Method and device for obtaining voice broadcast distance

Abstract

Disclosed is a method and device for obtaining a voice broadcast distance. By obtaining multiple candidate voice broadcast distances, an evaluation index corresponding to each candidate voice broadcast distance is determined, the evaluation index is obtained by simulating a cockpit operation risk scenario, the evaluation index includes at least one of driving behavior data and driver eye movement data, and the evaluation score corresponding to each candidate voice broadcast distance is determined according to the evaluation index, and the target voice broadcast distance is determined among the multiple candidate voice broadcast distances according to the evaluation score. In this way, the accuracy of the voice broadcast distance can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and device for acquiring a voice broadcast distance. Background Art

[0002] With the rapid development of society and the continuous advancement of science and technology, cars have become an indispensable means of transportation in people's daily lives. However, with the continuous increase in the number of cars, road traffic safety issues are becoming increasingly serious. In order to improve driving safety and reduce traffic accidents, vehicle voice warning prompt systems have emerged.

[0003] Reminding drivers through voice can enable them to understand road traffic conditions in a timely and accurate manner during driving and enhance accident warning awareness. However, different voice broadcast distances will produce different warning effects on drivers. When the voice broadcast distance is too large, the effect of voice reminders will be reduced. When the voice reminder distance is too small, the time left for drivers to receive information and complete reaction operations is too short, which is prone to traffic accidents. The voice reminder distance of the existing technology is not accurate enough. Summary of the invention

[0004] In view of this, an object of an embodiment of the present invention is to provide a method and device for obtaining a voice broadcast distance, which can improve the accuracy of the voice broadcast distance.

[0005] In a first aspect, an embodiment of the present invention provides a method for obtaining a voice broadcast distance, the method comprising:

[0006] Get multiple candidate voice broadcast distances;

[0007] Determine an evaluation index corresponding to each of the candidate voice broadcast distances, wherein the evaluation index is obtained by simulating a cockpit operation risk scenario, and the evaluation index includes at least one of driving behavior data and driver eye movement data;

[0008] Determine the evaluation score corresponding to each of the candidate voice broadcast distances according to the evaluation index; and

[0009] A target voice broadcast distance is determined from among the multiple candidate voice broadcast distances according to the evaluation score.

[0010] In some embodiments, obtaining multiple candidate voice broadcast distances includes:

[0011] Determine safe warning distances; and

[0012] Acquire multiple candidate voice broadcast distances according to the safety warning distance;

[0013] The safety warning distance is the sum of the parking sight distance, the safety spacing and the information delay distance. The parking sight distance is calculated by the following formula:

[0014]

[0015] Among them, S T is the stopping sight distance, v is the speed limit, t is the sum of perception time and reaction time, is the adhesion coefficient, is the sum of the sliding friction coefficient and the ramp coefficient.

[0016] In some embodiments, the risk scenario includes at least one of a pedestrian crossing conflict scenario, a pedestrian-vehicle conflict scenario in a blind spot, and a roadside vehicle suddenly starting conflict scenario.

[0017] In some embodiments, determining the evaluation index corresponding to each candidate voice broadcast distance includes:

[0018] Acquiring configuration information, the configuration information including at least one of a scene length, a distance between scenes, a number and level of roads, a number of intersections, a size of a traffic flow around a driving vehicle and a speed of the traffic flow, a speed of pedestrians, and a location of a conflict point;

[0019] Constructing the risk scenario according to the configuration information by simulation software; and

[0020] The risk scenario is run in a simulated cockpit to obtain evaluation indicators corresponding to the candidate voice broadcast distances.

[0021] In some embodiments, the step of running the risk scenario in a simulated cockpit to obtain an evaluation index corresponding to each of the candidate voice broadcast distances includes:

[0022] Running the risk scenarios through a simulated cockpit;

[0023] Obtaining the position of the simulated cockpit in the risk scenario;

[0024] In response to the distance between the position of the simulated cockpit in the risk scenario and the position of the conflict point being a predetermined distance, triggering a corresponding conflict scenario;

[0025] In response to the distance between the position of the simulated cockpit in the risk scenario and the position of the conflict point being a candidate voice broadcast distance, triggering a voice broadcast;

[0026] Get the position of the brake pedal in the simulated cockpit when it is triggered for the first time after the voice broadcast is triggered;

[0027] An evaluation index between the position of the brake pedal of the simulated cockpit when it is first triggered and the position of the conflict point is obtained.

[0028] In some embodiments, the driving behavior data includes at least one of acceleration, steering wheel angle change rate, and brake pedal force change rate, and the driver's eye movement data includes at least one of gaze duration, number of gazes, scan frequency, and pupil diameter.

[0029] In some embodiments, determining the evaluation score corresponding to each of the candidate voice broadcast distances according to the evaluation index includes:

[0030] Determine the original matrix according to the candidate voice broadcast distances and the corresponding evaluation indicators;

[0031] Determine the weight corresponding to each evaluation index according to the original matrix; and

[0032] The evaluation scores corresponding to the voice broadcast distances of the candidates are calculated according to the weights corresponding to the evaluation indicators.

[0033] In some embodiments, the original matrix is ​​an n*m matrix, where n is the number of candidate voice broadcast distances, and m is the number of evaluation indicators.

[0034] In some embodiments, determining the weights corresponding to the evaluation indicators according to the original matrix includes:

[0035] Performing normalization processing on the original matrix to obtain a normalized matrix;

[0036] Performing normalization processing on the standardized matrix to obtain a normalized matrix;

[0037] Determining the entropy value corresponding to each evaluation index according to the normalized matrix;

[0038] Calculating the differentiation coefficient corresponding to each evaluation index according to the entropy value; and

[0039] The weight corresponding to each evaluation index is calculated according to the differentiation coefficient.

[0040] In some embodiments, the normalizing the original matrix to obtain a normalized matrix comprises:

[0041] Determine the type of each evaluation indicator, the type includes a positive evaluation indicator and a negative evaluation indicator, the positive evaluation indicator is a value proportional to the effect, and the negative evaluation indicator is a value inversely proportional to the effect; and

[0042] The original matrix is ​​standardized according to the types of the evaluation indicators to obtain a standardized matrix.

[0043] In some embodiments, the positive evaluation index is standardized by the following formula:

[0044]

[0045] The negative evaluation index is standardized by the following formula:

[0046]

[0047] Among them, y ij represents the element in the i-th row and j-th column of the normalized matrix, x ij represents the element in the i-th row and j-th column of the original matrix, x j,min represents the minimum value of the elements in the jth column of the original matrix, x j,max Represents the maximum value of the elements in the j-th column of the original matrix.

[0048] In some embodiments, the normalized matrix is ​​calculated by the following formula:

[0049]

[0050] Among them, P ij represents the element in the i-th row and j-th column of the normalized matrix, y ij represents the element in the i-th row and j-th column of the normalized matrix, x ij represents the element in the i-th row and j-th column of the original matrix, and n is the number of candidate voice broadcast distances.

[0051] In some embodiments, the entropy value is calculated by the following formula:

[0052]

[0053] Among them, e j is the entropy value corresponding to the jth evaluation index, P ij represents the element in the i-th row and j-th column of the normalized matrix, n is the number of candidate voice broadcast distances.

[0054] In some embodiments, the differentiation coefficient is calculated by the following formula:

[0055] g j =1-e j

[0056] Among them, g j is the differentiation coefficient corresponding to the jth evaluation index, e j is the entropy value corresponding to the jth evaluation index.

[0057] In some embodiments, the weight is calculated by the following formula:

[0058]

[0059] Among them, W j is the weight corresponding to the jth evaluation index, g j is the differentiation coefficient corresponding to the jth evaluation index, and m is the number of evaluation indicators.

[0060] In some embodiments, the evaluation score is calculated using the following formula:

[0061]

[0062] Among them, F i is the evaluation score corresponding to the i-th candidate voice broadcast distance, W j is the weight corresponding to the jth evaluation index, P ij is the element in the i-th row and j-th column of the normalized matrix, and m is the number of evaluation indicators.

[0063] In some embodiments, determining the target voice broadcast distance from the plurality of candidate voice broadcast distances according to the evaluation score is specifically:

[0064] The candidate voice broadcast distance with the largest evaluation score is determined as the target voice broadcast distance.

[0065] In a second aspect, an embodiment of the present invention provides a device for acquiring a voice broadcast distance, the device comprising:

[0066] A candidate distance acquisition unit, used to acquire multiple candidate voice broadcast distances;

[0067] An evaluation index acquisition unit, used to determine an evaluation index corresponding to each of the candidate voice broadcast distances, wherein the evaluation index is acquired by simulating a cockpit operation risk scenario, and the evaluation index includes at least one of driving behavior data and driver eye movement data;

[0068] An evaluation score acquisition unit, used to determine the evaluation score corresponding to each of the candidate voice broadcast distances according to the evaluation index; and

[0069] The broadcast distance acquisition unit is used to determine a target voice broadcast distance from the plurality of candidate voice broadcast distances according to the evaluation score.

[0070] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method described in the first aspect.

[0071] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer program instructions, wherein the computer program instructions implement the method described in the first aspect when executed by a processor.

[0072] The technical solution of the embodiment of the present invention obtains multiple candidate voice broadcast distances, determines the evaluation index corresponding to each candidate voice broadcast distance, the evaluation index is obtained by simulating the cockpit operation risk scenario, the evaluation index includes at least one of driving behavior data and driver eye movement data, determines the evaluation score corresponding to each candidate voice broadcast distance according to the evaluation index, and determines the target voice broadcast distance among the multiple candidate voice broadcast distances according to the evaluation score. In this way, the accuracy of the voice broadcast distance can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] The above and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

[0074] Figure 1 is a schematic diagram of a data processing system according to an embodiment of the present invention;

[0075] Figure 2 is a flow chart of a method for obtaining a voice broadcast distance according to an embodiment of the present invention;

[0076] Figure 3 is a flow chart of determining the evaluation index corresponding to each candidate voice broadcast distance according to an embodiment of the present invention;

[0077] Figure 4 is a schematic diagram of a first risk scenario of an embodiment of the present invention;

[0078] Figure 5 is a schematic diagram of a second risk scenario of an embodiment of the present invention;

[0079] Figure 6 is a schematic diagram of a third risk scenario of an embodiment of the present invention;

[0080] Figure 7 is a flow chart of obtaining evaluation indicators corresponding to the broadcast distances of each candidate voice through a simulated cockpit according to an embodiment of the present invention;

[0081] Figure 8 is a schematic diagram of evaluation indicators of an embodiment of the present invention;

[0082] Fig. 9 is a flow chart of obtaining evaluation scores according to an embodiment of the present invention;

[0083] Fig.10 is a flow chart of determining weights according to an embodiment of the present invention;

[0084] Fig.11 is a schematic diagram of a device for acquiring a voice broadcast distance according to an embodiment of the present invention;

[0085] Fig.12 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0086] The present invention is described below based on embodiments, but the present invention is not limited to these embodiments. In the detailed description of the present invention below, some specific details are described in detail. It is possible for a person skilled in the art to fully understand the present invention without the description of these details. In order to avoid confusing the essence of the present invention, known methods, processes, flows, components and circuits are not described in detail.

[0087] In addition, persons of ordinary skill in the art will appreciate that the drawings provided herein are for illustration purposes and are not necessarily drawn to scale.

[0088] Unless the context clearly requires otherwise, the words "include", "comprising" and the like throughout this application should be interpreted as including rather than exclusive or exhaustive; that is, as meaning "including but not limited to".

[0089] In the description of the present invention, it should be understood that the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0090] Figure 1 Schematic diagram of a data processing system according to an embodiment of the present invention. Figure 1 As shown, the data processing system of the embodiment of the present invention includes a simulated cockpit 1, an eye tracker 2 and a data processing device 3.

[0091] The simulated cockpit 1 is a simulated driving environment for simulated driving training of vehicles such as cars. The simulated cockpit is equipped with various instruments, operating components (such as steering wheels, brake pedals, accelerator pedals), buttons, etc. of the car to simulate the operating environment of the real cockpit. In the simulated cockpit, people can simulate the real driving process by operating various devices to obtain the emergency response ability of the driver. At the same time, the simulated cockpit can also provide various simulation scenes, such as different weather conditions, traffic conditions, etc., to provide various complex driving environments.

[0092] Eye tracker 2 is a device that can track and measure eye position and eye movement information.

[0093] The data processing device 3 can be any device with data processing capability, such as a computer.

[0094] The embodiment of the present invention constructs a simulation environment of a risk scenario through a data processing device, and runs the simulation environment of the risk scenario through a simulation cockpit, and an experimenter operates the simulation cockpit to drive a vehicle in the simulation environment of the risk scenario, collects driving behavior data through the simulation cockpit, and collects eye movement data through an eye tracker, and uses the driving behavior data and the eye movement data as evaluation indicators. The evaluation scores at different candidate voice broadcast distances are calculated through the evaluation indicators, and a voice broadcast distance with better effect is selected from multiple candidate voice broadcast distances according to the evaluation scores to improve the accuracy of the voice broadcast distance.

[0095] Figure 2 It is a flow chart of a method for acquiring a voice broadcast distance according to an embodiment of the present invention. Figure 2 The method for obtaining the voice broadcast distance shown is applicable to a data processing device, and specifically comprises the following steps:

[0096] Step S100: Obtain multiple candidate voice broadcast distances.

[0097] In this embodiment, the data processing device determines a safety warning distance, and acquires a plurality of candidate voice broadcast distances according to the safety warning distance.

[0098] The safety warning distance is the sum of the parking sight distance, the safety spacing and the information delay distance. That is, the calculation formula of the safety warning distance is:

[0099] S=S T +S1+S2

[0100] Among them, S T is the parking sight distance, S1 is the safety distance, and S2 is the information delay distance. Among them, the safety distance S1 and the information delay distance S2 are preset values.

[0101] Furthermore, the stopping sight distance is calculated by the following formula:

[0102]

[0103] Among them, S T is the stopping sight distance, v is the speed limit, t is the sum of perception time and reaction time, is the adhesion coefficient, is the sum of the sliding friction coefficient and the ramp coefficient.

[0104] Among them, the speed limit v, the sum of perception time and reaction time t, and the adhesion coefficient The sum of the sliding friction coefficient and the slope coefficient These are preset values.

[0105] After the data processing device obtains the safety warning distance, it selects multiple candidate voice broadcast distances near the safety warning distance. For example, assuming that the safety warning distance is 100 meters, multiple candidate voice broadcast distances can be selected between 50-150 meters. Therefore, by using the safety warning distance as a theoretical value and selecting multiple candidate voice broadcast distances near the theoretical value, the range of candidate voice broadcast distances can be reduced without affecting the accuracy, thereby improving data processing efficiency.

[0106] Step S200: Determine the evaluation index corresponding to each candidate voice broadcast distance.

[0107] In this embodiment, the evaluation index is obtained by simulating a cockpit operation risk scenario, and the evaluation index includes at least one of driving behavior data and driver eye movement data.

[0108] Figure 3 1 is a flow chart of determining the evaluation index corresponding to each candidate voice broadcast distance according to an embodiment of the present invention. Figure 3 As shown, the evaluation index corresponding to each candidate voice broadcast distance is determined to include:

[0109] Step S210: Obtain configuration information.

[0110] In this embodiment, the data processing device displays a configuration interface to the user through the simulation software, and receives the configuration information of the risk scenario input by the user through the configuration interface. The configuration information includes at least one of the scene length, the distance between scenes, the number and level of roads, the number of intersections, the size of the traffic flow around the driving vehicle and the speed of the traffic flow, the speed of pedestrians, and the location of the conflict point. It should be noted that the configuration information can have one risk scene, or multiple risk scenes can be set at the same time. At the same time, the distance between the above-mentioned scenes refers to the distance between two adjacent risk scenes when multiple risk scenes are set. Among them, the speed of the traffic flow should be close to the speed of the simulated driving vehicle, and the size of the traffic flow should not be too large to cause road congestion, and should not be too small to cause the simulated driving vehicle to exceed the speed limit.

[0111] Step S220: construct the risk scenario according to the configuration information through simulation software.

[0112] In this embodiment, the data processing device constructs the risk scenario according to the configuration information input by the user through simulation software.

[0113] In some embodiments, the simulation software can be implemented through SCANeR studio, which is a dedicated automotive and traffic simulation solution for testing and driving ADAS (Advanced Driving Assistance System), autonomous vehicles and headlight use cases. SCANeR studio provides all the tools and models needed to build a virtual environment, road environment, vehicle dynamics, traffic, sensors, real / virtual drivers, headlights, weather conditions and scenario scripts.

[0114] In some embodiments, the risk scenario includes at least one of a pedestrian crossing conflict scenario, a pedestrian-vehicle conflict scenario in a blind spot, and a roadside vehicle suddenly starting conflict scenario.

[0115] Figure 4 is a schematic diagram of a first risk scenario of an embodiment of the present invention. Figure 4 The first risk scenario shown is a pedestrian crossing conflict scenario, in which a vehicle C1 and a pedestrian D1 are included. The vehicle C1 turns right from the illustrated position, and the pedestrian D1 goes across the road from the illustrated position. The vehicle turns right at the intersection and there is a conflict point E1 with the pedestrian D1 crossing the street.

[0116] Figure 5 is a schematic diagram of a second risk scenario of an embodiment of the present invention. Figure 5 The second risk scenario shown is a vehicle-pedestrian conflict scenario in a blind spot. In the vehicle-pedestrian conflict scenario in a blind spot, there are vehicles C2, C3 and pedestrian D2. Vehicles C2 and C3 are both moving forward, and pedestrian D2 is moving from the illustrated position to the other side of the road. Since vehicle C3 blocks the line of sight of vehicle C2, a visual blind spot is formed, and there is a conflict point E2 between vehicle C2 and pedestrian D2.

[0117] Figure 6 is a schematic diagram of a third risk scenario of an embodiment of the present invention. Figure 6 The third risk scenario shown is a roadside vehicle suddenly starting conflict scenario. In the roadside vehicle suddenly starting conflict scenario, vehicles C4 and C5 are included. The roadside vehicle C5 suddenly starts and there is a conflict point E3 with the straight-moving vehicle C4.

[0118] Step S230: Run the risk scenario in a simulated cockpit to obtain evaluation indicators corresponding to the candidate voice broadcast distances.

[0119] In this embodiment, a candidate voice broadcast distance is selected, and the risk scenario is run through the selected candidate voice broadcast distance to obtain the evaluation index of the simulated driving. Then, the next candidate voice broadcast distance is selected, and the corresponding evaluation index is obtained. Thus, each candidate voice broadcast distance is traversed to obtain the corresponding evaluation index.

[0120] Specifically, after setting the risk scenario, the risk scenario is imported into the simulated cockpit, and the experimenter operates the simulated cockpit to complete driving in the risk scenario. At the same time, during the driving process, the voice broadcast is performed at the corresponding position according to the selected candidate voice broadcast distance, and the evaluation index during the driving process is obtained.

[0121] It should be noted that, in order to improve accuracy, before obtaining the evaluation indicators during the driving process, the risk scenario can be preprocessed to eliminate errors caused by configuration errors. The preprocessing can be performed based on the data of the experimenter when operating the simulated cockpit, and the embodiment of the present invention does not limit this.

[0122] Figure 7 This is a flow chart of an embodiment of the present invention for obtaining evaluation indicators corresponding to the distances of each candidate voice broadcast through a simulated cockpit. Figure 7 In the illustrated embodiment, running the risk scenario in a simulated cockpit to obtain the evaluation index corresponding to each candidate voice broadcast distance includes the following steps:

[0123] Step S231: running the risk scenario through a simulated cockpit.

[0124] In this embodiment, after the risk scenario is set, the driver drives the simulated cockpit to perform simulated driving in the risk scenario. At the same time, the driver needs to wear an eye tracker to collect his eye movement data during the simulated driving process.

[0125] Step S232: Obtain the position of the simulated cockpit in the risk scenario.

[0126] In this embodiment, the operation of the risk scenario in the simulated cockpit is actually equivalent to simulating the entire driving process of the driver in the risk scenario, and obtaining the position of the simulated cockpit in the risk scenario in real time.

[0127] Step S233: In response to the distance between the position of the simulated cockpit in the risk scenario and the position of the conflict point being a predetermined distance, triggering a corresponding conflict scenario.

[0128] In this embodiment, a predetermined distance is preset, and the predetermined distance is the distance for triggering the conflict scenario, and the predetermined distance is greater than the candidate voice broadcast distance. The distance between the position of the simulated cockpit in the risk scenario and the conflict point is obtained, and in response to the distance between the position of the simulated cockpit in the risk scenario and the conflict point being the predetermined distance, the corresponding conflict scenario is triggered. The triggering of the conflict scenario is the beginning of the triggering of the conflict scenario. Figure 4 The risk scenario shown in the figure is used as an example to illustrate that the conflict triggering scenario is when pedestrian D1 starts to cross the road. Figure 5The risk scenario shown in the figure is used as an example to illustrate that the conflict triggering scenario is when pedestrian D2 starts to cross the road. Figure 6 The risk scenario shown is used as an example for explanation, and the conflict triggering scenario is that the vehicle C5 starts to move.

[0129] Step S234: In response to the distance between the position of the simulated cockpit in the risk scenario and the conflict point position being a candidate voice broadcast distance, triggering a voice broadcast.

[0130] In this embodiment, after the conflict scenario is triggered, it means that the simulated cockpit detects that a conflict will occur, but a voice broadcast will not be made immediately at this time. In response to the distance between the position of the simulated cockpit in the risk scenario and the conflict point position being a candidate voice broadcast distance, a voice broadcast is triggered. The voice broadcast is used to prompt that a conflict may occur ahead.

[0131] Step S235, obtaining the position of the brake pedal of the simulated cockpit when it is triggered for the first time after the voice broadcast is triggered.

[0132] In the present embodiment, after the voice broadcast is triggered, the position of the brake pedal of the simulated cockpit when it is triggered for the first time is obtained.

[0133] Step S236: Obtain an evaluation index between the position of the brake pedal of the simulated cockpit when it is first triggered and the position of the conflict point.

[0134] In this embodiment, after the voice broadcast is triggered, when the brake pedal of the simulated cockpit is triggered for the first time, the driving behavior data is collected through the simulated cockpit, and the driver's eye movement data is collected through the eye tracker until the conflict point is reached.

[0135] By executing a candidate voice broadcast distance through the above steps, an evaluation index corresponding to the candidate voice broadcast distance can be obtained. By changing the candidate voice broadcast distance and repeating the above steps, an evaluation index corresponding to each candidate voice broadcast distance can be obtained.

[0136] It should be noted that, in order to improve accuracy, each candidate voice broadcast distance can be realized by multiple drivers, and the final evaluation index is the average value of multiple drivers.

[0137] Figure 8 Schematic diagram of the evaluation index of the embodiment of the present invention. Figure 8 As shown in the figure, candidate warning distances include L1, L2 and L3, and evaluation indicators include acceleration (m / s 2 ), steering wheel rotation angle change rate (° / s), brake pedal force change rate (N / s), fixation duration (ms), fixation number (times), scan frequency (times / s), pupil diameter (mm), Figure 8The values ​​of various evaluation indicators at various candidate warning distances are shown, which are A1-A21 as described in the figure. Among them, acceleration, steering wheel angle change rate and brake pedal force change rate are driving behavior data, and fixation duration, fixation number, scan frequency and pupil diameter are eye movement data.

[0138] Step S300: Determine the evaluation score corresponding to each of the candidate voice broadcast distances according to the evaluation index.

[0139] In this embodiment, after the evaluation index is obtained, the evaluation score corresponding to each candidate voice broadcast distance is determined according to the evaluation index.

[0140] Fig. 9 FIG. 1 is a flowchart of obtaining evaluation scores according to an embodiment of the present invention. Fig. 9 As shown, determining the evaluation score corresponding to each candidate voice broadcast distance according to the evaluation index includes the following steps:

[0141] Step S310: determining an original matrix according to each of the candidate voice broadcast distances and corresponding evaluation indicators.

[0142] In this embodiment, the original matrix is ​​an n*m matrix, where n is the number of candidate voice broadcast distances and m is the number of evaluation indicators. That is, the i-th row of the original matrix represents the evaluation indicators corresponding to the i-th candidate voice broadcast distance, and the j-th column of the original matrix represents the j-th evaluation indicator.

[0143] Furthermore, the original matrix X can be expressed as:

[0144]

[0145] Among them, x ij It represents the element in the i-th row and j-th column of the original matrix, that is, the j-th evaluation index of the i-th candidate voice broadcast distance.

[0146] Step S320: Determine the weight corresponding to each evaluation index according to the original matrix.

[0147] In this embodiment, after the original matrix is ​​obtained, the entropy method is used to assign weights to each evaluation index.

[0148] Specifically, Fig.10 is a flow chart of determining weights according to an embodiment of the present invention. Fig.10 In the illustrated embodiment, determining the weights corresponding to the various evaluation indicators according to the original matrix includes the following steps:

[0149] Step S321: normalize the original matrix to obtain a normalized matrix.

[0150] In this embodiment, the evaluation indexes are standardized. Generally, the evaluation indexes have different types and dimensions and cannot be directly compared. It is necessary to perform dimensionless processing on these data and standardize them before calculation.

[0151] Specifically, obtaining the standardized matrix includes the following steps:

[0152] Step S3211: Determine the type of each evaluation indicator.

[0153] In this embodiment, the types include positive evaluation indicators and negative evaluation indicators. The positive evaluation indicators are indicators whose values ​​are proportional to the effects, that is, the larger the values, the better. The negative evaluation indicators are indicators whose values ​​are inversely proportional to the effects, that is, the smaller the values, the better.

[0154] Step S3222: Standardize the original matrix according to the types of the evaluation indicators to obtain a standardized matrix.

[0155] For positive evaluation indicators, standardization is performed using the following formula:

[0156]

[0157] Among them, y ij represents the element in the i-th row and j-th column of the normalized matrix, x ij represents the element in the i-th row and j-th column of the original matrix, x j,min represents the minimum value of the elements in the jth column of the original matrix, x j,max Represents the maximum value of the elements in the j-th column of the original matrix.

[0158] For negative evaluation indicators, standardization is performed using the following formula:

[0159]

[0160] Among them, y ij represents the element in the i-th row and j-th column of the normalized matrix, x ij represents the element in the i-th row and j-th column of the original matrix, x j,min represents the minimum value of the elements in the jth column of the original matrix, x j,max Represents the maximum value of the elements in the j-th column of the original matrix.

[0161] Thus, each element in the normalized matrix can be obtained. Further, the normalized matrix Y can be expressed as:

[0162]

[0163] Among them, y ijRepresents the element in the i-th row and j-th column of the normalized matrix.

[0164] Step S322: normalize the standardized matrix to obtain a normalized matrix.

[0165] Each element in the normalized matrix is ​​calculated by the following formula:

[0166]

[0167] Among them, P ij represents the element in the i-th row and j-th column of the normalized matrix, y ij represents the element in the i-th row and j-th column of the normalized matrix, x ij represents the element in the i-th row and j-th column of the original matrix, and n is the number of candidate voice broadcast distances.

[0168] Thus, each element in the normalized matrix can be obtained. Further, the normalized matrix P can be expressed as:

[0169]

[0170] Among them, P ij Represents the element in the i-th row and j-th column of the normalized matrix.

[0171] Step S323: Determine the entropy value corresponding to each evaluation index according to the normalized matrix.

[0172] The entropy value is calculated by the following formula:

[0173]

[0174] Among them, e j is the entropy value corresponding to the jth evaluation index, P ij represents the element in the i-th row and j-th column of the normalized matrix, n is the number of candidate voice broadcast distances.

[0175] Step S324: Calculate the differentiation coefficient corresponding to each evaluation index according to the entropy value.

[0176] The differentiation coefficient is calculated by the following formula:

[0177] g j =1-e j

[0178] Among them, g j is the differentiation coefficient corresponding to the jth evaluation index, e j is the entropy value corresponding to the jth evaluation index.

[0179] Step S325: Calculate the weight corresponding to each evaluation index according to the differentiation coefficient.

[0180] The weight is calculated by the following formula:

[0181]

[0182] Among them, W j is the weight corresponding to the jth evaluation index, g j is the differentiation coefficient corresponding to the jth evaluation index, and m is the number of evaluation indicators.

[0183] Step S330: Calculate the evaluation score corresponding to each candidate voice broadcast distance according to the weight corresponding to each evaluation indicator.

[0184] In this embodiment, weighted sum is performed on the elements in the normalized matrix according to the weights to obtain the evaluation score.

[0185] The evaluation score is calculated by the following formula:

[0186]

[0187] Among them, F i is the evaluation score corresponding to the i-th candidate voice broadcast distance, W j is the weight corresponding to the jth evaluation index, P ij is the element in the i-th row and j-th column of the normalized matrix, and m is the number of evaluation indicators.

[0188] Step S400: determining a target voice broadcast distance from among the plurality of candidate voice broadcast distances according to the evaluation score.

[0189] In this embodiment, the candidate voice broadcast distance with the largest evaluation score is determined as the target voice broadcast distance.

[0190] The embodiment of the present invention obtains multiple candidate voice broadcast distances, determines the evaluation index corresponding to each candidate voice broadcast distance, the evaluation index is obtained by simulating the cockpit operation risk scenario, the evaluation index includes at least one of driving behavior data and driver eye movement data, determines the evaluation score corresponding to each candidate voice broadcast distance according to the evaluation index, and determines the target voice broadcast distance among the multiple candidate voice broadcast distances according to the evaluation score. In this way, the accuracy of the voice broadcast distance can be improved.

[0191] Fig.11 Schematic diagram of a device for acquiring a voice broadcast distance according to an embodiment of the present invention. Fig.11In the illustrated embodiment, the device for acquiring the voice broadcast distance includes a candidate distance acquisition unit 101, an evaluation index acquisition unit 102, an evaluation score acquisition unit 103, and a broadcast distance acquisition unit 104. The candidate distance acquisition unit 101 is used to acquire multiple candidate voice broadcast distances. The evaluation index acquisition unit 102 is used to determine the evaluation index corresponding to each of the candidate voice broadcast distances, and the evaluation index is obtained by simulating a cockpit operation risk scenario, and the evaluation index includes at least one of driving behavior data and driver eye movement data. The evaluation score acquisition unit 103 is used to determine the evaluation score corresponding to each of the candidate voice broadcast distances according to the evaluation index. The broadcast distance acquisition unit 104 is used to determine the target voice broadcast distance among the multiple candidate voice broadcast distances according to the evaluation score.

[0192] In some embodiments, the candidate distance acquisition unit includes:

[0193] A safety warning distance acquisition subunit, used to determine the safety warning distance; and

[0194] A candidate voice broadcast distance acquisition subunit is used to acquire multiple candidate voice broadcast distances according to the safety warning distance;

[0195] The safety warning distance is the sum of the parking sight distance, the safety spacing and the information delay distance. The parking sight distance is calculated by the following formula:

[0196]

[0197] Among them, S T is the stopping sight distance, v is the speed limit, t is the sum of perception time and reaction time, is the adhesion coefficient, is the sum of the sliding friction coefficient and the ramp coefficient.

[0198] In some embodiments, the risk scenario includes at least one of a pedestrian crossing conflict scenario, a pedestrian-vehicle conflict scenario in a blind spot, and a roadside vehicle suddenly starting conflict scenario.

[0199] In some embodiments, the evaluation index acquisition unit includes:

[0200] A configuration information acquisition subunit, used to acquire configuration information, wherein the configuration information includes at least one of a scene length, a distance between scenes, the number and level of roads, the number of intersections, the size and speed of traffic flow around the driving vehicle, the speed of pedestrians, and the location of conflict points;

[0201] a risk scenario construction subunit, configured to construct the risk scenario according to the configuration information through simulation software; and

[0202] The evaluation index acquisition subunit is used to run the risk scenario in a simulated cockpit to obtain the evaluation index corresponding to each candidate voice broadcast distance.

[0203] In some embodiments, the evaluation index acquisition subunit includes:

[0204] A risk scenario running module, used to run the risk scenario through a simulated cockpit;

[0205] A simulated cockpit position acquisition module, used to acquire the position of the simulated cockpit in the risk scenario;

[0206] a conflict scenario triggering module, configured to trigger a corresponding conflict scenario in response to a predetermined distance between the position of the simulated cockpit in the risk scenario and the position of the conflict point;

[0207] A voice broadcast triggering module, configured to trigger a voice broadcast in response to the distance between the position of the simulated cockpit in the risk scenario and the position of the conflict point being a candidate voice broadcast distance;

[0208] A brake pedal trigger detection module is used to obtain the position of the brake pedal of the simulated cockpit when it is triggered for the first time after the trigger voice broadcast;

[0209] The evaluation index acquisition module is used to obtain the evaluation index between the position of the brake pedal of the simulated cockpit when it is first triggered and the position of the conflict point.

[0210] In some embodiments, the driving behavior data includes at least one of acceleration, steering wheel angle change rate, and brake pedal force change rate, and the driver's eye movement data includes at least one of gaze duration, number of gazes, scan frequency, and pupil diameter.

[0211] In some embodiments, the evaluation score acquisition unit includes:

[0212] An original matrix determination subunit, used to determine the original matrix according to each of the candidate voice broadcast distances and the corresponding evaluation index;

[0213] A weight acquisition subunit, used to determine the weight corresponding to each evaluation index according to the original matrix; and

[0214] The evaluation score calculation subunit is used to calculate the evaluation score corresponding to each candidate voice broadcast distance according to the weight corresponding to each evaluation indicator.

[0215] In some embodiments, the original matrix is ​​an n*m matrix, where n is the number of candidate voice broadcast distances, and m is the number of evaluation indicators.

[0216] In some embodiments, the weight acquisition subunit includes:

[0217] A standardized matrix acquisition module, used for performing a standardized process on the original matrix to acquire a standardized matrix;

[0218] A normalized matrix acquisition module, used for normalizing the standardized matrix to obtain a normalized matrix;

[0219] An entropy value acquisition module, used to determine the entropy value corresponding to each evaluation index according to the normalized matrix;

[0220] A differentiation coefficient acquisition module, used to calculate the differentiation coefficient corresponding to each evaluation index according to the entropy value; and

[0221] The weight acquisition module is used to calculate the weight corresponding to each evaluation indicator according to the differentiation coefficient.

[0222] In some embodiments, the standardized matrix acquisition module includes:

[0223] A type determination submodule, used to determine the type of each evaluation indicator, the type including a positive evaluation indicator and a negative evaluation indicator, the positive evaluation indicator has a value proportional to the effect, and the negative evaluation indicator has a value inversely proportional to the effect; and

[0224] The standardized matrix acquisition submodule is used to perform standardization processing on the original matrix according to the types of the various evaluation indicators to obtain a standardized matrix.

[0225] In some embodiments, the positive evaluation index is standardized by the following formula:

[0226]

[0227] The negative evaluation index is standardized by the following formula:

[0228]

[0229] Among them, y ij represents the element in the i-th row and j-th column of the normalized matrix, x ij represents the element in the i-th row and j-th column of the original matrix, x j,min represents the minimum value of the elements in the jth column of the original matrix, x j,max Represents the maximum value of the elements in the j-th column of the original matrix.

[0230] In some embodiments, the normalized matrix is ​​calculated by the following formula:

[0231]

[0232] Among them, P ijrepresents the element in the i-th row and j-th column of the normalized matrix, y ij represents the element in the i-th row and j-th column of the normalized matrix, x ij represents the element in the i-th row and j-th column of the original matrix, and n is the number of candidate voice broadcast distances.

[0233] In some embodiments, the entropy value is calculated by the following formula:

[0234]

[0235] Among them, e j is the entropy value corresponding to the jth evaluation index, P ij represents the element in the i-th row and j-th column of the normalized matrix, n is the number of candidate voice broadcast distances.

[0236] In some embodiments, the differentiation coefficient is calculated by the following formula:

[0237] g j =1-e j

[0238] Among them, g j is the differentiation coefficient corresponding to the jth evaluation index, e j is the entropy value corresponding to the jth evaluation index.

[0239] In some embodiments, the weight is calculated by the following formula:

[0240]

[0241] Among them, W j is the weight corresponding to the jth evaluation index, g j is the differentiation coefficient corresponding to the jth evaluation index, and m is the number of evaluation indicators.

[0242] In some embodiments, the evaluation score is calculated using the following formula:

[0243]

[0244] Among them, F i is the evaluation score corresponding to the i-th candidate voice broadcast distance, W j is the weight corresponding to the jth evaluation index, P ij is the element in the i-th row and j-th column of the normalized matrix, and m is the number of evaluation indicators.

[0245] In some embodiments, the broadcast distance acquisition unit is specifically used to:

[0246] The candidate voice broadcast distance with the largest evaluation score is determined as the target voice broadcast distance.

[0247] Therefore, the embodiment of the present invention determines the voice broadcast scene: selects the risk scene of voice broadcast, including the pedestrian crossing conflict scene, the person-vehicle conflict scene in the blind spot of vision, and the roadside vehicle suddenly starts the conflict scene. Design an experimental plan: Design a specific implementation plan of the experiment, including the following steps: The first step is to determine the location of the conflict point when the risk scenario occurs, that is, the location where the person-vehicle or vehicle-vehicle collision occurs. The second step is to formulate the voice broadcast distance. First, determine the speed limit of the simulated driving vehicle, and then calculate the warning distance according to the safety warning distance formula. Then, the time distance from the conflict point is used as the basis for triggering the warning, and a variety of different voice broadcast distance selection schemes are designed for each risk scenario. The third step is to design the pedestrian crossing conflict scene, the person-vehicle conflict scene in the blind spot of vision, and the roadside vehicle suddenly starts the conflict scene and build it on the simulation software SCANeRstudio. Scenario 1: Pedestrian crossing conflict: The vehicle turns right at the intersection and there is a conflict point with the pedestrian crossing the street. Scenario 2: Person-vehicle conflict in the blind spot of vision: The bus stops at the bus stop to block the driver's line of sight, forming a visual blind spot, and the pedestrian crossing the road in front causes a collision between people and vehicles. Scenario 3: Conflict caused by sudden start of roadside vehicle: A roadside parked vehicle suddenly starts and has a potential conflict with a straight-moving vehicle when turning right. The design contents of the three scenarios include the length of the scenario, the distance between the scenarios, the number and grade of roads, the number of intersections, the size of the traffic flow around the driving vehicle and the speed of the traffic flow, the speed of pedestrians, and the trigger point location of the conflict scenario. Among them, the speed of the traffic flow should be close to the speed of the simulated driving vehicle, and the size of the traffic flow should not be too large to cause road congestion, and should not be too small to cause the simulated driving vehicle to exceed the speed limit. In addition, the selection principles of the trigger point locations of all conflict scenarios must be consistent to facilitate data analysis. The fourth step is to recruit experimental personnel and screen them according to the basic information filled in by the participants when they sign up. Determine the data collection equipment and indicators: The experimental process includes pre-experiments and formal experiments. Pre-experiments refer to the verification of the entire system between formal experiments to determine whether there are design errors. During the formal experiment, the subjects need to complete all the designed scenarios in the driving simulation cabin. During the experiment, the driver needs to wear an eye tracker to collect his eye movement data during the experiment. After the experiment, the driver's driving behavior data needs to be exported from the SCANeR studio software, and then the evaluation indicators are determined. Among them, the driving behavior data includes acceleration, steering wheel angle change rate, brake pedal force change rate, and eye movement data includes fixation duration, number of fixations, scan frequency, and pupil diameter. Experimental data analysis: The driving behavior data and eye movement data within the average distance from the conflict point when the driver first steps on the brake pedal after hearing the voice broadcast are processed, and the entropy method is used to determine the weight of each indicator. First, the average distance from the conflict point when the driver first steps on the brake pedal after hearing the voice broadcast is calculated, and then the driving behavior data and eye movement data within this distance are collected to obtain the original indicator data matrix, and then the entropy method is used to weight it.Establish a matrix of raw data and standardize the evaluation indicators. Usually, the indicators have different types and dimensions and cannot be directly compared. These data must be dimensionless and standardized before calculation. For indicators with larger values ​​(positive indicators) and indicators with smaller values ​​(negative indicators), different processing methods are used to obtain a standardized matrix of evaluation indicators. Normalize the standardized matrix to obtain a normalized matrix. Calculate the entropy value of each evaluation indicator, calculate the differentiation coefficient of each evaluation indicator, and calculate the weight of each evaluation indicator. Distance scheme selection: Use the weights of each evaluation indicator obtained above to calculate the comprehensive score of each candidate voice broadcast distance, and select the one with the highest score as the optimal voice broadcast distance scheme. For example, suppose there are three candidate voice broadcast distances, and the calculated comprehensive scores are F1, F2, and F3. If F2 is the largest, it means that the second candidate voice broadcast distance scheme is better.

[0248] The embodiment of the present invention obtains multiple candidate voice broadcast distances, determines the evaluation index corresponding to each candidate voice broadcast distance, the evaluation index is obtained by simulating the cockpit operation risk scenario, the evaluation index includes at least one of driving behavior data and driver eye movement data, determines the evaluation score corresponding to each candidate voice broadcast distance according to the evaluation index, and determines the target voice broadcast distance among the multiple candidate voice broadcast distances according to the evaluation score. In this way, the accuracy of the voice broadcast distance can be improved.

[0249] Fig.12 is a schematic diagram of an electronic device according to an embodiment of the present invention. Fig.12 The electronic device shown is a general data processing device, which includes a general computer hardware structure, which includes at least a processor 111 and a memory 112. The processor 111 and the memory 112 are connected via a bus 113. The memory 112 is suitable for storing instructions or programs executable by the processor 111. The processor 111 can be an independent microprocessor or a collection of one or more microprocessors. Thus, the processor 111 executes the instructions stored in the memory 112, thereby executing the method flow of the embodiment of the present invention as described above to realize the processing of data and the control of other devices. The bus 113 connects the above-mentioned multiple components together, and at the same time connects the above-mentioned components to the display controller 114 and the display device and the input / output (I / O) device 115. The input / output (I / O) device 115 can be a mouse, a keyboard, a modem, a network interface, a touch input device, a somatosensory input device, a printer, and other devices known in the art. Typically, the input / output device 115 is connected to the system through an input / output (I / O) controller 116.

[0250] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, devices (equipment) or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0251] The present invention is described with reference to flowcharts of methods, apparatuses (devices) and computer program products according to embodiments of the present application. It should be understood that each process in the flowchart can be implemented by computer program instructions.

[0252] These computer program instructions may be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device that implements the process Figure 1 A function specified in a process or multiple processes.

[0253] These computer program instructions may also be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce the instructions for implementing the process Figure 1 A device that specifies functions in a process or multiple processes.

[0254] The solutions described in this specification and in the examples, if they involve the processing of personal information, will be processed on the premise of having a legal basis (such as obtaining the consent of the subject of personal information, or being necessary for the performance of a contract, etc.), and will only be processed within the scope of regulations or agreements. If a user refuses to process personal information other than the necessary information for basic functions, it will not affect the user's use of basic functions.

[0255] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for obtaining voice broadcast distance, characterized in that: The method comprises: Acquire multiple candidate voice broadcast distances, where the multiple candidate voice broadcast distances correspond to different voice broadcast distances in the same scene; Determine an evaluation index corresponding to each of the candidate voice broadcast distances, the evaluation index being obtained by simulating a cockpit operation risk scenario, the evaluation index being an evaluation index between a position of a brake pedal in a simulated cockpit when it is first triggered and a position of a conflict point when voice broadcasting is performed according to the candidate voice broadcast distance during the operation risk scenario, the evaluation index including at least one of driving behavior data and driver eye movement data; Determine the evaluation score corresponding to each of the candidate voice broadcast distances according to the evaluation index; and A target voice broadcast distance is determined from among the multiple candidate voice broadcast distances according to the evaluation score.

2. The method according to claim 1, characterized in that The obtaining of multiple candidate voice broadcast distances includes: Determine safe warning distances; and Acquire multiple candidate voice broadcast distances according to the safety warning distance; The safety warning distance is the sum of the parking sight distance, the safety spacing and the information delay distance. The parking sight distance is calculated by the following formula: Among them, S T is the stopping sight distance, v is the speed limit, t is the sum of perception time and reaction time, is the adhesion coefficient, is the sum of the sliding friction coefficient and the ramp coefficient.

3. The method according to claim 1, characterized in that The risk scenarios include at least one of a conflict scenario involving pedestrians crossing the street, a conflict scenario involving a person and a vehicle in a blind spot, and a conflict scenario involving a vehicle on the roadside suddenly starting up.

4. The method according to claim 1, characterized in that: The evaluation index corresponding to each candidate voice broadcast distance is determined as follows: Acquiring configuration information, the configuration information including at least one of a scene length, a distance between scenes, a number and level of roads, a number of intersections, a size of a traffic flow around a driving vehicle and a speed of the traffic flow, a speed of pedestrians, and a location of a conflict point; Constructing the risk scenario according to the configuration information by simulation software; and The risk scenario is run in a simulated cockpit to obtain evaluation indicators corresponding to the candidate voice broadcast distances.

5. The method according to claim 4, characterized in that The step of running the risk scenario in a simulated cockpit to obtain evaluation indicators corresponding to the distances of each candidate voice broadcast includes: Running the risk scenarios through a simulated cockpit; Obtaining the position of the simulated cockpit in the risk scenario; In response to the distance between the position of the simulated cockpit in the risk scenario and the position of the conflict point being a predetermined distance, triggering a corresponding conflict scenario; In response to the distance between the position of the simulated cockpit in the risk scenario and the position of the conflict point being a candidate voice broadcast distance, triggering a voice broadcast; Get the position of the brake pedal in the simulated cockpit when it is triggered for the first time after the voice broadcast is triggered; An evaluation index between the position of the brake pedal of the simulated cockpit when it is first triggered and the position of the conflict point is obtained.

6. The method according to claim 1, characterized in that The driving behavior data includes at least one of acceleration, steering wheel angle change rate, and brake pedal force change rate; the driver's eye movement data includes at least one of gaze duration, gaze number, scan frequency, and pupil diameter.

7. The method according to claim 1, characterized in that Determining the evaluation score corresponding to each candidate voice broadcast distance according to the evaluation index includes: Determine the original matrix according to the candidate voice broadcast distances and the corresponding evaluation indicators; Determine the weight corresponding to each evaluation index according to the original matrix; and The evaluation scores corresponding to the voice broadcast distances of the candidates are calculated according to the weights corresponding to the evaluation indicators.

8. The method according to claim 7, characterized in that The original matrix is ​​an n*m matrix, where n is the number of candidate voice broadcast distances and m is the number of evaluation indicators.

9. The method according to claim 7, characterized in that: Determining the weights corresponding to the various evaluation indicators according to the original matrix includes: Performing normalization processing on the original matrix to obtain a normalized matrix; Performing normalization processing on the standardized matrix to obtain a normalized matrix; Determining the entropy value corresponding to each evaluation index according to the normalized matrix; Calculating the differentiation coefficient corresponding to each evaluation index according to the entropy value; and The weight corresponding to each evaluation index is calculated according to the differentiation coefficient.

10. The method according to claim 9, characterized in that The performing normalization processing on the original matrix to obtain a normalized matrix comprises: Determine the type of each evaluation indicator, the type includes a positive evaluation indicator and a negative evaluation indicator, the positive evaluation indicator is a value proportional to the effect, and the negative evaluation indicator is a value inversely proportional to the effect; and The original matrix is ​​standardized according to the types of the evaluation indicators to obtain a standardized matrix.

11. The method according to claim 10, characterized in that The positive evaluation index is standardized by the following formula: The negative evaluation index is standardized by the following formula: Among them, y ij represents the element in the i-th row and j-th column of the normalized matrix, x ij represents the element in the i-th row and j-th column of the original matrix, x j,min represents the minimum value of the elements in the jth column of the original matrix, x j,max Represents the maximum value of the elements in the j-th column of the original matrix.

12. The method according to claim 11, characterized in that The normalized matrix is ​​calculated by the following formula: Among them, P ij represents the element in the i-th row and j-th column of the normalized matrix, y ij represents the element in the i-th row and j-th column of the normalized matrix, x ij represents the element in the i-th row and j-th column of the original matrix, and n is the number of candidate voice broadcast distances.

13. The method according to claim 12, characterized in that The entropy value is calculated by the following formula: Among them, e j is the entropy value corresponding to the jth evaluation index, P ij represents the element in the i-th row and j-th column of the normalized matrix, n is the number of candidate voice broadcast distances.

14. The method according to claim 13, characterized in that The differentiation coefficient is calculated by the following formula: g j =1-e j Among them, g j is the differentiation coefficient corresponding to the jth evaluation index, e j is the entropy value corresponding to the jth evaluation index.

15. The method according to claim 14, characterized in that The weight is calculated by the following formula: Among them, W j is the weight corresponding to the jth evaluation index, g j is the differentiation coefficient corresponding to the jth evaluation index, and m is the number of evaluation indicators.

16. The method according to claim 14, characterized in that The evaluation score is calculated by the following formula: Among them, F i is the evaluation score corresponding to the i-th candidate voice broadcast distance, W j is the weight corresponding to the jth evaluation index, P ij is the element in the i-th row and j-th column of the normalized matrix, and m is the number of evaluation indicators.

17. The method according to claim 1, characterized in that The method of determining the target voice broadcast distance from the plurality of candidate voice broadcast distances according to the evaluation score is specifically as follows: The candidate voice broadcast distance with the largest evaluation score is determined as the target voice broadcast distance.

18. A device for obtaining voice broadcast distance, characterized in that: The device comprises: A candidate distance acquisition unit, used to acquire a plurality of candidate voice broadcast distances, wherein the plurality of candidate voice broadcast distances correspond to different voice broadcast distances in the same scene; An evaluation index acquisition unit, used to determine an evaluation index corresponding to each of the candidate voice broadcast distances, wherein the evaluation index is acquired by simulating a cockpit operation risk scenario, wherein the evaluation index is an evaluation index between a position of a brake pedal of a simulated cockpit when it is first triggered and a position of a conflict point when voice broadcast is performed according to the candidate voice broadcast distance during the operation risk scenario, and the evaluation index includes at least one of driving behavior data and driver eye movement data; An evaluation score acquisition unit, used to determine the evaluation score corresponding to each of the candidate voice broadcast distances according to the evaluation index; and The broadcast distance acquisition unit is used to determine a target voice broadcast distance from the plurality of candidate voice broadcast distances according to the evaluation score.

19. An electronic device comprising a memory and a processor, characterized in that: The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method according to any one of claims 1-17.

20. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: The computer program instructions, when executed by a processor, implement the method of any one of claims 1-17.

Images