Taxi taking system and method, electronic equipment, storage medium and program product

Abstract

The embodiment of the invention provides a taxi taking system and method, electronic equipment, a storage medium and a program product. The method comprises the steps of receiving a taxi-taking request through a taxi-taking platform, obtaining a passenger half-body image and a passenger position of a passenger, generating a target order and sending the target order to a vehicle-mounted terminal, controlling vehicle driving through the vehicle-mounted terminal according to the target order and determining the remaining distance between the vehicle and the passenger position in real time, and when the remaining distance is first data, sending the first data to the taxi-taking platform; performing feature extraction on the real-time environment data to obtain pedestrian feature information, comparing pedestrian face information in the pedestrian feature information with passenger face information, and comparing a pedestrian half-body image in the pedestrian feature information with a passenger half-body image; the similarity corresponding to the face information of each pedestrian and the similarity corresponding to the half-body image of each pedestrian are obtained, the identity of the passenger is confirmed based on each similarity, and the method is used for achieving the effects of improving the reliability and accuracy of identity confirmation before the passenger takes a bus and improving the bus taking efficiency.

Description

Technical Field

[0001] The present application relates to online car-hailing technology, and in particular to a car-hailing system, method, electronic device, storage medium and program product. Background Art

[0002] Currently, passengers usually travel by booking a taxi online.

[0003] In the existing technology, passengers send travel orders to the taxi-hailing platform through terminal devices, and the taxi-hailing platform sends the travel orders to the driver's terminal, so that the driver receives the travel order through the driver's terminal and drives the vehicle to the passenger's location. The driver contacts the passenger to obtain the other party's relevant information (such as their respective location information and license plate number), thereby completing the identity confirmation before boarding.

[0004] However, in an environment with dense crowds and / or vehicles, it is difficult for the driver and the passenger to quickly complete identity confirmation through visual recognition, which reduces the accuracy and efficiency of identity confirmation. Summary of the invention

[0005] The embodiments of the present application provide a taxi-hailing system, method, electronic device, storage medium and program product to improve the reliability and efficiency of passenger identity confirmation, improve the accuracy of identity confirmation, and improve the efficiency of passengers taking taxis.

[0006] In a first aspect, an embodiment of the present application provides a taxi-hailing system, including:

[0007] The taxi-hailing platform is used to send a target order to the vehicle terminal; the target order is generated by obtaining the passenger's half-body image and the passenger's position when receiving a taxi-hailing request sent by the terminal device;

[0008] The vehicle computer end is used to receive the target order. When the remaining distance between the real-time position of the vehicle and the passenger position is determined as the first data according to the target order, the pedestrian feature information is obtained by collecting the real-time environmental data outside the vehicle and performing feature extraction. The pedestrian feature information includes the pedestrian facial information and the pedestrian half-body image; the similarity corresponding to the pedestrian facial information is determined according to the passenger facial information, and the similarity corresponding to the pedestrian half-body image is confirmed based on the passenger half-body image, and the passenger identity is confirmed according to the similarity corresponding to the pedestrian facial information and the similarity corresponding to the pedestrian half-body image. The passenger facial information is obtained by the taxi-hailing platform according to the passenger's registration information.

[0009] Optionally, when the vehicle computer confirms the similarity corresponding to the pedestrian half-body image based on the passenger half-body image, and confirms the passenger identity according to the similarity corresponding to the pedestrian face information and the similarity corresponding to the pedestrian half-body image, it is specifically used to:

[0010] Determine the characteristic information in the passenger's half-body image, and obtain a three-dimensional full-body model of the passenger by reconstructing the characteristic information;

[0011] Determine the similarity of the pedestrian half-body image based on the three-dimensional full-body model;

[0012] The similarity corresponding to the pedestrian's facial information and the similarity corresponding to the pedestrian's half-body image are compared with preset thresholds respectively. When at least one similarity exceeds the preset threshold, the passenger's identity is determined based on the pedestrian feature information corresponding to the similarity.

[0013] Optionally, the pedestrian feature information includes pedestrian gesture information and pedestrian voiceprint information;

[0014] The vehicle terminal is also used for:

[0015] When the remaining distance is determined to be the second data, determining whether the passenger identity is successfully confirmed;

[0016] When the passenger's identity is not confirmed successfully, the similarity corresponding to the pedestrian's gesture information is determined based on the preset gesture information, and when it is determined that the similarity corresponding to the pedestrian's gesture information exceeds a preset threshold, the passenger's identity is determined according to the pedestrian's gesture information.

[0017] Optionally, the vehicle terminal is also used for:

[0018] When it is determined that the passenger's identity has not been confirmed successfully, the similarity corresponding to the pedestrian's voiceprint information is determined based on the passenger's voiceprint information, and when it is determined that the similarity corresponding to the pedestrian's voiceprint information exceeds a preset threshold, the passenger's identity is determined based on the pedestrian's voiceprint information; wherein, the passenger's voiceprint information is obtained by the taxi platform based on the passenger's registration information.

[0019] Optionally, the vehicle terminal is further configured to generate a movement request and send the request to the taxi-hailing platform when determining that the remaining distance is the third data;

[0020] The taxi-hailing platform is also used to receive movement requests, determine the location indicated by the vehicle terminal according to the movement request, generate a transfer instruction based on the location and send it to the passenger's terminal device. The transfer instruction is used to instruct the passenger to move to the location so that the vehicle terminal can confirm the identity of the passenger.

[0021] In a second aspect, an embodiment of the present application provides a taxi-hailing method, which is applied to a taxi-hailing platform, including:

[0022] Receive a taxi request sent by a passenger's terminal device, obtain the passenger's half-body image and the passenger's location, and generate a target order;

[0023] The target order is sent to the vehicle computer end, so that the vehicle computer end determines the similarity corresponding to the pedestrian facial information based on the passenger facial information, and confirms the similarity corresponding to the pedestrian half-body image based on the passenger half-body image, and confirms the passenger identity based on the similarity corresponding to the pedestrian facial information and the similarity corresponding to the pedestrian half-body image; the pedestrian facial information and the pedestrian half-body image are obtained by the vehicle computer end by collecting real-time environmental data outside the vehicle and performing feature extraction when the remaining distance between the real-time position of the vehicle and the passenger position is determined as the first data according to the target order, and the passenger facial information is obtained by the taxi-hailing platform based on the passenger's registration information.

[0024] Optionally, a movement request is received, the location indicated by the vehicle-side is determined according to the movement request, a transfer instruction is generated according to the location and sent to the passenger's terminal device, the transfer instruction is used to instruct the passenger to move to the location so that the vehicle-side can confirm the identity of the passenger, wherein the movement request is generated by the vehicle-side when it determines that the remaining distance is the third data.

[0025] In a third aspect, an embodiment of the present application provides a taxi-hailing method, which is applied to a vehicle terminal, and includes:

[0026] receiving a target order sent by a taxi-hailing platform, and when determining the remaining distance between the real-time position of the vehicle and the position of the passenger as the first data according to the target order, obtaining pedestrian feature information by collecting real-time environmental data outside the vehicle and performing feature extraction, the pedestrian feature information includes pedestrian face information and a half-body image of the pedestrian. The target order is generated by the taxi-hailing platform through the obtained passenger half-body image and passenger position when receiving a taxi request sent by a terminal device;

[0027] The similarity corresponding to the pedestrian's facial information is determined based on the passenger's facial information, and the similarity corresponding to the pedestrian's half-body image is confirmed based on the passenger's half-body image. The passenger's identity is confirmed based on the similarity corresponding to the pedestrian's facial information and the similarity corresponding to the pedestrian's half-body image. The passenger's facial information is obtained by the taxi-hailing platform based on the passenger's registration information.

[0028] Optionally, when confirming the similarity corresponding to the half-body image of the pedestrian based on the half-body image of the passenger, and confirming the identity of the passenger according to the similarity corresponding to the facial information of the pedestrian and the similarity corresponding to the half-body image of the pedestrian, the method includes:

[0029] Determine the characteristic information in the passenger's half-body image, and obtain a three-dimensional full-body model of the passenger by reconstructing the characteristic information;

[0030] Determine the similarity of the pedestrian half-body image based on the three-dimensional full-body model;

[0031] The similarity corresponding to the pedestrian's facial information and the similarity corresponding to the pedestrian's half-body image are compared with preset thresholds respectively. When at least one similarity exceeds the preset threshold, the passenger's identity is determined based on the pedestrian feature information corresponding to the similarity.

[0032] Optionally, the pedestrian feature information includes pedestrian gesture information and pedestrian voiceprint information;

[0033] When the remaining distance is determined to be the second data, determining whether the passenger identity is successfully confirmed;

[0034] When the passenger's identity is not confirmed successfully, the similarity corresponding to the pedestrian's gesture information is determined based on the preset gesture information, and when it is determined that the similarity corresponding to the pedestrian's gesture information exceeds a preset threshold, the passenger's identity is determined according to the pedestrian's gesture information.

[0035] Optionally, when the passenger's identity is not confirmed successfully, the similarity corresponding to the pedestrian's voiceprint information is determined based on the passenger's voiceprint information, and when it is determined that the similarity corresponding to the pedestrian's voiceprint information exceeds a preset threshold, the passenger's identity is determined based on the pedestrian's voiceprint information; wherein the passenger's voiceprint information is obtained by the taxi platform based on the passenger's registration information.

[0036] Optionally, when the remaining distance is determined to be the third data, a movement request is generated and sent to the taxi-hailing platform; so that the taxi-hailing platform determines the location indicated by the vehicle-side according to the movement request, and generates a transfer instruction based on the location and sends it to the passenger's terminal device. The transfer instruction is used to instruct the passenger to move to the location so that the vehicle-side can confirm the identity of the passenger.

[0037] In a fourth aspect, an embodiment of the present application provides a taxi-hailing device, which is applied to a taxi-hailing platform, including:

[0038] The first receiving module is used to receive a taxi request sent by a passenger's terminal device, obtain a half-body image of the passenger and the passenger's location, and generate a target order;

[0039] The first processing module is used to send the target order to the vehicle computer end, so that the vehicle computer end determines the similarity corresponding to the pedestrian facial information based on the passenger facial information, and confirms the similarity corresponding to the pedestrian half-body image based on the passenger half-body image, and confirms the passenger identity according to the similarity corresponding to the pedestrian facial information and the similarity corresponding to the pedestrian half-body image; the pedestrian facial information and the pedestrian half-body image are obtained by the vehicle computer end when determining the remaining distance between the real-time position of the vehicle and the passenger position as the first data according to the target order, by collecting real-time environmental data outside the vehicle and performing feature extraction, and the passenger facial information is obtained by the taxi-hailing platform according to the passenger's registration information.

[0040] Optionally, the first receiving module is also used to receive a movement request, determine the location indicated by the vehicle-side according to the movement request, generate a transfer instruction according to the location and send it to the passenger's terminal device, the transfer instruction is used to instruct the passenger to move to the location so that the vehicle-side can confirm the identity of the passenger, wherein the movement request is generated by the vehicle-side when it determines that the remaining distance is the third data.

[0041] In a fifth aspect, an embodiment of the present application provides a taxi-hailing device, which is applied to a vehicle terminal, and includes:

[0042] The second receiving module is used to receive the target order sent by the taxi-hailing platform. When the remaining distance between the real-time position of the vehicle and the position of the passenger is determined as the first data according to the target order, the pedestrian feature information is obtained by collecting the real-time environmental data outside the vehicle and performing feature extraction. The pedestrian feature information includes the pedestrian face information and the pedestrian half-body image. The target order is generated by the taxi-hailing platform through the obtained passenger half-body image and passenger position when receiving the taxi request sent by the terminal device;

[0043] The second processing module is used to determine the similarity corresponding to the pedestrian's facial information based on the passenger's facial information, and to confirm the similarity corresponding to the pedestrian's half-body image based on the passenger's half-body image, and to confirm the passenger's identity based on the similarity corresponding to the pedestrian's facial information and the similarity corresponding to the pedestrian's half-body image. The passenger's facial information is obtained by the taxi-hailing platform based on the passenger's registration information.

[0044] Optionally, the second processing module is further used to determine feature information in the passenger's half-body image, and obtain a three-dimensional full-body model of the passenger by reconstructing the feature information;

[0045] Determine the similarity of the pedestrian half-body image based on the three-dimensional full-body model;

[0046] The similarity corresponding to the pedestrian's facial information and the similarity corresponding to the pedestrian's half-body image are compared with preset thresholds respectively. When at least one similarity exceeds the preset threshold, the passenger's identity is determined based on the pedestrian feature information corresponding to the similarity.

[0047] Optionally, the pedestrian feature information includes pedestrian gesture information and pedestrian voiceprint information; the second processing module is further used to determine whether the passenger identity is successfully confirmed when the remaining distance is determined to be the second data;

[0048] When the passenger's identity is not confirmed successfully, the similarity corresponding to the pedestrian's gesture information is determined based on the preset gesture information, and when it is determined that the similarity corresponding to the pedestrian's gesture information exceeds a preset threshold, the passenger's identity is determined according to the pedestrian's gesture information.

[0049] Optionally, the second processing module is also used to determine the similarity corresponding to the pedestrian's voiceprint information based on the passenger's voiceprint information when it is determined that the passenger's identity has not been successfully confirmed, and to determine the passenger's identity based on the pedestrian's voiceprint information when it is determined that the similarity corresponding to the pedestrian's voiceprint information exceeds a preset threshold; wherein the passenger's voiceprint information is obtained by the taxi platform based on the passenger's registration information.

[0050] Optionally, the second processing module is also used to generate a movement request and send it to the taxi-hailing platform when it is determined that the remaining distance is the third data; so that the taxi-hailing platform determines the location indicated by the vehicle-mounted terminal according to the movement request, and generates a transfer instruction based on the location and sends it to the passenger's terminal device. The transfer instruction is used to instruct the passenger to move to the location so that the vehicle-mounted terminal can confirm the identity of the passenger.

[0051] In a sixth aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor;

[0052] Memory stores computer-executable instructions;

[0053] The processor executes the computer-executable instructions stored in the memory, so that the processor executes various possible implementations of the second aspect and / or the third aspect as described above.

[0054] In the seventh aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-readable storage medium is stored computer execution instructions, which, when executed by a processor, are used to implement various possible implementations of the second aspect and / or the third aspect as described above.

[0055] In an eighth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements various possible implementations of the second aspect and / or the third aspect as described above.

[0056] The taxi-hailing system, method, electronic device, storage medium and program product provided in the embodiments of the present application receive a taxi-hailing request sent by a terminal device through a taxi-hailing platform and obtain the passenger's half-body image and passenger position corresponding to the taxi-hailing request, generate a target order for the taxi-hailing request and send it to the vehicle-computer end. When the vehicle-computer end receives the target order, it determines the real-time remaining distance between the vehicle and the passenger's position according to the target order. When the remaining distance is the first data, it collects real-time environmental data outside the vehicle and performs feature extraction to obtain pedestrian feature information, compares the pedestrian facial information in the pedestrian feature information with the passenger facial information, and compares the pedestrian half-body image in the pedestrian feature information with the passenger half-body image corresponding to the passenger when the passenger initiates the taxi-hailing request, obtains the similarity corresponding to each pedestrian facial information and the similarity corresponding to each pedestrian half-body image, confirms the passenger's identity based on each similarity, improves the reliability and accuracy of the passenger's identity confirmation before boarding, and improves the passenger's boarding efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0058] Figure 1 Schematic diagram of application scenarios provided for this application;

[0059] Figure 2 A schematic diagram of the structure of the taxi-hailing system provided for this application;

[0060] Figure 3 A flowchart of the taxi-hailing method provided for this application;

[0061] Figure 4 The structure diagram of the taxi-hailing device provided in this application Figure 1 ;

[0062] Figure 5 The structure diagram of the taxi-hailing device provided in this application Figure 2 ;

[0063] Figure 6 A schematic diagram of the structure of the electronic device provided in this application.

[0064] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0065] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0066] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards in the relevant regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0067] Figure 1 The application scenario diagram provided for this application is as follows: Figure 1 As shown, the specific application scenarios of the present application are as follows: a passenger initiates a taxi request to a taxi platform through a terminal device, and the taxi platform sends the order corresponding to the taxi request to the order-receiving vehicle, so that the order-receiving vehicle completes the passenger's order.

[0068] In the prior art, the order-receiving vehicle travels according to the destination indicated in the order. When it is near the destination, the driver of the order-receiving vehicle initiates a call to the passenger to inform the passenger that the vehicle (including the license plate number) has arrived at the destination, so that the passenger can find the vehicle according to the license plate number. The driver can also ask the passenger about the appearance characteristics or surrounding buildings nearby to facilitate the driver to visually find the passenger and drive the vehicle to the corresponding location when the passenger is found, and remind the passenger to move to the location of the order-receiving vehicle by shouting and / or horn, so as to complete the identity confirmation before boarding.

[0069] However, in an environment with dense crowds and / or vehicles, it is difficult for the driver to accurately identify the user based on the passenger's appearance. In addition, when the user wears headphones, it is difficult for the driver to effectively call the user by shouting and / or honking. Therefore, the existing taxi-hailing method reduces the efficiency and accuracy of identity confirmation, and is likely to cause traffic congestion when the driver is looking for or waiting for passengers for a long time, further affecting travel efficiency and reducing the passenger's riding experience.

[0070] The taxi-hailing method provided by the present application obtains and stores the registration information of registered passengers through the taxi-hailing platform. When receiving a taxi-hailing request initiated by the passenger through a terminal device, the passenger's current half-body image and passenger position are obtained, and an order is generated and sent to the vehicle-computer end that requests the order. The vehicle is controlled to travel to the passenger's position through the vehicle-computer end. During the driving process, if the remaining distance between the real-time position of the vehicle-computer end and the passenger's position is the first data, the surrounding environmental data of the vehicle during the driving process is collected and features are extracted from the collected environmental data. The facial information of the pedestrian obtained by the feature extraction is compared with the facial information of the passenger stored on the taxi-hailing platform. The corresponding three-dimensional full-body model is reconstructed based on the half-body image of the passenger stored on the taxi-hailing platform, and the half-body image of the pedestrian obtained by the feature extraction is compared with the facial information of the passenger stored on the taxi-hailing platform. The three-dimensional full-body model is compared to obtain the similarities corresponding to the facial information of each pedestrian and the half-body image of each pedestrian in the current environmental data. If the similarities obtained do not exceed the preset threshold until the remaining distance is the second data, the pedestrian gesture information and the pedestrian voiceprint information are extracted from the collected environmental data, and compared with the preset gesture information and the passenger voiceprint information respectively, until the remaining distance is the third data, if the above similarities do not exceed the preset threshold, a transfer instruction is sent to the passenger's terminal device through the taxi platform to transfer the passenger to the indicated location, so as to improve the accuracy and efficiency of passenger recognition on the vehicle side, improve the reliability and efficiency of passenger identity confirmation, reduce the probability of traffic jams, further enhance the passenger's riding experience and improve the passenger's travel efficiency.

[0071] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0072] Figure 2 The structural diagram of the taxi-hailing system provided for this application is as follows: Figure 2As shown, the taxi-hailing system includes a vehicle terminal and a taxi-hailing platform, and the vehicle terminal includes vehicle terminal 1, vehicle terminal 2... vehicle terminal n, where n is a positive integer. The above-mentioned taxi-hailing platform is used to send a target order to the vehicle terminal; the target order is generated by obtaining a passenger half-body image and a passenger position when receiving a taxi request sent by a terminal device; the vehicle terminal is used to receive the target order, and when the remaining distance between the real-time position of the vehicle and the passenger position is determined as the first data according to the target order, the real-time environmental data outside the vehicle is collected and feature extracted to obtain pedestrian feature information, and the pedestrian feature information includes pedestrian facial information and pedestrian half-body image; the similarity corresponding to the pedestrian facial information is determined according to the passenger facial information, and the similarity corresponding to the pedestrian half-body image is confirmed based on the passenger half-body image, and the passenger identity is confirmed according to the similarity corresponding to the pedestrian facial information and the similarity corresponding to the pedestrian half-body image, and the passenger facial information is obtained by the taxi-hailing platform according to the passenger's registration information.

[0073] In a possible embodiment, Figure 2 As shown, when a passenger initiates a taxi request to the taxi platform through a terminal device, the taxi platform obtains the passenger's current half-body image and passenger position, generates a corresponding target order based on the passenger half-body image and passenger position and publishes it to the vehicle terminal, and when the order acceptance request indicating the target order sent by the vehicle terminal 1 is received, the target order and the passenger facial information, passenger voiceprint information and the above-mentioned passenger half-body image collected when the passenger registered are sent to the vehicle terminal 1.

[0074] In a possible embodiment, Figure 2As shown, based on the first data of 8 meters, the second data of 5 meters, and the third data of 3 meters, the vehicle terminal 1 controls the vehicle to travel to the destination indicated by the target order. When the vehicle terminal 1 travels to position A, the camera of the vehicle is turned on and the camera is controlled to collect environmental data within the shooting range of the vehicle during the driving process. The environmental data includes the sound data and picture data of each pedestrian. The vehicle terminal performs feature analysis based on the environmental data collected in real time, obtains multiple pedestrian face information and multiple pedestrian half-body images in the current environmental data, and obtains the similarity corresponding to each pedestrian face information relative to the passenger face information by comparing each pedestrian face information with the passenger face information. At the same time, each pedestrian half-body image is compared with the passenger half-body image uploaded when the passenger initiates a taxi request, and the similarity corresponding to each pedestrian half-body image relative to the passenger half-body image is obtained, and it is determined whether each similarity exceeds the preset threshold. If it is determined that there is at least one similarity that exceeds the preset threshold, the pedestrian feature information corresponding to the similarity is determined, and the passenger identity is confirmed based on the pedestrian feature information. If it is determined that there is no similarity corresponding to the pedestrian feature information with a similarity exceeding the preset threshold in the current environmental data, the feature analysis of the environmental data at the next moment is continued and the above steps are repeated until the identity of the passenger is determined. Among them, the passenger face information is sent to the vehicle terminal together with the vehicle platform sending the target order to the vehicle terminal.

[0075] In this embodiment, when a passenger initiates a taxi request, a half-body image of the passenger is obtained through the taxi platform to generate an order and send it to the vehicle computer. When the vehicle computer controls the vehicle to drive near the passenger, the facial information and half-body image of each pedestrian are obtained by performing feature analysis on the environmental data, and the passenger is jointly identified based on the similarity between the facial information and the half-body image of the pedestrian, thereby improving the reliability and accuracy of the passenger's identity confirmation before boarding the vehicle, improving the efficiency of identity confirmation and further improving the efficiency of passengers' boarding.

[0076] Optionally, when the vehicle-computer end confirms the similarity corresponding to the pedestrian's half-body image based on the passenger's half-body image, and confirms the passenger's identity based on the similarity corresponding to the pedestrian's facial information and the similarity corresponding to the pedestrian's half-body image, the following steps are included: the vehicle-computer end determines the feature information in the passenger's half-body image, and obtains a three-dimensional full-body model of the passenger by reconstructing the feature information; determines the similarity corresponding to the pedestrian's half-body image based on the three-dimensional full-body model; compares the similarity corresponding to the pedestrian's facial information and the similarity corresponding to the pedestrian's half-body image with preset thresholds respectively, and when at least one similarity exceeds the preset threshold, determines the passenger's identity based on the pedestrian feature information (pedestrian half-body image and / or pedestrian facial information) corresponding to the similarity.

[0077] Exemplarily, the feature information in the passenger's half-body image determined by the vehicle computer includes but is not limited to: the passenger's hairstyle, the passenger's clothing color, the passenger's clothing style (such as long sleeves, short sleeves, jacket), the passenger's backpack color, the passenger's hat color, the passenger's hat style, etc.

[0078] Exemplarily, a 3D reconstruction algorithm is used to process feature information in the passenger's half-body image to obtain a 3D full-body model corresponding to the passenger's half-body image. The 3D reconstruction algorithm in this embodiment is an existing 3D reconstruction algorithm technology, and this embodiment of the application does not impose any limitation on this.

[0079] In a possible embodiment, when it is determined that the similarity between the facial information of pedestrian a and the facial information of the passenger exceeds a preset threshold, and when it is determined that the similarity between the half-body image of pedestrian a and the three-dimensional full-body model of the passenger exceeds a preset threshold, the passenger is determined to be pedestrian a.

[0080] In a possible embodiment, when it is determined that there is no pedestrian whose facial information has a similarity with the passenger's facial information exceeding a preset threshold, and the similarity between the half-body image of pedestrian b and the passenger's three-dimensional full-body model exceeds a preset threshold, the passenger is determined to be pedestrian b.

[0081] In a possible embodiment, when it is determined that the similarity between the facial information of pedestrian c and the facial information of the passenger exceeds a preset threshold, and there is no similarity between any half-body image of the pedestrian and the three-dimensional full-body model of the passenger that exceeds the preset threshold, the passenger is determined to be pedestrian c.

[0082] In a possible embodiment, when it is determined that the similarity between the facial information of pedestrian d and the facial information of the passenger exceeds a preset threshold, and when it is determined that the similarity between the half-body image of pedestrian e and the three-dimensional full-body model of the passenger exceeds a preset threshold, the identity of the passenger is determined based on the facial information of the pedestrian that exceeds the preset threshold, that is, the passenger is determined to be pedestrian d.

[0083] Since it is difficult for camera equipment to collect facial information of all pedestrians in real-time environmental data, it is difficult for camera equipment to obtain facial information when pedestrians lower their heads or turn their backs to the vehicle. The present embodiment not only compares the facial information of pedestrians with the facial information of passengers to determine the identity of the passengers, but also compares the easily collected half-body image of pedestrians with the three-dimensional full-body model of the passenger. When determining the passenger based on the facial information of the pedestrians, the identity of the passenger can be further verified, or when the passenger is not found based on the facial information of the pedestrians, the identity of the passenger can be auxiliary confirmed, thereby improving the accuracy and reliability of identity confirmation before passengers get on the vehicle.

[0084] Optionally, the vehicle computer performs feature extraction on the environmental data to obtain pedestrian feature information corresponding to the environmental data, which also includes pedestrian gesture information and pedestrian voiceprint information.

[0085] Optionally, when the vehicle computer determines that the remaining distance is the second data, it determines whether the passenger identity is successfully confirmed; when the passenger identity is not successfully confirmed, it determines the similarity corresponding to the pedestrian gesture information based on the preset gesture information, and when it is determined that the similarity corresponding to the pedestrian gesture information exceeds a preset threshold, the passenger identity is determined according to the pedestrian gesture information.

[0086] Optionally, on the vehicle side, when the passenger's identity is not confirmed successfully, the similarity corresponding to the pedestrian's voiceprint information is determined based on the passenger's voiceprint information, and when it is determined that the similarity corresponding to the pedestrian's voiceprint information exceeds a preset threshold, the passenger's identity is determined based on the pedestrian's voiceprint information; wherein the passenger's voiceprint information is obtained by the taxi platform based on the passenger's registration information.

[0087] In a possible embodiment, Figure 2 As shown, based on the first data of 10 meters, the second data of 5 meters, and the third data of 3 meters, when the vehicle terminal 1 controls the vehicle to arrive at position B from position A, it determines whether the passenger's identity has been successfully confirmed. When it is determined that it has not been successfully confirmed, the real-time collected environmental data is feature extracted to obtain the gesture information of each pedestrian in the real-time environmental data, and the pedestrian gesture information is compared with the preset gesture information (such as a waving gesture) to obtain the similarity corresponding to each pedestrian gesture information. When it is determined that the similarity corresponding to the gesture information of pedestrian a exceeds the preset threshold, pedestrian a is determined to be the passenger.

[0088] In a possible embodiment, when it is determined that the successfully confirmed pedestrian a is a passenger, feature extraction is performed on the real-time collected environmental data to obtain the gesture information of each pedestrian in the real-time environmental data, and the pedestrian gesture information is compared with the preset gesture information to obtain the similarity corresponding to each pedestrian gesture information. When it is determined that the similarity corresponding to the gesture information of pedestrian a exceeds the preset threshold, it is determined that the passenger identity verification of pedestrian a is successful.

[0089] In a possible embodiment, the method for determining the identity of a passenger based on pedestrian voiceprint information is similar in implementation principle and technical effect to the method for determining the identity of a passenger based on pedestrian gesture information provided in the above method embodiment, and is not described in detail in this embodiment.

[0090] Optionally, when determining that the vehicle has arrived at position B, the passenger identity can be determined or verified based on the extracted gesture information of each pedestrian, or the extracted voiceprint information of each pedestrian can be compared with the passenger voiceprint information, and the passenger identity can be determined or verified based on the comparison result. The passenger identity can also be confirmed or verified based on both the extracted gesture information of each pedestrian and the voiceprint information of each pedestrian. This embodiment of the present application does not impose any limitations.

[0091] In this embodiment, when the remaining distance is the second data, the method of identity confirmation is changed, that is, by extracting pedestrian gesture information and / or pedestrian voiceprint information from the environmental data, so as to determine the passenger based on gesture or sound comparison when the distance to the passenger is close, thereby further verifying the identity of the passenger when the passenger has been determined, or assisting in confirming the passenger's identity when the passenger is not found, thereby improving the accuracy and reliability of passenger identity confirmation before boarding.

[0092] Optionally, the vehicle-mounted terminal is also used to generate a movement request and send it to the taxi-hailing platform when determining that the remaining distance is the third data; the taxi-hailing platform is also used to receive the movement request, determine the location indicated by the vehicle-mounted terminal according to the movement request, generate a transfer instruction according to the location and send it to the passenger's terminal device, and the transfer instruction is used to instruct the passenger to move to the location so that the vehicle-mounted terminal can confirm the identity of the passenger.

[0093] Optionally, the location indicated by the vehicle terminal includes but is not limited to the current location of the vehicle where the vehicle terminal is located and the target location input by the driver.

[0094] In a possible embodiment, Figure 2 As shown, based on the first data of 10 meters, the second data of 5 meters, and the third data of 3 meters, when the vehicle terminal 1 controls the vehicle to arrive at position C from position B, it determines whether the passenger identity has been successfully confirmed. When it is determined that it has not been successfully confirmed, a movement request is generated according to the current position of the vehicle and sent to the taxi platform. After the taxi platform receives the movement request, it generates a route for the passenger to move to the current position of the vehicle according to the current position of the vehicle and the current position of the passenger indicated by the movement request, and generates a transfer instruction according to the route and the current position of the vehicle and sends it to the passenger's terminal device, so that the passenger can travel to the current position of the vehicle according to the route indicated by the transfer instruction.

[0095] In a possible embodiment, when the passenger moves to the target location according to the transfer instruction, the vehicle terminal 1 performs feature extraction based on the real-time environmental data, and confirms the passenger based on the pedestrian feature information obtained by the feature extraction, wherein the method for confirming the passenger based on the pedestrian feature information is similar to the implementation principle and technical effect of the passenger confirmation method provided in the above-mentioned method embodiment, and this embodiment will not be repeated here.

[0096] In a possible embodiment, when the passenger moves to the current position of the vehicle according to the transfer instruction, the passenger's identity is confirmed by the passenger checking the license plate number with the driver or the driver checking the mobile phone number with the passenger.

[0097] In a possible embodiment, when determining the identity of a passenger, the passenger's current location is determined and a real-time image of the passenger is captured and displayed on the vehicle display screen, so that the driver can further verify the passenger's identity based on the displayed image and invite the passenger to board the vehicle when the verification is passed.

[0098] Optionally, feature extraction technology is used to process real-time environmental data to obtain feature information of each pedestrian in the environmental data, wherein the feature extraction technology in this embodiment is an existing feature extraction method, and the embodiment of the present invention does not limit this.

[0099] When determining that the remaining distance is the third data, this embodiment determines that the current situation is difficult to identify the user. At this time, a movement signal is sent to the passenger so that the passenger can move by himself to an area where the passenger can be identified or the current position of the vehicle, thereby facilitating the completion of the passenger's identity confirmation before boarding the vehicle, and further improving the reliability and efficiency of identity confirmation.

[0100] Figure 3 A flow chart of the taxi-hailing method provided for this application, such as Figure 3 As shown, in this embodiment Figure 2 Based on the embodiment, a taxi-hailing method is described in detail, and the method includes:

[0101] S301. The terminal device sends registration information to the taxi-hailing platform.

[0102] More specifically, the passenger sends registration information to the taxi-hailing platform through the taxi-hailing application software of the terminal device, and the registration information includes the passenger's facial information and the passenger's voiceprint information. Among them, the passenger's facial information is obtained by taking a photo of the terminal device during the user registration process, and the passenger's voiceprint information is obtained by recording the terminal device during the user registration process.

[0103] S302: The terminal device sends a taxi request to the taxi platform.

[0104] More specifically, when a user needs to take a taxi, a taxi request is sent to the taxi platform through the taxi application software of the terminal device.

[0105] S303. The taxi-hailing platform obtains the passenger's half-body image and the passenger's location based on the taxi-hailing request and generates an order.

[0106] More specifically, after receiving the taxi request sent by the terminal device, the taxi platform feeds back a collection instruction to the terminal device to obtain the passenger's half-body image and the current passenger's position collected by the terminal device, and generates a corresponding order according to the passenger's half-body image and the passenger's position.

[0107] S304: The vehicle terminal sends an order acceptance request to the taxi-hailing platform.

[0108] S305. The taxi-hailing platform sends the order and the passenger's registration information to the vehicle terminal.

[0109] More specifically, the taxi-hailing platform receives an order request, determines the order indicated by the order request, and sends the order and the registration information of the passenger who initiated the order to the vehicle terminal corresponding to the order request.

[0110] S306: The vehicle receives the order and determines the remaining distance between the vehicle and the passenger's location in real time.

[0111] More specifically, the vehicle computer receives the order, controls the driving of the vehicle according to the passenger position indicated by the order, and determines the remaining distance between the vehicle and the passenger position in real time during driving.

[0112] S307: When the vehicle computer determines that the remaining distance is the first data, the vehicle computer processes the real-time environmental data outside the vehicle to obtain characteristic information of each pedestrian.

[0113] More specifically, when the vehicle computer determines that the remaining distance is the first data, it starts the vehicle's camera equipment, captures the real-time environmental data outside the vehicle during driving through the camera equipment, and performs feature extraction on the real-time environmental data obtained each time to obtain the feature information of each pedestrian in the corresponding environmental data.

[0114] Exemplarily, by performing feature extraction on the currently obtained real-time environmental data, multiple pedestrian face information and multiple pedestrian half-body images existing in the environmental data are obtained.

[0115] S308. The vehicle computer confirms the passenger based on the pedestrian's facial information and the pedestrian's half-body image.

[0116] More specifically, the vehicle computer compares the multiple pedestrian facial information obtained in step S307 with the passenger facial information respectively to obtain the similarity of each pedestrian facial information relative to the passenger facial information. At the same time, the passenger's half-body image is reconstructed to obtain a three-dimensional full-body model corresponding to the passenger's half-body image. The multiple pedestrian half-body images obtained in step S307 are compared with the above-mentioned three-dimensional full-body model to obtain the similarity of each pedestrian half-body image relative to the three-dimensional full-body model, and each obtained similarity is compared with a preset threshold to obtain the similarity corresponding to each pedestrian facial information and the similarity corresponding to each pedestrian half-body image.

[0117] S309: When the vehicle computer determines that the remaining distance is the second data and the passenger has not been confirmed, the passenger is confirmed based on the pedestrian gesture information in the real-time environmental data.

[0118] More specifically, when the vehicle is traveling from a position where the remaining distance is the first data to a position where the remaining distance is the second data, if there is no pedestrian face information and / or pedestrian half-body image whose similarity exceeds a preset threshold value in all the real-time environmental data obtained by the vehicle computer, it is determined that the passenger identity has not been successfully confirmed when the remaining distance is the second data. At this time, the real-time environmental data of the vehicle during driving is continuously collected through the vehicle's camera equipment, and features are extracted from the obtained real-time environmental data to obtain multiple pedestrian gesture information in the real-time environmental data, and each pedestrian gesture information is compared with the preset gesture information to obtain the similarity corresponding to each pedestrian gesture information.

[0119] Optionally, continue to collect real-time environmental data during the vehicle's driving process through the vehicle's camera equipment, and perform feature extraction on the obtained real-time environmental data to obtain multiple pedestrian voiceprint information present in the real-time environmental data, and compare each pedestrian voiceprint information with the passenger voiceprint information to obtain the similarity corresponding to each pedestrian voiceprint information.

[0120] S310: When the vehicle terminal determines that the remaining distance is the third data and no passenger has been confirmed, a movement request is generated.

[0121] More specifically, when the vehicle is traveling from a position where the remaining distance is the second data to a position where the remaining distance is the third data, if there is no pedestrian gesture information and / or pedestrian voiceprint information whose similarity exceeds a preset threshold value in all the real-time environmental data obtained by the vehicle computer, it is determined that the passenger identity has not been successfully confirmed when the remaining distance is the third data. At this time, the vehicle computer determines the current position of the vehicle and generates a movement request based on the current position.

[0122] S311. The vehicle terminal sends a movement request to the taxi-hailing platform.

[0123] S312: The taxi-hailing platform generates a transfer instruction.

[0124] More specifically, the taxi-hailing platform receives a movement request, determines the current location of the vehicle based on the movement request, determines a route from the passenger's location to the current location of the vehicle, and generates a movement instruction based on the route to the current location of the vehicle.

[0125] S313. The taxi-hailing platform sends a transfer instruction to the terminal device.

[0126] S314. The terminal device instructs the passenger to move based on the transfer instruction.

[0127] More specifically, the terminal device receives the transfer instruction, obtains the route and the current position of the vehicle provided by the transfer instruction, so that the passenger goes to the current position of the vehicle.

[0128] S315. The vehicle computer confirms the passenger's identity.

[0129] More specifically, as the passenger moves to the vehicle's current location, the vehicle computer extracts features from real-time environmental data to confirm the passenger. As the passenger moves, the vehicle computer finds and confirms the passenger, and displays a real-time image of the passenger's current location on the vehicle's display screen, allowing the driver of the vehicle to verify the passenger's identity based on the real-time image.

[0130] Among them, the method of confirming passengers by extracting features from real-time environmental data on the vehicle side is similar to the implementation principle and technical effect of steps S307 to S309, and will not be repeated here in this embodiment.

[0131] The taxi-hailing method provided in the embodiment of the present application obtains the remaining distance of the vehicle from the passenger's position in real time during the process of traveling to the passenger's position. When the remaining distance reaches a first data, the passenger is confirmed based on the facial information of pedestrians in the current environment, and a three-dimensional full-body model of the passenger is generated. The passenger's identity can be confirmed based on the half-body image of each pedestrian, thereby improving the efficiency and reliability of confirming the passenger's identity before boarding. When the remaining distance is a second data and the passenger's identity has not been confirmed, the passenger is confirmed based on the gesture information or voiceprint information of each pedestrian. When it is difficult to confirm the passenger, the convenience of identity confirmation and the probability of successful confirmation can be improved by guiding the passenger to move, thereby further improving the reliability and efficiency of identity confirmation and enhancing the passenger's riding experience.

[0132] Figure 4 The structure diagram of the taxi-hailing device provided in this application Figure 1 ,like Figure 4 As shown, the taxi-hailing device 40 provided in this embodiment is applied to a taxi-hailing platform and includes:

[0133] The first receiving module 401 is used to receive a taxi request sent by a passenger's terminal device, obtain a half-body image and a position of the passenger, and generate a target order;

[0134] The first processing module 402 is used to send the target order to the vehicle computer end, so that the vehicle computer end determines the similarity corresponding to the pedestrian facial information based on the passenger facial information, and confirms the similarity corresponding to the pedestrian half-body image based on the passenger half-body image, and confirms the passenger identity based on the similarity corresponding to the pedestrian facial information and the similarity corresponding to the pedestrian half-body image; the pedestrian facial information and the pedestrian half-body image are obtained by the vehicle computer end when determining the remaining distance between the real-time position of the vehicle and the passenger position as the first data according to the target order, by collecting real-time environmental data outside the vehicle and performing feature extraction, and the passenger facial information is obtained by the taxi-hailing platform based on the passenger's registration information.

[0135] Optionally, the first receiving module 401 is also used to receive a movement request, determine the location indicated by the vehicle-side according to the movement request, generate a transfer instruction according to the location and send it to the passenger's terminal device, the transfer instruction is used to instruct the passenger to move to the location so that the vehicle-side can confirm the identity of the passenger, wherein the movement request is generated by the vehicle-side when it determines that the remaining distance is the third data.

[0136] The taxi-hailing device provided in this embodiment is applied to a taxi-hailing platform and can execute the taxi-hailing method applied to the taxi-hailing platform provided in the above method embodiment. Its implementation principle and technical effects are similar and will not be described in detail in this embodiment.

[0137] Figure 5 The structure diagram of the taxi-hailing device provided in this application Figure 2 ,like Figure 5 As shown, applied to the vehicle terminal, the taxi-hailing device 50 provided in this embodiment includes:

[0138] The second receiving module 501 is used to receive the target order sent by the taxi-hailing platform. When the remaining distance between the real-time position of the vehicle and the position of the passenger is determined as the first data according to the target order, the real-time environmental data outside the vehicle is collected and feature extracted to obtain pedestrian feature information. The pedestrian feature information includes pedestrian face information and pedestrian half-body image. The target order is generated by the taxi-hailing platform through the obtained passenger half-body image and passenger position when receiving the taxi request sent by the terminal device.

[0139] The second processing module 502 is used to determine the similarity corresponding to the pedestrian's facial information based on the passenger's facial information, and to confirm the similarity corresponding to the pedestrian's half-body image based on the passenger's half-body image, and to confirm the passenger's identity based on the similarity corresponding to the pedestrian's facial information and the similarity corresponding to the pedestrian's half-body image. The passenger's facial information is obtained by the taxi-hailing platform based on the passenger's registration information.

[0140] Optionally, the second processing module 502 is further used to determine feature information in the passenger's half-body image, and obtain a three-dimensional full-body model of the passenger by reconstructing the feature information;

[0141] Determine the similarity of the pedestrian half-body image based on the three-dimensional full-body model;

[0142] The similarity corresponding to the pedestrian's facial information and the similarity corresponding to the pedestrian's half-body image are compared with preset thresholds respectively. When at least one similarity exceeds the preset threshold, the passenger's identity is determined based on the pedestrian feature information corresponding to the similarity.

[0143] Optionally, the pedestrian feature information includes pedestrian gesture information and pedestrian voiceprint information; the second processing module 502 is further used to determine whether the passenger identity is successfully confirmed when the remaining distance is determined to be the second data;

[0144] When the passenger's identity is not confirmed successfully, the similarity corresponding to the pedestrian's gesture information is determined based on the preset gesture information, and when it is determined that the similarity corresponding to the pedestrian's gesture information exceeds a preset threshold, the passenger's identity is determined according to the pedestrian's gesture information.

[0145] Optionally, the second processing module 502 is also used to determine the similarity corresponding to the pedestrian's voiceprint information based on the passenger's voiceprint information when it is determined that the passenger's identity has not been successfully confirmed, and to determine the passenger's identity based on the pedestrian's voiceprint information when it is determined that the similarity corresponding to the pedestrian's voiceprint information exceeds a preset threshold; wherein the passenger's voiceprint information is obtained by the taxi platform based on the passenger's registration information.

[0146] Optionally, the second processing module 502 is also used to generate a movement request and send it to the taxi-hailing platform when it is determined that the remaining distance is the third data; so that the taxi-hailing platform determines the location indicated by the vehicle-mounted terminal according to the movement request, and generates a transfer instruction based on the location and sends it to the passenger's terminal device. The transfer instruction is used to instruct the passenger to move to the location so that the vehicle-mounted terminal can confirm the identity of the passenger.

[0147] The taxi-hailing device provided in this embodiment is applied to the vehicle terminal and can execute the taxi-hailing method applied to the vehicle terminal provided in the above method embodiment. Its implementation principle and technical effect are similar and will not be described in detail in this embodiment.

[0148] Figure 6 This is a schematic diagram of the structure of the electronic device provided in this application. Figure 6 As shown, the electronic device 60 provided in this embodiment includes: at least one processor 601 and a memory 602. Optionally, the device 60 also includes a communication component 603. The processor 601, the memory 602 and the communication component 603 are connected via a bus 604.

[0149] In a specific implementation process, at least one processor 601 executes the computer execution instructions stored in the memory 602, so that at least one processor 601 executes the above method.

[0150] The specific implementation process of the processor 601 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0151] In the above embodiments, it should be understood that the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the invention can be directly implemented as a hardware processor, or can be implemented by a combination of hardware and software modules in the processor.

[0152] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk storage.

[0153] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of this application is not limited to only one bus or one type of bus.

[0154] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0155] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0156] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0157] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0158] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0159] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0160] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0161] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0162] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0163] The information (including but not limited to passenger facial information, passenger voiceprint information, passenger half-body image, etc.) and data (including but not limited to data used for analysis and processing, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0164] In the technical solution of this application, the collection, storage, use, processing, transmission, provision and disclosure of passenger information or environmental data involved are in compliance with the relevant laws and regulations and do not violate public order and good morals.

[0165] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0166] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A taxi-hailing system, characterized in that: include: The taxi-hailing platform is used to send target orders to the vehicle terminal; The target order is generated by obtaining the passenger's half-body image and the passenger's position when receiving a taxi request sent by a terminal device; The vehicle computer end is used to receive the target order. When the remaining distance between the real-time position of the vehicle and the passenger position is determined as the first data according to the target order, pedestrian feature information is obtained by collecting real-time environmental data outside the vehicle and performing feature extraction. The pedestrian feature information includes pedestrian facial information and a half-body image of the pedestrian; the similarity corresponding to the pedestrian facial information is determined according to the passenger facial information, and the similarity corresponding to the pedestrian half-body image is confirmed based on the passenger half-body image, and the passenger identity is confirmed according to the similarity corresponding to the pedestrian facial information and the similarity corresponding to the pedestrian half-body image, and the passenger facial information is obtained by the taxi-hailing platform according to the registration information of the passenger.

2. The system according to claim 1, characterized in that When the vehicle terminal confirms the similarity corresponding to the pedestrian half-body image based on the passenger half-body image, and confirms the passenger identity according to the similarity corresponding to the pedestrian face information and the similarity corresponding to the pedestrian half-body image, it is specifically used to: Determine feature information in the passenger's half-body image, and obtain a three-dimensional full-body model of the passenger by reconstructing the feature information; Determining the similarity corresponding to the pedestrian half-body image based on the three-dimensional full-body model; The similarity corresponding to the pedestrian's facial information and the similarity corresponding to the pedestrian's half-body image are compared with preset thresholds respectively. When at least one similarity exceeds the preset threshold, the passenger's identity is determined based on the pedestrian feature information corresponding to the similarity.

3. The system according to claim 1 or 2, characterized in that: The pedestrian feature information includes pedestrian gesture information and pedestrian voiceprint information; The vehicle terminal is also used for: When the remaining distance is determined to be the second data, determining whether the passenger identity is successfully confirmed; When the passenger identity is not confirmed successfully, the similarity corresponding to the pedestrian gesture information is determined based on preset gesture information, and when it is determined that the similarity corresponding to the pedestrian gesture information exceeds a preset threshold, the passenger identity is determined according to the pedestrian gesture information.

4. The system according to claim 3, characterized in that The vehicle terminal is also used for: When it is determined that the passenger's identity has not been confirmed successfully, the similarity corresponding to the pedestrian's voiceprint information is determined based on the passenger's voiceprint information, and when it is determined that the similarity corresponding to the pedestrian's voiceprint information exceeds a preset threshold, the passenger's identity is determined based on the pedestrian's voiceprint information; wherein, the passenger's voiceprint information is obtained by the taxi platform based on the passenger's registration information.

5. The system according to claim 4, characterized in that The vehicle terminal is further configured to generate a movement request and send the request to the taxi-hailing platform when the remaining distance is determined to be the third data; The taxi-hailing platform is also used to receive the movement request, determine the location indicated by the vehicle terminal according to the movement request, generate a transfer instruction according to the location and send it to the passenger's terminal device, and the transfer instruction is used to instruct the passenger to move to the location so that the vehicle terminal can confirm the identity of the passenger.

6. A taxi-hailing method, characterized in that: Applied to taxi-hailing platforms, including: Receive a taxi request sent by a passenger's terminal device, obtain the passenger's half-body image and the passenger's location, and generate a target order; The target order is sent to the vehicle computer end, so that the vehicle computer end determines the similarity corresponding to the pedestrian facial information based on the passenger facial information, and confirms the similarity corresponding to the pedestrian half-body image based on the passenger half-body image, and confirms the passenger identity according to the similarity corresponding to the pedestrian facial information and the similarity corresponding to the pedestrian half-body image; the pedestrian facial information and the pedestrian half-body image are obtained by the vehicle computer end by collecting real-time environmental data outside the vehicle and performing feature extraction when the remaining distance between the real-time position of the vehicle and the passenger position is determined as the first data according to the target order, and the passenger facial information is obtained by the taxi-hailing platform according to the registration information of the passenger.

7. A taxi-hailing method, characterized in that: Applied to the vehicle side, including: receiving a target order sent by a taxi-hailing platform, and when determining the remaining distance between the real-time position of the vehicle and the position of the passenger as first data according to the target order, obtaining pedestrian feature information by collecting real-time environmental data outside the vehicle and performing feature extraction, the pedestrian feature information includes pedestrian face information and a half-body image of the pedestrian, and the target order is generated by the taxi-hailing platform when receiving a taxi request sent by a terminal device, by obtaining the half-body image of the passenger and the position of the passenger; The similarity corresponding to the pedestrian's facial information is determined based on the passenger's facial information, and the similarity corresponding to the pedestrian's half-body image is confirmed based on the passenger's half-body image. The passenger's identity is confirmed based on the similarity corresponding to the pedestrian's facial information and the similarity corresponding to the pedestrian's half-body image. The passenger's facial information is obtained by the taxi-hailing platform based on the passenger's registration information.

8. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to claim 6 or 7.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to claim 6 or 7 when executed by a processor.

10. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to claim 6 or 7 when being executed by a processor.

Images