' language data into the probabilities of linguistic terms, thereby reflecting users' evaluation of the importance of different attributes, making the subjective weight calculation in subsequent steps more consistent with reality.

[0096] Step 3: Calculate the user's subjective preferences for different attributes.

[0097] To balance users' subjective preferences for different autonomous driving attributes, and thus make the behavior of the autonomous driving system more in line with users' expectations and needs, we establish a human behavior model based on the language data collected above and the established probabilistic language terminology set. Let... These are safety, driving smoothness, congestion rate, and fuel consumption. The subjective weight values ​​reflect the user's subjective preferences for different attributes in the autonomous driving system.

[0098] This model finds the optimal subjective weights for each attribute by minimizing the degree of dissatisfaction, as follows:

[0099] ;

[0100] ;

[0101] In the objective function of this model, and These are user-defined attributes Relative to attributes The difference between positive and negative preferences;

[0102] The goal is to find a balance that minimizes the overall dissatisfaction of users with all attribute preferences.

[0103] The number of language terms contained in the probabilistic linguistic terminology set;

[0104] This is the Kth language term; This represents the probability value corresponding to the Kth language term;

[0105] It is a constant used to adjust the ratio between weights, and the default value is 4;

[0106] It is an attribute Subjective weighting, It is an attribute Subjective weighting;

[0107] This is the expectation function, which reflects the user's expectations of the attribute. Relative to attributes The expected value of the preference intensity, through To calculate the expectation;

[0108] This is used to ensure that the deviation does not result in a logically unreasonable negative value;

[0109] constraint This is used to ensure that the sum of all subjective weights is 1 and that each weight is non-negative, in order to guarantee the rationality and interpretability of the weights.

[0110] Within the constraints, the deviation under subjective weights is calculated using the primary constraint formula. and Continuously updated and weight Iterate until the objective function converges to the optimal solution. This is the optimal value output by the model at its final stage; the obtained optimal value is... That is, attributes The required subjective weight.

[0111] Specifically, based on the subjective weight corresponding to the attribute, the objective weight corresponding to the attribute, and a preset weight model, a comprehensive weight parameter corresponding to the attribute is generated, including:

[0112] Based on the subjective weight corresponding to the security data, the objective weight corresponding to the security data, and the preset weight model, the first comprehensive weight parameter corresponding to the security data is generated.

[0113] Based on the subjective weights corresponding to the stable data, the objective weights corresponding to the stable data, and the weight model, the second comprehensive weight parameters corresponding to the stable data are generated.

[0114] The third comprehensive weight parameter corresponding to the congestion rate is generated based on the subjective weight corresponding to the congestion rate, the objective weight corresponding to the congestion rate, and the weight model.

[0115] The fourth comprehensive weight parameter corresponding to the energy consumption is generated based on the subjective weight corresponding to the energy consumption, the objective weight corresponding to the energy consumption, and the weight model.

[0116] For example, the weighting model is:

[0117] ;

[0118] Among them, parameters This represents the proportional coefficient corresponding to the subjective weight.

[0119] Among them, parameters This represents the proportional coefficient corresponding to the objective weight;

[0120] in, This is used to represent the overall importance of different attributes, namely the importance of four attributes: safety data, stability data, congestion rate, and energy consumption.

[0121] For ease of explanation, the following example is provided:

[0122] in, Indicates the serial number; ;

[0123] in, Indicates the first One comprehensive weighting parameter; ;

[0124] The This represents the first comprehensive weight parameter;

[0125] The This represents the second comprehensive weighting parameter;

[0126] The This represents the third comprehensive weighting parameter;

[0127] The This represents the fourth comprehensive weighting parameter;

[0128] in, This represents the j-th subjective weight;

[0129] ;

[0130] The These are the subjective weights corresponding to the security data;

[0131] The These are the subjective weights corresponding to the stable data;

[0132] The It is the subjective weight corresponding to the congestion rate;

[0133] The This is the subjective weight corresponding to the energy consumption;

[0134] in, This represents the j-th objective weight; ;

[0135] It is the objective weight corresponding to the security data;

[0136] These are the objective weights corresponding to the stable data;

[0137] It is the objective weight corresponding to the congestion rate;

[0138] It is the objective weight corresponding to the energy consumption.

[0139] Wherein, the parameters The parameters Whether it is user-defined or system default, no restrictions are imposed here.

[0140] S203, Obtain the priority function, which includes the Gaussian criterion function and the hierarchical priority function;

[0141] For ease of explanation, the following example is provided:

[0142] To more accurately reflect the relative merits of different decision options, and taking into account the bounded rationality of users, the following two functions are set as corresponding priority functions for selection in different situations. Indicates the selection of the first One function is used as the priority function.

[0143] For nonlinear characteristics, using a Gaussian criterion function is more appropriate:

[0144] Nonlinear features refer to feature variables that do not conform to linear relationships during data analysis and model building.

[0145] When evaluation criteria have different levels of importance, a hierarchical priority function is more suitable.

[0146] S204, based on the evaluation value of the Gaussian criterion function on the attribute, determine the preference weight of the Gaussian criterion function; based on the evaluation value of the hierarchical priority function on the attribute, determine the preference weight of the hierarchical priority function; based on the preference weight of the Gaussian criterion function, the preference weight of the hierarchical priority function, and the comprehensive deviation generation model, generate the comprehensive deviation between the strategy scheme and the reference scheme regarding the attribute.

[0147] The process of setting the preference weights of the priority function is detailed below:

[0148] Prospect theory describes people's actual behavior when faced with risky choices, taking into account their irrational preferences when assessing probabilities and outcomes. In the context of autonomous driving strategy decision-making, we use prospect theory combined with the user's evaluation of driving habits from the preceding steps to calculate a more realistic and accurate preference evaluation of the user's priority function.

[0149] The process of setting the preference weights of the priority function is detailed below:

[0150] Prospect theory describes people's actual behavior when faced with risky choices, taking into account their irrational preferences when assessing probabilities and outcomes. In the context of autonomous driving strategy decision-making, we use prospect theory combined with the user's evaluation of driving habits from the preceding steps to calculate a more realistic and accurate preference evaluation of the user's priority function.

[0151] The steps are as follows:

[0152] Step 1: Set This represents the weight vector of each priority function determined by the user's perspective theory. The T in the upper right corner of the matrix denotes the transpose of the matrix. Based on the previous collection of evaluations and judgments of intelligent vehicle users regarding their driving habits, we obtained a large number of existing evaluations of the priority functions. It indicates the user's opinion on the first The priority function in the first... Evaluation under class attributes. Step 2: To quantify users' perceived value of various outcomes and characterize people's different ways of perceiving gains and losses, the following value function is used. To represent the user's attributes Using the When evaluating a priority function... Transformed perceived value:

[0153] ;

[0154] Among them, when value At that time, perceived value is in the benefit section, and the default parameter settings are used. This represents diminishing marginal satisfaction resulting from the gains; when the evaluation value At that time, perceived value is in the loss portion, and the default parameter settings are used. This represents the diminishing marginal dissatisfaction caused by losses, with a default loss aversion coefficient. This reflects that in real-world autonomous driving scenarios, users are more averse to and sensitive to risks and losses due to their own safety considerations.

[0155] Step 3: In autonomous driving scenarios, users often misperceive low-probability and high-probability events, overestimating the impact of low-probability events and underestimating the impact of high-probability events. To accurately reflect this psychological bias, a probability weighting function is used. To adjust perceived value to better align with psychological preferences in actual decision-making:

[0156] ;

[0157] in, This refers to the perceived value derived from the user's specific evaluation in step two. For specific evaluation. Parameters This is used here to describe the user's distorted perception of value in autonomous driving scenarios; the default setting. This indicates the general situation of overestimating low-probability events and underestimating high-probability events.

[0158] Step 4: Calculate the user's preference weight for the priority function based on the above results:

[0159] ;

[0160] This yields the weight vectors of each preference function determined by the user's foreground theory. .

[0161] This represents the evaluation value of the Gaussian criterion function on the i-th type of attribute. This represents the evaluation value of the hierarchical priority function on the i-th type of attribute.

[0162] This represents the preference weights of the Gaussian criterion function. This represents the preference weights of the hierarchical priority function. The bias generation model is defined as follows:

[0163] ;

[0164] in, Indicates the selection preference function Time Plan With the plan Between attributes deviation, For the first A priority function, , It is the Gaussian criterion function It is a priority function. , They represent the alternative solutions respectively. In attributes The standardized evaluation value.

[0165] The greater the deviation, the greater the degree of difference; the smaller the deviation, the smaller the degree of difference.

[0166] Incorporating user preference weights for the priority function, the comprehensive bias generation model is as follows:

[0167] ;

[0168] in, Representation scheme Regarding the plan In attributes Overall deviation, For the first A priority function, , It is the Gaussian criterion function. It is a priority function. This represents the preference weight corresponding to the t-th preference function. This represents the preference weights of the Gaussian criterion function. This represents the preference weight of the hierarchical priority function. Representation of strategy scheme In attributes The evaluation value on the screen Representation of strategy scheme In attributes The evaluation value on the screen Representation of strategy scheme In attributes The standardized evaluation value, Indicates reference scheme In attributes The standardized evaluation value.

[0169] S205, Based on the comprehensive deviation, the comprehensive weight parameters, and the preset comprehensive priority value generation model, generate the comprehensive priority value of the strategy scheme relative to the reference scheme;

[0170] For ease of explanation, the following example is provided:

[0171] For any two alternative solutions in an autonomous driving scenario The comprehensive priority value generation model is as follows:

[0172] ;

[0173] in, It is an attribute The comprehensive weighting parameters, The strategy scheme is as described above. As the reference scheme, This is the overall priority value of the strategy scheme relative to the reference scheme. Representation scheme Regarding the plan In attributes Overall deviation, Representation of strategy scheme In attributes The evaluation value on the screen Representation of strategy scheme In attributes The evaluation value on the screen Representation of strategy scheme In attributes The standardized evaluation value, Indicates reference scheme In attributes The standardized evaluation value.

[0174] S206, Based on the comprehensive priority value of the strategy scheme relative to the reference scheme and the preset inflow generation model, generate the outflow of the strategy scheme; based on the comprehensive priority value of the strategy scheme relative to the reference scheme and the preset outflow generation model, generate the inflow of the strategy scheme.

[0175] For ease of explanation, the following example is provided:

[0176] For each strategy plan of the user in the autonomous driving scenario Define the inflow generation model and the outflow generation model.

[0177] The inflow generation model is as follows:

[0178] ;

[0179] The outflow generation model is as follows:

[0180] ;

[0181] in, Indicates reference scheme For strategy The overall priority value.

[0182] Where n is the number of schemes;

[0183] Among them, inflow This indicates that all reference options take precedence over strategic options. Traffic.

[0184] in, Representation of strategy scheme For the reference scheme The overall priority value.

[0185] Among them, outflow Representation scheme Traffic is prioritized over all reference schemes;

[0186] S207, Based on the outflow and inflow, determine the net flow corresponding to the strategy scheme, sort the net flows corresponding to multiple strategy schemes, and select the strategy scheme corresponding to the largest net flow as the optimal driving strategy.

[0187] For ease of explanation, the following example is provided:

[0188] Based on strategy scheme By analyzing the inflow and outflow volumes, the strategy for autonomous driving scenarios can be calculated. Priority :

[0189] ;

[0190] in, Net flow Used to reflect strategic plans Priority in autonomous driving scenarios For outflow, Inflow

[0191] in, The larger the value, the better the strategy. The higher the priority compared to other reference schemes, the better. The net flow corresponding to multiple policy schemes is ranked, and the policy scheme corresponding to the largest net flow is selected as the optimal driving strategy in the autonomous driving scenario.

[0192] For ease of explanation, the following example is provided:

[0193] For example, the net flow corresponding to multiple of the aforementioned strategy schemes includes PA, PB, and PC;

[0194] Wherein, PA represents the net flow of strategy scheme A;

[0195] Wherein, PB represents the net flow of strategy scheme B;

[0196] Wherein, PC represents the net flow of strategy scheme C;

[0197] When PA is 10, PB is 11, and PC is 12, PA, PB, and PC are sorted. PC is the largest net flow, and strategy scheme C corresponding to PC is selected as the optimal driving strategy.

[0198] The driving strategy selection method includes, after determining the net flow corresponding to the strategy scheme based on the outflow and inflow, sorting the net flows corresponding to multiple strategy schemes, and selecting the strategy scheme corresponding to the largest net flow as the optimal driving strategy, the method further includes:

[0199] Step A: Transmit the driving strategy to the preset autonomous driving system and control the autonomous driving system to execute the driving strategy.

[0200] Specifically, the driving strategy and preset control commands are transmitted to the preset autonomous driving system, and the autonomous driving system is controlled to execute the driving strategy through the control commands.

[0201] Wherein, after determining the net flow corresponding to the strategy scheme based on the outflow and the inflow, sorting the net flows corresponding to multiple strategy schemes, and selecting the strategy scheme corresponding to the largest net flow as the optimal driving strategy, the driving strategy selection method includes:

[0202] Step B: Read the preset upload time and determine whether the current time is the preset upload time;

[0203] If the current time is the upload time, then connect to the preset server and upload the driving strategy to the server.

[0204] Wherein, after determining the net flow corresponding to the strategy scheme based on the outflow and the inflow, sorting the net flows corresponding to multiple strategy schemes, and selecting the strategy scheme corresponding to the largest net flow as the optimal driving strategy, the driving strategy selection method includes:

[0205] Step C: Obtain a preset storage area and store the driving strategy in the storage area.

[0206] Step A can be executed before or after steps B and C, step B can be executed before or after steps A and C, step C can be executed before or after steps A and B, and steps A, B, and C can be executed simultaneously. The specific execution order is not restricted here.

[0207] The beneficial effects of this application embodiment are twofold. Firstly, based on the comprehensive priority value of the strategy scheme relative to the reference scheme and a preset inflow generation model, the outflow of the strategy scheme is generated, and based on the comprehensive priority value of the strategy scheme relative to the reference scheme and the preset outflow generation model, the inflow of the strategy scheme is generated. Based on the outflow and inflow, the net flow corresponding to the strategy scheme is determined. The net flows corresponding to multiple strategy schemes are sorted, and the strategy scheme corresponding to the largest net flow is selected as the optimal driving strategy. Since no manual selection is required, a large amount of human and time resources are saved, thus improving the efficiency of driving strategy selection. Secondly, through the comprehensive priority value generation model, the influence of human factors can be eliminated, which helps to improve the reliability and accuracy of the selected driving strategy.

[0208] Please see Figure 3 , Figure 3 The flowchart for obtaining evaluation data provided in the embodiments of this application is described in detail below:

[0209] S301, Obtain sensor data, vehicle logs and vehicle monitoring data corresponding to the strategy scheme;

[0210] This includes acquiring sensor data from the sensors in the autonomous driving system.

[0211] For ease of explanation, we will use sensor data as an example. Sensor data includes the following:

[0212] Point cloud data: provides accurate 3D images of the vehicle's surroundings for obstacle detection, path planning, and terrain recognition.

[0213] Camera image data: Captures visual information from the front, rear, and sides of the vehicle, used for traffic sign recognition, pedestrian detection, lane line detection, etc.

[0214] Inertial measurement unit (IMU) data contains acceleration and angular velocity information, which is used to determine the vehicle's attitude, velocity, and orientation changes, and is crucial for vehicle dynamic control and positioning.

[0215] Other sensor data: such as radar data, ultrasonic sensor data.

[0216] Among these methods, vehicle monitoring data is acquired through the in-vehicle system.

[0217] For ease of explanation, let's take vehicle monitoring data as an example. Vehicle monitoring data includes the following:

[0218] Vehicle speed: Records the vehicle's speed in real time.

[0219] Engine status: including engine speed, temperature, fuel consumption, fault codes, etc., used to monitor engine performance and predict potential faults.

[0220] Braking system performance: Monitors brake pad wear, brake fluid condition, brake pressure, etc., to ensure driving safety.

[0221] External environmental parameters, such as weather conditions, visibility, temperature, and humidity, affect vehicle performance and driving decisions.

[0222] Battery and energy management system: manages vehicle energy usage by monitoring battery level, charging status, current, voltage, etc.

[0223] This includes obtaining vehicle log data through the in-vehicle system.

[0224] For ease of explanation, let's take vehicle log data as an example. Vehicle log data includes the following:

[0225] System Start-up and Shutdown Log: Records the time, location, and status of each vehicle start-up and shutdown.

[0226] Fault Log: Records faults and corresponding fault codes that occur in various vehicle systems, helping to quickly locate problems.

[0227] Maintenance records: These include maintenance schedules, the dates and details of parts replaced, reflecting the vehicle's maintenance status.

[0228] Driver behavior log: Records the driver's operating habits, such as rapid acceleration, sudden braking, and speeding, and is used to assess driving safety and optimize driver assistance systems.

[0229] Mileage and route: Recording the total mileage of the vehicle, the specific route of each trip and the time taken helps with route optimization and energy consumption analysis.

[0230] S302, integrate the sensor data, the vehicle log, and the vehicle monitoring data into the evaluation data;

[0231] S302, Obtain the attribute value of the strategy scheme from the evaluation data.

[0232] In this embodiment of the application, the attribute values ​​of the strategy scheme are obtained from the evaluation data. The attribute values ​​include safety data, stability data, congestion rate, and energy consumption. The safety data, stability data, congestion rate, and energy consumption all have important application value, and these data can help electronic devices select driving strategies.

[0233] For the driving strategy selection method described in the above embodiments, please refer to [link / reference]. Figure 4 , Figure 4 This is a schematic block diagram of a driving strategy selection device provided in an embodiment of this application. Figure 4 The driving strategy selection device 400 shown can be applied to, for example... Figure 1 The application scenario diagram shows electronic devices. The following section uses electronic devices as an example to illustrate this. Figure 4 The driving strategy selection device 400 shown will be described in detail. The driving strategy selection device 400 may include an acquisition module 401, a first generation module 402, a setting module 403, a second generation module 404, a third generation module 405, a fourth generation module 406, and a selection module 407.

[0234] The acquisition module 401 is used to acquire the strategy scheme of the autonomous driving system and acquire the attributes of the strategy scheme;

[0235] The first generation module 402 is used to generate a comprehensive weight parameter corresponding to the attribute based on the subjective weight corresponding to the attribute, the objective weight corresponding to the attribute, and a preset weight model.

[0236] The setting module 403 is used to obtain the priority function, which includes the Gaussian criterion function and the hierarchical priority function;

[0237] The second generation module 404 is used to determine the preference weight of the Gaussian criterion function based on the evaluation value of the Gaussian criterion function on the attribute, determine the preference weight of the hierarchical priority function based on the evaluation value of the hierarchical priority function on the attribute, and generate the comprehensive deviation between the strategy scheme and the reference scheme regarding the attribute based on the preference weight of the Gaussian criterion function, the preference weight of the hierarchical priority function, and the comprehensive deviation generation model.

[0238] The third generation module 405 is used to generate a comprehensive priority value of the strategy scheme relative to the reference scheme based on the comprehensive deviation, the comprehensive weight parameters and the preset comprehensive priority value generation model.

[0239] The fourth generation module 406 is used to generate the outflow of the strategy scheme based on the comprehensive priority value of the strategy scheme relative to the reference scheme and the preset inflow generation model, and to generate the inflow of the strategy scheme based on the comprehensive priority value of the strategy scheme relative to the reference scheme and the preset outflow generation model.

[0240] Selection module 407 is used to determine the net flow corresponding to the strategy scheme based on the outflow and the inflow, sort the net flow corresponding to multiple strategy schemes, and select the strategy scheme corresponding to the largest net flow as the optimal driving strategy.

[0241] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0242] The beneficial effects of this application embodiment are twofold. Firstly, based on the comprehensive priority value of the strategy scheme relative to the reference scheme and a preset inflow generation model, the outflow of the strategy scheme is generated, and based on the comprehensive priority value of the strategy scheme relative to the reference scheme and the preset outflow generation model, the inflow of the strategy scheme is generated. Based on the outflow and inflow, the net flow corresponding to the strategy scheme is determined. The net flows corresponding to multiple strategy schemes are sorted, and the strategy scheme corresponding to the largest net flow is selected as the optimal driving strategy. Since no manual selection is required, a large amount of human and time resources are saved, thus improving the efficiency of driving strategy selection. Secondly, through the comprehensive priority value generation model, the influence of human factors can be eliminated, which helps to improve the reliability and accuracy of the selected driving strategy.

[0243] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0244] like Figure 5 As shown, Figure 5 The electronic device 2 includes: at least one processor 20, a memory 21, and a computer program 22 stored in the memory 21 and executable on the at least one processor 20, wherein the processor 20 executes the computer program 22 to implement the steps in any of the above method embodiments.

[0245] The electronic device 2 may include, but is not limited to, a processor 20 and a memory 21. Those skilled in the art will understand that... Figure 5 This is merely an example of electronic device 2 and does not constitute a limitation on electronic device 2. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0246] The processor 20 is used to run a computer program 22 stored in the memory 21, and performs the following steps when executing the computer program 22:

[0247] Obtain the strategy scheme of the autonomous driving system, and obtain the attributes of the strategy scheme;

[0248] Based on the subjective weight corresponding to the attribute, the objective weight corresponding to the attribute, and the preset weight model, a comprehensive weight parameter corresponding to the attribute is generated.

[0249] Obtain the priority function, which includes the Gaussian criterion function and the hierarchical priority function;

[0250] Based on the evaluation value of the Gaussian criterion function on the attribute, the preference weight of the Gaussian criterion function is determined. Based on the evaluation value of the hierarchical priority function on the attribute, the preference weight of the hierarchical priority function is determined. Based on the preference weight of the Gaussian criterion function, the preference weight of the hierarchical priority function, and the comprehensive deviation generation model, the comprehensive deviation between the strategy scheme and the reference scheme regarding the attribute is generated.

[0251] Based on the comprehensive deviation, the comprehensive weighting parameter, and a preset comprehensive priority value generation model, a comprehensive priority value of the strategy scheme relative to the reference scheme is generated; based on the comprehensive priority value of the strategy scheme relative to the reference scheme and a preset inflow generation model, the outflow of the strategy scheme is generated; based on the comprehensive priority value of the strategy scheme relative to the reference scheme and the preset outflow generation model, the inflow of the strategy scheme is generated; based on the outflow and inflow, the net flow corresponding to the strategy scheme is determined; the net flows corresponding to multiple strategy schemes are sorted, and the strategy scheme corresponding to the largest net flow is selected as the optimal driving strategy.

[0252] In some embodiments, the processor 20 is configured to implement:

[0253] Acquire the sensor data, vehicle logs, and vehicle monitoring data corresponding to the strategy scheme;

[0254] The sensor data, the vehicle log, and the vehicle monitoring data are integrated into the evaluation data;

[0255] The attribute values ​​of the strategy scheme are obtained from the evaluation data.

[0256] In some embodiments, the processor 20 is configured to implement:

[0257] Based on the subjective weight corresponding to the security data, the objective weight corresponding to the security data, and the preset weight model, the first comprehensive weight parameter corresponding to the security data is generated.

[0258] Based on the subjective weights corresponding to the stable data, the objective weights corresponding to the stable data, and the weight model, the second comprehensive weight parameters corresponding to the stable data are generated.

[0259] The third comprehensive weight parameter corresponding to the congestion rate is generated based on the subjective weight corresponding to the congestion rate, the objective weight corresponding to the congestion rate, and the weight model.

[0260] The fourth comprehensive weight parameter corresponding to the energy consumption is generated based on the subjective weight corresponding to the energy consumption, the objective weight corresponding to the energy consumption, and the weight model.

[0261] In some embodiments, the processor 20 is configured to implement:

[0262] Obtain a first score of the strategy on the security data, obtain a second score of the reference solution on the security data, subtract the second score from the first score, and generate a first priority value of the strategy relative to the reference solution on the security data;

[0263] Obtain the third score of the strategy scheme on the stationary data, obtain the fourth score of the reference scheme on the stationary data, subtract the fourth score from the third score, and generate the second priority value of the strategy scheme relative to the reference scheme on the stationary data;

[0264] Obtain the fifth score of the strategy scheme on the congestion rate, obtain the sixth score of the reference scheme on the congestion rate, subtract the sixth score from the fifth score, and generate the third priority value of the strategy scheme relative to the reference scheme on the congestion rate;

[0265] Obtain the seventh score of the strategy scheme on the energy consumption, obtain the eighth score of the reference scheme on the energy consumption, subtract the eighth score from the seventh score, and generate the fourth priority value of the strategy scheme relative to the reference scheme on the energy consumption.

[0266] In some embodiments, the processor 20 is configured to implement:

[0267] The driving strategy is transmitted to the preset autonomous driving system, and the autonomous driving system is controlled to execute the driving strategy.

[0268] In some embodiments, the processor 20 is configured to implement:

[0269] Read the preset upload time and determine whether the current time is the preset upload time;

[0270] If the current time is the upload time, then connect to the preset server and upload the driving strategy to the server.

[0271] In some embodiments, the processor 20 is configured to implement:

[0272] Obtain a preset storage area and store the driving strategy in the storage area.

[0273] The processor 20 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0274] In some embodiments, the memory 21 may be an internal storage unit of the electronic device 2, such as a hard disk or memory of the electronic device 2. In other embodiments, the memory 21 may be an external storage device of the electronic device 2, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device 2. Furthermore, the memory 21 may include both internal and external storage units of the electronic device 2. The memory 21 is used to store the operating system, applications, boot loader, data, and other programs, such as the program code of the computer program. The memory 21 can also be used to temporarily store data that has been output or will be output.

[0275] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0276] This application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0277] The computer-readable storage medium stores program code that can be called by a processor to execute the driving strategy selection method described in the above method embodiments.

[0278] Computer-readable storage media have storage space for program code.

[0279] The program code includes the code for any step of the driving strategy selection method described in the above method embodiments.

[0280] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0281] The computer-readable storage medium may also be an external storage device of the driving strategy selection device or electronic device, such as a plug-in hard drive, smart media card (SMC), secure digital (SD) card, flash card, or non-transitory computer-readable storage medium equipped on the driving strategy selection device or electronic device.

[0282] Since the computer program stored in the computer-readable storage medium can execute any of the driving strategy selection methods provided in the embodiments of this application, the computer-readable storage medium can achieve the beneficial effects that any of the driving strategy selection methods provided in the embodiments of this application can achieve, as detailed in the preceding embodiments, and will not be repeated here.

[0283] This application provides a computer program product that, when run on an electronic device, causes the electronic device to execute the aforementioned driving strategy selection method.

[0284] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0285] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0286] Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate form. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to an electronic device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include a USB flash drive, a portable hard drive, a magnetic disk, or an optical disk. In the above embodiments, the descriptions of each embodiment have different focuses; parts not described in detail or in a particular embodiment can be referred to in the relevant descriptions of other embodiments.

[0287] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A driving strategy selection method, characterized in that, An electronic device used in a vehicle, the electronic device storing an autonomous driving system, the driving strategy selection method including: Obtain the strategy scheme of the autonomous driving system, and obtain the attributes of the strategy scheme; Based on the subjective weight corresponding to the attribute, the objective weight corresponding to the attribute, and the preset weight model, a comprehensive weight parameter corresponding to the attribute is generated. Obtain the priority function, which includes the Gaussian criterion function and the hierarchical priority function; Based on the evaluation value of the Gaussian criterion function on the attribute, the preference weight of the Gaussian criterion function is determined. Based on the evaluation value of the hierarchical priority function on the attribute, the preference weight of the hierarchical priority function is determined. Based on the preference weight of the Gaussian criterion function, the preference weight of the hierarchical priority function, and the comprehensive deviation generation model, the comprehensive deviation between the strategy scheme and the reference scheme regarding the attribute is generated. Based on the comprehensive deviation, the comprehensive weight parameters, and the preset comprehensive priority value generation model, a comprehensive priority value of the strategy scheme relative to the reference scheme is generated; Based on the overall priority value of the strategy scheme relative to the reference scheme and the preset inflow generation model, the outflow of the strategy scheme is generated, and based on the overall priority value of the strategy scheme relative to the reference scheme and the preset outflow generation model, the inflow of the strategy scheme is generated. Based on the outflow and inflow, the net flow corresponding to the strategy scheme is determined, the net flow corresponding to multiple strategy schemes is sorted, and the strategy scheme corresponding to the largest net flow is selected as the optimal driving strategy. The step of obtaining the strategy scheme of the autonomous driving system and obtaining the attributes of the strategy scheme includes: Acquire the sensor data, vehicle logs, and vehicle monitoring data corresponding to the strategy scheme; The sensor data, the vehicle log, and the vehicle monitoring data are integrated into evaluation data, and the attributes of the strategy scheme are obtained from the evaluation data. Based on the subjective weight corresponding to the attribute, the objective weight corresponding to the attribute, and a preset weight model, a comprehensive weight parameter corresponding to the attribute is generated, including: Acquire language data, and determine the subjective weight corresponding to the attribute based on the language data and a preset probabilistic language terminology set; Based on the subjective weight corresponding to the attribute, the objective weight corresponding to the attribute, and the preset weight model, a comprehensive weight parameter corresponding to the attribute is generated.

2. The driving strategy selection method according to claim 1, characterized in that, Before obtaining the strategy scheme of the autonomous driving system and the attributes of the strategy scheme, the driving strategy selection method includes: Multiple alternative solutions for the autonomous driving system are obtained. Among the multiple alternative solutions, two alternative solutions are selected. One of the two alternative solutions is selected as the strategy solution, and the other of the two alternative solutions is selected as the reference solution.

3. The driving strategy selection method according to claim 1, characterized in that, After determining the net flow corresponding to the strategy scheme based on the outflow and inflow, sorting the net flows corresponding to multiple strategy schemes, and selecting the strategy scheme corresponding to the largest net flow as the optimal driving strategy, the driving strategy selection method includes: The driving strategy is transmitted to the preset autonomous driving system, and the autonomous driving system is controlled to execute the driving strategy.

4. The driving strategy selection method according to claim 1, characterized in that, After determining the net flow corresponding to the strategy scheme based on the outflow and inflow, sorting the net flows corresponding to multiple strategy schemes, and selecting the strategy scheme corresponding to the largest net flow as the optimal driving strategy, the driving strategy selection method includes: Read the preset upload time and determine whether the current time is the preset upload time; If the current time is the upload time, then connect to the preset server and upload the driving strategy to the server.

5. The driving strategy selection method according to claim 1, characterized in that, After determining the net flow corresponding to the strategy scheme based on the outflow and inflow, sorting the net flows corresponding to multiple strategy schemes, and selecting the strategy scheme corresponding to the largest net flow as the optimal driving strategy, the driving strategy selection method includes: Obtain a preset storage area and store the driving strategy in the storage area.

6. A driving strategy selection device, characterized in that, An electronic device used in a vehicle, the electronic device storing an autonomous driving system, including: The acquisition module is used to acquire the strategy scheme of the autonomous driving system and acquire the attributes of the strategy scheme; The first generation module is used to generate a comprehensive weight parameter corresponding to the attribute based on the subjective weight corresponding to the attribute, the objective weight corresponding to the attribute, and a preset weight model. The module is configured to obtain the priority function, which includes the Gaussian criterion function and the hierarchical priority function. The second generation module is used to determine the preference weight of the Gaussian criterion function based on the evaluation value of the Gaussian criterion function on the attribute, determine the preference weight of the hierarchical priority function based on the evaluation value of the hierarchical priority function on the attribute, and generate the comprehensive deviation between the strategy scheme and the reference scheme regarding the attribute based on the preference weight of the Gaussian criterion function, the preference weight of the hierarchical priority function, and the comprehensive deviation generation model. The third generation module is used to generate a comprehensive priority value of the strategy scheme relative to the reference scheme based on the comprehensive deviation, the comprehensive weight parameters and the preset comprehensive priority value generation model. The fourth generation module is used to generate the outflow of the strategy scheme based on the comprehensive priority value of the strategy scheme relative to the reference scheme and the preset inflow generation model, and to generate the inflow of the strategy scheme based on the comprehensive priority value of the strategy scheme relative to the reference scheme and the preset outflow generation model. The selection module is used to determine the net flow corresponding to the strategy scheme based on the outflow and the inflow, sort the net flow corresponding to multiple strategy schemes, and select the strategy scheme corresponding to the largest net flow as the optimal driving strategy. The step of obtaining the strategy scheme of the autonomous driving system and obtaining the attributes of the strategy scheme includes: Acquire the sensor data, vehicle logs, and vehicle monitoring data corresponding to the strategy scheme; The sensor data, the vehicle log, and the vehicle monitoring data are integrated into evaluation data, and the attributes of the strategy scheme are obtained from the evaluation data. Based on the subjective weight corresponding to the attribute, the objective weight corresponding to the attribute, and a preset weight model, a comprehensive weight parameter corresponding to the attribute is generated, including: Acquire language data, and determine the subjective weight corresponding to the attribute based on the language data and a preset probabilistic language terminology set; Based on the subjective weight corresponding to the attribute, the objective weight corresponding to the attribute, and the preset weight model, a comprehensive weight parameter corresponding to the attribute is generated.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the driving strategy selection method as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the driving strategy selection method as described in any one of claims 1 to 5.

Images