Intelligent interaction method, apparatus, device, and storage medium

Abstract

The present disclosure provides a method, device, equipment and storage medium for intelligent interaction, relates to the technical field of computers, in particular to the fields of artificial intelligence, intelligent transportation, voice technology and the like. The specific implementation scheme is: obtaining corresponding traffic information according to the detected interaction demand; generating interaction content according to the interaction demand and the filtering result of the traffic information; and generating driving parameters based on the interaction content, the driving parameters including parameters for driving a digital person in an interaction interface to broadcast the interaction content. The present disclosure can enable a terminal with an intelligent interaction function, such as a car machine, to actively identify interaction demands and then determine different interaction demands. The terminal with the intelligent interaction function can determine traffic information according to the interaction demand, thereby providing help for the driver from different dimensions.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to artificial intelligence, intelligent transportation, voice technology, etc., and especially to a method, apparatus, device and storage medium for intelligent interaction. Background Technology

[0002] With the continuous development of ground transportation, driving has become a common mode of travel for many people. Most drivers rely on navigation while driving. However, traditional navigation systems offer relatively limited information and cannot meet users' needs. Summary of the Invention

[0003] This disclosure provides a method, apparatus, device, and storage medium for intelligent interaction.

[0004] According to one aspect of this disclosure, a method for intelligent interaction is provided, which may include the following steps:

[0005] Based on the detected interaction requests, obtain the corresponding traffic information;

[0006] Generate interactive content based on interaction needs and the results of filtering traffic information;

[0007] Based on the interactive content, driving parameters are generated, including parameters used to drive the digital human in the interactive interface to broadcast the interactive content.

[0008] According to another aspect of this disclosure, an intelligent interaction device is provided, which may include:

[0009] The traffic information acquisition module is used to acquire corresponding traffic information based on the detected interaction requests;

[0010] The interactive content generation module is used to generate interactive content based on interactive requirements and the filtering results of traffic information;

[0011] The digital human driving module is used to generate driving parameters based on interactive content. The driving parameters include parameters used to drive the digital human in the interactive interface to broadcast interactive content.

[0012] According to another aspect of this disclosure, an electronic device is provided, comprising:

[0013] At least one processor; and

[0014] The memory is communicatively connected to the at least one processor; wherein,

[0015] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the methods in any embodiment of this disclosure.

[0016] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions for causing a computer to perform the methods of any embodiment of this disclosure.

[0017] According to another aspect of this disclosure, a computer program product is provided, including a computer program / instructions that, when executed by a processor, implement the methods in any embodiment of this disclosure.

[0018] The technology disclosed herein enables terminals with intelligent interactive functions, such as in-vehicle infotainment systems, to proactively identify and determine different interactive needs. These terminals can then determine traffic information based on the interactive needs, thereby providing assistance to drivers from various perspectives.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0020] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0021] Figure 1 This is a flowchart of the intelligent interaction method according to this disclosure;

[0022] Figure 2 This is one of the schematic diagrams of the interactive interface according to this disclosure;

[0023] Figure 3 This is a flowchart of obtaining traffic information based on this disclosure;

[0024] Figure 4 This is one of the flowcharts for generating interactive content based on this disclosure;

[0025] Figure 5 This is based on the second schematic diagram of the interactive interface disclosed herein;

[0026] Figure 6 This is a flowchart illustrating how navigation requirements are confirmed in accordance with this disclosure;

[0027] Figure 7 This is the second flowchart for generating interactive content based on this disclosure;

[0028] Figure 8 This is based on diagram three of the interactive interfaces disclosed herein;

[0029] Figure 9 This is flowchart number three of the flowcharts for generating interactive content based on this disclosure;

[0030] Figure 10 This is based on diagram four of the interactive interfaces disclosed herein;

[0031] Figure 11 This is one of the flowcharts for determining the recommendation requirements for points of interest based on this disclosure;

[0032] Figure 12 This is the second flowchart for determining the recommendation requirements based on this disclosure;

[0033] Figure 13 A method scenario diagram illustrating the intelligent interaction that can be implemented in the embodiments of this disclosure;

[0034] Figure 14 This is a schematic diagram of an intelligent interaction device according to the present disclosure;

[0035] Figure 15 This is a block diagram of an electronic device used to implement the interactive method of the embodiments of this disclosure. Detailed Implementation

[0036] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0037] like Figure 1 As shown, this disclosure relates to a method for intelligent interaction, which may include the following steps:

[0038] S101: Obtain the corresponding traffic information based on the detected interaction requests;

[0039] S102: Generate interactive content based on interaction requirements and the results of filtering traffic information;

[0040] S103: Based on the interactive content, generate driving parameters, including parameters used to drive the digital human in the interactive interface to broadcast interactive content.

[0041] The implementing entity of this disclosure can be an in-vehicle infotainment system of a vehicle with autonomous or assisted driving functions, or a cloud server communicating with the in-vehicle infotainment system. The interaction requirements can be determined by analyzing data detected by the vehicle's sensors. For example, sensors can include image acquisition devices and sound acquisition devices inside the vehicle. Additionally, sensors can also include external image sensors and sensors from different components of the vehicle.

[0042] For example, consider a vehicle carrying only the driver. Interaction requests can be triggered by the driver. For instance, if a sound acquisition device detects a trigger command from the driver, an interaction request can be determined. Alternatively, interaction requests can be triggered by detecting the driver's behavior. For example, by analyzing the content collected by image and sound acquisition devices, it can be determined that the driver is fatigued, hungry, or irritable. Based on this, an interaction request can be determined. Furthermore, interaction requests can be triggered based on the vehicle's state. For example, if the vehicle's speed is consistently below a certain speed threshold, traffic congestion can be identified, thus determining an interaction request. Another example is when a sensor on a vehicle component detects that the component is not functioning properly, also indicating an interaction request. In addition to the driver in the above examples, the interaction objects can also include other passengers.

[0043] Different traffic information can be obtained to meet different interaction needs. For driver-triggered interactions, the traffic information obtained can be determined based on the driver's interaction content. For example, if the driver's interaction content is "Let's chat," then the corresponding traffic information could be the road conditions of the remaining road segments. Based on this, traffic information can be referenced when generating interaction content. For instance, chatting with the driver can only be supported if it is determined that the current vehicle is traveling on a relatively simple road segment.

[0044] For example, based on different situations such as driver fatigue, hunger, or impatience, points of interest can be identified and used as corresponding traffic information. For instance, for fatigue, the identified points of interest could be hotels or service areas. For hunger, the identified points of interest could be restaurants. For impatience, the processing method could be the same as when the driver's interaction content is "chat with me."

[0045] For example, for interaction requests where the detected vehicle speed is below a certain threshold, the corresponding traffic information obtained could be such as querying alternative routes. For interaction requests related to vehicle component malfunctions, the corresponding traffic information obtained could be such as nearby parking spots or nearby repair shops.

[0046] Filtering traffic information can include the following scenarios. For example, if the traffic information consists of multiple navigation routes with road condition information, the route with the simpler road conditions can be selected as the filter result. If the traffic information includes multiple candidate points of interest (POIs), the target POI can be selected as the filter result based on the driver's preferences or evaluations of each POI. The interactive content can be formed by embedding the filtered traffic information results into pre-defined dialogue that matches the interaction requirements. Additionally, it can also include summary information generated based on the filtered results.

[0047] Based on the interactive content, driving parameters can be generated. This drives the digital human in the interactive interface to broadcast the interactive content. The digital human can be a product of digital character technology and artificial intelligence technology. A digital human can be a virtual character with a digital appearance, existing only through a display device. A digital human can have a human-like appearance (including cartoon characters), possessing specific facial features, gender, and personality traits. Based on control commands, the digital human can output voice and actions. The interactive interface containing the digital human can be overlaid on the original screen of the vehicle's infotainment system as a semi-transparent floating layer. The interactive interface can include multiple display areas, for example, such as... Figure 2 As shown, the interactive interface may include a digital human area, an interactive content display area, and an additional content display area. The digital human area includes at least one digital human, which can use driving parameters to display facial expressions and different lip movements to correspondingly deliver interactive content. The additional content display area can be used to display supplementary content such as candidate roads and introductions to candidate points of interest. The interactive content display area can be used to display the interaction history over a certain period of time.

[0048] Through the above process, terminals with intelligent interactive functions, such as in-vehicle infotainment systems, can proactively detect interaction requests. This allows these terminals to determine traffic information based on the interaction requests, providing assistance to drivers from different perspectives.

[0049] like Figure 3 As shown, in one embodiment, the method for obtaining the interaction requirements involved in step S101 may include the following process:

[0050] S301: Parse the acquired reference information to obtain the parsing result; the reference information includes at least one of user information and current vehicle driving information, the driving information includes vehicle parameters detected by vehicle sensors; the user information includes at least one of user voice information and action information.

[0051] S302: If the parsing result meets the predetermined conditions, it is determined that an interaction requirement has been detected; the interaction requirement includes at least one of navigation requirement, companionship requirement, or point of interest recommendation requirement.

[0052] Taking the driver as an example, the reference information can be information collected with the driver's authorization. For instance, the reference information could be driver information, specifically video or image information captured by image acquisition devices. This allows the driver's actions to be determined based on the video and / or image information. Additionally, it could be the driver's voice information collected by audio equipment. Another example is the vehicle's current driving information, which could include vehicle parameters detected by vehicle sensors, such as speed, remaining fuel, tire pressure, engine parameters, transmission parameters, electric motor parameters, and battery parameters.

[0053] By parsing the acquired reference information and determining whether predetermined conditions are met, automatic detection of interaction needs can be achieved. For example, if the voice message contains explicit instructions such as "turn on interaction mode" or "chat with me," it indicates that the driver has an interaction need. Alternatively, detecting specific actions performed by the driver through video and / or image information can also indicate that predetermined conditions are met, meaning the driver has an interaction need. It's easy to understand that the aforementioned instructions and specific actions are predetermined. Therefore, the interaction need can be identified as a companionship need.

[0054] For example, if visual, video, or audio signals detect anxiety, fatigue, or hunger in the driver, it can be determined that the predetermined conditions have been met. In this case, the interaction need can be identified as either a need for companionship or a need for a point of interest recommendation. In the case of a point of interest recommendation need, the driver can select a corresponding point of interest based on their specific situation. For example, a movie theater, a restaurant, or going home.

[0055] For example, if vehicle parameters determine that the vehicle speed is 0, or that the vehicle speed is consistently below a certain threshold for an extended period, it indicates traffic congestion. This confirms that a predetermined condition has been met. Therefore, the interaction requirement can be identified as a navigation requirement, i.e., navigating to alternative routes to avoid congestion.

[0056] For example, if a vehicle malfunction is determined through vehicle parameters, it can also be determined that predetermined conditions are met. In this case, the interaction requirement can be identified as a point-of-interest (POI) recommendation requirement. A POI could be an Automotive Sales Service 4S shop, a service area, or a vehicle repair shop, etc.

[0057] Through the above process, the interaction needs for drinks can be determined based on driver information, vehicle information, and other data. This allows for the provision of more diversified services to drivers.

[0058] like Figure 4As shown, in one embodiment, when the interaction requirement includes navigation requirements, step S102 may include the following process:

[0059] S401: Based on navigation requirements, select target navigation routes from traffic information that meet specified conditions, which are determined based on at least one of the navigation route's mileage and travel time.

[0060] S402: Generate interactive content based on the target navigation path.

[0061] When interaction requirements include navigation, traffic information can be based on multiple navigation routes to the destination. The filtering result of traffic information can be the selection of the target navigation route from among these multiple routes.

[0062] The filtering method can be based on at least one of the following: mileage of the navigation route, travel time of the navigation route, and travel cost of the navigation route. Travel cost can include fuel costs, electricity costs, toll fees, etc. For example, weights can be assigned to different filtering factors. For instance, the weight of travel time is greater than the weight of mileage, and the weight of mileage is greater than the weight of travel cost. For a given target route, only the travel time and mileage of the target route can be retained.

[0063] Combination Figure 5 As shown, for the target route, the corresponding interactive content could be, "Based on the current traffic conditions, it is expected that more and more vehicles will converge on the congested section ahead. I have found a new route for you, via XXX Road, which will save you 2 minutes and cover about the same distance. Do you want to change routes?" Traditional navigation interfaces typically display navigation guidance information, toll station information, remaining mileage, remaining time, recommended routes to avoid congestion, and comparisons of route time, tolls, traffic lights, and mileage when recommending routes. For drivers who want to know if the congestion ahead is worsening and need to change routes, this information is too scattered and cannot assist in making a quick decision.

[0064] In the current implementation, relatively concise information can help drivers make quick decisions.

[0065] like Figure 6 As shown, in one implementation, the confirmation of navigation requirements may include the following process:

[0066] S601: Determine the vehicle speed within a predetermined time period based on vehicle parameters;

[0067] S602: Determine the congestion level based on vehicle speed;

[0068] S603: If the congestion level meets the pre-set congestion standard, the interaction requirement is determined to be a navigation requirement.

[0069] Navigation requests can be confirmed based on vehicle speed parameters. For example, if, during driving, the vehicle speed remains at 0 for more than a predetermined time (e.g., 10 seconds) due to reasons other than traffic lights, or if the speed exceeds the predetermined time below a corresponding first speed threshold (e.g., 5 km / h), the congestion level can be determined as "severe." Conversely, if the speed exceeds the predetermined time between the aforementioned first and second speed thresholds (e.g., 15 km / h), the congestion level can be determined as "moderate."

[0070] Based on the congestion level, navigation needs can be determined. For example, if the congestion level is higher than "moderate," the interaction need can be determined to be a navigation need.

[0071] Through the above process, navigation needs can be determined based on vehicle speed.

[0072] like Figure 7 As shown, in one embodiment, when the interaction need includes the need for companionship, step S102 may include the following process:

[0073] S701: Based on the target navigation path and corresponding road conditions in the traffic information, determine the safe driving section. The safe driving section is the section with road condition complexity lower than the corresponding complexity threshold.

[0074] S702: Determine the current travel time of the vehicle within the safe driving section;

[0075] S703: Utilizes AIGC, an AI-based content production technology, to generate interactive content that matches driving time.

[0076] When interaction needs include companionship, the target navigation route and corresponding road conditions can be obtained from traffic information. For example, in scenarios involving highway or expressway driving, an exit can be determined from the remaining road segments. If the distance to the exit exceeds a corresponding distance threshold, it indicates that no complex operation is required by the driver; that is, it corresponds to a safe driving segment with road complexity below a corresponding complexity threshold. In other words, if the distance to the exit exceeds a corresponding distance threshold, it indicates that the driver only needs to drive on the main road (highway or expressway), and therefore can be considered to have low road complexity. The travel time for a safe driving segment can be estimated based on distance and road conditions.

[0077] For example, when waiting at a red light, the remaining duration of the red light can be obtained from the road conditions. If the remaining duration is longer than a corresponding threshold, it can be considered a safe driving segment with road complexity below the corresponding threshold. That is, a longer red light means no driver intervention is required, thus the road complexity can be considered low. Therefore, the road segment corresponding to the current stopping position can be identified as a safe driving segment. Correspondingly, the red light end time can be associated with the travel time within the safe driving segment.

[0078] For example, in cases of severe traffic congestion and the absence of alternative routes, congested sections can be identified as safe driving sections with road complexity below a corresponding complexity threshold. Correspondingly, the time taken to reach the end of the traffic jam can be defined as the travel time within the safe driving section.

[0079] Based on driving time on safe driving routes, AI-generated content (AIGC) technology can be used to generate topics to facilitate interaction with drivers. Correspondingly, the topics can be current trending topics, topics determined based on driver user profiles, etc. Alternatively, they can be combined with... Figure 8 As shown, the topic can also be determined based on the questions asked by the driver. For example, asking about the outcome of a sports event. AIGC refers to the ability to automatically generate multimedia content using artificial intelligence technology. For example, it can write poems, compose music, and generate news. AIGC can generate multimedia content based on trending events on the internet, or it can generate multimedia content based on user inquiries.

[0080] During multi-round interactions with users, interaction strategies can be determined based on user profiles. User profiles can include long-term, medium-term, and short-term preferences. For example, long-term preferences may include a user's interests and profession. Medium-term preferences may be the purpose of the current trip, such as tourism or attending a conference. Short-term preferences may be the user's current emotional needs, such as their current mood and tolerance for disturbances. When generating content, priorities can be determined in that order—short-term, medium-term, and long-term—to better improve the user experience.

[0081] Through the above process, topics of interest to drivers can be generated when they require companionship, helping them pass the time during a potentially monotonous driving experience. Furthermore, this companionship can be based on road conditions, thereby maximizing driver safety.

[0082] like Figure 9 As shown, in one implementation, when the interaction requirement includes a point-of-interest recommendation requirement, step S102 may include the following process:

[0083] S901: Determine the type of interest point corresponding to the interest point recommendation requirements;

[0084] S902: Based on the type of point of interest, filter out the target point of interest from the candidate points of interest contained in the traffic information;

[0085] S903: Generate interactive content based on target points of interest.

[0086] Points of interest (POI) recommendation requests can include multiple categories. For example, detecting frequent yawning or blinking in a driver could indicate driver fatigue. Based on this, the recommended POI request could be determined to be a need for rest. Figure 10 As shown, the type of point of interest can be leisure-related, such as service areas. Correspondingly, based on the point of interest search function, information about shops included in service areas retrieved from the network can be displayed. Figure 10 In the example shown, service area information can be introduced to the user based on the gas station brands they frequently visit. Additionally, information can be tailored to the user's preferences, such as their favorite types of food and preferred restaurants.

[0087] For example, when a vehicle malfunction is detected, the type of point-of-interest (POI) recommendation can be determined based on the anomaly. For instance, if a gasoline-powered vehicle is low on fuel, a gas station can be selected as a POI type. If a new energy vehicle is low on battery power, a charging station can be selected. If certain parts of the vehicle malfunction, a dealership or repair shop can be selected as a POI type.

[0088] Based on the type of point of interest (POI), the corresponding target POI is selected from the candidate POIs included in the traffic information. For example, if the POI type is gas station, the target gas station can be selected based on the driver's preferred gas station brand. Similarly, if the POI type is hotel, the target hotel can be selected based on the hotel's reputation, reviews, and the driver's preferred hotel brand. The selection methods for other target POIs are similar and will not be elaborated further.

[0089] Through the above process, the most suitable point of interest can be automatically selected as the interaction result based on the detected interaction needs.

[0090] like Figure 11 As shown, in one implementation, the determination of interest point recommendation requirements may include the following process:

[0091] S1101: Determine the type of the user's physiological state based on user information;

[0092] S1102: When the physiological state type is a predetermined type, determine the interaction requirement as an interest point recommendation requirement. The predetermined type includes at least one of fatigue, hunger, urination, and illness.

[0093] In one implementation, the determination of point-of-interest (POI) recommendation requirements can be based on driver information. For example, the driver's different physiological states can be determined based on the detection results of images, videos, and voice recordings of the driver (corresponding to the user).

[0094] For example, if a driver blinks or yawns frequently, their physiological state can be identified as fatigue. Based on this, the interaction requirements can be determined to include point-of-interest (POI) recommendation needs, with hotels, service areas, etc., selected as POIs for recommendation.

[0095] When a driver expresses information such as hunger, their physiological state can be determined to be hunger. Based on this, the interaction request can be identified as a request for point-of-interest (POI) recommendations, with restaurants and similar establishments listed as potential POIs.

[0096] If a driver expresses a need to use the restroom, their physiological condition can be identified as urgent. Therefore, the interaction request can be determined to include a request for point-of-interest recommendations, with service areas and shopping malls listed as potential points of interest for recommendation.

[0097] Based on the detection of the driver frequently frowning, inhaling, and repeatedly touching the same area, it can be determined that the driver's physiological state is that of an illness. Therefore, it can be determined that the interaction needs include a need for point-of-interest recommendations, and service areas and hospitals can be selected as points of interest for recommendation.

[0098] Through the above process, the driver's condition can be determined based on the driver's monitoring data. This information can then be used to confirm the demand for point-of-interest recommendations.

[0099] like Figure 12 As shown, in one implementation, the determination of interest point recommendation requirements may include the following process:

[0100] S1201: Determine the current vehicle condition based on vehicle parameters;

[0101] S1202: When the vehicle condition meets the fault criteria, the interaction requirement is determined to be the point of interest recommendation requirement.

[0102] Based on vehicle parameters, it can be determined whether the current vehicle condition is normal. If the vehicle parameters are outside the predetermined normal operating range, it can be determined that the vehicle condition has reached a fault standard. Based on this, the interaction requirement can be determined as an interest-point recommendation requirement.

[0103] Furthermore, points of interest can be selected based on the type of fault. For example, if the fuel level is too low, the gas station can be selected as a point of interest. If the battery level is too low, the charging station can be selected as a point of interest.

[0104] Through the above process, potential vehicle malfunctions can be predicted, thereby ensuring the normal operation of the vehicle.

[0105] like Figure 13 As shown, this disclosure relates to a method for intelligent interaction, which is executed by an input layer, a computation layer and an output layer.

[0106] The main function of the input layer is to receive user (driver) input or to actively trigger based on detected information. The input layer may include a speech recognition module, an audio-visual fusion emotion recognition module, and a scene discrimination module, etc.

[0107] The speech recognition module, based on Automatic Speech Recognition (ASR) technology, recognizes the user's speech in scenarios where the user actively wakes up the device and converts the speech into text. The speech recognition module has full-duplex, multi-turn communication capabilities.

[0108] The audio-visual fusion emotion recognition module is used to understand the user's current state through voice and visual emotion recognition, with the user's authorization, such as fatigue recognition and emotion classification (anger, relaxation, joy, boredom, etc.).

[0109] The scenario discrimination module makes proactive judgments based on preset rules, such as whether the user is in traffic jams, how severe the traffic jams are, whether the user is passing through scenic spots or rest areas, and whether the user needs to rest after driving for a long time.

[0110] Between the input layer and the computation layer lies a requirement analysis and processing layer. This requires building user profile capabilities to understand users' long-term (interests, occupation, etc.), medium-term (travel purpose, etc.), and short-term (current mood and tolerance for disturbance) needs and preferences. Based on user input or triggers from preset rules, this process completes the understanding of requirements.

[0111] The main function of the computing layer is to serve user needs and complete backend calculations. The computing layer may include modules such as a traffic management system module, a knowledge graph module, a map point of interest module, and a retrieval module.

[0112] The traffic brain module can be used for traffic condition prediction, dynamic event perception, and other functions, providing users with rich route and traffic information. Dynamic event perception can include road construction, road management, and road accidents.

[0113] The knowledge graph module is used to provide casual information. For example, when a user wants to know about certain news, entertainment, or sports information, the knowledge graph module will integrate, calculate, and output the content based on this information.

[0114] The Points of Interest (POI) module on the map provides information related to points of interest. When a user's needs are related to geolocation, such as wanting information about their destination, the POI module will provide relevant content, such as opening hours, pricing information, and reviews.

[0115] The search module can be used to search for points of interest. When a user's needs are related to finding a geographical location, such as wanting to find a gas station or rest area nearby, the search module will provide that service.

[0116] The main function of the output layer is to provide users with content presentation methods based on the results of parsing and processing, as well as the output of the computation layer. This includes modules such as navigation product services, automatic content generation, voice broadcasting, and 3D virtual human synthesis.

[0117] The navigation product service module is used to directly adjust and change product services for users when their needs are related to operating the navigation product page, such as enlarging the base map or switching to a car-head mode.

[0118] The automatic content generation module automatically produces content based on user preferences when it is necessary to provide users with spoken content.

[0119] The broadcast module converts the text generated by the automatic content generation module into speech. To make the broadcast content more human-like and imbue it with emotional and personalized characteristics, the broadcast module can use real human voice samples for model training, thereby converting the text generated by the automatic content generation module into speech.

[0120] The 3D virtual human synthesis module can drive a 3D virtual human according to the content to be played, so that the 3D virtual human can broadcast the content.

[0121] like Figure 14 As shown, this disclosure relates to an intelligent interaction device, which may include:

[0122] The traffic information acquisition module 1401 is used to acquire corresponding traffic information based on the detected interaction requests;

[0123] The interactive content generation module 1402 is used to generate interactive content based on interactive requirements and the filtering results of traffic information;

[0124] The digital human driving module 1403 is used to generate driving parameters based on interactive content. The driving parameters include parameters used to drive the digital human in the interactive interface to broadcast interactive content.

[0125] In one embodiment, the traffic information acquisition module 1401 may include:

[0126] The parsing submodule is used to parse the acquired reference information and obtain the parsing result; the reference information includes at least one of user information and current vehicle driving information, the driving information includes vehicle parameters detected by vehicle sensors; the user information includes at least one of user voice information and action information.

[0127] The interaction requirement determination and execution submodule is used to determine that an interaction requirement has been detected if the parsing result meets predetermined conditions. The interaction requirement includes at least one of navigation requirement, companionship requirement, or point of interest recommendation requirement.

[0128] In one implementation, when the interaction requirements include navigation requirements, the interaction content generation module 1402 may include:

[0129] The target navigation route determination submodule is used to filter target navigation routes from traffic information based on navigation requirements, and the specified conditions are determined based on at least one of the navigation route's mileage and navigation route's travel time.

[0130] The interactive content generation and execution submodule is used to determine the interactive content based on the target navigation path.

[0131] In one implementation, the interaction requirements that determine the execution submodule may include:

[0132] The vehicle speed determination unit is used to determine the current vehicle speed within a predetermined time period based on vehicle parameters.

[0133] The congestion level determination unit determines the congestion level based on vehicle speed.

[0134] The interaction demand determination unit is used to determine the interaction demand as a navigation demand when the congestion level meets the pre-set congestion standard.

[0135] In one implementation, when the interaction requirement includes a need for companionship, the interaction content generation module 1402 may include:

[0136] The safe driving route determination submodule is used to determine safe driving routes based on the target navigation route and corresponding road conditions in the traffic information. Safe driving routes are road sections with road condition complexity lower than the corresponding complexity threshold.

[0137] The travel time determination submodule is used to determine the travel time of the current vehicle in the safe driving section;

[0138] The interactive content generation and execution submodule is used to generate interactive content that matches the driving time by utilizing AIGC, an artificial intelligence-based content production technology.

[0139] In one implementation, when the interaction requirement includes an interest point recommendation requirement, the interaction content generation module 1402 may include:

[0140] The Interest Point Type Determination submodule is used to determine the type of interest point corresponding to the interest point recommendation requirements;

[0141] The target interest point filtering submodule is used to filter target interest points from the candidate interest points contained in the traffic information based on the interest point type.

[0142] The interactive content generation and execution submodule is used to generate interactive content based on target points of interest.

[0143] In one implementation, the interaction requirements that determine the execution submodule may include:

[0144] The type determination unit is used to determine the type of the user's physiological state based on user information;

[0145] The interaction demand determination unit is used to determine the interaction demand as an interest point recommendation demand when the physiological state type is a predetermined type. The predetermined type includes at least one of fatigue, hunger, urination, and illness.

[0146] In one implementation, the interaction requirements that determine the execution submodule may include:

[0147] The vehicle condition determination unit is used to determine the current vehicle condition based on vehicle parameters.

[0148] The interaction requirement determination unit is used to determine the interaction requirement as a point-of-interest recommendation requirement when the vehicle condition meets the fault criteria.

[0149] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0150] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0151] Figure 15A schematic block diagram of an example electronic device 1500 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0152] like Figure 15 As shown, device 1500 includes a computing unit 1510, which can perform various appropriate actions and processes according to a computer program stored in read-only memory (ROM) 1520 or a computer program loaded from storage unit 1580 into random access memory (RAM) 1530. The RAM 1530 may also store various programs and data required for the operation of device 1500. The computing unit 1510, ROM 1520, and RAM 1530 are interconnected via bus 1540. Input / output (I / O) interface 1550 is also connected to bus 1540.

[0153] Multiple components in device 1500 are connected to I / O interface 1550, including: input unit 1560, such as keyboard, mouse, etc.; output unit 1570, such as various types of monitors, speakers, etc.; storage unit 1580, such as disk, optical disk, etc.; and communication unit 1590, such as network card, modem, wireless transceiver, etc. Communication unit 1590 allows device 1500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0154] The computing unit 1510 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1510 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1510 performs the various methods and processes described above, such as the method of intelligent interaction. For example, in some embodiments, the method of intelligent interaction may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 1580. In some embodiments, part or all of the computer program may be loaded and / or installed on device 1500 via ROM 1520 and / or communication unit 1590. When the computer program is loaded into RAM 1530 and executed by the computing unit 1510, one or more steps of the method of intelligent interaction described above may be performed. Alternatively, in other embodiments, the computing unit 1510 may be configured to perform the method of intelligent interaction by any other suitable means (e.g., by means of firmware).

[0155] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0156] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0157] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, 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 devices, magnetic storage devices, or any suitable combination of the foregoing.

[0158] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0159] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0160] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0161] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0162] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for intelligent interaction, comprising: Based on the detected interaction requests, corresponding traffic information is obtained; wherein, the interaction requests include at least one of navigation requests, companion requests, or point-of-interest recommendation requests, and the interaction requests are obtained by parsing the obtained reference information, which includes user information and current vehicle driving information; Based on the interaction requirements and the filtering results of the traffic information, generate interactive content; Based on the interactive content, driving parameters are generated, including parameters used to drive the digital human in the interactive interface to broadcast the interactive content. Where the interaction requirement includes a need for companionship, the step of generating interactive content based on the interaction requirement and the filtering results of the traffic information includes: Based on the target navigation path and corresponding road conditions in the traffic information, a safe driving section is determined. The safe driving section is a road section whose road condition complexity is lower than the corresponding complexity threshold. Determine the current travel time of the vehicle on the safe driving section; Using AIGC, an artificial intelligence-based content production technology, interactive content is generated that matches the driving time.

2. The method according to claim 1, wherein the current vehicle driving information includes vehicle parameters detected by vehicle sensors; and the user information includes at least one of the user's voice information and action information.

3. The method according to claim 2, wherein, When the interaction request includes a navigation request, generating interactive content based on the interaction request and the filtering results of the traffic information includes: Based on the navigation requirements, target navigation routes that meet specified conditions are filtered from the traffic information. The specified conditions are determined based on at least one of the navigation route's mileage and the navigation route's travel time. The interactive content is generated based on the target navigation path.

4. The method according to claim 2 or 3, wherein, The methods for confirming the navigation request include: Based on the vehicle parameters, determine the current vehicle speed within the predetermined time period; The congestion level is determined based on the vehicle speed. If the congestion level meets the pre-set congestion criteria, the interaction request is determined to be a navigation request.

5. The method according to claim 2, wherein, When the interaction request includes a point-of-interest recommendation request, generating interactive content based on the interaction request and the filtering results of the traffic information includes: Determine the type of interest point corresponding to the interest point recommendation requirement; Based on the type of interest, the target interest is selected from the candidate interest points included in the traffic information. The interactive content is generated based on the target points of interest.

6. The method according to claim 2 or 5, wherein, The method for determining the interest point recommendation requirement includes: Based on the user information, determine the type of the user's physiological state; If the physiological state is of a predetermined type, the interaction request is determined to be an interest point recommendation request. The predetermined type includes at least one of fatigue, hunger, urination, and illness.

7. The method according to claim 2 or 5, wherein, The method for determining the interest point recommendation requirement includes: Based on the vehicle parameters, determine the current vehicle condition; If the vehicle condition meets the fault criteria, the interaction request is determined to be a point-of-interest recommendation request.

8. A smart interactive device, comprising: The traffic information acquisition module is used to acquire corresponding traffic information based on detected interaction requests. The traffic information acquisition module includes an interaction request determination and execution submodule, which is used to determine the interaction requests. The interaction requests include at least one of navigation requests, companion requests, or point of interest recommendation requests. The interaction requests are obtained by parsing the acquired reference information, which includes user information and the current vehicle's driving information. An interactive content generation module is used to generate interactive content based on the interactive requirements and the filtering results of the traffic information; A digital human driving module is used to generate driving parameters based on the interactive content, the driving parameters including parameters for driving the digital human in the interactive interface to broadcast interactive content; Where the interaction requirement includes companionship, the interaction content generation module includes: a safe driving route determination submodule, used to determine a safe driving route based on the target navigation path and corresponding road conditions in the traffic information, wherein the safe driving route is a route with road condition complexity below a corresponding complexity threshold; a driving time determination submodule, used to determine the driving time of the current vehicle in the safe driving route; and an interaction content generation execution submodule, used to generate interaction content matching the driving time using AIGC (Artificial Intelligence Generated Content) technology.

9. The apparatus according to claim 8, wherein, The current vehicle driving information includes vehicle parameters detected by vehicle sensors; the user information includes at least one of the user's voice information and action information.

10. The apparatus according to claim 9, wherein, When the interaction requirement includes a navigation requirement, the interaction content generation module includes: The target navigation route determination submodule is used to filter out target navigation routes that meet specified conditions from the traffic information according to the navigation requirements. The specified conditions are determined based on at least one of the mileage of the navigation route and the travel time of the navigation route. The interactive content generation and execution submodule is used to determine the interactive content based on the target navigation path.

11. The apparatus according to claim 9 or 10, wherein, The interaction requirements determine the execution submodule, including: The vehicle speed determination unit is used to determine the current vehicle speed within a predetermined time period based on the vehicle parameters. The congestion level determination unit determines the congestion level based on the vehicle speed. The interaction demand determination unit is used to determine the interaction demand as a navigation demand when the congestion level meets the preset congestion standard.

12. The apparatus according to claim 9, wherein, When the interaction requirement includes an interest point recommendation requirement, the interaction content generation module includes: The interest point type determination submodule is used to determine the interest point type corresponding to the interest point recommendation requirement; The target interest point filtering submodule is used to filter out target interest points from the candidate interest points contained in the traffic information according to the interest point type. The interactive content generation and execution submodule is used to generate the interactive content based on the target point of interest.

13. The apparatus according to claim 9 or 12, wherein, The interaction requirements determine the execution submodule, including: A type determination unit is used to determine the type of the user's physiological state based on the user information; An interaction demand determination unit is used to determine that the interaction demand is an interest point recommendation demand when the type of the physiological state is a predetermined type. The predetermined type includes at least one of fatigue, hunger, urination, and illness.

14. The apparatus according to claim 9 or 12, wherein, The interaction requirements determine the execution submodule, including: The vehicle condition determination unit is used to determine the current vehicle condition based on the vehicle parameters. The interaction requirement determination unit is used to determine that the interaction requirement is a point-of-interest recommendation requirement when the vehicle condition reaches the fault standard.

15. An electronic device comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 7.

16. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 7.

17. A computer program product comprising a computer program / instructions, wherein, When the computer program / instructions are executed by the processor, they implement the steps of the method according to any one of claims 1 to 7.

Images