Vehicle passenger recommendation method, network device and terminal

Abstract

The present invention provides a vehicle passenger recommendation method, network device, and terminal, relating to the field of vehicle networking technology. The method comprises: receiving current pedestrian information transmitted by a first terminal; generating a population density heat map based on the current pedestrian information; and transmitting the population density heat map to a second terminal; wherein the current pedestrian information is obtained by the first terminal after capturing a current road image. The vehicle passenger recommendation method, network device, and terminal provided by the present invention do not require analysis of large amounts of historical data, but utilize real-time population density statistics, overcoming the poor real-time performance of vehicle passenger recommendation in existing technologies.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle networking, and in particular to a vehicle passenger recommendation method, network equipment, and terminal. Background Art

[0002] Existing systems for recommending passenger routes for commercial vehicles require the acquisition of extensive historical vehicle trajectory data, followed by data cleaning and analysis. Using algorithms or rules, these systems extract information such as passenger hotspots and passenger capacity. These systems then build models to recommend routes for commercial vehicle drivers when they are not carrying passengers. However, existing systems are expensive to build, lack real-time performance, and are unable to predict unexpected passenger demand. Summary of the Invention

[0003] The embodiments of the present invention provide a vehicle passenger recommendation method, a network device, and a terminal to solve the problem of poor real-time performance of vehicle passenger recommendation in the prior art.

[0004] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0005] An embodiment of the present invention provides a vehicle passenger recommendation method, which is executed by a network device and includes:

[0006] receiving current pedestrian information transmitted by the first terminal;

[0007] generating a population density heat map based on the current pedestrian information;

[0008] Sending the population density heat map to a second terminal;

[0009] The current pedestrian information is obtained by the first terminal after collecting the current road image.

[0010] Optionally, the current pedestrian information includes pedestrian category, number of pedestrians, and pedestrian location, and generating a population density heat map based on the current pedestrian information includes:

[0011] Determining a target area where the pedestrian is located based on the pedestrian's position;

[0012] Determining a target weight for a population density heat map based on the pedestrian category and the number of pedestrians;

[0013] A population density heat map currently corresponding to the target area is generated according to the target area and the target weight.

[0014] Optionally, the current pedestrian information includes pedestrian categories and the number of pedestrians, and generating a population density heat map based on the current pedestrian information includes:

[0015] Calculate the first weight according to the number of pedestrians in different categories;

[0016] determining a target weight according to the first weight, the second weight, and the third weight;

[0017] The second weight is a weight calculated at a first moment before the current moment, and the third weight is a weight calculated at a second moment before the current moment.

[0018] Optionally, calculating the first weight according to the number of pedestrians of different pedestrian categories includes:

[0019] Obtain each weight corresponding to each pedestrian category, as well as the number of pedestrians corresponding to each pedestrian category;

[0020] The products of the weights of different pedestrian categories and the corresponding number of pedestrians are calculated and added together to obtain the first weight.

[0021] Optionally, determining the target weight according to the first weight, the second weight, and the third weight includes:

[0022] According to the formula:

[0023] weight n,d =r*weight n-1,d +p*weight n,d-1 +(1-rp)*now n,d , determine the target weight;

[0024] Among them, the weight n,d Represents the target weight; the weight n-1,d Represents the second weight; the weight n,d-1 Represents the third weight; the now n,d represents the first weight; r is the forgetting coefficient, p is the prediction coefficient, and satisfies the condition r+p<1.

[0025] Optionally, generating a population density heat map corresponding to the target area according to the target area and the target weight includes:

[0026] Dividing the map of the target area into a preset number of grids;

[0027] The average coordinate point of the pedestrians who have stayed in each grid is taken as the average coordinate point of the grid;

[0028] According to the target weight, different icons and colors are marked at the position corresponding to the average coordinate point to represent the pedestrian category and number in the pedestrian information, thereby forming a population density heat map;

[0029] The different icons are used to represent different types of pedestrians, and the different colors are used to represent different numbers of pedestrians.

[0030] Optionally, the first terminal is provided with an image acquisition component, an image processing component and a transmission component.

[0031] Optionally, the method further includes: re-receiving current pedestrian information transmitted by the first terminal at intervals of a first preset time, and updating the population density heat map based on the current pedestrian information.

[0032] An embodiment of the present invention provides a vehicle passenger recommendation method, which is executed by a second terminal and includes:

[0033] Receive population density heat maps sent by network devices;

[0034] displaying the population density heat map;

[0035] The population density heat map is generated by the network device according to current pedestrian information, and the current pedestrian information is obtained by the first terminal after collecting the current road image.

[0036] Optionally, displaying the population density heat map includes:

[0037] Determining multiple locations where pedestrians are densely populated based on the current population density heat map;

[0038] One of the location information is selected, and at least one driving route to the selected location information is generated.

[0039] An embodiment of the present invention provides a network device, including:

[0040] A first receiving module, configured to receive current pedestrian information transmitted by the first terminal;

[0041] A generation module, configured to generate a population density heat map based on the current pedestrian information;

[0042] A sending module, sending the population density heat map to a second terminal;

[0043] The current pedestrian information is obtained by the first terminal after collecting the current road image.

[0044] Furthermore, the generation module includes:

[0045] A first determining submodule is configured to determine a target area where the pedestrian is located based on the pedestrian's position;

[0046] A second determination submodule is configured to determine a target weight of a population density heat map based on the pedestrian category and the number of pedestrians;

[0047] The first generating submodule is used to generate a population density heat map currently corresponding to the target area according to the target area and the target weight.

[0048] Furthermore, the first generation submodule includes:

[0049] a first calculation unit, configured to calculate a first weight according to the number of pedestrians of different pedestrian categories;

[0050] a second calculation unit, configured to determine a target weight according to the first weight, the second weight, and the third weight;

[0051] The second weight is a weight calculated at a first moment before the current moment, and the third weight is a weight calculated at a second moment before the current moment.

[0052] Furthermore, the first computing unit includes:

[0053] A first acquisition subunit is used to obtain each weight corresponding to each pedestrian category and the number of pedestrians corresponding to each pedestrian category;

[0054] The first obtaining subunit is used to calculate the product of the weights of different pedestrian categories and the corresponding number of pedestrians, and add them up to obtain the first weight.

[0055] Furthermore, the second computing unit includes:

[0056] Second, get the subunits according to the formula:

[0057] weight n,d =r*weight n-1,d +p*weight n,d-1 +(1-rp)*now n,d , determine the target weight;

[0058] Among them, the weight n,d Represents the target weight; the weight n-1,d Represents the second weight; the weight n,d-1 Represents the third weight; the now n,d represents the first weight; r is the forgetting coefficient, p is the prediction coefficient, and satisfies the condition r+p<1.

[0059] Furthermore, the first generation submodule further includes:

[0060] a division unit, configured to divide the map of the target area into a preset number of grids;

[0061] The average coordinate point of the pedestrians who have stayed in each grid is taken as the average coordinate point of the grid;

[0062] a forming unit, configured to mark, according to the target weight, a position corresponding to the average coordinate point using different icons and different colors to represent the type and number of pedestrians in the pedestrian information, thereby forming a population density heat map;

[0063] The different icons are used to represent different types of pedestrians, and the different colors are used to represent different numbers of pedestrians.

[0064] It should be noted that the first terminal is provided with an image acquisition component, an image processing component and a transmission component.

[0065] Furthermore, the network device further includes:

[0066] The updating module is configured to re-receive the current pedestrian information transmitted by the first terminal at intervals of a first preset time, and update the population density heat map according to the current pedestrian information.

[0067] An embodiment of the present invention provides a terminal, including:

[0068] A second receiving module is used to receive a population density heat map sent by a network device;

[0069] A display module, configured to display the population density heat map;

[0070] The population density heat map is generated by the network device according to current pedestrian information, and the current pedestrian information is obtained by the first terminal after collecting the current road image.

[0071] Furthermore, the display module includes:

[0072] A first determining unit is configured to determine a plurality of locations where pedestrians are densely populated based on the current population density heat map;

[0073] The first generating unit is configured to select one of the position information and generate at least one driving route to the selected position information.

[0074] The beneficial effects of the present invention are:

[0075] In an embodiment of the present invention, current pedestrian information transmitted by a first terminal is received; a population density heat map is generated based on the current pedestrian information; and the population density heat map is transmitted to a second terminal; wherein the current pedestrian information is obtained by the first terminal after the first terminal captures the current road image. Thus, compared to existing technologies, the current pedestrian information received by the present invention is collected in real time, which has the advantages of high real-time performance, easy identification of passenger sources, and no reliance on previously collected trajectory data. Furthermore, the population density heat map generated based on the current pedestrian information can respond to sudden passenger flow demands and has high real-time performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] Figure 1 A schematic diagram showing the structure of a vehicle passenger recommendation system provided by an embodiment of the present invention;

[0077] Figure 2 A schematic diagram showing a flow chart of a vehicle passenger recommendation method provided by an embodiment of the present invention;

[0078] Figure 3 A schematic diagram showing a flow chart of another vehicle passenger recommendation method provided by an embodiment of the present invention;

[0079] Figure 4 A schematic diagram showing a module of a network device provided by an embodiment of the present invention;

[0080] Figure 5 A schematic diagram showing modules of a terminal provided by an embodiment of the present invention; DETAILED DESCRIPTION

[0081] To make the technical problems, technical solutions, and advantages to be solved by the present invention more apparent, a detailed description will be given below with reference to the accompanying drawings and specific embodiments. In the following description, specific details such as specific configurations and components are provided solely to facilitate a comprehensive understanding of the embodiments of the present invention. Therefore, it should be clear to those skilled in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. In addition, for the sake of clarity and brevity, descriptions of known functions and configurations have been omitted.

[0082] It should be understood that the term "comprise" and any variations thereof in the specification and claims of this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatus.

[0083] In the embodiments of the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present invention should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0084] The following describes embodiments of the present invention in conjunction with the accompanying drawings. The network device information receiving method, sending method, terminal, and network device provided in the embodiments of the present invention can be applied to a wireless communication system. The wireless communication system can be a New Radio (NR) system, an evolved Long Term Evolution (eLTE) system, a Long Term Evolution (LTE) system, or a subsequent evolution communication system.

[0085] Aiming at the problem of poor real-time performance of vehicle passenger recommendation in the prior art, the present invention provides a vehicle passenger recommendation method, network equipment and terminal.

[0086] like Figure 1 As shown, Figure 1 is a structural diagram of a vehicle passenger recommendation system provided by an embodiment of the present invention; Figure 1As shown, it includes a first terminal 10, a network device 20, and a second terminal 30. The first terminal includes a video acquisition module 11 and a video processing module 12. The first terminal 10 is applied to a passenger vehicle. The video acquisition module 11 and the video processing module 12 acquire the current road image in real time and send it to the network device 20. The second terminal 30 can be a user equipment (UE) or other terminal-side device, such as a mobile phone, a tablet computer (Tablet Personal Computer), a laptop computer (Laptop Computer), a personal digital assistant (PDA), a mobile Internet device (MID), a wearable device (Wearable Device) or a robot. It should be noted that the specific type of terminal 11 is not limited in the embodiment of the present invention. Here, the second terminal is preferably a user terminal applied to a vehicle. The above-mentioned network device 20 can be a server applied to a 4G base station or a server applied to a 5G base station. The network device has functions such as processing, analysis, receiving and sending. As long as the same technical effect is achieved, the network device is not limited to a specific technical vocabulary. It should be noted that in the embodiments of the present invention, only 5G base stations are taken as an example, but the specific type of network equipment is not limited.

[0087] like Figure 2 As shown, Figure 2 FIG. 1 is a flow chart of a vehicle passenger recommendation method provided by an embodiment of the present invention, which is executed by a network device. The method includes:

[0088] Step 100: Receive current pedestrian information transmitted by a first terminal; wherein the current pedestrian information is obtained by the first terminal after collecting a current road image.

[0089] In this embodiment, the first terminal includes a video acquisition module and a video processing module to collect road videos of the vehicle during driving. In this step, the network device can receive the current pedestrian information for subsequent method processing.

[0090] Step 200: Generate a population density heat map based on the current pedestrian information.

[0091] Here, the network device processes the current pedestrian information based on the information received in step 100. Since the current pedestrian information is collected in real time, the network device can update the generated population density heat map in real time, thereby improving the real-time performance of the data of the network device.

[0092] Step 300: Send the population density heat map to the second terminal.

[0093] In this step, the network device may send the population density heat map generated in step 200 to the second terminal. In this way, the second terminal may understand the current road conditions based on the population density heat map.

[0094] Thus, the method of an embodiment of the present invention is executed by a network device, which receives current pedestrian information transmitted by a first terminal; generates a population density heat map based on the current pedestrian information; and transmits the population density heat map to a second terminal; wherein the current pedestrian information is obtained by the first terminal after capturing the current road image. In this way, because the received current pedestrian information is collected in real time, it has the advantages of high real-time performance, easy identification of passenger sources, and no reliance on previously collected trajectory data. Furthermore, the population density heat map generated based on the current pedestrian information can respond to sudden passenger flow demands and has high real-time performance.

[0095] It should be noted that in this embodiment, the first terminal collects the current pedestrian information through an object recognition and classification algorithm, wherein the object recognition algorithm can be a YOLOv4 algorithm or a YOLOv5 algorithm, etc. After the first terminal completes the recognition, it transmits the current pedestrian information together with the positioning information of the navigation and positioning system (GPS) to the network device. In this embodiment, the network device can receive the current pedestrian information, which can be data information processed by the network device, or can be understood as indication information. After receiving the current pedestrian information, the network device can perform subsequent method processing.

[0096] It should be noted that before step 100, the above-mentioned first terminal has been installed on the vehicle transmitting information. The first terminal does not need to be replaced or improved on the vehicle with existing technology, and can be directly installed on the existing ordinary vehicle. In this way, the network device can receive the road video collected by the ordinary vehicle during driving for analysis; preferably, the video acquisition module of the first terminal is installed on the ordinary car, and the video acquisition module includes but is not limited to: a driving recorder, a vehicle rearview mirror, etc., and the video processing module of the first terminal is installed on the ordinary car, and the video processing module has a processing module of the object recognition algorithm.

[0097] In this embodiment, the network device can optimize the current population heat density map according to the current pedestrian information, thereby achieving better interactive operation. In addition, different methods can be used to generate the population density heat map according to the current pedestrian information.

[0098] In this embodiment, the second terminal can understand the current road conditions based on the population density heat map. Of course, if the vehicle user requests to plan a route, the network device can plan multiple paths to the destination based on the population density heat map, including but not limited to the shortest time path, the shortest distance path, etc., and send the generated multiple paths to the second terminal.

[0099] Of course, in the embodiment of the present invention, it is not limited to sending the indication information through the request message. For example, the network device may actively send the indication information.

[0100] As an optional implementation, the network device generates a population density heat map with different weights based on the received current pedestrian information. The current pedestrian information includes pedestrian categories and pedestrian numbers. Step 200 includes:

[0101] Step 210, calculating a first weight based on the number of pedestrians of different pedestrian categories;

[0102] In this embodiment, the pedestrian categories of the current pedestrian information include: children, adults and the elderly. Of course, pedestrian categories can also be divided according to gender and age groups, such as women aged 20-30 and men aged 40-50, etc. Here, children, adults and the elderly are used as examples to divide the weights, and the first weight is calculated according to the number of pedestrians in different pedestrian categories; the first weight can accurately represent the different numbers represented by different pedestrian categories, and the accuracy of passenger carrying can be achieved by adjusting the first weight.

[0103] Step 220, determining a target weight based on the first weight, the second weight, and the third weight; wherein the second weight is the weight calculated at the first moment before the current moment, and the third weight is the weight calculated at the second moment before the current moment.

[0104] In this embodiment, the second weight is the weight calculated at the first moment before the current moment, the first moment is a preset moment before the current moment, and the second weight can represent the population density at the first moment; for example: the weight of the current moment is 18:00 on day A, the second weight is the weight of (18-first moment) on day A, the first moment can be designed according to actual needs, and is not limited here; the third weight is the weight calculated at the second moment before the current moment, the second moment is the weight of the current moment of the previous day, for example: the weight of the current moment is 18:00 on day A, the third weight is the weight of 18:00 on day B(A-1), the second moment can be designed according to actual needs. According to the first weight, the second weight and the third weight, the target weight is determined, and the current population density heat map can be accurately updated according to the needs of vehicle users. The present invention can display different population density heat maps according to the target weight, thereby improving the accuracy of passenger demand. For example, a vehicle user plans to pick up passengers at a kindergarten after school and can set different first and second times. The network device can then generate a corresponding population density heat map. By viewing the population density heat map, the user's passenger carrying needs can be met.

[0105] Specifically, step 210 includes:

[0106] Obtain each weight corresponding to each pedestrian category, as well as the number of pedestrians corresponding to each pedestrian category;

[0107] The products of the weights of different pedestrian categories and the corresponding number of pedestrians are calculated and added together to obtain the first weight.

[0108] In this embodiment, each pedestrian category is obtained. Here, the pedestrian categories are divided into children, elderly and adults as an example. The weight of children is defined as c1, the weight of elderly is defined as c2, and the weight of adults is defined as c3. Define the first weight now of the current collection n,d The following formula:

[0109] now n,d =(c1*n1+c2*n2+c3*n3);

[0110] Among them, now n,d represents the first weight, n1 represents the number of children counted in the video image, n2 represents the number of elderly people counted in the video image, and n3 represents the number of adults counted in the video image. By calculating the first weight c1, the number of pedestrians corresponding to the current pedestrian category can be clearly determined, providing an intuitive sense of the current population density on the road and providing guidance for vehicle users on passenger loading.

[0111] Specifically, step 220 includes:

[0112] According to the formula:

[0113] weight n,d =r*weight n-1,d +p*weight n,d-1 +(1-rp)*now n,d , determine the target weight;

[0114] Among them, the weight n,d Represents the target weight; the weight n-1,d Represents the second weight; the weight n,d-1 Represents the third weight; the now n,d represents the first weight; r is the forgetting coefficient, p is the prediction coefficient, and satisfies the condition r+p<1.

[0115] It should be noted that when r is the largest and p=0, that is, the prediction coefficient is 0, which means that the current target weight no longer depends on the data of the third weight. The third weight is the weight calculated at the second moment before the current moment, and the second moment is the weight of the current moment of the previous day. For example: the weight of the current moment is 18:00 on day A, and the third weight is the weight of the current moment on day B(A-1).

[0116] It should also be noted that when p is the largest and r=0, that is, the forgetting coefficient is 0, which means that the current target weight no longer depends on the data of the second weight. The second weight is the weight calculated at the first moment before the current moment. The first moment is a preset moment before the current moment. The second weight can represent the population density at the first moment; for example: the weight at the current moment is 18:00 on day A, and the second weight is the weight of (18-first moment) on day A. The first moment can be designed according to actual needs and is not limited here.

[0117] It should also be noted that when p is the largest and r=0, it means that the current target weight only depends on the currently collected road information, that is, the current pedestrian information collected in real time.

[0118] As an optional implementation manner, the current pedestrian information includes pedestrian category, number of pedestrians, and pedestrian location. Step 200 includes:

[0119] Step 230: determining a target area where the pedestrian is located based on the pedestrian's position;

[0120] In this embodiment, when the current pedestrian information received by the network device includes the pedestrian's location, the behavior location is combined with pre-stored map information to determine the target area where the current pedestrian is located. For example, if the current pedestrian location is Square A, the network device retrieves the map of Square A and determines the target area where the current pedestrian is located based on a preset scale.

[0121] Step 240 , determining a target weight of a population density heat map based on the pedestrian category and the number of pedestrians;

[0122] In this embodiment, target weights corresponding to different pedestrian categories are determined according to the pedestrian categories and the number of pedestrians. The numbers and types of pedestrians of different densities are reflected according to the size of the target weights.

[0123] Step 250: Generate a population density heat map corresponding to the target area according to the target area and the target weight.

[0124] In this embodiment, pedestrians on the population density heat map can be framed, and coordinate points can be marked on the corresponding map according to the target weight. Different coordinate marks can be used to reflect the population density heat map corresponding to different types of pedestrians and different numbers of pedestrians, making the data display more intuitive.

[0125] Specifically, step 250 includes:

[0126] Dividing the map of the target area into a preset number of grids;

[0127] In this embodiment, the length and width of the unified map of the target area can be divided equally. For example, the length and width can be divided into ten equal parts, and the data intervals obtained are 0.1, that is, 0 to 0.1, 0.1 to 0.2, 0.2 to 0.3, 0.3 to 0.4, 0.4 to 0.5, 0.5 to 0.6, 0.6 to 0.7, 0.7 to 0.8, 0.8 to 0.9, and 0.9 to 1.0. Therefore, the coordinate value (0.45, 0.44) falls within the data interval of 0.4 to 0.5 for the length and 0.4 to 0.5 for the width. The dividing lines that divide the unified length and width equally can form a grid.

[0128] The average coordinate point of the pedestrians who have stayed in each grid is taken as the average coordinate point of the grid;

[0129] In this embodiment, the coordinate points of the people who have stayed in each grid are averaged as the average coordinate point of the grid. For example, for grid A, if 5 people have stayed in the first preset time period, the coordinate points (horizontal coordinate values and vertical coordinate values) of the 5 people can be obtained, and then the average of the horizontal coordinate values and the average of the vertical coordinate values are taken respectively, and the obtained average horizontal coordinate value and average vertical coordinate value are used as the average coordinate point.

[0130] According to the target weight, different icons and different colors are marked at the position corresponding to the average coordinate point to represent the pedestrian category and number of pedestrians in the pedestrian information, thereby forming a population density heat map; wherein, the different icons are used to represent different pedestrian categories, and different colors are used to represent different numbers of pedestrians.

[0131] In this embodiment, different weights are represented by different colors according to the determined target weights, that is, the darker the color, the greater the pedestrian density in the area, and the lighter the color, the smaller the pedestrian density in the area, so that the number of pedestrians on the current map can be intuitively understood; different pedestrian categories are represented by different icons.

[0132] As an optional implementation, the first terminal is provided with an image acquisition component, an image processing component and a transmission component.

[0133] Specifically, if Figure 1 As shown, the image acquisition component of the first terminal 10 of the present invention is a video acquisition module 11, and the image processing component is a video processing module 12 with an object recognition and classification algorithm. The first terminal also has a transmission component, and the transmission component can transmit information according to the requirements of the network device. The content of the transmitted information includes but is not limited to: current pedestrian information, vehicle location information, vehicle version information, etc.

[0134] As an optional implementation, the method further includes: re-receiving current pedestrian information transmitted by the first terminal at intervals of a first preset time, and updating the population density heat map based on the current pedestrian information.

[0135] In this embodiment, the first preset time is a time set according to the update requirements. If the current population density heat map needs to be updated every ten minutes, the first preset time is set to 10 minutes. For example, the network device receives the current pedestrian information again every 10 minutes, and redraws the population density heat map based on the current pedestrian information. The drawn population density heat map is updated to the previous population density heat map. Because the position, number and type of pedestrians will change during actual use, the data is updated in real time at intervals of the first preset time, which overcomes the problem of poor real-time performance of the population density heat map in the existing technology.

[0136] In summary, since different types of people may have different needs for riding in a vehicle and occupy different seats in a vehicle, the present invention draws a population density heat map, gives different weight values to different types of people, and updates the drawn population density heat map in real time, which is more instructive for vehicle users to carry passengers.

[0137] like Figure 3 As shown, Figure 3 FIG. 1 is a flow chart of another vehicle passenger recommendation method provided by an embodiment of the present invention, which is executed by a second terminal. The method includes:

[0138] Step S100, receiving a population density heat map sent by a network device;

[0139] Step S200, displaying the population density heat map;

[0140] The population density heat map is generated by the network device according to current pedestrian information, and the current pedestrian information is obtained by the first terminal after collecting the current road image.

[0141] It should be noted that the second terminal 30 can be a user terminal (User Equipment, UE) or other terminal-side devices, such as: a mobile phone, a tablet personal computer (Tablet Personal Computer), a laptop computer (Laptop Computer), a personal digital assistant (PDA), a mobile Internet device (Mobile Internet Device, MID), a wearable device (Wearable Device) or a robot and other terminal-side devices. It should be noted that in the embodiment of the present invention, the specific type of the terminal 11 is not limited. Here, the second terminal is preferably a user terminal used in a vehicle.

[0142] In this embodiment, the second terminal receives a population density heat map transmitted by the network device and displays the population density heat map, enabling intuitive observation of pedestrian conditions on the road. The population density heat map may include pedestrian information, and the second terminal may also select pedestrian information from different time periods and different maps. The present invention provides a real-time updated population density heat map, avoiding the problem of being unable to update in real time due to unexpected situations at the destination on the road.

[0143] As an optional implementation, step S200 includes:

[0144] Determining multiple locations where pedestrians are densely populated based on the current population density heat map;

[0145] One of the location information is selected, and at least one driving route to the selected location information is generated.

[0146] In this embodiment, by selecting one of the locations, the second terminal sends departure information to the network device, and the network device sends at least one driving route to the selected location information to the second terminal based on the received departure information. The multiple locations with dense pedestrian traffic can be determined by a navigation system, a positioning system, such as a GPS positioning system or a Beidou positioning system, or a combination thereof. The selection of one of the locations can be manually input by the vehicle owner or selected through voice recognition. Of course, the driving route is updated in real time as the vehicle owner travels to the selected location.

[0147] In summary, the vehicle passenger recommendation method provided by the present invention avoids the problem of poor real-time performance of the existing technology by generating a population density heat map through network equipment. The second terminal will also automatically generate and update the driving route to the destination, which is of guiding significance for vehicle passenger carrying.

[0148] like Figure 4 As shown, Figure 4 A network device provided by an embodiment of the present invention includes:

[0149] A first receiving module 10 is configured to receive current pedestrian information transmitted by a first terminal;

[0150] A generating module 20 is configured to generate a population density heat map based on the current pedestrian information;

[0151] A sending module 30 sends the population density heat map to a second terminal;

[0152] The current pedestrian information is obtained by the first terminal after collecting the current road image.

[0153] Furthermore, the generating module 20 includes:

[0154] A first determining submodule is configured to determine a target area where the pedestrian is located based on the pedestrian's position;

[0155] A second determination submodule is configured to determine a target weight of a population density heat map based on the pedestrian category and the number of pedestrians;

[0156] The first generating submodule is used to generate a population density heat map currently corresponding to the target area according to the target area and the target weight.

[0157] Furthermore, the first generation submodule includes:

[0158] a first calculation unit, configured to calculate a first weight according to the number of pedestrians of different pedestrian categories;

[0159] a second calculation unit, configured to determine a target weight according to the first weight, the second weight, and the third weight;

[0160] The second weight is a weight calculated at a first moment before the current moment, and the third weight is a weight calculated at a second moment before the current moment.

[0161] Furthermore, the first computing unit includes:

[0162] A first acquisition subunit is used to obtain each weight corresponding to each pedestrian category and the number of pedestrians corresponding to each pedestrian category;

[0163] The first obtaining subunit is used to calculate the product of the weights of different pedestrian categories and the corresponding number of pedestrians, and add them up to obtain the first weight.

[0164] Furthermore, the second computing unit includes:

[0165] Second, get the subunits according to the formula:

[0166] weight n,d =r*weight n-1,d +p*weight n,d-1 +(1-rp)*now n,d , determine the target weight;

[0167] Among them, the weight n,d Represents the target weight; the weight n-1,d Represents the second weight; the weight n,d-1 Represents the third weight; the now n,d represents the first weight; r is the forgetting coefficient, p is the prediction coefficient, and satisfies the condition r+p<1.

[0168] Furthermore, the first generation submodule further includes:

[0169] a division unit, configured to divide the map of the target area into a preset number of grids;

[0170] The average coordinate point of the pedestrians who have stayed in each grid is taken as the average coordinate point of the grid;

[0171] a forming unit, configured to mark, according to the target weight, a position corresponding to the average coordinate point using different icons and different colors to represent the type and number of pedestrians in the pedestrian information, thereby forming a population density heat map;

[0172] The different icons are used to represent different types of pedestrians, and the different colors are used to represent different numbers of pedestrians.

[0173] It should be noted that the first terminal is provided with an image acquisition component, an image processing component and a transmission component.

[0174] Furthermore, the network device further includes:

[0175] The updating module is configured to re-receive the current pedestrian information transmitted by the first terminal at intervals of a first preset time, and update the population density heat map according to the current pedestrian information.

[0176] like Figure 5 As shown, Figure 5 A terminal provided by an embodiment of the present invention includes:

[0177] The second receiving module 40 is used to receive the population density heat map sent by the network device;

[0178] A display module 50 is used to display the population density heat map;

[0179] The population density heat map is generated by the network device according to current pedestrian information, and the current pedestrian information is obtained by the first terminal after collecting the current road image.

[0180] Furthermore, the display module 50 includes:

[0181] A first determining unit is configured to determine a plurality of locations where pedestrians are densely populated based on the current population density heat map;

[0182] The first generating unit is configured to select one of the position information and generate at least one driving route to the selected position information.

[0183] In summary, the vehicle passenger recommendation method, network equipment and terminal provided by the present invention generate population density heat map data and share it with operating vehicle drivers in real time. It has the advantage of high real-time performance and does not require vehicle trajectory analysis or special roadside equipment to dynamically collect population density in real time and recommend passenger hotspots. The present invention can not only obtain the number of pedestrians, but also the category of pedestrians (adults, children, and the elderly), which can improve the accuracy of passenger recommendations.

[0184] In embodiments of the present invention, modules can be implemented in software so that they can be executed by various types of processors. For example, an identified executable code module can include one or more physical or logical blocks of computer instructions, for example, which can be constructed as objects, procedures, or functions. Nevertheless, the executable code of the identified module does not need to be physically located together, but can include different instructions stored in different locations, which, when logically combined together, constitute the module and achieve the specified purpose of the module.

[0185] In fact, executable code module can be a single instruction or many instructions, and can even be distributed on a plurality of different code segments, distributed in the middle of different programs, and distributed across a plurality of memory devices.Similarly, operating data can be identified in the module, and can be implemented and organized in the data structure of any appropriate type according to any appropriate form.Described operating data can be collected as a single data set, or can be distributed in different locations (including on different storage devices), and can only be present on a system or network as an electronic signal at least in part.

[0186] When a module can be implemented using software, given the current state of hardware technology, those skilled in the art can build corresponding hardware circuits to implement the corresponding functions of the module, regardless of cost. The hardware circuits may include conventional very large scale integration (VLSI) circuits or gate arrays, as well as existing semiconductors such as logic chips and transistors, or other discrete components. Modules may also be implemented using programmable hardware devices, such as field programmable gate arrays, programmable array logic, or programmable logic devices.

[0187] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary personnel in this technical field, several improvements and modifications can be made without departing from the principles described in the present invention. These improvements and modifications are also within the scope of protection of the present invention.

Claims

1. A vehicle passenger recommendation method, characterized in that: Performed by network devices, including: receiving current pedestrian information transmitted by the first terminal; Generating a population density heat map based on the current pedestrian information; the current pedestrian information includes pedestrian category, pedestrian number, and pedestrian location; generating a population density heat map based on the current pedestrian information includes: determining a target area where the pedestrian is located based on the pedestrian location; determining a target weight for the population density heat map based on the pedestrian category and pedestrian number; and generating a current population density heat map corresponding to the target area based on the target area and the target weight; Sending the population density heat map to a second terminal; The current pedestrian information is obtained by the first terminal after collecting the current road image; The current pedestrian information includes pedestrian categories and pedestrian numbers, and generating a population density heat map based on the current pedestrian information includes: Calculating a first weight based on the number of pedestrians in different pedestrian categories, including: obtaining each weight corresponding to each pedestrian category and the number of pedestrians corresponding to each pedestrian category; calculating the product of the weights of different pedestrian categories and the corresponding number of pedestrians, and adding the products to obtain the first weight; Determining a target weight according to the first weight, the second weight, and the third weight includes: According to the formula: weight n,d =r*weight n-1,d +p*weight n,d-1 +(1-rp)*now n,d , determine the target weight; Among them, the weight n,d Represents the target weight; the weight n-1,d Represents the second weight; the weight n,d-1 Represents the third weight; the now n,d represents the first weight; r is the forgetting coefficient, p is the prediction coefficient, and the condition r+p<1 is satisfied; The second weight is a weight calculated at a first moment before the current moment, and the third weight is a weight calculated at a second moment before the current moment.

2. The vehicle passenger recommendation method according to claim 1, characterized in that: Generating a population density heat map corresponding to the target area according to the target area and the target weight includes: Dividing the map of the target area into a preset number of grids; The average coordinate point of the pedestrians who have stayed in each grid is taken as the average coordinate point of the grid; According to the target weight, different icons and colors are marked at the position corresponding to the average coordinate point to represent the pedestrian category and number in the pedestrian information, thereby forming a population density heat map; The different icons are used to represent different types of pedestrians, and the different colors are used to represent different numbers of pedestrians.

3. The vehicle passenger recommendation method according to claim 1, characterized in that: The first terminal is provided with an image acquisition component, an image processing component and a transmission component.

4. The vehicle passenger recommendation method according to claim 1, characterized in that: The method further includes: re-receiving current pedestrian information transmitted by the first terminal at intervals of a first preset time, and updating the population density heat map according to the current pedestrian information.

5. A vehicle passenger recommendation method, characterized in that: Executed by the second terminal, including: Receive population density heat maps sent by network devices; displaying the population density heat map; The population density heat map is generated by the network device based on current pedestrian information, which is obtained by the first terminal after collecting the current road image; the current pedestrian information includes pedestrian categories and the number of pedestrians. The network device generates a population density heat map based on the current pedestrian information, including: Calculating a first weight based on the number of pedestrians in different pedestrian categories, including: obtaining each weight corresponding to each pedestrian category and the number of pedestrians corresponding to each pedestrian category; calculating the product of the weights of different pedestrian categories and the corresponding number of pedestrians, and adding the products to obtain the first weight; Determining a target weight according to the first weight, the second weight, and the third weight includes: According to the formula: weight n,d =r*weight n-1,d +p*weight n,d-1 +(1-rp)*now n,d , determine the target weight; Among them, the weight n,d Represents the target weight; the weight n-1,d Represents the second weight; the weight n,d-1 Represents the third weight; the now n,d represents the first weight; r is the forgetting coefficient, p is the prediction coefficient, and the condition r+p<1 is satisfied; The second weight is a weight calculated at a first moment before the current moment, and the third weight is a weight calculated at a second moment before the current moment.

6. The vehicle passenger recommendation method according to claim 5, characterized in that: The displaying of the population density heat map includes: Determining multiple locations where pedestrians are densely populated based on the current population density heat map; One of the location information is selected, and at least one driving route to the selected location information is generated.

7. A network device, characterized in that: include: A first receiving module, configured to receive current pedestrian information transmitted by the first terminal; A generation module, configured to generate a population density heat map based on the current pedestrian information; The generation module includes: a first determination submodule for determining a target area where the pedestrian is located based on the pedestrian's position; a second determination submodule for determining a target weight of a population density heat map based on the pedestrian category and the number of pedestrians; and a first generation submodule for generating a population density heat map currently corresponding to the target area based on the target area and the target weight. A sending module, sending the population density heat map to a second terminal; The current pedestrian information is obtained by the first terminal after collecting the current road image; The first generation submodule includes: a first calculation unit for calculating a first weight based on the number of pedestrians of different categories; a second calculation unit for determining a target weight based on the first weight, the second weight, and the third weight; wherein the second weight is a weight calculated at a first moment before the current moment, and the third weight is a weight calculated at a second moment before the current moment; The first calculation unit includes: a first acquisition subunit, configured to acquire each weight corresponding to each pedestrian category and the number of pedestrians corresponding to each pedestrian category; a first obtaining subunit, configured to calculate the product of the weights of different pedestrian categories and the corresponding number of pedestrians, and add them to obtain the first weight; The second calculating unit includes: a second obtaining subunit, configured to calculate the value of the second calculating unit according to the formula: weight n,d =r*weight n-1,d +p*weight n,d-1 +(1-rp)*now n,d , determine the target weight; Among them, the weight n,d Represents the target weight; the weight n-1,d Represents the second weight; the weight n,d-1 Represents the third weight; the now n,d represents the first weight; r is the forgetting coefficient, p is the prediction coefficient, and satisfies the condition r+p<1.

8. A terminal, characterized in that: include: A second receiving module is used to receive a population density heat map sent by a network device; A display module, configured to display the population density heat map; The population density heat map is generated by the network device based on current pedestrian information, and the current pedestrian information is obtained by the first terminal after collecting the current road image; The current pedestrian information includes pedestrian categories and pedestrian numbers, and the network device generates a population density heat map based on the current pedestrian information, including: Calculating a first weight based on the number of pedestrians in different pedestrian categories, including: obtaining each weight corresponding to each pedestrian category and the number of pedestrians corresponding to each pedestrian category; calculating the product of the weights of different pedestrian categories and the corresponding number of pedestrians, and adding the products to obtain the first weight; Determining a target weight according to the first weight, the second weight, and the third weight includes: According to the formula: weight n,d =r*weight n-1,d +p*weight n,d-1 +(1-rp)*now n,d , determine the target weight; Among them, the weight n,d Represents the target weight; the weight n-1,d Represents the second weight; the weight n,d-1 Represents the third weight; the now n,d represents the first weight; r is the forgetting coefficient, p is the prediction coefficient, and the condition r+p<1 is satisfied; The second weight is a weight calculated at a first moment before the current moment, and the third weight is a weight calculated at a second moment before the current moment.

Images