Perception recognition storage terminal system based on big data

Abstract

The invention discloses a big data-based perception recognition storage terminal system, which comprises a behavior recognition end, a scanning analysis end, a pre-judgment analysis end and a judgment control end, and is characterized in that the behavior recognition end is electrically connected with the scanning analysis end, the scanning analysis end is electrically connected with the pre-judgment analysis end, the pre-judgment analysis end is electrically connected with the judgment control end, and the judgment control end is electrically connected with the behavior recognition end. The behavior recognition end is used for recognizing the state of a rider in the riding process, the scanning analysis end is used for scanning and analyzing the situation in front of the rider, the pre-judgment analysis end is used for calculating and analyzing the accident occurrence probability after an object is detected, and the judgment control module is used for pre-judging the danger degree of the environment and controlling the vehicle. The behavior recognition end comprises a vehicle speed recognition module, an eye movement tracking module, a motion capture module and a danger recognition module, and the vehicle speed recognition module is electrically connected with the eye movement tracking module.

Description

Technical Field

[0001] The present invention relates to the field of perception recognition storage technology, and in particular to a perception recognition storage terminal system based on big data. Background Art

[0002] With the continuous development of the Internet and the catering industry, the "lazy economy" has become an economic phenomenon. Takeout has become one of people's mainstream lifestyles. Online takeout platforms are the first choice for netizens to order takeout. Under the trend of consumption upgrading, people's requirements for takeout delivery services are getting higher and higher, which has also prompted online takeout platforms to continuously increase their service system with delivery as the core. Therefore, every time it is mealtime, you can see busy takeout riders in the streets and alleys, rain or shine.

[0003] In addition, the traffic safety of food delivery drivers has always been a hot topic in society. Speeding, driving against traffic, running red lights, and talking on the phone while riding are common behaviors that "risk their lives to deliver food". Riders are constrained by assessments such as punctuality and bad review rates. Being in a hurry is the core factor for illegal driving of food delivery vehicles. For convenience, many riders will install mobile phone holders on their vehicles, which will result in them looking at their phones while riding, making traffic accidents more likely to occur. Therefore, it is necessary to design a perception, recognition, and storage terminal system based on big data to judge the rider's situation and conduct emergency control in emergencies. Summary of the invention

[0004] The purpose of the present invention is to provide a perception recognition storage terminal system based on big data to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a perception, recognition and storage terminal system based on big data, comprising a behavior recognition end, a scanning and analysis end, a pre-judgment analysis end and a judgment and control end, the behavior recognition end and the scanning and analysis end are electrically connected, the scanning and analysis end and the pre-judgment analysis end are electrically connected, the pre-judgment analysis end and the judgment and control end are electrically connected, the behavior recognition end is used to identify the state of the rider when riding a bicycle, the scanning and analysis end is used to scan and analyze the situation in front of the rider, the pre-judgment analysis end is used to calculate and analyze the probability of an accident after detecting an object, and the judgment and control end is used to predict the degree of danger of the environment and control the vehicle.

[0006] According to the above technical solution, the behavior recognition terminal includes a vehicle speed recognition module, an eye movement tracking module, an action capture module, and a danger recognition module. The vehicle speed recognition module is electrically connected to the eye movement tracking module, the eye movement tracking module is electrically connected to the action capture module, and the action capture module is electrically connected to the danger recognition module. The vehicle speed recognition module is used to recognize the current cycling speed, the eye movement tracking module is used to track the pupil focus of the rider, the eye movement tracking module includes a timing calculation sub-module, and the timing calculation sub-module is used to time the rider's dangerous actions. The action capture module is used to capture the dangerous actions of the rider during cycling, and the danger recognition module is used to recognize the danger level of the rider's cycling actions. The danger recognition module includes an action analysis sub-module and a danger transmission sub-module, and the action analysis sub-module is electrically connected to the danger transmission sub-module. The action analysis sub-module is used to analyze the danger coefficient of the action, and the danger transmission sub-module is used to transmit a danger instruction when the dangerous action lasts for more than a certain threshold.

[0007] According to the above technical solution, the scanning and analysis terminal includes a scanning detection module, a trajectory judgment module, and an object analysis module. The scanning detection module is electrically connected to the trajectory judgment module, and the trajectory judgment module is electrically connected to the object analysis module. The scanning detection module is used to perform infrared scanning detection on the rider's front environment, the trajectory judgment module is used to judge the movement trajectory of the detected object, the trajectory judgment module includes a speed analysis sub-module, and the speed analysis sub-module is used to analyze the movement speed of the identified object according to the database. The object analysis module is used to analyze whether the detected object is moving, and the object analysis module includes a radar detection sub-module, and the radar detection sub-module is used to perform radar detection on the detected object.

[0008] According to the above technical solution, the pre-judgment and analysis terminal includes a route analysis module and a calculation analysis module. The route analysis module is electrically connected to the calculation analysis module. The route analysis module is used to analyze the predicted accident route. The route analysis module includes an infrared distance measurement sub-module, and the infrared distance measurement sub-module is used to measure the distance between the object and the rider when a dangerous behavior of the rider is recognized. The calculation analysis module is used to calculate the required vehicle speed according to the situation analysis. The calculation analysis module includes an information collection sub-module, and the information collection sub-module is used to collect the acquired information;

[0009] The judgment and control terminal includes an information discrimination sub-module and an execution control module. The information discrimination sub-module is electrically connected to the execution control module. The information discrimination sub-module is used to distinguish the current dangerous situation and make corresponding responses. The information discrimination sub-module includes an information reception sub-module, and the information reception sub-module is used to receive the information of the transmitted instruction and analysis result. The execution control module is used to execute the control of the vehicle.

[0010] According to the above technical solution, the operation method of the perception recognition storage terminal system mainly includes the following steps:

[0011] Step S1: During the process of a food delivery rider riding, the behavior recognition terminal recognizes the rider's behavior;

[0012] Step S2: When a dangerous behavior is recognized, the scanning and analysis terminal conducts an infrared scanning detection on the front environment of the ride;

[0013] Step S3: According to the detected object by the scanning and detection, the pre-judgment and analysis terminal pre-judges the probability of an accident;

[0014] Step S4: For the pre-judged probability in advance, the judgment and control terminal executes control on the vehicle.

[0015] According to the above technical solution, step S1 further includes the following steps:

[0016] Step S11: When the vehicle speed recognition module recognizes that the vehicle has a speed value, it transmits a signal to the eye movement tracking module;

[0017] Step S12: The eye movement tracking module at the upper end of the mobile phone is activated, scans the rider's face, captures the rider's eye information, and when the pupil focus point of the rider is tracked in the direction of the mobile phone, the timing calculation sub-module times the current action;

[0018] Step S13: At the same time, the action capture module captures the action of the rider touching and sliding the mobile phone screen;

[0019] Step S14: According to the recognized behavior of the rider, the danger recognition module analyzes the current action of the rider according to the action analysis sub-module to recognize the danger level of the rider;

[0020] Step S15: When the time maintained by the dangerous behavior exceeds a certain threshold, the danger transmission sub-module sends a braking instruction;

[0021] Step S14 further includes the following steps:

[0022] Step S141: The action analysis sub-module analyzes the current dangerous behavior of the rider;

[0023] Step S142: When it is recognized that the pupil focus point of the rider is on the mobile phone, the behavior danger coefficient M = 1;

[0024] Step S143: When it is recognized that the pupil focus point of the rider is on the mobile phone and there is an action of touching and sliding the mobile phone screen, the behavior danger coefficient M = 2.

[0025] According to the above technical solution, in S14, the calculation formula for the recognized danger level W is:

[0026] W = K * T * V1 * M

[0027] Among them, W is the recognized degree of danger, K is the danger situation conversion coefficient, V1 is the vehicle speed value of the current ride, T is the time value maintained by the dangerous behavior, and M is the behavior danger coefficient of the rider during riding. The vehicle speed of the ride, the time maintained by the dangerous behavior, and the dangerous behavior performed are all proportional to the degree of danger. The time value T maintained by the dangerous behavior and the vehicle speed value V1 of the current ride cannot exceed a certain threshold. When the two sufficient conditions of T > 6s and V1 > 10m / s are met, the danger recognition module sends a braking instruction.

[0028] According to the above technical solution, the step S2 further includes the following steps:

[0029] Step S21: Recognize the dangerous behavior of the rider, and at the same time, the scanning detection module at the front of the vehicle forms an infrared detection barrier to scan and detect the environment in front of the rider;

[0030] Step S22: Use the radar detection sub-module to perform radar detection on whether the scanned and detected object moves;

[0031] Step S23: According to the result analyzed and judged by the object analysis module, the trajectory judgment module judges the action trajectory of the object, and analyzes the action speed of the target object from the speed analysis sub-module in the radar detection.

[0032] According to the above technical solution, the step S3 further includes the following steps:

[0033] Step S31: The infrared ranging sub-module uses infrared rays to measure the distance between the object and the rider;

[0034] Step S32: The route analysis module analyzes the probability of the predicted accident;

[0035] Step S33: According to the predicted situation, the calculation analysis module analyzes the information collected by the information collection sub-module and calculates the vehicle speed required by the current vehicle;

[0036] In the step S32, the calculation formula for predicting the accident situation:

[0037]

[0038] Among them, t is the time value predicted for an accident to occur during driving at the current vehicle speed, t > 0, C is the distance value measured by the rider at the current position from the object, V1 is the original vehicle speed value of the rider, V2 is the action speed value per second of the object whose action trajectory intersects with the rider, N is the probability of an accident occurring between the rider and the recognized object at the predicted same time. When V1 > V2, for an accident to occur, both Formula 1 and Formula 2 need to be satisfied. When V2 > V1, for an accident to occur, both Formula 1 and Formula 3 need to be satisfied. ε is the conversion coefficient. The faster the predicted time for an accident to occur during driving, the higher the probability of an accident occurring.

[0039] In the said step S33, the calculation formula for the required vehicle speed V0 of the current vehicle is:

[0040]

[0041] Among them, V0 is the vehicle speed that can avoid an accident. The recognized danger level W and the probability N of an accident occurring between the rider and the recognized object at the predicted same time are inversely proportional to the required vehicle speed V0 of the current vehicle. The more dangerous the danger level, the slower the required vehicle speed V0, and V0 < V1.

[0042] According to the above technical solution, the said step S4 further includes the following steps:

[0043] Step S41: The information receiving sub-module receives the transmitted instructions and the information of the analysis results.

[0044] Step S42: The information discrimination sub-module discriminates the current dangerous situation according to the received data and makes corresponding responses.

[0045] Step S43: According to the responses made, the execution control module controls the vehicle.

[0046] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: In the present invention, by providing a behavior recognition terminal, a scanning and analysis terminal, a prediction and analysis terminal, and a judgment and control terminal, dangerous actions of the rider can be recognized. During the process of making dangerous actions, the front situation of the rider's vehicle is detected. When a moving object is scanned, according to the current vehicle speed of the rider and the speed of the moving object, the probability of an accident occurring is calculated and analyzed, the danger level is judged, and the vehicle is controlled to avoid accidents and delay the food delivery time. Description of the Drawings

[0047] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention.

[0048] In the drawings:

[0049] Figure 1It is a schematic diagram of the system module composition of the present invention. Specific embodiments

[0050] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0051] Please refer to Figure 1 , the present invention provides a technical solution: a perception recognition storage terminal system based on big data, including a behavior recognition end, a scanning analysis end, a pre-judgment analysis end, and a judgment control end. The behavior recognition end is electrically connected to the scanning analysis end, the scanning analysis end is electrically connected to the pre-judgment analysis end, and the pre-judgment analysis end is electrically connected to the judgment control end. The behavior recognition end is used to recognize the state of the rider when riding a bike. The scanning analysis end is used to scan and analyze the situation in front of the rider. The pre-judgment analysis end is used to calculate and analyze the probability of an accident after detecting an object. The judgment control end is used to pre-judge the degree of danger of the environment and execute control on the vehicle. By setting up a behavior recognition end, a scanning analysis end, a pre-judgment analysis end, and a judgment control end, it is possible to recognize the dangerous actions of the rider, detect the situation in front of the rider's vehicle during the dangerous actions, calculate and analyze the probability of an accident according to the current speed of the rider and the speed of the moving object when a moving object is scanned, judge the degree of danger, and execute control on the vehicle to avoid accidents and delay the meal delivery time.

[0052] The behavior recognition end includes a vehicle speed recognition module, an eye movement tracking module, an action capture module, and a danger recognition module. The vehicle speed recognition module is electrically connected to the eye movement tracking module, the eye movement tracking module is electrically connected to the action capture module, and the action capture module is electrically connected to the danger recognition module. The vehicle speed recognition module is used to recognize the current riding speed. The eye movement tracking module is used to track the pupil focus of the rider. The eye movement tracking module includes a timing calculation sub-module, which is used to time the rider's dangerous actions. The action capture module is used to capture the dangerous actions of the rider during the ride. The danger recognition module is used to recognize the degree of danger of the rider's riding actions. The danger recognition module includes an action analysis sub-module and a danger transmission sub-module. The action analysis sub-module and the danger transmission sub-module are electrically connected. The action analysis sub-module is used to analyze the danger coefficient of the action. The danger transmission sub-module is used to transmit a danger instruction when the dangerous action lasts for more than a certain threshold.

[0053] The scanning and analysis terminal includes a scanning and detection module, a trajectory judgment module, and an object analysis module. The scanning and detection module is electrically connected to the trajectory judgment module, and the trajectory judgment module is electrically connected to the object analysis module. The scanning and detection module is used to perform infrared scanning and detection on the front environment of the rider. The trajectory judgment module is used to judge the movement trajectory of the detected object. The trajectory judgment module includes a speed analysis sub-module, which is used to analyze the movement speed of the identified object according to the database. The object analysis module is used to analyze whether the detected object is moving. The object analysis module includes a radar detection sub-module, which is used to perform radar detection on the detected object.

[0054] The pre-judgment and analysis terminal includes a route analysis module and a calculation and analysis module. The route analysis module is electrically connected to the calculation and analysis module. The route analysis module is used to analyze the predicted accident route. The route analysis module includes an infrared distance measurement sub-module, which is used to measure the distance between the object and the rider when a dangerous behavior of the rider is identified. The calculation and analysis module is used to calculate the required vehicle speed according to the situation analysis. The calculation and analysis module includes an information collection sub-module, which is used to collect the acquired information.

[0055] The judgment and control terminal includes an information discrimination sub-module and an execution control module. The information discrimination sub-module is electrically connected to the execution control module. The information discrimination sub-module is used to distinguish the current dangerous situation and make corresponding responses. The information discrimination sub-module includes an information reception sub-module, which is used to receive the transmitted instructions and the information of the analysis results. The execution control module is used to execute the control of the vehicle.

[0056] The operation method of the sensing, identifying, and storing terminal system mainly includes the following steps:

[0057] Step S1: During the ride of the food delivery rider, the behavior recognition terminal recognizes the rider's behavior.

[0058] Step S2: When a dangerous behavior is recognized, the scanning and analysis terminal performs infrared scanning and detection on the front environment of the ride.

[0059] Step S3: According to the detected object by scanning, the pre-judgment and analysis terminal pre-judges the probability of an accident.

[0060] Step S4: For the pre-judged probability, the judgment and control terminal executes the control of the vehicle.

[0061] Step S1 further includes the following steps:

[0062] Step S11: When the vehicle speed recognition module recognizes that the vehicle has a speed value, it transmits a signal to the eye movement tracking module.

[0063] Step S12: The eye movement tracking module at the upper end of the mobile phone is activated to scan the face of the rider, capture the rider's eye information, and when the pupil focus of the rider is tracked in the direction of the mobile phone, the timing calculation sub-module times the current action;

[0064] Step S13: At the same time, the motion capture module captures the action of the rider touching and sliding the mobile phone screen;

[0065] Step S14: According to the recognized behavior of the rider, the danger recognition module analyzes the current action of the rider according to the action analysis sub-module to identify the danger level of the rider;

[0066] Step S15: When the time maintained by the dangerous behavior exceeds a certain threshold, the danger transmission sub-module sends a braking instruction;

[0067] Step S14 further includes the following steps:

[0068] Step S141: The action analysis sub-module analyzes the current dangerous behavior of the rider;

[0069] Step S142: When it is recognized that the pupil focus of the rider is on the mobile phone, the behavior danger coefficient M = 1;

[0070] Step S143: When it is recognized that the pupil focus of the rider is on the mobile phone and there is an action of touching and sliding the mobile phone screen, the behavior danger coefficient M = 2.

[0071] In S14, the calculation formula for the recognized danger level W:

[0072] W = K * T * V1 * M

[0073] Wherein, W is the recognized danger level, K is the danger situation conversion coefficient, V1 is the vehicle speed value of the current ride, T is the time value of the maintained dangerous behavior, M is the behavior danger coefficient of the rider during riding, the vehicle speed of the ride, the time of the maintained dangerous behavior and the dangerous behavior done are all proportional to the danger level, the time value T of the maintained dangerous behavior and the vehicle speed value V1 of the current ride cannot exceed a certain threshold, when the two sufficient conditions of T > 6s and V1 > 10m / s are satisfied, the danger recognition module sends a braking instruction.

[0074] Step S2 further includes the following steps:

[0075] Step S21: When the dangerous behavior of the rider is recognized, the scanning and detection module at the front of the vehicle forms an infrared detection barrier to scan and detect the environment in front of the rider;

[0076] Step S22: The radar detection sub-module uses radar to detect whether the scanned and detected object moves, and the radar detects the scanned object twice at an interval of one second;

[0077] Step S23: According to the result analyzed and judged by the object analysis module, the trajectory judgment module judges the action trajectory of the object, and analyzes the action speed of the target object from the speed analysis sub-module in the radar detection.

[0078] Step S3 further includes the following steps:

[0079] Step S31: The infrared ranging sub-module uses infrared rays to measure the distance between the object and the rider;

[0080] Step S32: The route analysis module analyzes the probability of a predicted accident;

[0081] Step S33: According to the predicted situation, the calculation and analysis module analyzes and calculates the vehicle speed required by the current vehicle for the information collected by the information collection sub-module;

[0082] In step S32, the calculation formula for predicting the situation of an accident:

[0083]

[0084] Among them, t is the time value of predicting an accident when driving at the current vehicle speed, t > 0, C is the distance value measured by the rider between the current position and the object, V1 is the original vehicle speed value of the rider, V2 is the action speed value per second of the object whose action trajectory intersects with the rider, N is the probability of an accident occurring between the rider and the recognized object at the predicted same time. When V1 > V2, an accident needs to satisfy both formula 1 and formula 2 at the same time. When V2 > V1, an accident needs to satisfy both formula 1 and formula 3 at the same time. ε is a conversion coefficient. The faster the time of predicting an accident when driving, the higher the possibility of an accident. When both formulas are satisfied at the same time, according to the relationship between the distance traveled by the rider and the distance traveled by the recognized object at the predicted same time and the distance measured by the rider between the current position and the object, a triangle condition can be formed;

[0085] In step S33, the calculation formula for the vehicle speed V0 required by the current vehicle:

[0086]

[0087] Among them, V0 is the vehicle speed that can avoid an accident. The recognized danger level W, the probability N of an accident occurring between the rider and the recognized object at the predicted same time, and the vehicle speed V0 required by the current vehicle are inversely proportional. The more dangerous the danger level, the slower the vehicle speed V0 required, and V0 < V1.

[0088] Step S4 further includes the following steps:

[0089] Step S41: The information receiving sub-module receives the transmitted instructions and the information of the analysis results;

[0090] Step S42: The information discrimination sub-module discriminates the current dangerous situation based on the received data and makes corresponding responses.

[0091] Step S43: According to the response made, the execution control module controls the vehicle.

[0092] Implementation Example 1: When the vehicle speed value is recognized, the upper end of the mobile phone scans the rider's face, captures the rider's pupil focus point, the behavior danger coefficient M = 1, and the danger situation conversion coefficient The current vehicle speed of the rider V1 = 14 m / s, the time T that the pupil focus point stays on the mobile phone is 3 s. According to the formula W = K * T * V1 * M, the recognized danger level W = 8.4. A moving object is scanned and detected, the distance C between the rider's current position and the object is 8 m. According to the radar, it is judged that the moving object and the rider's moving trajectory cross, and the moving speed of the detected moving object V2 = 4 m / s. According to the formula It can be obtained that ε = 4, 5 < N < 9. According to the formula It can be obtained that 13.7 m / s < V0 < 13.81 m / s.

[0093] Implementation Example 2: When the vehicle speed value is recognized, the upper end of the mobile phone scans the rider's face, captures the rider's pupil focus point, the behavior danger coefficient M = 1, and the danger situation conversion coefficient The current vehicle speed of the rider V1 = 13 m / s, the time T that the pupil focus point stays on the mobile phone is 5 s. According to the formula W = K * T * V1 * M, the recognized danger level W = 6.5. A moving object is scanned and detected, the distance C between the rider's current position and the object is 10 m. According to the radar, it is judged that the moving object and the rider's moving trajectory cross, and the moving speed of the detected moving object V2 = 6 m / s. According to the formula It can be obtained that ε = 10, 7 < N < 19. According to the formula It can be obtained that 12.71 m / s < V0 < 12.9 m / s.

[0094] Implementation Example 3: When the vehicle speed value is recognized, the upper end of the mobile phone scans the rider's face, captures the rider's pupil focus point, and there is an action of touching and sliding the mobile phone screen. The behavior danger coefficient M = 2, and the danger situation conversion coefficient The current speed of the rider is V1 = 12 m / s, and the time T that the pupil's focus stays on the mobile phone is 7 s. According to the formula W = K * T * V1 * M, the recognized danger level W = 16.8. When the two sufficient conditions of T > 6 s and V > 10 m / s are met, the danger recognition module sends a braking instruction to control the vehicle to stop slowly to ensure safety.

[0095] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent in such process, method, article or device.

[0096] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A perception recognition storage terminal system based on big data, comprising a behavior recognition terminal, a scanning and analysis terminal, a pre-judgment and analysis terminal, and a judgment and control terminal, characterized in that: The behavior recognition terminal and the scanning and analysis terminal are electrically connected, the scanning and analysis terminal and the pre-judgment analysis terminal are electrically connected, the pre-judgment analysis terminal and the judgment and control terminal are electrically connected. The behavior recognition terminal is used to recognize the state of the rider when riding a bike. The scanning and analysis terminal is used to scan and analyze the situation in front of the rider. The pre-judgment analysis terminal is used to calculate and analyze the probability of an accident after detecting an object. The judgment and control terminal is used to pre-judge the degree of danger of the environment and execute control on the vehicle; The behavior recognition terminal includes a vehicle speed recognition module, an eye movement tracking module, an action capture module, and a danger recognition module. The vehicle speed recognition module and the eye movement tracking module are electrically connected. The eye movement tracking module and the action capture module are electrically connected. The action capture module and the danger recognition module are electrically connected. The vehicle speed recognition module is used to recognize the current riding speed. The eye movement tracking module is used to track the pupil focus of the rider. The eye movement tracking module includes a timing calculation sub-module, which is used to time the rider's dangerous actions. The action capture module is used to capture the dangerous actions of the rider during the ride. The danger recognition module is used to recognize the degree of danger of the rider's riding actions. The danger recognition module includes an action analysis sub-module and a danger transmission sub-module. The action analysis sub-module and the danger transmission sub-module are electrically connected. The action analysis sub-module is used to analyze the danger coefficient of the action. The danger transmission sub-module is used to transmit a danger instruction when the dangerous action lasts for more than a certain threshold; The scanning and analysis terminal includes a scanning detection module, a trajectory judgment module, and an object analysis module. The scanning detection module and the trajectory judgment module are electrically connected. The trajectory judgment module and the object analysis module are electrically connected. The scanning detection module is used to perform infrared scanning detection on the front environment of the rider. The trajectory judgment module is used to judge the action trajectory of the detected object. The trajectory judgment module includes a speed analysis sub-module, which is used to analyze the action speed of the identified object according to the database. The object analysis module is used to analyze whether the detected object is moving. The object analysis module includes a radar detection sub-module, which is used to perform radar detection on the detected object; The pre-judgment analysis terminal includes a route analysis module and a calculation and analysis module. The route analysis module and the calculation and analysis module are electrically connected. The route analysis module is used to analyze the predicted accident route. The route analysis module includes an infrared ranging sub-module, which is used to measure the distance between the object and the rider when a dangerous behavior of the rider is recognized. The calculation and analysis module is used to calculate the required vehicle speed according to the situation analysis. The calculation and analysis module includes an information collection sub-module, which is used to collect the acquired information; The operation method of the sensing, recognition and storage terminal system mainly includes the following steps: Step S1: During the ride of the food delivery rider, the behavior recognition terminal recognizes the rider's behavior; Step S2: When a dangerous behavior is recognized, the scanning and analysis terminal performs infrared scanning detection on the front environment of the ride; Step S3: Based on the detected object, the prediction analysis terminal predicts the probability of an accident occurring; Step S4: For the predicted probability, the control terminal controls the vehicle; The said step S1 further includes the following steps: Step S11: When the vehicle speed recognition module recognizes that the vehicle has a speed value, it transmits a signal to the eye movement tracking module; Step S12: The eye movement tracking module on the mobile phone upper end is activated to scan the rider's face, capture the rider's eye information, and when the pupil focus point of the rider is tracked in the direction of the mobile phone, the timing calculation sub-module times the current action; Step S13: At the same time, the action capture module captures the rider's action of touching and sliding the mobile phone screen; Step S14: According to the recognized rider's behavior, the danger recognition module analyzes the rider's current action according to the action analysis sub-module to recognize the rider's danger level; Step S15: When the time maintained by the dangerous behavior exceeds a certain threshold, the danger transmission sub-module sends a braking instruction; The said step S14 further includes the following steps: Step S141: The action analysis sub-module analyzes the rider's current dangerous behavior; Step S142: When it is recognized that the pupil focus point of the rider is on the mobile phone, the behavior danger coefficient M = 1; Step S143: When it is recognized that the pupil focus point of the rider is on the mobile phone and there is an action of touching and sliding the mobile phone screen, the behavior danger coefficient M = 2; In the said S14, the calculation formula for the recognized danger level W: W = K * T * V1 * M Where, W is the recognized danger level, K is the danger situation conversion coefficient, V1 is the current riding vehicle speed value, T is the time value maintained by the dangerous behavior, M is the behavior danger coefficient of the rider during riding, the riding vehicle speed, the time maintained by the dangerous behavior and the dangerous behavior done are all proportional to the danger level, the time value T maintained by the dangerous behavior and the current riding vehicle speed value V1 cannot exceed a certain threshold, when the two sufficient conditions of T > 6s and v1 > 10m / s are met, the danger recognition module sends a braking instruction; The said step S2 further includes the following steps: Step S21: When the rider's dangerous behavior is recognized, the scanning detection module at the front of the vehicle forms an infrared detection barrier to scan and detect the environment in front of the rider; Step S22: The radar detection sub-module uses radar to detect whether the detected object moves; Step S23: According to the result analyzed and judged by the object analysis module, the trajectory judgment module judges the action trajectory of the object, and analyzes the target object action speed from the speed analysis sub-module in the radar detection; The said step S3 further includes the following steps: Step S31: The infrared ranging sub-module uses infrared rays to measure the distance between the object and the rider; Step S32: The route analysis module analyzes the probability of the predicted accident; Step S33: According to the predicted situation, the calculation analysis module analyzes and calculates the information collected by the information collection sub-module to calculate the vehicle speed required by the current vehicle; In the said step S32, the calculation formula for the predicted accident situation: Among them, t is the time value predicted for an accident to occur during driving at the current vehicle speed, t > 0, C is the distance value measured by the rider at the current position from the object, v1 is the original vehicle speed value of the rider, V2 is the action speed value per second of the object whose action trajectory intersects with the rider, N is the probability of an accident occurring between the rider and the recognized object at the same predicted time. When V1 > v2, for an accident to occur, both Formula 1 and Formula 2 need to be satisfied. When v2 > v1, for an accident to occur, both Formula 1 and Formula 3 need to be satisfied. ε is the conversion coefficient. The faster the predicted time for an accident to occur during driving, the higher the probability of an accident occurring. In the said step S33, the calculation formula for the current vehicle required vehicle speed V0: Among them, V0 is the vehicle speed that can avoid accidents. The recognized degree of danger W, the predicted probability N of an accident occurring between the rider and the recognized object at the same time, and the required vehicle speed V0 of the current vehicle are inversely proportional. The more dangerous the degree of danger, the slower the required vehicle speed V0, and V0 < V1.

Images