Recommendation method and device of dining place, vehicle and storage medium
By obtaining vehicle driving data and user preferences, and actively recommending dining places to users, the limitations of the existing system in dining choices are solved, driving safety and car use experience are improved, and personalized and accurate dining recommendations are achieved.
Patent Information
- Application Number
- CN202411036688.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-31
- Publication Date
- 2024-12-06
AI Technical Summary
The existing in-car multimedia entertainment system cannot meet the needs of modern drivers for personalized, intelligent and interconnected services, especially in terms of dining options, which affects driving safety and car use experience.
By obtaining vehicle driving-related data and user preferences, we can determine whether the preset conditions are met, and we can determine the recommended dining place based on the current location and preferences, and actively recommend it to users, improve the initiative and personalization of dining recommendations, reduce irrelevant recommendations, and ensure information Accuracy and convenience.
It improves driving safety and car use experience, provides dining recommendations that meet users' preferences, reduces user operation steps, and ensures that you can enjoy a good reputation within a reasonable distance.
Smart Images

Figure CN119089022A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of vehicles, and more particularly, to a method, device, vehicle and storage medium for recommending dining places in the field of vehicles. Background Art
[0002] Traditional in-car multimedia entertainment systems mainly provide entertainment and information for passengers. Its core functions include audio playback, video playback and navigation services. Among them, audio playback includes radio, CD player, MP3 player, etc., allowing users to listen to music, news or podcasts. Video playback is to play movies, TV programs or games on models equipped with screens, mainly for passengers in the back seat and the front passenger seat. Navigation services provide users with route planning, real-time traffic information and voice guidance to help users find their destination.
[0003] Existing in-vehicle multimedia entertainment systems can only provide basic services in terms of entertainment and navigation. With the rise of intelligent connected vehicle technology, this limitation has become increasingly prominent and cannot meet the needs of modern drivers for more personalized, intelligent and interconnected services. Summary of the invention
[0004] The present application provides a method, device, vehicle and storage medium for recommending dining places. The method can proactively recommend dining places that meet the user's preferences to the user at an appropriate time, thereby improving the initiative and personalization of dining recommendations, improving driving safety, and improving the user's vehicle experience.
[0005] In a first aspect, a method for recommending dining places is provided, the method comprising: obtaining current driving-related data and user preferences of a vehicle; judging whether the vehicle meets preset conditions for recommending dining places based on the driving-related data; determining a recommended dining place based on the current position of the vehicle and user preferences when it is determined that the vehicle meets the preset conditions; obtaining information on the recommended dining place and recommending the information to the user.
[0006] In the above technical solution, preset conditions for recommending dining places are set, and the driving-related data of the vehicle is obtained to determine whether the vehicle meets the preset conditions. The vehicle is recommended to the user only when the preset conditions are met. This can automatically determine the appropriate recommendation time and recommend dining places to users, thereby improving the initiative of dining recommendations and avoiding the situation where the vehicle's unlimited frequent recommendations affect the user's driving. The recommended dining places are based on user preferences and driving data. On the premise of meeting the current driving scenario, the personalized dining recommendations are improved, making the dining recommendations more in line with user needs and improving user satisfaction and user experience. Obtaining information about recommended dining places and recommending them to users can facilitate users to complete subsequent meal ordering operations based on the recommended information.
[0007] In combination with the first aspect, in some possible implementations, the driving-related data include: driving time, driving duration, user status data and driving route. Based on the driving-related data, it is determined whether the vehicle meets the preset conditions for recommending a dining place, including: determining a recommendation score based on the driving time, driving duration, user status data and driving route; when it is determined that the recommended score is greater than the preset score, determining that the vehicle meets the preset conditions for recommending a dining place.
[0008] In the above technical solution, the recommendation score is determined by driving duration, driving time, user status data and driving route, and whether the preset conditions of the recommended dining place are met can be judged, so that the recommendation time can be determined comprehensively and intelligently. It can more accurately grasp the needs of users, reduce irrelevant or inappropriate recommendations, and improve user satisfaction.
[0009] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, a recommended score is determined based on driving time, driving duration, user status data and driving route, including: determining a first score corresponding to the driving time based on the proximity of the driving time to a preset dining time period; determining a second score corresponding to the driving duration based on the difference between the driving duration and the preset duration; determining a third score corresponding to the user status data based on the user's hunger level represented by the user status data; determining a fourth score corresponding to the driving route based on dining place data around the driving route; and determining a recommended score based on the first score, the second score, the third score and the fourth score.
[0010] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, the driving-related data includes the current position of the vehicle. When it is determined that the vehicle meets the preset conditions, the recommended dining place is determined in combination with the current position of the vehicle and the user's preferences, including: when it is determined that the vehicle meets the preset conditions, obtaining the dining places within a preset range near the current position of the vehicle; and selecting the recommended dining place that meets the user's preferences from the dining places.
[0011] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, a recommended dining place that meets the user's preferences is selected from dining places, including: determining the distance between the dining place and the current location; obtaining user feedback information of the dining place; calculating the similarity between the dining place and the user's preferences; calculating the recommendation weight of the dining place based on the distance, user feedback information and similarity; and selecting a recommended dining place from the dining places based on the recommendation weight.
[0012] In the above technical solution, distance, user feedback information and user preferences are comprehensively considered when determining the recommended dining places, and a comprehensive recommendation index, namely the above-mentioned recommendation weight, is generated. The recommended dining places are determined based on this recommendation weight that comprehensively considers distance, user feedback information and user preferences. This can ensure that users can enjoy a dining experience that is in line with their personal preferences and has a good reputation within a reasonable distance.
[0013] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, after obtaining the information of the recommended dining place and before recommending the information to the user, the method also includes: when it is determined that the information is missing key information, initiating an inquiry to the dining place based on the key information to complete the information of the recommended dining place.
[0014] In the above technical solution, by actively asking the recommended dining places for missing key information, it is ensured that the information of the dining places recommended to the user is the latest and most accurate. This reduces the number of user inquiries and avoids safety issues caused by driving analysis due to user inquiries. Complete and accurate information can help users make more informed dining decisions.
[0015] In combination with the first aspect and the above-mentioned implementation methods, in some possible implementation methods, after obtaining information about recommended dining places and recommending the information to the user, the method also includes: receiving ordering information sent by the user based on the information; initiating an order to the recommended dining place based on the ordering information, and calling the vehicle's payment system to pay for the order.
[0016] In the above technical solution, during driving, users can simply and quickly complete the ordering and payment operations based on the information of recommended dining places recommended by the vehicle at the right time. Users do not need to manually search, browse, and compare orders when they feel hungry, which reduces the user's operation steps and improves driving safety.
[0017] In summary, in this application, by judging whether the preset conditions of the recommended dining place are met through driving duration, driving time, and user status data, the recommendation time can be determined comprehensively and intelligently, and the dining place that meets the user's preferences can be actively recommended to the user when the preset conditions are met, thereby improving the initiative and personalization of dining recommendations, improving driving safety, and improving the user's car experience. In addition, when determining the recommended dining place, the distance, user feedback information, and user preferences are comprehensively considered, which can ensure that the user can enjoy a dining experience that meets personal preferences and has a good reputation within a reasonable distance. When key information is missing, the recommended dining place is actively asked, reducing the user's inquiry operations. Obtaining information about recommended dining places and recommending them to users can facilitate users to complete subsequent meal ordering operations based on the recommended information.
[0018] In a second aspect, a device for recommending dining places is provided, which includes: an acquisition module for acquiring the current driving-related data of the vehicle and the user's preferences; a judgment module for judging whether the vehicle meets the preset conditions for recommending dining places based on the driving-related data; a determination module for determining the recommended dining places in combination with the current position of the vehicle and the user's preferences if it is determined that the vehicle meets the preset conditions; and a recommendation module for obtaining information on recommended dining places and recommending the information to the user.
[0019] In combination with the second aspect, in some possible implementations, the driving-related data include: driving time, driving duration, user status data and driving route, and the judgment module is specifically used to determine the recommended score based on the driving time, driving duration, user status data and driving route; when it is determined that the recommended score is greater than the preset score, it is determined that the vehicle meets the preset conditions for recommending a dining place.
[0020] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, the judgment module is specifically used to determine a first score corresponding to the driving time based on the proximity between the driving time and the preset dining time period; determine a second score corresponding to the driving time based on the difference between the driving time and the preset time; determine a third score corresponding to the user status data based on the user's hunger level represented by the user status data; determine a fourth score corresponding to the driving route based on the dining place data around the driving route; and determine a recommended score based on the first score, the second score, the third score and the fourth score.
[0021] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, the determination module is specifically used to, when it is determined that the vehicle meets the preset conditions, obtain dining places within a preset range near the current position of the vehicle; and select recommended dining places that meet the user's preferences from the dining places.
[0022] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, the determination module is specifically used to determine the distance between the dining place and the current location; obtain user feedback information of the dining place; calculate the similarity between the dining place and the user preference; based on the distance, user feedback information and similarity, calculate the recommendation weight of the dining place; based on the recommendation weight, select a recommended dining place from the dining places.
[0023] In combination with the second aspect and the above-mentioned implementations, in some possible implementations, the device further includes: a completion module, which is used to initiate a query to the dining venue based on the key information to complete the information of the recommended dining venue when it is determined that the information is missing key information.
[0024] In combination with the second aspect and the above-mentioned implementation methods, in some possible implementation methods, the device also includes an ordering module, which is used to receive ordering information sent by the user based on the information after obtaining information about recommended dining places and recommending the information to the user; initiating an order to the recommended dining place based on the ordering information, and calling the vehicle's payment system to pay for the order.
[0025] In a third aspect, a vehicle is provided, comprising a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, so that the vehicle executes the method in the first aspect or any possible implementation of the first aspect.
[0026] In a fourth aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the method in the first aspect or any possible implementation of the first aspect.
[0027] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes the method in the above-mentioned first aspect or any possible implementation manner of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] Figure 1 It is a schematic flow chart of a method for recommending dining places provided in an embodiment of the present application.
[0029] Figure 2 It is a schematic flowchart of an implementation method for determining a recommendation score provided in an embodiment of the present application.
[0030] Figure 3 It is a structural schematic diagram of a dining place recommendation device provided in an embodiment of the present application.
[0031] Figure 4 It is a structural schematic diagram of a vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION
[0032] The technical solution in the present application will be described clearly and in detail below in conjunction with the accompanying drawings. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B: "and / or" in the text is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, "multiple" means two or more than two.
[0033] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.
[0034] Although existing in-vehicle multimedia entertainment systems provide basic services in terms of entertainment and navigation, their functions are relatively simple, mainly focusing on audio and video playback, and basic route navigation. With the rise of intelligent connected vehicle technology, this limitation has become increasingly prominent and cannot meet the needs of modern drivers for more personalized, intelligent and interconnected services.
[0035] Especially in terms of dining options, existing systems often rely on users to actively search and trigger recommendations, and lack the ability to actively recommend and personalize suggestions. During long-distance driving, this may cause drivers to miss the best dining places or be distracted by looking for dining places, affecting driving safety.
[0036] Based on this, the present application proposes a method for recommending dining places, which can proactively recommend dining places that meet the user's preferences to the user at the right time, thereby improving the initiative and personalization of dining recommendations, improving driving safety, and improving the user's car experience.
[0037] Figure 1 1 is a schematic flow chart of a method for recommending dining places provided in an embodiment of the present application. The method is applied to a vehicle.
[0038] For example, Figure 1 As shown, the method 100 includes:
[0039] Step 101, obtaining the vehicle's current driving related data and user preferences;
[0040] Step 102, based on the driving related data, determining whether the vehicle meets the preset conditions for recommending a dining place;
[0041] Step 103, when it is determined that the vehicle meets the preset conditions, a recommended dining place is determined in combination with the current location of the vehicle and the user's preference;
[0042] Step 104, obtaining information of recommended dining places and recommending the information to the user.
[0043] exist Figure 1In the illustrated embodiment, preset conditions for recommending dining places are set, and the driving-related data of the vehicle is obtained to determine whether the vehicle meets the preset conditions. When the preset conditions are met, the vehicle is recommended to the user. This can automatically determine the appropriate recommendation time and recommend dining places to the user, thereby improving the initiative of dining recommendations and avoiding the situation where the vehicle's unlimited frequent recommendations affect the user's driving. The recommended dining places are based on user preferences and driving data. On the premise of meeting the current driving scene, the personalized dining recommendations are improved, making the dining recommendations more in line with user needs, improving user satisfaction and vehicle experience. Obtaining information about recommended dining places and recommending them to users can facilitate users to complete subsequent meal ordering operations based on the recommended information.
[0044] Below Figure 1 The specific implementation methods of each step in the embodiment shown are described as follows:
[0045] In step 101, driving related data may include two categories: vehicle operation data and user status data during driving, wherein the vehicle operation data is data generated by the vehicle during the user driving the vehicle, and the user driving status data is data describing the user status during the driving of the vehicle. The user may also be understood as the driver of the vehicle.
[0046] The vehicle operation data may specifically include the vehicle's current location, the vehicle's driving route, the vehicle's driving time, vehicle speed, fuel consumption and other data.
[0047] The vehicle includes a GPS positioning system, which is used to collect the current position of the vehicle in real time during the driving process of the vehicle, and the current position of the vehicle collected by the GPS positioning system can be obtained. The vehicle is equipped with a speedometer or radar and other devices, which are used to collect the speed of the vehicle in real time during the driving process of the vehicle, and the speed of the vehicle collected by the speedometer or radar can be obtained. The vehicle also includes an on-board navigation system. The user can input the destination into the navigation system before driving the vehicle. The on-board navigation system plans the driving route according to the destination and the current position of the vehicle, and the driving route planned in the on-board navigation system can be obtained. The vehicle is equipped with an instrument or a large screen of the car computer, which is used to display the driving time, fuel consumption and other data in real time, and the driving time and fuel consumption and other data can be obtained from the instrument or the large screen of the car computer.
[0048] It is understandable that the current position of the vehicle is updated in real time while the vehicle is driving, and the driving route planned in the vehicle navigation system will be updated as the current position of the vehicle is updated, that is, the driving route in the vehicle navigation system is the route between the current position of the vehicle and the destination.
[0049] User status data includes but is not limited to: user physiological data, user behavior data, user voice data and other data.
[0050] The user can wear a wearable device such as a bracelet or a watch to monitor the user's physiological data in real time. A connection is established between the vehicle and the wearable device, and the vehicle can obtain the user's physiological data monitored by the connected bracelet, watch or other wearable device. The vehicle is equipped with a camera to collect images in real time during the driving process of the vehicle. The collected images may include user behavior data, and the user behavior data collected by the camera can be obtained. The vehicle is equipped with a microphone or other voice collection device to collect the user's voice in real time during the driving process of the vehicle, and the user's voice collected by the microphone or other voice collection device can be obtained.
[0051] In step 102, the preset condition may be a condition for determining whether the user needs to dine. After the vehicle obtains the above-mentioned driving-related data, it determines whether the current user needs to dine based on the driving-related data. If it is determined that the user needs to dine, it is determined that the vehicle meets the preset conditions for recommending a dining place.
[0052] In one possible implementation, the driving-related data includes: driving time, driving duration, user status data and driving route. Based on the driving-related data, it is determined whether the vehicle meets the preset conditions for recommending a dining place, including: determining a recommendation score based on the driving time, driving duration, user status data and driving route; when it is determined that the recommendation score is greater than the preset score, it is determined that the vehicle meets the preset conditions for recommending a dining place.
[0053] Among them, driving time is the length of time the user continuously drives the vehicle, which is an important parameter for evaluating the user's status. The driving time can be calculated based on the driving time when the user starts driving the vehicle and the current driving time. Driving time refers to the specific time of the day when the vehicle is driving, such as 12:00, 13:00, etc. User status data refers to the user's data collected by the vehicle when the user drives the vehicle, including but not limited to user physiological data, user behavior data, user voice data and other data. The driving route is the driving route planned by the on-board navigation system in the vehicle according to the destination and the current position of the vehicle, which is used to instruct the user to drive the vehicle to the destination. Driving time, driving time, user status data and driving route can all be used as factors affecting whether the vehicle recommends dining places.
[0054] Specifically, different scoring rules may be set for different data. After obtaining the above driving-related data, the scoring rule corresponding to each type of data may be determined first, and the score corresponding to the data may be determined based on the scoring rule of the data. Then, the recommended score may be determined based on the score of each type of data.
[0055] In one possible implementation, a recommendation score is determined based on driving time, driving duration, user status data, and driving route, such as Figure 2 As shown, including the following S11 to S15:
[0056] S11, determining a first score corresponding to the driving time based on the proximity between the driving time and the preset dining time period.
[0057] Among them, the preset dining time periods are usually set based on the normal dining time periods of the human body. For example, the preset dining time periods can be breakfast time (7:00-9:00 in the morning), lunch time (11:00-13:00 at noon) and dinner time (17:00-19:00 in the evening).
[0058] The rule for the score corresponding to the driving time may be: based on the proximity of the driving time to the preset dining period, the first score corresponding to the driving time is determined. The closer the driving time is to the preset dining period (i.e., the higher the proximity), the higher the first score, and the first score is the highest when the driving time is within the preset dining period.
[0059] In some embodiments, the preset dining time period can also be determined based on user preferences. For example, the vehicle can obtain the user's historical dining times, analyze and count the historical dining times, obtain the user's preferred dining time period, and use the user's preferred dining time period as the preset dining time period.
[0060] For example, assuming that the user's historical dining times are 9:00, 9:30, 10:00; 2:00, 2:30, 3:00; 21:00, 21:30, 22:00, the user's preferred dining time can be determined by statistics and analysis of these time points. The user's preferred breakfast time can be determined, for example, between 9:00 and 10:00; the user's preferred lunch time can be determined, for example, between 14:00 and 15:00; the user's preferred dinner time can be determined, for example, between 21:00 and 22:00. The preset dining time can include: breakfast time 9:00 to 10:00, lunch time 14:00 to 15:00, dinner time 21:00 to 22:00.
[0061] After the driving time is obtained, the difference between the driving time and the meal time closest to the driving time in the preset meal time period can be calculated, and the proximity between the driving time and the preset meal time period can be determined based on the difference. For example, a proximity function can be defined, which converts the difference into proximity. The proximity function can be a decreasing function, that is, the smaller the difference, the higher the proximity.
[0062] Exemplarily, the preset dining time periods include: breakfast time period 9:00 to 10:00, lunch time period 14:00 to 15:00, dinner time period 21:00 to 22:00, and the driving time is 13:30. The driving time and the dining time period closest to the driving time are 14:00, and the difference between the two is 30 minutes. Based on the difference of 30 minutes and the defined proximity function, the proximity between the driving time and the preset dining time period is determined, for example, 70%. For every 10 minutes the difference decreases, the proximity increases by 10%. The score can be a score of 10 points, and the proximity can be converted into a score of 10 points. Assuming that 70% can be converted into 7, the first score corresponding to the driving time is 7 points.
[0063] S12, determining a second score corresponding to the driving time based on the difference between the driving time and the preset time.
[0064] The preset duration can be set according to general driving rules and ergonomic principles to represent the maximum duration of a user's safe continuous driving. If the user's continuous driving duration exceeds the preset duration, it can be determined that the user is prone to fatigue, hunger, etc. during driving, which affects the user's safe driving. At this time, the user needs to rest and eat to ensure safe driving.
[0065] The scoring rule corresponding to the driving time may be: based on the difference between the driving time and the preset time, determine the second score corresponding to the driving time. The greater the difference between the driving time and the preset time, the higher the second score. In some embodiments, when the difference reaches the target value, the second score is the maximum, and when it exceeds the target value, the second score remains unchanged, which is the maximum score.
[0066] It is understandable that when the difference between the driving time and the preset time is larger, it means that the user has been driving continuously for a longer time, the user is more likely to become tired, hungry, etc., and the current time is more suitable for making recommendations to the user.
[0067] For example, the preset duration is 1 hour, the acquired continuous driving time of the user is 3 hours, the difference between the driving time of 3 hours and the preset time of 1 hour is 2 hours, and the second score determined based on the difference of 2 hours can be 8 points, for example.
[0068] S13: Determine a third score corresponding to the user status data based on the user hunger level represented by the user status data.
[0069] Among them, the greater the user's hunger level is, the more the user needs to eat, that is, the more appropriate it is to make recommendations to the user.
[0070] The rule for the score corresponding to the user status data may be to determine the third score corresponding to the user status data based on the user's hunger level represented by the user status data. The greater the user's hunger level, the higher the third score. In some embodiments, the user's hunger level has a maximum value, and when the user's hunger level is the maximum, the corresponding third score is the maximum.
[0071] The user status data may include at least one of the following data: the user's blood sugar level, the frequency of the user eating snacks, the frequency of food mentioned in the user's voice or the frequency of words expressing hunger, etc. The vehicle may determine the user's hunger level represented by the user status data based on the user's blood sugar level, the frequency of the user eating snacks, the frequency of food mentioned in the user's voice or the frequency of words expressing hunger. The higher the blood sugar level, the lower the user's hunger level, and the higher the frequency of the user eating snacks and the frequency of food mentioned in the user's voice or the frequency of words expressing hunger, the higher the user's hunger level.
[0072] Specifically, an inverse relationship between the blood sugar value and the user's hunger level can be set. For example, when the blood sugar value is lower than the first threshold, the user's hunger level is high (for example, 80%); when the blood sugar value is higher than the second threshold, the user's hunger level is low (for example, 20%). The intermediate value can be allocated in a linear or nonlinear ratio. Set a proportional relationship between the frequency of eating snacks and the user's hunger level. For example, if snacks are eaten more than 3 times per hour, the frequency is high, and the user's hunger level is high (for example, 70%); if snacks are almost not eaten, the frequency is low, and the user's hunger level is low (for example, 10%), and the intermediate value can be allocated in a linear or nonlinear ratio. Voice mention of food frequency score: Set a proportional relationship between the frequency of food mentions and the user's hunger level. For example, if food is mentioned more than 4 times per hour, the user's hunger level is high (for example, 60%); if food is almost not mentioned, the user's hunger level is low (for example, 10%), and the intermediate value can be allocated in a linear or nonlinear ratio.
[0073] Exemplarily, the user status data includes the user's blood sugar value, which is 3.9mmol / L, which is lower than the preset first threshold value of 4mmol / L. The user's hunger level is determined to be 80%. For every 0.1mmol / L decrease in blood sugar, the user's hunger level increases by 5%, until the user's hunger level increases to 100%, reaching a maximum value. The score can be a score of 10, and the user's hunger level of 80% can be converted into a score of 10. Assuming that 80% can be converted into 8, a third score of 8 corresponding to the user status data is obtained.
[0074] In some embodiments, the user status data may include multiple data among the above data, and the user hunger level represented by the various data may be determined, and then the average or maximum value is taken to obtain the target user hunger level, and then the third score is determined based on the target user hunger level.
[0075] S14, determining a fourth score corresponding to the driving route based on the dining venue data around the driving route.
[0076] The purpose of the user driving the vehicle may also be to travel and play. In this case, the user's dining needs may also include the user's desire to taste local specialties and popular foods, not just the user's need to eat when hungry. Therefore, the fourth score corresponding to the driving route may also be determined based on the dining venue data around the driving route.
[0077] The dining venue data around the driving route may include: distribution data of the dining venues around the driving route and / or evaluation data of the dining venues. The distribution data may specifically be the number of dining venues, and the evaluation data may specifically be a score reflecting the quality, characteristics or popularity of the dining venues.
[0078] The rule for the score corresponding to the driving route may be: based on the number and / or score of dining places around the driving route, the fourth score corresponding to the driving route is determined, wherein the greater the number, the greater the fourth score, and the higher the score, the greater the fourth score.
[0079] It is understandable that when there are more dining places, it indicates that the area has abundant catering services and is more likely to meet the diverse needs of users. It is more appropriate to recommend to users at this time, and the fourth score increases accordingly. The score of the dining place can be a five-point score. The higher the score, the better the quality, the more distinctive or the more popular the dining place in the area, and the corresponding fourth score increases.
[0080] Exemplarily, the information on dining places around the driving route is the number of dining places within 1 kilometer around the driving route. In this case, the fourth score corresponding to the driving route can be determined as follows: when there are more than 10 restaurants within 1 kilometer around the driving route, the fourth score can be determined as 8 points; if there are 5-10 restaurants within 1 kilometer around the driving route, the fourth score can be determined as 6 points; if there are less than 5 restaurants, the fourth score can be determined as 3 points.
[0081] Exemplarily, the information on dining places around the driving route is the scores of dining places within 1 kilometer around the driving route. In this case, the fourth score corresponding to the driving route can be determined as follows: if the highest score of dining places within 1 kilometer around the driving route is above 4.5 points (out of 5 points), the fourth score can be determined as 9 points; if the highest score is 4-4.4 points, the fourth score can be determined as 7 points; if the highest score is 3.5-3.9 points, the fourth score can be determined as 5 points; if the highest score is lower than 3.5 points, the fourth score can be determined as 2 points.
[0082] In some embodiments, when the information about dining places around the driving route includes the number and scores of dining places within 1 km around the driving route, a fourth score can be determined based on the number and the score respectively, and the largest score is used as the final fourth score.
[0083] S15, determining a recommendation score based on the first score, the second score, the third score, and the fourth score.
[0084] The first score, the second score, the third score and the fourth score may each correspond to a basic coefficient, and the sum of the basic coefficients corresponding to the four scores is 1. The recommended score may be calculated based on the first score, the second score, the third score and the fourth score and their corresponding basic coefficients.
[0085] In a possible implementation, the first score, the second score, the third score and the fourth score each correspond to a basic coefficient, and a recommended score is determined based on the first score, the second score, the third score and the fourth score, including: when the user's hunger level is less than a preset level threshold, reducing the basic coefficient corresponding to the first score and the basic coefficient corresponding to the second score, and increasing the basic coefficient corresponding to the fourth score; wherein the sum of the basic coefficients corresponding to the adjusted scores is equal to the sum of the basic coefficients corresponding to the scores before adjustment; and determining the recommended score based on the first score, the second score, the third score, the fourth score and the basic coefficients corresponding to the adjusted scores.
[0086] The preset level threshold is used to determine whether the user's hunger level has reached the critical point of needing to eat. When the user's hunger level is less than the preset level threshold, it can be determined that the user does not need to eat at the moment and the recommendation strategy needs to be adjusted. The basic coefficient is used to characterize the contribution of different data in the final recommendation decision, and the basic coefficient can be adjusted dynamically.
[0087] When it is determined that the hunger level is less than a preset threshold, it can be intuitively indicated that the user does not need a meal at the moment. At this time, the proportion of factors triggering recommendations based on the user's need for a meal in the final recommendation is reduced. These factors may be, for example, driving time and / or driving duration.
[0088] It is understandable that when the user's hunger level is low, if the first score corresponding to the driving time and / or the second score corresponding to the driving duration are high, the system will still recommend to the user, but the user does not need to eat at the moment. At this time, the recommendation is unnecessary. In order to reduce unnecessary recommendations to the user, when the user's hunger level is low, the basic coefficients of the driving time (first score) and the driving duration (second score) can be reduced to reduce the proportion of the driving time and driving duration in the final recommendation, and the basic coefficient of the driving route (fourth score) can be increased to increase the proportion of the driving route in the final recommendation. Avoid triggering unnecessary recommendations due to long driving time or driving duration when the user is not in urgent need of a meal, and instead focus more on recommending restaurants with rich surrounding catering services and good reviews, providing more diverse and personalized choices.
[0089] For example, assuming that the preset level threshold is 40%, the basic coefficients are initially set to correspond to the first score: 0.25, the second score: 0.25, the third score: 0.3, the fourth score: 0.2, and the total is 1.0. When the user's hunger level is lower than 40%, the system adjusts the basic coefficients of the first and second scores to 0.05, and the basic coefficient of the fourth score to 0.6, keeping the total at 1.0.
[0090] The specific steps for determining the recommended score may be: multiplying the first score by the adjusted basic coefficient corresponding to the first score to obtain a first value, multiplying the second score by the adjusted basic coefficient corresponding to the second score to obtain a second value, multiplying the third score by the adjusted basic coefficient corresponding to the third score to obtain a third value, multiplying the fourth score by the adjusted basic coefficient corresponding to the fourth score to obtain a fourth value, and adding the first value, the second value, the third value, and the fourth value to obtain the sum as the recommended score.
[0091] For example, the first score is 7 points, the second score is 8 points, the third score is 4 points, and the fourth score is 9 points. Under the adjusted basic coefficient, the recommended score is calculated as follows: 7*0.05+8*0.05+4*0.3+9*0.6=7.35 points.
[0092] In the above method, when the user's hunger level is less than the preset level threshold, by reducing the basic coefficients of the first score and the second score, it is possible to avoid making recommendations when the user's hunger level is low simply because the driving time or duration is long, thereby reducing disturbance to the user and improving the accuracy of the recommendation. Increasing the basic coefficient of the fourth score means that the recommendation will pay more attention to the distribution and quality of dining places around the driving route, which helps to provide better quality and more user-friendly dining recommendations when the user does not have an urgent need for dining. Dynamically adjusting the basic coefficient can provide recommendations that are more in line with the user's expectations based on the user's current actual status and needs, avoid excessive or insufficient recommendations, and thus improve the overall user experience.
[0093] The recommendation score is used to determine whether a recommendation can be made to the user at present. The preset score is a maximum score set in advance for determining that a recommendation cannot be made to the user at present. When the recommendation score is greater than the preset score, it is determined that a recommendation can be made to the user at present, i.e., it is determined that the vehicle meets the preset conditions for recommending a dining place.
[0094] Exemplarily, the preset score is 5 points. If the recommended score calculated in the above embodiment is 7.35 points, and the recommended score 7.35 points is greater than the preset score of 5 points, it is determined that the vehicle meets the preset conditions for recommending a dining place.
[0095] In the above method, the recommendation score is determined by driving duration, driving time, user status data and driving route, and whether the preset conditions of the recommended dining place are met can be judged, so that the recommendation time can be determined comprehensively and intelligently. It can more accurately grasp the needs of users, reduce irrelevant or inappropriate recommendations, and improve user satisfaction.
[0096] In some embodiments, when the driving-related data includes only one type of data, judging whether the vehicle meets the preset conditions for recommending a dining place based on the driving-related data may further include the following steps S21 to S23:
[0097] S21, when the driving-related data includes driving time, when it is determined that the driving time is greater than a preset time, determining that the vehicle meets a preset condition.
[0098] It is understandable that if the user's continuous driving time exceeds the preset time, it can be determined that the user is prone to fatigue, hunger, etc. during driving, which affects the user's safe driving. At this time, the user needs to rest and eat to ensure safe driving. Therefore, when the user's continuous driving time exceeds the preset time, it can be determined that the current vehicle meets the preset conditions for recommending dining places.
[0099] For example, the preset duration is 2 hours. The obtained driving duration of the user continuously driving the vehicle is 2.5 hours, which is greater than 2 hours. At this time, it is determined that the user's continuous driving duration is greater than the preset duration, the user needs to rest and eat, and the vehicle meets the preset conditions for recommending a dining place.
[0100] S22, when the driving-related data includes the current driving time, if it is determined that the driving time is within the preset dining time period, it is determined that the vehicle meets the preset conditions.
[0101] It is understandable that when the driving time is within the preset dining time period, it can be determined that the user needs to eat, and at this time it is necessary to recommend a dining place to the user. If the user does not eat on time, hunger and hypoglycemia are likely to occur, affecting driving safety. Therefore, when it is determined that the driving time is within the preset driving time period, it can be determined that the vehicle meets the preset conditions for recommending a dining place.
[0102] Exemplarily, the preset dining time periods include: breakfast period from 9:00 to 10:00, lunch period from 14:00 to 15:00, and dinner period from 21:00 to 22:00. The acquired driving time is 21:09. 21:09 is within the range of 21:00 to 22:00 during the dinner period. It can be determined that the driving time is within the preset dining time period, the user needs to eat, and the vehicle meets the preset conditions for recommending a dining place.
[0103] S23, when the driving-related data includes user status data, in the case where it is determined that the user status data indicates that the user is in a hungry state, determining that the vehicle meets a preset condition.
[0104] As in the above embodiment, the user status data includes but is not limited to user physiological data, user behavior data, user voice data and other data. The vehicle can determine whether the user is currently in a hungry state based on the collected user status data.
[0105] Specifically, the user's physiological data may be, for example, the user's blood sugar level, heart rate and other data. The vehicle may determine that the user is in a hungry state when it determines that the blood sugar level is lower than a preset blood sugar threshold and / or the heart rate is higher than a preset heart rate threshold. The user's behavioral data may be, for example, the frequency with which the user eats snacks. The vehicle may determine that the user is in a hungry state when the frequency with which the user eats snacks is greater than a preset frequency. When the user's status data includes the user's voice, the vehicle may also analyze the content of the user's voice through voice recognition technology. If the content of the user's voice frequently mentions food or contains text expressing hunger, it is determined that the user is in a hungry state. When the user is in a hungry state, the user usually needs to eat, and the vehicle is determined to meet the preset conditions.
[0106] There is a situation where the user has not eaten for a long time before driving. In this case, even if the driving time of the user does not exceed the preset time and the driving time is not within the preset dining time, the user may be hungry and need to eat. In this case, it can be determined based on the user status data that the user is hungry, and timely dining recommendations can be implemented when the user is hungry.
[0107] For example, the user did not eat lunch and started driving the vehicle at 3:20. The current driving time is 3:50. The driving time does not exceed the preset time, and the driving time is not in the preset meal period. At this time, it is impossible to determine whether the vehicle meets the preset conditions based on the driving time and driving time. Then, it can be determined whether the user is hungry based on the acquired user status data. Assuming that the driving-related data includes the user's blood sugar value, which is 3.9mmol / L, and the preset blood sugar threshold is 6.0mmol / L, it is determined that the user's blood sugar value of 3.9mmol / L is lower than the preset blood sugar threshold of 6.0mmol / L, and it is determined that the user is hungry and needs to eat, and the vehicle meets the preset conditions for recommending a dining place.
[0108] In some embodiments, the purpose of the user driving the vehicle may be to travel and play. In this case, the user's dining needs may also include the user's desire to taste local specialties and popular foods, not just the user's need to eat when hungry. The driving-related data may also include the vehicle's current location. If there are local specialty restaurants or popular restaurants near the current location, it is determined that the vehicle meets the conditions for recommending a restaurant to the user.
[0109] In the above method, by judging whether the preset conditions for recommending dining places are met through driving duration, driving time, and user status data, the timing of recommendation can be determined comprehensively and intelligently. Among them, when the driving time exceeds the preset time, it is determined that the vehicle meets the preset conditions and recommends it to the user, which can reduce the driving risk caused by hunger due to long-term driving. When the driving time is in the preset dining period, it is determined that the vehicle meets the preset conditions and recommends it to the user, which can achieve dining recommendations that meet the user's dining habits. When the user status data indicates that the user is in a hungry state, it is determined that the vehicle meets the preset conditions and recommends it to the user, which can achieve timely recommendations when the user is in a hungry state.
[0110] In step 103 , when the vehicle meets the preset conditions for recommending dining places, the vehicle starts to determine the recommended dining places to recommend to the user.
[0111] Specifically, the vehicle is integrated with an online service platform, which may be a map service platform or a catering service platform, etc. These online service platforms usually include a database of dining places that cooperate with them. After determining that the preset conditions for recommending dining places are met, the vehicle can check whether the vehicle is currently connected to the Internet. If the vehicle is not connected to the Internet, it will first connect to the Internet. After connecting to the Internet, the vehicle can access the above-mentioned online service platform through an API (application programming interface), obtain dining places that cooperate with the online service platform, and then determine the recommended dining place from the obtained dining places in combination with the current location of the vehicle and user preferences.
[0112] A possible implementation is characterized in that the driving-related data includes the current position of the vehicle. When it is determined that the vehicle meets preset conditions, the recommended dining place is determined in combination with the current position of the vehicle and the user's preferences, including: when it is determined that the vehicle meets the preset conditions, obtaining dining places within a preset range near the current position of the vehicle; and selecting a recommended dining place that meets the user's preferences from the dining places.
[0113] The preset range is a range set in advance, and specifically can be a range obtained by taking the current position of the vehicle as the center and the preset distance as the radius. For example, the preset distance can be 6 kilometers, and the preset range can be a circular range obtained by taking the current position of the vehicle as the center and the radius of 6 kilometers.
[0114] In some embodiments, the driving-related data also includes the driving route of the vehicle, and the preset range may also be a strip area along the driving route determined based on the driving route and the preset distance, with the width defined by the preset distance. Because the online service platform includes dining places in various areas, the user currently needs to dine, and the vehicle has a certain driving route, it is necessary to filter out dining places near the current location and on the driving route from the dining places on the online service platform as candidates, to ensure that the recommended dining places determined later are near the current location and conform to the driving route, to ensure that the user eats in time while reducing the impact of the user's dining on the driving route and reducing extra distance.
[0115] Specifically, after determining that the preset conditions are met, the vehicle constructs a request including the coordinates of the vehicle's current location and the parameters of the preset range, and then sends the request to the online service platform, and the request is used to instruct the online service platform to return information about all dining places within the preset range near the current location. After receiving the request, the online service platform will filter out dining places that meet the conditions from the database based on the provided coordinates of the current location and the parameters of the preset range, and send the dining places to the vehicle, so that the vehicle obtains the dining places within the preset range near the current location.
[0116] After obtaining the dining venues, the vehicle can calculate the similarity between each dining venue and the user's preferences, and select the dining venue with the greatest similarity to the user's preferences as the recommended dining venue. The user's preferences may specifically include: taste preferences, environment preferences, price preferences, etc.
[0117] For example, the user's preferences are: spicy taste, quiet environment, and average price of about 50 yuan per person. The obtained dining places include: Restaurant A, Restaurant B, and Restaurant C. Among them, Restaurant A has a light taste, a quiet environment, and an average price of 60 yuan per person, and the calculated similarity with the user's preferences is 66%. Restaurant B has a spicy taste, a quiet environment, and an average price of 50 yuan per person, and the calculated similarity with the user's preferences is 89%. Restaurant C has a spicy taste, a quiet environment, and an average price of 55 yuan per person, and the calculated similarity with the user's preferences is 98%. The vehicle selects Restaurant C with the highest similarity from Restaurant A, Restaurant B, and Restaurant C as the recommended dining place.
[0118] In some embodiments, the conditions for screening recommended dining places include not only user preferences, but also sometimes need to combine distance and evaluation information of the dining place to jointly determine a recommended dining place that can bring a better dining experience to the user. The following embodiment describes this situation in detail:
[0119] In one possible implementation, a recommended dining place that meets user preferences is selected from dining places, including: determining the distance between the dining place and the current location; obtaining user feedback information about the dining place; calculating the similarity between the dining place and the user preference; calculating the recommendation weight of the dining place based on the distance, user feedback information and similarity; and selecting a recommended dining place from the dining places based on the recommendation weight.
[0120] When recommending dining places to users, the distance between the dining places and the current location is a factor that needs to be considered. Because dining places are places within a preset range near the current location of the vehicle, the distances between each dining place and the current location of the vehicle are not the same. When it is determined that the user is hungry, especially for users with hypoglycemia, recommending a closer dining place to the user can ensure that the user completes the meal in time, replenishes energy, and avoids driving risks caused by hypoglycemia due to failure to eat in time. The online service platform usually includes the location of dining places, and the location of the dining places obtained by the above screening can be obtained from the online service platform, and then the distance between each dining place and the current location is determined based on the location of each dining place and the current location of the vehicle.
[0121] The distance between each dining place and the current location may specifically be the distance of the driving route from the current location to the dining place. The current location may be located in the map service platform, and then the location of each dining place may be input into the map service platform in sequence. The map service platform uses its internal route planning algorithm to plan the optimal driving route based on the current location of the vehicle and the locations of the recommended dining places, thereby obtaining the distance between the current location and each dining place.
[0122] The online service platform usually also includes user feedback information of each dining place, where the user feedback information can be the feedback information of other users who have dined at the dining place in the historical period, and the user feedback information can be the rating of the dishes of the dining place by other users based on the dining experience, or it can be the comprehensive rating of the overall environment, service and dishes of the dining place by other users based on the dining experience. The rating system has a unified standard, assuming that the full score is 5 points.
[0123] User feedback information can usually reflect the quality of dining places. When recommending dining places to users, the quality of the recommendation needs to be guaranteed, so the user feedback information of dining places is also a factor that needs to be considered. Online service platforms usually include user feedback information of dining places, so user feedback information of each dining place in the online service platform can be obtained.
[0124] The recommendation also needs to be personalized to ensure that the recommended dining places meet the user's preferences. Therefore, the similarity between the dining places and the user's preferences is also one of the factors that need to be considered. The similarity between the dining places and the user's preferences can be calculated. The calculation method is the same as in the above embodiment and will not be repeated here.
[0125] The recommendation weight can be understood as the priority of recommending dining places, and the recommended places are usually those with higher priority. The rule for determining the recommendation weight is that the closer the distance, the greater the recommendation weight; the greater the similarity, the greater the recommendation weight; the higher the score in the user feedback information, the greater the recommendation weight. The formula for calculating the recommendation weight can be, for example: recommendation weight = α*similarity+β*(1 / distance)+γ*user feedback information; where α, β, and γ are weight coefficients, corresponding to the importance of similarity, inverse distance, and user feedback information, respectively.
[0126] Exemplarily, it is assumed that the weight coefficient β of the inverse of the distance is as low as 20%, and the weight coefficients α and γ of the user feedback information and similarity are as high as 40% each. The dining places obtained in the above embodiment include: restaurant A, restaurant B, and restaurant C. Among them, the distance between restaurant A and the current location is 4.2km, the distance between restaurant B and the current location is 1.2km, and the distance between restaurant C and the current location is 5.9km. The score of restaurant A is 3.9, the score of restaurant B is 4.7, and the score of restaurant C is 4.5. The similarity between restaurant A and user preferences is 66%, the similarity between restaurant B and user preferences is 89%, and the similarity between restaurant C and user preferences is 98%. Substitute the data of each dining place into the formula: recommendation weight = α*similarity + β*(1 / distance) + γ*user feedback information to obtain the recommendation weight of each dining place. For example, the recommendation weight of restaurant A is W1 = 40%*3.9 + 20%*1 / 4.2 + 40%*66% = 1.872, the recommendation weight of restaurant B is W2 = 40%*4.7 + 20%*1 / 1.2 + 40%*89% = 2.4, and the recommendation weight of restaurant C is W3 = 40%*4.5 + 20%*1 / 5.9 + 40%*98% = 2.226.
[0127] Selecting a recommended dining place from dining places based on the recommendation weights specifically includes: sorting the dining places from large to small based on the recommendation weights, and determining the dining place with the largest recommendation weight value as the recommended dining place.
[0128] For example, W1=1.872, W2=2.4, W3=2.226, and the order is W2>W3>W1. Accordingly, the order of dining places is restaurant B, restaurant A, and restaurant C. Among them, restaurant B has the largest recommendation weight value, so restaurant B is determined to be the recommended dining place.
[0129] In some embodiments, a plurality of dining places having recommendation weights greater than a preset weight value may be determined as recommended dining places, and the recommended places may be recommended to the user in sequence according to the recommendation weights.
[0130] In the above method, distance, user feedback information and user preferences are comprehensively considered when determining the recommended dining places, and a comprehensive recommendation index, namely the above-mentioned recommendation weight, is generated. The recommended dining places are determined based on this recommendation weight that comprehensively considers distance, user feedback information and user preferences, which can ensure that users can enjoy a dining experience that is in line with their personal preferences and has a good reputation within a reasonable distance.
[0131] Step 104, the information may include dishes, prices, business hours, parking conditions, etc., and information on recommended dining places is obtained and recommended to the user, which can facilitate the user to place subsequent orders based on the recommended information.
[0132] It is understandable that merchants usually provide information such as dishes, prices, business hours, parking conditions, etc. to online service platforms, and online service platforms generally display the information provided by merchants on the page of the dining venue. Therefore, after determining the recommended dining venue, the vehicle can obtain the dishes, prices, business hours, parking conditions, etc. provided by the merchant from the page of the recommended dining venue on the online service platform and make recommendations.
[0133] The specific method of vehicle recommendation information can be: displaying the information through the vehicle's large screen, or playing the information through voice broadcast.
[0134] In some embodiments, the information provided by the merchant to the online service platform may be incomplete and may lack key information. After obtaining the information of the recommended dining place, it is necessary to complete the missing key information in the information. The following embodiment describes this situation in detail:
[0135] In a possible implementation, after obtaining the information of the recommended dining place and before recommending the information to the user, the method further includes: when it is determined that the information is missing key information, initiating a query to the recommended dining place based on the key information to complete the information of the recommended dining place.
[0136] The missing key information may be, for example, any one or more of the menu information, price, business hours, and parking conditions. It is understandable that if the user needs to order food, he needs to know the menu information and prices of the recommended dining places, and needs to make sure that the recommended dining places are open at the current time. If the user needs to pick up food or eat, he needs a parking space. Therefore, any one or more of the menu information, price, business hours, and parking conditions can be called key information.
[0137] The method to determine whether the information is missing key information can be: set a set of checking rules to automatically scan the information of each restaurant to verify whether it contains all necessary fields, such as menu information, prices, business hours, parking conditions, etc. If any field is found to be empty or abnormal, it can be marked as missing key information.
[0138] When it is determined that the information obtained is missing key information, the vehicle can generate a question instruction based on the key information, and initiate an inquiry to the merchant who recommends the dining place based on the question instruction. The merchant can reply with feedback information to the vehicle based on the inquiry instruction. The vehicle records the feedback information and extracts key information from the feedback information to complete the information.
[0139] For example, the key information missing in the information is price. The vehicle can generate a question instruction such as "How much do the dishes cost?" to inquire the merchant of the recommended dining place. The merchant can reply to the vehicle with feedback information including the price of each dish based on the inquiry instruction. The vehicle records the feedback information and extracts the price completion information of each dish from the feedback information.
[0140] The vehicle inquiry method includes text inquiry and voice inquiry. Text inquiry means that the vehicle sends the text "How much is the dish?" to the merchant of the recommended dining place through a dialog box. Voice inquiry means that the vehicle sends the voice "How much is the dish?" to the merchant of the recommended dining place through a voice dialogue.
[0141] It is understandable that the page for recommending dining places in the online service platform may include an online consultation dialog box, and the vehicle may implement text inquiries based on the online consultation dialog box. In some embodiments, the page for recommending dining places in the online service platform may also include a contact number. After the vehicle generates a question instruction, it can let the AI assistant call the contact number and make a voice inquiry based on the question instruction. During the voice inquiry process, it is necessary to record the voice of the merchant's reply, analyze the voice of the merchant's reply through voice recognition technology, extract key information from it based on semantic understanding, and supplement it to the information of the recommended dining place.
[0142] In some embodiments, the vehicle can also record samples of each human-computer dialogue for continuous training and optimization of the AI assistant's voice interaction capabilities.
[0143] In the above method, by proactively asking the recommended dining venues for missing key information, it is ensured that the information of the dining venues recommended to the user is the latest and most accurate. This reduces the number of user inquiries and avoids safety issues caused by driving analysis due to user inquiries. Complete and accurate information can help users make more informed dining decisions. For example, knowing the menu information and prices can help users control their budgets, and knowing the business hours and parking availability can avoid the situation where they cannot dine at the restaurant or find a parking space after arriving at the restaurant, reducing unnecessary travel troubles.
[0144] In one possible implementation, after obtaining information about recommended dining places and recommending the information to the user, the method further includes: receiving ordering information sent by the user based on the information; initiating an order to the recommended dining place based on the ordering information, and calling the vehicle's payment system to pay for the order.
[0145] Optionally, users can use the displayed information to order food in-store or by delivery. In-store means that after users submit an order to a recommended dining place, they need to drive to the recommended dining place to pick up or eat. Delivery means that after users submit an order to a recommended dining place, the merchant or a food delivery platform cooperating with the merchant will deliver the order to the target address.
[0146] When a user wants to dine in a restaurant, the ordering information sent by the user based on the information can only include the selected target dish information. At this time, the vehicle generates an order for dining in the restaurant based on the target dish information in the ordering information and sends the order to the recommended dining place.
[0147] For example, the scenario may be that the user drives out for a trip. During the trip, the user drives continuously for 3 hours, which exceeds the preset time of 2 hours. It is determined that the vehicle meets the preset conditions of the recommended dining place. After the vehicle displays the information of the recommended dining place to the user, the user selects the target dish information that he likes in the displayed information to order the meal. The vehicle generates an order for dining in the restaurant based on the target dish information and sends the order to the recommended dining place. Afterwards, the user drives to the recommended dining place to pick up the meal or eat.
[0148] When a user wants a merchant to deliver food, the order information sent by the user based on the information may include the selected target dish information and the target address to be delivered. At this time, the vehicle generates a delivery order based on the target dish information and the target address, and sends the order to the recommended dining place. The target address may be the address of the destination of the user's driving route.
[0149] Exemplary, the scenario may be that a user drives home after get off work, the target destination of the driving route is home, the driving time is 21:00 which is the dinner time, and the vehicle is determined to meet the preset conditions for recommending a dining place. After the vehicle displays the information of the recommended dining place to the user, the user selects the target dish information he likes from the displayed information to place an order, and sends the destination of the driving route to the vehicle as the target address for delivery. The vehicle generates a delivery order based on the target dish information and the target address, and sends the order to the recommended dining place so that the recommended dining place completes the delivery based on the target address.
[0150] The user can specifically use voice commands, touch operations, etc. to browse and select dishes recommended in the displayed information and input a target address, which is not limited in this embodiment of the present application.
[0151] The vehicle can be integrated with a payment system, such as a wallet application. When the vehicle places an order to a recommended dining place, it can call the vehicle's payment system to pay for the order. The specific payment process can be: the user selects the desired target dishes from the recommended dining place, and the vehicle generates an order based on the target dishes, including information such as dishes, quantity, price, etc., and prompts the user to confirm the order. After the user confirms that it is correct, the vehicle automatically calls the on-board payment system, such as a pre-set electronic wallet, credit card information or a third-party payment platform account (such as Alipay, WeChat Pay, etc.), and prompts the user to authorize. After the user authorizes the payment, the vehicle deducts the order amount from the payment account and sends the order to the merchant.
[0152] In the above method, during driving, the user can simply and quickly complete the ordering and payment operations based on the information of recommended dining places recommended by the vehicle at the right time. The user does not need to manually search, browse, and compare orders when feeling hungry, which reduces the steps of user operations and improves driving safety.
[0153] In one possible implementation, after initiating an order to a recommended dining place based on the order information and calling the vehicle's payment system to support the order, the method also includes: when the order is an in-store dining order, planning a route from the current location to the recommended dining place, and providing dining navigation services to the user based on the route; when the order is a delivery order, monitoring the delivery status of the order in real time and displaying the delivery status to the user.
[0154] When the order sent by the vehicle to a recommended dining place is an in-store dining order, the user needs to drive the vehicle from the current location to the recommended dining place. At this time, the vehicle's onboard navigation system can automatically plan the route between the current location and the recommended dining place, and provide the user with dining navigation services in real time based on the planned route, so that the user can quickly reach the recommended dining place.
[0155] When the order sent by the vehicle to the recommended dining place is a store delivery order, the merchant needs to deliver the order from the recommended dining place to the target address after the order is placed. The vehicle can monitor the merchant's delivery status of the order in real time. The delivery status may include, for example, any one or more of the current distance to the target address, the estimated delivery time, and the remaining time. The vehicle can display the monitored delivery status on the vehicle's display screen or broadcast it in the form of voice, so that users can understand the delivery status in real time.
[0156] In some embodiments, after initiating an order to a recommended dining place based on the order information and calling the vehicle's payment system to pay for the order, the method further includes: recording the order data, wherein the order data includes: the dining time, the amount of consumption, and the types of dishes, and collecting user feedback on the meal after the user evaluates and provides feedback on the meal, and continuously optimizing the personalized recommendation algorithm and strategy based on the collected order data and user feedback on the meal to improve the quality of the next recommendation.
[0157] Specifically, user preferences can be updated based on the consumption amount and types of dishes in the recorded order data, the preset dining time periods can be updated based on the dining times, and the recommendation weights of dining places can be reasonably adjusted based on user feedback information. For example, when the feedback information indicates that the recommended dining place does not meet the user's needs, the weight coefficients of multiple data when calculating the recommendation weight value are appropriately adjusted to reduce the recommendation weights of dining places similar to the recommended dining place, thereby optimizing personalized recommendation algorithms and strategies.
[0158] In the above method, for in-store dining orders, the vehicle automatically plans the route to provide dining navigation services to users, which can help users quickly find the location of recommended dining places, avoid the trouble of manually searching and entering the destination, ensure the accuracy of the driving direction, save time, and reduce the risk of getting lost. For delivery orders, the vehicle monitors and displays the delivery status in real time, so that users can keep abreast of the dynamics of the food at any time, such as whether the food has been served, how far it is from the target address, how long it is expected to be delivered, etc., so that users can reasonably arrange their time based on the delivery status.
[0159] In summary, in this application, by judging whether the preset conditions of the recommended dining place are met through driving duration, driving time, and user status data, the recommendation time can be determined comprehensively and intelligently, and the dining place that meets the user's preferences can be actively recommended to the user when the preset conditions are met, thereby improving the initiative and personalization of dining recommendations, improving driving safety, and improving the user's car experience. In addition, when determining the recommended dining place, the distance, user feedback information, and user preferences are comprehensively considered, which can ensure that the user can enjoy a dining experience that meets personal preferences and has a good reputation within a reasonable distance. When key information is missing, the recommended dining place is actively asked, reducing the user's inquiry operations. Obtaining information about recommended dining places and recommending them to users can facilitate users to complete subsequent meal ordering operations based on the information.
[0160] Figure 3 It is a structural schematic diagram of a dining place recommendation device provided in an embodiment of the present application.
[0161] For example, Figure 3 As shown, the device 300 includes:
[0162] The acquisition module 301 is used to acquire the vehicle's current driving related data and user preferences;
[0163] A judgment module 302 is used to judge whether the vehicle meets the preset conditions for recommending a dining place based on the driving related data;
[0164] A determination module 303 is used to determine a recommended dining place in combination with the current location of the vehicle and the user's preference when it is determined that the vehicle meets the preset conditions;
[0165] The recommendation module 304 is used to obtain information about recommended dining places and recommend the information to the user.
[0166] In one possible implementation, the driving-related data includes: driving time, driving duration, user status data and driving route. The judgment module 302 is specifically used to determine the recommendation score based on the driving time, driving duration, user status data and driving route; when it is determined that the recommended score is greater than the preset score, it is determined that the vehicle meets the preset conditions for recommending a dining place.
[0167] In one possible implementation, the judgment module 302 is specifically used to determine a first score corresponding to the driving time based on the proximity between the driving time and the preset dining time period; determine a second score corresponding to the driving time based on the difference between the driving time and the preset time period; determine a third score corresponding to the user status data based on the user's hunger level represented by the user status data; determine a fourth score corresponding to the driving route based on the dining place data around the driving route; and determine a recommended score based on the first score, the second score, the third score, and the fourth score.
[0168] In a possible implementation, the determination module 303 is specifically used to, when it is determined that the vehicle meets preset conditions, obtain dining places within a preset range near the current position of the vehicle; and select a recommended dining place that meets the user's preferences from the dining places.
[0169] In one possible implementation, the determination module 303 is specifically used to determine the distance between the dining place and the current location; obtain user feedback information of the dining place; calculate the similarity between the dining place and the user preference; calculate the recommendation weight of the dining place based on the distance, user feedback information and similarity; and select a recommended dining place from the dining places based on the recommendation weight.
[0170] In a possible implementation, the device further includes: a completion module, which is used to initiate a query to the dining venue based on the key information to complete the information of the recommended dining venue when it is determined that the information is missing key information.
[0171] In one possible implementation, the device also includes an ordering module, which is used to receive ordering information sent by the user based on the information after obtaining information about recommended dining places and recommending the information to the user; initiate an order to the recommended dining place based on the ordering information, and call the vehicle's payment system to pay for the order.
[0172] Figure 4 It is a structural schematic diagram of a vehicle provided in an embodiment of the present application.
[0173] For example, Figure 4 As shown, the vehicle 400 includes: a memory 401 and a processor 402, wherein the memory 401 stores an executable program code 4011, and the processor 402 is used to call and execute the executable program code 4011 to perform a method for recommending dining places.
[0174] In addition, an embodiment of the present application also protects a device, which may include a memory and a processor, wherein the memory stores an executable program code, and the processor is used to call and execute the executable program code to execute a dining place recommendation method provided in an embodiment of the present application.
[0175] In this embodiment, the functional modules of the device can be divided according to the above method example. For example, each functional module can be corresponded, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is schematic and is only a logical function division. There may be other division methods in actual implementation.
[0176] In the case of dividing each functional module according to each function, the device may also include an acquisition module, a judgment module, a determination module, a recommendation module, etc. It should be noted that all relevant contents of each step involved in the above method embodiment can be referred to the functional description of the corresponding functional module, which will not be repeated here.
[0177] It should be understood that the device provided in this embodiment is used to execute the above-mentioned method for recommending dining places, and thus can achieve the same effect as the above-mentioned implementation method.
[0178] In the case of an integrated unit, the device may include a processing module and a storage module. When the device is applied to a vehicle, the processing module may be used to control and manage the actions of the vehicle. The storage module may be used to support the vehicle in executing relevant program codes, etc.
[0179] The processing module may be a processor or a controller, which may implement or execute various exemplary logic blocks, modules and circuits shown in conjunction with the disclosure of the present application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module may be a memory.
[0180] In addition, the device provided in the embodiments of the present application may specifically be a chip, a module or a module, and the chip may include a connected processor and a memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute a dining place recommendation method provided in the above embodiment.
[0181] This embodiment also provides a computer-readable storage medium, in which a computer program code is stored. When the computer program code is executed on a computer, the computer executes the above-mentioned related method steps to implement a method for recommending dining places provided in the above embodiment.
[0182] This embodiment also provides a computer program product. When the computer program product is run on a computer, the computer is caused to execute the above-mentioned related steps to implement a method for recommending dining places provided in the above embodiment.
[0183] Among them, the device, computer-readable storage medium, computer program product or chip provided in this embodiment is used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be repeated here.
[0184] Through the description of the above implementation methods, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.
[0185] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or modules can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0186] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. A method for recommending dining places, characterized in that: The method comprises: Obtain the vehicle's current driving-related data and user preferences; Based on the driving-related data, determining whether the vehicle meets preset conditions for recommending a dining place; In the case where it is determined that the vehicle meets the preset condition, determining a recommended dining place in combination with the current location of the vehicle and the user preference; The information of the recommended dining places is obtained and recommended to the user.
2. The method according to claim 1, characterized in that The driving related data includes: driving time, driving duration, user status data and driving route. The determining whether the vehicle meets the preset conditions for recommending a dining place based on the driving related data includes: Determining a recommendation score based on the driving time, driving duration, user status data, and driving route; When it is determined that the recommendation score is greater than the preset score, it is determined that the vehicle meets the preset condition for recommending a dining place.
3. The method according to claim 2, characterized in that The determining of the recommendation score based on the driving time, driving duration, user status data and driving route includes: Determining a first score corresponding to the driving time based on the proximity between the driving time and the preset dining time period; Determining a second score corresponding to the driving time based on a difference between the driving time and a preset time; determining a third score corresponding to the user status data based on the user hunger degree represented by the user status data; Determining a fourth score corresponding to the driving route based on the dining venue data around the driving route; The recommendation score is determined based on the first score, the second score, the third score, and the fourth score.
4. The method according to any one of claims 1 to 3, characterized in that When it is determined that the vehicle meets the preset condition, determining a recommended dining place in combination with the current location of the vehicle and the user preference includes: When it is determined that the vehicle meets the preset condition, obtaining dining places within a preset range near the current position of the vehicle; From the dining places, a recommended dining place that meets the user's preference is selected.
5. The method according to claim 4, characterized in that The step of selecting a recommended dining place that meets the user's preference from the dining places includes: Determining the distance between the dining venue and the current location; Obtaining user feedback information of the dining venue; Calculating the similarity between the dining venue and the user preference; Calculating the recommendation weight of the dining place based on the distance, the user feedback information and the similarity; The recommended dining place is selected from the dining places based on the recommendation weight.
6. The method according to any one of claims 1 to 3, characterized in that: After obtaining the information of the recommended dining place and before recommending the information to the user, the method further includes: When it is determined that the information is missing key information, an inquiry is initiated to the dining place based on the key information to complete the information of the recommended dining place.
7. The method according to any one of claims 1 to 3, characterized in that After obtaining the information of the recommended dining place and recommending the information to the user, the method further includes: receiving meal ordering information sent by the user based on the information; An order is initiated to the recommended dining place based on the ordering information, and a payment system of the vehicle is called to pay for the order.
8. A device for recommending dining places, characterized in that: The device comprises: An acquisition module is used to obtain the vehicle's current driving-related data and user preferences; A judgment module, used for judging whether the vehicle meets the preset conditions for recommending a dining place based on the driving-related data; A determination module, configured to determine a recommended dining place in combination with the current location of the vehicle and the user preference when it is determined that the vehicle meets the preset condition; The recommendation module is used to obtain the information of the recommended dining places and recommend the information to the user.
9. A vehicle, characterized in that: The vehicle comprises: A memory for storing executable program codes; A processor, configured to call and run the executable program code from the memory, so that the vehicle executes the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the method according to any one of claims 1 to 7 is implemented.
Citation Information
Cited By
Dining place determination method and device based on vehicle-mounted intelligent agent
CN122470692A
