Illegal passenger-carrying identification method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an illegal passenger-carrying identification method, and the method comprises the steps: obtaining the feature data of a rider in a multi-person riding event when the multi-person riding event is detected, carrying out the collision processing of the feature data of the rider and the feature data of a specific person in a specific person library, determining that the rider is a specific person or a non-specific person, and carrying out the recognition of the illegal passenger-carrying. And if the rider is a non-specific person, determining whether the rider has illegal passenger-carrying suspicion, if the rider is a specific person or the rider has illegal passenger-carrying suspicion, obtaining structured data of the rider, and determining whether the rider is an illegal passenger-carrying person based on the structured data. Through comprehensive analysis of the specific personnel library and the structured data, whether the rider is the illegal passenger-carrying personnel is determined, the attribute data of the rider and the potential relationship between the illegal data and the illegal behavior are fully considered, rapid and efficient illegal passenger-carrying identification is further realized, and the efficiency and level of urban traffic management can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method, device, electronic equipment and storage medium for identifying illegal passenger carrying. Background Art

[0002] There are many people who illegally carry passengers in cities today. Their illegal behavior poses a great threat to the safety of life and property of citizens. The existing screening and identification methods often use road cameras to analyze key areas and then arrange personnel to go to key areas for manual screening. However, this method requires a lot of manpower and material resources and is inefficient. Therefore, how to provide a method for automatically identifying illegal passenger carrying and improving identification efficiency has become an urgent problem to be solved. Summary of the invention

[0003] The embodiment of the present invention provides a method for identifying illegal passenger carrying, aiming to solve the problem that the existing illegal passenger carrying investigation wastes a lot of manpower and material resources and has low efficiency. Through comprehensive analysis of a specific personnel database and structured data, it is determined whether a cyclist is an illegal passenger carrier, and the attribute data of the cyclist and the potential relationship between the illegal data and the illegal behavior are fully considered, thereby realizing fast and efficient illegal passenger carrying identification, which can effectively reduce the risk of life and property safety of citizens and improve the efficiency and level of urban traffic management.

[0004] In a first aspect, an embodiment of the present invention provides a method for identifying illegal passenger carrying, the method comprising:

[0005] When a multi-person riding event is detected, obtaining characteristic data of the riders in the multi-person riding event;

[0006] Perform collision processing on the characteristic data of the rider and the characteristic data of the specific person in the specific person database to determine whether the rider is a specific person or a non-specific person, and the specific person is a person who illegally carries passengers;

[0007] If the rider is a non-specific person, determining whether the rider is suspected of illegally carrying passengers;

[0008] If the rider is a specific person or the rider is suspected of illegally carrying passengers, obtaining structured data of the rider;

[0009] Based on the structured data, determine whether the rider is a person who illegally carries passengers.

[0010] Optionally, performing collision processing on the characteristic data of the rider and a specific person database to determine whether the rider is a specific person or a non-specific person includes:

[0011] The characteristic data of the rider is collided with the characteristic data of the specific person in the specific person database one by one;

[0012] If the characteristic data of the rider successfully collides with the characteristic data of any specific person in the specific person database, the rider is determined to be a specific person;

[0013] If the characteristic data of the rider fails to collide with the characteristic data of all specific persons in the specific person database, it is determined that the rider is a non-specific person.

[0014] Optionally, if the rider is a non-specific person, determining whether the rider is suspected of illegally carrying passengers includes:

[0015] If the rider is a non-specific person, a first historical multi-rider riding event is obtained, where the first historical multi-rider riding event includes feature data of historical riders;

[0016] Performing collision processing on the characteristic data of the rider and the characteristic data of the historical riders to obtain a second historical multi-rider riding event corresponding to the rider;

[0017] Based on the second historical multi-person riding event, determine whether the riding person is suspected of illegally carrying passengers.

[0018] Optionally, the second historical multi-passenger riding event includes characteristic data of historical passengers of the rider, and determining whether the rider is suspected of illegally carrying passengers based on the second historical multi-passenger riding event includes:

[0019] performing collision processing between the characteristic data of the historical passengers of the rider to determine whether the rider has multiple historical passengers;

[0020] If the rider has multiple historical passengers, it is determined that the rider is suspected of illegally carrying passengers.

[0021] Optionally, the structured data includes attribute data and violation data of the rider, and determining whether the rider is a person who illegally carries passengers based on the structured data includes:

[0022] Based on the attribute data, determining whether the rider has illegal intention to carry passengers;

[0023] Based on the violation data, determining whether the rider has a history of violations;

[0024] Based on the illegal intention of carrying passengers and the historical illegal behavior, it is determined whether the rider is an illegal passenger-carrying person.

[0025] Optionally, the attribute data includes the appearance location data and identity data of the rider, and determining whether the rider has illegal intention to carry passengers based on the attribute data includes:

[0026] Determine a group portrait of the riders based on the identity data;

[0027] Based on the appearance location data, determine the high-frequency locations where the rider appears and the time period when the rider appears in the high-frequency locations;

[0028] Determining the appearance intention of the rider based on the high-frequency places and the time period;

[0029] Based on the group portrait and the intention of appearance, determine whether the rider has the intention of illegally carrying passengers.

[0030] Optionally, the determining whether the rider is an illegal passenger-carrying person based on the illegal passenger-carrying intention and the historical illegal behavior includes:

[0031] Determining a score value of the rider based on the illegal passenger-carrying intention and the historical illegal behavior;

[0032] According to the integral value, it is determined whether the rider is a person who illegally carries passengers.

[0033] In a second aspect, an embodiment of the present invention further provides a device for identifying illegal passenger carrying, the device comprising:

[0034] The first detection module is used to obtain characteristic data of riders in a multi-rider riding event when a multi-rider riding event is detected;

[0035] A first collision module is used to perform collision processing on the characteristic data of the rider and the characteristic data of the specific person in the specific person database, and determine whether the rider is a specific person or a non-specific person, and the specific person is a person who illegally carries passengers;

[0036] A first determination module is used to determine whether the rider is suspected of illegally carrying passengers if the rider is a non-specific person;

[0037] A first acquisition module is used to acquire structured data of the rider if the rider is a specific person or the rider is suspected of illegally carrying passengers;

[0038] The second determination module is used to determine whether the rider is a person who illegally carries passengers based on the structured data.

[0039] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the illegal passenger identification method provided in the embodiment of the present invention when executing the computer program.

[0040] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the illegal passenger identification method provided in the embodiment of the invention are implemented.

[0041] In an embodiment of the present invention, when a multi-person cycling event is detected, characteristic data of the cyclists in the multi-person cycling event is obtained, and the characteristic data of the cyclists is collided with the characteristic data of the specific person in the specific person database to determine whether the cyclist is a specific person or a non-specific person. If the cyclist is a non-specific person, it is determined whether the cyclist is suspected of illegally carrying passengers. If the cyclist is a specific person or the cyclist is suspected of illegally carrying passengers, the structured data of the cyclist is obtained, and based on the structured data, it is determined whether the cyclist is an illegal passenger carrier. Through comprehensive analysis of the specific person database and the structured data, it is determined whether the cyclist is an illegal passenger carrier, which fully considers the attribute data of the cyclist and the potential relationship between the illegal data and the illegal behavior, thereby realizing fast and efficient identification of illegal passenger carrying, which can effectively reduce the risk of life and property safety of citizens and improve the efficiency and level of urban traffic management. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 paying creative work.

[0043] Figure 1 is a flow chart of a method for identifying illegal passenger carrying provided by an embodiment of the present invention;

[0044] Figure 2 It is a structural schematic diagram of an illegal passenger identification device provided in an embodiment of the present invention;

[0045] Figure 3 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 are within the scope of protection of the present invention.

[0047] like Figure 1 As shown, Figure 1 1 is a flow chart of a method for identifying illegal passenger carrying provided by an embodiment of the present invention. The method for identifying illegal passenger carrying includes the following steps:

[0048] 101. When a multi-person riding event is detected, characteristic data of the riders in the multi-person riding event is obtained.

[0049] In an embodiment of the present invention, the above-mentioned illegal passenger carrying identification method can be deployed to a server or a server cluster. The above-mentioned server or server cluster can be an electronic device with functions such as image recognition, data storage, data processing, and data transmission. The above-mentioned multiple persons can include a rider and at least one corresponding passenger. The above-mentioned rider can be a rider of a non-motor vehicle, and the above-mentioned non-motor vehicle can be an electric vehicle. The characteristic data of the above-mentioned rider can be facial characteristic data, behavioral characteristic data, and other characteristic data of the above-mentioned rider. The above-mentioned multi-person riding event can be detected by an image acquisition device deployed in a public place. The above-mentioned multi-person riding event corresponds to the above-mentioned rider. Each multi-person riding event can correspond to a rider, and each multi-person riding event can correspond to at least one passenger.

[0050] In a possible embodiment, when the image acquisition device detects the multi-person cycling event, it obtains images of the cyclists in the multi-person cycling event, performs feature extraction on the images of the cyclists, obtains feature data of the cyclists, and transmits the feature data to the server or server cluster through the data transmission function.

[0051] In another possible embodiment, when the image acquisition device detects the multi-person cycling event, images of the cyclists and images of the passengers in the multi-person cycling event are obtained, features are extracted from the images of the cyclists and images of the passengers respectively to obtain feature data of the cyclists and feature data of the passengers, and the feature data of the cyclists and the feature data of the passengers are transmitted to the server or server cluster through the data transmission function.

[0052] 102. Perform collision processing on the characteristic data of the rider and the characteristic data of the specific person in the specific person database to determine whether the rider is a specific person or a non-specific person.

[0053] In an embodiment of the present invention, the above-mentioned specific personnel database may store characteristic data of persons who have a history of illegal passenger carrying behavior. The above-mentioned specific personnel database may be deployed in the above-mentioned server or server cluster. The above-mentioned specific personnel may be persons who have a history of illegal passenger carrying behavior. The characteristic data of the above-mentioned cyclist is collided with the characteristic data of the above-mentioned specific personnel. If the characteristic data of the above-mentioned cyclist successfully collides with the characteristic data of any specific person in the above-mentioned specific personnel database, the above-mentioned cyclist is a specific person. If the characteristic data of the above-mentioned cyclist fails to collide with the characteristic data of all specific persons in the above-mentioned specific personnel database, the above-mentioned cyclist is a non-specific person.

[0054] In a possible embodiment, after the server obtains the characteristic data of the rider, the characteristic data of the rider is compared one by one with the characteristic data of all specific persons in the specific person database. If the characteristic data of the rider is successfully compared with the characteristic data of any specific person in the specific person database, the rider is a specific person. If the characteristic data of the rider fails to be compared with the characteristic data of all specific persons in the specific person database, the rider is a non-specific person.

[0055] 103. If the rider is a non-specific person, determine whether the rider is suspected of illegally carrying passengers.

[0056] In an embodiment of the present invention, if the above-mentioned cyclists are non-specific persons, the riding time and riding location corresponding to the above-mentioned multi-person riding event can be obtained, and based on the above-mentioned riding time and riding location, the historical multi-person riding events within the period are obtained.

[0057] The above-mentioned historical multi-person cycling event may be multiple historical multi-person cycling events, the above-mentioned multiple historical multi-person cycling events may be greater than or equal to two historical multi-person cycling events, the above-mentioned historical multi-person cycling events may include characteristic data of historical cyclists and characteristic data of historical passengers, the characteristic data of historical cyclists in the multiple historical multi-person cycling events within the above-mentioned period are compared with the characteristic data of the above-mentioned cyclist to determine the historical multi-person cycling event corresponding to the above-mentioned cyclist, based on the historical multi-person cycling event corresponding to the above-mentioned cyclist, the characteristic data of the historical passengers corresponding to the above-mentioned cyclist are determined, the characteristic data of the historical passengers corresponding to the above-mentioned cyclist are compared respectively to obtain a comparison result.

[0058] Based on the comparison results, determine whether there are multiple different passengers in the historical multi-passenger riding events corresponding to the above-mentioned cyclist. If there are multiple different passengers in the historical multi-passenger riding events corresponding to the above-mentioned cyclist, and the passenger threshold is reached, it is determined that the above-mentioned cyclist is suspected of illegally carrying passengers.

[0059] The above-mentioned preset passenger threshold can be set according to the place where the cyclists appeared in the above-mentioned historical multi-person cycling events and / or the number of historical multi-person cycling events corresponding to the above-mentioned cyclists. Specifically, if the place where the above-mentioned cyclists appeared is a public place, such as subway stations, railway stations and other public places, the above-mentioned passenger threshold is smaller; if the number of historical multi-person cycling events corresponding to the above-mentioned cyclists is smaller, the above-mentioned passenger threshold is smaller.

[0060] In a possible embodiment, if the above-mentioned cyclist is a non-specific person, the riding time and riding location of the above-mentioned multi-person cycling event are obtained, and based on the riding time and riding location of the above-mentioned multi-person cycling event, the historical multi-person cycling events within a radius of five kilometers within ten days of the above-mentioned multi-person cycling event are determined, and the characteristic data of the historical cyclists in the above-mentioned historical multi-person cycling events are compared with the characteristic data of the above-mentioned cyclist to determine the historical multi-person cycling events corresponding to the above-mentioned cyclist, and based on the historical multi-person cycling events corresponding to the above-mentioned cyclist, the characteristic data of the historical passengers corresponding to the above-mentioned cyclist are determined, and the characteristic data of the historical passengers corresponding to the above-mentioned cyclist are compared respectively to determine that the number of historical passengers corresponding to the above-mentioned cyclist is 15.

[0061] If the number of historical multi-passenger cycling events is 15, the passenger threshold can be set to 10. If the number of historical passengers is greater than the passenger threshold, the cyclist is judged to be suspected of illegally carrying passengers. If the number of historical multi-passenger cycling events is 30, the passenger threshold can be set to 20. If the number of historical passengers is less than the passenger threshold, the cyclist is judged not to be suspected of illegally carrying passengers.

[0062] If in the above-mentioned historical multi-person cycling events, the places where the cyclists appeared were public places such as subway stations and railway stations, the above-mentioned passenger threshold can be set to 10. If the number of the above-mentioned historical passengers is greater than the above-mentioned passenger threshold, it is determined that the above-mentioned cyclists are suspected of illegally carrying passengers. If in the above-mentioned historical multi-person cycling events, the places where the cyclists appeared were fixed places such as residential areas, schools and other places, the above-mentioned passenger threshold can be set to 20. If the number of the above-mentioned historical passengers is less than the above-mentioned passenger threshold, it is determined that the above-mentioned cyclists are not suspected of illegally carrying passengers.

[0063] 104. If the rider is a specific person or is suspected of illegally carrying passengers, obtain the rider's structured data.

[0064] In an embodiment of the present invention, the structured data of the rider may include structured data such as the rider's violation data and attribute data. The attribute data may include identity data and location data. The violation data may include the number of times the rider appears in a motor vehicle lane while driving a non-motor vehicle and the number of times the rider runs a red light while driving a non-motor vehicle. The identity data may include the rider's age and occupation. The location data may include the number of times the rider appears in a crowded area while driving a non-motor vehicle and the number of times the rider drives a non-motor vehicle during peak hours. The identity data and illegal riding data may be obtained through the personnel identity database built into the server or server cluster, and the location data may be obtained through the image acquisition device deployed in the public place.

[0065] In a possible embodiment, when the rider is a specific person or is suspected of illegally carrying passengers, the appearance location data of the rider is obtained through the image acquisition equipment deployed in the public place, and the identity data and violation data of the rider are obtained through the personal identity database.

[0066] 105. Based on structured data, determine whether the rider is illegally carrying passengers.

[0067] In an embodiment of the present invention, the illegal intention of the above-mentioned cyclist to carry passengers can be determined based on the attribute data in the above-mentioned structured data, and the historical illegal behavior of the above-mentioned cyclist can be determined based on the illegal data in the above-mentioned structured data. Through the above-mentioned illegal intention of carrying passengers and the above-mentioned historical illegal behavior, it can be determined whether the above-mentioned cyclist is an illegal passenger-carrying person.

[0068] In a possible embodiment, the above-mentioned structured data may include multiple sub-data. After the structured data of the above-mentioned cyclist is obtained, weight allocation is performed based on the above-mentioned structured data to obtain a data weight integral. Based on the above-mentioned data weight integral, it is determined whether the above-mentioned cyclist is an illegal passenger carrier. The above-mentioned weight allocation can be set according to the correlation between the sub-data in the structured data and the illegal passenger carrying to obtain the weight corresponding to the sub-data. The weights corresponding to the above-mentioned sub-data are added to obtain the data weight integral corresponding to the above-mentioned structured data. When the above-mentioned data weight integral reaches a preset integral threshold, the above-mentioned cyclist is an illegal passenger carrier.

[0069] Specifically, if the correlation between a sub-data in the above-mentioned structured data and the image of illegal passenger carrying is stronger, the weight assigned to the corresponding sub-data in the above-mentioned structured data is higher; if the correlation between the sub-data in the above-mentioned attribute data or illegal data and the image of illegal passenger carrying is weaker, the weight assigned to the corresponding sub-data in the above-mentioned attribute data or illegal data is lower.

[0070] In an embodiment of the present invention, when a multi-person cycling event is detected, characteristic data of the cyclists in the multi-person cycling event is obtained, and the characteristic data of the cyclists is collided with the characteristic data of the specific person in the specific person database to determine whether the cyclist is a specific person or a non-specific person. If the cyclist is a non-specific person, it is determined whether the cyclist is suspected of illegally carrying passengers. If the cyclist is a specific person or the cyclist is suspected of illegally carrying passengers, the structured data of the cyclist is obtained, and based on the structured data, it is determined whether the cyclist is an illegal passenger carrier. Through comprehensive analysis of the specific person database and the structured data, it is determined whether the cyclist is an illegal passenger carrier, which fully considers the attribute data of the cyclist and the potential relationship between the illegal data and the illegal behavior, thereby realizing fast and efficient identification of illegal passenger carrying, which can effectively reduce the risk of life and property safety of citizens and improve the efficiency and level of urban traffic management.

[0071] Optionally, in the step of colliding the characteristic data of the rider with the specific person library to determine whether the rider is a specific person or a non-specific person, the characteristic data of the rider can also be collided one by one with the characteristic data of specific persons in the specific person library; if the characteristic data of the rider successfully collides with the characteristic data of any specific person in the specific person library, the rider is determined to be a specific person; if the characteristic data of the rider fails to collide with the characteristic data of all specific persons in the specific person library, the rider is determined to be a non-specific person.

[0072] In an embodiment of the present invention, the characteristic data of the above-mentioned rider can be collided with the characteristic data of a specific person in the specific person library one by one. When the matching degree between the characteristic data of the above-mentioned rider and the characteristic data of any specific person in the specific person library is higher than a preset matching degree threshold, it indicates that the collision is successful. When the matching degree between the characteristic data of the above-mentioned rider and the characteristic data of all specific persons in the specific person library is less than the preset matching degree threshold, it indicates that the collision fails. The above-mentioned matching degree can be the degree of data similarity between the characteristic data of the above-mentioned rider and the characteristic data of the specific person in the above-mentioned specific person library. If the collision is successful, the rider is determined to be a specific person. If the collision fails, the rider is determined to be a non-specific person.

[0073] In a possible embodiment, when a multi-person riding event is detected and the characteristic data of the riders are obtained, the characteristic data of the riders can be collided one by one with the characteristic data of specific persons in a specific person library preset in a server or a server cluster. If the characteristic data of the rider successfully collides with the characteristic data of any specific person in the specific person library, the rider is determined to be a specific person. If the characteristic data of the rider fails to collide with the characteristic data of all specific persons in the specific person library, the rider is determined to be a non-specific person, and the suspicion of illegal carrying of passengers by the above-mentioned rider is further explored.

[0074] Optionally, in the step of determining whether the cyclist is suspected of illegally carrying passengers if the cyclist is a non-specific person, if the cyclist is a non-specific person, obtaining a first historical multi-person cycling event; performing collision processing on the characteristic data of the cyclist and the characteristic data of historical cyclists to obtain a second historical multi-person cycling event corresponding to the cyclist; and determining whether the cyclist is suspected of illegally carrying passengers based on the second historical multi-person cycling event.

[0075] In an embodiment of the present invention, the above-mentioned first historical multi-person cycling event may include characteristic data of the historical cyclists, characteristic data of the passengers corresponding to the historical cyclists, and characteristic data of the cycling vehicles corresponding to the historical cyclists. The above-mentioned first historical multi-person cycling event can be determined based on the riding time and riding location of the multi-person cycling event corresponding to the above-mentioned cyclists.

[0076] Specifically, according to the riding time of the above-mentioned multi-person riding event, the time range of the above-mentioned first historical multi-person riding event is determined, according to the riding location of the above-mentioned multi-person riding event, the spatial range of the above-mentioned first historical multi-person riding event is determined, based on the above-mentioned time range and the above-mentioned spatial range, the acquisition range of the above-mentioned first historical multi-person riding event is determined, and the first historical multi-person riding event occurring within the above-mentioned acquisition range is acquired through the image acquisition equipment in the above-mentioned public place, the feature data of the above-mentioned cyclists are collided with the feature data of the above-mentioned historical cyclists, and the historical multi-person riding event corresponding to the feature data of the historical cyclists who have successfully collided is used as the second historical multi-person riding event.

[0077] In a possible embodiment, when the above-mentioned cyclist is a non-specific person, the above-mentioned first historical multi-person cycling event is obtained through the image acquisition device in the above-mentioned public place, and the feature data of the above-mentioned cyclist is subjected to collision processing with the feature data of the historical cyclist corresponding to the above-mentioned first historical multi-person cycling event, and the historical multi-person cycling event corresponding to the feature data of the historical cyclist that has successfully collided is used as the second historical multi-person cycling event, and the suspicion of illegal carrying of passengers by the above-mentioned cyclist is further analyzed based on the above-mentioned second historical multi-person cycling event to determine whether the above-mentioned cyclist is suspected of illegal carrying of passengers.

[0078] Optionally, in the step of determining whether the cyclist is suspected of illegally carrying passengers based on the second historical multi-person riding event, collision processing can also be performed between the characteristic data of the cyclist's historical passengers to determine whether the cyclist has multiple historical passengers; if the cyclist has multiple historical passengers, it is determined that the cyclist is suspected of illegally carrying passengers.

[0079] In an embodiment of the present invention, the above-mentioned second historical multi-passenger riding event includes characteristic data of historical passengers of the riding personnel. The above-mentioned multiple historical passengers may be historical passengers whose number is greater than the threshold number of passengers. Collision processing is performed between the characteristic data of the historical passengers of the riding personnel to determine whether the above-mentioned riding personnel has multiple historical passengers. If the number of the above-mentioned multiple historical passengers is greater than the threshold number of passengers, it is determined that the riding personnel is suspected of illegally carrying passengers.

[0080] In a possible embodiment, after obtaining the above-mentioned second historical multi-passenger riding event, collision processing is performed between the characteristic data of the above-mentioned riding personnel's historical passengers to determine whether the riding personnel has multiple historical passengers. If the number of the above-mentioned multiple historical passengers is greater than the number of passengers threshold, it is determined that the riding personnel is suspected of illegally carrying passengers.

[0081] Optionally, in the step of determining whether the cyclist is an illegal passenger carrier based on structured data, it is also possible to determine whether the cyclist has an illegal intention to carry passengers based on attribute data; determine whether the cyclist has a history of illegal behavior based on the violation data; and determine whether the cyclist is an illegal passenger carrier based on the illegal intention to carry passengers and the historical illegal behavior.

[0082] In an embodiment of the present invention, the above-mentioned structured data may include attribute data and violation data of the rider. When the above-mentioned rider is a specific person or is suspected of illegally carrying passengers, it is determined whether the above-mentioned rider has the intention of illegally carrying passengers based on the above-mentioned attribute data, and it is determined whether the rider has a history of illegal behavior based on the above-mentioned violation data.

[0083] For example, the age and occupation of the above-mentioned cyclist can be determined based on the above-mentioned attribute data. When the age of the above-mentioned cyclist is between 40 and 60 and the occupation is unemployed, the above-mentioned cyclist has a stronger intention to illegally carry passengers. Cyclists who are between 40 and 60 and are unemployed often have no fixed income. Under this background, the possibility of illegal passenger carrying by the above-mentioned cyclist is higher. If the above-mentioned cyclist has a history of illegal behavior, the above-mentioned historical illegal behavior may be riding a non-motor vehicle on a motor vehicle lane, riding a non-motor vehicle through a red light and other illegal behaviors, which often indicate that the above-mentioned cyclist has a weak legal awareness. Therefore, when the above-mentioned cyclist is between 40 and 60 years old and has no fixed occupation, the above-mentioned cyclist is determined to be an illegal passenger carrier based on the background that the above-mentioned cyclist has a historical violation record according to the violation data.

[0084] Optionally, in the step of determining whether the cyclist has the intention of illegally carrying passengers based on the attribute data, the group portrait of the cyclist can also be determined based on the identity data; the high-frequency places where the cyclist appears and the time periods when they appear in the high-frequency places can be determined based on the appearance place data; the appearance intention of the cyclist can be determined based on the high-frequency places and time periods; and whether the cyclist has the intention of illegally carrying passengers can be determined based on the group portrait and appearance intention.

[0085] In an embodiment of the present invention, the above-mentioned attribute data include the appearance place data and identity data of the cyclist. The above-mentioned group portrait can be used to map whether the above-mentioned cyclist has the potential intention of illegally carrying passengers. The identity data in the above-mentioned attribute data is used to determine the identity, age and occupation of the above-mentioned cyclist. The group portrait corresponding to the above-mentioned cyclist is determined based on the above-mentioned identity, age and occupation information. The above-mentioned appearance place data may be the high-frequency places and time periods where the above-mentioned cyclist appears. The above-mentioned high-frequency places may be crowded areas such as subway stations and railway stations. The above-mentioned time period may be the rush hour time period. The appearance intention of the above-mentioned cyclist can be determined through the above-mentioned high-frequency places and the above-mentioned time periods.

[0086] For example, if the identities of the above-mentioned cyclists are ordinary people, their ages are 40-60, and their occupations are unfixed, then based on the above information, it can be determined that the group portrait of the above-mentioned cyclists is a group of people who are prone to illegal passenger carrying behavior, and based on the data of the appearance locations of the above-mentioned cyclists, it can be determined that the above-mentioned cyclists appear frequently in crowded areas such as subway stations and railway stations, and their appearance time period is rush hour. It can be determined that the intention of the above-mentioned cyclists is to illegally carry passengers. Based on the group portrait of the above-mentioned cyclists and their intention, it can be determined that the above-mentioned cyclists have the intention of illegally carrying passengers.

[0087] Optionally, in the step of determining whether the rider is an illegal passenger-carrying person based on illegal passenger-carrying intention and historical illegal behavior, the rider's point value can also be determined based on the illegal passenger-carrying intention and historical illegal behavior; based on the point value, determine whether the rider is an illegal passenger-carrying person.

[0088] In an embodiment of the present invention, the above-mentioned integral value may be a weighted integral value, and the above-mentioned weighted integral value may be obtained by performing an integral calculation operation through a model, and the above-mentioned model may be a unit root process model (Unit Root Process Model), an autoregressive integrated moving average model (Autoregressive Integrated Moving Average Model, ARIMA), a stochastic integral model (Stochastic Integral Model) and the like. The integral weight of the above-mentioned illegal passenger carrying intention is determined based on the above-mentioned illegal passenger carrying intention and historical illegal behavior, and the above-mentioned model is configured based on the above-mentioned integral weight to obtain a configured model. The illegal passenger carrying intention and historical illegal behavior corresponding to the above-mentioned rider are input into the above-mentioned configured model to obtain the integral value corresponding to the above-mentioned rider, and the above-mentioned integral value is compared with a preset integral threshold value. If the above-mentioned integral value is greater than or equal to the above-mentioned integral threshold value, the above-mentioned rider is an illegal passenger carrying person, and if the above-mentioned integral value is less than the above-mentioned integral threshold value, the above-mentioned rider is a non-illegal passenger carrying person.

[0089] It should be noted that the illegal passenger carrying identification method provided in the embodiment of the present invention can be applied to photographing equipment, smart phones, computers, servers and other devices that can perform illegal passenger carrying identification.

[0090] like Figure 2 As shown, an embodiment of the present invention provides an illegal passenger identification device, the illegal passenger identification device comprising:

[0091] The first detection module 201 is used to obtain characteristic data of riders in a multi-rider riding event when a multi-rider riding event is detected;

[0092] The first collision module 202 is used to perform collision processing on the characteristic data of the rider and the characteristic data of the specific person in the specific person database, and determine whether the rider is a specific person or a non-specific person, and the specific person is a person who illegally carries passengers;

[0093] The first determination module 203 is used to determine whether the rider is suspected of illegally carrying passengers if the rider is a non-specific person;

[0094] The first acquisition module 204 is used to acquire the structured data of the cyclist if the cyclist is a specific person or the cyclist is suspected of illegally carrying passengers;

[0095] The second determination module 205 is used to determine whether the rider is a passenger-carrying person illegally based on the structured data.

[0096] Optionally, the first collision module 202 includes:

[0097] A second collision module is used to collide the characteristic data of the rider with the characteristic data of the specific person in the specific person database one by one;

[0098] A third determination module is used to determine that the rider is a specific person if the characteristic data of the rider successfully collides with the characteristic data of any specific person in the specific person database;

[0099] The fourth determination module is used to determine that the rider is a non-specific person if the feature data of the rider fails to collide with the feature data of all specific persons in the specific person database.

[0100] Optionally, the first determining module 203 includes:

[0101] A second acquisition module is used for acquiring a first historical multi-person cycling event if the cyclist is a non-specific person, wherein the first historical multi-person cycling event includes feature data of historical cyclists;

[0102] A third collision module is used to perform collision processing on the characteristic data of the rider and the characteristic data of the historical riders to obtain a second historical multi-rider riding event corresponding to the rider;

[0103] The fifth determination module is used to determine whether the rider is suspected of illegally carrying passengers based on the second historical multi-rider riding event.

[0104] Optionally, the fifth determining module includes:

[0105] A fourth collision module, configured to perform collision processing between feature data of historical passengers of the rider, and determine whether the rider has multiple historical passengers;

[0106] The sixth determination module is used to determine whether the cyclist is suspected of illegally carrying passengers if the cyclist has multiple historical passengers.

[0107] Optionally, the second determining module 205 includes:

[0108] A seventh determination module, for determining whether the rider has an illegal intention to carry passengers based on the attribute data;

[0109] An eighth determination module, configured to determine whether the rider has a history of illegal behavior based on the illegal data;

[0110] The ninth determination module is used to determine whether the rider is an illegal passenger-carrying person based on the illegal passenger-carrying intention and the historical illegal behavior.

[0111] Optionally, the seventh determining module includes:

[0112] A first determination submodule, configured to determine a group portrait of the riders based on the identity data;

[0113] A second determination submodule is used to determine the high-frequency places where the cyclist appears and the time period when the cyclist appears in the high-frequency places based on the appearance place data;

[0114] A third determination submodule is used to determine the appearance intention of the rider based on the high-frequency place and the time period;

[0115] The fourth determination submodule is used to determine whether the rider has the intention of illegally carrying passengers based on the group portrait and the appearance intention.

[0116] Optionally, the ninth determining module includes:

[0117] a fifth determination submodule, configured to determine a score value of the rider based on the illegal passenger carrying intention and the historical illegal behavior;

[0118] The sixth determination submodule is used to determine whether the rider is a passenger-carrying person illegally based on the integral value.

[0119] It should be noted that the illegal passenger carrying identification device provided in the embodiment of the present invention can be applied to photographing equipment, smart phones, computers, servers and other equipment that can perform illegal passenger carrying identification.

[0120] The illegal passenger carrying identification device provided in the embodiment of the present invention can implement each process implemented by the illegal passenger carrying identification method in the above method embodiment, and can achieve the same beneficial effects. To avoid repetition, it will not be described here.

[0121] See also Figure 3 , Figure 3 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 3 As shown, it includes: a memory 302, a processor 301, and a computer program of a method for identifying illegal passenger carrying stored in the memory 302 and executable on the processor 301, wherein:

[0122] The processor 301 is used to call the computer program stored in the memory 302 and execute the following steps:

[0123] When a multi-person riding event is detected, obtaining characteristic data of the riders in the multi-person riding event;

[0124] Perform collision processing on the characteristic data of the rider and the characteristic data of the specific person in the specific person database to determine whether the rider is a specific person or a non-specific person, and the specific person is a person who illegally carries passengers;

[0125] If the rider is a non-specific person, determining whether the rider is suspected of illegally carrying passengers;

[0126] If the rider is a specific person or the rider is suspected of illegally carrying passengers, obtaining structured data of the rider;

[0127] Based on the structured data, determine whether the rider is a person who illegally carries passengers.

[0128] Optionally, the processor 301 performs collision processing on the characteristic data of the rider with a specific person database to determine whether the rider is a specific person or a non-specific person, including:

[0129] The characteristic data of the rider is collided with the characteristic data of the specific person in the specific person database one by one;

[0130] If the characteristic data of the rider successfully collides with the characteristic data of any specific person in the specific person database, the rider is determined to be a specific person;

[0131] If the characteristic data of the rider fails to collide with the characteristic data of all specific persons in the specific person database, it is determined that the rider is a non-specific person.

[0132] Optionally, the processor 301 performs, if the rider is a non-specific person, determining whether the rider is suspected of illegally carrying passengers, including:

[0133] If the rider is a non-specific person, a first historical multi-rider riding event is obtained, where the first historical multi-rider riding event includes feature data of historical riders;

[0134] Performing collision processing on the characteristic data of the rider and the characteristic data of the historical riders to obtain a second historical multi-rider riding event corresponding to the rider;

[0135] Based on the second historical multi-person riding event, determine whether the riding person is suspected of illegally carrying passengers.

[0136] Optionally, the processor 301 executes the second historical multi-person riding event including characteristic data of historical passengers of the rider, and the determining whether the rider is suspected of illegally carrying passengers based on the second historical multi-person riding event includes:

[0137] performing collision processing between the characteristic data of the historical passengers of the rider to determine whether the rider has multiple historical passengers;

[0138] If the rider has multiple historical passengers, it is determined that the rider is suspected of illegally carrying passengers.

[0139] Optionally, the processor 301 executes, the structured data includes attribute data and violation data of the rider, and the determining whether the rider is an illegal passenger-carrying person based on the structured data includes:

[0140] Based on the attribute data, determining whether the rider has illegal intention to carry passengers;

[0141] Based on the violation data, determining whether the rider has a history of violations;

[0142] Based on the illegal intention of carrying passengers and the historical illegal behavior, it is determined whether the rider is an illegal passenger-carrying person.

[0143] Optionally, the processor 301 executes, wherein the attribute data includes the appearance location data and identity data of the rider, and the determining whether the rider has illegal intention of carrying passengers based on the attribute data includes:

[0144] Determine a group portrait of the riders based on the identity data;

[0145] Based on the appearance location data, determine the high-frequency locations where the rider appears and the time period when the rider appears in the high-frequency locations;

[0146] Determining the appearance intention of the rider based on the high-frequency places and the time period;

[0147] Based on the group portrait and the intention of appearance, determine whether the rider has the intention of illegally carrying passengers.

[0148] Optionally, the processor 301 determines whether the rider is a person who illegally carries passengers based on the illegal intention to carry passengers and the historical illegal behavior, including:

[0149] Determining a score value of the rider based on the illegal passenger-carrying intention and the historical illegal behavior;

[0150] According to the integral value, it is determined whether the rider is a person who illegally carries passengers.

[0151] It should be noted that the electronic device provided in the embodiment of the present invention can be applied to smart phones, computers, servers and other devices that can perform illegal passenger identification methods.

[0152] The electronic device provided in the embodiment of the present invention can implement each process implemented by the illegal passenger identification method in the above method embodiment, and can achieve the same beneficial effect. To avoid repetition, it will not be described here.

[0153] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the computer program implements the various processes of the illegal passenger identification method or the application-side illegal passenger identification method provided by the embodiment of the present invention, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0154] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0155] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for identifying illegal passenger carrying, characterized in that: The method comprises the following steps: When a multi-person riding event is detected, obtaining characteristic data of the riders in the multi-person riding event; Perform collision processing on the characteristic data of the rider and the characteristic data of the specific person in the specific person database to determine whether the rider is a specific person or a non-specific person, and the specific person is a person who illegally carries passengers; If the rider is a non-specific person, determining whether the rider is suspected of illegally carrying passengers; If the rider is a specific person or the rider is suspected of illegally carrying passengers, obtaining structured data of the rider; Based on the structured data, determine whether the rider is a person who illegally carries passengers.

2. The method for identifying illegal passenger carrying as claimed in claim 1, characterized in that: The step of performing collision processing on the characteristic data of the rider and the specific person database to determine whether the rider is a specific person or a non-specific person includes: The characteristic data of the rider is collided with the characteristic data of the specific person in the specific person database one by one; If the characteristic data of the rider successfully collides with the characteristic data of any specific person in the specific person database, the rider is determined to be a specific person; If the characteristic data of the rider fails to collide with the characteristic data of all specific persons in the specific person database, it is determined that the rider is a non-specific person.

3. The method for identifying illegal passenger carrying as claimed in claim 1 or 2, characterized in that: If the rider is a non-specific person, determining whether the rider is suspected of illegally carrying passengers includes: If the rider is a non-specific person, a first historical multi-rider riding event is obtained, where the first historical multi-rider riding event includes feature data of historical riders; Performing collision processing on the characteristic data of the rider and the characteristic data of the historical riders to obtain a second historical multi-rider riding event corresponding to the rider; Based on the second historical multi-person riding event, determine whether the riding person is suspected of illegally carrying passengers.

4. The method for identifying illegal passenger carrying as claimed in claim 3, characterized in that: The second historical multi-passenger riding event includes characteristic data of historical passengers of the rider, and determining whether the rider is suspected of illegally carrying passengers based on the second historical multi-passenger riding event includes: performing collision processing between the characteristic data of the historical passengers of the rider to determine whether the rider has multiple historical passengers; If the rider has multiple historical passengers, it is determined that the rider is suspected of illegally carrying passengers.

5. The method for identifying illegal passenger carrying as claimed in any one of claims 1 to 4, characterized in that: The structured data includes attribute data and violation data of the rider, and determining whether the rider is a passenger-carrying person illegally based on the structured data includes: Based on the attribute data, determining whether the rider has illegal intention to carry passengers; Based on the violation data, determining whether the rider has a history of violations; Based on the illegal intention of carrying passengers and the historical illegal behavior, it is determined whether the rider is an illegal passenger-carrying person.

6. The method for identifying illegal passenger carrying as claimed in claim 5, characterized in that: The attribute data includes the appearance location data and identity data of the rider, and the determining whether the rider has illegal intention of carrying passengers based on the attribute data includes: Determine a group portrait of the riders based on the identity data; Based on the appearance location data, determine the high-frequency locations where the rider appears and the time period when the rider appears in the high-frequency locations; Determining the appearance intention of the rider based on the high-frequency places and the time period; Based on the group portrait and the intention of appearance, determine whether the rider has the intention of illegally carrying passengers.

7. The method for identifying illegal passenger carrying as claimed in claim 5 or 6, characterized in that: The determining whether the rider is an illegal passenger-carrying person based on the illegal passenger-carrying intention and the historical illegal behavior includes: Determining a score value of the rider based on the illegal passenger-carrying intention and the historical illegal behavior; According to the integral value, it is determined whether the rider is a person who illegally carries passengers.

8. An illegal passenger identification device, characterized in that: The illegal passenger identification device comprises: A first detection module is used to obtain characteristic data of riders in a multi-rider riding event when a multi-rider riding event is detected; A first collision module is used to perform collision processing on the characteristic data of the rider and the characteristic data of the specific person in the specific person database, and determine whether the rider is a specific person or a non-specific person, and the specific person is a person who illegally carries passengers; A first determination module is used to determine whether the rider is suspected of illegally carrying passengers if the rider is a non-specific person; A first acquisition module is used to acquire structured data of the rider if the rider is a specific person or the rider is suspected of illegally carrying passengers; The second determination module is used to determine whether the rider is a passenger-carrying person illegally based on the structured data.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the illegal passenger carrying identification method as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the illegal passenger carrying identification method as described in any one of claims 1 to 7 are implemented.

Images