In-vehicle service recommendation method, apparatus and device, and storage medium

Abstract

The present application relates to the technical field of information recommendation. Disclosed are an in-vehicle service recommendation method, apparatus and device, and a storage medium. The method comprises: on the basis of traveling data corresponding to a vehicle, determining position information and a traveling state of the vehicle; on the basis of the position information, the traveling state and user behavior data, determining a target traveling scenario corresponding to the vehicle; determining a scenario attribute corresponding to the target traveling scenario; and determining a service recommendation strategy on the basis of the scenario attribute, current time information and the user behavior data, and performing service recommendation on the basis of the service recommendation strategy.

Description

In-vehicle service recommendation method, device, equipment and storage medium

[0001] This application claims priority to Chinese patent application No. 202410377095.2 filed on March 29, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0002] The present application relates to the field of information recommendation technology, and in particular to a method, device, equipment and storage medium for recommending in-vehicle services. Background Art

[0003] With the development of connected vehicle (IoV) technology, more and more cars are equipped with intelligent connectivity systems. The core of IoV is personalized, intelligent user services, capturing each user's needs and providing the most precise services. Existing IoV systems typically require user operation data and recommend corresponding in-vehicle services based on this data. However, this approach often fails to provide personalized services, resulting in a poor driving experience.

[0004] The above content is only used to assist in understanding the technical solution of this application and does not constitute an admission that the above content is prior art. Technical issues

[0005] The main purpose of this application is to provide a method, device, equipment and storage medium for recommending in-vehicle services, aiming to solve the technical problem in the prior art that the Internet of Vehicles system cannot provide personalized services to users, resulting in a poor driving experience for users. Technical Solutions

[0006] To achieve the above objectives, the present application provides a method for recommending in-vehicle services, which includes:

[0007] Determine the location information and driving status of the vehicle according to the driving data corresponding to the vehicle;

[0008] Determining a target driving scenario corresponding to the vehicle based on the location information, the driving status, and the user behavior data;

[0009] Determining scene attributes corresponding to the target driving scene;

[0010] A service recommendation strategy is determined based on the scene attributes, current time information and the user behavior data, and service recommendations are made according to the service recommendation strategy.

[0011] In one embodiment, the step of determining the target driving scene corresponding to the vehicle based on the location information, the driving status, and the user behavior data includes:

[0012] Inputting the location information and the driving status into a preset scenario prediction model to obtain a plurality of prediction scenarios;

[0013] Determine whether the user has triggered the scenario triggering conditions corresponding to each prediction scenario based on user behavior data;

[0014] The target driving scene corresponding to the vehicle is determined according to the judgment result.

[0015] In one embodiment, the step of determining a service recommendation strategy based on the scene attributes, current time information, and the user behavior data includes:

[0016] Determining a service category to be recommended based on the scene attributes;

[0017] Obtaining a service recommendation time period corresponding to the service category to be recommended;

[0018] Determining whether to trigger vehicle service recommendation based on the service recommendation time period and current time information;

[0019] If so, a service recommendation strategy is determined based on the service category to be recommended and the user behavior data.

[0020] In one embodiment, the step of determining a service recommendation strategy based on the service category to be recommended and the user behavior data includes:

[0021] Obtain the target user's corresponding emotional state information;

[0022] determining a service to be recommended based on the emotional state information, the category of the service to be recommended, and the user behavior data;

[0023] A server recommendation strategy is determined based on the services to be recommended and service weight information corresponding to the services to be recommended.

[0024] In one embodiment, the step of determining a server recommendation strategy based on the service to be recommended and the service weight information corresponding to the service to be recommended includes:

[0025] Determining a target recommended service from the services to be recommended based on service weight information corresponding to the services to be recommended;

[0026] Acquire historical service recommendation information, and determine the number of hits of the target recommended service based on the historical service recommendation information;

[0027] Determining a service recommendation method corresponding to the target recommended service according to the number of hits;

[0028] A service recommendation strategy is determined based on the target recommendation service and the service recommendation method.

[0029] In one embodiment, the service category to be recommended includes: a destination recommendation service; and the step of determining a service recommendation strategy based on the service category to be recommended and the user behavior data includes:

[0030] If the service category to be recommended is the destination recommendation service, determining the destination category according to the user behavior data;

[0031] determining user intent based on the location information and historical driving data;

[0032] determining a destination recommendation range based on the location information and the user intention;

[0033] Destination recommendation information is acquired based on the destination category and the destination recommendation range, and a service recommendation strategy is determined according to the destination recommendation information.

[0034] In one embodiment, the step of determining a destination recommendation range based on the location information and the user intention includes:

[0035] determining a recommended radius based on an area attribute corresponding to the location information, and predicting a target driving direction of the vehicle based on the user's intention;

[0036] The recommended destination range is determined based on the current position as the center of the circle and the target driving direction as the center line, and according to the recommended radius.

[0037] In addition, to achieve the above-mentioned purpose, the present application also proposes an in-vehicle service recommendation device, which includes:

[0038] An information determination module, configured to determine the location information and driving status of the vehicle based on the driving data corresponding to the vehicle;

[0039] a scene determination module, configured to determine a target driving scene corresponding to the vehicle based on the location information, the driving status, and user behavior data;

[0040] An attribute determination module, configured to determine a scene attribute corresponding to the target driving scene;

[0041] The service recommendation module is used to determine a service recommendation strategy based on the scene attributes, current time information and the user behavior data, and make service recommendations according to the service recommendation strategy.

[0042] In addition, to achieve the above-mentioned purpose, the present application also proposes an in-vehicle service recommendation device, which includes: a memory, a processor, and an in-vehicle service recommendation program stored on the memory and executable on the processor, wherein the in-vehicle service recommendation program is configured to implement the steps of the in-vehicle service recommendation method described above.

[0043] In addition, to achieve the above objectives, the present application also proposes a storage medium, on which a vehicle service recommendation program is stored. When the vehicle service recommendation program is executed by a processor, the steps of the vehicle service recommendation method described above are implemented. Beneficial effects

[0044] In the present application, it is disclosed to determine the location information and driving status of a vehicle based on the driving data corresponding to the vehicle; determine the target driving scene corresponding to the vehicle based on the location information, driving status and user behavior data; determine the scene attributes corresponding to the target driving scene; determine the service recommendation strategy based on the scene attributes, current time information and user behavior data, and make service recommendations based on the service recommendation strategy; compared with the existing technology in which the Internet of Vehicles system recommends corresponding in-vehicle services to users based on user operation data and cannot provide personalized services to users, the present application determines the target driving scene corresponding to the vehicle based on the location information, driving status and user behavior data of the vehicle, and determines the service recommendation strategy based on the scene attributes, current time information and user behavior data corresponding to the target driving scene, so as to make service recommendations based on the service recommendation strategy, thereby solving the technical problem that the Internet of Vehicles system in the existing technology cannot provide personalized services to users, resulting in poor user driving experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] FIG1 is a schematic diagram of the structure of an in-vehicle service recommendation device in a hardware operating environment according to an embodiment of the present application;

[0046] FIG2 is a flow chart of a first embodiment of the in-vehicle service recommendation method of the present application;

[0047] FIG3 is a flow chart of a second embodiment of the in-vehicle service recommendation method of the present application;

[0048] FIG4 is a flow chart of a third embodiment of the in-vehicle service recommendation method of the present application;

[0049] FIG5 is a schematic diagram of a destination recommendation range in a third embodiment of the in-vehicle service recommendation method of the present application;

[0050] FIG6 is a structural block diagram of the first embodiment of the in-vehicle service recommendation device of the present application.

[0051] The realization of the objectives, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. Modes for Carrying Out the Invention

[0052] It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application.

[0053] Refer to Figure 1, which is a schematic diagram of the structure of an in-vehicle service recommendation device in the hardware operating environment involved in the embodiment of the present application.

[0054] As shown in Figure 1, the in-vehicle service recommendation device may include a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display and an input unit, such as a keyboard. The user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. The memory 1005 may also be a storage device independent of the processor 1001.

[0055] Those skilled in the art will appreciate that the structure shown in FIG1 does not limit the in-vehicle service recommendation device, and may include more or fewer components than shown, or a combination of certain components, or a different arrangement of components.

[0056] As shown in FIG. 1 , the memory 1005 as a storage medium may include an operating system, a network communication module, a user interface module, and an in-vehicle service recommendation program.

[0057] In the in-vehicle service recommendation device shown in Figure 1, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the in-vehicle service recommendation device of this application can be set in the in-vehicle service recommendation device, and the in-vehicle service recommendation device calls the in-vehicle service recommendation program stored in the memory 1005 through the processor 1001, and executes the in-vehicle service recommendation method provided in the embodiment of this application.

[0058] An embodiment of the present application provides an in-vehicle service recommendation method. Referring to FIG. 2 , FIG. 2 is a flow chart of a first embodiment of the in-vehicle service recommendation method of the present application.

[0059] In this embodiment, the in-vehicle service recommendation method includes the following steps:

[0060] Step S10: Determine the location information and driving status of the vehicle according to the driving data corresponding to the vehicle.

[0061] It should be noted that the method of this embodiment can be executed by an in-vehicle device that provides personalized service recommendations to users, or by another in-vehicle system that includes this in-vehicle device and can perform the same or similar functions. The in-vehicle service recommendation method provided in this embodiment and the following embodiments will be specifically described using an in-vehicle service recommendation system (hereinafter referred to as the system).

[0062] It should be understood that the aforementioned driving data may be relevant data during vehicle travel, such as driving position, driving speed, and remaining fuel level, and this embodiment is not limited thereto. In practical applications, the system may obtain corresponding driving data of the vehicle through onboard monitoring equipment. Specifically, the vehicle's driving position may be obtained through a vehicle positioning device such as a GPS (Global Positioning System); the vehicle's driving speed may be determined through wheel speed sensors; and the vehicle's remaining fuel level may be monitored in real time through a fuel consumption monitoring device.

[0063] It is understandable that the above-mentioned location information may be the current location information of the vehicle.

[0064] It should be noted that the aforementioned driving state may be a corresponding operating state of the vehicle. In this embodiment, the driving state may include: a constant speed driving state, an accelerated driving state, a decelerated driving state, and a stopped driving state. The constant speed driving state may be a state where the vehicle is traveling at a relatively stable speed; the accelerated driving state may be a state where the vehicle speed is continuously increasing; the decelerated driving state may be a state where the vehicle speed is gradually decreasing; and the stopped driving state may be a state where the vehicle is stopped.

[0065] In actual applications, after the on-board equipment is started, the vehicle's driving data such as the driving position and driving speed can be obtained in real time through the monitoring equipment in the vehicle, so that the vehicle's current position information and driving status can be determined based on the obtained driving position and driving speed.

[0066] Step S20: Determine a target driving scenario corresponding to the vehicle based on the location information, the driving status, and the user behavior data.

[0067] In this embodiment, the above-mentioned user behavior data may be data generated when the user interacts with the vehicle, such as: the behavior of turning on or off a certain vehicle function (such as the user operating the steering wheel or brake pedal, the user turning on the navigation, the user turning on the music or radio), the behavior of voice interaction with the in-vehicle voice assistant, etc. This embodiment does not impose any restrictions on this.

[0068] It is understood that in this embodiment, user behavior data can be collected by data embedding. After collecting and obtaining user behavior data, the system can also pre-process the user behavior data to eliminate invalid information and extract key data from it so as to subsequently determine the user's current triggered behavior based on the user behavior data.

[0069] It should be noted that the target driving scene may be the scene in which the vehicle is currently located, such as a commuting scene, a travel scene, a parking and rest scene, etc., and this embodiment does not impose any restrictions on this.

[0070] In this embodiment, the system can determine the target driving scene corresponding to the vehicle based on the vehicle's current driving location information, driving status, and user behavior data.

[0071] In practical applications, the system can first determine the vehicle's corresponding driving state based on the vehicle's driving data. If the vehicle's current driving state is stopped, the vehicle's current location can be determined based on the vehicle's corresponding location information. If the vehicle is currently in a garage at work or home and no corresponding user behavior data has been generated (i.e., the user has not interacted with the vehicle), the target driving scenario for the current vehicle can be determined to be a parking and resting scenario. If the vehicle's current driving state is driving (including constant speed driving, accelerating driving, and decelerating driving), the target driving scenario for the vehicle can be further determined based on the vehicle's current location information and user behavior data. For example, if the user's behavior data indicates that the user has opened the navigation system, the user's navigation destination can be obtained, and the target driving scenario for the vehicle can be determined based on the navigation destination. Specifically, if the user's navigation destination is the company address, the vehicle's current target driving scenario can be determined to be a going-to-work scenario. If the user's navigation destination is the user's home address, the vehicle's current target driving scenario can be determined to be a leaving-get off work scenario. If the user's navigation destination is a tourist attraction, the vehicle's current target driving scenario can be determined to be a travel scenario. Among them, in this embodiment, the user can pre-set the corresponding home address and company address in the system, or the system can predict the user's corresponding home address and company address based on user habits, user settings, address name and other information. This embodiment does not limit this.

[0072] In one embodiment, in order to accurately determine the driving scenario corresponding to the vehicle and thus accurately provide personalized services to the user, the step S20 includes: inputting the location information and the driving status into a preset scenario prediction model to obtain several predicted scenarios; judging whether the user triggers the scenario trigger conditions corresponding to each predicted scenario based on the user behavior data; and determining the target driving scenario corresponding to the vehicle based on the judgment result.

[0073] It should be noted that the above-mentioned preset scene prediction model can be a pre-built model for predicting the driving scene in which the vehicle is currently located; correspondingly, the above-mentioned prediction scene can be the scene that the vehicle may currently be in, predicted by the preset scene prediction model, such as: parking and rest scene, commuting scene, etc., which is not limited in this embodiment.

[0074] In this embodiment, the preset scenario prediction model can be a convolutional neural network model. The system can learn the user's car usage habits in the preset scenario to learn and obtain the scenario prediction model. This embodiment does not limit the specific type and training method of the preset scenario prediction model.

[0075] It should be understood that the above-mentioned scenario trigger conditions may be conditions that need to be met to trigger the driving scenario. In actual applications, the system may pre-define scenario trigger conditions corresponding to various driving scenarios. For example, scenario trigger conditions corresponding to the travel scenario may include, but are not limited to, the vehicle being in driving state, navigation being turned on and the navigation destination being a scenic spot or a non-residential city, music or radio being turned on, and checking the road conditions or weather in a non-residential city; scenario trigger conditions corresponding to the commuting scenario may include, but are not limited to, the vehicle being in driving state, navigation being turned on and the navigation destination being the user's company address or home address, music or radio being turned on, checking the road conditions on the commute route, and the weather in the current city; scenario trigger conditions corresponding to the parking and resting scenario may include, but are not limited to, the vehicle being stopped, the seat being adjusted, and the vehicle ventilation being turned on.

[0076] In this embodiment, corresponding conditional weights can be set for the scene trigger conditions corresponding to each driving scene, and the scene weights corresponding to each predicted scene can be determined based on the conditional weights, so that the predicted scene with the highest scene weight can be determined as the target driving scene.

[0077] In a specific implementation, after determining the vehicle's current location and driving status, the system may input this location and driving status into a preset scenario prediction model. The preset scenario prediction model then outputs several possible driving scenarios (i.e., the aforementioned predicted scenarios) for the vehicle. Specifically, if the vehicle is currently driving and its location information indicates it is between its home address and its work address, the predicted scenarios output by the preset scenario prediction model may be either a commuting scene or a commuting scene. The system then continues to acquire user behavior data. If the user has activated navigation, the system can determine, based on the user's navigation destination, whether the user has triggered the corresponding scenario triggering conditions to determine the target driving scenario. Furthermore, the system may also determine the target driving scenario based on the current time. Specifically, if the current time is between 8:00 AM and 11:00 AM, the predicted scenario may be determined as a commuting scene; if the current time is between 6:00 PM and 8:00 PM, the predicted scenario may be determined as a commuting scene. The specific time periods for commuting scenes can be set based on actual needs or user habits, and this embodiment is not limited thereto.

[0078] Step S30: Determine the scene attributes corresponding to the target driving scene.

[0079] It should be noted that the above scene attributes are attributes corresponding to the target driving scene. In this embodiment, when the vehicle is in different driving scenes, there may be different scene attributes.

[0080] In one embodiment, if the target driving scene corresponding to the vehicle is a parking and rest scene, the scene attributes corresponding to the parking and rest scene may include but are not limited to the temperature inside the vehicle, oxygen concentration, etc.; if the target driving scene corresponding to the vehicle is a commuting scene, the scene attributes corresponding to the commuting scene may include but are not limited to rainy and snowy weather, vehicle fuel level, fatigue driving, music playing, making phone calls, etc.; if the target driving scene corresponding to the vehicle is a travel scene, the scene attributes corresponding to the travel scene may include but are not limited to rainy and snowy weather, vehicle fuel level, fatigue driving, city switching, map search, music playing, making phone calls, etc.

[0081] Step S40: determining a service recommendation strategy based on the scene attributes, current time information and the user behavior data, and performing service recommendations according to the service recommendation strategy.

[0082] It should be understood that the above-mentioned current time information is the time information corresponding to the current moment.

[0083] It should be noted that the above service recommendation strategy may be a strategy for recommending personalized services to users.

[0084] In this embodiment, the system can determine the services that can be recommended to the user at the current moment based on scene attributes, current time information and user behavior data, and generate corresponding service recommendation strategies based on these services that can be recommended to the user, so that personalized service recommendations can be made to the user based on the service recommendation strategy, thereby improving the user's driving experience.

[0085] The present embodiment discloses determining the location information and driving status of a vehicle based on driving data corresponding to the vehicle; determining a target driving scenario corresponding to the vehicle based on the location information, driving status and user behavior data; determining scene attributes corresponding to the target driving scenario; determining a service recommendation strategy based on the scene attributes, current time information and user behavior data, and making service recommendations based on the service recommendation strategy; compared with the prior art in which the Internet of Vehicles system recommends corresponding in-vehicle services to users based on user operation data and is unable to provide personalized services to users, the present embodiment determines the target driving scenario corresponding to the vehicle based on the location information, driving status and user behavior data of the vehicle, and determines a service recommendation strategy based on the scene attributes, current time information and user behavior data corresponding to the target driving scenario, so as to make service recommendations based on the service recommendation strategy, thereby solving the technical problem in the prior art in which the Internet of Vehicles system is unable to provide personalized services to users, resulting in a poor driving experience for users.

[0086] Refer to FIG3 , which is a flow chart of a second embodiment of the in-vehicle service recommendation method of the present application.

[0087] Based on the first embodiment above, in order to achieve accurate recommendation of personalized services for users, in this embodiment, step S40 includes:

[0088] Step S401: Determine the service category to be recommended according to the scene attributes.

[0089] It should be understood that the recommended service categories may be categories corresponding to services currently recommended to the user, such as communication category, entertainment category, basic driving category, etc., and this embodiment does not impose any limitation on this.

[0090] Among them, the communication category can be a service category recommended for users when talking to others. The services that can be recommended in this category include but are not limited to answering calls, hanging up calls, replying to text messages, adjusting call volume, etc.; the entertainment category can be a service category recommended for users when they need to relax. The services that can be recommended in this category include but are not limited to playing music and radio; the basic driving category can be a category recommended for basic services when users are driving a vehicle. The services that can be recommended in this category include but are not limited to adjusting seats, adjusting the temperature in the car, etc.

[0091] Step S402: Obtain the service recommendation time period corresponding to the service category to be recommended.

[0092] In this embodiment, the service recommendation time period may be a time period corresponding to recommended services of different categories determined based on user habits. In actual applications, corresponding recommended time periods may be pre-set for different service categories. For example, the recommended time period for communication services may be set to within one minute after an incoming call is detected; the recommended time period for entertainment services may be set to while the vehicle is in motion; and the recommended time period for basic driving services may be set to within ten minutes after the vehicle is started, or within three minutes after a user voice control command is detected. This embodiment does not impose any restrictions on this.

[0093] Step S403: determining whether to trigger vehicle service recommendation based on the service recommendation time period and current time information.

[0094] It should be noted that since the system has pre-set corresponding service recommendation times for various services, the current time information can be obtained in real time later to determine whether to trigger the vehicle service recommendation strategy based on the service recommendation time periods corresponding to various services and the current time information. Specifically, if the current moment is in the service recommendation time period, it can be determined that the vehicle service recommendation is triggered at this time, that is, user personalized service recommendations can be made at the current moment.

[0095] Step S404: If yes, a service recommendation strategy is determined based on the service category to be recommended and the user behavior data.

[0096] It is understandable that after triggering the vehicle service recommendation, the services that can currently be recommended can be determined based on the service category to be recommended and user behavior data, and corresponding service recommendation strategies can be generated based on these services that can be recommended to users, so that personalized services can be accurately recommended to users based on the service recommendation strategy.

[0097] In one embodiment, the step of determining a service recommendation strategy based on the service category to be recommended and the user behavior data includes: obtaining emotional state information corresponding to the target user; determining the service to be recommended based on the emotional state information, the service category to be recommended and the user behavior data; and determining a server recommendation strategy based on the service to be recommended and the service weight information corresponding to the service to be recommended.

[0098] It should be noted that the aforementioned emotional state information may be information reflecting the user's current emotional state. In this embodiment, the user's emotional state information may be obtained using sensors and cameras within the vehicle, and the user's current emotional state may be determined based on the emotional state information. The recommended service may then be determined by combining the user's emotional state, the category of the service to be recommended, and the user's behavior data.

[0099] It should be understood that the aforementioned recommended services may be personalized services currently recommended to the user. In practical applications, after obtaining the category of the recommended service and user behavior data, the recommended service can be determined in combination with the user's corresponding emotional state information. Specifically, if the current category of the recommended service is entertainment, and the user behavior data indicates that the user currently has a music player open, the user's emotional state information can be obtained to determine the user's current emotional state. If the user's current emotional state is happy, upbeat music can be recommended and played based on the user's preferences.

[0100] It is understandable that the above service weight information can be the weight information of the currently recommended service. In this embodiment, the weight information corresponding to the service to be recommended can be determined through expert experience and statistical analysis. Specifically, the system can obtain the service information corresponding to the services that can be recommended under different scene attributes in different driving scenarios, and analyze these service information based on the knowledge and experience of experts in the corresponding fields, determine the importance of all recommended services, and then determine the weight information corresponding to these services in combination with user preferences and the response frequency of these services, and establish a weight mapping relationship table that stores the corresponding relationships between driving scenarios, scene attributes, recommended services, and recommended services. After the service to be recommended is determined, the service weight information corresponding to the service to be recommended can be queried from the weight mapping relationship table.

[0101] In this embodiment, the step of determining the server recommendation strategy based on the service to be recommended and the service weight information corresponding to the service to be recommended includes: determining the target recommended service from the services to be recommended based on the service weight information corresponding to the service to be recommended; obtaining historical service recommendation information, and determining the number of hits of the target recommended service based on the historical service recommendation information; determining the service recommendation method corresponding to the target recommended service based on the number of hits; and determining the service recommendation strategy based on the target recommended service and the service recommendation method.

[0102] It should be noted that the target recommended service may be a recommended service among the services to be recommended whose weight exceeds a preset weight threshold. In actual applications, if no recommended service exists whose weight exceeds the preset weight threshold, the recommended service with the highest weight among the services to be recommended may be determined as the target recommended service. If multiple recommended services exist whose weights exceed the preset weight threshold, any one of these recommended services may be determined as the target recommended service.

[0103] It should be understood that the above historical service recommendation information may be related information of personalized services recommended to users in historical time; correspondingly, the above hit count may be the number of times users accept personalized services recommended by the system.

[0104] It is understood that the aforementioned service recommendation method may be a method for recommending a target recommendation service, such as voice broadcast or pop-up window recommendation, and this embodiment does not limit this. In actual applications, if the number of hits for a target recommendation service exceeds the target hit number (e.g., 20 times), it indicates that the target recommendation service has a high command rate, and in this case, the voice broadcast method can be used to recommend the target recommendation service. If the number of hits for a target recommendation service does not exceed the target hit number, it indicates that the target recommendation service has an average command rate, and in this case, the pop-up window recommendation method can be used to recommend the target recommendation service.

[0105] In a specific implementation, the system can first determine the service category to be recommended based on the scene attributes corresponding to the target driving scene, and obtain the service recommendation time period corresponding to the service category to be recommended. If it is found based on the current time information that the service recommendation time period is currently in progress, the vehicle service recommendation can be triggered. After the vehicle service recommendation is triggered, the service to be recommended can be determined based on the service category to be recommended, the user's behavior data, and the user's corresponding emotional state information. Then, the target recommended service can be determined based on the service weight information corresponding to the service to be recommended, and the service recommendation strategy can be determined based on the target recommended service and its corresponding service recommendation method, so that personalized services can be recommended to users based on the service recommendation strategy.

[0106] This embodiment determines the service category to be recommended based on the scene attributes, and determines whether to trigger vehicle service recommendation based on the service recommendation time period corresponding to the service category to be recommended and the current time information. When triggering vehicle service recommendation, the service recommendation strategy is determined based on the service category to be recommended and user behavior data, so that service recommendations can be made according to the service recommendation strategy subsequently, thereby realizing accurate recommendation of personalized services for users.

[0107] Refer to FIG4 , which is a flowchart of a third embodiment of the in-vehicle service recommendation method of the present application.

[0108] Based on the above embodiments, in order to improve the practicality of service recommendation, in this embodiment, the service category to be recommended includes: destination recommendation service; step S404 includes:

[0109] Step S404a: If the category of the service to be recommended is the destination recommendation service, then determine the destination category according to the user behavior data.

[0110] It should be noted that the above-mentioned destination recommendation service can be a service for the system to recommend travel destinations to users; accordingly, the above-mentioned destination categories can be categories of destinations recommended by the system to users, such as: restaurants, hotels, shops, gas stations and other stores, as well as scenic spots, parks and other tourist attractions. This embodiment does not limit this.

[0111] In this embodiment, the system can obtain user behavior data in real time and determine the category of destinations to be recommended by the destination recommendation service based on the user behavior data. For example, if the user behavior data indicates that the user is searching for a nearby hotel, the destination category can be determined as a hotel. In addition, this embodiment can also determine the destination category based on vehicle driving data. For example, if the vehicle driving data indicates that the vehicle's current remaining fuel is low and the user is searching for a nearby gas station, the destination category can be determined as a gas station.

[0112] Step S404b: Determine the user intention based on the location information and historical driving data.

[0113] It should be understood that the historical driving data may be driving data previously acquired by the user, such as driving routes and driving preferences, and this embodiment is not limited thereto. The user intention may be the current driving intention of the user driving the vehicle. In this embodiment, the system may search the historical driving data for the vehicle based on the vehicle's current location, thereby determining the vehicle's intention during the historical time period when it reached the current location, thereby facilitating subsequent prediction of the vehicle's driving direction.

[0114] Step S404c: Determine a destination recommendation range based on the location information and the user intention.

[0115] It can be understood that the above-mentioned destination recommendation range may be the range within which the destination recommended to the user is located.

[0116] In one embodiment, in order to improve the accuracy of determining the recommended destination range and thus accurately recommend a driving destination to the user, step S404c includes: determining a recommended radius based on the area attributes corresponding to the location information, and predicting the target driving direction of the vehicle based on the user's intention; taking the current location as the center of the circle and the target driving direction as the center line, and determining the recommended destination range based on the recommended radius.

[0117] It should be understood that the above-mentioned regional attributes may be attributes corresponding to the current location of the vehicle, such as a business district, a highway section, a suburb, etc., and this embodiment does not impose any limitation on this.

[0118] It is understood that the target driving direction may be a predicted vehicle driving direction. In this embodiment, the user's travel destination may be predicted based on the user's intention, and the direction of the line connecting the vehicle's travel start and travel destination may be determined as the vehicle's corresponding target driving direction.

[0119] It should be noted that the recommended radius can be the maximum straight-line distance between the recommended destination and the vehicle's current location. In practice, the density and category of nearby destinations may vary depending on the area attributes corresponding to the current location. Therefore, this embodiment determines the recommended radius based on the area attributes of the current location. Specifically, if the area attribute corresponding to the vehicle's current location is a highway, the recommended radius can be set longer based on actual circumstances. If the area attribute corresponding to the vehicle's current location is a commercial district, the recommended radius can be set shorter.

[0120] In this embodiment, referring to FIG5 , FIG5 is a schematic diagram of a destination recommendation range in the third embodiment of the in-vehicle service recommendation method of this application. As shown in FIG5 , after determining the recommended radius, a sector-shaped area can be defined with the vehicle's current location as the center o, the vehicle's target driving direction oa as the center line, and the recommended radius as the radius R. In this case, the sector-shaped area is the destination recommendation range.

[0121] Step S404d: Acquire destination recommendation information based on the destination category and the destination recommendation range, and determine a service recommendation strategy according to the destination recommendation information.

[0122] It can be understood that the above-mentioned destination recommendation information may be information of all destinations corresponding to the destination category within the destination recommendation range.

[0123] In a specific implementation, if the destination category is a restaurant, the destination recommendation information can include the names, menu items, and store reviews of all restaurants within the recommended destination range. The system can also obtain the user's historical meal ordering information to determine the user's dining preferences. It can then sort all restaurants within the recommended destination range in descending order based on the user's dining preferences and store reviews. Based on the sorting results, a corresponding service recommendation strategy is generated, allowing subsequent destination recommendations to be made for the user based on this service recommendation strategy, thereby improving the accuracy and practicality of service recommendations.

[0124] In this embodiment, when the service category to be recommended is a destination recommendation service, the destination category is determined based on user behavior data, and the destination recommendation range is determined based on location information and user intention. Destination recommendation information is then obtained based on the destination category and the destination recommendation range to determine a service recommendation strategy based on the destination recommendation information, so that destination recommendations can be made to users based on the service recommendation strategy in the future, thereby improving the accuracy and practicality of service recommendations.

[0125] In addition, an embodiment of the present application further provides a storage medium, on which an in-vehicle service recommendation program is stored. When the in-vehicle service recommendation program is executed by a processor, the steps of the in-vehicle service recommendation method described above are implemented.

[0126] 6 , which is a structural block diagram of the first embodiment of the in-vehicle service recommendation device of the present application.

[0127] As shown in FIG6 , the vehicle service recommendation device proposed in the embodiment of the present application includes:

[0128] An information determination module 601 is configured to determine the location information and driving status of a vehicle based on driving data corresponding to the vehicle;

[0129] A scene determination module 602 is configured to determine a target driving scene corresponding to the vehicle based on the location information, the driving status, and the user behavior data;

[0130] An attribute determination module 603 is used to determine the scene attribute corresponding to the target driving scene;

[0131] The service recommendation module 604 is configured to determine a service recommendation strategy based on the scene attributes, current time information, and the user behavior data, and perform service recommendations according to the service recommendation strategy.

[0132] In one embodiment, the scene determination module 602 is also used to input the location information and the driving status into a preset scene prediction model to obtain several predicted scenes; determine whether the user triggers the scene trigger conditions corresponding to each predicted scene based on the user behavior data; and determine the target driving scene corresponding to the vehicle based on the judgment result.

[0133] The in-vehicle service recommendation device of this embodiment discloses determining the location information and driving status of a vehicle based on the driving data corresponding to the vehicle; determining the target driving scene corresponding to the vehicle based on the location information, driving status and user behavior data; determining the scene attributes corresponding to the target driving scene; determining the service recommendation strategy based on the scene attributes, current time information and user behavior data, and making service recommendations based on the service recommendation strategy; compared with the existing technology in which the Internet of Vehicles system recommends corresponding in-vehicle services to users based on user operation data and cannot provide personalized services to users, this embodiment determines the target driving scene corresponding to the vehicle based on the location information, driving status and user behavior data of the vehicle, and determines the service recommendation strategy based on the scene attributes, current time information and user behavior data corresponding to the target driving scene, so as to make service recommendations based on the service recommendation strategy, thereby solving the technical problem in the existing technology that the Internet of Vehicles system cannot provide personalized services to users, resulting in a poor driving experience for users.

[0134] Based on the first embodiment of the in-vehicle service recommendation device of the present application, a second embodiment of the in-vehicle service recommendation device of the present application is proposed.

[0135] In this embodiment, the service recommendation module 604 is also used to determine the service category to be recommended based on the scene attributes; obtain the service recommendation time period corresponding to the service category to be recommended; determine whether to trigger vehicle service recommendation based on the service recommendation time period and current time information; if so, determine the service recommendation strategy based on the service category to be recommended and the user behavior data.

[0136] In one embodiment, the service recommendation module 604 is also used to obtain emotional state information corresponding to the target user; determine the service to be recommended based on the emotional state information, the service category to be recommended and the user behavior data; and determine the server recommendation strategy based on the service to be recommended and the service weight information corresponding to the service to be recommended.

[0137] In one embodiment, the service recommendation module 604 is also used to determine a target recommended service from the services to be recommended based on the service weight information corresponding to the services to be recommended; obtain historical service recommendation information, and determine the number of hits of the target recommended service based on the historical service recommendation information; determine the service recommendation method corresponding to the target recommended service based on the number of hits; and determine a service recommendation strategy based on the target recommended service and the service recommendation method.

[0138] This embodiment determines the service category to be recommended based on the scene attributes, and determines whether to trigger vehicle service recommendation based on the service recommendation time period corresponding to the service category to be recommended and the current time information. When triggering vehicle service recommendation, the service recommendation strategy is determined based on the service category to be recommended and user behavior data, so that service recommendations can be made according to the service recommendation strategy subsequently, thereby realizing accurate recommendation of personalized services for users.

[0139] Based on the above-mentioned device embodiments, a third embodiment of the in-vehicle service recommendation device of the present application is proposed.

[0140] In this embodiment, the service category to be recommended includes: destination recommendation service; the service recommendation module 604 is also used to determine the destination category based on the user behavior data if the service category to be recommended is the destination recommendation service; determine the user intention based on the location information and historical driving data; determine the destination recommendation range based on the location information and the user intention; obtain destination recommendation information based on the destination category and the destination recommendation range, and determine the service recommendation strategy based on the destination recommendation information.

[0141] In one embodiment, the service recommendation module 604 is further used to determine a recommended radius based on the area attributes corresponding to the location information, and predict the target driving direction of the vehicle based on the user intention; with the current location as the center of the circle and the target driving direction as the center line, and determine the destination recommendation range based on the recommended radius.

[0142] In this embodiment, when the service category to be recommended is a destination recommendation service, the destination category is determined based on user behavior data, and the destination recommendation range is determined based on location information and user intention. Destination recommendation information is then obtained based on the destination category and the destination recommendation range to determine a service recommendation strategy based on the destination recommendation information, so that destination recommendations can be made to users based on the service recommendation strategy in the future, thereby improving the accuracy and practicality of service recommendations.

[0143] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0144] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0145] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the existing technology, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0146] The above are only some embodiments of the present application and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for recommending in-vehicle services, comprising: Determine the location information and driving status of the vehicle according to the driving data corresponding to the vehicle; Determining a target driving scenario corresponding to the vehicle based on the location information, the driving status, and the user behavior data; Determining scene attributes corresponding to the target driving scene; A service recommendation strategy is determined based on the scene attributes, current time information and the user behavior data, and service recommendations are made according to the service recommendation strategy.

2. The in-vehicle service recommendation method according to claim 1, wherein: The driving data includes driving position, driving speed and remaining fuel, and the position information includes the current driving position information of the vehicle.

3. The in-vehicle service recommendation method according to claim 1, wherein: The driving state includes a constant speed driving state, an accelerated driving state, a decelerated driving state and a stopped driving state.

4. The in-vehicle service recommendation method according to claim 1, wherein: The user behavior data is data generated when the user interacts with the vehicle.

5. The in-vehicle service recommendation method according to claim 1, wherein: The step of determining a target driving scene corresponding to the vehicle based on the location information, the driving status, and the user behavior data includes: Inputting the location information and the driving status into a preset scenario prediction model to obtain a plurality of prediction scenarios; Determine whether the user has triggered the scenario triggering conditions corresponding to each prediction scenario based on user behavior data; The target driving scene corresponding to the vehicle is determined according to the judgment result.

6. The in-vehicle service recommendation method according to claim 5, wherein: The preset scenario prediction model is a pre-built model for predicting the driving scenario in which the vehicle is currently located. The predicted scenarios include parking and rest scenarios and commuting scenarios.

7. The in-vehicle service recommendation method according to claim 1, wherein: The step of determining a service recommendation strategy based on the scene attributes, current time information, and the user behavior data includes: Determining a service category to be recommended based on the scene attributes; Obtaining a service recommendation time period corresponding to the service category to be recommended; Determining whether to trigger vehicle service recommendation based on the service recommendation time period and current time information; If so, a service recommendation strategy is determined based on the service category to be recommended and the user behavior data.

8. The in-vehicle service recommendation method according to claim 7, wherein: The recommended service categories include communication category, entertainment category and basic driving category.

9. The in-vehicle service recommendation method according to claim 8, wherein: The communication category is a service category recommended for a user when talking to others, the entertainment category is a service category recommended for a user when relaxing, and the basic driving category is a service category recommended for a user when driving a vehicle.

10. The in-vehicle service recommendation method according to claim 7, wherein: The step of determining a service recommendation strategy based on the service category to be recommended and the user behavior data includes: Obtain the target user's corresponding emotional state information; determining a service to be recommended based on the emotional state information, the category of the service to be recommended, and the user behavior data; A server recommendation strategy is determined based on the services to be recommended and service weight information corresponding to the services to be recommended.

11. The in-vehicle service recommendation method according to claim 10, wherein: The step of determining a server recommendation strategy based on the service to be recommended and the service weight information corresponding to the service to be recommended includes: Determining a target recommended service from the services to be recommended based on service weight information corresponding to the services to be recommended; Acquire historical service recommendation information, and determine the number of hits of the target recommended service based on the historical service recommendation information; Determining a service recommendation method corresponding to the target recommended service according to the number of hits; A service recommendation strategy is determined based on the target recommendation service and the service recommendation method.

12. The in-vehicle service recommendation method according to claim 7, wherein: The service category to be recommended includes: a destination recommendation service; and the step of determining a service recommendation strategy based on the service category to be recommended and the user behavior data includes: If the service category to be recommended is the destination recommendation service, determining the destination category according to the user behavior data; determining user intent based on the location information and historical driving data; determining a destination recommendation range based on the location information and the user intention; Destination recommendation information is acquired based on the destination category and the destination recommendation range, and a service recommendation strategy is determined according to the destination recommendation information.

13. The in-vehicle service recommendation method according to claim 12, wherein: The step of determining a destination recommendation range based on the location information and the user intention includes: determining a recommended radius based on an area attribute corresponding to the location information, and predicting a target driving direction of the vehicle based on the user's intention; The recommended destination range is determined based on the current position as the center of the circle and the target driving direction as the center line, and according to the recommended radius.

14. An in-vehicle service recommendation device, comprising: An information determination module, configured to determine the location information and driving status of the vehicle based on the driving data corresponding to the vehicle; a scene determination module, configured to determine a target driving scene corresponding to the vehicle based on the location information, the driving status, and user behavior data; An attribute determination module, configured to determine a scene attribute corresponding to the target driving scene; The service recommendation module is used to determine a service recommendation strategy based on the scene attributes, current time information and the user behavior data, and make service recommendations according to the service recommendation strategy.

15. An in-vehicle service recommendation device, comprising: A memory, a processor, and an in-vehicle service recommendation program stored in the memory and executable on the processor, wherein the in-vehicle service recommendation program is configured to implement the steps of the in-vehicle service recommendation method according to any one of claims 1 to 13.

16. A storage medium, wherein: The storage medium stores an in-vehicle service recommendation program, which, when executed by the processor, implements the steps of the in-vehicle service recommendation method according to any one of claims 1 to 13.

Images