A method, apparatus and device for recommending a car-mounted system wallpaper

Abstract

The application discloses a kind of vehicle-mounted system wallpaper recommendation method, device and equipment, the method comprises: the driving scene data of target vehicle in current driving scene is collected;Driving scene data includes environment acquisition image, image acquisition geographic position and image acquisition time;Environment acquisition image, image acquisition geographic position and image acquisition time are associated with the wallpaper image of the wallpaper database in multiple candidate wallpapers, wallpaper acquisition geographic position and wallpaper acquisition time are matched, and the correlation degree of driving scene data and candidate wallpaper is obtained;Based on the correlation degree of driving scene data and multiple candidate wallpapers, determine the target wallpaper adapted to current driving scene from multiple candidate wallpapers.The application obtains driving scene data, and calculates the correlation degree between driving scene data and multiple candidate wallpapers, so as to determine the highest picture as the target wallpaper, which can improve the correlation between wallpaper recommendation and driving scene, and enrich user experience.

Description

Technical Field

[0001] This invention relates to the field of intelligent vehicle technology, specifically to a method, apparatus, and device for recommending wallpapers for in-vehicle systems. Background Technology

[0002] With the development of internet technology, the variety and quantity of wallpapers for in-vehicle systems have also increased. Although users can choose any wallpaper they like, the sheer number makes it increasingly difficult to find one that best matches the scene. Using the same wallpaper repeatedly can lead to aesthetic fatigue, creating a demand for changing desktop wallpapers. This has led to the emergence of numerous wallpaper recommendation systems. However, existing systems primarily recommend wallpapers that have been downloaded frequently or recently updated, lacking relevance to the scenery, location, and time of the vehicle's journey. This results in monotony and poor interactivity and user experience. Summary of the Invention

[0003] In view of the above-mentioned deficiencies of the prior art, the technical problem to be solved by the present invention is how to improve the correlation between the driving process and the in-vehicle system wallpaper, and enrich the user experience.

[0004] To address at least one of the aforementioned technical problems, this invention discloses a method, apparatus, and device for recommending in-vehicle system wallpapers.

[0005] According to one aspect of this disclosure, a method for recommending wallpapers for an in-vehicle system is provided, comprising:

[0006] Collect driving scenario data of the target vehicle in the current driving scenario; the driving scenario data includes environmental images, image acquisition geographical location, and image acquisition time.

[0007] The environmental image, the geographical location of the image acquisition, and the image acquisition time are matched with the wallpaper images, wallpaper acquisition geographical locations, and wallpaper acquisition times of multiple candidate wallpapers in the wallpaper database according to the corresponding dimensions to obtain the correlation degree between the driving scene data and the multiple candidate wallpapers;

[0008] Based on the correlation between the driving scene data and the multiple candidate wallpapers, a target wallpaper that is suitable for the current driving scene is determined from the multiple candidate wallpapers.

[0009] In some possible embodiments, the step of performing corresponding dimension-based association matching between the environmental image, the image acquisition location, and the image acquisition time, and multiple candidate wallpapers in the wallpaper database, to obtain the correlation degree between the driving scene data and the multiple candidate wallpapers, includes:

[0010] Based on the environmental images and the wallpaper images, a correlation detection is performed to determine the image correlation.

[0011] Geographic location matching is performed based on the geographic location of the image acquisition and the geographic location of the wallpaper acquisition to determine the location correlation.

[0012] Based on the image acquisition time and the wallpaper acquisition time, acquisition time matching is performed to determine the time correlation.

[0013] The correlation between the driving scene data and the multiple candidate wallpapers is obtained by performing correlation matching based on the image correlation, the location correlation, and the time correlation.

[0014] In some possible embodiments, the association matching based on the image correlation, the location correlation, and the time correlation to obtain the correlation between the driving scene data and the multiple candidate wallpapers includes:

[0015] Obtain image association weights, location association weights, and time association weights;

[0016] The correlation between the driving data scene and the candidate wallpaper is obtained by performing a weighted summation based on the image correlation degree and the image correlation weight, the location correlation degree and the location correlation weight, and the time correlation degree and the time correlation weight.

[0017] In some possible embodiments, the step of performing correlation detection based on the environmentally acquired image and the wallpaper image to determine the image correlation includes:

[0018] Determine the image features in the acquired environmental images;

[0019] Feature matching is performed on the image features and the wallpaper image to obtain feature matching results;

[0020] Based on the feature matching results, an image to be associated is determined from the multiple candidate wallpaper images; the image to be associated is an image containing the image features and / or an image containing associated image features related to the image features;

[0021] The image correlation degree is determined based on the image to be associated and the environmental acquisition image.

[0022] In some possible embodiments, the step of performing geographic location matching based on the geographic location of the image acquisition and the geographic location of the wallpaper acquisition to determine the location correlation includes:

[0023] The location recognition range is determined based on a preset distance and the geographic location of the image acquisition.

[0024] Based on the location identification range and the geographical location of the wallpaper collection, a geographical location matching is performed to obtain the location matching result;

[0025] When the location matching result indicates that the geographical location of the wallpaper collection is within the location identification range, the location correlation is determined.

[0026] In some possible embodiments, the step of matching the acquisition time based on the image acquisition time and the wallpaper acquisition time to determine the time correlation includes:

[0027] The time recognition range is determined based on the preset time and the image acquisition time.

[0028] Based on the time recognition range and the wallpaper acquisition time, the acquisition time is matched to obtain the time matching result;

[0029] When the time matching result indicates that the wallpaper acquisition time is within the time identification range, the time correlation is determined.

[0030] In some possible embodiments, determining the target wallpaper that matches the current driving scenario from the multiple candidate wallpapers based on the correlation between the driving scenario data and the multiple candidate wallpapers includes:

[0031] Determine the highest correlation value among the multiple candidate wallpapers;

[0032] When the highest correlation value corresponds to multiple candidate wallpapers, obtain the image correlation degree corresponding to each of the multiple candidate wallpapers;

[0033] The candidate wallpaper with the highest image correlation score among the multiple candidate wallpapers is the target wallpaper.

[0034] According to a second aspect of this disclosure, a device for recommending wallpapers for an in-vehicle system is provided, the device comprising:

[0035] The data acquisition module is used to collect driving scenario data of the target vehicle in the current driving scenario; the driving scenario data includes environmental images, image acquisition geographical location, and image acquisition time;

[0036] The image association module is used to perform corresponding dimension association matching between the environmental image, the geographical location of the image acquisition, and the image acquisition time, and the wallpaper image, the geographical location of the wallpaper acquisition, and the wallpaper acquisition time of multiple candidate wallpapers in the wallpaper database, so as to obtain the association degree between the environmental image and the multiple candidate wallpapers;

[0037] The wallpaper determination module is used to determine a target wallpaper that is suitable for the current driving scenario from the multiple candidate wallpapers based on the correlation between the environmental acquisition image and the multiple candidate wallpapers.

[0038] According to a third aspect of this disclosure, an electronic device is provided, the device including a processor and a memory, the memory storing at least one instruction and at least one program, the at least one instruction and the at least one program being loaded and executed by the processor to implement the recommended method for in-vehicle system wallpaper as described above.

[0039] According to a fourth aspect of this disclosure, a computer storage medium is provided that stores at least one instruction and at least one program, the at least one instruction and the at least one program being loaded and executed by a processor to implement the recommended method for in-vehicle system wallpaper as described above.

[0040] Implementing this invention has the following beneficial effects:

[0041] In this invention, by acquiring driving scene data under the current driving scenario, the real-time nature of data acquisition can be guaranteed. Based on the environmental images, acquisition geographical location, and image acquisition time in the driving scene data, association matching can be performed with multiple candidate wallpapers in the wallpaper database to establish a connection between the in-vehicle system wallpaper and the driving scenario, thereby enriching the user experience. Based on the correlation, the target wallpaper is determined from multiple candidate wallpapers, and the candidate wallpaper with the highest correlation is determined as the target wallpaper, which can improve the correlation between the current driving scenario and the in-vehicle system wallpaper, as well as the adaptability between the in-vehicle system wallpaper and the current driving scenario. Attached Figure Description

[0042] To more clearly illustrate the technical solution of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 A flowchart illustrating the method for recommending in-vehicle system wallpapers provided in this embodiment of the invention;

[0044] Figure 2 A flowchart illustrating the process of determining the correlation degree provided in this embodiment of the invention;

[0045] Figure 3 This is a flowchart illustrating the correlation calculation process provided in an embodiment of the present invention.

[0046] Figure 4This is a schematic diagram of the process for determining image correlation degree provided in an embodiment of the present invention;

[0047] Figure 5 This is a flowchart illustrating the process of determining the location correlation degree in an embodiment of the present invention.

[0048] Figure 6 A flowchart illustrating the determination of time correlation degree provided in this embodiment of the invention;

[0049] Figure 7 This is a schematic diagram illustrating the process of determining the target wallpaper according to an embodiment of the present invention.

[0050] Figure 8 A schematic diagram of the structure of the device for recommending in-vehicle system wallpapers provided in an embodiment of the present invention. Detailed Implementation

[0051] 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 specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0052] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises 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 such processes, methods, products, or devices.

[0053] Various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0054] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0055] In this document, 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 three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0056] Furthermore, to better illustrate this disclosure, numerous specific details are set forth in the following detailed description. Those skilled in the art will understand that this disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art have not been described in detail in order to highlight the main points of this disclosure.

[0057] Figure 1 This diagram illustrates a flowchart of the method for recommending in-vehicle system wallpapers provided in an embodiment of the present invention. The executing entity can be a vehicle body processor capable of implementing the method for recommending in-vehicle system wallpapers, or a vehicle equipped with a vehicle body processor capable of implementing the method for recommending in-vehicle system wallpapers. Please refer to [link to relevant documentation]. Figure 1 A recommended method for selecting wallpapers for in-vehicle systems includes:

[0058] Step S101: Collect driving scenario data of the target vehicle in the current driving scenario; the driving scenario data includes environmental images, image acquisition geographical location, and image acquisition time;

[0059] In one feasible embodiment, the driving scenario data can be data corresponding to the target vehicle in the current driving scenario. The driving scenario data may include environmental images, image acquisition geographic location, and image acquisition time, both of which correspond to the environmental images. The environmental images can be acquired through a dashcam, recording video and audio images of the vehicle's exterior throughout the entire driving process. The image acquisition geographic location may include the location of the target vehicle at the time the environmental images were acquired, and can be GPS (Global Positioning System) data. The image acquisition time may include the time information at the time the environmental images were acquired.

[0060] Step S102: The environmental image, image acquisition location, and image acquisition time are matched with the wallpaper images, wallpaper acquisition locations, and wallpaper acquisition times of multiple candidate wallpapers in the wallpaper database according to the corresponding dimensions to obtain the correlation degree between the driving scene data and the multiple candidate wallpapers;

[0061] In one specific embodiment, in order to establish the association between the in-vehicle system wallpaper and the current driving scene, the acquired driving scene data, namely the environmental acquisition image, the image acquisition geographical location, and the image acquisition time, can be associated and matched with multiple candidate wallpapers in the wallpaper database to determine the degree of association between the current driving scene and each candidate wallpaper in the wallpaper database.

[0062] Step S103: Based on the correlation between the driving scene data and the multiple candidate wallpapers, determine the target wallpaper that is compatible with the current driving scene from the multiple candidate wallpapers.

[0063] In one specific embodiment, the candidate wallpaper with the highest relevance in the wallpaper database is selected as the target wallpaper based on the numerical value of the relevance.

[0064] In this embodiment of the invention, by acquiring driving scene data under the current driving scenario, the real-time nature of data acquisition can be guaranteed; based on the environmental images, acquisition geographical location, and image acquisition time in the driving scene data, and by associating and matching with multiple candidate wallpapers in the wallpaper database, an association between the in-vehicle system wallpaper and the driving scenario can be established, thereby enriching the user experience; based on the correlation, the target wallpaper is determined from multiple candidate wallpapers, and the candidate wallpaper with the highest correlation is determined as the target wallpaper, which can improve the correlation between the current driving scenario and the in-vehicle system wallpaper, as well as the adaptability between the in-vehicle system wallpaper and the current driving scenario.

[0065] Figure 2 This diagram illustrates the process for determining the correlation degree provided in an embodiment of the present invention, such as... Figure 2 As shown, the process of performing corresponding dimension-based correlation matching between the environmental image, the image acquisition location, and the image acquisition time, and multiple candidate wallpapers in the wallpaper database, to obtain the correlation degree between the driving scene data and the multiple candidate wallpapers, includes:

[0066] Step S201: Based on the environmental image and the wallpaper image, perform correlation detection to determine the image correlation.

[0067] In a feasible embodiment, the image correlation degree can be represented by S, which has a value range of 0-1. The image correlation degree is used to characterize the similarity between the environmentally captured image and the wallpaper image, as well as the correlation between the environmentally captured image and the wallpaper image.

[0068] Step S202: Perform geographic location matching based on the geographic location of the image acquisition and the geographic location of the wallpaper acquisition to determine the location correlation.

[0069] In a specific embodiment, the location correlation degree can be represented by G, with a value range of 0-1. The location correlation degree is used to characterize whether the geographical location of the wallpaper acquisition is within the location recognition range of the geographical location of the image acquisition; the location recognition range can be determined according to the geographical location of the image acquisition.

[0070] Step S203: Based on the image acquisition time and the wallpaper acquisition time, perform acquisition time matching to determine the time correlation.

[0071] In a specific embodiment, the time correlation degree can be represented by T, with a value range of 0-1. The time correlation degree is used to characterize whether the wallpaper acquisition time is within the time recognition range of the image acquisition time; the time recognition range can be determined according to the image acquisition time.

[0072] Step S204: Perform association matching based on the image correlation, the location correlation, and the time correlation to obtain the correlation between the driving scene data and the multiple candidate wallpapers.

[0073] In a specific embodiment, the correlation degree can be represented by P. For a candidate wallpaper, correlation matching is performed by combining image correlation degree, location correlation degree, and time correlation degree to determine the correlation degree between this candidate wallpaper and the driving scene data corresponding to the current driving scene. Furthermore, it is necessary to determine the correlation degree of each candidate wallpaper in the wallpaper database.

[0074] Specifically, the wallpaper database contains three wallpaper images: Wallpaper 1, Wallpaper 2, and Wallpaper 3. Based on the environmentally captured images, the image correlation degree between the environmentally captured images and Wallpaper 1 is calculated as S1, the positional correlation degree as G1, and the temporal correlation degree as T1; the image correlation degree between the environmentally captured images and Wallpaper 2 is S2, the positional correlation degree as G2, and the temporal correlation degree as T2; the image correlation degree between the environmentally captured images and Wallpaper 3 is S3, the positional correlation degree as G3, and the temporal correlation degree as T3. Based on T1, S1, and G1, the correlation degree P1 between Wallpaper 1 and the environmentally captured images is determined; based on T2, S2, and G2, the correlation degree P2 between Wallpaper 2 and the environmentally captured images is determined; and based on T3, S3, and G3, the correlation degree P3 between Wallpaper 3 and the environmentally captured images is determined. In other words, for each wallpaper in the wallpaper database, its correlation degree with the environmentally captured images is calculated separately.

[0075] In this embodiment of the invention, the correlation between each wallpaper image and the environmentally captured image is determined by calculating the image correlation, temporal correlation, and location correlation between each wallpaper image and the environmentally captured image. Combining multiple conditions to determine the correlation can improve the accuracy and richness of the correlation determination.

[0076] Figure 3This diagram illustrates the flowchart for correlation calculation provided in an embodiment of the present invention; for example... Figure 3 As shown, the association matching based on the image correlation, the location correlation, and the time correlation to obtain the correlation between the driving scene data and the multiple candidate wallpapers includes:

[0077] Step S301: Obtain image association weights, location association weights, and time association weights;

[0078] In one specific embodiment, to calculate the correlation degree P, the image correlation degree S, the location correlation degree G, and the time correlation degree T need to be weighted to obtain the image correlation weight K1, the location correlation weight K2, and the time correlation weight K3, respectively; wherein the image correlation weight K1 > the location correlation weight K2 > the time correlation weight K3. In one specific embodiment, K1 can be 10, K2 can be 5, and K3 can be 2.

[0079] Step S302: Perform a weighted summation based on the image correlation degree and the image correlation weight, the location correlation degree and the location correlation weight, and the time correlation degree and the time correlation weight to obtain the correlation degree between the driving data scene and the candidate wallpaper.

[0080] In one specific embodiment, the relevance P of the candidate wallpaper is obtained by weighted summation of image relevance, location relevance, and time relevance. The relevance P of the candidate wallpaper is calculated as follows: Image Relevance Weight K1 * Image Relevance S + Location Relevance Weight K2 * Location Relevance G + Time Relevance Weight K3 * Time Relevance T, i.e., P = K1 * S + K2 * G + K3 * T. In one specific embodiment, P = 10 * S + 5 * G + 2 * T.

[0081] In this embodiment of the invention, the correlation between each candidate wallpaper and the current driving scenario is calculated based on the image correlation, location correlation, and time correlation between the environmental acquisition image and each candidate wallpaper, according to the different weights of these three factors. This can optimize the correlation between wallpaper recommendations and the current driving scenario.

[0082] Figure 4 This diagram illustrates the process for determining image correlation according to an embodiment of the present invention; for example... Figure 4 As shown, the process of determining image correlation based on the environmental images and the wallpaper images includes:

[0083] Step S401: Determine the image features in the acquired environmental images;

[0084] In a specific embodiment, image features may include any features that can characterize image information, such as weather features, natural landscape features, architectural features, and road sign features; correlation detection may include correlation detection and similarity detection, wherein similarity detection refers to detecting whether the image features contained in the environmentally acquired image and the image features contained in the wallpaper image are similar and / or the same; correlation detection refers to detecting whether there is a correlation between the image features contained in the environmentally acquired image and the image features contained in the wallpaper image.

[0085] Step S402: Perform feature matching on the image features and the wallpaper image to obtain the feature matching result;

[0086] In one specific embodiment, a wallpaper image is retrieved from a wallpaper database and its image features are determined. The image features of the environmentally captured image and the image features of the wallpaper image are then matched against each type of feature information to determine whether the wallpaper image is related to or similar to the environmentally captured image. Furthermore, feature matching is performed on each wallpaper image in the wallpaper database, resulting in multiple feature matching results.

[0087] Step S403: Based on the feature matching results, determine the image to be associated from the multiple candidate wallpaper images; the image to be associated is an image containing the image features and / or an image containing associated image features related to the image features;

[0088] In one specific embodiment, based on the feature matching results, an image to be associated is determined from multiple candidate wallpaper images, and its image correlation degree is calculated. The image to be associated is a candidate wallpaper image that has at least one image feature that is related to and / or similar to the image feature of the environmental acquisition image. For candidate wallpaper images that do not have image features that are related to and / or similar to the image feature of the environmental acquisition image, their image correlation degree is directly determined to be 0, without the need to calculate the image correlation degree, which can save computing resources and improve the calculation efficiency of image correlation degree.

[0089] The images to be associated can be candidate wallpaper images containing image features of environmental data collection, or candidate wallpaper images containing image features related to environmental data collection. This can further improve the association between driving scenarios and wallpaper recommendations and avoid deviations in image association calculation results due to different image features.

[0090] Specifically, image recognition is performed on images of the current environment to determine image features. Based on these features, image identifiers are determined in the images of the current environment. Based on these image identifiers, candidate wallpapers with the same and / or related image identifiers can be identified from the wallpaper database. Among these, image identifiers can be image features that can identify the image landscape, such as landmark buildings, natural landscapes, and road facilities. Related image identifiers are image identifiers that are different from image identifiers but are related to them. For example, if image identifier 1 is Nanjing University and image identifier 2 is Nanjing City Library, then image identifier 2 is a related image identifier relative to image identifier 1.

[0091] Step S404: Determine the image correlation degree based on the image to be associated and the environmental acquisition image.

[0092] In one specific embodiment, image similarity can be calculated using any method capable of determining image similarity, such as cosine similarity, hash algorithms, structural similarity metrics, or deep learning. Image similarity calculation is existing technology and will not be elaborated upon in this invention. Image correlation can be determined by analyzing the information contained in image features. The information contained in the image features of the environmental data collection is compared with the information contained in the image features of the candidate wallpaper image, combined with the image similarity calculation results, to determine whether there is a correlation between the two images.

[0093] Specifically, there are environmental image a, candidate wallpaper image b, candidate wallpaper image c, and candidate wallpaper image d. Candidate wallpaper image b contains the image features a1 - sunny day, a2 - Oriental Pearl Tower; candidate wallpaper image b contains the image features b1 - cloudy day, b2 - Jin Mao Tower; candidate wallpaper image c contains the image features c1 - Oriental Pearl Tower, c2 - Huangpu River; and candidate wallpaper image d contains the image features d1 - cloudy day, d2 - Nanjing University. Based on the image feature information, the image features of candidate wallpaper image d are completely unrelated to those of environmental image a, therefore its image correlation is directly determined to be 0. Candidate wallpaper images b and c are then identified as images to be associated.

[0094] For candidate wallpaper image b, image feature b1 does not match image feature a1. Although image feature b2 is different from image feature a2, since a2 and b2 are both located near the Bund, it can be determined that candidate wallpaper image b is related to the environmental image a. The similarity is further calculated using the image similarity algorithm, and the similarity is determined as the image correlation degree between a and b. For candidate wallpaper image c, it can be determined that image feature c1 is the same as image feature a2, and image feature c2 is related to image feature a2.

[0095] In this embodiment of the invention, calculating image relevance can determine the association between the current driving scene and candidate wallpaper images, which can improve the intuitiveness of the relevance determination when making wallpaper recommendations. For candidate wallpaper images, it is possible to identify whether they are the same as the environmental images and analyze whether they are related to the environmental images, which can improve the diversity and richness of wallpaper recommendations.

[0096] Figure 5 This diagram illustrates the flow chart for determining the location correlation degree provided in an embodiment of the present invention; for example... Figure 5 As shown, the step of performing geographic location matching based on the geographic location of the image acquisition and the geographic location of the wallpaper acquisition to determine the location correlation includes:

[0097] Step S501: Determine the location recognition range based on the preset distance and the geographical location of the image acquisition;

[0098] In a specific embodiment, the preset distance can be determined based on the image acquisition geographic location corresponding to the current driving scenario and the image acquisition geographic location corresponding to the historical driving scenario. The time interval between the acquisition time of the historical driving scenario and the acquisition time of the current driving scenario is a preset time. The preset distance is calculated based on the image acquisition geographic location corresponding to the historical driving scenario and the image acquisition geographic location corresponding to the current driving scenario. Further, the location recognition range is determined with the image acquisition geographic location as the center and the preset distance as the radius.

[0099] Step S502: Perform location matching based on the location identification range and the location of the wallpaper collection to obtain the location matching result;

[0100] In one specific embodiment, the location matching result can be obtained by determining whether the geographical location of the wallpaper collection is within the location identification range. For wallpaper collection geographical locations that are within the location identification range, their location correlation is calculated; for wallpaper collection geographical locations that are not within the location identification range, their location correlation is directly determined to be 0.

[0101] Step S503: If the location matching result indicates that the geographical location of the wallpaper collection is within the location identification range, determine the location correlation degree.

[0102] In a specific embodiment, the location correlation can be calculated based on the relative position of the wallpaper collection location within the location recognition range. Within the location recognition range, the closer the wallpaper collection location is to the image collection location, the higher its corresponding location correlation, and vice versa.

[0103] Specifically, a coordinate system can be established with the image acquisition location as the origin and a preset distance as the radius R. The resulting circle represents the location recognition range. When the wallpaper acquisition location is within the circle, the distance L1 from it to the origin is calculated, and the location correlation is obtained by calculating the value of R / L1. The location correlation can also be achieved using any other method capable of determining the relative position between the image acquisition location and the wallpaper acquisition location; this embodiment of the invention does not impose any limitations on this.

[0104] In this embodiment of the invention, establishing a location recognition range based on a preset distance and the geographical location of image acquisition can improve the accuracy and real-time performance of location correlation determination.

[0105] Figure 6 This diagram illustrates the flow chart corresponding to the time correlation provided in the embodiments of the present invention; for example... Figure 6 As shown, the step of matching the acquisition time based on the image acquisition time and the wallpaper acquisition time to determine the time correlation includes:

[0106] Step S601: Determine the time recognition range based on the preset time and the image acquisition time;

[0107] In a specific embodiment, the preset time is the same as the time corresponding to the preset distance. The preset time can be determined based on the target vehicle's driving speed and the data acquisition distance. The data acquisition distance represents the driving distance interval during which the target vehicle acquires driving scene data. The data acquisition distance can be 20km or can be customized by the user. The time recognition range is [image acquisition time - preset time, image acquisition time + preset time]. For example, if the preset time is 10 minutes and the image acquisition time is 14:30, then the time recognition range is 14:20-14:40.

[0108] Step S602: Based on the time recognition range and the wallpaper acquisition time, perform acquisition time matching to obtain time matching results;

[0109] In one specific embodiment, the time matching result is obtained by determining whether the wallpaper collection time falls within the time identification range. For wallpaper collection times that fall within the time identification range, their time correlation is calculated; for wallpaper collection times that do not fall within the time identification range, their time correlation is directly determined to be 0.

[0110] Step S603: If the time matching result indicates that the wallpaper acquisition time is within the time identification range, determine the time correlation degree.

[0111] In a specific embodiment, the calculation of time correlation can be determined based on the relative position of the wallpaper acquisition time within the time recognition range; within the time recognition range, the closer the wallpaper acquisition time is to the image acquisition time, the higher its corresponding time correlation, and vice versa.

[0112] Specifically, a coordinate axis can be established with the image acquisition time as the origin, and 'image acquisition time - preset time' and 'image acquisition time + preset time' as the two endpoints. The resulting line segment interval is the time recognition range, and the distance from the origin to one endpoint is T. When the wallpaper acquisition time is within the line segment interval, its distance to the origin is calculated, and the time correlation is obtained by calculating the value of T / L2. The time correlation can also be achieved using any other method that can determine the relative position between the image acquisition time and the wallpaper acquisition time; this embodiment of the invention does not impose any limitations on this.

[0113] In this embodiment of the invention, establishing a time recognition range based on a preset time and an image acquisition time can improve the accuracy and real-time performance of determining time correlation.

[0114] Figure 7 This diagram illustrates the process for determining the target wallpaper according to an embodiment of the present invention; for example... Figure 7 As shown, the step of determining a target wallpaper that matches the current driving scenario from the multiple candidate wallpapers based on the correlation between the driving scenario data and the multiple candidate wallpapers includes:

[0115] Step S701: Determine the highest correlation value among the multiple candidate wallpapers;

[0116] In one specific embodiment, after obtaining the relevance P of each candidate wallpaper in the wallpaper database, each relevance P can be sorted from largest to smallest to obtain the highest relevance value P. max Alternatively, a ranking algorithm can be used to directly determine the highest correlation value P from multiple correlation values ​​P. max .

[0117] Step S702: When the highest correlation value corresponds to multiple candidate wallpapers, obtain the image correlation degree corresponding to each of the multiple candidate wallpapers;

[0118] In a specific embodiment, if the highest correlation value P max There are multiple candidate wallpapers. The image correlation scores for each candidate wallpaper are obtained, and the candidate wallpaper with the highest image correlation score is selected as the target wallpaper. If the highest correlation score P... max The corresponding number of candidate wallpapers is one, which is directly selected as the target wallpaper.

[0119] Step S703: Determine the candidate wallpaper with the highest image correlation among the multiple candidate wallpapers as the target wallpaper.

[0120] In a specific embodiment, if the obtained image correlation scores are all equal, then the location correlation score is obtained, and the candidate wallpaper corresponding to the maximum location correlation score is selected as the target wallpaper; if the location correlation scores are also equal, then the time correlation score is obtained, and the candidate wallpaper corresponding to the maximum time correlation score is selected as the target wallpaper; if the correlation score, image correlation score, location correlation score, and time correlation score are all equal, then multiple candidate wallpapers can be displayed for the user to select a target wallpaper, or multiple candidate wallpapers can be determined as the target wallpaper and played in a scrolling manner within a preset time.

[0121] In this embodiment of the invention, since wallpapers focus on displaying image information, when the relevance is the same, the target wallpaper is first determined from multiple candidate wallpapers with the same relevance based on the image relevance, which can improve the relevance between the target wallpaper and the environmentally captured image; when there are multiple candidate wallpapers with the same relevance in all dimensions, the user selects the target wallpaper, and personalized wallpaper recommendation can be achieved through user interaction with the in-vehicle system; scrolling through multiple wallpaper images can improve the diversity and richness of wallpaper display.

[0122] This invention also provides a device for recommending wallpapers for in-vehicle systems, such as... Figure 8 As shown, the device includes:

[0123] The data acquisition module 810 is used to acquire driving scenario data of the target vehicle in the current driving scenario; the driving scenario data includes environmental acquisition images, image acquisition geographical location, and image acquisition time;

[0124] The image association module 820 is used to perform corresponding dimension association matching between the environmental acquisition image, the image acquisition geographical location, and the image acquisition time, and multiple candidate wallpapers in the wallpaper database, to obtain the association degree between the environmental acquisition image and the multiple candidate wallpapers;

[0125] The wallpaper determination module 830 is used to determine a target wallpaper that is compatible with the current driving scenario from the multiple candidate wallpapers based on the correlation between the environmental acquisition image and the multiple candidate wallpapers.

[0126] In other embodiments, the image association module 820 further includes:

[0127] The first image association determination module is used to perform association degree detection based on the environmental acquired image and the wallpaper image, and determine the image association degree.

[0128] The first location association determination module is used to perform location matching based on the geographic location of the image acquisition and the geographic location of the wallpaper acquisition to determine the location association degree;

[0129] The first-time association determination module is used to match the acquisition time based on the image acquisition time and the wallpaper acquisition time to determine the time association degree.

[0130] The first wallpaper correlation determination module is used to perform correlation matching based on the image correlation, the location correlation, and the time correlation to obtain the correlation between the driving scene data and the multiple candidate wallpapers.

[0131] In other embodiments, the first wallpaper association determination module further includes:

[0132] The weight acquisition module is used to acquire image association weights, location association weights, and time association weights;

[0133] The weighted processing module is used to perform weighted summation processing based on the image correlation degree and the image correlation weight, the location correlation degree and the location correlation weight, and the time correlation degree and the time correlation weight to obtain the correlation degree between the driving data scene and the candidate wallpaper.

[0134] In other embodiments, the first image association determination module includes:

[0135] The feature determination module is used to determine the image features in the environmental acquisition images;

[0136] The feature matching module is used to perform feature matching on the image features and the wallpaper image to obtain the feature matching result;

[0137] An image determination module is used to determine an image to be associated from the plurality of candidate wallpaper images based on the feature matching results; the image to be associated is an image containing the image features and / or an image containing associated image features related to the image features;

[0138] The second image association determination module is used to determine the image association degree based on the image to be associated and the environmental acquisition image.

[0139] In other embodiments, the first location association determination module further includes:

[0140] The first range determination module is used to determine the location recognition range based on a preset distance and the geographical location of the image acquisition.

[0141] The location matching module is used to perform location matching based on the location identification range and the geographical location of the wallpaper collection to obtain the location matching result;

[0142] The second location association determination module determines the location association degree when the location matching result indicates that the geographical location of the wallpaper collection is within the location identification range.

[0143] In other embodiments, the first-time association determination module further includes:

[0144] The second range determination module is used to determine the time recognition range based on a preset time and the image acquisition time.

[0145] The time matching module is used to perform time matching based on the time recognition range and the wallpaper acquisition time to obtain the time matching result;

[0146] The second time association determination module determines the time association degree when the time matching result indicates that the wallpaper collection time is within the time recognition range.

[0147] In other embodiments, the wallpaper determination module 830 further includes:

[0148] An extreme value determination module is used to determine the highest correlation value among the correlations of the multiple candidate wallpapers;

[0149] The third image association determination module is used to obtain the image association degree corresponding to each of the multiple candidate wallpapers when the highest association degree value corresponds to multiple candidate wallpapers;

[0150] The wallpaper filtering module is used to determine the candidate wallpaper with the highest image correlation among the multiple candidate wallpapers as the target wallpaper.

[0151] The apparatus and method embodiments described above are based on the same inventive concept and are used to implement the recommended method for in-vehicle system wallpapers.

[0152] This invention also provides a device for recommending in-vehicle system wallpapers. The device includes a processor and a memory. The memory stores at least one instruction, at least one program, a code set, or an instruction set. The at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the method for recommending in-vehicle system wallpapers as described in any of the method embodiments.

[0153] Embodiments of the present invention also provide a storage medium, which may be disposed in a server to store at least one instruction, at least one program, code set, or instruction set for implementing the method of recommending in-vehicle system wallpapers as described in any of the method embodiments. The at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the method of recommending in-vehicle system wallpapers as described in any of the method embodiments.

[0154] Optionally, in embodiments of the present invention, the storage medium may be located at at least one of a plurality of network servers in a computer network. Optionally, in embodiments of the present invention, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0155] As can be seen from the embodiments provided by the present invention above, by acquiring driving scene data under the current driving scenario, the real-time acquisition of data can be guaranteed; based on the environmental images, acquisition geographical location, and image acquisition time in the driving scene data, and by associating and matching with multiple candidate wallpapers in the wallpaper database, the association between the in-vehicle system wallpaper and the driving scenario can be established, thereby enriching the user experience; based on the correlation, the target wallpaper is determined from multiple candidate wallpapers, and the candidate wallpaper with the highest correlation is determined as the target wallpaper, which can improve the correlation between the current driving scenario and the in-vehicle system wallpaper, as well as the adaptability between the in-vehicle system wallpaper and the current driving scenario.

[0156] It should be noted that the various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical applications, or technological improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method of recommending a car system wallpaper, characterized by, The method comprises: collecting driving scene data of a target vehicle in a current driving scene; the driving scene data comprises an environment collection image, an image collection geographical position, and an image collection time; performing correlation degree detection based on the environment collection image and wallpaper images of multiple candidate wallpapers in a wallpaper database to determine an image correlation degree of each candidate wallpaper; determining a position recognition range based on a preset distance and the image collection geographical position; performing geographical position matching based on the position recognition range and a wallpaper collection geographical position of each candidate wallpaper to determine a position correlation degree of each candidate wallpaper; determining a time recognition range based on a preset time and the image collection time; performing collection time matching based on the time recognition range and a wallpaper collection time of each candidate wallpaper to determine a time correlation degree of each candidate wallpaper; performing correlation matching based on the image correlation degree, the position correlation degree, and the time correlation degree to obtain a correlation degree between the driving scene data and each candidate wallpaper; determining a target wallpaper that is suitable for the current driving scene from the multiple candidate wallpapers based on the correlation degrees between the driving scene data and the multiple candidate wallpapers. The preset time is determined based on a driving speed of the target vehicle and a data acquisition distance, and the data acquisition distance represents a driving distance interval at which the target vehicle acquires driving scene data during driving; and the preset distance is determined based on the image collection geographical position and historical image collection geographical positions corresponding to historical driving scenes, and a time interval between an acquisition time of the historical driving scenes and an acquisition time of the current driving scene is the preset time. 2.The method of claim 1, wherein, The correlation matching based on the image correlation degree, the position correlation degree, and the time correlation degree to obtain a correlation degree between the driving scene data and each candidate wallpaper comprises: obtaining an image correlation weight, a position correlation weight, and a time correlation weight; performing weighted summation processing based on the image correlation degree and the image correlation weight, the position correlation degree and the position correlation weight, and the time correlation degree and the time correlation weight to obtain the correlation degree between the driving scene data and each candidate wallpaper. 3.The method of claim 1, wherein, The correlation degree detection based on the environment collection image and wallpaper images of multiple candidate wallpapers in a wallpaper database to determine an image correlation degree comprises: determining an image feature in the environment collection image; performing feature matching on the image feature and the wallpaper images to obtain a feature matching result; determining a to-be-associated image from the multiple candidate wallpaper images based on the feature matching result; the to-be-associated image is an image containing the image feature and / or an image containing an associated image feature that is associated with the image feature; determining the image correlation degree based on the to-be-associated image and the environment collection image. 4.The method of claim 1, wherein, The geographical position matching based on the position recognition range and a wallpaper collection geographical position of each candidate wallpaper to determine a position correlation degree of each candidate wallpaper comprises: perform geographical position matching based on the position recognition range and the wallpaper collection geographical position of each candidate wallpaper, to obtain a position matching result of each candidate wallpaper; determine the position correlation degree in a case where the position matching result represents that the wallpaper collection geographical position is within the position recognition range. 5.The method of claim 1, wherein, The collection time matching based on the time recognition range and the wallpaper collection time of each candidate wallpaper includes: perform collection time matching based on the time recognition range and the wallpaper collection time of each candidate wallpaper, to obtain a time matching result of each candidate wallpaper; determine the time correlation degree in a case where the time matching result represents that the wallpaper collection time is within the time recognition range. 6.The method of claim 1, wherein, The determining of the target wallpaper from the multiple candidate wallpapers based on the correlation degrees of the driving scene data and the multiple candidate wallpapers includes: determining a highest correlation degree value in the correlation degrees of the multiple candidate wallpapers; in a case where the highest correlation degree value corresponds to multiple candidate wallpapers, obtaining respective image correlation degrees of the multiple candidate wallpapers; determining that a candidate wallpaper corresponding to a maximum image correlation degree in the respective image correlation degrees of the multiple candidate wallpapers is the target wallpaper.

7. A device for recommending a car system wallpaper, characterized by, The apparatus includes: a data collection module configured to collect driving scene data of a target vehicle in a current driving scene, the driving scene data including an environment collection image, an image collection geographical position, and an image collection time; a first image correlation determination module configured to perform correlation degree detection based on the environment collection image and wallpaper images of multiple candidate wallpapers in a wallpaper database, to determine an image correlation degree of each candidate wallpaper; a first position correlation determination module configured to determine a position recognition range based on a preset distance and the image collection geographical position, and perform geographical position matching based on the position recognition range and a wallpaper collection geographical position of each candidate wallpaper, to determine a position correlation degree of each candidate wallpaper; a first time correlation determination module configured to determine a time recognition range based on a preset time and the image collection time, and perform collection time matching based on the time recognition range and a wallpaper collection time of each candidate wallpaper, to determine a time correlation degree of each candidate wallpaper; a first wallpaper correlation degree determination module configured to perform correlation matching based on the image correlation degree, the position correlation degree, and the time correlation degree, to obtain a correlation degree between the driving scene data and each candidate wallpaper; a wallpaper determination module configured to determine a target wallpaper that is adapted to the current driving scene from the multiple candidate wallpapers based on the correlation degree between the environment collection image and the multiple candidate wallpapers. The preset time is determined based on a driving speed of the target vehicle and a data acquisition distance, and the data acquisition distance represents a driving distance interval of the target vehicle for acquiring driving scene data during driving; the preset distance is determined based on the image collection geographic position and a historical image collection geographic position corresponding to a historical driving scene, and a time interval between an acquisition time of the historical driving scene and an acquisition time of the current driving scene is the preset time. 8.An electronic device, comprising a processor and a memory, wherein the memory stores at least one instruction and at least one program, and the at least one instruction and the at least one program are loaded and executed by the processor to implement the method for recommending the wallpaper of the vehicle-mounted system according to any one of claims 1-6. 9.A computer storage medium, wherein the computer storage medium stores at least one instruction and at least one program, and the at least one instruction and the at least one program are loaded and executed by a processor to implement the method for recommending the wallpaper of the vehicle-mounted system according to any one of claims 1-6.

Images