Method, device and storage medium for reminding of items in a vehicle

Abstract

The application discloses a reminding method, device and equipment for vehicle-mounted articles and a storage medium. The method comprises the following steps: acquiring real-time ambient light intensity data of a current vehicle, and determining whether a driving scene in which the current vehicle is located is a special light scene based on the real-time ambient light intensity data; if the driving scene in which the current vehicle is located is the special light scene, generating a vehicle-mounted article reminding strategy based on the special light scene and sunglasses equipment information of the current vehicle; if the driving scene in which the current vehicle is located is not the special light scene, determining a target driving scene of the current vehicle according to visual information, real-time position information and driving state information of the current vehicle, and generating the vehicle-mounted article reminding strategy based on the target driving scene; and reminding a user of the current vehicle based on the vehicle-mounted article reminding strategy. The technical scheme of the application can effectively improve the accuracy of driving scene determination, thereby enhancing the practicality and reliability of the reminding function, improving the driving experience and improving the driving safety.

Description

Technical Field

[0001] This invention relates to the field of automotive technology, and more particularly to a method, apparatus, device, and storage medium for reminding users of items in a vehicle. Background Technology

[0002] With the rapid development of the automotive industry and the increasing demands for driving experience and safety, vehicles are becoming increasingly intelligent and convenient. Among these features, the intelligent management of in-vehicle items is gradually becoming a key element in improving driving comfort and safety. During driving, drivers need to appropriately access various in-vehicle items based on different driving scenarios (such as bright sunlight, highway entrances, gas stations, etc.), such as sunglasses, fuel cards, mobile phones, and Electronic Toll Collection (ETC) cards, to ensure both comfort and safety.

[0003] However, most existing in-vehicle item reminder methods rely on a single parameter (such as vehicle location) to determine the driving scenario. This single-dimensional judgment method is prone to scenario recognition bias, which leads to the push reminder content being out of touch with the user's actual needs. This not only reduces the practicality of the reminder function, but may also cause irrelevant reminders to distract the driver's attention, affecting the driving experience and driving safety.

[0004] Therefore, there is an urgent need to propose a new method to solve the above problems. Summary of the Invention

[0005] This invention provides a method, apparatus, device, and storage medium for reminding vehicle items, which can effectively improve the accuracy of driving scenario determination, thereby enhancing the practicality and reliability of the reminder function, improving the driving experience, and increasing driving safety.

[0006] In a first aspect, embodiments of the present invention provide a method for reminding about items in a vehicle, the method comprising:

[0007] The system acquires real-time ambient light intensity data of the current vehicle and determines whether the current driving scenario of the vehicle is a special lighting scenario based on the real-time ambient light intensity data.

[0008] If the current driving scenario of the vehicle is a special lighting scenario, then a vehicle item reminder strategy is generated based on the special lighting scenario and the current vehicle's sunglasses equipment information.

[0009] If the current driving scenario of the vehicle is not a special lighting scenario, then the target driving scenario of the current vehicle is determined based on the current vehicle's visual information, real-time location information and driving status information, and an in-vehicle item reminder strategy is generated based on the target driving scenario.

[0010] The system provides reminders to the user of the current vehicle based on the in-vehicle item reminder strategy.

[0011] The technical solution of this invention first acquires the real-time ambient light intensity data of the current vehicle, and then determines whether the current driving scenario is a special lighting scenario based on the real-time ambient light intensity data. This clearly distinguishes between special lighting scenarios and normal lighting scenarios, thus providing clear triggering conditions for scenario-based reminder strategies. Simultaneously, it effectively avoids sending invalid reminders such as "take your sunglasses" to the driver in normal lighting scenarios, balancing driving safety and user experience. Furthermore, the need to take sunglasses is usually triggered by sudden changes in light (such as entering a strong light environment), exhibiting strong immediacy. Therefore, by quickly determining the special lighting scenario before triggering the corresponding reminder, the timeliness of the reminder is improved, and the interference of irrelevant information on the driver is reduced, further optimizing the user experience. Next, if it is a special lighting scenario, an in-vehicle item reminder strategy is generated based on the special lighting scenario and the vehicle's sunglasses equipment information. This generates a more accurate in-vehicle item reminder strategy, effectively avoiding invalid reminders that interfere with the driver, thus optimizing the user's driving experience and further improving driving safety. If the lighting conditions are not special, the target driving scenario for the current vehicle is determined based on its visual information, real-time location information, and driving status information. Based on this target driving scenario, an in-vehicle item reminder strategy is generated. This enables multi-dimensional and comprehensive recognition of driving scenarios, significantly improving the accuracy of scenario determination, overcoming the limitations of a single data dimension, effectively reducing the scenario misjudgment rate, and ensuring a high degree of matching between the target driving scenario and actual working conditions. Simultaneously, the in-vehicle item reminder strategy generated based on accurate scenarios truly meets the needs of driving scenarios, further optimizing the user's driving experience. Finally, reminders are given to the user of the current vehicle based on the in-vehicle item reminder strategy, achieving scenario-based and accurate reminders, thereby improving driving safety and user experience. Therefore, the technical solution of this invention can solve the problems in the prior art where recognition deviations caused by single-dimensional scenario determination lead to a disconnect between reminder content and needs, reduced practicality, interference with driving, and impact on safety.

[0012] Secondly, embodiments of the present invention also provide a reminder device for in-vehicle items, the device comprising:

[0013] The determination module is used to acquire the real-time ambient light intensity data of the current vehicle and determine whether the driving scenario in which the current vehicle is located is a special lighting scenario based on the real-time ambient light intensity data.

[0014] The first generation module is used to generate an in-vehicle item reminder strategy based on the special lighting scenario and the current vehicle's sunglasses equipment information if the current driving scenario is a special lighting scenario.

[0015] The second generation module is used to determine the target driving scenario of the current vehicle based on the visual information, real-time location information and driving status information of the current vehicle if the current driving scenario is not a special lighting scenario, and to generate an in-vehicle item reminder strategy based on the target driving scenario.

[0016] The reminder module is used to remind the user of the current vehicle based on the in-vehicle item reminder strategy.

[0017] Thirdly, embodiments of the present invention also provide an electronic device, the electronic device comprising:

[0018] At least one processor; and a memory communicatively connected to said at least one processor;

[0019] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the vehicle-mounted item reminder method according to any embodiment of the present invention.

[0020] Fourthly, embodiments of the present invention also provide a storage medium containing computer-executable instructions, which, when executed by a computer processor, implement the vehicle-mounted item reminder method described in any embodiment of the present invention.

[0021] It should be noted that the aforementioned computer instructions may be stored, in whole or in part, on a computer-readable storage medium. This computer-readable storage medium may be packaged together with the processor of the vehicle-mounted item reminder device, or it may be packaged separately from the processor of the vehicle-mounted item reminder device; this application does not impose any limitations on this.

[0022] The descriptions of the second, third, and fourth aspects in this application can be referenced to the detailed description of the first aspect; and the beneficial effects described in the second, third, and fourth aspects can be referenced to the analysis of the beneficial effects of the first aspect, which will not be repeated here.

[0023] In this application, the name of the aforementioned vehicle-mounted item reminder device does not limit the device or functional module itself. In actual implementation, these devices or functional modules may appear under other names. As long as the function of each device or functional module is similar to that of this application, it falls within the scope of the claims of this application and its equivalents.

[0024] These or other aspects of this application will become more readily apparent in the following description. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 A flowchart illustrating a method for reminding users of items in a vehicle, as provided in an embodiment of the present invention;

[0027] Figure 2 A flowchart illustrating another method for reminding vehicle-mounted items provided in an embodiment of the present invention;

[0028] Figure 3 A schematic diagram of the structure of a vehicle-mounted item reminder device provided in an embodiment of the present invention;

[0029] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0030] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0031] In this article, the term "and / or" is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0032] The terms "first" and "second," etc., used in the specification and drawings of this application are used to distinguish different objects or to distinguish different treatments of the same object, rather than to describe a specific order of objects.

[0033] Furthermore, the terms "comprising" and "having," and any variations thereof, used in the description of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include other steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus.

[0034] Before discussing the exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the operations (or steps) as sequential processes, many of these operations can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but may also have additional steps not included in the figures. The process can correspond to a method, function, procedure, subroutine, subroutine, etc. Moreover, without conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0035] It should be noted that in the embodiments of this application, the words "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0036] In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0037] Figure 1 This is a flowchart illustrating a method for reminding drivers of in-vehicle items according to an embodiment of the present invention. This embodiment is applicable to situations where, during vehicle operation, the driver is dynamically reminded to retrieve suitable in-vehicle items based on real-time driving scenarios. The method can be executed by an in-vehicle item reminder device, which can be implemented using software and / or hardware. For example, the device can be an electronic device within the vehicle. (Reference) Figure 1 The method for reminding users of in-vehicle items in this embodiment specifically includes the following steps:

[0038] Step 110: Obtain the real-time ambient light intensity data of the current vehicle, and determine whether the current driving scenario of the vehicle is a special lighting scenario based on the real-time ambient light intensity data.

[0039] If it is a special lighting scene, proceed to step 120; otherwise, proceed to step 130.

[0040] Specifically, "current vehicle" refers to the specific vehicle being monitored, having data acquired, and performing related operational procedures. Real-time ambient light intensity data refers to quantitative data collected in real-time by onboard sensors, characterizing the intensity of external light irradiance on the vehicle; its unit is lux. Special lighting scenarios refer to situations where light intensity exceeds the range of normal driving environments, or where lighting conditions significantly interfere with the driver's visual perception and operational safety. Examples of special lighting scenarios include strong light scenarios (such as open roads at midday in summer) and low light scenarios (such as a vehicle entering a tunnel).

[0041] In practice, the vehicle's onboard light sensors (such as ambient light sensors or illuminance detectors) can be used to acquire real-time ambient light intensity data. Based on this data, it can be determined whether the vehicle is in a special lighting scenario. Specifically, if the real-time ambient light intensity data is greater than the upper limit of the strong light threshold, the current driving scenario is determined to be a special lighting scenario; if the real-time ambient light intensity data is less than the lower limit of the weak light threshold, the current driving scenario is determined to be a special lighting scenario; if the real-time ambient light intensity data is between the two, the current driving scenario is determined not to be a special lighting scenario, and the process returns to acquiring the current vehicle's real-time ambient light intensity data and determining whether the current driving scenario is a special lighting scenario based on this data. The upper limit of the strong light threshold is a pre-set upper limit value for the ambient light intensity of a typical sunny daytime driving environment, such as 100,000 lux. The lower limit of the weak light threshold is a pre-set lower limit value for the ambient light intensity of typical nighttime urban roads (including street lighting), such as 50 lux.

[0042] If the current driving scenario is determined to be a special lighting scenario, it means that the lighting conditions will significantly affect the driver's vision, requiring the use of equipment such as sunglasses to improve the visual environment. In this case, an in-vehicle item reminder strategy can be generated based on the special lighting scenario and the vehicle's sunglasses configuration information. If the current driving scenario is determined to be a special lighting scenario, it means that the lighting conditions are within the normal range. The specific driving scenario needs to be determined by considering the vehicle's surrounding environment, location, and driving status. In this case, the target driving scenario can be determined based on the vehicle's visual information, real-time location information, and driving status information. An in-vehicle item reminder strategy can then be generated based on the target driving scenario.

[0043] In this embodiment, the above steps clearly distinguish between special lighting scenarios and normal lighting scenarios, thus providing clear triggering conditions for scenario-based reminder strategies. Simultaneously, it effectively avoids sending invalid reminders such as "take your sunglasses" to the driver under normal lighting scenarios, balancing driving safety and user experience. Furthermore, the need to take out sunglasses is usually triggered by sudden changes in lighting (such as entering a bright light environment), exhibiting strong immediacy. Therefore, by quickly identifying special lighting scenarios before triggering corresponding reminders, the timeliness of reminders is improved, and interference from irrelevant information to the driver is reduced, further optimizing the user experience.

[0044] Step 120: Generate an in-vehicle item reminder strategy based on the special lighting scene and the current vehicle's sunglasses equipment information.

[0045] Specifically, sunglasses configuration information refers to the configuration status data of sunglasses associated with the current vehicle, such as the storage location of the sunglasses. In-vehicle item reminder strategy refers to a targeted reminder plan based on driving scenario characteristics and the configuration status of in-vehicle items, including reminder content, reminder methods (such as pop-up windows on the central control screen, voice broadcasts, flashing indicator lights on the instrument panel), and reminder frequency.

[0046] In practice, the system first determines whether the driver needs to wear sunglasses based on the specific lighting conditions. For example, if the specific lighting condition is a bright light scene, the driver needs to wear sunglasses; if the specific lighting condition is a low light scene, the driver needs to remove sunglasses.

[0047] If it is determined that sunglasses are required, the driver's facial information is collected through the in-vehicle camera, and image recognition technology is used to determine whether the driver is wearing sunglasses: If the driver is wearing sunglasses, no in-vehicle item reminder strategy is generated, or a safety reminder is generated, such as "Strong sunlight, drive carefully"; if the driver is not wearing sunglasses, the vehicle's sunglasses configuration information is retrieved from the in-vehicle item information database, and a reminder strategy is generated accordingly: If the sunglasses configuration information indicates that the vehicle is equipped with sunglasses, an in-vehicle item reminder strategy is generated based on the location of the sunglasses, such as: a voice reminder: "Strong sunlight, it is recommended to wear sunglasses. Your sunglasses are at XX location"; if the sunglasses configuration information indicates that the vehicle is not equipped with sunglasses, no in-vehicle item reminder strategy is generated, or a safety reminder is generated, such as "Strong sunlight, drive carefully". The vehicle-mounted item information database refers to a database deployed in the vehicle's central control system or cloud server, used to structurally store the entire lifecycle information of various vehicle-mounted items related to the current vehicle, such as item name, specifications, quantity, and storage location in the vehicle. It can automatically record the placement / retrieval location of items and update it in real time through image recognition technology from multi-view cameras in the vehicle. At the same time, it supports users to manually enter or modify item information to ensure the accuracy and timeliness of the data.

[0048] If it is determined that sunglasses are not required, the driver's facial information is collected through the in-vehicle camera, and image recognition technology is used to determine whether the driver is wearing sunglasses: if the driver is wearing sunglasses, an in-vehicle item reminder strategy is generated, such as suggesting that sunglasses be removed if they are not required due to the current light conditions; if the driver is not wearing sunglasses, no in-vehicle item reminder strategy is generated, or a safety reminder is generated, such as driving carefully in dim light.

[0049] In this embodiment, the above steps can generate a more accurate in-vehicle item reminder strategy, effectively avoiding interference from invalid reminders to the driver, thus optimizing the user's driving experience and further improving driving safety.

[0050] Step 130: Determine the target driving scenario of the current vehicle based on the vehicle's visual information, real-time location information, and driving status information, and generate an in-vehicle item reminder strategy based on the target driving scenario.

[0051] Specifically, visual information refers to images or video data of the vehicle's surrounding environment collected by in-vehicle cameras (such as front-view cameras and surround-view cameras). Real-time location information refers to the instantaneous geographical location information of the vehicle obtained through positioning modules such as the in-vehicle GPS and BeiDou Navigation Satellite System, usually presented in coordinates such as latitude, longitude, and altitude. Driving status information refers to parameter data reflecting the vehicle's current operating conditions, such as vehicle speed, driving direction, acceleration / deceleration status, steering angle, braking status, and gear information. The target driving scenario refers to the specific driving scenario in which the vehicle is currently located, determined based on multi-dimensional data such as vehicle visual information, real-time location, and driving status information, such as a traffic light intersection scenario, a service area passage scenario, or a highway toll station passage scenario.

[0052] In practice, after determining that the current driving scenario is not a special lighting scenario, visual information, real-time location information, and driving status information of the vehicle can be collected based on the vehicle's onboard visual sensors, positioning sensors, and driving status sensors. These multi-dimensional data are then standardized and cleaned to improve data quality and usability. For example, for visual information, image enhancement and noise reduction can be performed to make it clearer and more accurate; for location information, a unified coordinate system can be used to convert location data from different sources into a unified standard format; for driving status information, data normalization can be performed to map data of different dimensions to the same numerical range. Then, the standardized and cleaned data is input into a pre-trained scene recognition model to obtain the target driving scenario of the current vehicle. Then, based on the target driving scenario, a matching search is performed in the scenario and in-vehicle item reminder association rule library to generate an in-vehicle item reminder strategy adapted to the current scenario. For example, when the target driving scenario is a highway service area scenario, the generated reminder content is: "It is recommended to take a water bottle from the car and store it in the center console," and the adapted reminder method is voice reminder; when the target driving scenario is a traffic light intersection scenario, the generated reminder content is: "It is recommended to check the in-vehicle tissues and store them in the passenger-side storage compartment," and the adapted reminder method is voice reminder. Here, the scenario and in-vehicle item reminder association rule library refers to the in-vehicle items and corresponding reminder strategies that need to be used in different driving scenarios and are pre-established according to actual situation or needs. The scenario recognition model refers to the model obtained by training a deep learning model with different historical visual information, historical location information, historical driving status information, and corresponding historical driving scenarios (all of which have been professionally labeled) as training samples.

[0053] In this embodiment, the above steps enable multi-dimensional and comprehensive identification of driving scenarios, significantly improving the accuracy of scenario judgment, breaking through the limitations of a single data dimension, effectively reducing the scenario misjudgment rate, and ensuring that the target driving scenario is highly matched with the actual working conditions. At the same time, the in-vehicle item reminder strategy generated based on accurate scenarios can truly meet the needs of driving scenarios and further optimize the user's driving experience.

[0054] Step 140: Provide reminders to the current vehicle user based on the in-vehicle item reminder strategy.

[0055] In practice, after obtaining the in-vehicle item reminder strategy, the system can prioritize using the reminder method set in the strategy to output the corresponding reminder content, such as voice broadcast, text or icon prompts on the central control screen, etc. If the strategy does not specify a specific reminder method, the system will automatically use the default reminder method (such as voice reminder) for output.

[0056] In this embodiment, the above steps can achieve scenario-based and precise reminders, thereby improving driving safety and user experience.

[0057] The in-vehicle item reminder method provided in this invention first acquires the real-time ambient light intensity data of the current vehicle and determines whether the current driving scenario is a special lighting scenario based on the real-time ambient light intensity data. This clearly distinguishes between special lighting scenarios and normal lighting scenarios, thus providing clear triggering conditions for scene-based reminder strategies. Simultaneously, it effectively avoids sending invalid reminders such as "take your sunglasses" to the driver in normal lighting scenarios, balancing driving safety and user experience. Furthermore, the need to take out sunglasses is usually triggered by sudden changes in light (such as entering a strong light environment), exhibiting strong immediacy. Therefore, by quickly determining the special lighting scenario before triggering the corresponding reminder, the timeliness of the reminder is improved, and the interference of irrelevant information on the driver is reduced, further optimizing the user experience. Next, if it is a special lighting scenario, an in-vehicle item reminder strategy is generated based on the special lighting scenario and the current vehicle's sunglasses equipment information. This generates a more accurate in-vehicle item reminder strategy, effectively avoiding invalid reminders that interfere with the driver, thus optimizing the user's driving experience and further improving driving safety. If the lighting conditions are not special, the target driving scenario for the current vehicle is determined based on its visual information, real-time location information, and driving status information. Based on this target driving scenario, an in-vehicle item reminder strategy is generated. This enables multi-dimensional and comprehensive recognition of driving scenarios, significantly improving the accuracy of scenario determination, overcoming the limitations of a single data dimension, effectively reducing the scenario misjudgment rate, and ensuring a high degree of matching between the target driving scenario and actual working conditions. Simultaneously, the in-vehicle item reminder strategy generated based on accurate scenarios truly meets the needs of driving scenarios, further optimizing the user's driving experience. Finally, reminders are given to the user of the current vehicle based on the in-vehicle item reminder strategy, achieving scenario-based and accurate reminders, thereby improving driving safety and user experience. Therefore, the technical solution of this invention can solve the problems in the prior art where recognition deviations caused by single-dimensional scenario determination lead to a disconnect between reminder content and needs, reduced practicality, interference with driving, and impact on safety.

[0058] Figure 2 This is a flowchart illustrating another method for alerting in-vehicle items provided by an embodiment of the present invention. This embodiment is a specific implementation based on the above embodiments. In this embodiment, the method may further include:

[0059] Step 210: Obtain the real-time ambient light intensity data of the current vehicle, and determine whether the driving scenario in which the current vehicle is located is a special lighting scenario based on the real-time ambient light intensity data.

[0060] If it is a special lighting scene, proceed to step 219; otherwise, proceed to step 211.

[0061] Optional special lighting scenarios include high-light scenarios and low-light scenarios.

[0062] Furthermore, determining whether the current driving scenario of the vehicle is a special lighting scenario based on real-time ambient light intensity data includes: determining whether the real-time ambient light intensity data is greater than a first preset light intensity threshold; if it is greater, then if the real-time ambient light intensity data is greater than the first preset light intensity threshold and the duration exceeds a first preset duration, the current driving scenario of the vehicle is determined to be a strong light scenario; if it is not greater, then determining whether the real-time ambient light intensity data is less than a second preset light intensity threshold; if it is less, then if the real-time ambient light intensity data is less than the second preset light intensity threshold and the duration exceeds a second preset duration, the current driving scenario of the vehicle is determined to be a low light scenario.

[0063] Specifically, a strong light scene refers to a specific type of special lighting scenario, such as direct sunlight at noon or glare from snow. A low light scene refers to another specific type of special lighting scenario, such as nighttime driving, driving in tunnels, or underground parking lots. The first preset light intensity threshold refers to a pre-set threshold for determining a strong light scene based on actual conditions or needs, such as a first preset light intensity threshold of 8000 Lux. The first preset duration refers to a pre-set duration for verifying strong light conditions based on actual conditions or needs, such as a first preset duration of 30 seconds. The second preset light intensity threshold refers to a pre-set threshold for determining a low light scene based on actual conditions or needs, such as a second preset light intensity threshold of 100 Lux. The second preset duration refers to a pre-set duration for verifying low light conditions based on actual conditions or needs, such as a second preset duration of 30 seconds. The duration refers to the continuous length of time during which the real-time light intensity data of the vehicle's environment continuously meets the preset threshold conditions (e.g., greater than the first preset light intensity threshold or less than the second preset light intensity threshold).

[0064] In practice, the system first determines whether the real-time ambient light intensity data is greater than a first preset light intensity threshold. If the real-time ambient light intensity data is greater than the first preset light intensity threshold, it enters a continuous monitoring state. If the duration for which the real-time ambient light intensity data is greater than the first preset light intensity threshold exceeds a first preset duration, the vehicle is determined to be in a strong light scene. If the real-time ambient light intensity data is not greater than the first preset light intensity threshold, it further determines whether the real-time ambient light intensity data is less than a second preset light intensity threshold. If it is less, it enters a continuous monitoring state. If the duration for which the real-time ambient light intensity data is less than the second preset light intensity threshold exceeds a second preset duration, the vehicle is determined to be in a low-light scene; otherwise, the vehicle is determined to be in a non-special lighting scene.

[0065] In this embodiment, the above steps can effectively filter out interference caused by instantaneous light fluctuations, improve the accuracy of driving scenario determination, thereby reducing the frequency of invalid reminders, improving the practicality and reliability of the reminder function, and optimizing the user's driving experience.

[0066] Optionally, special lighting scenarios also include light surge scenarios.

[0067] Further, determining whether the current driving scenario of the vehicle is a special lighting scenario based on real-time ambient light intensity data includes: acquiring ambient light intensity data within a first preset time period to obtain first historical ambient light intensity data, and acquiring ambient light intensity data within a second preset time period to obtain second historical ambient light intensity data; calculating the average value of the first historical ambient light intensity data to obtain a first average light intensity, and calculating the average value of the second historical ambient light intensity data and the real-time ambient light intensity data to obtain a second average light intensity; calculating the product of a first preset multiple and the first average light intensity to obtain a light surge reference intensity; determining whether the second average light intensity is greater than the light surge reference intensity; if it is greater, then if the second average light intensity is greater than a third preset light intensity threshold, the current driving scenario of the vehicle is determined to be a light surge scenario.

[0068] Specifically, a light surge scenario refers to another specific type of special lighting scenario, specifically a driving scenario where the light intensity of the vehicle's environment increases sharply within a short period of time. Examples of light surge scenarios include vehicles exiting tunnels or moving from shaded sections of road into open, sunny areas. The first preset time period is a historical time interval pre-set according to actual conditions or needs, used to reflect the stable baseline level before the sudden change in light intensity. For example, the first preset time period can be set to the time interval 5 seconds prior to the start time of the second preset time period (i.e., 5 seconds before the start of the second preset time period to that start). The second preset time period is another historical time interval pre-set according to actual conditions or needs, used to reflect the light intensity change state immediately adjacent to the real-time monitoring time. For example, the second preset time period can be set to the time interval 5 seconds prior to the current time. The first historical ambient light intensity data is the set of ambient light intensity data collected within the first preset time period. The second historical ambient light intensity data is the set of ambient light intensity data collected within the second preset time period. The first average light intensity is the value obtained by calculating the arithmetic mean of the first historical ambient light intensity data, representing the stable baseline level before the sudden change in light intensity. The second average light intensity is the value obtained by arithmetically averaging the second historical ambient light intensity data and the real-time ambient light intensity data, representing the average level after a sudden change in light intensity. The first preset multiple is a quantification coefficient for the magnitude of the light intensity change, preset according to actual conditions or needs, such as a first preset multiple of 3. The light surge reference intensity is the product of the first average light intensity and the first preset multiple, and is the critical threshold for determining whether the light intensity has reached the degree of surge. The third preset light intensity threshold is the minimum light intensity threshold for determining the light surge scenario, preset according to actual conditions or needs, such as a third preset light intensity threshold of 5000 Lux.

[0069] In specific implementation, the system can determine whether the current driving scenario of the vehicle is a special lighting scenario based on historical and current ambient light intensity data. Specifically, ambient light intensity data within a first preset time period is obtained as first historical ambient light intensity data, and ambient light intensity data within a second preset time period is obtained as second historical ambient light intensity data. Next, the average value of the first historical ambient light intensity data is calculated to obtain a first average light intensity, and the average value of the second historical ambient light intensity data and the real-time ambient light intensity data is calculated to obtain a second average light intensity. Then, the product of a first preset multiple and the first average light intensity is calculated to obtain a light surge reference intensity. Afterward, it is determined whether the second average light intensity is greater than the light surge reference intensity; if the second average light intensity is greater than the light surge reference intensity, it is further determined whether the second average light intensity is greater than a third preset light intensity threshold; if it is greater, the current driving scenario of the vehicle is determined to be a light surge scenario; if it is not greater, the current driving scenario of the vehicle is determined not to be a light surge scenario. If the second average light intensity is not greater than the light surge reference intensity, the current driving scenario of the vehicle is determined not to be a light surge scenario.

[0070] In this embodiment, the above steps can accurately identify sudden changes in lighting conditions, effectively improve the targeting of driving scenario judgment, reduce the scenario misjudgment rate, and thus provide reliable data support for the formulation of subsequent in-vehicle item reminder strategies.

[0071] Optionally, special lighting scenarios also include scenarios with sudden drops in lighting.

[0072] Furthermore, after obtaining the second average light intensity, the method further includes: calculating the product of the second preset multiple and the second average light intensity to obtain the light drop reference intensity; determining whether the first average light intensity is greater than the light drop reference intensity; if it is greater, then if the first average light intensity is greater than the fourth preset light intensity threshold, the driving scenario in which the current vehicle is located is determined to be a light drop scenario.

[0073] Specifically, a sudden drop in light intensity is another specific type of special lighting scenario, referring to driving scenarios where the light intensity in the vehicle's environment drops sharply within a short period of time. Examples of sudden drop in light intensity scenarios include vehicles entering tunnels, densely shaded roads, and shadowed areas under overpasses. The second preset multiple is a quantification coefficient pre-set according to the actual application scenario or requirements to determine the magnitude of the sudden drop in light intensity, such as a second preset multiple of 3. The reference intensity for sudden light intensity drop is the product of the second average light intensity and the second preset multiple, and is the critical threshold for determining whether the light intensity has reached the degree of sudden drop. The fourth preset light intensity threshold is the lowest baseline light intensity threshold pre-set according to the actual application scenario or requirements for determining sudden light intensity drop scenarios, such as a fourth preset light intensity threshold of 5000 Lux.

[0074] In specific implementation, after obtaining the second average light intensity, the product of the second preset multiple and the second average light intensity can be calculated to obtain the light drop reference intensity. Then, it is determined whether the first average light intensity is greater than the light drop reference intensity. If the first average light intensity is greater than the light drop reference intensity, it is further determined whether it is greater than a fourth preset light intensity threshold. When the first average light intensity is greater than the fourth preset light intensity threshold, the current driving scenario of the vehicle is determined to be a light drop scenario. If the first average light intensity is not greater than the light drop reference intensity or the first average light intensity is not greater than the fourth preset light intensity threshold, the current driving scenario of the vehicle is determined not to be a special lighting scenario. At this time, the product of the first preset multiple and the first average light intensity can be calculated again to obtain the light surge reference intensity, and the step of determining whether the current driving scenario of the vehicle is a light surge scenario can be initiated.

[0075] In this embodiment, the above steps can accurately capture the situation of a sudden drop in light intensity, fill the gap in scene judgment, reduce the scene misjudgment rate, and thus provide a reliable basis for the formulation of subsequent vehicle-mounted item reminder strategies.

[0076] Step 211: Input the visual information into the pre-trained visual scene determination model to obtain the first candidate driving scene.

[0077] Specifically, the visual scene determination model refers to the model obtained by training a deep learning model based on different historical visual scenes and corresponding historical driving scene labels. The first candidate driving scene refers to the preliminary judgment result of the driving scene based solely on the output of onboard visual information, and its output includes the driving scene type and the corresponding confidence level.

[0078] In practice, after obtaining the visual information, preprocessing operations can be performed on it, such as image denoising, image enhancement, size normalization, and distortion correction. Then, the preprocessed visual information is input into a pre-trained visual scene determination model to obtain the first candidate driving scene.

[0079] Optionally, after obtaining the visual information, object detection algorithms (such as YOLO, SSD, Faster R-CNN, etc.) can be used to detect the image and extract traffic sign information contained in the visual information. The extracted traffic sign information is then input into a pre-trained sign scene determination model to obtain the first candidate driving scene. The sign scene determination model is a deep learning model trained based on different historical traffic sign information and corresponding historical driving scene labels. Traffic sign information consists of feature data corresponding to various road functional signs identified from the visual information, such as tollbooth signs, parking lot P signs, gas station signs, tunnel signs, service area signs, highway entrance signs, etc. It should be noted that if no valid traffic sign information is extracted from the vehicle's visual information, the result for the first candidate driving scene is directly determined to be empty.

[0080] In this embodiment, the above steps can improve the objectivity and accuracy of subsequent scene determination.

[0081] Step 212: Determine candidate service nodes based on real-time location information and preset filtering distance, and determine the second candidate driving scenario based on the candidate service nodes and the service node-scenario correspondence table.

[0082] Specifically, the preset filtering distance refers to a geographical range threshold centered on the vehicle's current location, pre-set according to actual conditions or needs. For example, the preset filtering distance could be 3 kilometers. Candidate service nodes refer to various functional locations directly related to vehicle driving scenario determination within the preset filtering distance, such as gas stations, highway service areas, parking lots, and charging stations. The service node-scenario mapping table refers to a structured data table pre-built according to actual conditions or needs, used to store the mapping relationship between different types of service nodes and driving scenarios. For example, if the service node type is a gas station, the corresponding driving scenario is a gas station scenario; if the service node type is a parking lot, the corresponding driving scenario is a parking lot scenario. The second candidate driving scenario refers to the preliminary judgment result of the driving scenario determined based on the candidate service nodes and the service node-scenario mapping table, including the driving scenario type and its corresponding confidence level.

[0083] In practice, the system first searches a map database (a pre-built, structured geographic information storage and management system deployed in the vehicle system) based on the vehicle's real-time location information, preset filtering distances, and preset service node types (such as gas stations, highway service areas, and parking lots) to filter out candidate service nodes that meet the criteria. Then, it queries the service node-scenario correspondence table to obtain the driving scenario type corresponding to each candidate service node. Subsequently, based on the straight-line distance from the current vehicle to each candidate service node, the confidence level of the corresponding candidate driving scenario is calculated using the formula: Confidence Level = 1 - |(Straight-line distance from the current vehicle to the candidate service node - Optimal alert distance)| / Preset baseline value. The specific values ​​of the optimal alert distance and the preset baseline value can be obtained by querying the service node-confidence calculation relationship table. The service node-confidence calculation relationship table is a pre-built structured data mapping table based on actual conditions or needs, used to store the one-to-one correspondence between different types of candidate service nodes and the core parameters required for confidence calculation. For example, if the candidate service node type is a toll station, the optimal reminder distance is 2000 meters, and the preset baseline value is 3000 meters; if the candidate service node type is a parking lot, the optimal reminder distance is 200 meters, and the preset baseline value is 5000 meters.

[0084] In this embodiment, the above steps can improve the objectivity and accuracy of subsequent scene determination.

[0085] Step 213: Based on the driving status information, perform rule matching in the driving status and scenario matching library to obtain the third candidate driving scenario.

[0086] Specifically, the driving state and scenario matching library refers to a rule-based database established according to actual conditions or needs, used to store different combinations of driving state parameters, as well as their corresponding driving scenario matching rules and confidence levels. The third candidate driving scenario refers to the preliminary judgment result of the driving scenario obtained after matching the driving state information with the driving state and scenario matching library according to rules, including the driving scenario type and the corresponding confidence level.

[0087] In practice, after obtaining the driving status information, rule matching can be performed in the driving status and scenario matching library based on the driving status information to obtain the third candidate driving scenario. For example, if the driving status information is that the vehicle speed is continuously decreasing and the brake pedal is activated, the matched driving scenario is the toll station scenario, with a confidence level of 0.6; if the driving status information is that the vehicle speed is 0, the gear is D, and the duration of this state exceeds 30 seconds, it is determined to be the long-term parking scenario at the traffic light, with a confidence level of 0.75; if the driving status information is that the turn signal is activated (left turn or right turn) and the vehicle speed is less than 30 km / h, the matched driving scenario is the parking lot scenario, with a confidence level of 0.5.

[0088] In this embodiment, the above steps can improve the objectivity and accuracy of subsequent scene determination.

[0089] Step 214: Determine the target driving scenario based on the first candidate driving scenario, the second candidate driving scenario, and the third candidate driving scenario.

[0090] In practice, after obtaining the first candidate driving scenario, the second candidate driving scenario, and the third candidate driving scenario, the candidate driving scenario with the highest confidence among the three can be determined as the target driving scenario for the current vehicle.

[0091] In this embodiment, the limitations of a single data source can be effectively avoided through the above steps, the misjudgment rate of the scene can be greatly reduced, thereby improving the accuracy of driving scene judgment and ensuring the reliability of the target driving scene judgment result.

[0092] Further, step 214 may specifically include: integrating the first candidate driving scenario, the second candidate driving scenario, and the third candidate driving scenario to obtain a scenario set; weighting and summing the confidence scores of the same candidate driving scenario in the scenario set to obtain the comprehensive confidence score of each candidate driving scenario in the scenario set; and determining the driving scenario with the highest comprehensive confidence score in the scenario set as the target driving scenario.

[0093] Specifically, the scenario set refers to the candidate driving scenario dataset composed of the first, second, and third candidate driving scenarios. The comprehensive confidence score refers to the normalized confidence score value obtained by weighting or fusing the confidence scores of the first, second, and third candidate driving scenarios, and is used to quantitatively evaluate the overall matching degree after the fusion of multi-dimensional candidate scenarios.

[0094] In practice, the first, second, and third candidate driving scenarios can be integrated to construct a scenario set containing all candidate scenario types and their corresponding confidence levels. Then, the confidence levels of candidate driving scenarios of the same type within the scenario set are weighted and summed to obtain the comprehensive confidence level for each scenario type. The calculation formula is as follows: Comprehensive Confidence Level = ∑ 3 i=1 (W) i ×C i ), where W i Let C be the weight coefficient of the i-th dimension. i Let be the single-dimensional confidence score for the i-th dimension; this embodiment includes three dimensions: visual, location, and driving state, and the sum of the weight coefficients must be 1. Finally, the driving scenario with the highest overall confidence score in the scenario set is determined as the target driving scenario.

[0095] For example: if the first candidate driving scenario is a toll station scenario with a confidence level of 0.6 and a weighting coefficient of 0.33; the second candidate driving scenario is a parking lot scenario with a confidence level of 0.7 and a weighting coefficient of 0.34; and the third candidate driving scenario is a toll station scenario with a confidence level of 0.5 and a weighting coefficient of 0.33, then the overall confidence level of the toll station scenario is 0.363; the overall confidence level of the parking lot scenario is 0.238; and the target driving scenario is the toll station scenario.

[0096] For example: If the first candidate driving scenario is a toll station scenario with a confidence level of 0.6 and a gas station scenario with a confidence level of 0.5, and the weighting coefficient is 0.5; the second candidate driving scenario is a toll station scenario with a confidence level of 0.4 and a gas station scenario with a confidence level of 0.6, and the weighting coefficient is 0.2; and the third candidate driving scenario is a toll station scenario with a confidence level of 0.7 and a gas station scenario with a confidence level of 0.3, and the weighting coefficient is 0.3, then the overall confidence level of the toll station scenario is 0.59, and the overall confidence level of the gas station scenario is 0.46; the target driving scenario is the toll station scenario.

[0097] Optionally, to further improve the reliability of driving scenario determination and reduce the risk of false alarms, when the overall confidence of the target driving scenario exceeds the preset confidence threshold (e.g., 0.7), the subsequent step 215 is executed; otherwise, the execution of step 210 is returned.

[0098] In this embodiment, the above steps improve the scientific rigor and rationality of the scenario determination, thereby ensuring that the determination result of the target driving scenario is unique and authoritative.

[0099] Step 215: Match the target driving scenario with the scene item association rule library to obtain the reminder item information.

[0100] Specifically, the scene-item association rule base is a pre-built structured rule dataset based on extensive statistical analysis of real user behavior. It stores the one-to-one correspondence between different target driving scenarios and the items the driver needs to be reminded of. All user behavior data is collected compliantly after authorization. The reminder item information is the data related to items the driver needs to prepare or pay attention to in the corresponding scenario after matching the target driving scenario with the scene-item association rule base. This information may include item name, reminder priority, and probability of need.

[0101] In practice, after obtaining the target driving scenario, the system can perform matching in the scenario item association rule library based on the target driving scenario to obtain the corresponding reminder item information.

[0102] For example, a sample table of the scene item association rule base is shown in Table 1:

[0103] Table 1. Example Table of Scene Item Association Rule Base

[0104]

[0105] Note: "-" in the table indicates empty, "Scene" is the English identifier for a scene, and "-0x" (where x ranges from 1 to 10) is the scene number used to distinguish different scenes.

[0106] In addition, to further enhance the personalized adaptation capability of the scene item association rule base, the rule base can be dynamically updated and optimized based on the historical behavior data of the current vehicle driver. The specific optimization methods are as follows: 1. When the cumulative occurrence of a certain driving scene reaches 10 times or more, the actual usage frequency of various in-vehicle items by the driver in that scene is automatically counted; 2. The item demand probability is calculated using a personalized adjustment formula: The formula is: Adjusted demand probability = Original demand probability × 0.3 + Actual usage frequency × 0.7.

[0107] In this embodiment, the above steps achieve precise linkage between the scene and the object, thereby improving the targeting of the reminder and enhancing the user experience.

[0108] Step 216: Query the item location database based on the item information to obtain the item location information, and determine the reminder frequency parameter based on the item information.

[0109] Specifically, the item location database refers to a structured database built according to actual conditions or needs, used to store the storage location information of various items inside the vehicle. It can automatically record and update the actual placement location of various items inside the vehicle using image data collected by multi-view cameras inside the vehicle, combined with image recognition algorithms. It also supports manual entry / modification of personalized storage locations. The reminder item location information is the storage location data of the corresponding item inside the vehicle obtained after querying and matching in the item location database. The reminder frequency parameter is a reminder frequency rule determined based on the reminder item information. Such parameters include item name, initial reminder timing, number of repetitions, repetition interval, and repetition trigger conditions.

[0110] In practice, after obtaining the information about the items to be reminded, the system can search the item location database based on the item name in the reminder item information to obtain the corresponding reminder item location information; at the same time, it can search the item reminder frequency parameter correspondence table based on the item name in the reminder item information to obtain the reminder frequency parameter of the corresponding item.

[0111] The item reminder frequency parameter correspondence table is a pre-built structured parameter table based on actual conditions or needs. It is used to store reminder strategy parameters corresponding to different in-vehicle items. For example: Item name: ETC card, parking ticket, key; First reminder timing: 3 kilometers from the target driving scenario trigger location; Number of repetitions: 2; Repetition interval: 1 kilometer traveled; Repetition condition: The distance to the target driving scenario trigger location is reduced by more than 1 kilometer and the item is detected as not taken out. Item name: fuel card, wallet, sunglasses; First reminder timing: 2 kilometers from the target driving scenario trigger location; Number of repetitions: 1; Repetition interval: 1 kilometer traveled; Repetition condition: The distance to the target driving scenario trigger location is reduced by more than 1 kilometer and the item is detected as not taken out. Item name: water cup, tissue, mobile phone; First reminder timing: 500 meters from the target driving scenario trigger location; Number of repetitions: 0; Repetition interval: None; Repetition condition: None. The trigger location of the target driving scenario refers to the core geographical location of each type of target driving scenario. For example, the trigger location for a gas station scenario is the coordinates of the gas station entrance, and the trigger location for a toll station scenario is the coordinates of the toll station ramp start point.

[0112] For example: Item name: ETC card, parking ticket, key; First reminder timing: Immediate reminder; Number of repetitions: 2; Repetition interval: 5 seconds. Item name: Gas card, wallet, sunglasses; First reminder timing: Immediate reminder; Number of repetitions: 2; Repetition interval: 3 seconds.

[0113] Additionally, if no matching record is found in the item location database, it is determined that the item is either not recorded or not in the vehicle. In this case, no corresponding in-vehicle item reminder strategy will be generated to avoid misleading the user. Furthermore, a storage and placement confidence parameter can be added to the item location database: the initial storage and placement confidence is 1, decreasing over time; if an item record exists but the confidence is below a preset threshold (e.g., 0.3), the reminder content will be supplemented with the message: "May be at location XX, but it is uncertain whether it has been moved," ensuring the accuracy of the feedback information.

[0114] In this embodiment, the above steps can effectively reduce the cost for drivers to retrieve and find items in the vehicle, avoid the interference of invalid reminder information with driving attention, and thus significantly improve the user's driving experience; at the same time, it also lays a data foundation for the generation of subsequent in-vehicle item reminder strategies.

[0115] Step 217: Determine the reminder method based on the driving status information.

[0116] Specifically, the reminder method is a push notification format determined based on vehicle driving status information.

[0117] In practice, the reminder method can be obtained by querying the mapping table between driving status and reminder method based on the driving status information. This mapping table is a pre-built structured matching table based on actual conditions or needs, used to store the one-to-one correspondence between different vehicle driving statuses and corresponding reminder methods. For example: Driving status information (vehicle speed): Full speed range, reminder method: voice reminder, head-up display; Driving status information (vehicle speed): Below 50 km / h, reminder method: central control screen display; Driving status information (vehicle speed): Below 30 km / h, reminder method: vibration alert.

[0118] Optionally, after determining the reminder method based on driving status information, the reminder method can be dynamically adjusted in conjunction with driver status information. The specific adjustment rules are as follows: if the driver is detected to be slightly distracted, a vibration alert will be enabled, and the voice reminder volume will be increased by 10% and the information display time on the central control screen / head-up display will be extended; if the driver is detected to be highly focused, the information display time on the central control screen / head-up display will be appropriately shortened and the voice reminder volume will be reduced.

[0119] In this embodiment, the above steps can adapt the reminder method to driving conditions and improve driving safety.

[0120] Step 218: Generate an in-vehicle item reminder strategy based on the reminder item information, reminder item location information, reminder method, and reminder frequency parameters.

[0121] In practice, the core information of four dimensions—item, location, frequency, and method—is first integrated to generate a standardized reminder content template. For scenarios with multiple items to be reminded, low-priority items with a demand probability below a preset threshold (e.g., 0.1) are filtered out. The remaining items are first sorted hierarchically according to a preset priority, and items within the same priority are then sorted in descending order of demand probability. Based on the sorting results and the standardized reminder content template, an in-vehicle item reminder strategy is generated.

[0122] In this embodiment, the above steps provide a data foundation for subsequent reminders.

[0123] Step 219: Generate an in-vehicle item reminder strategy based on the special lighting scene and the current vehicle's sunglasses equipment information.

[0124] In practice, the system first determines whether the driver needs to wear sunglasses based on specific lighting conditions. For example, in a scenario of sudden light surge, the driver needs to wear sunglasses; in a scenario of sudden light drop, the driver needs to remove sunglasses. If it is determined that sunglasses are required, the system collects the driver's facial information through the in-vehicle camera and uses image recognition technology to determine whether the driver is already wearing sunglasses. If the driver is already wearing sunglasses, no in-vehicle item reminder strategy is generated, or a safety reminder is generated. If the driver is not wearing sunglasses, the system retrieves the vehicle's sunglasses configuration information from the in-vehicle item information database, determines the appropriate reminder method based on driving status information, and then generates a targeted in-vehicle item reminder strategy based on the sunglasses configuration information, the selected reminder method, and preset reminder frequency parameters. If the sunglasses configuration information indicates that the vehicle is equipped with sunglasses, an in-vehicle item reminder strategy is generated based on the location of the sunglasses. If the sunglasses configuration information indicates that the vehicle is not equipped with sunglasses, no in-vehicle item reminder strategy is generated, or a safety reminder is generated. If it is determined that sunglasses are not required, the driver's facial information is collected through the in-vehicle camera, and image recognition technology is used to determine whether the driver is wearing sunglasses: if the driver is wearing sunglasses, a reminder is generated, suggesting that the driver remove sunglasses if the current lighting does not require them; if the driver is not wearing sunglasses, the reminder is not executed, or a safety reminder is generated.

[0125] Step 220: Remind the current vehicle user based on the in-vehicle item reminder strategy.

[0126] Optionally, when executing the recurring reminder process, the reminder method can be dynamically updated based on the vehicle's real-time driving status.

[0127] Optionally, before reminding the current user of the vehicle based on the in-vehicle item reminder strategy, it can be determined whether the current user's state is dangerous: if it is determined to be dangerous, the reminder is immediately prohibited, and the process returns to step 210; if it is determined to be non-dangerous, the established in-vehicle item reminder strategy is executed normally. A dangerous state is triggered by any of the following conditions: 1. Emergency braking: brake pedal pressure is greater than 80% and vehicle deceleration is greater than 0.6 times the gravitational acceleration (g); 2. Collision warning: the advanced driver assistance system issues a collision warning signal; 3. Seatbelt status: the seatbelt sensor provides a signal that the driver is not wearing a seatbelt; 4. Driver fatigue / analysis: the advanced driver assistance system detects that the driver's attention level is "severely distracted" or "severely fatigued"; 5. Lane departure: the advanced driver assistance system detects non-active lane departure.

[0128] The in-vehicle item reminder method provided in this invention first acquires the real-time ambient light intensity data of the current vehicle and determines whether the current driving scenario is a special lighting scenario based on the real-time ambient light intensity data. This clearly distinguishes between special lighting scenarios and normal lighting scenarios, thus providing clear triggering conditions for scene-based reminder strategies. Simultaneously, it effectively avoids sending invalid reminders such as "take your sunglasses" to the driver in normal lighting scenarios, balancing driving safety and user experience. Furthermore, the need to take out sunglasses is usually triggered by sudden changes in light (such as entering a strong light environment), exhibiting strong immediacy. Therefore, by quickly determining the special lighting scenario before triggering the corresponding reminder, the timeliness of the reminder is improved, and the interference of irrelevant information on the driver is reduced, further optimizing the user experience. Next, if it is a special lighting scenario, an in-vehicle item reminder strategy is generated based on the special lighting scenario and the current vehicle's sunglasses equipment information. This generates a more accurate in-vehicle item reminder strategy, effectively avoiding invalid reminders that interfere with the driver, thus optimizing the user's driving experience and further improving driving safety. If the lighting conditions are not special, the visual information is input into a pre-trained visual scene determination model to obtain the first candidate driving scene. Candidate service nodes are determined based on real-time location information and a preset filtering distance. A second candidate driving scene is determined based on the correspondence between candidate service nodes and service nodes and scenes. A third candidate driving scene is obtained by matching rules in a driving state and scene matching library based on driving state information, which improves the objectivity and accuracy of subsequent scene determination. Determining the target driving scene based on the first, second, and third candidate driving scenes effectively avoids the limitations of a single data source, significantly reduces the scene misjudgment rate, and thus improves the accuracy of driving scene determination, ensuring the reliability of the target driving scene determination results. Matching the target driving scene in a scene item association rule library yields reminder item information, achieving precise linkage between scenes and items, thereby improving the targeting of reminders and enhancing the user experience. By querying the item location database based on the item information, the location information of the items is obtained. The reminder frequency parameter is then determined based on this information. This effectively reduces the cost for drivers to retrieve items from their vehicles and avoids irrelevant reminders interfering with driving attention, thus significantly improving the user's driving experience. Simultaneously, it lays the data foundation for the generation of subsequent in-vehicle item reminder strategies. Determining the reminder method based on driving status information allows the reminder method to adapt to driving conditions, improving driving safety. The in-vehicle item reminder strategy is generated based on the item information, location information, reminder method, and reminder frequency parameters, providing a data foundation for subsequent reminders. Finally, reminders are delivered to the current vehicle user based on the in-vehicle item reminder strategy, enabling scenario-based and precise reminders, thereby improving driving safety and user experience.Therefore, the technical solution of the present invention can solve the problem in the prior art that recognition deviation caused by single-dimensional scene judgment leads to a disconnect between reminder content and needs, reduced practicality, interference with driving and impact on safety.

[0129] Figure 3 This is a schematic diagram of a vehicle-mounted item reminder device provided in an embodiment of the present invention. This device belongs to the same inventive concept as the vehicle-mounted item reminder methods in the above embodiments. Details not described in detail in the embodiments of the vehicle-mounted item reminder device can be found in the embodiments of the above-described vehicle-mounted item reminder methods. Figure 3 As shown, the device includes:

[0130] like Figure 3 As shown, the device includes:

[0131] The determination module 310 is used to acquire the real-time ambient light intensity data of the current vehicle and determine whether the driving scenario in which the current vehicle is located is a special lighting scenario based on the real-time ambient light intensity data.

[0132] The first generation module 320 is used to generate an in-vehicle item reminder strategy based on the special lighting scene and the current vehicle's sunglasses equipment information if the current driving scene of the vehicle is a special lighting scene.

[0133] The second generation module 330 is used to determine the target driving scenario of the current vehicle based on the visual information, real-time location information and driving status information of the current vehicle if the current driving scenario is not a special lighting scenario, and to generate an in-vehicle item reminder strategy based on the target driving scenario.

[0134] The reminder module 340 is used to remind the user of the current vehicle based on the in-vehicle item reminder strategy.

[0135] Based on the above embodiments, the special lighting scenarios include strong light scenarios and low light scenarios. The determining module 310 determines whether the current driving scenario of the vehicle is a special lighting scenario based on the real-time ambient light intensity data, including:

[0136] If the real-time ambient light intensity data is greater than a first preset light intensity threshold, then if the real-time ambient light intensity data is greater than the first preset light intensity threshold and the duration exceeds a first preset duration, the current driving scenario of the vehicle is determined to be the strong light scenario; if the real-time ambient light intensity data is not greater than the first preset light intensity threshold, then if the real-time ambient light intensity data is less than a second preset light intensity threshold, then if the real-time ambient light intensity data is less than the second preset light intensity threshold and the duration exceeds a second preset duration, the current driving scenario of the vehicle is determined to be the low light scenario.

[0137] Based on the above embodiments, the special lighting scenario also includes a lighting surge scenario. The determining module 310 determines whether the current driving scenario of the vehicle is a special lighting scenario based on the real-time ambient light intensity data, including:

[0138] Ambient light intensity data within a first preset time period is acquired to obtain first historical ambient light intensity data, and ambient light intensity data within a second preset time period is acquired to obtain second historical ambient light intensity data; the average value of the first historical ambient light intensity data is calculated to obtain a first average light intensity, and the average value of the second historical ambient light intensity data and the real-time ambient light intensity data is calculated to obtain a second average light intensity; the product of a first preset multiple and the first average light intensity is calculated to obtain a light surge reference intensity; it is determined whether the second average light intensity is greater than the light surge reference intensity; if it is greater, then if the second average light intensity is greater than a third preset light intensity threshold, the current driving scenario of the vehicle is determined to be the light surge scenario.

[0139] Based on the above embodiments, the special lighting scenario also includes a sudden drop in lighting, and the device further includes:

[0140] The judgment module is used to calculate the product of the second preset multiple and the second average light intensity after obtaining the second average light intensity to obtain the light drop reference intensity; determine whether the first average light intensity is greater than the light drop reference intensity; if it is greater, then if the first average light intensity is greater than the fourth preset light intensity threshold, determine that the current driving scenario of the vehicle is the light drop scenario.

[0141] Based on the above embodiments, the second generation module 330 determines the target driving scenario of the current vehicle according to the current vehicle's visual information, real-time location information, and driving status information, including:

[0142] The visual information is input into a pre-trained visual scene determination model to obtain a first candidate driving scene; candidate service nodes are determined based on the real-time location information and a preset filtering distance; a second candidate driving scene is determined based on the candidate service nodes and the service node-scene correspondence table; rule matching is performed in the driving state and scene matching library based on driving state information to obtain a third candidate driving scene; and the target driving scene is determined based on the first candidate driving scene, the second candidate driving scene, and the third candidate driving scene.

[0143] Based on the above embodiments, the second generation module 330 determines the target driving scenario according to the first candidate driving scenario, the second candidate driving scenario, and the third candidate driving scenario, including: integrating the first candidate driving scenario, the second candidate driving scenario, and the third candidate driving scenario to obtain a scenario set; weighting and summing the confidence scores of the same candidate driving scenario in the scenario set to obtain the comprehensive confidence score of each candidate driving scenario in the scenario set; and determining the driving scenario with the highest comprehensive confidence score in the scenario set as the target driving scenario.

[0144] Based on the above embodiments, the second generation module 330 generates an in-vehicle item reminder strategy based on the target driving scenario, including:

[0145] Based on the target driving scenario, a matching process is performed in the scenario item association rule base to obtain reminder item information; based on the reminder item information, a query is performed in the item location database to obtain reminder item location information, and a reminder frequency parameter is determined based on the reminder item information; a reminder method is determined based on the driving status information; and the vehicle item reminder strategy is generated based on the reminder item information, the reminder item location information, the reminder method, and the reminder frequency parameter.

[0146] The vehicle-mounted item reminder device provided in this embodiment of the invention can execute the vehicle-mounted item reminder method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0147] It is worth noting that in the above embodiments of the vehicle-mounted item reminder device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0148] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Figure 4 A block diagram of an exemplary electronic device 4 suitable for implementing embodiments of the present invention is shown. Figure 4 The electronic device 4 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0149] like Figure 4 As shown, electronic device 4 is represented in the form of a general-purpose computing electronic device. The components of electronic device 4 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0150] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0151] Electronic device 4 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by electronic device 4, including volatile and non-volatile media, removable and non-removable media.

[0152] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Electronic device 4 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (… Figure 4 Not shown; usually referred to as a "hard drive"). Although Figure 4 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. System memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0153] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of the present invention.

[0154] Electronic device 4 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with electronic device 4, and / or with any device that enables electronic device 4 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed through input / output (I / O) interface 22. Furthermore, electronic device 4 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. Figure 4 As shown, network adapter 20 communicates with other modules of electronic device 4 via bus 18. It should be understood that, although... Figure 4 Not shown, it can be combined with electronic device 4 to use other hardware and / or software modules, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0155] The processing unit 16 executes various functional applications and page displays by running programs stored in the system memory 28, such as implementing the vehicle item reminder method provided in the embodiments of the present invention.

[0156] Of course, those skilled in the art will understand that the processor can also implement the technical solution of the vehicle-mounted item reminder method provided in any embodiment of the present invention.

[0157] This invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements, for example, the in-vehicle item reminder method provided in this invention.

[0158] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0159] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0160] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0161] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0162] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computing device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0163] Furthermore, the acquisition, storage, use, and processing of data in the technical solution of this invention all comply with relevant laws and regulations.

[0164] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for reminding about items in a vehicle, characterized in that, The method includes: The system acquires real-time ambient light intensity data of the current vehicle and determines whether the current driving scenario of the vehicle is a special lighting scenario based on the real-time ambient light intensity data. If the current driving scenario of the vehicle is a special lighting scenario, then a vehicle item reminder strategy is generated based on the special lighting scenario and the current vehicle's sunglasses equipment information. If the current driving scenario of the vehicle is not a special lighting scenario, then the target driving scenario of the current vehicle is determined based on the current vehicle's visual information, real-time location information and driving status information, and an in-vehicle item reminder strategy is generated based on the target driving scenario. The user of the current vehicle is reminded based on the in-vehicle item reminder strategy; The special lighting scenarios also include lighting surge scenarios. Determining whether the current driving scenario of the vehicle is a special lighting scenario based on the real-time ambient light intensity data includes: acquiring ambient light intensity data within a first preset time period to obtain first historical ambient light intensity data, and acquiring ambient light intensity data within a second preset time period to obtain second historical ambient light intensity data; calculating the average value of the first historical ambient light intensity data to obtain a first average light intensity, and calculating the average value of the second historical ambient light intensity data and the real-time ambient light intensity data to obtain a second average light intensity; calculating the product of a first preset multiple and the first average light intensity to obtain a lighting surge reference intensity; determining whether the second average light intensity is greater than the lighting surge reference intensity; if it is greater, then if the second average light intensity is greater than a third preset light intensity threshold, the current driving scenario of the vehicle is determined to be the lighting surge scenario. The special lighting scenario also includes a sudden drop in lighting scenario. After obtaining the second average light intensity, the method further includes: calculating the product of the second preset multiple and the second average light intensity to obtain a sudden drop in lighting reference intensity; determining whether the first average light intensity is greater than the sudden drop in lighting reference intensity; if it is greater, then if the first average light intensity is greater than the fourth preset light intensity threshold, the driving scenario in which the current vehicle is located is determined to be the sudden drop in lighting scenario.

2. The method according to claim 1, characterized in that, The special lighting scenarios include strong light scenarios and low light scenarios. Determining whether the current driving scenario of the vehicle is a special lighting scenario based on the real-time ambient light intensity data includes: Determine whether the real-time ambient light intensity data is greater than a first preset light intensity threshold; If the real-time ambient light intensity data is greater than the first preset light intensity threshold and the duration exceeds the first preset duration, then the driving scenario in which the current vehicle is located is determined to be the strong light scenario. If it is not greater than, then determine whether the real-time ambient light intensity data is less than the second preset light intensity threshold; if it is less than, then if the real-time ambient light intensity data is less than the second preset light intensity threshold and the duration exceeds the second preset duration, determine that the current driving scenario of the vehicle is the low light scenario.

3. The method according to claim 1, characterized in that, The target driving scenario for the current vehicle is determined based on the vehicle's visual information, real-time location information, and driving status information, including: The visual information is input into a pre-trained visual scene determination model to obtain the first candidate driving scene; Based on the real-time location information and the preset filtering distance, candidate service nodes are determined, and a second candidate driving scenario is determined based on the candidate service nodes and the service node-scenario correspondence table. Based on driving status information, rule matching is performed in the driving status and scenario matching library to obtain the third candidate driving scenario; The target driving scenario is determined based on the first candidate driving scenario, the second candidate driving scenario, and the third candidate driving scenario.

4. The method according to claim 3, characterized in that, Determining the target driving scenario based on the first candidate driving scenario, the second candidate driving scenario, and the third candidate driving scenario includes: The first candidate driving scenario, the second candidate driving scenario, and the third candidate driving scenario are integrated to obtain a scenario set; The confidence scores of the same candidate driving scenario in the scenario set are weighted and summed to obtain the comprehensive confidence score of each candidate driving scenario in the scenario set. The driving scenario with the highest overall confidence level in the set of scenarios is determined as the target driving scenario.

5. The method according to claim 1, characterized in that, Based on the target driving scenario, a vehicle-mounted item reminder strategy is generated, including: Based on the target driving scenario, a match is made in the scenario item association rule library to obtain the reminder item information; Based on the information of the reminder item, a query is performed in the item location database to obtain the location information of the reminder item, and the reminder frequency parameter is determined based on the information of the reminder item; The reminder method is determined based on the driving status information; The vehicle-mounted item reminder strategy is generated based on the item information, the item location information, the reminder method, and the reminder frequency parameter.

6. A vehicle-mounted item reminder device, characterized in that, The device comprising: (The method for reminding of in-vehicle items as described in any one of claims 1 to 5) The determination module is used to acquire the real-time ambient light intensity data of the current vehicle and determine whether the driving scenario in which the current vehicle is located is a special lighting scenario based on the real-time ambient light intensity data. The first generation module is used to generate an in-vehicle item reminder strategy based on the special lighting scenario and the current vehicle's sunglasses equipment information if the current driving scenario is a special lighting scenario. The second generation module is used to determine the target driving scenario of the current vehicle based on the visual information, real-time location information and driving status information of the current vehicle if the current driving scenario is not a special lighting scenario, and to generate an in-vehicle item reminder strategy based on the target driving scenario. The reminder module is used to remind the user of the current vehicle based on the in-vehicle item reminder strategy.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and a memory communicatively connected to said at least one processor; The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the reminder method for in-vehicle items as described in any one of claims 1-5.

8. A storage medium containing computer-executable instructions, characterized in that, The computer-executable instructions, when executed by a computer processor, are used to perform the reminder method for in-vehicle items as described in any one of claims 1-5.

Images