Information pushing method and system for vehicle
By determining the driving scenarios based on real-time information in the vehicle, combined with local and cloud push, the service information delay problem caused by vehicle hardware performance limitations is solved, and fast and effective service information push is achieved, improving user experience and network Independence.
Patent Information
- Application Number
- CN202310519857.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-08
- Publication Date
- 2024-11-08
AI Technical Summary
In the prior art, due to vehicle hardware performance limitations, data upload time to cloud servers for calculation and processing is long, resulting in delayed service information push, which cannot meet the real-time requirements of certain scenarios, affecting the effect of service information push and user experience. , especially when the network environment is poor.
By determining whether to identify driving scenarios locally or in the cloud based on real-time information in the vehicle, and determining the push method based on the timeliness of information push, and working together to meet users' travel needs based on the characteristics of locally and cloud-based push.
It realizes the rapid push of service information in scenarios with high real-time requirements, improves the effectiveness and efficiency of user experience and service information push, reduces the dependence on the network, and ensures that timely services can still be provided when the network environment is poor. information.
Smart Images

Figure CN118921401A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of information technology, and in particular to a method and system for pushing information for a vehicle. Background Art
[0002] With the development of science and technology and the progress of urbanization, the number of vehicles has increased rapidly and road conditions have become more complicated. In recent years, with the rapid development of automobile intelligence and networking, vehicles have gradually evolved from traditional means of transportation to smart cockpits that can provide rich travel services.
[0003] At present, due to the limitations of vehicle hardware performance, for example, the vehicle's processor has limited computing power and limited storage space, cloud servers generally make judgments and processes based on vehicle data, generate service information, and push it to the vehicle.
[0004] It should be noted that the above introduction to the technical background is only for the convenience of providing a clear and complete description of the technical solutions of the present invention and for the convenience of understanding by those skilled in the art. It cannot be considered that the above technical solutions are well known to those skilled in the art simply because these solutions are described in the background technology section of the present invention. Summary of the invention
[0005] However, since the data is uploaded to the cloud server, calculated and processed by the cloud server, and the service information is generated and then sent to the vehicle, this process takes a long time, resulting in a certain delay in sending the service information through the server. For some scenarios, the real-time requirements for providing services are high. If the service information related to the scenario cannot be displayed to the user in time, the scene is easy to be missed, resulting in the pushed service information not matching the current scenario, affecting the effect and efficiency of the service information push, and reducing the user experience. In addition, the server-based information push mechanism needs to rely on a good network environment. When the network environment is not good, the service information push cannot be provided or will be provided with a delay.
[0006] In order to solve one or more problems in the above-mentioned prior art, the embodiments of the present invention provide a method and system for information push for vehicles, which can flexibly utilize the characteristics of local push and cloud push according to actual conditions, so that local push and cloud push work together to meet the travel needs of users.
[0007] According to a first aspect of an embodiment of the present invention, a method for pushing information for a vehicle is provided, the method comprising: the vehicle determines whether to identify a driving scene locally or in the cloud based on real-time first vehicle information; in the case of determining to identify the driving scene locally, the vehicle identifies the current driving scene based on the real-time first vehicle information, and the vehicle displays first service information corresponding to the identified driving scene through an on-board terminal; and in the case of determining to identify the driving scene in the cloud, the cloud server identifies the current driving scene based on cloud data formed based on second vehicle information, user information and third-party information, and the cloud server sends second service information corresponding to the identified driving scene to the vehicle, and the vehicle displays the second service information through the on-board terminal.
[0008] According to a second aspect of an embodiment of the present invention, the vehicle determines whether to identify a driving scene locally or in the cloud based on real-time first vehicle information, including: the vehicle determines whether a trigger condition for information push is met based on the real-time first vehicle information and using a preset first rule; when the trigger condition for information push is met, the timeliness of the information push is determined based on the first vehicle information and using a preset second rule, and the driving scene is determined whether to be identified locally or in the cloud based on the timeliness of the information push.
[0009] According to a third aspect of an embodiment of the present invention, the contents of the first rule, the second rule, the first service information and the second service information can be updated through a cloud server.
[0010] According to a fourth aspect of an embodiment of the present invention, the first vehicle information includes at least one of vehicle driving information, vehicle terminal operation information, vehicle position information, identification information of an in-vehicle camera, and sensor identification information.
[0011] According to a fifth aspect of an embodiment of the present invention, the cloud data includes regularly updated tag data, real-time second vehicle information, real-time third-party information and user feedback information.
[0012] According to the sixth aspect of an embodiment of the present invention, the label data includes a vehicle portrait label, a user portrait label and a road portrait label, the vehicle portrait label is calculated based on the second vehicle information uploaded cumulatively by the vehicle, the user portrait label is calculated based on the second vehicle information uploaded cumulatively and user information, and the road portrait label is calculated based on the second vehicle information uploaded cumulatively and third-party information.
[0013] According to a seventh aspect of an embodiment of the present invention, the cloud server identifies the current driving scene based on cloud data formed based on second vehicle information, user information and third-party information, including: the cloud server determines the current driving scene based on the periodically updated label data, real-time second vehicle information, real-time third-party information and user feedback information, and uses a preset third rule or a trained model, the third rule includes an identification rule and a filtering rule, the identification rule includes determining a candidate driving scene based on the periodically updated label data, real-time second vehicle information and real-time third-party information, and the filtering rule includes determining whether to use the candidate driving scene as an identified driving scene based on the user feedback information.
[0014] According to the eighth aspect of an embodiment of the present invention, the second vehicle information includes at least one of vehicle status information, vehicle fault information, vehicle driving information and vehicle location information; the user information includes at least one of user behavior information, user purchase record and user basic information; the third-party information includes at least one of weather information and POI information.
[0015] According to a ninth aspect of an embodiment of the present invention, when multiple driving scenes are identified, the driving scene with the highest priority among the multiple driving scenes is taken as the final driving scene.
[0016] According to a tenth aspect of an embodiment of the present invention, the vehicle displays a screen including the first service information or the second service information through a vehicle-mounted terminal, and / or voice broadcasts the content of the first service information or the second service information.
[0017] According to an eleventh aspect of an embodiment of the present invention, there is provided an information push system for a vehicle, the system comprising a vehicle system and a cloud server arranged in the vehicle, the vehicle system determining whether to identify a driving scene locally or in the cloud based on real-time first vehicle information; in the case of determining to identify a driving scene locally, the vehicle system identifies the current driving scene based on the real-time first vehicle information, and the vehicle system displays first service information corresponding to the identified driving scene through a vehicle-mounted terminal; in the case of determining to identify a driving scene in the cloud, the vehicle system sends an instruction to identify the driving scene in the cloud to the cloud server; after receiving the instruction, the cloud server identifies the current driving scene based on cloud data formed based on second vehicle information, user information and third-party information, and the cloud server sends second service information corresponding to the identified driving scene to the vehicle system of the vehicle, and the vehicle displays the second service information through the vehicle-mounted terminal of the vehicle system.
[0018] According to the twelfth aspect of an embodiment of the present invention, the vehicle system includes: a first determination module, which determines whether a trigger condition for information push is met based on real-time first vehicle information and using a preset first rule; a second determination module, which determines the timeliness of the information push based on the first vehicle information and using a preset second rule when the trigger condition for information push is met, and determines whether to identify the driving scene locally or in the cloud based on the timeliness of the information push; a first identification module, which identifies the current driving scene based on the real-time first vehicle information when determining to identify the driving scene locally.
[0019] According to a thirteenth aspect of an embodiment of the present invention, the cloud server includes: a first updating module, which is used to update the content of the first rule, the second rule, the first service information and the second service information.
[0020] According to the fourteenth aspect of an embodiment of the present invention, the first vehicle information includes at least one of vehicle driving information, vehicle terminal operation information, vehicle position information, identification information of an in-vehicle camera, and sensor identification information.
[0021] According to a fifteenth aspect of an embodiment of the present invention, the cloud data includes regularly updated tag data, real-time second vehicle information, real-time third-party information and user feedback information.
[0022] According to the sixteenth aspect of an embodiment of the present invention, wherein the label data includes a vehicle portrait label, a user portrait label and a road portrait label, the cloud server includes: a data acquisition and processing module, which acquires uploaded second vehicle information, user information and third-party information; a calculation module, which calculates and outputs the vehicle portrait label based on the second vehicle information cumulatively uploaded by the vehicle; and, calculates and outputs the user portrait label based on the cumulatively uploaded second vehicle information and user information; and, calculates and outputs the road portrait label based on the cumulatively uploaded second vehicle information and third-party information; a storage module, which stores the vehicle portrait label, the user portrait label and the road portrait label; and a second update module, which updates the vehicle portrait label, the user portrait label and the road portrait label.
[0023] According to the seventeenth aspect of an embodiment of the present invention, the cloud server includes: a second identification module, which determines the current driving scene based on the regularly updated label data, real-time second vehicle information, real-time third-party information and user feedback information, and uses a preset third rule or a trained model, the third rule includes an identification rule and a filtering rule, the identification rule includes determining a candidate driving scene based on the regularly updated label data, real-time second vehicle information and real-time third-party information, and the filtering rule includes determining whether to use the candidate driving scene as an identified driving scene based on the user feedback information.
[0024] According to the eighteenth aspect of an embodiment of the present invention, the second vehicle information includes at least one of vehicle status information, vehicle fault information, vehicle driving information and vehicle location information; the user information includes at least one of user behavior information, user purchase record and user basic information; the third-party information includes at least one of weather information and POI information.
[0025] According to the nineteenth aspect of an embodiment of the present invention, when there are multiple identified driving scenes, the driving scene with the highest priority among the multiple driving scenes is taken as the final driving scene.
[0026] According to the twentieth aspect of the embodiment of the present invention, the vehicle-mounted terminal displays a screen including the first service information or the second service information, and / or the vehicle-mounted terminal voice broadcasts the content of the first service information or the second service information.
[0027] One of the beneficial effects of the embodiments of the present invention is:
[0028] The vehicle determines whether to identify the driving scene locally or in the cloud based on the real-time first vehicle information. When it is determined that the driving scene is to be identified locally, the first vehicle information is used to quickly determine the driving scene and directly display the corresponding service information locally. In this way, in certain scenarios, such as scenarios with high real-time requirements, relevant service information can be quickly pushed, thereby ensuring the effect and efficiency of service information push and improving user experience.
[0029] When it is determined that the driving scene is to be identified in the cloud, the cloud server identifies the driving scene based on the cloud data formed by multiple data and pushes corresponding service information to the vehicle. In this way, in some scenarios, such as scenarios with low real-time requirements, the cloud server can accurately identify the driving scene and push relevant service information after performing relatively complex calculations based on the cloud data, thereby improving the accuracy and richness of the driving scene identification and the push of relevant service information in the scenario;
[0030] Therefore, the respective characteristics of local push and cloud push can be flexibly utilized according to actual conditions, so that local push and cloud push can work together to meet the travel needs of users.
[0031] In addition, the push mechanism that combines local push and cloud push reduces dependence on the network. When the network environment is poor, local push can also be used to meet the needs of certain scenarios, such as the need to quickly provide service information in scenarios with high real-time requirements, thereby ensuring user experience and security.
[0032] Furthermore, when determining whether to identify the driving scene locally or in the cloud, first determine whether the trigger condition for information push is met based on the real-time first vehicle information and the first rule, and if the trigger condition is met, further combine the second rule to determine the timeliness of the information push, and judge whether to identify the driving scene locally or in the cloud based on the timeliness. In this way, service information can be pushed in time at the appropriate time, for example, service information can be pushed in time in scenarios with high timeliness requirements, thereby further improving the effect and efficiency of service information push.
[0033] Furthermore, the contents of the first rule, the second rule, the first service information and the second service information can be updated through the cloud server, so that the identification rules and the contents of the service information can be flexibly adjusted to further improve the effect and efficiency of service information push.
[0034] Furthermore, the first vehicle information includes vehicle driving information, vehicle terminal operation information, vehicle location information, identification information of the in-vehicle camera, and at least one of sensor identification information. In this way, it is possible to combine multiple data to comprehensively determine whether to perform identification locally or in the cloud, and to combine multiple data locally to identify driving scenes, thereby improving the accuracy of identification.
[0035] Furthermore, the cloud data includes regularly updated tag data, real-time second vehicle information, real-time third-party information, and user feedback information. In this way, the cloud data used for scene recognition is processed based on multiple data, which can further improve the accuracy of recognition and the diversity of scenes that can be recognized.
[0036] Furthermore, the label data includes a vehicle portrait label, a user portrait label, and a road portrait label. The vehicle portrait label is calculated based on the second vehicle information uploaded cumulatively by the vehicle, the user portrait label is calculated based on the second vehicle information uploaded cumulatively and user information, and the road portrait label is calculated based on the second vehicle information uploaded cumulatively and third-party information. In this way, the vehicle portrait label, the user portrait label, and the road portrait label respectively represent the vehicle preference characteristics, the user preference characteristics, and the road preference characteristics, which can provide a reliable basis for scene recognition.
[0037] Furthermore, the cloud server uses recognition rules and filtering rules to determine the driving scenario, that is, determines the candidate driving scenario based on the regularly updated tag data, the real-time second vehicle information and the real-time third-party information, and determines whether to use the candidate driving scenario as the identified driving scenario based on the user feedback information. In this way, the user's feeling about the service push can be fully considered to determine whether to continue the push, further improving the effect of the service information push and the user experience.
[0038] Furthermore, the second vehicle information includes at least one of vehicle status information, vehicle fault information, vehicle driving information, and vehicle location information; the user information includes at least one of user behavior information, user purchase records, and user basic information; and the third-party information includes at least one of weather information and POI information. In this way, the cloud can make scene judgments based on richer data, which can further improve the accuracy of recognition and the diversity of scenes that can be recognized.
[0039] Furthermore, when there are multiple identified driving scenes, the driving scene with the highest priority among the multiple driving scenes is used as the final driving scene. In this way, service information can be pushed based on the driving scene with the highest priority, further improving the effect of pushing service information.
[0040] Furthermore, the vehicle displays a screen including the first service information or the second service information through the vehicle-mounted terminal, and / or voice broadcasts the content of the first service information or the second service information, so that the user can quickly understand the content of the service.
[0041] With reference to the following description and accompanying drawings, the embodiments of the present invention are disclosed in detail. It should be understood that the embodiments of the present invention are not limited in scope. Within the spirit and scope of the appended claims, the embodiments of the present invention include many changes, modifications and equivalents.
[0042] Features described and / or illustrated with respect to one embodiment may be used in the same or similar manner in one or more other embodiments, combined with features in other embodiments, or substituted for features in other embodiments.
[0043] It should be emphasized that the terms “include / comprising / having” when used herein refer to the existence of a feature, an integer, or a component, but do not exclude the existence or addition of one or more other features, integers, or components. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] The above and other objects, features and advantages of the embodiments of the present invention will become more apparent from the following detailed description in conjunction with the accompanying drawings, in which:
[0045] Figure 1 is a schematic diagram of an information push method for a vehicle according to Embodiment 1 of the present invention;
[0046] Figure 2 is a schematic diagram of a method for implementing step 101 of embodiment 1 of the present invention;
[0047] Figure 3 is a schematic diagram of the information processing and interaction process of Example 1 of the present invention;
[0048] Figure 4 is a schematic diagram of an information push system for a vehicle according to Embodiment 2 of the present invention;
[0049] Figure 5 is a schematic diagram of a vehicle system according to Embodiment 2 of the present invention;
[0050] Figure 6 is a schematic diagram of a cloud server according to Embodiment 2 of the present invention;
[0051] Figure 7 It is a schematic block diagram of the system structure of the electronic device according to the third embodiment of the present invention. DETAILED DESCRIPTION
[0052] With reference to the accompanying drawings, the above and other features of the present invention will become apparent through the following description. In the description and the accompanying drawings, specific embodiments of the present invention are specifically disclosed, which show some embodiments in which the principles of the present invention can be adopted, and it should be understood that the present invention is not limited to the described embodiments, but includes all modifications and equivalents falling within the scope of the attached claims.
[0053] The information push method for a vehicle according to an embodiment of the present invention is described below with reference to the accompanying drawings.
[0054] Example 1
[0055] Embodiment 1 of the present invention provides an information push method for a vehicle.
[0056] Figure 1 FIG. 1 is a schematic diagram of a method for pushing information to a vehicle according to Embodiment 1 of the present invention. Figure 1 As shown, the method includes:
[0057] Step 101: The vehicle determines to identify a driving scene locally or in the cloud according to real-time first vehicle information;
[0058] Step 102: When it is determined that the driving scene is identified locally, the vehicle identifies the current driving scene according to the real-time first vehicle information, and the vehicle displays first service information corresponding to the identified driving scene through the vehicle terminal; and
[0059] Step 103: When it is determined that the driving scene is identified in the cloud, the cloud server identifies the current driving scene based on the cloud data formed based on the second vehicle information, the user information and the third-party information, and the cloud server sends the second service information corresponding to the identified driving scene to the vehicle, and the vehicle displays the second service information through the vehicle-mounted terminal.
[0060] In some embodiments, the method can be applied to various vehicles.
[0061] The vehicle may be various types of vehicles, for example, a car, an electric car, or a hybrid car; for example, a private car, a public bus, a bus, a van, a truck, a motorcycle, a tour bus, etc.; for example, an unmanned car or an automatic driving car, etc.
[0062] In step 101 , the vehicle determines whether to identify a driving scene locally or in the cloud based on real-time first vehicle information.
[0063] In some embodiments, the first vehicle information includes at least one of vehicle driving information, vehicle terminal operation information, vehicle location information, identification information of an in-vehicle camera, and sensor identification information.
[0064] The sensor is, for example, at least one of a sound sensor, a temperature sensor, and a humidity sensor.
[0065] In this way, it is possible to combine multiple data to comprehensively determine whether to perform identification locally or in the cloud, and to combine multiple data locally to identify driving scenarios, thereby improving recognition accuracy.
[0066] In some embodiments, the driving scene represents various scenes such as the driver state, vehicle state, and vehicle environment, and the type of the driving scene may be pre-set, for example, "high-speed driving", "fatigue driving", "slow driving in congested roads", "slippery roads", etc.
[0067] The following is an exemplary description of the execution process of step 101.
[0068] Figure 2 FIG. 1 is a schematic diagram of a method for implementing step 101 of embodiment 1 of the present invention. Figure 2 As shown, the method includes:
[0069] Step 201: The vehicle determines whether a triggering condition for information push is met based on real-time first vehicle information and using a preset first rule;
[0070] Step 202: When the triggering condition for information push is met, the timeliness of the information push is determined based on the first vehicle information and using a preset second rule, and the driving scene is identified locally or in the cloud based on the timeliness of the information push.
[0071] In this way, service information can be pushed in time at the right time, for example, in a scenario with high timeliness requirements, further improving the effect and efficiency of service information push.
[0072] In addition, when the triggering conditions for information push are not met, the process returns, i.e., no driving scene recognition is performed.
[0073] In some embodiments, the triggering condition for information push is a preset condition, and the first rule is a preset rule. The triggering condition and the first rule can be set according to actual needs.
[0074] For example, the trigger condition includes when the vehicle performs a specific action, such as when the vehicle starts or when the vehicle switches gears; and / or, the trigger condition includes when the driver is in a specific state, such as when the driver is in a fatigued state.
[0075] For example, the first rule includes: when the vehicle performs a specific operation, the trigger condition is met, for example, the trigger condition is met when the vehicle starts, or the trigger condition is met when the vehicle switches gears, or the trigger condition is met when the driver is in a fatigued state.
[0076] In some embodiments, the second rule is a preset rule, and the second rule can be set according to actual needs.
[0077] For example, the second rule includes determining whether the timeliness of information push is high or low when the vehicle data meets a preset condition.
[0078] For example, when the vehicle speed is greater than a first threshold, such as when the vehicle speed is greater than 100 km / h, the timeliness of information push is determined to be high; when the vehicle speed is less than a second threshold, such as when the vehicle speed is less than 10 km / h, the timeliness of information push is determined to be low.
[0079] In some embodiments, timeliness may also be referred to as real-time. For example, timeliness refers to the urgency of information push or the degree of influence of time on the effect of information push.
[0080] In some embodiments, when the timeliness of information push is high, it is determined to identify the driving scene locally, that is, local push is performed; when the timeliness of information push is low, it is determined to identify the driving scene in the cloud, that is, cloud push is performed.
[0081] For example, when a vehicle is traveling at high speed, it is easy to miss the current scene quickly or the possibility of risk increases, and the urgency of information push increases. If the information is not pushed in time, the current scene may be missed, affecting the effect and efficiency of information push. Therefore, when the vehicle is traveling at high speed, the timeliness of information push is high. In this case, by quickly identifying the driving scene locally in the vehicle and pushing service information locally in the vehicle, it is guaranteed that the service information can be pushed in time.
[0082] When the vehicle is just started or driving at a low speed, it is not easy to miss the current scene quickly or the possibility of risk is small. Therefore, a certain delay in information push is allowed, and the timeliness of information push is low. In this case, the driving scene is identified through the cloud and the service information is sent to the vehicle, which improves the accuracy and richness of the driving scene identification and push related service information in this scene.
[0083] When it is determined that the driving scene is identified locally, in step 102, the vehicle identifies the current driving scene based on the real-time first vehicle information, and the vehicle displays first service information corresponding to the identified driving scene through the vehicle-mounted terminal.
[0084] In some embodiments, the pushed first service information corresponds to the identified driving scenario. For example, the first service information corresponding to the driving scenario is stored in the vehicle system. Once the driving scenario is determined, the content of the first service information to be pushed can be directly determined.
[0085] In some embodiments, the vehicle displays a screen including the first service information through a vehicle-mounted terminal, and / or voice broadcasts the content of the first service information, so that the user can quickly understand the content of the service.
[0086] In some embodiments, the screen displayed on the vehicle terminal may be a card screen. In addition, for example, the card screen includes an interactive button, and the user clicks the interactive button to execute a specified action instruction, such as closing the card, jumping to an application in the vehicle terminal, etc., for example, jumping to an application or a start button related to the recommended function.
[0087] For example, if the vehicle recognizes that the current driving scenario is "high-speed driving" based on the current vehicle speed, then the driver will be recommended to turn on relevant driving assistance functions, such as full-speed adaptive cruise control (ACC) and lane keeping (LKAS) functions, for example, through voice broadcast or display on the on-board terminal.
[0088] For example, if the vehicle identifies the current driving scenario as "speeding" based on the current vehicle speed, the vehicle will issue a reminder to the driver that the vehicle is speeding too fast, such as by broadcasting the reminder by voice.
[0089] In this way, when it is determined that a driving scene is identified locally, the first vehicle information is used to quickly determine the driving scene and directly display the corresponding service information locally. In certain scenarios, such as scenarios with high real-time requirements, relevant service information can be quickly pushed, thereby ensuring the effectiveness and efficiency of service information push, improving user experience, and ensuring user safety.
[0090] When it is determined that the driving scene is identified in the cloud, in step 103 , the cloud server identifies the current driving scene based on cloud data formed based on the second vehicle information, the user information, and the third-party information.
[0091] In some embodiments, the second vehicle information includes at least one of vehicle status information, vehicle fault information, vehicle driving information, and vehicle location information; the user information includes at least one of user behavior information, user purchase record, and user basic information; the third-party information includes at least one of weather information and POI (Point of Information) information.
[0092] In this way, the cloud can make scene judgments based on richer data, which can further improve the accuracy of recognition and the diversity of scenes that can be identified.
[0093] In some embodiments, the cloud data includes regularly updated tag data, real-time second vehicle information, real-time third-party information, and user feedback information.
[0094] In this way, the cloud data used for scene recognition is obtained based on processing of multiple data, which can further improve the accuracy of recognition and the diversity of scenes that can be recognized.
[0095] In some embodiments, the label data includes a vehicle portrait label, a user portrait label and a road portrait label, wherein the vehicle portrait label is calculated based on the second vehicle information uploaded cumulatively by the vehicle, the user portrait label is calculated based on the second vehicle information uploaded cumulatively and user information, and the road portrait label is calculated based on the second vehicle information uploaded cumulatively and third-party information.
[0096] In some embodiments, the vehicle portrait label, the user portrait label, and the road portrait label are also referred to as vehicle preference features, user preference features, and road preference features.
[0097] For example, the vehicle preference feature is a vehicle image label calculated according to preset rules based on the vehicle information (such as vehicle status, vehicle fault, vehicle location, etc.) uploaded by the vehicle, such as vehicle age label, vehicle cumulative mileage label, vehicle frequent fault label, vehicle usual route label, etc.;
[0098] For example, user preference features are user portrait tags calculated according to preset rules based on the accumulated uploaded vehicle information (such as driving behavior and vehicle location), user information (such as user identity, user operation behavior, user purchase history, and user basic information), such as driving style, travel habits, and vehicle setting habits;
[0099] For example, the road preference feature is a road portrait label calculated according to preset rules based on the accumulated uploaded vehicle data (such as vehicle failures, vehicle locations, etc.) and third-party information (such as weather data), such as areas with high incidence of waterlogging and dangerous driving.
[0100] In this way, the vehicle preference characteristics, user preference characteristics, and road preference characteristics are represented by the vehicle portrait label, the user portrait label, and the road portrait label, respectively, which can provide a reliable basis for scene recognition.
[0101] In step 103, when the cloud server identifies the driving scene, the cloud server determines the current driving scene based on the regularly updated label data, the real-time second vehicle information, the real-time third-party information and the user feedback information, and uses a preset third rule or a trained model.
[0102] In some embodiments, the third rule includes an identification rule and a filtering rule.
[0103] The identification rule includes determining a candidate driving scene according to the regularly updated tag data, the real-time second vehicle information and the real-time third-party information, and the filtering rule includes determining whether to use the candidate driving scene as an identified driving scene according to the user feedback information.
[0104] In some embodiments, the user feedback information includes negative feedback information from the user, such as the user rejecting the recommended service or not responding to the recommended service.
[0105] For example, the cloud server determines that the current driving scenario is "congested road, slow driving" based on regularly updated label data, real-time second vehicle information, and real-time third-party information. However, when the user previously received service information corresponding to the scenario, for example, when receiving the service information of "recommended to play light music", the user rejected the recommended service, or the user did not take further action on the recommended service. Therefore, when the current driving scenario is identified as "congested road, slow driving" this time, the service information is not generated and pushed.
[0106] In this way, the cloud server uses recognition rules and filtering rules to determine the driving scene, that is, determines the candidate driving scene according to the regularly updated tag data, the real-time second vehicle information and the real-time third-party information, and determines whether to use the candidate driving scene as the identified driving scene according to the user feedback information. In this way, the user's feeling about the service push can be fully considered to determine whether to continue the push, thereby further improving the effect of the service information push and the user experience.
[0107] In some embodiments, the first rule, the second rule, the third rule, the first service information and the second service information can be updated through the cloud server. In this way, the identification rules and the content of the service information can be flexibly adjusted to further improve the effect and efficiency of the service information push.
[0108] For example, these rules and service information are adjusted based on user feedback.
[0109] In step 103, after the cloud server identifies the current driving scene, the cloud server sends second service information corresponding to the identified driving scene to the vehicle, and the vehicle displays the second service information through the vehicle terminal.
[0110] For example, similar to the first service information, the vehicle displays a screen including the second service information through the vehicle-mounted terminal, and / or voice broadcasts the content of the second service information, so that the user can quickly understand the content of the service.
[0111] In some embodiments, the screen displayed on the vehicle terminal may be a card screen. In addition, for example, the card screen includes an interactive button, and the user clicks the interactive button to execute a specified action instruction, such as closing the card, jumping to an application in the vehicle terminal, etc., for example, jumping to an application related to the recommended function or a start button.
[0112] In this way, in some scenarios, such as scenarios with low real-time requirements, the cloud server can accurately identify the driving scene and push relevant service information after performing relatively complex calculations based on the cloud data, thereby improving the accuracy and richness of the driving scene identification and the push of relevant service information in the scenario;
[0113] In some embodiments, when there are multiple identified driving scenes, the driving scene with the highest priority among the multiple driving scenes is used as the final driving scene. In this way, service information can be pushed based on the driving scene with the highest priority, further improving the effect of pushing service information.
[0114] In some embodiments, the priority of driving scenarios is pre-set, which can be set according to actual needs.
[0115] Figure 3 FIG. 1 is a schematic diagram of the information processing and interaction process of Example 1 of the present invention. Figure 3 As shown, the process includes:
[0116] Step 301: The vehicle obtains real-time first vehicle information;
[0117] Step 302: The vehicle determines to identify a driving scene locally or in the cloud according to the real-time first vehicle information;
[0118] When it is determined to identify the driving scene locally, steps 303-304 represented by dashed lines are executed, and when it is determined to identify the driving scene in the cloud, steps 305-308 represented by dotted lines are executed;
[0119] Step 303: When determining to identify the driving scene locally, the vehicle identifies the current driving scene according to the real-time first vehicle information;
[0120] Step 304: The vehicle displays first service information corresponding to the identified driving scenario through the vehicle terminal;
[0121] Step 305: When it is determined that the driving scene is to be recognized in the cloud, the vehicle sends an instruction for recognizing the driving scene in the cloud to the cloud server;
[0122] Step 306: The cloud server identifies the current driving scene according to the cloud data formed based on the second vehicle information, the user information and the third-party information;
[0123] Step 307: The cloud server sends second service information corresponding to the identified driving scene to the vehicle;
[0124] Step 308: The vehicle displays the second service information via the vehicle-mounted terminal.
[0125] The specific implementation of the above steps 301 to 308 can refer to the above records and will not be repeated here.
[0126] The information push method according to the embodiment of the present invention is further described below through two examples.
[0127] Example 1: Local scene recognition and push
[0128] For example, when the vehicle is driving normally, when the driver fatigue detection system finds that the user is slightly fatigued, only voice reminders are given to the user. However, when the user turns on advanced driver assistance, the user is prone to relax and fatigue, which may cause the user to be unable to take over the steering wheel in time, causing greater accident damage. Therefore, when the user turns on advanced driver assistance, a stronger fatigue reminder method will be used when the user is slightly fatigued. At this time, it is necessary to send a reminder to the user immediately, so the local scene recognition and push method is adopted.
[0129] Corresponding to step 101, first, the vehicle obtains the fatigue level signal (for example, mild fatigue) of the driver fatigue detection system in real time; then, the vehicle determines that the current fatigue level signal meets the trigger condition according to the first rule; then, the vehicle determines that the vehicle has turned on advanced driver assistance according to the second rule, and determines to identify the driving scene locally.
[0130] Corresponding to step 102, if the vehicle recognizes that the current scene is a mild fatigue after the advanced driver assistance is turned on, the following service information is sent: turn on the air conditioner and play music (there is no such reminder content during normal driving); give a voice reminder to the user; after receiving the above information, the vehicle terminal reminds the user to turn on the air conditioner and play music on the screen, and gives a voice reminder. Alternatively, the air conditioner can be turned on automatically, music can be played, and a voice reminder can be given.
[0131] Example 2: Cloud scene recognition and push
[0132] For example, when the vehicle is started, it will determine whether there are abnormal road conditions or weather conditions (such as slippery roads) on the user's usual route based on the user's travel habits. If so, the user will be given a voice reminder. In this scenario, the timeliness of information push is not required to be high, so the cloud scene recognition and push method is adopted.
[0133] Corresponding to step 101, the vehicle obtains the vehicle start signal in real time; the vehicle determines according to the first rule that the current vehicle start signal has satisfied the trigger condition; then, the vehicle determines according to the second rule that the vehicle is in the start state and the vehicle speed is less than 5km / h, then it determines to identify the driving scene in the cloud, and sends an instruction to identify the driving scene in the cloud to the cloud server.
[0134] Corresponding to step 103, after receiving the instruction sent by the vehicle to identify the driving scene in the cloud, the cloud server identifies that the user currently has a habitual route and there is a slippery section on the habitual route according to the preset identification rules and filtering rules, and then determines that the current driving scene of the vehicle is a scene where the road surface is slippery on the driving route. When the cloud server identifies that the current driving scene is a scene where the road surface is slippery on the driving route, it sends the following service information to the vehicle: remind the vehicle that the road surface is slippery on the driving route through voice and display screen. After the vehicle receives the service information, the vehicle terminal reminds the vehicle that the road surface is slippery on the driving route through voice and display screen.
[0135] It can be seen from the above embodiments that the vehicle determines whether to identify the driving scene locally or in the cloud based on the real-time first vehicle information. When it is determined that the driving scene is to be identified locally, the first vehicle information is used to quickly determine the driving scene and directly display the corresponding service information locally. In this way, in certain scenarios, such as scenarios with high real-time requirements, relevant service information can be quickly pushed, thereby ensuring the effect and efficiency of service information push and improving user experience.
[0136] When it is determined that the driving scene is to be identified in the cloud, the cloud server identifies the driving scene based on the cloud data formed by multiple data and pushes corresponding service information to the vehicle. In this way, in some scenarios, such as scenarios with low real-time requirements, the cloud server can accurately identify the driving scene and push relevant service information after performing relatively complex calculations based on the cloud data, thereby improving the accuracy and richness of the driving scene identification and the push of relevant service information in the scenario;
[0137] Therefore, the respective characteristics of local push and cloud push can be flexibly utilized according to actual conditions, so that local push and cloud push can work together to meet the travel needs of users.
[0138] In addition, the push mechanism that combines local push and cloud push reduces dependence on the network. When the network environment is poor, local push can also be used to meet the needs of certain scenarios, such as the need to quickly provide service information in scenarios with high real-time requirements, thereby ensuring user experience and security.
[0139] Furthermore, when determining whether to identify the driving scene locally or in the cloud, first determine whether the trigger condition for information push is met based on the real-time first vehicle information and the first rule, and if the trigger condition is met, further combine the second rule to determine the timeliness of the information push, and judge whether to identify the driving scene locally or in the cloud based on the timeliness. In this way, service information can be pushed in time at the appropriate time, for example, service information can be pushed in time in scenarios with high timeliness requirements, thereby further improving the effect and efficiency of service information push.
[0140] Furthermore, the contents of the first rule, the second rule, the first service information and the second service information can be updated through the cloud server, so that the identification rules and the contents of the service information can be flexibly adjusted to further improve the effect and efficiency of service information push.
[0141] Furthermore, the first vehicle information includes vehicle driving information, vehicle terminal operation information, vehicle location information, identification information of the in-vehicle camera, and at least one of sensor identification information. In this way, it is possible to combine multiple data to comprehensively determine whether to perform identification locally or in the cloud, and to combine multiple data locally to identify driving scenes, thereby improving the accuracy of identification.
[0142] Furthermore, the cloud data includes regularly updated tag data, real-time second vehicle information, real-time third-party information, and user feedback information. In this way, the cloud data used for scene recognition is processed based on multiple data, which can further improve the accuracy of recognition and the diversity of scenes that can be recognized.
[0143] Furthermore, the label data includes a vehicle portrait label, a user portrait label, and a road portrait label. The vehicle portrait label is calculated based on the second vehicle information uploaded cumulatively by the vehicle, the user portrait label is calculated based on the second vehicle information uploaded cumulatively and user information, and the road portrait label is calculated based on the second vehicle information uploaded cumulatively and third-party information. In this way, the vehicle portrait label, the user portrait label, and the road portrait label respectively represent the vehicle preference characteristics, the user preference characteristics, and the road preference characteristics, which can provide a reliable basis for scene recognition.
[0144] Furthermore, the cloud server uses recognition rules and filtering rules to determine the driving scenario, that is, determines the candidate driving scenario based on the regularly updated tag data, the real-time second vehicle information and the real-time third-party information, and determines whether to use the candidate driving scenario as the identified driving scenario based on the user feedback information. In this way, the user's feeling about the service push can be fully considered to determine whether to continue the push, further improving the effect of the service information push and the user experience.
[0145] Furthermore, the second vehicle information includes at least one of vehicle status information, vehicle fault information, vehicle driving information, and vehicle location information; the user information includes at least one of user behavior information, user purchase records, and user basic information; and the third-party information includes at least one of weather information and POI information. In this way, the cloud can make scene judgments based on richer data, which can further improve the accuracy of recognition and the diversity of scenes that can be recognized.
[0146] Furthermore, when there are multiple identified driving scenes, the driving scene with the highest priority among the multiple driving scenes is used as the final driving scene. In this way, service information can be pushed based on the driving scene with the highest priority, further improving the effect of pushing service information.
[0147] Furthermore, the vehicle displays a screen including the first service information or the second service information through the vehicle-mounted terminal, and / or voice broadcasts the content of the first service information or the second service information, so that the user can quickly understand the content of the service.
[0148] Example 2
[0149] Embodiment 2 of the present invention provides an information push system for a vehicle, which corresponds to the information push method for a vehicle described in Embodiment 1. For specific contents, please refer to the description in Embodiment 1, and repeated contents will not be described in detail.
[0150] Figure 4 FIG. 2 is a schematic diagram of an information push system for a vehicle according to Embodiment 2 of the present invention. Figure 4 As shown, the information push system 400 for a vehicle includes a vehicle system 410 and a cloud server 420, wherein the vehicle system 410 includes a vehicle terminal 411, wherein:
[0151] The vehicle system 410 determines whether to identify the driving scene locally or in the cloud according to the real-time first vehicle information; when it is determined to identify the driving scene locally, the vehicle system 410 identifies the current driving scene according to the real-time first vehicle information, and the vehicle system 410 displays the first service information corresponding to the identified driving scene through the vehicle terminal 411; when it is determined to identify the driving scene in the cloud, the vehicle system 410 sends an instruction for identifying the driving scene in the cloud to the cloud server;
[0152] After receiving the instruction, the cloud server 420 identifies the current driving scene based on the cloud data formed based on the second vehicle information, user information and third-party information, and the cloud server 420 sends the second service information corresponding to the identified driving scene to the vehicle system 410 of the vehicle, and the vehicle displays the second service information through the on-board terminal 411 of the vehicle system 410.
[0153] Figure 5 FIG. 2 is a schematic diagram of a vehicle system according to Embodiment 2 of the present invention. Figure 5 As shown, the vehicle system 410 includes the above-mentioned vehicle terminal 411. In addition, the vehicle system 410 also includes:
[0154] A first determination module 412, which determines whether a triggering condition for information push is met based on the real-time first vehicle information and using a preset first rule;
[0155] A second determination module 413, which, when a triggering condition for information push is met, determines the timeliness of information push according to the first vehicle information and using a preset second rule, and determines whether to identify the driving scene locally or in the cloud according to the timeliness of the information push;
[0156] The first recognition module 414 recognizes the current driving scene according to the real-time first vehicle information when determining to recognize the driving scene locally.
[0157] In some embodiments, the first vehicle information includes at least one of vehicle driving information, vehicle terminal operation information, vehicle location information, identification information of an in-vehicle camera, and sensor identification information.
[0158] In some embodiments, the vehicle-mounted terminal 411 displays a screen including the first service information or the second service information, and / or the vehicle-mounted terminal 411 voice broadcasts the content of the first service information or the second service information.
[0159] In some embodiments, the cloud data includes regularly updated tag data, real-time second vehicle information, real-time third-party information, and user feedback information.
[0160] In some embodiments, the label data includes a vehicle image label, a user image label, and a road image label.
[0161] Figure 6 Schematic diagram of a cloud server according to Embodiment 2 of the present invention. Figure 6 As shown, the cloud server 420 includes:
[0162] A data collection and processing module 421 collects uploaded second vehicle information, user information, and third-party information;
[0163] A calculation module 422, which calculates and labels the vehicle portrait according to the second vehicle information uploaded cumulatively by the vehicle; and calculates and labels the user portrait according to the second vehicle information uploaded cumulatively and the user information; and calculates and labels the road portrait according to the second vehicle information uploaded cumulatively and the third-party information;
[0164] A storage module 423, which stores the vehicle portrait label, the user portrait label and the road portrait label;
[0165] A second recognition module 424, which determines the current driving scene according to the regularly updated label data, the real-time second vehicle information, the real-time third-party information and the user feedback information, and uses a preset third rule or a trained model;
[0166] A first updating module 425, which is used to update the content of the first rule, the second rule, the third rule, the first service information and the second service information;
[0167] The second updating module 426 updates the vehicle portrait label, the user portrait label and the road portrait label.
[0168] In some embodiments, the third rule includes an identification rule and a filtering rule. The identification rule includes determining a candidate driving scene based on the periodically updated tag data, real-time second vehicle information, and real-time third-party information. The filtering rule includes determining whether to use the candidate driving scene as an identified driving scene based on the user feedback information.
[0169] In some embodiments, the second vehicle information includes at least one of vehicle status information, vehicle fault information, vehicle driving information, and vehicle location information; the user information includes at least one of user behavior information, user purchase records, and user basic information; the third-party information includes at least one of weather information and POI information.
[0170] In some embodiments, when multiple driving scenarios are identified, the driving scenario with the highest priority among the multiple driving scenarios is used as the final driving scenario.
[0171] It can be seen from the above embodiments that the vehicle determines whether to identify the driving scene locally or in the cloud based on the real-time first vehicle information. When it is determined that the driving scene is to be identified locally, the first vehicle information is used to quickly determine the driving scene and directly display the corresponding service information locally. In this way, in certain scenarios, such as scenarios with high real-time requirements, relevant service information can be quickly pushed, thereby ensuring the effect and efficiency of service information push and improving user experience.
[0172] When it is determined that the driving scene is to be identified in the cloud, the cloud server identifies the driving scene based on the cloud data formed by multiple data and pushes corresponding service information to the vehicle. In this way, in some scenarios, such as scenarios with low real-time requirements, the cloud server can accurately identify the driving scene and push relevant service information after performing relatively complex calculations based on the cloud data, thereby improving the accuracy and richness of the driving scene identification and the push of relevant service information in the scenario;
[0173] Therefore, the respective characteristics of local push and cloud push can be flexibly utilized according to actual conditions, so that local push and cloud push can work together to meet the travel needs of users.
[0174] In addition, the push mechanism that combines local push and cloud push reduces dependence on the network. When the network environment is poor, local push can also be used to meet the needs of certain scenarios, such as the need to quickly provide service information in scenarios with high real-time requirements, thereby ensuring user experience and security.
[0175] Example 3
[0176] Embodiment 3 of the present invention provides an electronic device, which includes the information push system for a vehicle described in Embodiment 2. For specific contents, please refer to the description in Embodiment 2, and repeated contents will not be described in detail again.
[0177] In some embodiments, the electronic device may be set in a cloud server; or, may be set in a vehicle; or, may be partially set in a cloud server and partially set in a vehicle.
[0178] Figure 7 FIG. 1 is a schematic block diagram of the system structure of the electronic device according to the third embodiment of the present invention. Figure 7 As shown, the electronic device 500 may include a processor 510 and a memory 520; the memory 520 is coupled to the processor 510. It should be noted that this figure is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.
[0179] In one embodiment, the processor 510 can be configured as follows: the vehicle determines whether to identify a driving scene locally or in the cloud based on real-time first vehicle information; in the case of determining to identify a driving scene locally, the vehicle identifies the current driving scene based on the real-time first vehicle information, and the vehicle displays first service information corresponding to the identified driving scene through an on-board terminal; and in the case of determining to identify a driving scene in the cloud, the cloud server identifies the current driving scene based on cloud data formed based on second vehicle information, user information and third-party information, and the cloud server sends second service information corresponding to the identified driving scene to the vehicle, and the vehicle displays the second service information through the on-board terminal.
[0180] like Figure 7 As shown, the electronic device 500 may further include: a communication module 530, an input unit 540, a display 550, and a power supply 560. It is worth noting that the electronic device 500 does not necessarily have to include Figure 7 In addition, the electronic device 500 may also include Figure 7For components not shown in the figure, reference may be made to the related art.
[0181] like Figure 7 As shown, the processor 510 is sometimes also referred to as a controller or an operation control, and may include a microprocessor or other processor devices and / or logic devices. The processor 510 receives inputs and controls the operations of various components of the electronic device 500 .
[0182] The memory 520 may be, for example, one or more of a cache, a flash memory, a hard drive, a removable medium, a volatile memory, a non-volatile memory or other suitable devices. Various data may be stored, and programs for executing related information may also be stored. The processor 510 may execute the program stored in the memory 520 to implement information storage or processing, etc. The functions of other components are similar to those of the prior art and will not be described in detail herein. The components of the electronic device 500 may be implemented by dedicated hardware, firmware, software or a combination thereof without departing from the scope of the present invention.
[0183] It can be seen from the above embodiments that the vehicle determines whether to identify the driving scene locally or in the cloud based on the real-time first vehicle information. When it is determined that the driving scene is to be identified locally, the first vehicle information is used to quickly determine the driving scene and directly display the corresponding service information locally. In this way, in certain scenarios, such as scenarios with high real-time requirements, relevant service information can be quickly pushed, thereby ensuring the effect and efficiency of service information push and improving user experience.
[0184] When it is determined that the driving scene is to be identified in the cloud, the cloud server identifies the driving scene based on the cloud data formed by multiple data and pushes corresponding service information to the vehicle. In this way, in some scenarios, such as scenarios with low real-time requirements, the cloud server can accurately identify the driving scene and push relevant service information after performing relatively complex calculations based on the cloud data, thereby improving the accuracy and richness of the driving scene identification and the push of relevant service information in the scenario;
[0185] Therefore, the respective characteristics of local push and cloud push can be flexibly utilized according to actual conditions, so that local push and cloud push can work together to meet the travel needs of users.
[0186] In addition, the push mechanism that combines local push and cloud push reduces dependence on the network. When the network environment is poor, local push can also be used to meet the needs of certain scenarios, such as the need to quickly provide service information in scenarios with high real-time requirements, thereby ensuring user experience and security.
[0187] The embodiments of the present invention are described in detail with reference to the accompanying drawings, indicating the manner in which the principles of the present invention can be adopted. However, it should be understood that the implementation of the present invention is not limited to the manner of the above-mentioned embodiments, but also includes all changes, modifications and equivalents that do not depart from the scope of the present invention.
Claims
1. A method for pushing information to a vehicle, It is characterized in that The method comprises: The vehicle determines to identify the driving scene locally or in the cloud according to the real-time first vehicle information; In the case where it is determined that the driving scene is identified locally, the vehicle identifies the current driving scene according to the real-time first vehicle information, and the vehicle displays first service information corresponding to the identified driving scene through the vehicle terminal; and When it is determined that the driving scene is identified in the cloud, the cloud server identifies the current driving scene based on the cloud data formed based on the second vehicle information, user information and third-party information, and the cloud server sends second service information corresponding to the identified driving scene to the vehicle, and the vehicle displays the second service information through the vehicle-mounted terminal.
2. The method according to claim 1, It is characterized in that The vehicle determines to identify the driving scene locally or in the cloud according to the real-time first vehicle information, including: The vehicle determines whether a triggering condition for information push is met according to the real-time first vehicle information and using a preset first rule; When the triggering condition for information push is met, the timeliness of the information push is determined according to the first vehicle information and using a preset second rule, and the driving scene is identified locally or in the cloud according to the timeliness of the information push.
3. The method according to claim 2, It is characterized in that The contents of the first rule, the second rule, the first service information and the second service information can be updated through the cloud server.
4. The method according to any one of claims 1 to 3, It is characterized in that The first vehicle information includes at least one of vehicle driving information, vehicle terminal operation information, vehicle position information, identification information of an in-vehicle camera, and sensor identification information.
5. The method according to claim 1, It is characterized in that The cloud data includes regularly updated tag data, real-time second vehicle information, real-time third-party information, and user feedback information.
6. The method according to claim 5, It is characterized in that The label data includes vehicle image labels, user image labels and road image labels. The vehicle portrait tag is calculated based on the second vehicle information cumulatively uploaded by the vehicle. The user portrait tag is calculated based on the accumulated uploaded second vehicle information and user information. The road portrait label is calculated based on the accumulated uploaded second vehicle information and third-party information.
7. The method according to claim 5, It is characterized in that The cloud server identifies the current driving scene based on the cloud data formed based on the second vehicle information, the user information and the third-party information, including: The cloud server determines the current driving scenario based on the regularly updated label data, the real-time second vehicle information, the real-time third-party information and the user feedback information, and uses a preset third rule or a trained model. The third rule includes an identification rule and a filtering rule. The identification rule includes determining a candidate driving scenario according to the regularly updated tag data, the real-time second vehicle information, and the real-time third-party information, The filtering rule includes determining whether to use the candidate driving scene as the identified driving scene according to the user feedback information.
8. The method according to any one of claims 5 to 7, It is characterized in that The second vehicle information includes at least one of vehicle status information, vehicle fault information, vehicle driving information and vehicle position information; The user information includes at least one of user behavior information, user purchase records and user basic information; The third-party information includes at least one of weather information and POI information.
9. The method according to claim 1, It is characterized in that When there are multiple identified driving scenarios, the driving scenario with the highest priority among the multiple driving scenarios is taken as the final driving scenario.
10. The method according to claim 1, It is characterized in that The vehicle displays the first service information or the second service information through the vehicle-mounted terminal, including: The vehicle displays a screen including the first service information or the second service information through a vehicle-mounted terminal, and / or voice broadcasts the content of the first service information or the second service information.
11. An information push system for vehicles, It is characterized in that The system includes a vehicle computer system and a cloud server arranged in the vehicle. The vehicle system determines whether to identify the driving scene locally or in the cloud according to the real-time first vehicle information; when it is determined to identify the driving scene locally, the vehicle system identifies the current driving scene according to the real-time first vehicle information, and the vehicle system displays first service information corresponding to the identified driving scene through the vehicle terminal; when it is determined to identify the driving scene in the cloud, the vehicle system sends an instruction for identifying the driving scene in the cloud to the cloud server; After receiving the instruction, the cloud server identifies the current driving scene based on the cloud data formed based on the second vehicle information, user information and third-party information, and the cloud server sends the second service information corresponding to the identified driving scene to the vehicle system of the vehicle, and the vehicle displays the second service information through the on-board terminal of the vehicle system.
12. The system according to claim 11, It is characterized in that The vehicle system comprises: A first determination module, which determines whether a triggering condition for information push is met based on the real-time first vehicle information and using a preset first rule; A second determination module, which, when a triggering condition for information push is met, determines the timeliness of information push according to the first vehicle information and using a preset second rule, and determines whether to identify the driving scene locally or in the cloud according to the timeliness of the information push; The first recognition module recognizes the current driving scene according to the real-time first vehicle information when determining to recognize the driving scene locally.
13. The system according to claim 12, It is characterized in that The cloud server includes: The first updating module is used to update the content of the first rule, the second rule, the first service information and the second service information.
14. The system according to any one of claims 11 to 13, It is characterized in that The first vehicle information includes at least one of vehicle driving information, vehicle terminal operation information, vehicle position information, identification information of an in-vehicle camera, and sensor identification information.
15. The system according to claim 11, It is characterized in that The cloud data includes regularly updated tag data, real-time second vehicle information, real-time third-party information, and user feedback information.
16. The system according to claim 15, It is characterized in that The label data includes vehicle image labels, user image labels and road image labels. The cloud server includes: A data collection and processing module, which collects uploaded second vehicle information, user information, and third-party information; a calculation module, which calculates the vehicle portrait label according to the second vehicle information uploaded cumulatively by the vehicle; and calculates the user portrait label according to the second vehicle information uploaded cumulatively and the user information; and calculates the road portrait label according to the second vehicle information uploaded cumulatively and the third-party information; A storage module, which stores the vehicle portrait label, the user portrait label and the road portrait label; The second updating module updates the vehicle portrait label, the user portrait label and the road portrait label.
17. The system according to claim 15, It is characterized in that The cloud server includes: The second recognition module determines the current driving scene based on the regularly updated label data, the real-time second vehicle information, the real-time third-party information and the user feedback information, and uses a preset third rule or a trained model. The third rule includes an identification rule and a filtering rule. The identification rule includes determining a candidate driving scenario according to the regularly updated tag data, the real-time second vehicle information, and the real-time third-party information, The filtering rule includes determining whether to use the candidate driving scene as the identified driving scene according to the user feedback information.
18. The system according to any one of claims 15 to 17, It is characterized in that The second vehicle information includes at least one of vehicle status information, vehicle fault information, vehicle driving information and vehicle position information; The user information includes at least one of user behavior information, user purchase records and user basic information; The third-party information includes at least one of weather information and POI information.
19. The system according to claim 11, It is characterized in that When there are multiple identified driving scenarios, the driving scenario with the highest priority among the multiple driving scenarios is taken as the final driving scenario.
20. The system according to claim 11, It is characterized in that The vehicle-mounted terminal displays a screen including the first service information or the second service information, and / or the vehicle-mounted terminal voice broadcasts the content of the first service information or the second service information.
Citation Information
Cited By
Large model AI central control platform control method and double-protocol large model AI central control platform
CN121209340A
