Method and device for determining emotion detection frequency, equipment and medium

Abstract

The invention discloses an emotion detection frequency determination method and device, equipment and a medium, and relates to the technical field of intelligent vehicles, and the method comprises the steps: obtaining an emotion detection reference frequency and vehicle driving information of a total driving distance of a vehicle driver in a current time period; according to the vehicle driving information, predicting an emotion abnormal probability of a vehicle driver in a future time period; wherein the future time period is adjacent to the current time period and is located after the current time period; adjusting the emotion detection reference frequency according to the vehicle driving information and the emotion abnormal probability in the future time period to obtain the emotion detection frequency of the future time period, and performing emotion detection on the vehicle driver in the future time period according to the emotion detection frequency. And the computing power resource and the electric power resource of the vehicle are saved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent vehicle technology, and in particular to a method, device, equipment and medium for determining an emotion detection frequency. Background Art

[0002] With the development of smart cars and autonomous driving technology, intelligent management of the in-vehicle environment and detection of vehicle driver emotions have become particularly important. At present, vehicle driver emotion detection methods mainly rely on visual information and judge the emotional state of vehicle drivers by analyzing their facial expressions in real time.

[0003] This prior art will detect the emotional state of the driver in real time during the driving process, continuously occupying high computing resources and consuming power resources. Although the driver's emotions fluctuate during driving, they remain generally stable. The technical solution for real-time emotional state detection in the prior art has the defect of wasting resources. Summary of the invention

[0004] The present invention provides a method, device, equipment and medium for determining the frequency of emotion detection, so as to improve the flexibility of emotion detection and save the computing power resources and power resources of the vehicle.

[0005] In a first aspect, the present invention provides a method for determining an emotion detection frequency, comprising:

[0006] Obtaining the emotion detection benchmark frequency and the vehicle driving information of the total distance driven by the vehicle driver in the current time period;

[0007] Predicting the probability of abnormal emotions of the vehicle driver in a future time period according to the vehicle driving information; wherein the future time period is adjacent to the current time period and is located after the current time period;

[0008] According to the vehicle driving information and the probability of abnormal emotions in the future time period, the emotion detection reference frequency is adjusted to obtain the emotion detection frequency in the future time period, so as to perform emotion detection on the vehicle driver in the future time period according to the emotion detection frequency.

[0009] In a second aspect, the present invention further provides a device for determining an emotion detection frequency, comprising:

[0010] An information acquisition module, used to acquire a reference frequency of emotion detection and vehicle driving information of the vehicle driver in a current time period;

[0011] A probability prediction module, used to predict the probability of abnormal emotions of the vehicle driver in the current time period based on the vehicle driving information in the current time period;

[0012] The frequency adjustment module is used to adjust the emotion detection reference frequency according to the emotion abnormality probability in the current time period and the emotion abnormality probability in the current time period, so as to obtain the emotion detection frequency in the future time period, so as to perform emotion detection on the vehicle driver in the future time period according to the emotion detection frequency; wherein the future time period is a time period adjacent to the current time period and located after the current time period.

[0013] In a third aspect, an embodiment of the present invention further provides an electronic device, including:

[0014] at least one processor; and

[0015] a memory communicatively coupled to at least one processor; wherein

[0016] The memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor so that the at least one processor can execute the method for determining the emotion detection frequency provided by any embodiment of the present invention.

[0017] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining the emotion detection frequency of any embodiment of the present invention when executed.

[0018] The technical solution of the embodiment of the present invention obtains the emotion detection reference frequency and the vehicle driving information of the total distance driven by the vehicle driver in the current time period; predicts the probability of abnormal emotion of the vehicle driver in the future time period according to the vehicle driving information; wherein the future time period is adjacent to the current time period and is located after the current time period; adjusts the emotion detection reference frequency according to the vehicle driving information and the probability of abnormal emotion in the future time period to obtain the emotion detection frequency of the future time period, so as to perform emotion detection on the vehicle driver in the future time period according to the emotion detection frequency. Compared with the technical solution of real-time detection in the prior art, the embodiment of the present invention can predict the probability of abnormal emotion of the vehicle driver in the future time period according to the vehicle driving information in the current time period, and flexibly adjusts the emotion detection reference probability according to the probability of abnormal emotion in the future time period and the vehicle driving information in the current time period. When predicting that the vehicle driver has abnormal emotion, the detection frequency is increased, and when predicting that the vehicle driver has stable emotion, the detection frequency is reduced. By intermittently detecting the emotion of the vehicle driver, the occupation of computing resources is reduced, and the vehicle's power resources are also saved.

[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 is a flow chart of a method for determining emotion detection frequency provided according to Embodiment 1 of the present invention;

[0022] Figure 2 is a flow chart of a method for determining emotion detection frequency provided according to Embodiment 2 of the present invention;

[0023] Figure 3 is a flow chart of a method for determining emotion detection frequency provided according to Embodiment 3 of the present invention;

[0024] Figure 4 is a schematic diagram of the structure of a device for determining emotion detection frequency provided according to a fourth embodiment of the present invention;

[0025] Figure 5 It is a structural schematic diagram of an electronic device for implementing the method for determining the emotion detection frequency according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first" and "second" and the like in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] In the technical solution of the embodiment of the present invention, the acquisition, storage and application of the emotion detection reference frequency and vehicle driving information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0029] Embodiment 1

[0030] Figure 1 A flowchart of a method for determining an emotion detection frequency is provided in Embodiment 1 of the present invention. This embodiment is applicable to the case of determining the emotion detection frequency of a vehicle driver. The method can be executed by a device for determining an emotion detection frequency. The device for determining an emotion detection frequency can be implemented in the form of hardware and / or software and specifically configured in an electronic device, such as a server.

[0031] See also Figure 1 The method for determining the emotion detection frequency shown includes:

[0032] S101. Obtaining an emotion detection reference frequency and vehicle driving information of a total distance driven by a vehicle driver in a current time period.

[0033] In this embodiment, the emotion detection reference frequency may be a reference value of the frequency of emotion detection for the vehicle driver. The current time period may be a time period to which the current real moment belongs. The vehicle driving information may include but is not limited to at least one of vehicle control information and external environment information. It should be noted that the specific value of the emotion detection reference frequency and the duration of the time period can be independently set by the technician according to real-time needs or practical experience, and the present invention does not limit this.

[0034] Among them, the vehicle driving information of the total distance driven by the vehicle driver in the current time period may refer to the vehicle driving information of the total distance driven by the vehicle driver from the moment the vehicle was started to the current time period.

[0035] Optionally, the vehicle control information may include but is not limited to the frequency of honking, the continuous driving time and the total driving time; the external environment information may include but is not limited to the average waiting time at traffic lights and the number of times being overtaken, that is, the vehicle driving information may include but is not limited to the frequency of honking, the average waiting time at traffic lights, the continuous driving time, the total driving time and the number of times being overtaken.

[0036] The honking frequency may be the frequency of the honking of the horn by the vehicle driver. The average waiting time for the signal light may be the average time for the vehicle driver to wait for the signal light to change from the indication color of prohibiting passage to the indication color of allowing passage. The continuous driving time may be the time the vehicle driver continuously drives the vehicle. The total driving time may be the total driving time in a vehicle driving process; illustratively, if the vehicle driver does not stop during a vehicle driving process, the total driving time is the same as the continuous driving time; if the vehicle driver stops once during a vehicle driving process, the total driving time is the sum of the parking time and the duration between the two continuous driving times; wherein, the length of the parking time between the two adjacent continuous driving times can be used to determine whether the two adjacent continuous driving times belong to the same vehicle driving process. The number of times overtaken may be the number of times the vehicle driven by the vehicle driver is overtaken by other vehicles.

[0037] In a specific embodiment, for each time period, vehicle driving information of the vehicle in the time period is collected; if the starting moment of the current time period is the vehicle start-up moment, that is, the current time period is the first time period after the vehicle is started, the vehicle driving information collected in the current time period is determined as the vehicle driving information of the total distance driven by the vehicle driver; if the starting moment of the current time period is not the vehicle start-up moment, that is, there is a historical time period before the current time period, the vehicle driving information of the total distance driven by the vehicle driver in the historical time period and the vehicle driving information collected in the current time period are counted to obtain the vehicle driving information of the total distance driven by the vehicle driver in the current time period; wherein the historical time period is a time period adjacent to the current time period and located before the current time period; the duration of the historical time period is the same as the duration of the current time period.

[0038] S102. Predicting the probability of abnormal emotions of the vehicle driver in a future time period based on the vehicle driving information; wherein the future time period is adjacent to the current time period and is located after the current time period.

[0039] In this embodiment, the probability of abnormal emotion may refer to the probability of abnormal emotion of the vehicle driver, wherein abnormal emotion may refer to excessive emotion such as irritability and excitement. The length of the future time period, the length of the current time period and the length of the historical time period are the same. Specifically, a certain algorithm may be used to predict the probability of abnormal emotion of the vehicle driver in the future time period according to the vehicle driving information.

[0040] S103. According to the vehicle driving information and the probability of abnormal emotions in the future time period, the emotion detection reference frequency is adjusted to obtain the emotion detection frequency in the future time period, so as to perform emotion detection on the vehicle driver in the future time period according to the emotion detection frequency.

[0041] In this embodiment, the emotion detection frequency may be the frequency of emotion detection on the vehicle driver in the future time period. Specifically, a certain algorithm may be used to adjust the emotion detection reference frequency according to the vehicle driving information and the probability of abnormal emotions in the future time period to obtain the emotion detection frequency in the future time period, so as to detect the emotion of the vehicle driver according to the emotion detection frequency.

[0042] Optionally, after obtaining the emotion detection frequency in the future time period, the method further includes: collecting a facial image of the vehicle driver in the future time period according to the emotion detection frequency; and performing emotion detection on the vehicle driver according to the facial image.

[0043] For example, if the emotion detection frequency is twice per minute and the length of the future time period is two minutes, then in the future time period, the facial image of the vehicle driver is collected every 30 seconds; and after each facial image is collected, the emotion detection of the vehicle driver is performed based on the facial image. It should be noted that any existing technology can be used to perform emotion detection on the vehicle driver through facial images, and the present invention is not limited to this.

[0044] It can be understood that by adopting the above-mentioned technical scheme, the facial image of the vehicle driver can be collected according to the emotion detection frequency, and the emotion of the vehicle driver can be recognized after the facial image is collected, so as to flexibly adjust the frequency of facial image collection, which can further reduce the computing power occupation and the power resource occupation in the vehicle.

[0045] The technical solution of the embodiment of the present invention obtains the emotion detection reference frequency and the vehicle driving information of the total distance driven by the vehicle driver in the current time period; predicts the probability of abnormal emotion of the vehicle driver in the future time period according to the vehicle driving information; wherein the future time period is adjacent to the current time period and is located after the current time period; adjusts the emotion detection reference frequency according to the vehicle driving information and the probability of abnormal emotion in the future time period to obtain the emotion detection frequency of the future time period, so as to perform emotion detection on the vehicle driver in the future time period according to the emotion detection frequency. Compared with the technical solution of real-time detection in the prior art, the embodiment of the present invention can predict the probability of abnormal emotion of the vehicle driver in the future time period according to the vehicle driving information in the current time period, and flexibly adjusts the emotion detection reference probability according to the probability of abnormal emotion in the future time period and the vehicle driving information in the current time period. When predicting that the vehicle driver has abnormal emotion, the detection frequency is increased, and when predicting that the vehicle driver has stable emotion, the detection frequency is reduced. By intermittently detecting the emotion of the vehicle driver, the occupation of computing resources is reduced, and the vehicle's power resources are also saved.

[0046] Embodiment 2

[0047] Figure 2 This is a flow chart of a method for determining an emotion detection frequency provided in the second embodiment of the present invention. Based on the technical solutions of the above embodiments, the embodiment of the present invention optimizes and improves the prediction operation of the probability of abnormal emotions.

[0048] Further, "predicting the probability of abnormal emotions of the vehicle driver in the future time period based on the vehicle driving information" is refined into "fusing the frequency of honking and the number of times being overtaken to obtain the first fused data; fusing the average waiting time at the traffic light, the continuous driving time and the total driving time to obtain the second fused data; fusing the number of times being overtaken and the total driving time to obtain the third fused data; fusing the frequency of honking, the average waiting time at the traffic light and the number of times being overtaken to obtain the fourth fused data; fusing the continuous driving time and the total driving time to obtain the fifth fused data; fusing the honking rating rate, the average waiting time at the traffic light, the number of times being overtaken and the continuous driving time to obtain the sixth fused data; through the trained risk prediction model, according to the first fused data, the second fused data, the third fused data, the fourth fused data, the fifth fused data and the sixth fused data, predicting the probability of abnormal emotions of the vehicle driver in the future time period" to improve the prediction operation of the probability of abnormal emotions.

[0049] It should be noted that, for the parts not described in detail in the embodiments of the present invention, reference may be made to the descriptions in the aforementioned embodiments.

[0050] See also Figure 2 The method for determining the emotion detection frequency shown includes:

[0051] S201. Obtaining an emotion detection reference frequency and vehicle driving information of a total distance driven by the vehicle driver in a current time period.

[0052] In this embodiment, the vehicle driving information may include, but is not limited to, the frequency of honking, the average waiting time at traffic lights, the continuous driving time, the total driving time, and the number of times the vehicle was overtaken.

[0053] S202: Fuse the horn honking frequency and the number of times of being overtaken to obtain first fused data.

[0054] Specifically, a certain algorithm is used to fuse the honking frequency and the number of times the vehicle is overtaken to obtain the first fused data. Optionally, the honking frequency and the number of times the vehicle is overtaken to obtain the first fused data include: performing a logarithmic transformation on the number of times the vehicle is overtaken to obtain a logarithmic transformation result; determining the product between the logarithmic transformation result and the honking frequency; performing an exponential transformation on the product to obtain the first fused data. Exemplarily, the first fused data can be determined by the following formula:

[0055] R1=eh×log(1+o) ;

[0056] Among them, R1 represents the first fusion data; h represents the frequency of honking; o represents the number of times being overtaken; log(1+o) represents the logarithmic transformation result.

[0057] It can be understood that by adopting the above technical solution, the number of overtaken times can be smoothed by performing a logarithmic transformation on the number of times overtaken, thereby avoiding the impact of an excessively large number of overtaken times on the accuracy of the probability of abnormal emotions; and by performing an exponential transformation on the product of the logarithmic transformation result and the honking frequency, the compound effect between the honking frequency and the number of times overtaken can be amplified, so that the first fusion data obtained has a stronger feature of abnormal emotions.

[0058] S203: Fuse the average waiting time at the traffic light, the continuous driving time, and the total driving time to obtain second fused data.

[0059] Specifically, the product of the average waiting time at the traffic light and the continuous driving time is determined; the ratio between the obtained product and the total driving time is determined, and the square value of the obtained ratio is determined. Exemplarily, the second fused data can be determined by the following formula:

[0060]

[0061] Among them, R2 represents the second fusion data; a represents the average waiting time at the traffic light; c represents the continuous driving time; and t represents the total driving time.

[0062] It can be understood that by adopting the above technical solution, by determining the product of the average waiting time for the traffic light and the continuous driving time; determining the ratio between the obtained product and the total driving time, and determining the square value of the obtained ratio, the comprehensive effect between the average waiting time for the traffic light and the driving time can be amplified, so that the second fusion data obtained has a stronger feature of abnormal emotions.

[0063] S204: Fuse the number of times of being overtaken and the total driving time to obtain third fused data.

[0064] Specifically, determine the ratio between the number of times of being overtaken and the total driving time; determine the square root of the obtained ratio; determine the cube of the obtained square root, and determine the obtained cube as the third fused data; illustratively, the third fused data can be determined by the following formula:

[0065]

[0066] Wherein, R3 represents the third fused data.

[0067] It can be understood that by adopting the above technical solution, the square root of the ratio between the number of times being overtaken and the total driving time can be taken first and then a cubic calculation can be performed, so that the initial changes in the number of times being overtaken and the total driving time can be smoothed through the square root operation, making the data more stable; through the cubic operation, the smoothed data can be further amplified, making the characteristics of abnormal emotions more prominent.

[0068] S205: Fuse the horn honking frequency, the average waiting time at the traffic light, and the number of times of being overtaken to obtain fourth fused data.

[0069] Specifically, the honking frequency, the average waiting time at the traffic light, and the number of times of being overtaken are weighted and fused to obtain the fourth fused data; illustratively, the fourth fused data can be determined by the following formula:

[0070] R4=α×h+β×a+γ×o;

[0071] Among them, R4 represents the fourth fusion data; α represents the weight corresponding to the frequency of honking; β represents the weight corresponding to the average waiting time of the traffic light; γ represents the weight corresponding to the number of times being overtaken.

[0072] It should be noted that the weight corresponding to the frequency of honking, the weight corresponding to the average waiting time at the traffic light, and the weight corresponding to the number of times being overtaken can be independently set by technical personnel based on actual needs or practical experience, and the present invention does not limit this.

[0073] It is understandable that by adopting the above technical solution, the fourth fusion data can be obtained through weighted combination, integrating the frequency of honking, the average waiting time of traffic lights and the number of times being overtaken, so that the fourth fusion data obtained can more comprehensively represent the emotional state of the driver.

[0074] S206: Fuse the continuous driving time and the total driving time to obtain fifth fused data.

[0075] Specifically, the ratio between the continuous driving time and the total driving time is determined; the logarithm of the obtained ratio is determined, and the obtained logarithm result is determined as the fifth fused data; illustratively, the fifth fused data can be determined by the following formula:

[0076]

[0077] Among them, R5 represents the fifth fusion data.

[0078] It can be understood that by adopting the above technical scheme, the fifth fusion data obtained by determining the logarithm of the ratio between the continuous driving time and the total driving time can characterize the impact of the relative change of the continuous driving time between the total driving time on the emotions of the vehicle driver, so that the obtained fifth fusion data has a stronger feature of abnormal emotions.

[0079] S207: Fuse the honking evaluation rate, the average waiting time at the traffic light, the number of times of being overtaken, and the continuous driving time to obtain sixth fused data.

[0080] Specifically, the product of the honking evaluation rate and the average waiting time of the traffic light is determined; the square value of the obtained product is determined; the product of the number of times of being overtaken and the continuous driving time is determined; the sum of the product of the number of times of being overtaken and the continuous driving time and the obtained square value is determined as the sixth fused data; illustratively, the sixth fused data can be determined by the following formula:

[0081] R6=(h×a) 2 +o×c;

[0082] Among them, R6 represents the sixth fusion data.

[0083] It can be understood that the above technical solution can amplify the characteristic representation of the vehicle driver's emotions by the frequency of honking, the average waiting time at traffic lights, the number of times being overtaken and the continuous driving time, so that the sixth fusion data obtained has a stronger characteristic of abnormal emotions.

[0084] S208. Predict the probability of abnormal emotions of the vehicle driver in the current driving event through the trained risk prediction model according to the first fusion data, the second fusion data, the third fusion data, the fourth fusion data, the fifth fusion data and the sixth fusion data; wherein the future time period is a time period adjacent to the current time period and located after the current time period.

[0085] In this embodiment, the risk prediction model can be a neural network model for predicting the probability of abnormal emotions of the vehicle driver, for example, a regression model or a hidden Markov model. Specifically, the first fusion data, the second fusion data, the third fusion data, the fourth fusion data, the fifth fusion data and the sixth fusion data are input into the trained risk prediction model to obtain the probability of abnormal emotions of the vehicle driver in the future time period.

[0086] In a specific embodiment, the risk prediction model may include an input layer, hidden layer 1, hidden layer 2, hidden layer 3 and an output layer; hidden layer 1 may be a fully connected layer including 64 neurons and a ReLU activation function; hidden layer 2 may be a fully connected layer including 32 neurons and a ReLU activation function; hidden layer 3 may be a fully connected layer including 16 neurons and a ReLU activation function; the output layer may include one neuron and a Sigmoid activation function.

[0087] S209. According to the vehicle driving information in the current time period and the probability of abnormal emotions in the future time period, the emotion detection reference frequency is adjusted to obtain the emotion detection frequency in the future time period, so as to perform emotion detection on the vehicle driver in the future time period according to the emotion detection frequency.

[0088] The embodiment of the present invention obtains the first fused data by fusing the honking frequency and the number of times being overtaken; obtains the second fused data by fusing the average waiting time for traffic lights, the continuous driving time and the total driving time; obtains the third fused data by fusing the number of times being overtaken and the total driving time; obtains the fourth fused data by fusing the honking frequency, the average waiting time for traffic lights and the number of times being overtaken; obtains the fifth fused data by fusing the continuous driving time and the total driving time; obtains the sixth fused data by fusing the honking rating rate, the average waiting time for traffic lights, the number of times being overtaken and the continuous driving time; and predicts the probability of abnormal emotions of the vehicle driver in the future time period according to the first fused data, the second fused data, the third fused data, the fourth fused data, the fifth fused data and the sixth fused data through the trained risk prediction model, and can fuse the vehicle driving information to obtain the first fused data, the second fused data, the third fused data, the fourth fused data, the fifth fused data and the sixth fused data with enhanced features, and input them into the risk prediction model to obtain the probability of abnormal emotions of the vehicle driver, thereby improving the accuracy of the probability of abnormal emotions.

[0089] Embodiment 3

[0090] Figure 3 This is a flow chart of a method for determining an emotion detection frequency provided in a third embodiment of the present invention. Based on the technical solutions of the above embodiments, the embodiment of the present invention optimizes and improves the allocation operation of candidate cranes.

[0091] Furthermore, “according to the vehicle driving information and the probability of abnormal emotions in the future time period, the emotion detection baseline frequency is adjusted to obtain the emotion detection frequency in the future time period” is refined into “performing a logarithmic transformation on the horn frequency to obtain the transformed data; fusing the average waiting time for traffic lights and the total driving time to obtain the seventh fused data; fusing the number of times of being overtaken and the continuous driving time to obtain the eighth fused data; according to the probability of abnormal emotions, the transformed data, the seventh fused data and the eighth fused data, the emotion baseline frequency is adjusted to obtain the emotion detection frequency in the future time period”, so as to improve the allocation operation of the candidate tower cranes.

[0092] It should be noted that, for the parts not described in detail in the embodiments of the present invention, reference may be made to the descriptions in the aforementioned embodiments.

[0093] See also Figure 3 The method for determining the emotion detection frequency shown includes:

[0094] S301. Obtaining an emotion detection reference frequency and vehicle driving information of a total distance driven by the vehicle driver in a current time period.

[0095] S302. Predicting the probability of abnormal emotions of the vehicle driver in a future time period based on the vehicle driving information; wherein the future time period is adjacent to the current time period and is located after the current time period.

[0096] S303: Perform logarithmic transformation on the whistle frequency to obtain transformed data.

[0097] Exemplarily, the transformation data may be determined by the following formula:

[0098] S=log (1+h) ;

[0099] Wherein, S represents the transformed data.

[0100] It is understandable that by adopting the above technical solution and performing a logarithmic transformation on the whistle frequency, the whistle frequency can be compressed, so that the whistle frequency tends to be flat with respect to the emotion detection frequency, thereby avoiding extreme values ​​of the whistle frequency causing drastic fluctuations in the determined emotion detection frequency.

[0101] S304: Fuse the average waiting time at the traffic light and the total driving time to obtain seventh fused data.

[0102] Specifically, the ratio between the average waiting time at the traffic light and the total driving time is determined; the square value of the obtained ratio is determined as the seventh fusion data; illustratively, the seventh fusion data can be determined by the following formula:

[0103]

[0104] Among them, R7 represents the seventh fusion data.

[0105] It can be understood that, by adopting the above technical scheme, by determining the ratio between the average waiting time of the traffic light and the total driving time; the square value of the obtained ratio is determined as the seventh fusion data, the average waiting time of the traffic light can be smoothed by the total driving time, and the influence of the waiting time of the traffic light on abnormal emotions can be amplified through the square transformation, thereby improving the matching rate of the emotion detection frequency and the emotional state of the vehicle driver.

[0106] S305: Fuse the number of times of being overtaken and the continuous driving time to obtain eighth fused data.

[0107] Specifically, the ratio between the number of times of being overtaken and the continuous driving time is determined; the obtained ratio is subjected to exponential transformation to obtain the eighth fusion data; illustratively, the eighth fusion data may be determined by the following formula:

[0108]

[0109] Among them, R8 represents the eighth fusion data.

[0110] It can be understood that, by adopting the above technical solution, the ratio between the number of times being overtaken and the continuous driving time is determined; the obtained ratio is subjected to exponential transformation to obtain the eighth fusion data, which can determine the frequency of being overtaken within the continuous driving time and perform exponential transformation, thereby amplifying the influence of the frequency of being overtaken on the determination of the emotion detection frequency, and improving the matching rate of the emotion detection frequency and the emotional state of the vehicle driver.

[0111] S306. Adjust the emotion reference frequency according to the emotion abnormality probability, the transformed data, the seventh fusion data and the eighth fusion data to obtain the emotion detection frequency of the future time period, so as to perform emotion detection on the vehicle driver in the future time period according to the emotion detection frequency.

[0112] Specifically, a certain algorithm is used to adjust the emotion reference frequency according to the emotion abnormality probability, the transformed data, the seventh fusion data and the eighth fusion data to obtain the emotion detection frequency of the future time period.

[0113] Optionally, the emotion baseline frequency is adjusted according to the emotion abnormality probability, the transformed data, the seventh fusion data and the eighth fusion data to obtain the emotion detection frequency for the future time period, including: weighted fusion of the emotion abnormality probability, the transformed data, the seventh fusion data and the eighth fusion data to obtain a weighted fusion result; according to the weighted fusion result, the emotion baseline probability is adjusted to obtain the emotion detection frequency for the future time period.

[0114] Specifically, the weighted fusion result is added to the emotion reference detection frequency to obtain the emotion detection frequency corresponding to the future time period. Exemplarily, the emotion detection frequency can be determined by the following formula:

[0115] F=f+Q1×P+Q2×S+Q3×R7+Q4×R8;

[0116] Among them, F represents the frequency of emotion detection; f represents the baseline probability of emotion detection; Q1 represents the weight corresponding to the probability of emotion abnormality; P represents the probability of emotion abnormality; Q2 represents the weight corresponding to the transformed data; Q3 represents the weight corresponding to the seventh fusion data; Q4 represents the weight corresponding to the eighth fusion data.

[0117] It should be noted that the weights corresponding to the transformed data, the weights corresponding to the seventh fused data, and the weights corresponding to the eighth fused data can be independently set by technical personnel according to actual needs or practical experience, and the present invention does not limit this.

[0118] It is understandable that by adopting the above technical scheme, the emotion detection baseline probability can be adjusted through weighted combination, comprehensive emotion abnormality probability, transformation data, seventh fusion data and eighth fusion data, thereby improving the matching rate between the emotion detection frequency and the emotional state of the vehicle driver.

[0119] The embodiment of the present invention performs logarithmic transformation on the horn frequency to obtain transformation data; fuses the average waiting time for traffic lights and the total driving time to obtain seventh fused data; fuses the number of times of being overtaken and the continuous driving time to obtain eighth fused data; adjusts the emotion reference frequency according to the emotion abnormality probability, the transformation data, the seventh fused data and the eighth fused data to obtain the emotion detection frequency of the future time period, so that when the emotion of the vehicle driver is abnormal, the emotion detection of the vehicle driver is performed at a higher emotion detection frequency, and when the emotional state of the vehicle driver is stable, the emotion detection of the vehicle driver is performed at a lower emotion detection probability, thereby improving the matching degree between the emotion detection frequency and the emotional state of the vehicle driver.

[0120] Embodiment 4

[0121] Figure 4 A schematic diagram of the structure of a device for determining an emotion detection frequency provided in Embodiment 4 of the present invention. This embodiment can be applied to the case of determining the emotion detection frequency of a vehicle driver, the device can execute a method for determining an emotion detection frequency, the device for determining an emotion detection frequency can be implemented in the form of hardware and / or software, and the device can be configured in an electronic device.

[0122] See also Figure 4 The device for determining the emotion detection frequency shown in the figure comprises an information acquisition module 401, a probability prediction module 402 and a frequency adjustment module 403, wherein:

[0123] The information acquisition module 401 is used to acquire the emotion detection reference frequency and the vehicle driving information of the total distance driven by the vehicle driver in the current time period;

[0124] The probability prediction module 402 is used to predict the probability of abnormal emotions of the vehicle driver in a future time period according to the vehicle driving information; wherein the future time period is adjacent to the current time period and is located after the current time period;

[0125] The frequency adjustment module 403 is used to adjust the emotion detection reference frequency according to the vehicle driving information and the probability of emotion abnormality in the future time period, and obtain the emotion detection frequency of the future time period, so as to perform emotion detection on the vehicle driver in the future time period according to the emotion detection frequency.

[0126] The embodiment of the present invention obtains the emotion detection reference frequency and the vehicle driving information of the total distance driven by the vehicle driver in the current time period through the information acquisition module; predicts the probability of abnormal emotion of the vehicle driver in the future time period according to the vehicle driving information through the probability prediction module; wherein the future time period is adjacent to the current time period and is located after the current time period; adjusts the emotion detection reference frequency according to the vehicle driving information and the probability of abnormal emotion in the future time period through the frequency adjustment module to obtain the emotion detection frequency of the future time period, so as to perform emotion detection on the vehicle driver in the future time period according to the emotion detection frequency. Compared with the technical solution of real-time detection in the prior art, the embodiment of the present invention can predict the probability of abnormal emotion of the vehicle driver in the future time period according to the vehicle driving information in the current time period, and flexibly adjust the emotion detection reference probability according to the probability of abnormal emotion in the future time period and the vehicle driving information in the current time period. When predicting that the vehicle driver has abnormal emotion, the detection frequency is increased, and when predicting that the vehicle driver has stable emotion, the detection frequency is reduced. By intermittently detecting the emotion of the vehicle driver, the occupation of computing resources is reduced, and the power resources of the vehicle are also saved.

[0127] Optionally, the vehicle driving information includes the frequency of honking, the average waiting time at traffic lights, the continuous driving time, the total driving time and the number of times being overtaken.

[0128] Optionally, the probability prediction module 402 includes:

[0129] A first fusion unit is used to fuse the horn honking frequency and the number of times of being overtaken to obtain first fusion data;

[0130] A second fusion unit is used to fuse the average waiting time of the traffic light, the continuous driving time and the total driving time to obtain second fusion data;

[0131] A third fusion unit is used to fuse the number of times of being overtaken and the total driving time to obtain third fusion data;

[0132] a fourth fusion unit, for fusing the horn frequency, the average waiting time at the traffic light, and the number of times of being overtaken to obtain fourth fusion data;

[0133] a fifth fusion unit, configured to fuse the continuous driving time and the total driving time to obtain fifth fusion data;

[0134] A sixth fusion unit is used to fuse the honking evaluation rate, the average waiting time at the traffic light, the number of times of being overtaken, and the continuous driving time to obtain sixth fusion data;

[0135] The probability prediction unit is used to predict the probability of abnormal emotions of the vehicle driver in a future time period according to the first fusion data, the second fusion data, the third fusion data, the fourth fusion data, the fifth fusion data and the sixth fusion data through the trained risk prediction model.

[0136] Optionally, the first fusion unit is specifically used for:

[0137] Perform logarithmic transformation on the number of times of being overtaken to obtain the logarithmic transformation result;

[0138] Determine the product between the logarithmic transformation result and the whistle frequency;

[0139] Perform exponential transformation on the product to obtain first fused data.

[0140] Optionally, the frequency adjustment module 402 includes:

[0141] A transformation unit, used for performing logarithmic transformation on the whistle frequency to obtain transformation data;

[0142] a seventh fusion unit, used for fusing the average waiting time of the traffic light and the total driving time to obtain seventh fusion data;

[0143] an eighth fusion unit, used for fusing the number of times of being overtaken and the continuous driving time to obtain eighth fusion data;

[0144] The frequency adjustment unit adjusts the emotion reference frequency according to the emotion abnormality probability, the transformation data, the seventh fusion data and the eighth fusion data to obtain the emotion detection frequency of the future time period.

[0145] Optionally, the frequency adjustment unit is specifically used for:

[0146] Performing weighted fusion on the emotion abnormality probability, the transformed data, the seventh fusion data and the eighth fusion data to obtain a weighted fusion result;

[0147] According to the weighted fusion results, the emotion baseline probability is adjusted to obtain the emotion detection frequency in the future time period.

[0148] Optionally, the device further comprises:

[0149] An image acquisition module, for acquiring a facial image of a vehicle driver in a future time period according to the emotion detection frequency;

[0150] The emotion detection module is used to detect the emotion of the vehicle driver based on the facial image.

[0151] The device for determining the emotion detection frequency provided in the embodiment of the present invention can execute the method for determining the emotion detection frequency provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method for determining the emotion detection frequency.

[0152] Embodiment 5

[0153] Figure 5 A schematic diagram of the structure of an electronic device 500 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0154] like Figure 5 As shown, the electronic device 500 includes at least one processor 501, and a memory connected to the at least one processor 501 in communication, such as a read-only memory (ROM) 502, a random access memory (RAM) 503, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 501 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 502 or the computer program loaded from the storage unit 508 to the random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 can also be stored. The processor 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0155] Multiple components in the electronic device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the electronic device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0156] The processor 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 501 performs the various methods and processes described above, such as a method for determining the frequency of emotion detection.

[0157] In some embodiments, the method for determining the emotion detection frequency may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the processor 501, one or more steps of the method for determining the emotion detection frequency described above may be performed. Alternatively, in other embodiments, the processor 501 may be configured to perform the method for determining the emotion detection frequency in any other appropriate manner (e.g., by means of firmware).

[0158] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0159] The computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable emotion detection frequency determination device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0160] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0161] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0162] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0163] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS (Virtual Private Server) services.

[0164] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0165] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining emotion detection frequency, characterized in that: The method comprises: Obtaining the emotion detection benchmark frequency and the vehicle driving information of the total distance driven by the vehicle driver in the current time period; Predicting the probability of abnormal emotions of the vehicle driver in a future time period according to the vehicle driving information; wherein the future time period is adjacent to the current time period and is located after the current time period; According to the vehicle driving information and the probability of abnormal emotions in the future time period, the emotion detection reference frequency is adjusted to obtain the emotion detection frequency of the future time period, so as to perform emotion detection on the vehicle driver in the future time period according to the emotion detection frequency.

2. The method according to claim 1, characterized in that The vehicle driving information includes honking frequency, average waiting time at traffic lights, continuous driving time, total driving time and number of times being overtaken.

3. The method according to claim 2, characterized in that The predicting, based on the vehicle driving information, the probability of abnormal emotions of the vehicle driver in a future time period includes: fusing the horn honking frequency and the number of times of being overtaken to obtain first fused data; fusing the average waiting time for the traffic light, the continuous driving time and the total driving time to obtain second fused data; fusing the number of times of being overtaken and the total driving time to obtain third fused data; The whistle frequency, the average waiting time of the traffic light, and the number of times of being overtaken are integrated to obtain fourth integrated data; fusing the continuous driving time and the total driving time to obtain fifth fused data; The honking evaluation rate, the average waiting time at the traffic light, the number of times of being overtaken, and the continuous driving time are integrated to obtain sixth integrated data; By using the trained risk prediction model, the probability of abnormal emotions of the vehicle driver in a future time period is predicted based on the first fusion data, the second fusion data, the third fusion data, the fourth fusion data, the fifth fusion data and the sixth fusion data.

4. The method according to claim 3, characterized in that The step of fusing the horn honking frequency and the number of times of being overtaken to obtain first fused data includes: Performing logarithmic transformation on the number of times of being overtaken to obtain a logarithmic transformation result; Determining the product between the logarithmic transformation result and the whistle frequency; Performing exponential transformation on the product to obtain first fused data.

5. The method according to claim 2, characterized in that: The step of adjusting the emotion detection reference frequency according to the vehicle driving information and the probability of abnormal emotion in the future time period to obtain the emotion detection frequency in the future time period includes: Performing logarithmic transformation on the whistle frequency to obtain transformation data; fusing the average waiting time of the traffic light and the total driving time to obtain seventh fused data; fusing the number of times of being overtaken and the continuous driving time to obtain eighth fused data; According to the emotion abnormality probability, the transformed data, the seventh fusion data and the eighth fusion data, the emotion reference frequency is adjusted to obtain the emotion detection frequency of the future time period.

6. The method according to claim 5, characterized in that The step of adjusting the emotion reference frequency according to the emotion abnormality probability, the transformed data, the seventh fusion data and the eighth fusion data to obtain the emotion detection frequency in the future time period includes: Performing weighted fusion on the emotion abnormality probability, the transformed data, the seventh fused data, and the eighth fused data to obtain a weighted fusion result; According to the weighted fusion result, the emotion baseline probability is adjusted to obtain the emotion detection frequency in the future time period.

7. The method according to claim 1, characterized in that After obtaining the emotion detection frequency in the future time period, the method further includes: collecting a facial image of the vehicle driver within the future time period according to the emotion detection frequency; Emotion detection is performed on the vehicle driver based on the facial image.

8. A device for determining emotion detection frequency, characterized in that: The device comprises: An information acquisition module is used to obtain the emotion detection reference frequency and the vehicle driving information of the total distance driven by the vehicle driver in the current time period; A probability prediction module, used to predict the probability of abnormal emotions of the vehicle driver in a future time period according to the vehicle driving information; wherein the future time period is adjacent to the current time period and is located after the current time period; A frequency adjustment module is used to adjust the emotion detection reference frequency according to the vehicle driving information and the probability of abnormal emotions in the future time period, so as to obtain the emotion detection frequency of the future time period, so as to perform emotion detection on the vehicle driver in the future time period according to the emotion detection frequency.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the method for determining the emotion detection frequency according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining the emotion detection frequency according to any one of claims 1 to 7 when executed.

Images