Voice broadcast determination method, system, voice prompt method and electronic device

Abstract

The embodiment of the present invention discloses a method, system, voice prompt method and electronic device for determining voice broadcast, which determines at least one candidate voice broadcast mode corresponding to the current dangerous traffic scene, and determines the score of each simulated driving behavior based on the data set corresponding to the collected multiple simulated driving behaviors, each candidate voice broadcast mode has a corresponding voice broadcast information volume, the data set includes index data corresponding to at least one evaluation index collected during each simulated driving behavior, each simulated driving behavior has a corresponding candidate voice broadcast mode, and based on the score of each simulated driving behavior and its corresponding candidate voice broadcast mode, the comprehensive score of each candidate voice broadcast mode is determined, and the candidate voice broadcast mode with the highest comprehensive score is determined as the target voice broadcast mode. Thus, voice prompts are given through the target voice broadcast mode corresponding to the dangerous traffic scene, so that users can perform relevant operations in a timely manner, effectively avoiding the occurrence of traffic accidents.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a voice broadcast determination method, system, voice prompt method and electronic equipment. Background Art

[0002] As various means of transportation (such as cars, electric vehicles, etc.) become popular in people's lives, voice broadcasting is becoming more and more important in traffic accident warning. However, existing voice broadcasting is difficult to effectively remind users of traffic accidents, resulting in low effectiveness in avoiding traffic accidents. Summary of the invention

[0003] In view of this, the embodiments of the present invention provide a voice broadcast determination method, system, voice prompt method and electronic device, so as to give corresponding prompts to users through the target voice broadcast method corresponding to dangerous traffic scenes, so that users can perform relevant operations in time, thereby effectively avoiding the occurrence of traffic accidents.

[0004] In a first aspect, a method for determining a voice broadcast is provided, the method comprising:

[0005] Determine at least one candidate voice broadcast mode corresponding to the current dangerous traffic scene, each of the candidate voice broadcast modes having a corresponding amount of voice broadcast information;

[0006] Collecting a data set corresponding to a plurality of simulated driving behaviors, the data set comprising index data corresponding to at least one evaluation index collected during each of the simulated driving behaviors, each of the simulated driving behaviors having a corresponding candidate voice broadcast mode;

[0007] Determining a score for each of the simulated driving behaviors based on each of the data sets;

[0008] Determining a comprehensive score of each of the candidate voice broadcasting methods based on the score of each of the simulated driving behaviors and the candidate voice broadcasting methods corresponding to each of the simulated driving behaviors;

[0009] The candidate voice broadcast mode with the highest comprehensive score is determined as the target voice broadcast mode.

[0010] In some embodiments, the dangerous traffic scenario is designed using preset simulation software based on data of similar historical dangerous traffic scenarios.

[0011] In some embodiments, each of the candidate voice broadcast modes has corresponding voice broadcast information content and / or voice broadcast position.

[0012] In some embodiments, the word classes in each of the voice broadcast information contents include at least one or a combination of the following: distance, road facilities, safety information, visual requirements, and driving requirements.

[0013] In some embodiments, determining at least one candidate voice broadcast mode corresponding to the current dangerous traffic scene includes:

[0014] Obtain the voice broadcast information content corresponding to multiple preset voice broadcast modes;

[0015] Calculate the entropy value of the voice broadcast information amount corresponding to each of the preset voice broadcast modes according to the ratio of the number of words of each feature name in the content of each voice broadcast information to the total number of words of the feature name;

[0016] According to the ranking of the entropy values ​​of the voice broadcast information amounts, at least one candidate voice broadcast mode is determined from the preset voice broadcast modes.

[0017] In some embodiments, the at least one evaluation index includes driving indicators and / or visual indicators, the driving indicators include vehicle speed, vehicle lateral displacement, vehicle longitudinal acceleration and / or steering wheel angular velocity, and the visual indicators include gaze point, gaze area, gaze number and / or gaze time.

[0018] In some embodiments, the collecting of data sets corresponding to multiple simulated driving behaviors includes:

[0019] Collecting data corresponding to each of the driving indicators through a driving simulation system; and / or

[0020] The data corresponding to each of the visual indicators is collected through an eye tracker.

[0021] In some embodiments, determining a score for each of the simulated driving behaviors based on each of the data sets includes:

[0022] Determine the indicator data corresponding to each of the evaluation indicators according to each of the data sets;

[0023] Performing data conversion processing on the indicator data of each evaluation indicator to determine the matrix corresponding to each evaluation indicator;

[0024] Determine the set of optimal values ​​and the set of worst values ​​in each of the matrices as a positive ideal solution and a negative ideal solution, respectively;

[0025] The distance between each indicator data in each simulated driving behavior and the positive ideal solution and / or the negative ideal solution is calculated to determine the score of each simulated driving behavior.

[0026] In some embodiments, performing data conversion processing on the indicator data of each evaluation indicator to determine the matrix corresponding to each evaluation indicator includes:

[0027] Standardizing the indicator data of each evaluation indicator;

[0028] Calculate the indicator parameters and weights corresponding to each indicator data according to the standardized indicator data, wherein the indicator parameters represent the probability of the indicator data appearing in the corresponding evaluation indicator;

[0029] The indicator parameter corresponding to the indicator data in each of the evaluation indicators is multiplied by the weight to determine the matrix corresponding to each of the evaluation indicators.

[0030] In a second aspect, a voice prompt method is provided, the method comprising:

[0031] Acquiring driving information, wherein the driving information at least includes location information;

[0032] determining whether there is a dangerous traffic scene within a predetermined range according to the driving information;

[0033] In response to the presence of a dangerous traffic scene, determining a type of the dangerous traffic scene;

[0034] Determining a target voice broadcast mode according to the type of the dangerous traffic scene, wherein the target voice broadcast mode is determined according to index data corresponding to at least one evaluation index collected during the historical simulated driving behavior corresponding to the dangerous traffic scene;

[0035] The target voice broadcasting method is used for voice prompting.

[0036] In some embodiments, the method further comprises:

[0037] Determine the dangerous locations of various dangerous traffic scenarios based on historical dangerous traffic scenario data;

[0038] Store the relationship between the location where the danger occurs and the corresponding dangerous traffic scene type.

[0039] In some embodiments, the driving information includes environmental perception information;

[0040] Determining whether there is a dangerous traffic scene within a predetermined range according to the driving information includes:

[0041] Determining current danger occurrence parameters according to the environmental perception information;

[0042] In response to the danger occurrence parameter being greater than a threshold, it is determined that a dangerous traffic scene currently exists.

[0043] In some embodiments, determining the type of dangerous traffic scene includes:

[0044] The environmental perception information is identified to determine the type of the corresponding dangerous traffic scene.

[0045] In a third aspect, a voice broadcast determination device is provided, the device comprising:

[0046] A first determination module is configured to determine at least one candidate voice broadcast mode corresponding to the current dangerous traffic scene, each of the candidate voice broadcast modes having a corresponding voice broadcast information amount;

[0047] A collection module is configured to collect a plurality of data sets corresponding to simulated driving, wherein the data sets include index data corresponding to at least one evaluation index collected during the simulated driving behavior, and the simulated driving has a corresponding candidate voice broadcast mode;

[0048] A second determination module is configured to determine a score of each of the simulated drivings based on each of the data sets;

[0049] A third determination module is configured to determine a comprehensive score of each of the candidate voice broadcasting methods based on the score of each of the simulated driving and the candidate voice broadcasting methods corresponding to the simulated driving;

[0050] The fourth determination module is configured to determine the candidate voice broadcast mode with the highest comprehensive score as the target voice broadcast mode.

[0051] In a fourth aspect, a voice prompting device is provided, the device comprising:

[0052] An acquisition module is configured to acquire driving information, wherein the driving information at least includes location information;

[0053] A scene determination module, configured to determine whether there is a dangerous traffic scene within a predetermined range according to the driving information;

[0054] a type determination module, configured to determine the type of the dangerous traffic scene in response to the presence of the dangerous traffic scene;

[0055] A mode determination module is configured to determine a target voice broadcast mode according to the type of the dangerous traffic scene, wherein the target voice broadcast mode is determined according to index data corresponding to at least one evaluation index collected during the historical simulated driving behavior corresponding to the dangerous traffic scene;

[0056] The prompt module is configured to use the target voice broadcast mode for voice prompting.

[0057] In a fifth aspect, a voice broadcast determination system is provided, the system comprising:

[0058] A data collection device, including a driving simulation system and / or an eye tracker, for collecting at least one indicator data during the simulated driving behavior and sending the indicator data to a memory;

[0059] A voice broadcasting device, used for broadcasting candidate voice broadcasting modes;

[0060] A memory and a processor, wherein the memory is used to store indicator data and one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method as described in the first aspect.

[0061] In a sixth aspect, an electronic device is provided, 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 as described in the first aspect or the second aspect.

[0062] In a seventh aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect or the second aspect is implemented.

[0063] According to an eighth aspect, a computer program product is provided. When the computer program product is run on a computer, the computer is caused to execute the method according to the first aspect or the second aspect.

[0064] The embodiment of the present invention determines at least one candidate voice broadcast mode corresponding to the current dangerous traffic scene, each candidate voice broadcast mode has a corresponding voice broadcast information volume, collects a plurality of data sets corresponding to simulated driving behaviors, the data sets include index data corresponding to at least one evaluation index collected during each simulated driving behavior, each simulated driving behavior has a corresponding candidate voice broadcast mode, determines the score of each simulated driving behavior based on each data set, determines the comprehensive score of each candidate voice broadcast mode based on the score of each simulated driving behavior and the candidate voice broadcast mode corresponding to each simulated driving behavior, and determines the candidate voice broadcast mode with the highest comprehensive score as the target voice broadcast mode. Thus, the user can be prompted accordingly through the target voice broadcast mode corresponding to the dangerous traffic scene, so that the user can perform relevant operations in time, thereby effectively avoiding the occurrence of traffic accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] 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:

[0066] Figure 1 is a flow chart of a method for determining a voice broadcast according to an embodiment of the present invention;

[0067] Figure 2 is a flow chart of determining a candidate voice broadcasting method according to an embodiment of the present invention;

[0068] Figure 3 is a flow chart of determining a score of a simulated driving behavior according to an embodiment of the present invention;

[0069] Figure 4 is a flow chart of determining a matrix corresponding to an evaluation index according to an embodiment of the present invention;

[0070] Figure 5 is a flow chart of a voice prompt method according to an embodiment of the present invention;

[0071] Figure 6 is a schematic diagram of a voice broadcast determination system according to an embodiment of the present invention;

[0072] Figure 7 is a schematic diagram of a voice broadcast determination device according to an embodiment of the present invention;

[0073] Figure 8 is a schematic diagram of a voice prompt device according to an embodiment of the present invention;

[0074] Fig. 9 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0075] The present application is described below based on embodiments, but the present application is not limited to these embodiments. In the detailed description of the present application below, some specific details are described in detail. It is possible for those skilled in the art to fully understand the present application without the description of these details. In order to avoid confusing the essence of the present application, known methods, processes, flows, components and circuits are not described in detail.

[0076] 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.

[0077] Unless the context clearly requires otherwise, the words "include", "comprising" and similar words throughout the application should be interpreted as including rather than exclusive or exhaustive; that is, the meaning is "including but not limited to".

[0078] In the description of this application, 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 this application, unless otherwise specified, the meaning of "plurality" is two or more.

[0079] 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.

[0080] Figure 1 FIG. 1 is a flow chart of a method for determining a voice broadcast according to an embodiment of the present invention. Figure 1 As shown, the voice broadcast determination method of this embodiment includes the following steps:

[0081] Step S110, determining at least one candidate voice broadcast mode corresponding to the current dangerous traffic scene, each of the candidate voice broadcast modes having a corresponding amount of voice broadcast information.

[0082] Among them, dangerous traffic scenes can be designed by a preset driving simulation system based on the data of historical dangerous traffic scenes of the same type. For example, various existing simulation software related to driving simulators such as SCANNER STUDIO are used to build corresponding dangerous traffic simulation scenes based on the data of historical dangerous traffic scenes. For example, dangerous traffic scenes that may conflict with the current vehicle can be built, such as "a vehicle stopped on the roadside suddenly starts quickly and changes lanes to the left lane", "a pedestrian crosses the road at a red light", "a pedestrian suddenly rushes out from the front of a large vehicle", "a large vehicle driving in front of the current vehicle suddenly brakes", and "a pedestrian at a bus stop suddenly rushes out from the front of the bus".

[0083] In some implementations, this embodiment can set a plurality of preset voice broadcast modes in each dangerous traffic scenario, and screen out candidate voice broadcast modes corresponding to the current dangerous traffic scenario based on the amount of voice broadcast information corresponding to the preset voice broadcast modes.

[0084] Specifically, Figure 2 As shown, the steps of determining at least one candidate voice broadcast mode corresponding to the current dangerous traffic scene in this embodiment are as follows, including:

[0085] Step S210, obtaining voice broadcast information contents corresponding to a plurality of preset voice broadcast modes.

[0086] Among them, each preset voice broadcast mode has a corresponding voice broadcast information content and / or voice broadcast position. The word classes in each of the voice broadcast information contents include at least one or more of the following combinations: distance, road facilities, safety information, visual requirements and driving requirements. The distance refers to the distance from the current vehicle to the accident-prone point, the road facilities include bus stops, crosswalks, etc., the safety information includes accident-prone points, etc., the visual requirements include please pay attention to blind spots, etc., and the driving requirements include please slow down, etc.

[0087] In some implementations, the word class combination in the preset voice broadcast content can be driving requirements, or distance, road facilities and driving requirements, or distance, road facilities, safety information, visual requirements and driving requirements, or distance, road facilities, visual requirements and driving requirements, etc. The voice broadcast position can be a meter, b meter, or c meter away from the accident-prone point. Therefore, there are 12 preset voice broadcast methods according to the word classes and broadcast positions contained in the above voice broadcast content. It should be understood that the distance in the voice broadcast content matches the broadcast position.

[0088] For example, when the dangerous traffic scene is "a pedestrian at a bus stop suddenly rushes out in front of a bus", the word class combination is distance, road facilities, and driving requirements, and the voice broadcast position is b, the corresponding voice broadcast content can be "there is a bus stop b meters ahead, please slow down."

[0089] Step S220, calculating the entropy value of the voice broadcast information amount corresponding to each of the preset voice broadcast modes according to the ratio of the number of words of each feature name in the voice broadcast information content to the total number of words of the feature name.

[0090] The entropy value represents the amount of information in the voice broadcast information content.

[0091] Specifically, in some implementations, the formula for calculating the entropy value may be:

[0092]

[0093] P(i) represents the probability of the feature name i appearing in the voice broadcast information content, which is the number of words m of the feature name i. i The ratio of the total number of words in the feature name n, that is,

[0094] It is not difficult to understand that since the entropy value is calculated based on the ratio of the number of words in each feature name to the total number of words in the feature name, when the word classes corresponding to the voice broadcast content in the voice broadcast mode are the same, even if the broadcast position (that is, the distance) is different, the entropy value of the voice broadcast information corresponding to the voice broadcast mode is the same.

[0095] In other implementations, the calculation formula for the entropy value may also be set according to actual conditions, and this embodiment does not limit this.

[0096] Step S230, determining at least one candidate voice broadcast mode from each of the preset voice broadcast modes according to the ranking of the entropy values ​​of the voice broadcast information amounts.

[0097] Specifically, in some implementations, the entropy values ​​of the voice broadcast information amount can be sorted from small to large, and the preset voice broadcast modes corresponding to one or more entropy values ​​ranked first are selected as candidate voice broadcast modes. It should be understood that in actual applications, the selection method of the preset voice broadcast mode can also be determined according to actual conditions, and this embodiment does not limit this.

[0098] Thus, a candidate broadcast mode having corresponding voice broadcast information content and / or voice broadcast position can be determined from the preset voice broadcast modes.

[0099] Step S120, collecting data sets corresponding to multiple simulated driving behaviors, wherein the data sets include index data corresponding to at least one evaluation index collected during each of the simulated driving behaviors, and each of the simulated driving behaviors has a corresponding candidate voice broadcasting method.

[0100] The simulated driving behavior refers to the process of completing a simulated driving in the current dangerous traffic scene. The operator and voice broadcast method in each simulated driving behavior can be set according to the actual situation, and this embodiment does not limit this. That is, the operator performing the simulated driving in each simulated driving behavior can be the same or different, and the candidate voice broadcast method in each simulated driving process can be the same or different.

[0101] In each simulated driving behavior, the driver drives within a preset speed range. The preset speed range is set according to the historical vehicle driving speeds on urban roads. In some implementations, the historical vehicle driving speeds can be sorted to determine the range of historical driving speeds, and the preset speed range can be determined within the range of historical driving speeds. For example, when the historical driving speed range is X to Y, the preset speed range can be set to M to N, where M is greater than X and N is less than Y. Thus, the speed of the driver during simulated driving can be limited based on the actual conditions of urban roads, and the speed during simulated driving is not too high or too low, thereby improving the actual reference significance of the index data collected by the simulated driving behavior.

[0102] In some embodiments, the at least one evaluation index may include a driving index and / or a visual index, the driving index characterizes the driving state of the vehicle, the driving index may include vehicle speed, vehicle lateral displacement, vehicle longitudinal acceleration and / or steering wheel angular velocity, and the data corresponding to each driving index may be collected by a driving simulation system. The visual index characterizes the visual state of the driver, the visual index may include gaze point, gaze area, gaze number and / or gaze time, and the data corresponding to each visual index may be collected by an eye tracker. It should be understood that the driving index and the visual index can be set according to actual needs, as long as the set driving index can reflect the driving state of the vehicle and the set visual index can reflect the visual state, this embodiment does not limit this.

[0103] In some embodiments, this embodiment can perform multiple simulated driving in each candidate voice broadcast mode based on the current dangerous traffic scenario. During each simulated driving process, when voice prompts are given in the corresponding candidate voice broadcast mode, the driving simulation system and / or eye tracker is started to collect data, so that based on the data collected after the broadcast prompt, the impact of the corresponding candidate voice broadcast mode on the simulated driving behavior can be directly analyzed.

[0104] In some implementations, this embodiment can use the data corresponding to each driving index collected by the driving simulation system as a data set corresponding to each simulated driving behavior, and perform corresponding data analysis. Specifically, the driving index can be used to analyze whether the driver has performed corresponding operations on the vehicle in a timely manner based on the voice prompt, so as to determine the driver's understanding of the corresponding candidate voice broadcast method. For example, when a voice broadcast prompt is given to the driver that the content is "The bus stop is b meters ahead, please slow down", the driver should decelerate the vehicle in a timely manner. By analyzing driving index data such as vehicle speed, vehicle lateral displacement, vehicle longitudinal acceleration or steering wheel angular velocity, it can be determined whether the driver has performed a deceleration operation.

[0105] In some implementations, this embodiment can also use the data corresponding to each visual indicator collected by the eye tracker as a data set corresponding to each simulated driving behavior, and perform corresponding data analysis. Specifically, the visual indicators can be used to analyze whether the driver has paid timely attention to the conditions in the corresponding area based on the voice prompt, so as to determine the driver's understanding of the corresponding candidate voice broadcast method. For example, when a voice broadcast prompt is given to the driver that the content is "The bus stop is b meters ahead, please slow down", the driver should increase the number of gazes on the right side of the road ahead to avoid someone rushing out near the bus stop and colliding. By analyzing visual indicator data such as gaze point, gaze area, gaze number or gaze time, it can be determined whether the driver has paid timely attention to the conditions in the corresponding area.

[0106] In other implementations, this embodiment may also use the data corresponding to each driving indicator collected by the driving simulation system and the data corresponding to each visual indicator collected by the eye tracker as a data set corresponding to each simulated driving behavior to perform corresponding data analysis.

[0107] In other embodiments, the driving simulation system and / or the eye tracker may be directly started at the beginning of the simulated driving behavior to collect corresponding data in the entire simulated driving behavior. When it is necessary to analyze the impact of the corresponding candidate voice broadcasting methods on the simulated driving behavior later, the data after the voice prompt is screened out for data analysis.

[0108] Step S130, determining a score for each of the simulated driving behaviors based on each of the data sets.

[0109] In some implementations, the step of determining a score for each of the simulated driving behaviors based on each of the data sets is as follows: Figure 3 As shown, including:

[0110] Step S310: determining the indicator data corresponding to each of the evaluation indicators according to each of the data sets.

[0111] For example, under candidate voice broadcast mode A, when the evaluation indicators are vehicle speed v, vehicle lateral displacement x, vehicle longitudinal acceleration a and steering wheel angular velocity w, there are s data sets collected from s simulated driving behaviors, each of which is {v1, x1, a1, w1}, {v2, x2, a2, w2}, ..., {vs, xs, as, ws}, and the indicator data corresponding to the speed evaluation indicator includes {v1, v2, ..., vs}. Therefore, the indicator data corresponding to each evaluation indicator can be determined respectively according to the data set.

[0112] Step S320: performing data conversion processing on the indicator data of each evaluation indicator to determine a matrix corresponding to each evaluation indicator.

[0113] In some implementations, the step of performing data conversion processing on the indicator data of each evaluation indicator to determine the matrix corresponding to each evaluation indicator is as follows: Figure 4 As shown, including:

[0114] Step S410, standardizing the indicator data of each evaluation indicator.

[0115] Among them, the index data of each evaluation index can represent whether the driver has made positive or negative feedback based on the voice prompt.

[0116] For example, when the evaluation index is vehicle speed, if the vehicle speed decreases after the voice announcement, it can be determined that the driver has performed positive feedback, otherwise it can be determined as negative feedback. It should be understood that the determination conditions of the indicator data of each evaluation index can be set according to actual conditions, as long as the corresponding determination conditions can distinguish whether the driver has performed corresponding operations based on the voice prompt, and this embodiment does not limit this.

[0117] In some implementations, the indicator data corresponding to the positive feedback and the indicator data corresponding to the negative feedback may be standardized using different rules.

[0118] For example, for the indicator data corresponding to positive feedback, the standardized calculation formula is:

[0119]

[0120] For the indicator data corresponding to negative feedback, the standardized calculation formula is:

[0121]

[0122] x j is the indicator data currently being standardized, min(Σx j ) represents the minimum data among the evaluation indicators corresponding to the current indicator data, max(Σx j ) represents the largest data among the evaluation indicators corresponding to the current indicator data.

[0123] In other implementations, each indicator data may also be standardized using the same rule. For example, each indicator data may be standardized by directly calculating the ratio of each indicator data to a reference value. The reference value may be any value preset according to requirements, for example, the reference value may be the maximum value of the evaluation index corresponding to the current indicator data.

[0124] Step S420, calculating the indicator parameters and weights corresponding to each indicator data according to the standardized indicator data, wherein the indicator parameters represent the probability of the indicator data appearing in the corresponding evaluation indicator.

[0125] In some implementations, the ratio of the normalized indicator data to the sum of all indicator data in the evaluation index corresponding to the indicator data may be determined as the indicator parameter. j The formula can be:

[0126]

[0127] Among them, n represents the number of indicator data in the evaluation indicator corresponding to the indicator data.

[0128] Furthermore, the weight of the indicator data is determined based on the indicator parameters. In some implementations, the entropy of the indicator data can be first determined based on the indicator parameters, and then the redundancy corresponding to the indicator data can be determined based on the entropy, and then the weight corresponding to the indicator data can be determined based on the redundancy.

[0129] In some implementations, determining the indicator data E j The formula for the entropy can be:

[0130]

[0131] Here, k is a reference coefficient, and the value of k can be set according to actual needs, which is not limited in this embodiment.

[0132] Redundancy d j The calculation formula can be:

[0133] d j =1-E j

[0134] The weight ω corresponding to the indicator data j The calculation formula can be:

[0135]

[0136] Step S430: multiply the indicator parameter corresponding to the indicator data in each evaluation indicator by the weight to determine a matrix corresponding to each evaluation indicator.

[0137] In some implementations, the matrix Z corresponding to each evaluation index data is:

[0138] Z=(p j *ω jj )

[0139] Step S330: Determine the set of optimal values ​​and the set of worst values ​​in each of the matrices as a positive ideal solution and a negative ideal solution, respectively.

[0140] Specifically, the optimal value represents the data that best meets expectations, and the worst value represents the data that deviates the most from expectations. For example, when the evaluation index is a gaze point, the expected gaze position is point P, and the index data in the gaze point can reflect the actual gaze position of the driver. The index data at the position closest to point P is determined as the optimal value in the gaze point, and the index data at the position farthest from point P is determined as the worst value in the gaze point. Thus, the optimal value and the worst value in the matrix corresponding to each evaluation index are selected, and the set of optimal values ​​and the set of worst values ​​in each matrix are respectively determined as the positive ideal solution and the negative ideal solution.

[0141] Step S340 , calculating the distance between each indicator data in each simulated driving behavior and the positive ideal solution and / or the negative ideal solution to determine the score of each simulated driving behavior.

[0142] In some implementations, the distance to the ideal solution is The calculation formula can be:

[0143]

[0144] In some implementations, the distance to the ideal solution is The calculation formula can be:

[0145]

[0146] Among them, z j Characterize the current indicator data, Characterizes the positive ideal solution in the evaluation index corresponding to the current index data, Represents the negative ideal solution in the evaluation index corresponding to the current index data.

[0147] It is not difficult to understand that the closer the distance between each indicator data and the positive ideal solution and the farther the distance from the negative ideal solution, the higher the score of the corresponding simulated driving behavior.

[0148] In some implementations, the sum of the distances between each indicator data and the positive ideal solution and the negative ideal solution may be calculated, and the proportion of the distance between each indicator data and the negative ideal solution in the sum of the distances may be determined as the corresponding simulated driving behavior score. j The formula can be:

[0149]

[0150] In actual application scenarios, the distance relationship between each indicator data and the positive ideal solution and the negative ideal solution can be set according to the specific situation, and this embodiment does not limit this. For example, the reciprocal of the distance between each indicator data in each simulated driving behavior and the positive ideal solution can also be determined as the score of the simulated driving behavior. Alternatively, the distance between each indicator data in each simulated driving behavior and the negative ideal solution can also be directly determined as the score of the simulated driving behavior.

[0151] Step S140, determining a comprehensive score of each of the candidate voice broadcasting methods based on the score of each of the simulated driving behaviors and the candidate voice broadcasting methods corresponding to each of the simulated driving behaviors.

[0152] In some implementations, this embodiment may determine the sum of the scores of the simulated driving behaviors corresponding to each candidate voice broadcasting method as the comprehensive score of the corresponding candidate voice broadcasting method.

[0153] Step S150: determine the candidate voice broadcast mode with the highest comprehensive score as the target voice broadcast mode.

[0154] For example, when the dangerous traffic scenario is "pedestrians at the bus stop suddenly rush out in front of the bus", the candidate voice broadcast method with the highest comprehensive score is the voice broadcast content of "The bus stop is b meters ahead, please slow down" when the distance from the bus stop is b meters. The above candidate voice broadcast method is determined as the target voice broadcast method for the dangerous traffic scenario "pedestrians at the bus stop suddenly rush out in front of the bus".

[0155] Thus, the determined target voice broadcast mode is the voice broadcast mode that can most effectively provide traffic prompts to the user in the current dangerous traffic scene. Based on the above steps S110 to S150, this embodiment can respectively determine the target voice broadcast modes corresponding to various dangerous traffic scenes.

[0156] In some embodiments, after determining the mapping relationship between various dangerous traffic scenarios and corresponding target voice broadcast methods in the above manner, in actual driving scenarios, when the vehicle may encounter corresponding dangerous traffic scenarios, voice prompts can be given to the user based on the corresponding target voice broadcast methods, so that the user can perform relevant operations in a timely manner, thereby effectively avoiding the occurrence of traffic accidents.

[0157] Specifically, Figure 5 FIG. 1 is a flow chart of a voice prompt method according to an embodiment of the present invention. Figure 5 As shown, the steps of the voice prompt method of the embodiment of the present invention include:

[0158] Step S510: Acquire driving information, where the driving information at least includes location information.

[0159] This embodiment can determine the dangerous occurrence locations of various dangerous traffic scenes based on historical dangerous traffic scene data, and store the relationship between the dangerous occurrence locations and the corresponding dangerous traffic scene types. During vehicle driving, the vehicle driving information is obtained in real time or periodically.

[0160] Step S520: determining whether there is a dangerous traffic scene within a predetermined range according to the driving information.

[0161] The specific value of the predetermined range may be set according to actual conditions, and this embodiment does not limit this.

[0162] In some implementations, the driving information also includes environmental perception information such as vehicle speed, humidity information, pedestrian density, and vehicle density. This embodiment can also determine the current danger occurrence parameter based on the environmental perception information, and when the danger occurrence parameter is greater than a threshold, it is determined that a dangerous traffic scene currently exists. The danger parameter includes the vehicle's driving speed, the humidity value near the danger occurrence location, and the like.

[0163] It should be understood that the corresponding dangerous traffic scene will only occur when the environmental perception information meets the corresponding conditions, that is, the environmental perception information and the dangerous traffic scene have a corresponding relationship. For example, since the type of dangerous traffic scene 1 is caused by the characteristics of the road position itself, it can be directly determined that there is a dangerous traffic scene 1 when the vehicle travels to the vicinity of the dangerous location, that is, the dangerous traffic scene 1 has the corresponding vehicle location and this environmental perception information. The occurrence of dangerous traffic scene 2 may also be related to other environmental factors. For example, the vehicle speed and / or humidity will exceed a certain value before the corresponding dangerous traffic scene occurs on a certain road section. Therefore, when the vehicle travels to the vicinity of the corresponding dangerous location and the vehicle speed and / or humidity meet certain conditions, it is determined that there is a dangerous traffic scene, that is, dangerous traffic scene 2 has the corresponding vehicle position, vehicle speed and / or humidity and other environmental perception information.

[0164] Step S530, in response to the existence of a dangerous traffic scene, determining the type of the dangerous traffic scene.

[0165] Specifically, since each type of dangerous traffic scene has corresponding environmental perception information, this embodiment can determine the type of dangerous traffic scene by identifying environmental information such as vehicle location information. When it is determined that there is a dangerous traffic scene within the predetermined range, this embodiment identifies the environmental perception information to determine the type of the corresponding dangerous traffic scene.

[0166] Step S540, determining a target voice broadcast mode according to the type of the dangerous traffic scene, wherein the target voice broadcast mode is determined according to index data corresponding to at least one evaluation index collected during the historical simulated driving behavior corresponding to the dangerous traffic scene.

[0167] The location of the danger can be directly determined based on the location information of the identified vehicle, and then the target voice broadcast method can be determined based on the relationship between the location of the danger and the corresponding dangerous traffic scene type. For example, when the vehicle is determined to be in the section of the road where the dangerous traffic scene "a pedestrian at a bus stop suddenly rushes out from in front of a bus" occurs based on the location information of the vehicle, and is traveling towards the location of the danger, the target voice broadcast method is determined to be a voice broadcast content of "a bus stop is b meters ahead, please slow down" when the distance from the bus stop is b meters.

[0168] Step S550: Providing voice prompts using the target voice broadcasting method.

[0169] For example, when a dangerous traffic scene is "a pedestrian suddenly rushes out from in front of a bus at a bus stop", when the vehicle is b meters away from the bus stop, a voice prompt will be broadcasted saying "bus stop b meters ahead, please slow down". This allows the driver to operate the vehicle in time based on the corresponding voice prompt to avoid the occurrence of dangerous traffic scenes.

[0170] The embodiment of the present invention determines at least one candidate voice broadcast mode corresponding to the current dangerous traffic scene, each candidate voice broadcast mode has a corresponding voice broadcast information volume, collects a plurality of data sets corresponding to simulated driving behaviors, the data sets include index data corresponding to at least one evaluation index collected during each simulated driving behavior, each simulated driving behavior has a corresponding candidate voice broadcast mode, determines the score of each simulated driving behavior based on each data set, determines the comprehensive score of each candidate voice broadcast mode based on the score of each simulated driving behavior and the candidate voice broadcast mode corresponding to each simulated driving behavior, and determines the candidate voice broadcast mode with the highest comprehensive score as the target voice broadcast mode. Thus, the user can be prompted accordingly through the target voice broadcast mode corresponding to the dangerous traffic scene, so that the user can perform relevant operations in time, thereby effectively avoiding the occurrence of traffic accidents.

[0171] Figure 6 Schematic diagram of a voice broadcast determination system according to an embodiment of the present invention. Figure 6 As shown, the voice broadcast determination system 6 of the embodiment of the present invention includes a data acquisition device 61, a voice broadcast device 62, a memory 63 and a processor 64.

[0172] Among them, the data acquisition device 61 includes a driving simulation system and / or an eye tracker, which is used to collect at least one indicator data in the process of simulating driving behavior and send the indicator data to the memory. Specifically, the present embodiment can collect the data corresponding to each of the driving indicators through the driving simulation system, and collect the data corresponding to each of the visual indicators through the eye tracker. In some implementations, the data corresponding to the driving indicators or the data corresponding to the visual indicators can be used as the data set corresponding to each simulated driving behavior, so as to perform data analysis in the subsequent data analysis to determine the voice broadcast method. In other implementations, the data corresponding to the driving indicators and the data corresponding to the visual indicators can be used as the data set corresponding to each simulated driving behavior, so as to perform data analysis in the subsequent data analysis to determine the voice broadcast method.

[0173] The voice broadcast device 62 is used to broadcast the candidate voice broadcast modes. In some implementations, each simulated driving behavior has a corresponding candidate voice broadcast mode. By analyzing the data in the data set, the operation performed by the driver based on the corresponding voice broadcast mode can be determined, and then the driver's understanding of the voice broadcast can be determined, so as to select the optimal voice broadcast mode in the current dangerous scene based on the driver's understanding, thereby effectively avoiding the occurrence of traffic accidents.

[0174] The memory 63 is used to store indicator data and one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor 64 to implement the method described in steps S110 to S150.

[0175] Therefore, the embodiment of the present invention determines at least one candidate voice broadcast mode corresponding to the current dangerous traffic scene, each candidate voice broadcast mode has a corresponding voice broadcast information volume, collects a plurality of data sets corresponding to simulated driving behaviors, the data sets include index data corresponding to at least one evaluation index collected during each simulated driving behavior, each simulated driving behavior has a corresponding candidate voice broadcast mode, determines the score of each simulated driving behavior based on each data set, determines the comprehensive score of each candidate voice broadcast mode based on the score of each simulated driving behavior and the candidate voice broadcast mode corresponding to each simulated driving behavior, and determines the candidate voice broadcast mode with the highest comprehensive score as the target voice broadcast mode. Therefore, the user can be prompted accordingly through the target voice broadcast mode corresponding to the dangerous traffic scene, so that the user can perform relevant operations in time, thereby effectively avoiding the occurrence of traffic accidents.

[0176] Figure 7 Schematic diagram of a voice broadcast determination device according to an embodiment of the present invention. Figure 7 As shown, the voice broadcast determination device of the embodiment of the present invention includes a first determination module 71 , a collection module 72 , a second determination module 73 , a third determination module 74 and a fourth determination module 75 .

[0177] Among them, the first determination module 71 is configured to determine at least one candidate voice broadcast mode corresponding to the current dangerous traffic scene, and each candidate voice broadcast mode has a corresponding voice broadcast information volume. The acquisition module 72 is configured to collect a plurality of data sets corresponding to simulated driving, and the data set includes index data corresponding to at least one evaluation index collected during the simulated driving behavior, and the simulated driving has a corresponding candidate voice broadcast mode. The second determination module 73 is configured to determine the score of each simulated driving based on each of the data sets. The third determination module 74 is configured to determine the comprehensive score of each of the candidate voice broadcast modes based on the score of each simulated driving and the candidate voice broadcast mode corresponding to the simulated driving. The fourth determination module 75 is configured to determine the candidate voice broadcast mode with the highest comprehensive score as the target voice broadcast mode. Among them, the dangerous traffic scene is designed by a preset driving simulation system according to the data of the same type of historical dangerous traffic scene. Each of the candidate voice broadcast modes has a corresponding voice broadcast information content and / or voice broadcast position. The word classes in each of the voice broadcast information contents include at least one or a combination of the following: distance, road facilities, safety information, visual requirements and driving requirements. The at least one evaluation index includes a driving index and / or a visual index, the driving index includes vehicle speed, vehicle lateral displacement, vehicle longitudinal acceleration and / or steering wheel angular velocity, and the visual index includes a fixation point, a fixation area, a fixation number and / or a fixation time.

[0178] In some embodiments, the first determination module 71 further includes an acquisition unit, a calculation unit, and a candidate voice determination unit. The acquisition unit is configured to acquire voice broadcast information contents corresponding to a plurality of preset voice broadcast modes. The calculation unit is configured to calculate the entropy value of the voice broadcast information amount corresponding to each preset voice broadcast mode according to the ratio of the number of words of each feature name in each voice broadcast information content to the total number of words of the feature name. The candidate voice unit is configured to determine at least one candidate voice broadcast mode from each preset voice broadcast mode according to the ranking of the entropy values ​​of each voice broadcast information amount.

[0179] In some embodiments, the acquisition module 72 further includes a first acquisition unit and a second acquisition unit. The first acquisition unit is configured to acquire data corresponding to each of the driving indicators through a driving simulation system. The second acquisition unit is configured to acquire data corresponding to each of the visual indicators through an eye tracker.

[0180] In some embodiments, the second determination module 73 further includes an index data determination unit, a matrix determination unit, an ideal solution determination unit, and a score determination unit. The index data determination unit is configured to determine the index data corresponding to each of the evaluation indicators according to each of the data sets. The matrix determination unit is configured to perform data conversion processing on the index data of each of the evaluation indicators to determine the matrix corresponding to each of the evaluation indicators. The ideal solution determination unit is configured to determine the set of optimal values ​​and the set of worst values ​​in each of the matrices as positive ideal solutions and negative ideal solutions, respectively. The score determination unit is configured to calculate the distance between each of the index data in each of the simulated driving behaviors and the positive ideal solution and / or the negative ideal solution to determine the score of each of the simulated driving behaviors. Further, in some embodiments, the matrix determination unit further includes a standardization subunit, a calculation subunit, and a determination subunit, and the standardization subunit is configured to standardize the index data of each of the evaluation indicators. The calculation subunit is configured to calculate the index parameters and weights corresponding to each of the index data according to the standardized index data, and the index parameters represent the probability of the index data appearing in the corresponding evaluation indicator. The determination subunit is configured to multiply the indicator parameter corresponding to the indicator data in each of the evaluation indicators by a weight to determine a matrix corresponding to each of the evaluation indicators.

[0181] The embodiment of the present invention determines at least one candidate voice broadcast mode corresponding to the current dangerous traffic scene, each candidate voice broadcast mode has a corresponding voice broadcast information volume, collects a plurality of data sets corresponding to simulated driving behaviors, the data sets include index data corresponding to at least one evaluation index collected during each simulated driving behavior, each simulated driving behavior has a corresponding candidate voice broadcast mode, determines the score of each simulated driving behavior based on each data set, determines the comprehensive score of each candidate voice broadcast mode based on the score of each simulated driving behavior and the candidate voice broadcast mode corresponding to each simulated driving behavior, and determines the candidate voice broadcast mode with the highest comprehensive score as the target voice broadcast mode. Thus, the user can be prompted accordingly through the target voice broadcast mode corresponding to the dangerous traffic scene, so that the user can perform relevant operations in time, thereby effectively avoiding the occurrence of traffic accidents.

[0182] Figure 8 Schematic diagram of a voice prompt device according to an embodiment of the present invention. Figure 8 As shown, the voice prompting device of the embodiment of the present invention includes an acquisition module 81, a scene determination module 82, a type determination module 83, a mode determination module 84 and a prompting module 85.

[0183] Among them, the acquisition module 81 is configured to acquire driving information, and the driving information at least includes location information. The scene determination module 82 is configured to determine whether there is a dangerous traffic scene within a predetermined range based on the driving information. The type determination module 83 is configured to determine the type of the dangerous traffic scene in response to the existence of the dangerous traffic scene. The mode determination module 84 is configured to determine the target voice broadcast mode according to the type of the dangerous traffic scene, and the target voice broadcast mode is determined based on the indicator data corresponding to at least one evaluation indicator collected during the historical simulated driving behavior corresponding to the dangerous traffic scene. The prompt module 85 is configured to use the target voice broadcast mode for voice prompting.

[0184] In some embodiments, the voice prompt device also includes a storage module configured to store the relationship between the danger occurrence location and the corresponding dangerous traffic scene type.

[0185] In some embodiments, the driving information includes environmental perception information. The scene determination module 82 includes a parameter determination unit and a scene determination unit, wherein the parameter determination unit is configured to determine a current danger occurrence parameter according to the environmental perception information. The scene determination unit is configured to determine that a dangerous traffic scene currently exists in response to the danger occurrence parameter being greater than a threshold.

[0186] In some embodiments, the type determination module 83 further includes a recognition unit, which is configured to recognize the environmental perception information to determine the type of the corresponding dangerous traffic scene.

[0187] The embodiment of the present invention determines at least one candidate voice broadcast mode corresponding to the current dangerous traffic scene, each candidate voice broadcast mode has a corresponding voice broadcast information volume, collects a plurality of data sets corresponding to simulated driving behaviors, the data sets include index data corresponding to at least one evaluation index collected during each simulated driving behavior, each simulated driving behavior has a corresponding candidate voice broadcast mode, determines the score of each simulated driving behavior based on each data set, determines the comprehensive score of each candidate voice broadcast mode based on the score of each simulated driving behavior and the candidate voice broadcast mode corresponding to each simulated driving behavior, and determines the candidate voice broadcast mode with the highest comprehensive score as the target voice broadcast mode. Thus, the user can be prompted accordingly through the target voice broadcast mode corresponding to the dangerous traffic scene, so that the user can perform relevant operations in time, thereby effectively avoiding the occurrence of traffic accidents.

[0188] Fig. 9 Schematic diagram of an electronic device according to an embodiment of the present invention. Fig. 9 As shown, Fig. 9The electronic device shown is a general address query device, which includes a general computer hardware structure, which at least includes a processor 91 and a memory 92. The processor 91 and the memory 92 are connected via a bus 93. The memory 92 is suitable for storing instructions or programs executable by the processor 91. The processor 91 can be an independent microprocessor or a collection of one or more microprocessors. Thus, the processor 91 executes the instructions stored in the memory 92, 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 93 connects the above-mentioned multiple components together, and at the same time connects the above-mentioned components to the display controller 94 and the display device and the input / output (I / O) device 95. The input / output (I / O) device 95 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 95 is connected to the system via an input / output (I / O) controller 96.

[0189] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, devices (equipment) or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may adopt 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 code.

[0190] The present application 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.

[0191] 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.

[0192] 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.

[0193] Another embodiment of the present invention relates to a non-volatile storage medium for storing a computer-readable program, wherein the computer-readable program is used for a computer to execute part or all of the above method embodiments.

[0194] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by specifying relevant hardware through a program, and the program is stored in a storage medium, including several instructions for a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0195] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for determining a voice broadcast, characterized in that: The method comprises: Determine a plurality of candidate voice broadcast modes corresponding to the current dangerous traffic scene, each of the candidate voice broadcast modes having a corresponding amount of voice broadcast information; Collecting a data set corresponding to a plurality of simulated driving behaviors, the data set comprising index data corresponding to at least one evaluation index collected during each of the simulated driving behaviors, each of the simulated driving behaviors having a corresponding candidate voice broadcast mode; Determining a score for each of the simulated driving behaviors based on each of the data sets; Determining a comprehensive score of each of the candidate voice broadcasting methods based on the score of each of the simulated driving behaviors and the candidate voice broadcasting methods corresponding to each of the simulated driving behaviors; Determine the candidate voice broadcast mode with the highest comprehensive score as the target voice broadcast mode; The simulated driving behavior refers to a simulated driving process in which voice prompts are given in a corresponding candidate voice broadcast mode under the current dangerous traffic scenario; Among them, the at least one evaluation index includes a driving index and / or a visual index, and the driving index and the visual index are used to characterize the driver's understanding of the corresponding candidate voice broadcast method.

2. The method according to claim 1, characterized in that The dangerous traffic scenario is designed by preset simulation software based on data of similar historical dangerous traffic scenarios.

3. The method according to claim 1, characterized in that Each of the candidate voice broadcast modes has corresponding voice broadcast information content and / or voice broadcast position.

4. The method according to claim 3, characterized in that The word classes in each of the voice broadcast information contents include at least one or a combination of the following: distance, road facilities, safety information, visual requirements and driving requirements.

5. The method according to claim 1, characterized in that The multiple candidate voice broadcasting modes for determining the current dangerous traffic scene include: Obtain the voice broadcast information content corresponding to multiple preset voice broadcast modes; Calculate the entropy value of the voice broadcast information amount corresponding to each of the preset voice broadcast modes according to the ratio of the number of words of each feature name in the content of each voice broadcast information to the total number of words of the feature name; According to the ranking of the entropy values ​​of the voice broadcast information amounts, a plurality of candidate voice broadcast modes are determined from the preset voice broadcast modes.

6. The method according to claim 1, characterized in that The driving index includes vehicle speed, vehicle lateral displacement, vehicle longitudinal acceleration and / or steering wheel angular velocity, and the visual index includes gaze point, gaze area, gaze number and / or gaze time.

7. The method according to claim 6, characterized in that The collecting of data sets corresponding to multiple simulated driving behaviors includes: Collecting data corresponding to each of the driving indicators through a driving simulation system; and / or The data corresponding to each of the visual indicators is collected through an eye tracker.

8. The method according to claim 1, characterized in that: Determining the score of each of the simulated driving behaviors based on each of the data sets includes: Determine the indicator data corresponding to each of the evaluation indicators according to each of the data sets; Performing data conversion processing on the indicator data of each evaluation indicator to determine the matrix corresponding to each evaluation indicator; Determine the set of optimal values ​​and the set of worst values ​​in each of the matrices as a positive ideal solution and a negative ideal solution, respectively; The distance between each indicator data in each simulated driving behavior and the positive ideal solution and / or the negative ideal solution is calculated to determine the score of each simulated driving behavior.

9. The method according to claim 8, characterized in that The step of performing data conversion processing on the indicator data of each evaluation indicator to determine a matrix corresponding to each evaluation indicator includes: Standardizing the indicator data of each evaluation indicator; Calculate the indicator parameters and weights corresponding to each indicator data according to the standardized indicator data, wherein the indicator parameters represent the probability of the indicator data appearing in the corresponding evaluation indicator; The indicator parameter corresponding to the indicator data in each of the evaluation indicators is multiplied by the weight to determine the matrix corresponding to each of the evaluation indicators.

10. A voice prompt method, characterized in that: The method comprises: Acquiring driving information, wherein the driving information at least includes location information; determining whether there is a dangerous traffic scene within a predetermined range according to the driving information; In response to the presence of a dangerous traffic scene, determining a type of the dangerous traffic scene; Determining a target voice broadcast mode according to the type of the dangerous traffic scene, wherein the target voice broadcast mode is determined according to index data corresponding to at least one evaluation index collected during the historical simulated driving behavior corresponding to the dangerous traffic scene; Providing voice prompts using the target voice broadcasting method; The simulated driving behavior refers to a simulated driving process in which voice prompts are given in a corresponding candidate voice broadcast mode under the current dangerous traffic scenario; Among them, the at least one evaluation index includes a driving index and / or a visual index, and the driving index and the visual index are used to characterize the driver's understanding of the corresponding candidate voice broadcast method.

11. The method according to claim 10, characterized in that The method further comprises: Determine the dangerous locations of various dangerous traffic scenarios based on historical dangerous traffic scenario data; Store the relationship between the location where the danger occurs and the corresponding dangerous traffic scene type.

12. The method according to claim 10, characterized in that The driving information includes environmental perception information; Determining whether there is a dangerous traffic scene within a predetermined range according to the driving information includes: Determining current danger occurrence parameters according to the environmental perception information; In response to the danger occurrence parameter being greater than a threshold, it is determined that a dangerous traffic scene currently exists.

13. The method according to claim 12, characterized in that Determining the type of the dangerous traffic scene includes: The environmental perception information is identified to determine the type of the corresponding dangerous traffic scene.

14. A voice broadcast determination device, characterized in that: The device comprises: A first determination module is configured to determine a plurality of candidate voice broadcast modes corresponding to the current dangerous traffic scene, each of the candidate voice broadcast modes having a corresponding amount of voice broadcast information; A collection module is configured to collect a plurality of data sets corresponding to simulated driving, wherein the data sets include index data corresponding to at least one evaluation index collected during the simulated driving behavior, and the simulated driving has a corresponding candidate voice broadcast mode; A second determination module is configured to determine a score of each of the simulated drivings based on each of the data sets; A third determination module is configured to determine a comprehensive score of each of the candidate voice broadcasting methods based on the score of each of the simulated driving and the candidate voice broadcasting methods corresponding to the simulated driving; A fourth determination module is configured to determine the candidate voice broadcast mode with the highest comprehensive score as the target voice broadcast mode; The simulated driving behavior refers to a simulated driving process in which voice prompts are given in a corresponding candidate voice broadcast mode under the current dangerous traffic scenario; Among them, the at least one evaluation index includes a driving index and / or a visual index, and the driving index and the visual index are used to characterize the driver's understanding of the corresponding candidate voice broadcast method.

15. A voice prompting device, characterized in that: The device comprises: An acquisition module is configured to acquire driving information, wherein the driving information at least includes location information; A scene determination module, configured to determine whether there is a dangerous traffic scene within a predetermined range according to the driving information; a type determination module, configured to determine the type of the dangerous traffic scene in response to the presence of the dangerous traffic scene; A mode determination module is configured to determine a target voice broadcast mode according to the type of the dangerous traffic scene, wherein the target voice broadcast mode is determined according to index data corresponding to at least one evaluation index collected during the historical simulated driving behavior corresponding to the dangerous traffic scene; A prompt module is configured to use the target voice broadcast mode to provide voice prompts; The simulated driving behavior refers to a simulated driving process in which voice prompts are given in a corresponding candidate voice broadcast mode under the current dangerous traffic scenario; Among them, the at least one evaluation index includes a driving index and / or a visual index, and the driving index and the visual index are used to characterize the driver's understanding of the corresponding candidate voice broadcast method.

16. A voice broadcast determination system, characterized in that: The system comprises: A data collection device, including a driving simulation system and / or an eye tracker, for collecting at least one indicator data during the simulated driving behavior and sending the indicator data to a memory; A voice broadcasting device, used for broadcasting candidate voice broadcasting modes; A memory and a processor, wherein the memory is used to store indicator data and 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 1-9.

17. 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 1-13.

18. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 13 is implemented.

19. A computer program product, characterized in that When the computer program product is run on a computer, the computer is caused to execute the method according to any one of claims 1 to 13.

Images