Group simulation model parameter calibration method and electronic equipment

Abstract

The invention discloses a group simulation model parameter calibration method and electronic equipment, and the method comprises the steps: extracting a feature set from a first reference data set, and the feature set comprises the dynamic group features and static scene features of individuals; performing offline calibration on a group simulation model through the first reference data set to obtain a model parameter set; according to the feature set and the model parameter set, a first relation is obtained, and the first relation is the optimal mapping relation between model parameters in the model parameter set and the dynamic group features and between the model parameters in the model parameter set and the static scene features; and in the online calibration process of the group simulation model, calibrating parameters of the group simulation model according to the first relationship, the static scene characteristics of current simulation and the dynamic group characteristics, and combining offline calibration with online calibration, so that the parameter calibration of the Agent-based group simulation model gives consideration to scene matching and real-time time performance.

Description

Technical Field

[0001] The invention relates to the field of computer technology, and in particular to a group simulation model parameter calibration method and electronic equipment. Background Art

[0002] The parameter calibration of the Agent-based group simulation model (such as crowd, traffic, bird flock, ant colony, particle simulation) can be divided into offline calibration and online calibration according to the timing and method of parameter calibration. When the simulation scene is greatly different from the reference trajectory scene, the offline calibration parameters are directly used for simulation, and the fidelity and credibility are difficult to convince people. Online calibration relies on real-time access to real scene data, and often sacrifices the accuracy of simulation calibration in order to meet real-time time performance. Therefore, the parameter calibration of the Agent-based group simulation model cannot take into account both scene matching and real-time time performance. Summary of the invention

[0003] In view of this, the embodiments of the present invention provide a group simulation model parameter calibration method and electronic device, which combine offline calibration with online calibration, so that the parameter calibration of the agent-based group simulation model takes into account both scene matching and real-time performance.

[0004] In a first aspect, an embodiment of the present invention provides a group simulation model parameter calibration method, the method comprising:

[0005] Extracting a feature set from the first reference data set, the feature set comprising individual dynamic group features and static scene features;

[0006] Offline calibration of the group simulation model is performed using the first reference data set to obtain a model parameter set;

[0007] According to the feature set and the model parameter set, a first relationship is obtained, where the first relationship is an optimal mapping relationship between the model parameters in the model parameter set and the dynamic group feature and the static scene feature;

[0008] During the online calibration process of the group simulation model, the parameters of the group simulation model are calibrated according to the first relationship, static scene characteristics of the current simulation, and dynamic group characteristics.

[0009] In combination with the first aspect, in some implementations of the first aspect, the offline calibration of the group simulation model using the first reference data set to obtain a model parameter set includes:

[0010] Slicing the data of individuals in the first reference data set according to the first numerical frame to obtain a second reference data set;

[0011] The group simulation model is offline calibrated according to the second reference data set and an offline calibration algorithm to obtain a model parameter set.

[0012] In combination with the first aspect, in some implementations of the first aspect, the amount of data in the first reference data set is less than a first threshold, and obtaining the first relationship according to the feature set and the model parameter set includes:

[0013] According to the feature set and the model parameter set, the dynamic group feature, the static scene feature and the model parameter are calculated by linear transformation to obtain an objective function;

[0014] The objective function is optimized and solved by the least square method to obtain the first relationship.

[0015] In combination with the first aspect, in some implementations of the first aspect, the amount of data in the first reference data set is greater than or equal to a first threshold, and obtaining the first relationship according to the feature set and the model parameter set includes:

[0016] According to the feature set and the model parameter set, a mapping relationship among the dynamic group features, the static scene features and the model parameters is learned through a convolutional neural network method to obtain a first relationship.

[0017] In combination with the first aspect, in some implementations of the first aspect, learning the mapping relationship between the dynamic group feature, the static scene feature, and the model parameter by using a convolutional neural network includes:

[0018] Using the dynamic group features and the static scene features as inputs of the convolutional neural network, and using the model parameters as outputs of the convolutional neural network;

[0019] The mapping relationship between the input and the output is learned through the convolutional layer, the pooling layer and the fully connected layer in the convolutional neural network.

[0020] In combination with the first aspect, in some implementations of the first aspect, the offline calibration algorithm is a random optimization algorithm.

[0021] In combination with the first aspect, in some implementations of the first aspect, the random optimization algorithm includes a genetic algorithm, an ant colony algorithm, or a simulated annealing algorithm.

[0022] In combination with the first aspect, in certain implementations of the first aspect, the first reference data set includes: location trajectory information of each individual in the group and layout information of the scene where the group is located.

[0023] In combination with the first aspect, in some implementations of the first aspect, the dynamic group feature includes: one or any combination of speed, movement direction, relative distance to surrounding neighbors, and relative speed.

[0024] In combination with the first aspect, in certain implementations of the first aspect, the static scene features include: one or any combination of the passable area within the individual's forward field of vision, the passable area within the individual's lateral field of vision, and the distance between the individual and surrounding static obstacles.

[0025] In combination with the first aspect, in some implementations of the first aspect, the first numerical frame includes 100 frames.

[0026] In a second aspect, an embodiment of the present invention provides an electronic device, comprising a processor and a memory, wherein the memory is used to store a computer program, and the computer program comprises program instructions, and when the processor runs the program instructions, the electronic device executes the steps of the method described above.

[0027] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program request is executed by a computer, the computer is caused to execute the method as described above.

[0028] In a fourth aspect, an embodiment of the present invention provides a computer program product, which includes instructions, and when the computer program product is run on a computer or any at least one processor, the computer executes the functions / steps in the above method.

[0029] In the technical solution of the group simulation model parameter calibration method and electronic device provided by the embodiment of the present invention, the group simulation model parameter calibration method includes: extracting a feature set from a first reference data set, the feature set including individual dynamic group features and static scene features; performing offline calibration on the group simulation model through the first reference data set to obtain a model parameter set; obtaining a first relationship based on the feature set and the model parameter set, the first relationship being the optimal mapping relationship between the model parameters in the model parameter set and the dynamic group features and the static scene features; in the online calibration process of the group simulation model, calibrating the parameters of the group simulation model based on the first relationship, the static scene features of the current simulation, and the dynamic group features, combining the offline calibration with the online calibration, so that the parameter calibration of the agent-based group simulation model takes into account both scene matching and real-time time performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1A flow chart of a group simulation model parameter calibration method provided by an embodiment of the present invention;

[0031] Figure 2 for Figure 1 In the specific flow chart of performing offline calibration on the group simulation model through the first reference data set to obtain a model parameter set;

[0032] Figure 3 for Figure 1 According to the feature set and the model parameter set, a first relationship is obtained, where the first relationship is a specific flow chart of an optimal mapping relationship between the model parameters in the model parameter set and the dynamic group features and the static scene features;

[0033] Figure 4 for Figure 1 According to the feature set and the model parameter set, a first relationship is obtained, where the first relationship is another specific flow chart of an optimal mapping relationship between the model parameters in the model parameter set and the dynamic group features and the static scene features;

[0034] Figure 5 It is a schematic diagram of using a convolutional neural network to learn the mapping relationship between dynamic group features, static scene features and the model parameters in an embodiment of the present invention;

[0035] Figure 6 A schematic diagram of a parameter calibration process of a traffic simulation IDM in an embodiment of the present invention;

[0036] Figure 7 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention;

[0037] Figure 8 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention;

[0038] Fig. 9 1 is a software structure block diagram of the electronic device 100 according to an embodiment of the present invention. DETAILED DESCRIPTION

[0039] In order to better understand the technical solution of the present invention, the embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0040] It should be clear that the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0042] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0043] First, the relevant terms involved in the present invention are explained as follows:

[0044] Crowd Simulation: It uses computer simulation technology to integrate knowledge from subjects such as group behavior, sociology, and kinematics to model and simulate group behavior processes. Crowd simulation technology provides a scientific, objective, and repeatable method to simulate group behavior, providing strong support for the development and progress of human society.

[0045] Agent-based simulation method: A method that uses agents as basic units to explore group behavior by simulating the interactions and behavioral patterns between agents. In agent-based simulation, individuals are the basic units of simulation, the environment is the basis of agent behavior, and the behavioral interactions between individuals are the necessary expression of group behavior. Agent-based simulation methods are widely used in social modeling and simulation, urban planning and traffic forecasting, organizational management, and collaborative behavior analysis.

[0046] Model Parameter Calibration: refers to the process of adjusting or optimizing the parameters of the model so that its output more accurately reflects the true probability distribution.

[0047] Agent-based group simulation needs to consider the environment and group dynamics. Different environments (such as open squares and narrow indoor passages), different cultures (such as the tolerance of social distance in the East and the West), and even different times (such as rush hour in the morning and evening) require different simulation parameters to be applied in the group simulation model so that the simulation effect matches the current scene. Modeling many influencing factors in group simulation, as well as matching and finding suitable simulation parameters, has always been a challenge in the field of group simulation.

[0048] At present, the parameter calibration of Agent-based group simulation (such as crowd, traffic, bird flock, ant colony, particle simulation) models can be divided into offline calibration and online calibration according to the timing and method of parameter calibration.

[0049] Offline calibration is to adjust the parameters of the group simulation model in an offline environment after the group simulation model is deduced, and use an independent reference data set to evaluate and optimize the model performance. The basic process is to perform a random search in the parameter domain based on the reference data set to obtain a parameter set that minimizes the error between the simulated trajectory data and the reference trajectory data in the reference data set. During real-time simulation, the calibrated parameters are randomly assigned to the simulated individuals and will not change during the simulation. When the simulation scene is very different from the reference trajectory scene, this offline calibration directly uses the parameters after offline calibration for simulation, and the fidelity and credibility are difficult to convince people. In addition, the computational complexity of offline calibration is generally high, resulting in high computational cost and time consumption.

[0050] For example, offline calibration of group simulation based on genetic algorithm is to use the parameters of the group simulation model as individuals of the genetic algorithm, run the group simulation model under a set of initial parameters, and obtain the simulated group trajectory; calculate the error between the group simulation and the reference trajectory data. Then, the parameters are continuously optimized through genetic operations such as gene crossover and mutation until the expected model performance is achieved. The genetic algorithm will consume a lot of time in the iterative process, and can only guarantee good performance on the reference data set, but cannot guarantee the same effectiveness on other data sets. When the calibrated parameters are applied to simulation scenarios that are significantly different from the reference trajectory scenarios, the realism and credibility are difficult to convince people.

[0051] Online calibration is to dynamically adjust model parameters according to the feedback data of real-time simulation in real-time simulation to adapt to changes in the actual simulation environment. Online calibration relies on real-time access to real scene data, and often sacrifices the accuracy of simulation calibration in order to meet real-time time performance.

[0052] For example, the online calibration of traffic flow simulation based on fuzzy reasoning uses fuzzy rules to describe the interaction between driver model parameters and driving strategies, performs cluster analysis on reference trajectory data, and pre-calculates and sets fuzzy rules. During online simulation, the driver model parameters of the simulated vehicle are extracted in real time for reasoning, simulation, and calibration. Designing a set of accurate and representative fuzzy rules requires rich experience and expertise, and may involve subjectivity and uncertainty. Similar to offline calibration, the online calibration method based on fuzzy reasoning has limited adaptability to different scenarios and environments. In addition, in order to achieve a higher calibration accuracy, the simulation reasoning system needs to consider more factors, the computational complexity is higher, and a longer calculation time is required. In order to achieve real-time purposes, the factors in the fuzzy system are often simplified.

[0053] Therefore, the parameter calibration of the Agent-based group simulation model cannot take into account both scene matching and real-time performance.

[0054] Based on the above technical problems, the embodiments of the present invention provide a group simulation model parameter calibration method and electronic device, which combine offline calibration with online calibration, so that the parameter calibration of the agent-based group simulation model takes into account both scene matching and real-time time performance. The present invention is applicable to all calibration scenarios of agent-based group simulation, and establishes a mapping relationship between the parameters of the agent-based group simulation model and the static environment scene and the macro-micro dynamic properties of the group by learning a large amount of reference group motion trajectory data, and applies it to real-time online simulation to perform real-time adaptive tuning of the group simulation model parameters.

[0055] Figure 1 Flow chart of a group simulation model parameter calibration method provided by an embodiment of the present invention. Figure 1 As shown, the method includes:

[0056] Step 202: extract a feature set from the first reference data set, where the feature set includes individual dynamic group features and static scene features.

[0057] Exemplarily, the first reference data set includes: location trajectory information of each individual in the group and layout information of the scene where the group is located.

[0058] Exemplarily, the dynamic group characteristics include: speed magnitude, movement direction, relative distance to surrounding neighbors, and relative speed, or any combination thereof.

[0059] Exemplarily, the static scene features include: one or any combination of the passable area within the individual's forward field of vision, the passable area within the individual's lateral field of vision, and the distance between the individual and surrounding static obstacles.

[0060] Step 204: Offline calibration of the group simulation model is performed using the first reference data set to obtain a model parameter set.

[0061] In this step, simulation updates and parameter calibration are performed on each Agent. During this period, the trajectories of other simulated individuals in the group are consistent with the reference trajectory data in the first reference data set; by continuously adjusting the group simulation model parameters, the trajectories of the simulated individuals are made to fit the reference trajectory data more closely.

[0062] In some possible embodiments, Figure 2 As shown, step 204 specifically includes:

[0063] Step 2042: Slice the individual data in the first reference data set according to the first numerical frame to obtain a second reference data set.

[0064] Exemplarily, the first numerical frame includes 100 frames. According to actual working experience, when using calibrated parameters for simulation, the accuracy of the first 100 frames of simulation can be maintained above 85%, and after the 100th frame, as the accumulated error increases, the accuracy decreases significantly.

[0065] Step 2044: perform offline calibration on the group simulation model according to the second reference data set and the offline calibration algorithm to obtain a model parameter set.

[0066] Exemplarily, the offline calibration algorithm is a stochastic optimization algorithm.

[0067] Exemplarily, the random optimization algorithm includes a genetic algorithm, an ant colony algorithm, or a simulated annealing algorithm.

[0068] Taking the offline calibration algorithm as a genetic algorithm as an example, the group simulation model is calibrated offline. First, a fitness function that measures the model fit is defined based on the actual observation data and the output results of the group simulation model. The fitness function can be designed according to the specific requirements of the problem, such as minimizing the residual sum of squares or maximizing the likelihood function. Then the population is initialized, and a set of initial parameters is randomly generated as individuals in the population based on the range of parameters and prior knowledge. Each individual in the population represents a parameter combination of the model. A selection operator is used to select a part of individuals from the population as parents. During selection, individuals with higher fitness have a higher probability of being selected. The selected parent individuals are exchanged with genes through the crossover operator to generate new offspring individuals. Crossover can be performed by single-point crossover, multi-point crossover or uniform crossover. The newly generated offspring individuals are mutated to introduce new gene combinations. Mutation can be achieved by randomly changing one or some gene values ​​in the individual. For the newly generated offspring individuals, their fitness values ​​are calculated, that is, the fit between the model output and the observed data. A part of individuals are selected from the parent and offspring individuals as the population of the next generation. During selection, individuals with higher fitness have a higher probability of being selected. According to the preset termination conditions, determine whether to terminate the algorithm. The termination conditions can be reaching the maximum number of iterations, fitness reaching a certain threshold, etc. Repeat the steps of "using the selection operator to select a part of individuals from the population as parents" to "according to the preset termination conditions, determine whether to terminate the algorithm" until the termination conditions are met. After the algorithm terminates, select the individual with the highest fitness as the optimal parameter combination, which is the parameter set output after offline calibration. By continuously iterating the above steps, each simulated individual finds the optimal model parameter combination every 100 frames, so that the model can better fit the reference data. When recording the optimal model parameters corresponding to each individual's trajectory every 100 frames, the calibration accuracy is also recorded.

[0069] Step 206: Obtain a first relationship according to the feature set and the model parameter set, where the first relationship is an optimal mapping relationship between the model parameters in the model parameter set and the dynamic group features and the static scene features.

[0070] As an optional solution, the data volume of the first reference data set is less than the first threshold, such as Figure 3 As shown, step 206 specifically includes:

[0071] Step 2062: According to the feature set and the model parameter set, the dynamic group features, the static scene features and the model parameters are calculated by linear transformation to obtain the objective function.

[0072] When the amount of data in the first reference data set is small, a linear transformation method is used to calculate the dynamic group features, static scene features and model parameters to obtain the objective function.

[0073] Exemplarily, the objective function is as follows:

[0074]

[0075] w i =(p i -p min ) / (p max -p min )

[0076] Among them, X is the dynamic group feature and static scene feature, Y is the model parameter, R is the mapping relationship between X and Y, M is the number of reference sets in the first reference data set used for offline calibration, and p i is the calibration accuracy of the ith trajectory, w i is the influence weight of the trajectory parameter after standardization, p min and p max are the minimum and maximum calibration accuracy, respectively.

[0077] Step 2064: Optimize and solve the objective function using the least squares method to obtain a first relationship.

[0078] In this step, the objective function is optimized and solved by the least square method to obtain the optimal solution of R, that is, the first relationship.

[0079] As another optional solution, the amount of data in the first reference data set is greater than or equal to the first threshold, and step 206 specifically includes: learning the mapping relationship between dynamic group features, static scene features and model parameters through a convolutional neural network (CNN) method according to the feature set and the model parameter set to obtain a first relationship. In some possible embodiments, such as Figure 4As shown, step 206 specifically includes:

[0080] Step 206a: Use the dynamic group features and static scene features as inputs of the convolutional neural network, and use the model parameters as outputs of the convolutional neural network.

[0081] When the data volume of the first reference data set is large, a convolutional neural network is used to learn the mapping relationship between dynamic group features, static scene features and the model parameters. Figure 5 Schematic diagram of the mapping relationship between the dynamic group features, the static scene features and the model parameters learned by using a convolutional neural network in an embodiment of the present invention, as shown in FIG. Figure 5 As shown, the eigenvector X=(x1,x2,x3,…,x n ) represents all dynamic group features and static scene features contained in every 100 frames of each simulated individual in the group, n is the length of the feature vector X; model parameter vector Y = (y1, y2, ..., y d ) represents the model parameters obtained by the corresponding offline calibration, and d is the number of model parameters. The feature vector X is used as the input of the convolutional neural network, and the model parameter vector Y is used as the output of the convolutional neural network.

[0082] Step 206b: learn the mapping relationship between input and output through the convolutional layer, pooling layer and fully connected layer in the convolutional neural network.

[0083] like Figure 5 As shown, in the convolutional neural network, the mapping relationship between the feature vector X and the model parameter vector Y is learned through the convolution layer, the pooling layer and the fully connected layer. The present invention does not specify a specific CNN structure.

[0084] Step 208: During the online calibration process of the group simulation model, the parameters of the group simulation model are calibrated according to the first relationship, the static scene characteristics of the current simulation, and the dynamic group characteristics.

[0085] In the online calibration process of the group simulation model, for each individual i at each simulation update of time t, first calculate the current dynamic group features and static scene features x of individual i. Then, according to the mapping relationship R learned in step 206b, use y=xR to calculate the optimal simulation model parameter vector y of individual i at time t.

[0086] The present invention aims to solve the problem of how to maximize the value of the parameter set generated by the reference data set in the ever-changing simulation scenarios in the Agent-based group simulation, and to be able to adaptively cope with the dynamically changing group simulation scenarios, while meeting the time performance requirements of the real-time online simulation. In response to this demand, the present invention establishes the simulation model parameters after offline calibration, that is, the mapping relationship between the model parameters in the parameter set and the dynamic group characteristics and static scene characteristics of the first reference data set, and designs efficient mapping learning methods according to the data volume of different reference data sets, thereby effectively solving the scene matching and real-time time performance problems of the model parameter calibration.

[0087] In microscopic traffic simulation models, such as the Intelligent Driver Model (IDM), each vehicle is modeled as an independent agent, and its behavior can be simulated by calculating its perception, decision-making, and action processes. The model parameters of the IDM that need to be calibrated are shown in Table 1.

[0088] Table 1 shows the model parameters of the IDM that need to be calibrated.

[0089] <![CDATA[ parameter ]]> <![CDATA[ meaning ]]> <![CDATA[ Value range ]]> <![CDATA[ Maximum acceleration a_max ]]> <![CDATA[ The maximum acceleration that the vehicle can achieve ]]> <![CDATA[ 2.0-3.0m / s 2 ]]> <![CDATA[ Maximum deceleration b_max ]]> <![CDATA[ The maximum deceleration that the vehicle can achieve ]]> <![CDATA[ 3.0-5.0m / s 2 ]]> <![CDATA[ Expected speed v_des ]]> <![CDATA[ The average speed that the vehicle expects in free-running conditions ]]> <![CDATA[ 120km / h ]]> <![CDATA[ Minimum headway time T_min ]]> <![CDATA[ Minimum safe distance between the vehicle and the vehicle ahead ]]> <![CDATA[ 1.2-2.0s ]]> <![CDATA[ Comfort acceleration a_comf ]]> <![CDATA[ Comfortable acceleration of the vehicle ]]> <![CDATA[ 0.3-0.7m / s 2 ]]> <![CDATA[ Headway scaling parameter delta ]]> <![CDATA[ Factors affecting headway ]]> <![CDATA[ 4.0 ]]>

[0090] In order to calculate the optimal model parameters of the IDM corresponding to each update step in real time in online simulation, it is first necessary to learn the mapping relationship between individual static scene features and dynamic group features and the model parameters of the IDM. Figure 6 FIG. 1 is a schematic diagram of a parameter calibration process of a traffic simulation IDM in an embodiment of the present invention. Figure 6As shown, the first reference data set uses the Next Generation Simulation (NGSIM) publicly available traffic flow data set, covering a total of 90 hours of vehicle driving trajectory data at 6 highway locations and a total of 30 hours of vehicle driving trajectory data at 2 urban street locations. Static scene features and dynamic group features X of vehicle behavior are collected from the NGSIM data set. The static scene features and dynamic group features X include road network topology, road width, road length, lane capacity, vehicle speed, vehicle acceleration, headway, distance between the vehicle and surrounding vehicles, and relative speed. The vehicle driving trajectory data in the NGSIM data set is used to perform offline calibration of the model parameters of the IDM to obtain the parameter set Y of the calibrated IDM. According to the static scene features and dynamic group features X of the vehicle and the parameter set Y, the mapping relationship R between the two is learned. For the case of NGSIM with a small amount of data, a linear transformation method is used to calculate the mapping relationship R using the objective function. During online simulation, the traffic flow simulation state at time t is input, and the static scene features and dynamic group features of each vehicle are captured, and the optimal model parameters of the IDM corresponding to the simulated vehicle at time t can be calculated using y=xR.

[0091] The group simulation model parameter calibration method of the present invention is a universal parameter real-time online adaptive tuning method for various agent-based group simulation methods; defines the information composition of static scene features and dynamic group features related to simulation parameter calibration; combines offline calibration with online calibration; considers the correlation between calibration parameters and current simulation scene features during the calibration process; establishes a mapping relationship between group simulation model parameters and group scene features; based on the mapping relationship, uses a real-time group simulation parameter calibration method based on scene features to complete the real-time online adaptive tuning of virtual individual simulation model parameters.

[0092] The embodiment of the present invention introduces static scene features and dynamic group features in the real-time online adaptive tuning of group simulation parameters. When the amount of reference data is small, a modeling method for the mapping relationship between model parameters of the group simulation model and group scene features (static scene features and dynamic group features) is provided based on linear transformation. When the amount of reference data is large, a modeling method for the mapping relationship between model parameters of the group simulation model and group scene features is provided based on deep learning. Real-time online adaptive tuning of group simulation parameters based on scene features is provided.

[0093] In the technical solution of the group simulation model parameter calibration method provided by the embodiment of the present invention, the method includes: extracting a feature set from a first reference data set, the feature set including individual dynamic group features and static scene features; performing offline calibration on the group simulation model through the first reference data set to obtain a model parameter set; obtaining a first relationship based on the feature set and the model parameter set, the first relationship being the optimal mapping relationship between the model parameters in the model parameter set and the dynamic group features and the static scene features; in the online calibration process of the group simulation model, calibrating the parameters of the group simulation model based on the first relationship, the static scene features of the current simulation, and the dynamic group features, combining the offline calibration with the online calibration, so that the parameter calibration of the agent-based group simulation model takes into account both scene matching and real-time time performance.

[0094] Figure 7 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. It should be understood that the electronic device 400 can execute each step in the above group simulation model parameter calibration method. To avoid repetition, it will not be described in detail here. The electronic device 400 includes: a processing unit 401.

[0095] The processing unit 401 is used to extract a feature set from a first reference data set, wherein the feature set includes individual dynamic group features and static scene features; perform offline calibration on a group simulation model using the first reference data set to obtain a model parameter set; obtain a first relationship based on the feature set and the model parameter set, wherein the first relationship is an optimal mapping relationship between the model parameters in the model parameter set and the dynamic group features and the static scene features; and during the online calibration process of the group simulation model, calibrate the parameters of the group simulation model based on the first relationship, the static scene features of the current simulation, and the dynamic group features.

[0096] Optionally, the processing unit 401 is specifically used to: slice the individual data in the first reference data set according to the first numerical frame to obtain a second reference data set; and offline calibrate the group simulation model according to the second reference data set and an offline calibration algorithm to obtain a model parameter set.

[0097] Optionally, the data volume of the first reference data set is less than a first threshold value, and the processing unit 401 is specifically used to: calculate the dynamic group features, the static scene features and the model parameters by linear transformation according to the feature set and the model parameter set to obtain an objective function; optimize and solve the objective function by the least squares method to obtain the first relationship.

[0098] Optionally, the data volume of the first reference data set is greater than or equal to a first threshold, and the processing unit 401 is specifically used to: learn the mapping relationship between the dynamic group features, the static scene features and the model parameters through a convolutional neural network method according to the feature set and the model parameter set, and obtain a first relationship.

[0099] Optionally, the processing unit 401 is specifically used to: use the dynamic group features and the static scene features as inputs of the convolutional neural network, and use the model parameters as outputs of the convolutional neural network; and learn the mapping relationship between the input and the output through the convolutional layer, pooling layer and fully connected layer in the convolutional neural network.

[0100] Optionally, the offline calibration algorithm is a stochastic optimization algorithm.

[0101] Optionally, the random optimization algorithm includes a genetic algorithm, an ant colony algorithm or a simulated annealing algorithm.

[0102] Optionally, the first reference data set includes: location trajectory information of each individual in the group and layout information of the scene where the group is located.

[0103] Optionally, the dynamic group feature includes: speed, movement direction, relative distance to surrounding neighbors, and relative speed, or any combination thereof.

[0104] Optionally, the static scene features include: one or any combination of: a passable area within the individual's forward field of vision, a passable area within the individual's lateral field of vision, and a distance between the individual and surrounding static obstacles.

[0105] Optionally, the first numerical frame includes 100 frames.

[0106] It should be understood that the electronic device 400 here is embodied in the form of a functional unit. The term "unit" here can be implemented in the form of software and / or hardware, and is not specifically limited to this. For example, a "unit" can be a software program, a hardware circuit, or a combination of the two that implements the above functions. The hardware circuit may include an application-specific integrated circuit (ASIC), an electronic circuit, a processor (such as a shared processor, a proprietary processor, or a group processor, etc.) and a memory for executing one or more software or firmware programs, a merged logic circuit, and / or other suitable components that support the described functions.

[0107] Therefore, the units of each example described in the embodiments of the present invention can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0108] Figure 8 A schematic structural diagram of an electronic device 100 is shown.

[0109] The electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, an earphone interface 170D, a sensor module 180, a button 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a subscriber identification module (SIM) card interface 195, etc. The sensor module 180 may include a pressure sensor 180A, a gyroscope sensor 180B, an air pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, an ambient light sensor 180L, a bone conduction sensor 180M, etc.

[0110] It is to be understood that the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 may include more or fewer components than shown in the figure, or combine some components, or separate some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0111] The processor 110 may include one or more processing units, for example, the processor 110 may include an application processor (AP), a modem processor, a graphics processor (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors.

[0112] The controller can generate operation control signals according to the instruction operation code and timing signal to complete the control of instruction fetching and execution.

[0113] The processor 110 may also be provided with a memory for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. The memory may store instructions or data that the processor 110 has just used or cyclically used. If the processor 110 needs to use the instruction or data again, it may be directly called from the memory. This avoids repeated access, reduces the waiting time of the processor 110, and thus improves the efficiency of the system.

[0114] In some embodiments, the processor 110 may include one or more interfaces. The interface may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a subscriber identity module (SIM) interface, and / or a universal serial bus (USB) interface, etc.

[0115] The USB interface 130 is an interface that complies with the USB standard specification, and specifically can be a Mini USB interface, a Micro USB interface, a USB Type C interface, etc. The USB interface 130 can be used to connect a charger to charge the electronic device 100, and can also be used to transfer data between the electronic device 100 and a peripheral device. It can also be used to connect headphones to play audio through the headphones. The interface can also be used to connect other electronic devices, such as AR devices, etc.

[0116] It is understandable that the interface connection relationship between the modules illustrated in the embodiment of the present invention is only a schematic illustration and does not constitute a structural limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 may also adopt different interface connection methods in the above embodiments, or a combination of multiple interface connection methods.

[0117] The charging management module 140 is used to receive charging input from a charger. The charger may be a wireless charger or a wired charger. In some wired charging embodiments, the charging management module 140 may receive charging input from a wired charger through the USB interface 130. In some wireless charging embodiments, the charging management module 140 may receive wireless charging input through a wireless charging coil of the electronic device 100. While the charging management module 140 is charging the battery 142, it may also power the electronic device through the power management module 141.

[0118] The power management module 141 is used to connect the battery 142, the charging management module 140 and the processor 110. The power management module 141 receives input from the battery 142 and / or the charging management module 140, and supplies power to the processor 110, the internal memory 121, the display screen 194, the camera 193, and the wireless communication module 160. The power management module 141 can also be used to monitor parameters such as battery capacity, battery cycle number, battery health status (leakage, impedance), etc. In some other embodiments, the power management module 141 can also be set in the processor 110. In other embodiments, the power management module 141 and the charging management module 140 can also be set in the same device.

[0119] The wireless communication function of the electronic device 100 can be implemented through the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, the modem processor and the baseband processor.

[0120] Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in electronic device 100 can be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve the utilization of antennas. For example, antenna 1 can be reused as a diversity antenna for a wireless local area network. In some other embodiments, the antenna can be used in combination with a tuning switch.

[0121] The mobile communication module 150 can provide solutions for wireless communications including 2G / 3G / 4G / 5G, etc., applied to the electronic device 100. The mobile communication module 150 may include at least one filter, a switch, a power amplifier, a low noise amplifier (LNA), etc. The mobile communication module 150 can receive electromagnetic waves from the antenna 1, and filter, amplify, and process the received electromagnetic waves, and transmit them to the modulation and demodulation processor for demodulation. The mobile communication module 150 can also amplify the signal modulated by the modulation and demodulation processor, and convert it into electromagnetic waves for radiation through the antenna 1. In some embodiments, at least some of the functional modules of the mobile communication module 150 can be set in the processor 110. In some embodiments, at least some of the functional modules of the mobile communication module 150 can be set in the same device as at least some of the modules of the processor 110.

[0122] The modem processor may include a modulator and a demodulator. Among them, the modulator is used to modulate the low-frequency baseband signal to be sent into a medium-high frequency signal. The demodulator is used to demodulate the received electromagnetic wave signal into a low-frequency baseband signal. The demodulator then transmits the demodulated low-frequency baseband signal to the baseband processor for processing. After the low-frequency baseband signal is processed by the baseband processor, it is passed to the application processor. The application processor outputs a sound signal through an audio device (not limited to a speaker 170A, a receiver 170B, etc.), or displays an image or video through a display screen 194. In some embodiments, the modem processor may be an independent device. In other embodiments, the modem processor may be independent of the processor 110 and be set in the same device as the mobile communication module 150 or other functional modules.

[0123] The wireless communication module 160 can provide wireless communication solutions including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR), etc., which are applied to the electronic device 100. The wireless communication module 160 can be one or more devices integrating at least one communication processing module. The wireless communication module 160 receives electromagnetic waves via the antenna 2, modulates the frequency of the electromagnetic wave signal and performs filtering, and sends the processed signal to the processor 110. The wireless communication module 160 can also receive the signal to be sent from the processor 110, modulate the frequency of it, amplify it, and convert it into electromagnetic waves for radiation through the antenna 2.

[0124] In some embodiments, the antenna 1 of the electronic device 100 is coupled to the mobile communication module 150, and the antenna 2 is coupled to the wireless communication module 160, so that the electronic device 100 can communicate with the network and other devices through wireless communication technology. The wireless communication technology may include global system for mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), wideband code division multiple access (WCDMA), time-division code division multiple access (TD-SCDMA), long term evolution (LTE), BT, GNSS, WLAN, NFC, FM, and / or IR technology. The GNSS may include a global positioning system (GPS), a global navigation satellite system (GLONASS), a Beidou navigation satellite system (BDS), a quasi-zenith satellite system (QZSS) and / or a satellite based augmentation system (SBAS).

[0125] The electronic device 100 implements the display function through a GPU, a display screen 194, and an application processor. The GPU is a microprocessor for image processing, which connects the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor 110 may include one or more GPUs that execute program instructions to generate or change display information.

[0126] The display screen 194 is used to display images, videos, etc. The display screen 194 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode or an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), Miniled, MicroLed, Micro-oLed, a quantum dot light-emitting diode (QLED), etc. In some embodiments, the electronic device 100 may include 1 or N display screens 194, where N is a positive integer greater than 1.

[0127] The electronic device 100 can realize the shooting function through ISP, camera 193, video codec, GPU, display screen 194 and application processor.

[0128] ISP is used to process the data fed back by camera 193. For example, when taking a photo, the shutter is opened, and the light is transmitted to the camera photosensitive element through the lens. The light signal is converted into an electrical signal, and the camera photosensitive element transmits the electrical signal to ISP for processing and converts it into an image visible to the naked eye. ISP can also perform algorithm optimization on the noise, brightness, and skin color of the image. ISP can also optimize the exposure, color temperature and other parameters of the shooting scene. In some embodiments, ISP can be set in camera 193.

[0129] The camera 193 is used to capture still images or videos. The object generates an optical image through the lens and projects it onto the photosensitive element. The photosensitive element can be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. The photosensitive element converts the optical signal into an electrical signal, and then passes the electrical signal to the ISP to be converted into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. The DSP converts the digital image signal into an image signal in a standard RGB, YUV or other format. In some embodiments, the electronic device 100 may include 1 or N cameras 193, where N is a positive integer greater than 1.

[0130] The digital signal processor is used to process digital signals, and can process not only digital image signals but also other digital signals. For example, when the electronic device 100 is selecting a frequency point, the digital signal processor is used to perform Fourier transform on the frequency point energy.

[0131] Video codecs are used to compress or decompress digital videos. The electronic device 100 may support one or more video codecs. Thus, the electronic device 100 may play or record videos in a variety of coding formats, such as moving picture experts group (MPEG) 1, MPEG2, MPEG3, MPEG4, etc.

[0132] NPU is a neural network (NN) computing processor. By drawing on the structure of biological neural networks, such as the transmission mode between neurons in the human brain, it can quickly process input information and can also continuously self-learn. Through NPU, applications such as intelligent cognition of electronic device 100 can be realized, such as image recognition, face recognition, voice recognition, text understanding, etc.

[0133] The external memory interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 100. The external memory card communicates with the processor 110 through the external memory interface 120 to implement a data storage function, such as storing music, video and other files in the external memory card.

[0134] The internal memory 121 can be used to store computer executable program codes, which include instructions. The internal memory 121 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc. The data storage area may store data created during the use of the electronic device 100 (such as audio data, a phone book, etc.), etc. In addition, the internal memory 121 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), etc. The processor 110 executes various functional applications and data processing of the electronic device 100 by running instructions stored in the internal memory 121, and / or instructions stored in a memory provided in the processor.

[0135] The electronic device 100 can implement audio functions such as music playing and recording through the audio module 170, the speaker 170A, the receiver 170B, the microphone 170C, the headphone jack 170D, and the application processor.

[0136] The audio module 170 is used to convert digital audio information into analog audio signal output, and is also used to convert analog audio input into digital audio signals. The audio module 170 can also be used to encode and decode audio signals. In some embodiments, the audio module 170 can be arranged in the processor 110, or some functional modules of the audio module 170 can be arranged in the processor 110.

[0137] The speaker 170A, also called a "speaker", is used to convert an audio electrical signal into a sound signal. The electronic device 100 can listen to music or listen to a hands-free call through the speaker 170A.

[0138] The receiver 170B, also called a "earpiece", is used to convert audio electrical signals into sound signals. When the electronic device 100 receives a call or voice message, the voice can be received by placing the receiver 170B close to the human ear.

[0139] Microphone 170C, also called "microphone" or "microphone", is used to convert sound signals into electrical signals. When making a call or sending a voice message, the user can speak by putting their mouth close to microphone 170C to input the sound signal into microphone 170C. The electronic device 100 can be provided with at least one microphone 170C. In other embodiments, the electronic device 100 can be provided with two microphones 170C, which can not only collect sound signals but also realize noise reduction function. In other embodiments, the electronic device 100 can also be provided with three, four or more microphones 170C to collect sound signals, reduce noise, identify the sound source, realize directional recording function, etc.

[0140] The earphone interface 170D is used to connect a wired earphone and can be a USB interface 130 or a 3.5 mm open mobile terminal platform (OMTP) standard interface or a cellular telecommunications industry association of the USA (CTIA) standard interface.

[0141] The key 190 includes a power key, a volume key, etc. The key 190 may be a mechanical key or a touch key. The electronic device 100 may receive key input and generate key signal input related to user settings and function control of the electronic device 100.

[0142] Motor 191 can generate vibration prompts. Motor 191 can be used for incoming call vibration prompts, and can also be used for touch vibration feedback. For example, touch operations acting on different applications (such as taking pictures, audio playback, etc.) can correspond to different vibration feedback effects. For touch operations acting on different areas of the display screen 194, motor 191 can also correspond to different vibration feedback effects. Different application scenarios (for example: time reminders, receiving messages, alarm clocks, games, etc.) can also correspond to different vibration feedback effects. The touch vibration feedback effect can also support customization.

[0143] Indicator 192 may be an indicator light, which may be used to indicate charging status, power changes, messages, missed calls, notifications, etc.

[0144] The SIM card interface 195 is used to connect a SIM card. The SIM card can be connected to and separated from the electronic device 100 by inserting it into the SIM card interface 195 or pulling it out from the SIM card interface 195. The electronic device 100 can support 1 or N SIM card interfaces, where N is a positive integer greater than 1. The SIM card interface 195 can support Nano SIM cards, Micro SIM cards, SIM cards, and the like. Multiple cards can be inserted into the same SIM card interface 195 at the same time. The types of the multiple cards can be the same or different. The SIM card interface 195 can also be compatible with different types of SIM cards. The SIM card interface 195 can also be compatible with external memory cards. The electronic device 100 interacts with the network through the SIM card to implement functions such as calls and data communications. In some embodiments, the electronic device 100 uses an eSIM, i.e., an embedded SIM card. The eSIM card can be embedded in the electronic device 100 and cannot be separated from the electronic device 100.

[0145] The software system of the electronic device 100 may adopt a layered architecture, an event-driven architecture, a micro-core architecture, a micro-service architecture, or a cloud architecture. In the embodiment of the present invention, the Android system of the layered architecture is taken as an example to exemplify the software structure of the electronic device 100.

[0146] Fig. 9 1 is a software structure block diagram of the electronic device 100 according to an embodiment of the present invention.

[0147] The layered architecture divides the software into several layers, each with clear roles and division of labor. The layers communicate with each other through software interfaces. In some embodiments, the Android system is divided into four layers, from top to bottom: the application layer, the application framework layer, the Android runtime and system library, and the kernel layer.

[0148] The application layer can include a series of application packages.

[0149] like Fig. 9 As shown, the application package may include applications such as camera, gallery, calendar, call, map, navigation, WLAN, Bluetooth, music, video, short message, etc.

[0150] The application framework layer provides an application programming interface (API) and a programming framework for the applications in the application layer. The application framework layer includes some predefined functions.

[0151] like Fig. 9 As shown, the application framework layer may include a window manager, a content provider, a view system, a phone manager, a resource manager, a notification manager, and the like.

[0152] The window manager is used to manage window programs. The window manager can obtain the display screen size, determine whether there is a status bar, lock the screen, capture the screen, etc.

[0153] Content providers are used to store and retrieve data and make it accessible to applications. The data may include videos, images, audio, calls made and received, browsing history and bookmarks, phone books, etc.

[0154] The view system includes visual controls, such as controls for displaying text, controls for displaying images, etc. The view system can be used to build applications. A display interface can be composed of one or more views. For example, a display interface including a text notification icon can include a view for displaying text and a view for displaying images.

[0155] The phone manager is used to provide communication functions of the electronic device 100, such as management of call status (including connecting, hanging up, etc.).

[0156] The resource manager provides various resources for applications, such as localized strings, icons, images, layout files, video files, and so on.

[0157] The notification manager enables applications to display notification information in the status bar. It can be used to convey notification-type messages and can disappear automatically after a short stay without user interaction. For example, the notification manager is used to notify download completion, message reminders, etc. The notification manager can also be a notification that appears in the system top status bar in the form of a chart or scroll bar text, such as notifications of applications running in the background, or a notification that appears on the screen in the form of a dialog window. For example, a text message is displayed in the status bar, a prompt sound is emitted, an electronic device vibrates, an indicator light flashes, etc.

[0158] Android Runtime includes core libraries and virtual machines. Android runtime is responsible for scheduling and management of the Android system.

[0159] The core library consists of two parts: one is the function that needs to be called by the Java language, and the other is the Android core library.

[0160] The application layer and the application framework layer run in a virtual machine. The virtual machine executes the Java files of the application layer and the application framework layer as binary files. The virtual machine is used to perform functions such as object life cycle management, stack management, thread management, security and exception management, and garbage collection.

[0161] The system library may include multiple functional modules, such as surface manager, media library, 3D graphics processing library (such as OpenGL ES), 2D graphics engine (such as SGL), etc.

[0162] The surface manager is used to manage the display subsystem and provide the fusion of 2D and 3D layers for multiple applications.

[0163] The media library supports playback and recording of a variety of commonly used audio and video formats, as well as static image files, etc. The media library can support a variety of audio and video encoding formats, such as: MPEG4, H.264, MP3, AAC, AMR, JPG, PNG, etc.

[0164] The 3D graphics processing library is used to implement 3D graphics drawing, image rendering, compositing, and layer processing.

[0165] A 2D graphics engine is a drawing engine for 2D drawings.

[0166] The kernel layer is the layer between hardware and software. The kernel layer contains at least display driver, camera driver, audio driver, and sensor driver.

[0167] The following is an illustrative description of the workflow of the software and hardware of the electronic device 100 in conjunction with capturing a photo scene.

[0168] When the touch sensor 180K receives a touch operation, the corresponding hardware interrupt is sent to the kernel layer. The kernel layer processes the touch operation into a raw input event (including touch coordinates, timestamp of the touch operation, and other information). The raw input event is stored in the kernel layer. The application framework layer obtains the raw input event from the kernel layer and identifies the control corresponding to the input event. For example, if the touch operation is a touch single-click operation and the control corresponding to the single-click operation is the control of the camera application icon, the camera application calls the interface of the application framework layer to start the camera application, and then starts the camera driver by calling the kernel layer to capture static images or videos through the camera 193.

[0169] The embodiment of the present application provides an electronic device, which may be a terminal device or a circuit device built into the terminal device. The electronic device may be used to execute the functions / steps in the above method embodiment.

[0170] An embodiment of the present application provides a computer-readable storage medium, in which instructions are stored. When the instructions are executed on a terminal device, the terminal device executes the functions / steps in the above method embodiment.

[0171] The embodiment of the present application also provides a computer program product comprising instructions, and when the computer program product is run on a computer or any at least one processor, the computer executes the functions / steps in the above method embodiment.

[0172] In the embodiments of the present application, "at least one" refers to one or more, and "plurality" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and subsequent associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0173] Those of ordinary skill in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented in a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0174] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0175] In several embodiments provided in the present application, any function can be stored in a computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for enabling an electronic device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0176] The above is only a specific implementation of the present application. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. The protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A group simulation model parameter calibration method, characterized in that: The method comprises: Extracting a feature set from the first reference data set, the feature set comprising individual dynamic group features and static scene features; Performing offline calibration on the group simulation model using the first reference data set to obtain a model parameter set; According to the feature set and the model parameter set, a first relationship is obtained, where the first relationship is an optimal mapping relationship between the model parameters in the model parameter set and the dynamic group feature and the static scene feature; During the online calibration process of the group simulation model, the parameters of the group simulation model are calibrated according to the first relationship, static scene characteristics of the current simulation, and dynamic group characteristics.

2. The method according to claim 1, characterized in that The offline calibration of the group simulation model by using the first reference data set to obtain a model parameter set includes: Slice the data of individuals in the first reference data set according to the first numerical frame to obtain a second reference data set; The group simulation model is offline calibrated according to the second reference data set and an offline calibration algorithm to obtain a model parameter set.

3. The method according to claim 1 or 2, characterized in that: The amount of data in the first reference data set is less than a first threshold, and obtaining the first relationship according to the feature set and the model parameter set includes: According to the feature set and the model parameter set, the dynamic group feature, the static scene feature and the model parameter are calculated by linear transformation to obtain an objective function; The objective function is optimized and solved by the least square method to obtain the first relationship.

4. The method according to claim 1 or 2, characterized in that: The data volume of the first reference data set is greater than or equal to a first threshold, and obtaining the first relationship according to the feature set and the model parameter set includes: According to the feature set and the model parameter set, a mapping relationship among the dynamic group features, the static scene features and the model parameters is learned through a convolutional neural network method to obtain a first relationship.

5. The method according to claim 4, characterized in that The learning of the mapping relationship between the dynamic group features, the static scene features and the model parameters by means of a convolutional neural network includes: Using the dynamic group features and the static scene features as inputs of the convolutional neural network, and using the model parameters as outputs of the convolutional neural network; The mapping relationship between the input and the output is learned through the convolutional layer, the pooling layer and the fully connected layer in the convolutional neural network.

6. The method according to claim 2, characterized in that The offline calibration algorithm is a stochastic optimization algorithm.

7. The method according to claim 3, characterized in that The random optimization algorithm includes a genetic algorithm, an ant colony algorithm or a simulated annealing algorithm.

8. The method according to any one of claims 1 to 7, characterized in that The first reference data set includes: location trajectory information of each individual in the group and layout information of the scene where the group is located.

9. The method according to any one of claims 1 to 8, characterized in that The dynamic group characteristics include: speed, movement direction, relative distance to surrounding neighbors, and relative speed, or any combination thereof.

10. The method according to any one of claims 1 to 9, characterized in that The static scene features include: one or any combination of the passable area within the individual's forward field of vision, the passable area within the individual's lateral field of vision, and the distance between the individual and surrounding static obstacles.

11. The method according to claim 2, characterized in that The first numerical frame includes 100 frames.

12. An electronic device, characterized in that: The electronic device comprises a processor and a memory, wherein the memory is used to store a computer program, and the computer program comprises program instructions. When the processor runs the program instructions, the electronic device executes the steps of the method as claimed in any one of claims 1 to 11.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program request is executed by a computer, the computer is enabled to execute the method according to any one of claims 1 to 11.

Images