An AR car show display method and device, a storage medium and an electronic device

Abstract

The application relates to an AR car show display method and device, a storage medium and an electronic equipment, and relates to the technical field of car show display. The method comprises the following steps: obtaining a target portrait of a target visitor and a vehicle to be visited; determining a first display angle of the vehicle to be visited based on the target portrait, a key vehicle part of an exhibited vehicle in an online car show which is easy to be visited, and at least one key visitor portrait corresponding to the key vehicle part; the key visitor portrait is a portrait of a visitor who is easy to visit the corresponding key vehicle part; displaying the vehicle to be visited in a terminal of the target visitor through a preset AR framework according to the first display angle; when the target visitor does not select a vehicle to be visited, determining at least one vehicle of interest of the target visitor, and displaying the vehicle of interest in the terminal based on the vehicle of interest. The application has the effect of improving the visiting experience of visitors.

Description

Technical Field

[0001] This application relates to the field of auto show display technology, specifically to an AR auto show display method, device, storage medium, and electronic device. Background Technology

[0002] With the development of Augmented Reality (AR) technology, more and more industries are beginning to utilize AR to provide a more intuitive and realistic user experience. This is especially true in the automotive industry, where traditional offline auto shows are gradually shifting to online AR auto shows, allowing potential buyers worldwide to easily visit the latest car exhibitions. AR auto shows are a new exhibition format that brings the traditional auto show experience online. It breaks through the limitations of time and space, allowing visitors to "immerse" themselves in the auto show anytime, anywhere through their devices, enjoying an immersive experience of viewing, selecting, and purchasing cars. AR auto shows primarily use 3D models to highly recreate cars, presenting them to visitors. Through their devices, visitors can view the exterior and interior of the vehicles in 3D and even engage in simulated interactions with them.

[0003] Currently, AR auto show displays typically employ a universal display model for each type of attendee. However, since different attendees have varying focuses and personalized viewing needs, this universal model sometimes fails to showcase vehicles or parts that interest them, resulting in a poor overall viewing experience. Summary of the Invention

[0004] To improve the viewing experience for visitors, this application provides an AR auto show display method, device, storage medium, and electronic device.

[0005] The first aspect of this application provides an AR auto show display method, specifically including:

[0006] Obtain the target profile and the vehicles to be visited for the target visitors, wherein the vehicles to be visited are the exhibited vehicles selected by the target visitors to visit in the online auto show;

[0007] Based on the target profile, the key vehicle parts of the exhibited vehicles in the online auto show that are easy to visit, and the corresponding profile of at least one key visitor, the first display perspective of the vehicle to be visited is determined, and the profile of the key visitor is the profile of the visitor who is easy to visit the corresponding key vehicle parts.

[0008] Based on the first display perspective, the vehicle to be visited is displayed in the terminal of the target visitor through a preset AR frame;

[0009] If the vehicle selected by the target visitor is not obtained, at least one vehicle of interest to the target visitor is determined, and the vehicle is displayed on the terminal based on the vehicle of interest.

[0010] By employing the aforementioned technical solution, after obtaining the target profile and the vehicles to be visited, and combining key vehicle parts with corresponding profiles of key visitors, the system analyzes and determines the parts of the vehicles that the target visitors are most likely to be interested in. This allows for the determination of a primary display perspective that best matches the visitors' viewing needs. The vehicles are then displayed using AR technology from this primary perspective, effectively meeting the personalized viewing requirements of the target visitors and improving their overall experience. Furthermore, if no vehicles selected by the target visitors are found, it indicates that they are unsure which vehicles they are interested in. In this case, it is necessary to specifically identify the vehicles that interest the target visitors. Finally, based on these vehicles, the vehicles are displayed on the terminal, further enhancing the visitor's viewing experience.

[0011] Optionally, determining the first display angle of the vehicle to be visited based on the target profile, key vehicle parts easily viewed in the online auto show, and at least one corresponding key visitor profile specifically includes:

[0012] Obtain the historical vehicle parts that visitors clicked to visit during the online auto show, count the first occurrence number of each historical vehicle part, and select the first number of historical vehicle parts as key vehicle parts according to the first occurrence number in descending order.

[0013] Obtain historical portraits of visitors who have visited a single key vehicle section, count the second occurrence frequency of each historical portrait, and select a second number of historical portraits from each historical portrait in descending order of the second occurrence frequency to determine them as the key visitor portraits corresponding to a single key vehicle section.

[0014] A first weight is determined for each of the key vehicle parts, and a second weight is determined for the key visitor profile corresponding to each key vehicle part. The first weight is the ratio of the first occurrence of each key vehicle part to the sum of the first occurrences of all key vehicle parts, and the second weight is the ratio of the second occurrence of a single key visitor profile corresponding to a key vehicle part to the sum of the second occurrences of all key visitor profiles.

[0015] Based on the target profile, the first weight, and the second weight, the first display perspective of the vehicle to be visited is determined.

[0016] By adopting the above technical solution, the greater the frequency of the first occurrence, the easier it is for visitors to view the historical vehicle parts corresponding to the exhibited vehicles in the online auto show, thus identifying key vehicle parts; the greater the frequency of the second occurrence, the easier it is for visitors with corresponding historical profiles to visit the key vehicle parts, thus identifying key visitor profiles. Finally, by combining the first and second weights, the analysis determines the display angles that are more likely to interest the target visitors, thereby ensuring a better viewing experience for the target visitors during vehicle displays.

[0017] Optionally, determining the first display perspective of the vehicle to be visited based on the target profile, the first weight, and the second weight specifically includes:

[0018] When the target image exists in the portraits of key visitors corresponding to the key vehicle locations, the corresponding key vehicle locations are identified as the target vehicle locations.

[0019] Calculate the first product of the first weight of each target vehicle part and the second weight of the corresponding target image, and select the largest first product from all the first products;

[0020] The target vehicle part corresponding to the maximum first product is determined as the part of interest, and at least one candidate display view containing the part of interest is determined in the display area.

[0021] The first products corresponding to the target vehicle parts contained in the display parts of a single candidate display view are summed to obtain the sum of the corresponding first products, and the largest sum of the first products is selected from the sums of the first products.

[0022] The candidate display viewpoint corresponding to the sum of the largest first products is determined as the first display viewpoint of the vehicle to be visited.

[0023] By adopting the above technical solution, the larger the sum of the first products, the greater the overall likelihood that the corresponding candidate display view will arouse the interest of the target visitors. Then, the largest sum of the first products is selected from the sums of the various first products, and finally, the candidate display view corresponding to the largest sum of the first products is determined as the first display view of the vehicle to be visited, thereby enabling the target visitors to have a better viewing experience from the first display view.

[0024] Optionally, the step of displaying the vehicle to be visited in the terminal of the target visitor through a preset AR frame according to the first display perspective specifically includes:

[0025] Obtain the network quality index of the terminal of the target exhibition visitor. The higher the network quality index, the worse the network quality of the terminal.

[0026] If the network quality index exceeds a preset index threshold, the transmission loading order of the target vehicle part is determined according to the first product corresponding to the target vehicle part included in the display part of the first display perspective. The larger the first product, the earlier the corresponding transmission loading order.

[0027] According to the transmission loading order and the first display perspective, the vehicle to be visited is displayed on the terminal of the target visitor through a preset AR frame.

[0028] By adopting the above technical solution, if the network quality index exceeds the preset index threshold, it indicates that the network quality of the current terminal is poor. Then, based on the first product corresponding to the target vehicle part included in the display area of ​​the first display perspective, the transmission and loading order of the corresponding target vehicle part is determined. The larger the first product, the more likely the target visitors are to be interested in the corresponding target vehicle part, and the earlier the corresponding transmission and loading order is. In the case of poor network quality, data transmission and loading are given priority and displayed in the field of vision of the target visitors, thereby reducing the impact of poor network quality on the viewing experience of the target visitors.

[0029] Optionally, determining at least one vehicle of interest to the target visitors specifically includes:

[0030] When the target image exists in the profiles of key visitors corresponding to the key vehicle locations, the corresponding key vehicle location is determined as the target vehicle location. The second product of the first weight of each target vehicle location and the second weight of the corresponding target image is calculated, and the vehicle attention dimension to which each target vehicle location belongs is determined.

[0031] The second products corresponding to each target vehicle part involved in the same vehicle attention dimension are summed to obtain the sum of the corresponding second products. If the sum of the second products exceeds a preset threshold, the corresponding vehicle attention dimension is determined as the dimension of interest.

[0032] Determine the selling points of each vehicle exhibited in the online auto show. If the selling point is a dimension of interest, then the corresponding vehicle is determined as the vehicle of interest to the target audience.

[0033] By employing the above technical solution, the larger the sum of the second products, the greater the likelihood that the target visitors are interested in the corresponding vehicle attention dimension. If the sum of the second products is greater than a preset threshold, it indicates a high probability that the target visitors are interested in the corresponding vehicle attention dimension, and thus the corresponding vehicle attention dimension is determined as the dimension of interest. If the selling point dimension is the dimension of interest, then the corresponding exhibited vehicle is determined as the vehicle of interest for the target visitors, thereby more accurately identifying the vehicles that the target visitors are interested in at the online auto show, facilitating subsequent targeted AR displays.

[0034] Optionally, the step of displaying the vehicle on the terminal based on the vehicle of interest specifically includes:

[0035] Each of the vehicles of interest is sent to the terminal. If a selection instruction is received from the terminal, the vehicle of interest corresponding to the selection instruction is displayed on the terminal through a preset AR framework.

[0036] If no selection instruction is received from the terminal, then the selling point dimension other than the dimension of interest will be determined as the reference dimension.

[0037] The key vehicle parts involved in the reference dimension are identified as reference vehicle parts, and the third product of the first weight of each reference vehicle part and the second weight of the corresponding key visitor profile is calculated.

[0038] Summing up the third products corresponding to the portraits of the same key visitors, obtaining the sum of the corresponding third products, selecting the largest sum of the third products from the sums of the third products, and determining the portrait of the key visitor corresponding to the largest sum of the third products as the final portrait;

[0039] The target image is replaced with the final image, and the vehicle is displayed on the terminal based on the final image.

[0040] By adopting the above technical solution, if no selection instruction is received from the terminal, it indicates that none of the vehicles among the interested vehicles belong to the target visitors. The target visitors are more likely to be interested in vehicles exhibited based on selling points other than the core interest dimension, suggesting an error in the target profile. Furthermore, the larger the sum of the third products, the greater the overall probability that the key visitors are interested in the reference dimensions. Therefore, the maximum sum of the third products is determined, and the key visitor profile corresponding to the maximum sum of the third products is identified as the final profile. The target profile is then adjusted to the final profile, thus more accurately determining the target visitor profile.

[0041] Optionally, the method further includes:

[0042] If a viewing instruction for a vehicle to be visited is received from the terminal of the target visitor, the vehicle part corresponding to the viewing instruction is determined as the part to be viewed. If the target image exists in the portraits of each key visitor corresponding to the key vehicle part, the corresponding key vehicle part is determined as the target vehicle part.

[0043] Determine at least one adjustable display view that includes the part to be viewed in the display area, calculate the fourth product of the first weight of the target vehicle part included in the display area of ​​a single adjustable display view and the second weight of the corresponding target image, and sum the fourth products to obtain the corresponding sum of the fourth products.

[0044] Select the largest sum of fourth products from the sums of all the fourth products, determine the display view to be adjusted corresponding to the largest sum of fourth products as the second display view, and adjust the first display view to the second display view.

[0045] By adopting the above technical solution, the larger the sum of the fourth products, the greater the likelihood that the target visitors will be interested in the overall vehicle parts displayed from the corresponding display perspective to be adjusted. Finally, the largest sum of the fourth products is selected from the sums of the various fourth products, and the display perspective to be adjusted corresponding to the largest sum of the fourth products is determined as the second display perspective. The first display perspective is then adjusted to the second display perspective, thereby providing the target visitors with a better viewing experience.

[0046] A second aspect of this application provides an AR auto show display device, specifically comprising:

[0047] The information acquisition module is used to acquire the target profile and the vehicles to be visited for the target visitors, wherein the vehicles to be visited are the exhibited vehicles selected by the target visitors to visit in the online auto show;

[0048] The perspective determination module is used to determine the first display perspective of the vehicle to be visited based on the target profile, key vehicle parts that are easy to visit in the online auto show, and at least one key visitor profile. The key visitor profile is a profile of a visitor who is easy to visit the corresponding key vehicle parts.

[0049] The first display module is used to display the vehicle to be visited in the terminal of the target visitor through a preset AR frame according to the first display perspective.

[0050] The second display module is used to determine at least one vehicle of interest to the target visitor when no vehicle selected by the target visitor is obtained, and to display the vehicle on the terminal based on the vehicle of interest.

[0051] By adopting the above technical solution, after the information acquisition module obtains the target profile and the vehicle to be visited, the perspective determination module determines the first display perspective of the vehicle to be visited. Then, the first display module displays the vehicle to be visited on the terminal of the target visitor based on the first display perspective. Finally, if the second display module does not obtain the vehicle to be visited selected by the target visitor, it displays the vehicle on the terminal based on the vehicle of interest.

[0052] A third aspect of this application provides a computer-readable storage medium storing a computer program that, when loaded and executed by a processor, performs the steps of the method described in any of the first aspects.

[0053] A fourth aspect of this application provides an electronic device, specifically comprising:

[0054] A processor, a memory, and a computer program stored in the memory and capable of running on the processor, the processor being configured to load and execute the computer program stored in the memory to cause the electronic device to perform the method as described in any one of the first aspects.

[0055] In summary, this application includes at least one of the following beneficial technical effects: After obtaining the target profile and the vehicles to be visited, by combining key vehicle parts with the corresponding key visitor profiles, the analysis determines the vehicle parts of the vehicles that the target visitors are most likely to be interested in. This allows for the determination of a first display perspective that best matches the visitor's viewing needs, and the vehicles to be visited are then displayed using AR from this first perspective, thereby better meeting the personalized viewing needs of the target visitors and improving the viewing experience. Furthermore, if the vehicles selected by the target visitors are not obtained, it indicates that the target visitors are not clear about the vehicles they are interested in. Therefore, it is necessary to specifically determine the vehicles that the target visitors are interested in, and finally, based on these vehicles, display them on the terminal, further improving the visitor's viewing experience. Attached Figure Description

[0056] Figure 1 This is a flowchart illustrating an AR auto show display method provided in an embodiment of this application;

[0057] Figure 2 This is a schematic diagram of the structure of an AR auto show display device provided in an embodiment of this application;

[0058] Figure 3 This is a schematic diagram of another AR auto show display device provided in the embodiments of this application.

[0059] Explanation of reference numerals in the attached diagram: 11. Information acquisition module; 12. Viewpoint determination module; 13. First display module; 14. Second display module; 15. Viewpoint switching module. Detailed Implementation

[0060] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0061] In the description of the embodiments of this application, words such as "exemplarily," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplarily," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of words such as "exemplarily," "for example," or "for instance" is intended to present the relevant concepts in a specific manner.

[0062] In the description of the embodiments of this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, B existing alone, or A and B existing simultaneously. Furthermore, unless otherwise stated, the term "multiple" means two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and their variations all mean "including but not limited to," unless otherwise specifically emphasized.

[0063] See Figure 1 This application discloses a flowchart of an AR auto show display method, which can be implemented using a computer program or run on an AR auto show display device based on the von Neumann architecture. The computer program can be integrated into an application or run as a standalone utility application, specifically including:

[0064] S101: Obtain the target profile of the target visitors and the vehicles to be visited.

[0065] Specifically, in this embodiment, the vehicles to be visited are those selected by the target visitors in the online auto show, representing multiple vehicles on display. The target visitors are those currently watching the online auto show via a terminal, which can be a smartphone or personal computer. The online auto show is an Augmented Reality (AR) auto show, a new exhibition format that brings the traditional auto show experience online. It breaks through the limitations of time and space, allowing visitors to "be" at the auto show anytime, anywhere via their terminals, enjoying an immersive experience of viewing, selecting, and purchasing cars. Furthermore, the target profile is a representative user model abstracted from the basic information of the target visitors, including but not limited to gender, age, and interests.

[0066] Furthermore, the AR auto show display method disclosed in this application is executed by a server. The terminal has an AR auto show-related client installed, and the server serves as the client's backend server. Specifically, it can be a standalone physical server or a cluster of multiple physical servers. Additionally, the implementation scenario of the AR auto show display method is as follows: when a target viewer needs to participate in an online auto show, they send an auto show display command to the server through the client. The server then obtains the target viewer's profile and the vehicles to be viewed, and accordingly personalizes the AR display of the vehicles on the target viewer's terminal.

[0067] One feasible method for obtaining a target profile is as follows: With the user's authorization and consent, the registration information of the target visitor in the client application is retrieved from the database. This registration information includes, but is not limited to, age, gender, and interests. This determines the basic information, which is then input into a preset profile prediction model to obtain the target profile. The profile prediction model is a trained recurrent neural network model; in other embodiments, it can also be a trained random forest model. The training process is briefly described as follows: the model is trained using basic information samples labeled with the correct profile, and parameters are tuned using the backpropagation algorithm until the model converges. Additionally, the vehicle to be visited is determined by receiving vehicle selection instructions from the online auto show sent by the terminal.

[0068] S102: Based on the target profile, the key vehicle parts of the vehicles on display in the online auto show that are easy to visit, and the corresponding profile of at least one key visitor, determine the first display angle of the vehicle to be visited.

[0069] Specifically, the profile of key visitors is one that facilitates viewing specific parts of the vehicle. These key vehicle parts could be the center console, taillights, or trunk of the exhibited vehicle, etc. The first viewing angle of the vehicle to be viewed is a single angle view of the 3D model of the vehicle loaded and displayed on the terminal. This first viewing angle could be an oblique side view, a frontal side view, or a top-down view, etc. It should be noted that visitors can also automatically rotate and zoom the exhibited vehicle via screen touch, and even click on a specific part of the vehicle to enlarge it for better viewing. In other embodiments, voice commands can also be used to switch the viewed vehicle part.

[0070] Furthermore, based on historical visitor monitoring records, the system retrieves the historical vehicle sections clicked on by past visitors during the online auto show. It then counts the first occurrence frequency of each historical vehicle section; the higher the first occurrence frequency, the easier it is for visitors to view the corresponding historical vehicle section of the exhibited vehicle during the online auto show. Next, based on the first occurrence frequency in descending order, the most frequently accessed historical vehicle sections are selected as key vehicle sections. The first occurrence frequency refers to the frequency of occurrence of the same historical vehicle section across all historical vehicle sections. Additionally, the historical visitor monitoring records include, but are not limited to, the vehicle sections clicked by past visitors and the basic information of the past visitors who clicked on them.

[0071] Furthermore, historical profiles of visitors who have visited individual key vehicle sections are obtained, and the second occurrence frequency of each historical profile is counted. The higher the second occurrence frequency, the more likely the visitors with the corresponding historical profile are to visit that key vehicle section. Next, in descending order of the second occurrence frequency, the second number of historical profiles are selected from all historical profiles to determine the key visitor profiles corresponding to that key vehicle section—that is, the profiles of people likely to visit that key vehicle section. It should be noted that based on historical visit monitoring records, basic information of historical visitors who clicked on individual key vehicle sections is obtained, and then the corresponding profiles are determined through a profile prediction model. The second occurrence frequency is the frequency of the same historical profile appearing among all historical profiles.

[0072] A first weight is determined for each key vehicle section, and a second weight is determined for the profile of the key visitors corresponding to each key vehicle section. The first weight is the ratio of the first occurrence frequency of each key vehicle section to the sum of the first occurrence frequencies of all key vehicle sections. The second weight is the ratio of the second occurrence frequency of a single key visitor profile corresponding to a key vehicle section to the sum of the second occurrence frequencies of all corresponding key visitor profiles. Finally, based on the target profile, the first weight, and the second weight, the first display angle of the vehicle to be visited, tailored to the needs of the target visitors, is determined. One feasible implementation method is as follows:

[0073] If a target profile exists within the profiles of key visitors corresponding to key vehicle sections, then the corresponding key vehicle section is designated as the target vehicle section. The first weight of each target vehicle section is calculated as the first product of the second weight of the corresponding target profile. The larger the first product, the more likely the target visitors are to be interested in the target vehicle section of the vehicle to be visited during the online auto show. Then, the largest first product is selected from all the first products, and the target vehicle section corresponding to the largest first product is designated as the section of interest—that is, the vehicle section that the target visitors are most likely to be interested in for the vehicle to be visited. Next, based on the historical viewpoint selection records of visitors, the number of times each historical display view was selected is counted. Historical display views with selection counts exceeding a preset threshold are designated as candidate display views. Then, from all candidate display views, the viewpoint containing the section of interest is selected as a candidate display view. The vehicle to be visited is displayed from this candidate display view, allowing the target visitors to see the section of interest. The viewpoint selection records are server-cached records of historical visitors' vehicle display viewpoint selections, including but not limited to display views selected by different historical visitors.

[0074] Furthermore, the first products corresponding to the target vehicle parts included in the display areas of a single candidate display perspective are summed to obtain the sum of the corresponding first products. The larger the sum of the first products, the greater the overall probability that the corresponding candidate display perspective will arouse the interest of the target visitors. Then, the largest sum of the first products is selected from all the sums of the first products, and finally, the candidate display perspective corresponding to the largest sum of the first products is determined as the first display perspective of the vehicle to be visited.

[0075] S103: Based on the first display perspective, display the vehicle to be visited in the terminal of the target visitors through a preset AR frame.

[0076] Specifically, an AR framework refers to a set of tools and functions that provide developers with the necessary resources to build augmented reality applications. These frameworks typically include 3D engines, scene graphs, input systems, audio systems, and network functionalities, aiming to simplify the development process of AR applications and enable developers to create immersive and interactive augmented reality experiences more efficiently. After the first viewing perspective is determined, the server transmits the model data of the vehicle to be visited to the client on the terminal, and displays the vehicle in AR on the terminal from the first viewing perspective using a preset AR framework. This allows the target audience to see the parts of the vehicle that are most likely to be of interest, as well as other potentially interesting parts, satisfying their personalized viewing needs while avoiding the need for them to frequently switch viewing perspectives to find specific parts. The AR framework can utilize the ARCore tool; in other embodiments, the Vuforia tool can also be used.

[0077] In other embodiments, the network quality index of the target visitor's terminal is obtained. Specifically, the latency and packet loss rate during the process of obtaining the model data of the vehicle to be visited using a preset Wireshark tool are used. Then, the latency and packet loss rate are weighted and summed to obtain the network quality index. The higher the network quality index, the worse the network quality and the slower the model data transmission. Further, if the network quality index exceeds a preset index threshold, it indicates that the current terminal's network quality is poor. Then, based on the first product corresponding to the target vehicle parts included in the display area of ​​the first display perspective, the transmission and loading order of the corresponding target vehicle parts is determined, that is, the order of transmission and loading of model data for the target vehicle parts. The larger the first product, the more likely the target visitor is to be interested in the corresponding target vehicle part, and the earlier the corresponding transmission and loading order is. In the case of poor network quality, data transmission and loading are prioritized and displayed in the target visitor's field of vision. Finally, in the first display perspective, according to each transmission and loading order, the vehicle to be visited is displayed in the target visitor's terminal in a step-by-step manner using an AR framework, thereby reducing the impact of poor network quality on the target visitor's viewing experience.

[0078] In one embodiment, during the display of the vehicle to be visited from a first display perspective, at least one actual viewing area of ​​the vehicle to be visited that triggers a click event is acquired in real time on the terminal; that is, the vehicle part of the vehicle to be visited that the target visitor clicks to view. Further, when the actual viewing area is the target vehicle part, the weighted product of the first weight of the actual viewing area and the corresponding second weight of the target profile is calculated. The weighted products are summed to obtain a summation result. If the summation result is greater than a preset product sum threshold, it indicates that the target visitor is likely interested in all the actual viewing areas as a whole, indicating that the target profile is confirmed to be correct, thereby ensuring the accuracy of the target visitor profile to a certain extent.

[0079] In another embodiment, when the network quality index exceeds the index threshold, a third number of target vehicle parts are selected from each target vehicle part in descending order of the first product, and then aggregated to obtain a first set. Then, a fourth number of target vehicle parts are selected from each target vehicle part in ascending order of the model data transmission loading rate, and then aggregated to obtain a second set. Finally, the intersection of the first and second sets is performed to obtain the target set. The target vehicle parts in the target set are determined as the optimal vehicle parts. The number of optimal vehicle parts present in each candidate display perspective is counted, and the candidate display perspective with the most optimal vehicle parts is determined as the first display perspective. When displaying the vehicles to be visited from this first display perspective, the vehicle parts that are of greater interest to the target visitors can be displayed more effectively.

[0080] S104: If the target visitor's selected vehicle is not obtained, determine at least one vehicle of interest to the target visitor and display the vehicle on the terminal based on the vehicle of interest.

[0081] Specifically, if no vehicle selection instruction is received from the target visitor's terminal, it indicates that the target visitor is unclear about the vehicles they are interested in. Therefore, it is necessary to specifically identify the vehicles the target visitor is interested in. One feasible method is as follows: when a target profile exists in the profiles of key visitors corresponding to key vehicle sections, the corresponding key vehicle section is designated as the target vehicle section. The second product of the first weight of each target vehicle section and the second weight of the corresponding target profile is calculated. The larger the second product, the more likely the target visitor is to be interested in the corresponding target vehicle section. Next, a preset dimension matching table is used to determine the vehicle attention dimension associated with each target vehicle section. The dimension matching table includes different vehicle sections and their associated vehicle attention dimensions, all set based on human experience. These vehicle attention dimensions are the dimensions that people refer to when purchasing vehicles, including but not limited to passenger space, interior design, and exterior appearance.

[0082] Furthermore, the second products corresponding to each target vehicle part involved in the same vehicle attention dimension are summed to obtain the sum of the corresponding second products. The larger the sum of the second products, the greater the likelihood that the target visitors are interested in the corresponding vehicle attention dimension. If the sum of the second products is greater than a preset threshold, it indicates that the target visitors are more likely to be interested in the corresponding vehicle attention dimension, and thus the corresponding vehicle attention dimension is determined as the dimension of interest. For example, if the target visitor's profile is a father of two, then the corresponding dimension of interest is the passenger space dimension. Next, web scraping technology can be used to collect the introductory text data corresponding to each exhibited vehicle in the online auto show from social media platforms. Then, Natural Language Processing (NLP) is used based on the introductory text data to determine the selling point dimension of each exhibited vehicle. For example, if keywords such as "not crowded" and "large legroom" frequently appear in the introductory text data of exhibited vehicle A, then the selling point dimension of exhibited vehicle A is determined to be the passenger space dimension. Furthermore, if the selling point dimension is an interest dimension, it means that the target audience of the exhibited vehicle is highly likely to be interested in it. Therefore, the corresponding exhibited vehicle is identified as the vehicle of interest for the target audience. Finally, the vehicle model data of the vehicle of interest is transmitted to the terminal, and this vehicle of interest is loaded and displayed on the terminal through an AR framework.

[0083] In one embodiment, after identifying vehicles of interest, the vehicles are displayed on the terminal. One possible implementation is as follows: Images of each vehicle of interest are sent to the terminal of the target visitor. If a selection command is received from the terminal, it indicates that the target visitor wants to see a vehicle among the vehicles of interest. Then, the vehicle of interest corresponding to the selection command is displayed on the terminal using an AR framework. If no selection command is received from the terminal, it indicates that the target visitor does not want to see a vehicle among the vehicles of interest. The target visitor is more likely to be interested in vehicles exhibited based on selling points (other than the interest dimension), which may indicate an error in the target profile. In this case, the selling points (other than the interest dimension) are designated as reference dimensions, and the key vehicle parts involved in the reference dimensions are designated as reference vehicle parts. The third product of the first weight of each reference vehicle part and the second weight of the corresponding key visitor profile is calculated. The larger the third product, the greater the likelihood that the person in the key visitor profile is interested in the reference vehicle part. Next, the third products corresponding to the same key visitor profile are summed to obtain the sum of the corresponding third products. The larger the sum of the third products, the greater the overall probability that the key visitor profile is interested in the reference dimension. The largest sum of the third products is selected from the sums of the third products, and the key visitor profile corresponding to this largest sum of the third products is determined as the final profile, that is, the profile that is more suitable for the target visitor. Finally, this target profile is replaced with the final profile, and the vehicle is re-displayed on the terminal based on this final profile. For details, please refer to step S104, which will not be repeated here.

[0084] In another embodiment, after displaying the vehicle to be visited on the target visitor's terminal from the first display perspective, if a viewing instruction for a specific part of the vehicle is received from the target visitor's terminal, indicating that the target visitor needs to switch to viewing a different part of the vehicle after viewing it from the first display perspective, then the vehicle part corresponding to the viewing instruction is determined as the part to be viewed. Specifically, this involves obtaining the vehicle part spoken by the target visitor through a preset voice recognition module, and then determining the part to be viewed. Further, if a target profile exists in the profiles of key visitors corresponding to key vehicle parts, the corresponding key vehicle part is determined as the target vehicle part. Then, from the aforementioned alternative display perspectives, display perspectives containing the part to be viewed are selected for adjustment. The fourth product of the first weight of the target vehicle part included in the display area of ​​a single display view to be adjusted and the second weight of the corresponding target image is calculated. The fourth products are summed to obtain the sum of the fourth products. The larger the sum of the fourth products, the greater the likelihood that the target visitors are interested in the vehicle part displayed in the corresponding display view to be adjusted as a whole. Finally, the largest sum of the fourth products is selected from the sums of the fourth products. The display view to be adjusted corresponding to the largest sum of the fourth products is determined as the second display view. The first display view is adjusted to the second display view, thereby providing the target visitors with a better display view for their viewing experience.

[0085] The implementation principle of an AR auto show display method according to an embodiment of this application is as follows: After obtaining the target profile and the vehicles to be visited, the method combines key vehicle parts with the corresponding key visitor profiles to analyze and determine the vehicle parts that the target visitors are most likely to be interested in. Then, a first display perspective that best matches the visitor's viewing needs is determined, and the vehicles to be visited are displayed in AR from this first perspective, thereby better meeting the personalized viewing needs of the target visitors and improving the viewing experience. Furthermore, if no vehicles selected by the target visitors are obtained, it indicates that the target visitors are not clear about the vehicles they are interested in. In this case, it is necessary to specifically determine the vehicles that the target visitors are interested in, and finally, based on these vehicles, display them on the terminal to improve the visitor's viewing experience.

[0086] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0087] Please see Figure 2This is a schematic diagram of the structure of the AR auto show display device provided in this application embodiment. This AR auto show display device can be implemented as all or part of the device through software, hardware, or a combination of both. The device includes an information acquisition module 11, a viewing angle determination module 12, a first display module 13, and a second display module 14.

[0088] Information acquisition module 11 is used to acquire the target profile and the vehicles to be visited for the target visitors. The vehicles to be visited are the exhibited vehicles selected by the target visitors in the online auto show.

[0089] The perspective determination module 12 is used to determine the first display perspective of the vehicle to be visited based on the target profile, the key vehicle parts of the exhibited vehicles in the online auto show that are easy to visit, and the corresponding profile of at least one key visitor. The profile of the key visitor is the profile of the visitor who is easy to visit the corresponding key vehicle parts.

[0090] The first display module 13 is used to display the vehicle to be visited in the terminal of the target visitors through a preset AR frame according to the first display perspective.

[0091] The second display module 14 is used to determine at least one vehicle of interest to the target visitor when the vehicle selected by the target visitor has not been obtained, and to display the vehicle on the terminal based on the vehicle of interest.

[0092] Optional, the viewpoint determination module 12 is specifically used for:

[0093] Get the historical vehicle parts that visitors clicked to visit in the online auto show, count the number of times each historical vehicle part appeared, and select the historical vehicle parts with the most first appearances from each historical vehicle part in descending order of the number of first appearances to determine the key vehicle parts.

[0094] Obtain historical portraits of visitors who have visited a single key vehicle section, count the number of times each historical portrait appears, and select the historical portraits with the second most occurrences from each historical portrait in descending order of the number of times the second occurrences occur, and determine them as the key visitors portraits corresponding to the single key vehicle section.

[0095] Determine the first weight for each key vehicle part and the second weight for the key visitor profile corresponding to each key vehicle part. The first weight is the ratio of the first occurrence of each key vehicle part to the sum of the first occurrences of all key vehicle parts. The second weight is the ratio of the second occurrence of a single key visitor profile corresponding to a key vehicle part to the sum of the second occurrences of all key visitor profiles.

[0096] Based on the target profile, the first weight, and the second weight, the first display perspective of the vehicle to be visited is determined.

[0097] Optional, the viewpoint determination module 12 is specifically used for:

[0098] When a target image exists in the portraits of key visitors corresponding to key vehicle locations, the corresponding key vehicle location is identified as the target vehicle location.

[0099] Calculate the first product of the first weight of each target vehicle part and the second weight of the corresponding target profile, and select the largest first product from all the first products;

[0100] The target vehicle part corresponding to the largest first product is identified as the part of interest, and at least one candidate display view containing the part of interest is identified as the display part.

[0101] Summing the first products corresponding to the target vehicle parts contained in the display parts of a single candidate display viewpoint, obtaining the sum of the corresponding first products, and selecting the largest sum of the first products from all the sums of the first products;

[0102] The candidate display view corresponding to the sum of the largest first products is determined as the first display view of the vehicle to be visited.

[0103] Optionally, the first display module 13 is specifically used for:

[0104] Obtain the network quality index of the target visitors' terminals. The higher the network quality index, the worse the network quality of the terminal.

[0105] If the network quality index exceeds the preset index threshold, the transmission loading order of the target vehicle part is determined according to the first product corresponding to the target vehicle part included in the display part of the first display perspective. The larger the first product, the earlier the corresponding transmission loading order.

[0106] Based on the loading order of each transmission and the first display perspective, the vehicle to be visited is displayed on the terminal of the target visitors through a preset AR framework.

[0107] Optionally, the second display module 14 is specifically used for:

[0108] When a target profile exists in the profiles of key visitors corresponding to key vehicle locations, the corresponding key vehicle location is identified as the target vehicle location. The second product of the first weight of each target vehicle location and the second weight of the corresponding target profile is calculated, and the vehicle attention dimension to which each target vehicle location belongs is determined.

[0109] The second product corresponding to each target vehicle part involved in the same vehicle attention dimension is summed to obtain the sum of the corresponding second products. If the sum of the second products exceeds a preset threshold, the corresponding vehicle attention dimension is determined as the dimension of interest.

[0110] Determine the selling points of each vehicle exhibited in the online auto show. If a selling point is a point of interest, then the corresponding vehicle will be identified as a vehicle of interest to the target audience.

[0111] Optionally, the second display module 14 is specifically used for:

[0112] Send each vehicle of interest to the terminal. If a selection command is received from the terminal, the vehicle of interest corresponding to the selection command will be displayed on the terminal through a preset AR framework.

[0113] If no selection instruction is received from the terminal, then the selling point dimensions other than the dimension of interest will be determined as the reference dimensions.

[0114] The key vehicle parts involved in the reference dimension are identified as reference vehicle parts, and the third product of the first weight of each reference vehicle part and the second weight of the corresponding key visitor profile is calculated.

[0115] Summing up the third products corresponding to the portraits of the same key visitors, the sum of the third products is obtained. The largest sum of the third products is selected from the sums of the third products, and the portrait of the key visitor corresponding to the largest sum of the third products is determined as the final portrait.

[0116] Replace the target image with the final image, and display the vehicle on the terminal based on the final image.

[0117] Optional, such as Figure 3 As shown, the device also includes a viewpoint switching module 15, specifically used for:

[0118] If a viewing instruction for a vehicle to be visited is received from the terminal of the target visitor, the vehicle part corresponding to the viewing instruction is identified as the part to be viewed. If the target image exists in the portrait of each key visitor corresponding to the key vehicle part, the corresponding key vehicle part is identified as the target vehicle part.

[0119] Determine at least one adjustable display view that contains the part to be viewed in the display area, calculate the fourth product of the first weight of the target vehicle part contained in the display area of ​​a single adjustable display view and the second weight of the corresponding target image, and sum the fourth products to obtain the sum of the corresponding fourth products.

[0120] Select the largest sum of fourth products from the sums of all fourth products, determine the display view to be adjusted corresponding to the largest sum of fourth products as the second display view, and adjust the first display view to the second display view.

[0121] It should be noted that the AR auto show display device provided in the above embodiments, when executing the AR auto show display method, is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the AR auto show display device and the AR auto show display method embodiment provided in the above embodiments belong to the same concept, and the implementation process is detailed in the method embodiment, which will not be repeated here.

[0122] This application also discloses a computer-readable storage medium, which stores a computer program, wherein when the computer program is executed by a processor, it implements an AR auto show display method of the above embodiments.

[0123] The computer program can be stored in a computer-readable medium. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or certain middleware. The computer-readable medium includes any entity or device capable of carrying computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the computer-readable medium includes, but is not limited to, the above-mentioned components.

[0124] The AR auto show display method of the above embodiment is stored in the computer-readable storage medium and loaded and executed on the processor to facilitate the storage and application of the above method.

[0125] This application also discloses an electronic device in which a computer program is stored in a computer-readable storage medium. When the computer program is loaded and executed by a processor, it implements the above-mentioned AR auto show display method.

[0126] The electronic device can be a desktop computer, a laptop computer, or a cloud server, and includes, but is not limited to, a processor and a memory. For example, the electronic device may also include input / output devices, network access devices, and buses.

[0127] The processor can be a central processing unit (CPU). Of course, depending on the actual use, it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc., and this application does not limit it.

[0128] The memory can be an internal storage unit of an electronic device, such as a hard disk or RAM, or an external storage device, such as a plug-in hard disk, smart memory card (SMC), secure digital card (SD), or flash memory card (FC) equipped on the electronic device. Furthermore, the memory can be a combination of an internal storage unit and an external storage device. The memory is used to store computer programs and other programs and data required by the electronic device. The memory can also be used to temporarily store data that has been output or will be output. This application does not limit this.

[0129] In this electronic device, an AR auto show display method according to the above embodiment is stored in the memory of the electronic device and loaded and executed on the processor of the electronic device for convenient use.

[0130] The foregoing description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described in this disclosure. The specification and embodiments are considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. An AR auto show display method, characterized in that, The method includes: Obtain the target profile and the vehicles to be visited for the target visitors, wherein the vehicles to be visited are the exhibited vehicles selected by the target visitors to visit in the online auto show; Based on the target profile, the key vehicle parts of the exhibited vehicles in the online auto show that are easy to visit, and the corresponding profile of at least one key visitor, the first display perspective of the vehicle to be visited is determined, and the profile of the key visitor is the profile of the visitor who is easy to visit the corresponding key vehicle parts. Based on the first display perspective, the vehicle to be visited is displayed in the terminal of the target visitors through a preset AR frame; If the vehicle selected by the target visitor is not obtained, at least one vehicle of interest to the target visitor is determined, and the vehicle is displayed on the terminal based on the vehicle of interest.

2. The AR auto show display method according to claim 1, characterized in that, The process of determining the first display perspective of the vehicle to be visited based on the target profile, key vehicle parts easily accessible to visitors in the online auto show, and at least one corresponding profile of a key visitor specifically includes: Obtain the historical vehicle parts that visitors clicked to visit during the online auto show, count the first occurrence number of each historical vehicle part, and select the first number of historical vehicle parts as key vehicle parts according to the first occurrence number in descending order. Obtain historical portraits of visitors who have visited a single key vehicle section, count the second occurrence frequency of each historical portrait, and select a second number of historical portraits from each historical portrait in descending order of the second occurrence frequency to determine them as the key visitor portraits corresponding to a single key vehicle section. A first weight is determined for each of the key vehicle parts, and a second weight is determined for the key visitor profile corresponding to each key vehicle part. The first weight is the ratio of the first occurrence of each key vehicle part to the sum of the first occurrences of all key vehicle parts, and the second weight is the ratio of the second occurrence of a single key visitor profile corresponding to a key vehicle part to the sum of the second occurrences of all key visitor profiles. Based on the target profile, the first weight, and the second weight, the first display perspective of the vehicle to be visited is determined.

3. The AR auto show display method according to claim 2, characterized in that, The step of determining the first display perspective of the vehicle to be visited based on the target profile, the first weight, and the second weight specifically includes: When the target image exists in the portraits of key visitors corresponding to the key vehicle locations, the corresponding key vehicle locations are identified as the target vehicle locations. Calculate the first product of the first weight of each target vehicle part and the second weight of the corresponding target image, and select the largest first product from all the first products; The target vehicle part corresponding to the maximum first product is determined as the part of interest, and at least one candidate display view containing the part of interest is determined in the display area. The first products corresponding to the target vehicle parts contained in the display parts of a single candidate display view are summed to obtain the sum of the corresponding first products, and the largest sum of the first products is selected from the sums of the first products. The candidate display view corresponding to the sum of the largest first products is determined as the first display view of the vehicle to be visited.

4. The AR auto show display method according to claim 3, characterized in that, The step of displaying the vehicle to be visited on the terminal of the target visitor through a preset AR frame, based on the first display perspective, specifically includes: Obtain the network quality index of the terminal of the target exhibition visitor. The higher the network quality index, the worse the network quality of the terminal. If the network quality index exceeds a preset index threshold, the transmission loading order of the target vehicle part is determined according to the first product corresponding to the target vehicle part included in the display part of the first display perspective. The larger the first product, the earlier the corresponding transmission loading order. According to the transmission loading order and the first display perspective, the vehicle to be visited is displayed on the terminal of the target visitor through a preset AR frame.

5. The AR auto show display method according to claim 2, characterized in that, The determination of at least one vehicle of interest to the target visitors specifically includes: When the target image exists in the profiles of key visitors corresponding to the key vehicle locations, the corresponding key vehicle location is determined as the target vehicle location. The second product of the first weight of each target vehicle location and the second weight of the corresponding target image is calculated, and the vehicle attention dimension to which each target vehicle location belongs is determined. The second products corresponding to each target vehicle part involved in the same vehicle attention dimension are summed to obtain the sum of the corresponding second products. If the sum of the second products exceeds a preset threshold, the corresponding vehicle attention dimension is determined as the dimension of interest. Determine the selling points of each vehicle exhibited in the online auto show. If the selling point is a dimension of interest, then the corresponding vehicle is determined as the vehicle of interest to the target audience.

6. The AR auto show display method according to claim 5, characterized in that, The process of displaying vehicles on the terminal based on the vehicles of interest specifically includes: Each of the vehicles of interest is sent to the terminal. If a selection instruction is received from the terminal, the vehicle of interest corresponding to the selection instruction is displayed on the terminal through a preset AR framework. If no selection instruction is received from the terminal, then the selling point dimension other than the dimension of interest will be determined as the reference dimension. The key vehicle parts involved in the reference dimension are identified as reference vehicle parts, and the third product of the first weight of each reference vehicle part and the second weight of the corresponding key visitor profile is calculated. Summing up the third products corresponding to the portraits of the same key visitors, obtaining the sum of the corresponding third products, selecting the largest sum of the third products from the sums of the third products, and determining the portrait of the key visitor corresponding to the largest sum of the third products as the final portrait; The target image is replaced with the final image, and the vehicle is displayed on the terminal based on the final image.

7. The AR auto show display method according to claim 2, characterized in that, The method further includes: If a viewing instruction for a vehicle to be visited is received from the terminal of the target visitor, the vehicle part corresponding to the viewing instruction is determined as the part to be viewed. If the target image exists in the portraits of each key visitor corresponding to the key vehicle part, the corresponding key vehicle part is determined as the target vehicle part. Determine at least one adjustable display view that includes the part to be viewed in the display area, calculate the fourth product of the first weight of the target vehicle part included in the display area of ​​a single adjustable display view and the second weight of the corresponding target image, and sum the fourth products to obtain the corresponding sum of the fourth products. Select the largest sum of fourth products from the sums of all the fourth products, determine the display view to be adjusted corresponding to the largest sum of fourth products as the second display view, and adjust the first display view to the second display view.

8. An AR auto show display device, characterized in that, include: The information acquisition module (11) is used to acquire the target profile and the vehicle to be visited corresponding to the target visitors, wherein the vehicle to be visited is the exhibited vehicle selected by the target visitors in the online auto show; The perspective determination module (12) is used to determine the first display perspective of the vehicle to be visited based on the target profile, the key vehicle parts of the vehicle on display in the online auto show that are easy to visit, and the corresponding profile of at least one key visitor. The profile of the key visitor is a profile of a visitor who is easy to visit the corresponding key vehicle parts. The first display module (13) is used to display the vehicle to be visited in the terminal of the target visitor through a preset AR frame according to the first display perspective. The second display module (14) is used to determine at least one vehicle of interest of the target visitor when the vehicle selected by the target visitor is not obtained, and to display the vehicle on the terminal based on the vehicle of interest.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is loaded and executed by the processor, it implements the method of any one of claims 1-7.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that, When the processor loads and executes the computer program, it implements the method of any one of claims 1-7.

Images