Information prompting methods, devices and computer-readable storage media

Abstract

This application discloses an information prompting method, apparatus, and computer-readable storage medium. It can acquire sound signals corresponding to acoustic events; determine weight coefficients for each acoustic event based on the sound signals, and determine the volume value of the sound signal corresponding to each acoustic event; determine the weight priority order of acoustic events based on the weight coefficients and volume values, and select acoustic events to be processed first based on the weight priority order; acquire target images corresponding to the acoustic events to be processed first, and perform image information analysis on the target images to obtain target event information corresponding to the acoustic events to be processed first; and provide information prompts based on the target event information. Thus, it is possible to determine the acoustic events that relevant users need to respond to first based on the weight coefficients of the acoustic events and the volume of the sound signals, and combine the image information of the acoustic events that need to be responded to first to determine the target event information for information prompting.

Description

Technical Field

[0001] This application relates to the field of computer technology, and specifically to an information prompting method, apparatus, and computer-readable storage medium. Background Technology

[0002] As the automotive industry develops and vehicle manufacturing technology becomes increasingly sophisticated, automakers are placing greater emphasis on the user's driving experience, such as vehicle ride smoothness. However, besides ride smoothness, the sound insulation of the vehicle's interior is also a major concern for both automakers and passengers, as it can significantly impact the driving experience. In response, automakers have made progress in automotive sound insulation technology, enhancing the sound insulation of the sealed interior spaces to protect passengers from external noise and improve the overall driving experience.

[0003] However, while improved vehicle interior sound insulation can protect passengers from external noise, it may also prevent them from acquiring important sound information about the external environment, potentially leading to safety hazards and reducing the safety of the journey. Summary of the Invention

[0004] This application provides an information prompting method, apparatus, and computer-readable storage medium. These features enable passengers to obtain important sound information about the external environment, avoiding potential safety hazards and improving the safety of the travel process.

[0005] This application provides an information prompting method, including:

[0006] Collect sound signals corresponding to acoustic events;

[0007] The weighting coefficients corresponding to the acoustic events are determined based on the sound signals, and the volume value of the sound signal corresponding to each acoustic event is determined.

[0008] The weight priority order of the acoustic events is determined based on the weight coefficients and volume values, and the acoustic events to be processed first are selected based on the weight priority order.

[0009] Obtain the target image corresponding to the priority acoustic event, and perform image information analysis on the target image to obtain the target event information corresponding to the priority acoustic event;

[0010] Information prompts will be provided based on the target event information.

[0011] Accordingly, embodiments of this application provide an information prompting device, including:

[0012] Acquisition unit, used to acquire sound signals corresponding to acoustic events;

[0013] The determining unit is used to determine the weighting coefficients corresponding to the acoustic events based on the sound signals, and to determine the volume value of the sound signals corresponding to each acoustic event.

[0014] The selection unit is used to determine the weight priority order of the acoustic events based on the weight coefficient and the volume value, and to select the acoustic events to be processed first based on the weight priority order.

[0015] The analysis unit is used to acquire the target image corresponding to the priority acoustic event, and to perform image information analysis on the target image to obtain the target event information corresponding to the priority acoustic event;

[0016] The prompting unit is used to provide information prompts based on the target event information.

[0017] In some embodiments, the determining unit is further configured to:

[0018] The sound signal is analyzed and processed to obtain the sound signal spectrum information;

[0019] The event category of the acoustic event is determined based on the spectral information of the sound signal;

[0020] The weight coefficients corresponding to the event categories are determined based on a preset list of acoustic event weights.

[0021] In some embodiments, the selection unit is further configured to:

[0022] The weight priority value is obtained by weighting the weight coefficient and the volume value.

[0023] Obtain the second weight priority value of the second acoustic event within a preset time period, wherein the second acoustic event is an acoustic event to be processed other than the aforementioned acoustic event;

[0024] The weight priority order corresponding to the acoustic event is determined based on the weight priority value and the second weight priority value.

[0025] In some embodiments, the analysis unit is further configured to:

[0026] Determine the event category of the priority acoustic events;

[0027] Image information elements are obtained by recognizing image information based on the event category and the target image using a target recognition model. The target recognition model is obtained by iterative training of sample images, sample event categories, and sample image information elements.

[0028] Based on the image information elements, determine the target event information corresponding to the priority acoustic event.

[0029] In some embodiments, the analysis unit is further configured to:

[0030] The target image features are obtained by extracting features from the target image based on the event category using a target recognition model;

[0031] Key point feature recognition is performed on the target image features to obtain multiple key point features;

[0032] Based on the aforementioned key point features, image information elements are determined.

[0033] In some embodiments, the analysis unit is further configured to:

[0034] Determine the position coordinates of the image information element in the target image;

[0035] The location coordinates are subjected to vector transformation to obtain image information element vectors;

[0036] Based on the image information element vector, the target event information corresponding to the priority acoustic event is determined.

[0037] In some embodiments, the image information feature vector includes a body posture information feature vector of the target object, and the analysis unit is further configured to:

[0038] Construct a Cartesian coordinate system for the target object in the target image;

[0039] Determine the vector direction corresponding to the body posture information element vector, and determine the quadrant characteristic relationship of the body posture information element in the rectangular coordinate system based on the vector direction;

[0040] The object pose information corresponding to the quadrant characteristic relationship is retrieved from the preset quadrant information list, and the object pose information is determined as the target event information corresponding to the priority acoustic event.

[0041] In some embodiments, the image information element vector includes the vehicle information element vector of the target vehicle, and the analysis unit is further configured to:

[0042] Obtain the current local location information of the local terminal, and construct a Cartesian coordinate system based on the local location information;

[0043] Based on the vehicle information element vector, determine the target quadrant characteristic relationship of the target vehicle in the Cartesian coordinate system;

[0044] Based on the vehicle information element vector and the local location information, the vehicle distance information between the target vehicle and the local terminal is evaluated, and the vehicle distance information is determined as the target event information corresponding to the priority acoustic event.

[0045] Furthermore, this application also provides a computer device, including a processor and a memory, wherein the memory stores a computer program, and the processor is used to run the computer program in the memory to implement the steps in the information prompting method provided in this application.

[0046] Furthermore, embodiments of this application also provide a computer-readable storage medium storing a plurality of instructions adapted for loading by a processor to execute steps in any of the information prompting methods provided in embodiments of this application.

[0047] Furthermore, embodiments of this application also provide a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps in any of the information prompting methods provided in embodiments of this application.

[0048] This application embodiment can collect sound signals corresponding to acoustic events; determine the weight coefficients corresponding to the acoustic events based on the sound signals, and determine the volume value of the sound signal corresponding to each acoustic event; determine the weight priority order of acoustic events based on the weight coefficients and volume values, and select the acoustic events to be processed first based on the weight priority order; acquire the target image corresponding to the acoustic event to be processed first, and perform image information analysis on the target image to obtain the target event information corresponding to the acoustic event to be processed first; and provide information prompts based on the target event information. Therefore, this solution can determine the weight coefficients of acoustic events based on the collected sound signals, and combine this with the volume of the sound signals to determine the acoustic events that relevant users need to respond to first. Furthermore, it analyzes the image information of the acoustic events that need to be responded to first to obtain the target event information, so that information prompts can be provided subsequently based on the target event information. This allows passengers to obtain important sound information about the external environment, avoids safety hazards, and improves the safety of the riding process. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of this application, 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 this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a schematic diagram of a scenario for the information prompting system provided in an embodiment of this application;

[0051] Figure 2This is a flowchart illustrating the steps of the information prompting method provided in the embodiments of this application;

[0052] Figure 3 This is a schematic diagram of the structure of the information prompting device provided in the embodiments of this application;

[0053] Figure 4 This is a schematic diagram of the structure of the computer device provided in the embodiments of this application. Detailed Implementation

[0054] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0055] This application provides an information prompting method, apparatus, and computer-readable storage medium. This application will describe the information prompting apparatus from the perspective of the apparatus itself. Specifically, the information prompting apparatus can be integrated into a computer device, which can be a server. The server can be a standalone physical server, a server cluster composed of multiple physical servers, or a distributed system. It can also provide cloud services, cloud databases, cloud computing, cloud functions, cloud storage, etc. Furthermore, the computer device can be a terminal device. The terminal can be a television, smartphone, tablet computer, laptop computer, desktop computer, smart speaker, smartwatch, wearable device, in-vehicle terminal, etc., but is not limited to these.

[0056] For example, see Figure 1 This is a schematic diagram of a scenario for an information prompting system provided in an embodiment of this application. The scenario includes a terminal or a server.

[0057] Acquire sound signals corresponding to acoustic events; determine weight coefficients for each acoustic event based on the sound signals, and determine the volume value of the sound signal for each acoustic event; determine the weight priority order of acoustic events based on the weight coefficients and volume values, and select the acoustic events to be processed first based on the weight priority order; acquire the target images corresponding to the acoustic events to be processed first, and perform image information analysis on the target images to obtain the target event information corresponding to the acoustic events to be processed first; provide information prompts based on the target event information.

[0058] The information prompts may include processing methods such as collecting sound signals, determining the weighting coefficients and volume values ​​of the sound signals, determining the acoustic events to be processed first, determining the target event information corresponding to the acoustic events to be processed first, and providing information prompts.

[0059] The following sections provide detailed descriptions of each example. It should be noted that the order in which the embodiments are described is not intended to limit the preferred order of the embodiments.

[0060] In this embodiment, the description will focus on an information prompting device, which can be integrated into a computer device such as a terminal device. See also Figure 2 , Figure 2 This is a flowchart illustrating the steps of an information prompting method provided in an embodiment of this application. When the processor on the terminal device executes the program corresponding to the information prompting method, the specific flow of the information prompting method is as follows:

[0061] 101. Collect the sound signals corresponding to acoustic events.

[0062] The acoustic event can be a sound event corresponding to a sound signal of instantaneous or continuous duration. Each sound signal from its start to its end is considered an acoustic event. For example, a 5-second horn blast can be considered an acoustic event, as can an abnormal sound that is triggered and ends instantaneously (e.g., 0.5 seconds). Therefore, an acoustic event can be determined by the duration of the sound signal from its end.

[0063] The sound signal can be the acoustic signal corresponding to an acoustic event, which is a type of electrical signal used to represent information about the acoustic event. Specifically, in order to perform subsequent information processing on the acoustic event, it needs to be represented in the form of an electrical signal. For example, the sound signal can be an analog signal or a digital signal, so that the information about the acoustic event can be processed subsequently using this signal.

[0064] To provide information alerts for acoustic events, embodiments of this application can detect acoustic events in real time and collect the corresponding sound signals. Specifically, sound sensors are used to collect the sound signals corresponding to the acoustic events, so that information can be processed based on the collected sound signals and information alerts can be sent to relevant users.

[0065] Using the above methods, it is possible to detect in real time whether there are acoustic events occurring around the user, and after detecting an acoustic event, it is possible to collect the corresponding sound signal in real time, so as to process the information and provide prompts for the acoustic event based on the collected sound signal.

[0066] 102. Determine the weighting coefficients corresponding to acoustic events based on the sound signals, and determine the volume value of the sound signal corresponding to each acoustic event.

[0067] The weighting coefficient can be the weight value of the relevant acoustic event, reflecting its priority, and is used in the priority calculation of the acoustic event. It should be noted that this weighting coefficient can be a pre-set coefficient. Specifically, a corresponding weighting coefficient can be pre-set for each type of acoustic event to determine the priority order of multiple acoustic events occurring at the same time or within a time period.

[0068] The volume value can be the volume level corresponding to the acoustic event, specifically referring to the volume of the acoustic event expressed in numerical form.

[0069] It should be noted that in order to process acoustic events based on the acquired sound signals, if the sound signal is analog, it needs to be converted into a digital sound signal. Specifically, before further processing of the acoustic event, the analog sound signal needs to be digitized. This digitization process involves: converting the time-continuous analog signal into a time-discrete, amplitude-continuous signal based on the acquired sound signal; converting each sample with continuous amplitude values ​​(analog quantity) into a discrete value (digital quantity); and then compressing and encoding the sampled and quantized sound signal according to certain requirements. This completes the digitization of the sound signal, facilitating subsequent information processing.

[0070] It should be noted that acoustic events contain different acoustic information, and the importance of this information also varies. Therefore, in processing acoustic events, one can select an acoustic event to process based on its importance, or process multiple acoustic events within the same time period (e.g., the most recent minute) according to their priority. For example, if multiple acoustic events were generated in the surrounding environment within the last 30 seconds, the acoustic event that needs to be processed can be determined according to its different importance or priority.

[0071] To determine the acoustic event to be prioritized, it is necessary to determine the priority number corresponding to each acoustic event. Specifically, in this embodiment, after obtaining the sound signal, the weight coefficient of the corresponding acoustic event and the volume level of the acoustic signal can be determined based on the acoustic signal. This allows the priority order of the relevant acoustic events to be determined based on the weight coefficient and volume level, and the acoustic events that need to be prioritized can then be determined based on the priority order of each acoustic event.

[0072] In some implementations, in order to determine the weight coefficients of acoustic events and the volume levels corresponding to acoustic signals, step 102, "determining the weight coefficients corresponding to acoustic events based on sound signals," may include: analyzing and processing the sound signals to obtain sound signal spectrum information; determining the event category of the acoustic event based on the sound signal spectrum information; and determining the weight coefficients corresponding to the event category based on a preset acoustic event weight list.

[0073] The audio signal spectrum information can be the spectrum information of sounds related to an acoustic event, which corresponds to / matches the category or attribute of the acoustic event. Specifically, since different acoustic events have different data such as sound quality, timbre, and voiceprint, the corresponding audio signal spectrum information is also different. Therefore, the event category or attribute of the relevant acoustic event can be determined by analyzing the audio signal spectrum information.

[0074] The preset acoustic event weight list can be a list containing weight coefficients corresponding to multiple categories of acoustic events, that is, it includes the mapping relationship between event categories and weight coefficients. Specifically, for different types of acoustic events, a weight value for the acoustic event can be preset so that when multiple types of acoustic events occur in the same time period, the priority of each type of acoustic event can be determined by weighting according to the weight coefficients; for example, a weight coefficient can be set for the acoustic event of a traffic police whistle, a weight coefficient can be set for the acoustic event of a vehicle horn, a weight coefficient can be set for the acoustic event of a certain animal sound, and so on, so as to establish a preset acoustic event weight list based on the above weight coefficients; the above is just an example, and the weight coefficient settings for other acoustic events can also be included, which will not be elaborated here.

[0075] Specifically, to determine the weight coefficient corresponding to each acoustic event, after obtaining the sound signal corresponding to the acoustic event, spectral data analysis can be performed on the acoustic signal to obtain the sound signal spectrum information. Then, this sound signal spectrum information is matched with spectrum information in a preset sound signal spectrum information database, which contains the mapping relationship between spectrum information and acoustic event categories. The event category of the acoustic event is determined based on the matching result. Finally, based on the determined event category, a preset acoustic event weight list is searched to determine the weight coefficient corresponding to the acoustic event. In this way, the weight coefficient corresponding to each acoustic event can be determined, so that it can be used in subsequent priority calculations of the acoustic event to determine the priority order of the acoustic events.

[0076] Using the above methods, the weighting coefficient and volume of the corresponding acoustic event can be determined based on the obtained acoustic signal, so that subsequent learners can determine the priority of the acoustic event based on the weighting coefficient and volume.

[0077] 103. Determine the weight priority of acoustic events based on the weight coefficient and volume value, and select the acoustic events to be processed first according to the weight priority.

[0078] The priority acoustic event can be any acoustic event that requires priority information processing at the current moment. For example, among acoustic events occurring in the same time period, such as traffic police whistles, vehicle horns, pet barks, and shop loudspeakers, if the traffic police whistle event has the highest priority, then the traffic police whistle event will be the priority acoustic event for processing.

[0079] In some implementations, to determine the priority of acoustic events at the current moment, it is necessary to first calculate the priority order of the acoustic events. Specifically, step 103, "determining the weight priority order of acoustic events based on weight coefficients and volume values," may include: performing weighted processing based on weight coefficients and volume values ​​to obtain weight priority values; obtaining a second weight priority value for a second acoustic event within a preset time period, where the second acoustic event is an acoustic event to be processed other than the first acoustic event; and determining the weight priority order corresponding to the acoustic events based on the weight priority value and the second weight priority value.

[0080] Specifically, for an acoustic event, a weighted calculation can be performed on the weight coefficient and volume value corresponding to the acoustic event to obtain the weight priority value corresponding to the acoustic event. Furthermore, a second weight priority value for other acoustic events within a preset time period (e.g., the most recent 30 seconds) is calculated in the same way. Then, based on the magnitude of the first and second weight priority values, the acoustic event is sorted from largest to smallest among the two acoustic events, thereby determining the weight priority order for each acoustic event.

[0081] Furthermore, after determining the weight priority order corresponding to each acoustic event, the acoustic event with the highest ranking (i.e., the acoustic event with the highest weight priority value) can be selected from the event sequence as the priority acoustic event to be processed at the current moment.

[0082] By using the above method, the weight priority order of each acoustic event within a preset time period can be determined. Based on the priority order of each event, the priority acoustic event to be processed at the current moment can be determined so that information processing can be performed on the priority acoustic event and information prompts can be provided to relevant users, which is reliable.

[0083] 104. Obtain the target image corresponding to the priority acoustic event, and perform image information analysis on the target image to obtain the target event information corresponding to the priority acoustic event.

[0084] The target image can be an image containing visual information of the subject that generated the priority acoustic event. For example, for an acoustic event of a traffic police whistle, the corresponding image can include the traffic police's actions, gestures, posture, direction, etc.; similarly, for an acoustic event of a vehicle horn, the corresponding image can include image information such as the vehicle's position, direction, and flashing lights.

[0085] In this embodiment of the application, after determining the priority acoustic event, the main process involves processing information based on the environmental factors and / or the scene and people involved, so as to provide information prompts to the user based on the processing results. Specifically, to obtain the priority acoustic event, an image corresponding to the event can be captured, and the environmental factors and / or scene and people involved can be determined based on the image information.

[0086] Specifically, when capturing the image corresponding to the priority acoustic event, a visual sensor (such as a camera, infrared sensor, etc.) can be used to capture the target image corresponding to the priority acoustic event. It should be noted that the location and direction of the acoustic event are uncertain relative to the local terminal, but can be determined based on the sound signal corresponding to the acoustic event. Specifically, this can be done by: determining the target acoustic signal of the priority acoustic event, identifying the identifier of the acoustic sensor that acquires the target acoustic signal, querying the layout position information of the acoustic sensor identifier relative to the local terminal, determining the identifier of the target visual sensor corresponding to the layout position information, generating an image capturing command based on the layout position information and the target visual sensor identifier, and then activating the target visual sensor to capture image information according to the image capturing command to obtain the target image information.

[0087] In order to process information about acoustic events, embodiments of this application can obtain environmental information related to the priority acoustic event. Specifically, the target image of the priority acoustic event can be obtained through a visual sensor, and then the acquired target image can be processed.

[0088] In some implementations, information processing is performed on the target image of the priority acoustic event, mainly involving extracting information elements from the target image and determining, based on the extracted information, the information that needs to be prompted to the user for the priority acoustic event, i.e., the target event information. Specifically, step 104, "performing image information analysis on the target image to obtain the target event information corresponding to the priority acoustic event," may include:

[0089] (104.1) Determine the event categories for priority handling of acoustic events;

[0090] (104.2) Image information elements are obtained by using a target recognition model to identify image information based on event categories and target images. The target recognition model is obtained by iterative training of sample images, sample event categories and sample image information elements.

[0091] (104.3) Based on the image information elements, determine the target event information corresponding to the acoustic event to be processed first.

[0092] The event category can be an information category of acoustic events, such as vehicle acoustic events, human acoustic events, animal acoustic events, plant acoustic events, geographic acoustic events, etc. This event category is used to indicate the target event elements to be extracted from the target image. For example, for the vehicle acoustic event category, information elements related to the target vehicle are extracted from the acquired target image; similarly, for the human acoustic event category, information elements related to the target person are extracted from the target image corresponding to that category, and so on. It should be noted that since the acquired target image of an event category may contain a considerable amount of information, such as people, vehicles, mountains, trees, and roads, this event category allows for more targeted extraction of event elements from the target image, reducing data computation, improving information processing efficiency, and accelerating the information prompting process.

[0093] To extract target event elements corresponding to prioritized acoustic events from a target image, this embodiment first determines the event category corresponding to the prioritized acoustic event. The specific process for determining the event category is as follows: spectral data analysis is performed on the acoustic signal of the prioritized acoustic event to obtain sound signal spectrum information. Then, this sound signal spectrum information is matched with spectrum information in a preset sound signal spectrum information database. Based on the matching result, the event category of the acoustic event is determined. Next, the event category of the prioritized acoustic event and the target image are input into a trained target recognition model. The target recognition model then extracts the information elements corresponding to the prioritized acoustic event from the target image based on the event category, obtaining the image information elements corresponding to the prioritized acoustic event. Finally, the target event information corresponding to the prioritized acoustic event is determined based on these image information elements, so that information prompts can be issued to the target user subsequently based on the target event information.

[0094] This application embodiment involves extracting image information elements from a target image using a target recognition model. Before extracting image information elements, model training is required. Specifically, a sample image, the corresponding sample event category, and sample image information elements are obtained. The sample image and sample event category are input into a preset recognition model, such as a Convolutional Neural Network (CNN) model or a model obtained by combining it with other neural networks, to output predicted image information elements. The information loss value between the predicted image information elements and the sample image information elements is determined, and the network parameters of the preset recognition model are adjusted according to the information loss value using the backpropagation gradient algorithm. The adjusted preset recognition model is then iteratively trained until iterative convergence, resulting in a trained target recognition model for subsequent extraction of image information elements from the target image.

[0095] In some implementations, step (104.2) "to identify image information based on event category and target image using target recognition model to obtain image information elements" may include: extracting features from target image based on event category using target recognition model to obtain target image features; identifying key point features of target image features to obtain multiple key point features; and determining image information elements based on multiple key point features.

[0096] The key point feature can be a key feature of related objects in the image, conveying relevant information corresponding to the priority acoustic event. Specifically, after extracting the target image features corresponding to the event category, key point features can be further identified, labeled, and extracted from the target image features to subsequently determine image information elements based on these key point features. For example, taking the human acoustic event category as an example, the key point feature can be the body posture key point features in the target image features (human image features), such as key point features of fingers, arms, legs, torso, head, eyes, face, and mouth. Furthermore, taking the vehicle acoustic event category as an example, the key point feature can be the vehicle status information features in the target image features (vehicle image features), such as license plate, wheel steering, current location, headlights (including turn signals), and other key point features.

[0097] Specifically, when extracting information elements from a target image using a target recognition model, the model primarily extracts relevant image features based on event categories to obtain image features related to the prioritized acoustic event. For example, for a person acoustic event category, corresponding person image features are extracted from the target image, down to a specific person, such as the image features of a traffic police officer. Then, key point feature recognition and / or labeling are performed on the extracted target image features to determine key point features, such as identifying key point features like fingers, arms, legs, torso, head, eyes, face, and mouth in the traffic police officer image. Finally, the extracted key point features are combined to obtain image information elements that reflect the image information corresponding to the prioritized acoustic event. For example, by combining key point features corresponding to the traffic police officer image, image information elements representing the traffic police officer's gestures and commands can be obtained.

[0098] In some implementations, step (104.3), "determining the target event information corresponding to the acoustic event to be prioritized for processing based on image information elements," may include:

[0099] (104.3.1) Determine the position coordinates of image information elements in the target image;

[0100] (104.3.2) Perform vector transformation on the position coordinates to obtain the image information element vector;

[0101] (104.3.3) Based on the image information element vector, determine the target event information corresponding to the acoustic event to be processed first.

[0102] The image information element vector is used to describe the vector between corresponding key point features, specifically representing the direction of the vector between two key point features. For example, taking the torso, arm, and fingers as key point features, a vector is constructed from the torso (specifically, the connection point with the arm, such as the shoulder) to the arm. Similarly, a vector is constructed from the arm to the fingers.

[0103] Specifically, in order to determine the target event information corresponding to the acoustic event to be prioritized, this embodiment of the application, after obtaining the image information elements, can first establish a Cartesian coordinate system for the bottom or middle of the object in the target image. Taking a person image as an example, a Cartesian coordinate system can be established with the person's feet as the center point of the two-dimensional Cartesian coordinate system, or a Cartesian coordinate system (xoy) can be established with the person's waist (middle). Thus, after the establishment of the Cartesian coordinate system, the position coordinate information of the image information elements in the target image can be determined, such as the coordinates of the arm, the leg, the head, etc. Furthermore, vector transformation processing is performed based on multiple position coordinates to obtain the image information element vectors between adjacent key points, such as the element vector from the torso to the left arm, the element vector from the left arm to the left finger, the element vector from the torso to the right arm, the element vector from the right arm to the right finger, etc. Finally, based on the image information element vectors determined above, information related to the priority acoustic events is identified, thereby obtaining the target event information corresponding to the priority acoustic events. For example, taking the image element event of traffic police as an example, the traffic police's gestures and command information are determined through the traffic police's element vectors to obtain the target event information.

[0104] In some implementations, taking the category of human acoustic events as an example, the target event information for priority processing of acoustic events is determined based on the relevant element vectors of the human figure. Specifically, the image information element vector includes the body posture information element vector of the target object. Step (104.3.3) "determining the target event information corresponding to the priority processing acoustic event based on the image information element vector" may include: constructing a Cartesian coordinate system for the target object in the target image; determining the vector direction corresponding to the body posture information element vector, and determining the quadrant characteristic relationship of the body posture information element in the Cartesian coordinate system based on the vector direction; searching for the object posture information corresponding to the quadrant characteristic relationship from a preset quadrant information list, and determining the object posture information as the target event information corresponding to the priority processing acoustic event.

[0105] The vector direction corresponding to this body posture information element vector is used to describe the direction of the relevant key point feature vectors. Specifically, it can represent the direction of the vector between two key point features. Taking the torso (specifically, the connection point with the arm, such as the shoulder) as the starting point, the direction of the vector from the torso to the arm is constructed. Similarly, taking the arm as the starting point, the direction of the vector from the arm to the fingers is constructed.

[0106] The quadrant characteristic relationship can be the quadrant position and direction of a certain image information element vector in the Cartesian coordinate system. For example, the direction of the image information element vector in the first quadrant. Taking the element vector from the torso to the left arm as an example, if the arm and fingers of the target object are at a 45° angle to the torso, the quadrant characteristic relationship of the image information element vector can be that it points from the vertical coordinate axis (y) to the horizontal coordinate system (x) in the first quadrant, and its vector direction is at a 45° angle to the vertical coordinate axis (y). The above is only a partial example, and it can also include element vectors such as from the wrist to the palm, from the palm to the fingers, and between fingers.

[0107] The preset quadrant information list can contain mapping relationships between various postures and quadrant characteristics. For example, the waving gesture, the stop gesture, the right-leaning gesture, the extended gesture, etc., all have different quadrant characteristic relationships.

[0108] Specifically, in order to determine the target event information corresponding to the priority acoustic event, the vector direction corresponding to the body posture information element vector can be determined, and the quadrant characteristic relationship of various body posture information elements in the rectangular coordinate system can be determined according to the vector direction; the object posture information corresponding to the quadrant characteristic relationship can be found from the preset quadrant information list, and the object posture information can be determined as the information that needs to be prompted to the target object for the priority acoustic event, that is, the target event information, such as one or more command event information such as the waving posture, stop gesture posture, and right-hand gesture posture of a traffic policeman.

[0109] In some implementations, taking vehicle acoustic events outside the local terminal as an example, the target event information for priority processing of acoustic events is determined based on the relevant element vectors obtained from the vehicle image. Specifically, the image information element vector includes the vehicle information element vector of the target vehicle. Step (104.3.3) "determining the target event information corresponding to the priority acoustic event based on the image information element vector" may include: obtaining the current local location information of the local terminal and constructing a Cartesian coordinate system based on the local location information; determining the target quadrant characteristic relationship of the target vehicle in the Cartesian coordinate system based on the vehicle information element vector; evaluating the vehicle distance information between the target vehicle and the local terminal based on the vehicle information element vector and the local location information, and determining the vehicle distance information as the target event information corresponding to the priority acoustic event.

[0110] The quadrant characteristic relationship can be the quadrant position and direction of a certain image information element vector in the rectangular coordinate system, such as the direction of the image information element vector in the first quadrant, the direction in the third quadrant, the direction in the fourth quadrant, etc. Taking vehicle element vectors as an example, a Cartesian coordinate system (xoy) is established with the local terminal or the current location of the local terminal (local location) as the center point o. The image information element vectors of the target vehicle image corresponding to the acoustic event to be processed first are obtained. This vector can be the vector from the rear of the target vehicle to the front of the vehicle, the left turn signal vector, the right turn signal vector, etc. For example, the vector from the rear of the vehicle to the front of the vehicle is located in the fourth quadrant of the Cartesian coordinate system, and the specific vector direction (the direction of the vector from the rear of the vehicle to the front of the vehicle) is tilted towards the vertical (y) coordinate axis of the Cartesian coordinate system. For another example, the vector from the rear of the vehicle to the front of the vehicle is located in the third quadrant of the Cartesian coordinate system, and the specific vector direction (the direction of the vector from the rear of the vehicle to the front of the vehicle) is tilted towards the vertical (y) coordinate axis of the Cartesian coordinate system. The above are just examples, and other quadrant situations can also be included, depending on the actual situation when the vehicle is driving. They will not be elaborated here.

[0111] Specifically, in order to determine the target event information corresponding to the priority acoustic event of the vehicle, a Cartesian coordinate system corresponding to the current local location information of the local terminal can be constructed; based on the vehicle information element vector, the target quadrant characteristic relationship of the target vehicle in the Cartesian coordinate system can be determined; based on the vehicle information element vector and the local location information, the vehicle distance information between the target vehicle and the local terminal can be evaluated, and the vehicle distance information can be determined as the target event information corresponding to the priority acoustic event. For example, based on the vehicle information element vector, if the quadrant characteristic relationship of the target vehicle is determined to be in the fourth quadrant of the rectangular coordinate system, and the specific vector direction (the vector direction from the rear of the vehicle to the front of the vehicle) is tilted towards the vertical (y) coordinate axis in the rectangular coordinate system, then the target vehicle is located to the right rear of the local vehicle (or local terminal). The purpose of its acoustic event (such as the horn sounding event) is to inform the local vehicle that it is turning left to change lanes. In addition, the local location information belongs to the position information of the local vehicle while it is moving, and its corresponding coordinates (or vectors) are (0,0). The difference between the target vehicle's vehicle information element vector and the local location information vector is calculated. Then, based on the difference result and the relevant distance ratio algorithm of the electronic map, the vehicle distance information between the target vehicle and the local terminal is evaluated. Thus, the vehicle distance information, the target vehicle's turning information, and the target vehicle's driving information are individually or jointly treated as the target event information corresponding to the acoustic event for priority processing.

[0112] Using the above methods, we can extract the corresponding target event information for priority acoustic events, so as to provide prompts based on the target event information in the future, which is reliable.

[0113] 105. Provide information prompts based on the target event information.

[0114] Specifically, in order to provide relevant acoustic event information prompts to target users, this embodiment of the application, after obtaining the target event information corresponding to the priority acoustic event, prompts the target event information through a local terminal. For example, the target event information can be prompted through voice, image, video, or other broadcast methods.

[0115] By implementing any one or a combination of implementation methods in the embodiments of this application, vehicle driving information prompts, aviation information prompts, military vehicle driving information prompts, etc., can be realized. To facilitate understanding of the application scenarios, the application scenario of vehicle driving information prompts is taken as an example. This application scenario is not limited to acoustic events including traffic police whistles, vehicle horn sounds, etc.; a specific example of this scenario is as follows:

[0116] The vehicle at the local terminal can be equipped with visual sensors in various directions (such as front, rear, left, and right), such as cameras, infrared sensors, and radar. In addition, acoustic sensors, such as microphones, are installed at the same or adjacent positions as the visual sensors to accurately collect acoustic events (such as vehicle horns, traffic police whistles, etc.) from various directions. It should be noted that since multiple acoustic events may exist at the same time, and an acoustic event may be collected by multiple acoustic sensors or a single corresponding acoustic sensor, it is necessary to analyze each acoustic event.

[0117] Specifically, after each acoustic sensor detects an acoustic event, the vehicle's onboard terminal prioritizes and assigns weights to the detected events. For example, a traffic police whistle has the highest priority and is assigned a weight coefficient 'a', followed by a vehicle horn and assigned a weight coefficient 'b', and so on. Then, the weights are calculated based on the volume of the detected acoustic events. For example, if the volume of a traffic police whistle is 'x' and the volume of a vehicle horn is 'y', then the weight of the traffic police whistle is 'a*x', and the weight of the vehicle horn is 'b*y', and so on. Finally, all acoustic events are ranked according to their weights, and the top N (e.g., one or two) target acoustic events are further analyzed to save computational resources.

[0118] Specifically, the analysis process is as follows: For the top-ranked target acoustic events, the corresponding visual sensors are activated to acquire target images. For example, if a traffic police whistle is detected, an image of the traffic police officer is acquired; if a horn is detected, an image of the vehicle honking is extracted. After image extraction, further analysis is performed. For example, the traffic police officer's hand gestures are analyzed based on the traffic police image, and the distance and trajectory of adjacent vehicles are analyzed based on the vehicle images. Information from all directions is summarized and analyzed to extract information to be prompted to the driver of this vehicle. Finally, the driver is prompted via image or voice. For example, if a traffic police whistle is detected, the driver is prompted to stop / turn / move after analyzing the hand gestures; if a horn is detected, the driver is prompted to overtake / avoid sudden braking after analyzing the distance and trajectory.

[0119] As described above, this application embodiment can collect sound signals corresponding to acoustic events; determine the weight coefficients corresponding to acoustic events based on the sound signals, and determine the volume value of the sound signal corresponding to each acoustic event; determine the weight priority order of acoustic events based on the weight coefficients and volume values, and select the acoustic events to be processed first based on the weight priority order; acquire the target image corresponding to the acoustic event to be processed first, and perform image information analysis on the target image to obtain the target event information corresponding to the acoustic event to be processed first; and provide information prompts based on the target event information. Therefore, this solution can determine the weight coefficients of acoustic events based on the collected sound signals, and, combined with the volume of the sound signals, determine the acoustic events that relevant users need to respond to first. Furthermore, it analyzes the image information of the acoustic events that need to be responded to first to obtain the target event information, so that information prompts can be provided subsequently based on the target event information. This allows passengers to obtain important sound information about the external environment, avoids safety hazards, and improves the safety of the riding process.

[0120] To better implement the above methods, this application also provides an information prompting device that can be integrated into computer equipment, such as servers or terminals.

[0121] For example, such as Figure 3 As shown, the information prompting device may include a data acquisition unit 301, a determination unit 302, a selection unit 303, an analysis unit 304, and a prompting unit 305.

[0122] Acquisition unit 301 is used to acquire sound signals corresponding to acoustic events;

[0123] The determining unit 302 is used to determine the weighting coefficients corresponding to the acoustic events based on the sound signals, and to determine the volume value of the sound signals corresponding to each acoustic event.

[0124] Unit 303 is selected to determine the weight priority order of acoustic events based on the weight coefficient and volume value, and to select the acoustic events to be processed first based on the weight priority order.

[0125] The analysis unit 304 is used to acquire the target image corresponding to the priority acoustic event and perform image information analysis on the target image to obtain the target event information corresponding to the priority acoustic event.

[0126] The prompting unit 305 is used to provide information prompts based on the target event information.

[0127] In some embodiments, the determining unit 302 is further configured to: analyze and process the sound signal to obtain sound signal spectrum information; determine the event category of the acoustic event based on the sound signal spectrum information; and determine the weight coefficient corresponding to the event category based on a preset acoustic event weight list.

[0128] In some embodiments, the selection unit 303 is further configured to: perform weighted processing based on the weight coefficient and the volume value to obtain a weight priority value; obtain a second weight priority value of a second acoustic event within a preset time period, wherein the second acoustic event is an acoustic event to be processed other than the acoustic event; and determine the weight priority order corresponding to the acoustic event based on the weight priority value and the second weight priority value.

[0129] In some embodiments, the analysis unit 304 is further configured to: determine the event category of the acoustic event to be prioritized; perform image information recognition based on the event category and the target image using a target recognition model to obtain image information elements, wherein the target recognition model is obtained by iterative training of sample images, sample event categories and sample image information elements; and determine the target event information corresponding to the acoustic event to be prioritized based on the image information elements.

[0130] In some embodiments, the analysis unit 304 is further configured to: extract features from the target image based on the event category using a target recognition model to obtain target image features; perform key point feature recognition on the target image features to obtain multiple key point features; and determine image information elements based on the multiple key point features.

[0131] In some embodiments, the analysis unit 304 is further configured to: determine the position coordinates of image information elements in the target image; perform vector transformation processing on the position coordinates to obtain an image information element vector; and determine the target event information corresponding to the acoustic event to be processed first based on the image information element vector.

[0132] In some embodiments, the image information element vector includes the body posture information element vector of the target object. The analysis unit 304 is further configured to: construct a Cartesian coordinate system for the target object in the target image; determine the vector direction corresponding to the body posture information element vector, and determine the quadrant characteristic relationship of the body posture information element in the Cartesian coordinate system based on the vector direction; search for the object posture information corresponding to the quadrant characteristic relationship from the preset quadrant information list, and determine the object posture information as the target event information corresponding to the acoustic event to be processed first.

[0133] In some embodiments, the image information element vector includes the vehicle information element vector of the target vehicle. The analysis unit 304 is further configured to: obtain the current local location information of the local terminal and construct a Cartesian coordinate system based on the local location information; determine the target quadrant characteristic relationship of the target vehicle in the Cartesian coordinate system according to the vehicle information element vector; evaluate the vehicle distance information between the target vehicle and the local terminal according to the vehicle information element vector and the local location information, and determine the vehicle distance information as the target event information corresponding to the acoustic event to be processed first.

[0134] As described above, this embodiment of the application acquires sound signals corresponding to acoustic events through the acquisition unit 301; determines the weight coefficients corresponding to the acoustic events based on the sound signals through the determination unit 302, and determines the volume value of the sound signals corresponding to each acoustic event; determines the weight priority order of acoustic events based on the weight coefficients and volume values ​​through the selection unit 303, and selects the acoustic events to be processed first based on the weight priority order; acquires the target image corresponding to the acoustic events to be processed first through the analysis unit 304, and performs image information analysis on the target image to obtain the target event information corresponding to the acoustic events to be processed first; and provides information prompts based on the target event information through the prompting unit 305. Therefore, this solution can determine the weight coefficients of acoustic events based on the acquired sound signals, and determine the acoustic events that relevant users need to respond to first based on the volume of the sound signals. Furthermore, it analyzes the image information of the acoustic events that need to be responded to first to obtain the target event information, so that information prompts can be provided subsequently based on the target event information. This allows passengers to obtain important sound information about the external environment, avoids safety hazards, and improves the safety of the riding process.

[0135] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0136] This application also provides a computer device, such as... Figure 4 As shown, it illustrates a structural schematic diagram of the computer device involved in the embodiments of this application, specifically:

[0137] The computer device may include components such as a processor 401 with one or more processing cores, a memory 402 with one or more computer-readable storage media, a power supply 403, and an input unit 404. Those skilled in the art will understand that... Figure 4 The computer device structure shown does not constitute a limitation on the computer device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0138] The processor 401 is the control center of the computer device. It connects various parts of the computer device via various interfaces and lines, and performs various functions and processes data by running or executing software programs and / or modules stored in the memory 402, and by calling data stored in the memory 402, thereby providing overall monitoring of the computer device. Optionally, the processor 401 may include one or more processing cores; preferably, the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 401.

[0139] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and information prompts by running the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

[0140] The computer device also includes a power supply 403 that supplies power to the various components. Preferably, the power supply 403 can be logically connected to the processor 401 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 403 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0141] The computer device may also include an input unit 404, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0142] Although not shown, the computer device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 401 in the computer device loads the executable files corresponding to the processes of one or more applications into the memory 402 according to the following instructions, and the processor 401 runs the applications stored in the memory 402 to realize various functions, as follows:

[0143] Acquire sound signals corresponding to acoustic events; determine weight coefficients for each acoustic event based on the sound signals, and determine the volume value of the sound signal for each acoustic event; determine the weight priority order of acoustic events based on the weight coefficients and volume values, and select the acoustic events to be processed first based on the weight priority order; acquire the target images corresponding to the acoustic events to be processed first, and perform image information analysis on the target images to obtain the target event information corresponding to the acoustic events to be processed first; provide information prompts based on the target event information.

[0144] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0145] As can be seen from the above, the embodiments of this application can determine the weight coefficient of acoustic events based on the collected sound signals, and determine the acoustic events that relevant users need to respond to first based on the volume of the sound signals. Then, the image information of the acoustic events that need to be responded to first is analyzed to obtain target event information, so as to provide information prompts based on the target event information. In this way, passengers can obtain important sound information of the external environment, avoid safety hazards, and improve the safety of the riding process.

[0146] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0147] Therefore, embodiments of this application provide a computer-readable storage medium storing a plurality of instructions that can be loaded by a processor to execute steps in any of the information prompting methods provided in embodiments of this application. For example, the instructions can execute the following steps:

[0148] Acquire sound signals corresponding to acoustic events; determine weight coefficients for each acoustic event based on the sound signals, and determine the volume value of the sound signal for each acoustic event; determine the weight priority order of acoustic events based on the weight coefficients and volume values, and select the acoustic events to be processed first based on the weight priority order; acquire the target images corresponding to the acoustic events to be processed first, and perform image information analysis on the target images to obtain the target event information corresponding to the acoustic events to be processed first; provide information prompts based on the target event information.

[0149] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0150] The computer-readable storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0151] This application also provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the information prompting methods provided in the various optional implementations of the above embodiments.

[0152] Since the instructions stored in the computer-readable storage medium can execute the steps in any of the information prompting methods provided in the embodiments of this application, the beneficial effects that any of the information prompting methods provided in the embodiments of this application can achieve can be realized. For details, please refer to the previous embodiments, which will not be repeated here.

[0153] The above provides a detailed description of an information prompting method, apparatus, and computer-readable storage medium provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. An information presentation method characterized by comprising: The method comprises the following steps: collecting sound signals corresponding to acoustic events; determining weight coefficients corresponding to the acoustic events according to the sound signals, and determining volume values of the sound signals corresponding to each acoustic event; determining a weight priority of the acoustic events according to the weight coefficients and the volume values, and selecting a priority processing acoustic event according to the weight priority; obtaining a target image corresponding to the priority processing acoustic event, and performing image information analysis on the target image to obtain target event information corresponding to the priority processing acoustic event; when the target image corresponding to the priority processing acoustic event is obtained, a target acoustic signal of the priority processing acoustic event is determined, an identifier of an acoustic sensor collecting the target acoustic signal is determined, layout position information of the identifier of the acoustic sensor is queried, a target visual sensor identifier corresponding to the layout position information is determined, an image shooting instruction is generated according to the layout position information and the target visual sensor identifier, and the target visual sensor is started to shoot image information according to the image shooting instruction, so as to obtain the target image information; performing information prompting according to the target event information.

2. The method of claim 1, wherein, The method comprises the following steps: analyzing and processing the sound signals to obtain sound signal spectrum information; determining an event category of the acoustic event according to the sound signal spectrum information; determining a weight coefficient corresponding to the event category according to a preset acoustic event weight list.

3. The method of claim 1, wherein, The method comprises the following steps: performing weighted processing on the weight coefficients and the volume values to obtain a weight priority value; obtaining a second weight priority value of a second acoustic event in a preset time period, the second acoustic event being a to-be-processed acoustic event other than the acoustic event; determining a weight priority order corresponding to the acoustic event according to the weight priority value and the second weight priority value.

4. The method of claim 1, wherein, The method comprises the following steps: determining an event category of the priority processing acoustic event; performing image information recognition based on the event category and the target image through a target recognition model to obtain an image information element, wherein the target recognition model is obtained by iteratively training a sample image, a sample event category, and a sample image information element; determining target event information corresponding to the priority processing acoustic event according to the image information element.

5. The method of claim 4, wherein, The method comprises the following steps: extracting features of the target image based on the event category through a target recognition model to obtain target image features; performing key point feature recognition on the target image features to obtain a plurality of key point features; determining an image information element based on the plurality of key point features.

6. The method of claim 4, wherein, The method comprises the following steps: determining a position coordinate of the image information element in the target image; Conduct vector conversion processing on the position coordinates to obtain an image information element vector; Determine target event information corresponding to the priority processing acoustic event according to the image information element vector.

7. The method of claim 6, wherein, The image information element vector includes a body state information element vector of a target object, and the determination of the target event information corresponding to the priority processing acoustic event according to the image information element includes: Constructing a rectangular coordinate system for a target object in the target image; Determining a vector direction corresponding to the body state information element vector, and determining a quadrant characteristic relationship of the body state information element in the rectangular coordinate system according to the vector direction; Searching for object posture information corresponding to the quadrant characteristic relationship from a preset quadrant information list, and determining the object posture information as the target event information corresponding to the priority processing acoustic event.

8. The method of claim 6, wherein, The image information element vector includes a vehicle information element vector of a target vehicle, and the determination of the target event information corresponding to the priority processing acoustic event according to the image information element includes: Obtaining local position information of a local terminal at present, and constructing a rectangular coordinate system based on the local position information; Determining a target quadrant characteristic relationship of the target vehicle in the rectangular coordinate system according to the vehicle information element vector; Evaluating vehicle distance information between the target vehicle and the local terminal according to the vehicle information element vector and the local position information, and determining the vehicle distance information as the target event information corresponding to the priority processing acoustic event.

9. An information presentation device, characterized by comprising: The method includes: The acquisition unit is configured to acquire a sound signal corresponding to an acoustic event; The determination unit is configured to determine a weight coefficient corresponding to the acoustic event according to the sound signal, and determine a volume value of the sound signal corresponding to each acoustic event; The selection unit is configured to determine a weight priority order of the acoustic events according to the weight coefficient and the volume value, and select a priority processing acoustic event according to the weight priority order; The analysis unit is configured to acquire a target image corresponding to the priority processing acoustic event, and perform image information analysis on the target image to obtain target event information corresponding to the priority processing acoustic event. The prompt unit is configured to perform information prompting according to the target event information.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium is computer readable and stores a plurality of instructions, and the instructions are suitable for being loaded by the processor to execute the steps in the information prompting method of any one of claims 1 to 8. The computer readable storage medium is computer readable and stores a plurality of instructions, and the instructions are suitable for being loaded by the processor to execute the steps in the information prompting method of any one of claims 1 to 8.

Images