WO2023173657A1

WO2023173657A1 - Intelligent interaction method and apparatus, device, and storage medium

Info

Publication number: WO2023173657A1
Application number: PCT/CN2022/110117
Authority: WO
Inventors: 黄际洲; 张昊
Original assignee: 北京百度网讯科技有限公司
Priority date: 2022-03-18
Filing date: 2022-08-03
Publication date: 2023-09-21
Also published as: CN116798254A

Abstract

An intelligent interaction method and apparatus, a device, and a storage medium. The specific implementation solution comprises: S101: obtaining corresponding traffic information according to a detected interaction requirement; S102: generating interactive content according to the interaction requirement and a screening result of the traffic information; and S103: generating a driving parameter on the basis of the interactive content, the driving parameter comprising a parameter used for driving a digital human in an interactive interface to broadcast the interactive content.

Description

Intelligent interaction methods, devices, equipment and storage media

Cross-references to related applications

This application is filed based on a Chinese patent application with application number 202210273184.3 and a filing date of March 18, 2022, and claims the priority of the Chinese patent application. The entire content of the Chinese patent application is hereby incorporated into this application as a reference.

Technical field

The present disclosure relates to the field of computer technology, in particular to artificial intelligence, intelligent transportation, voice technology, etc., and in particular to an intelligent interaction method, device, equipment and storage medium.

Background technique

With the continuous development of ground transportation, driving has become a common way of travel for many people. For most drivers, they need to rely on navigation while driving. The content provided by traditional navigation is relatively simple and cannot meet the needs of users.

Contents of the invention

The present disclosure provides an intelligent interaction method, device, equipment and storage medium.

According to one aspect of the present disclosure, a method of intelligent interaction is provided, which may include the following steps:

Obtain corresponding traffic information based on the detected interaction requirements;

Generate interactive content based on interaction needs and screening results of traffic information;

Based on the interactive content, driving parameters are generated, and the driving parameters include parameters used to drive the digital human in the interactive interface to broadcast the interactive content.

According to another aspect of the present disclosure, an intelligent interactive device is provided, which may include:

The traffic information acquisition module is used to obtain corresponding traffic information based on the detected interaction requirements;

The interactive content generation module is used to generate interactive content based on interactive needs and screening results of traffic information;

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.

According to another aspect of the present disclosure, an electronic device is provided, including:

at least one processor; and

A memory communicatively connected to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can perform the method in any embodiment of the present disclosure.

According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, the computer instructions being used to cause a computer to execute the method in any embodiment of the present disclosure.

According to another aspect of the present disclosure, a computer program product is provided, including a computer program/instructions that, when executed by a processor, implements the method in any embodiment of the present disclosure.

According to the technology of the present disclosure, terminals with intelligent interaction functions, such as cars and machines, can proactively identify interaction needs, and then determine different interaction needs. Terminals with intelligent interaction functions can determine traffic information based on interaction needs, thereby providing assistance to drivers from different dimensions.

It should be understood that what is described in this section is not intended to identify key or important features of the embodiments of the disclosure, nor is it intended to limit the scope of the disclosure. Other features of the present disclosure will become readily understood from the following description.

Description of the drawings

The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure. in:

Figure 1 is a flow chart of a method of intelligent interaction according to some embodiments of the present disclosure;

Figure 2 is a schematic diagram of an interactive interface according to some embodiments of the present disclosure;

Figure 3 is a flow chart for obtaining traffic information according to some embodiments of the present disclosure;

Figure 4 is a flowchart of generating interactive content according to some embodiments of the present disclosure;

Figure 5 is a schematic diagram of an interactive interface according to some embodiments of the present disclosure;

Figure 6 is a flowchart of a manner of confirming navigation requirements according to some embodiments of the present disclosure;

Figure 7 is a flowchart of generating interactive content according to some embodiments of the present disclosure;

Figure 8 is a schematic diagram of an interactive interface according to some embodiments of the present disclosure;

Figure 9 is a flowchart of generating interactive content according to some embodiments of the present disclosure;

Figure 10 is a schematic diagram of an interactive interface according to some embodiments of the present disclosure;

Figure 11 is a flowchart of determining interest point recommendation requirements according to some embodiments of the present disclosure;

Figure 12 is a flowchart of determining interest point recommendation requirements according to some embodiments of the present disclosure;

Figure 13 is a scene diagram of a method that can implement intelligent interaction according to an embodiment of the present disclosure;

Figure 14 is a schematic diagram of an intelligent interactive device according to some embodiments of the present disclosure;

FIG. 15 is a block diagram of an electronic device used to implement an intelligent interaction method according to an embodiment of the present disclosure.

Detailed ways

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the present disclosure are included to facilitate understanding and should be considered to be exemplary only. Accordingly, those of ordinary skill 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 the disclosure. Also, descriptions of well-known functions and constructions are omitted from the following description for clarity and conciseness.

As shown in Figure 1, the present disclosure relates to a method of intelligent interaction, which may include the following steps:

S101: Obtain corresponding traffic information based on the detected interaction requirements;

S102: Generate interactive content based on interaction requirements and the screening results of traffic information;

S103: Based on the interactive content, generate driving parameters. The driving parameters include parameters used to drive the digital human in the interactive interface to broadcast the interactive content.

The execution subject of this disclosure may be a vehicle machine of a vehicle with automatic driving or assisted driving functions, or it may be a cloud server that communicates with the car machine, etc. The interaction needs may be determined by analyzing the data detected by the vehicle's sensors. For example, sensors may include image capture devices, sound capture devices, etc. inside the vehicle. In addition, sensors may also include image sensors outside the vehicle, sensors on different components of the vehicle, etc.

By way of example, the vehicle only includes the driver. Interaction requirements can be actively triggered by the driver. For example, when the sound collection device collects the driver's trigger command, it can be determined that the interaction requirement is detected. Alternatively, interaction requirements can be triggered by detecting driver behavior. For example, by analyzing the content collected by image collection equipment and sound collection equipment, it can be determined whether the driver is tired, hungry, irritated, etc. Based on this, it can be determined that an interaction requirement is detected. Or, the interaction requirement can be triggered based on the status of the vehicle. For example, when the vehicle's driving speed is lower than the corresponding speed threshold for a long time, it can be determined that a traffic jam has occurred, and thus it can be determined that the interaction requirement has been detected. For another example, when the sensor of a certain component of the vehicle detects that the component is not in normal working condition, it can also be determined that an interaction requirement is detected. In addition, in addition to the driver in the above example, the interaction objects may also include other passengers.

For different interaction needs, corresponding traffic information can be obtained. In response to the interaction requirements triggered by the driver, the traffic information obtained can be determined based on the interaction content sent by the driver. For example, if the driver's interaction content is "Chat with me", then the corresponding traffic information can be the traffic condition information of the remaining road sections. Based on this, traffic information can be referenced when generating interactive content. For example, chatting with the driver can only be supported if it is determined that the current vehicle is traveling on a road section with relatively simple road conditions.

For another example, according to different situations such as driver fatigue, hunger, boredom, etc., points of interest can be determined as corresponding traffic information. For example, in the case of fatigue, the identified points of interest can be hotels or service areas. For hunger situations, the identified points of interest can be restaurants, etc. For impatient situations, the method can be the same as the above-mentioned handling method when the driver's interaction content is "Chat with me."

For another example, for the interaction requirement where the detected vehicle speed is lower than the corresponding threshold, the corresponding traffic information obtained may be to query other routes, etc. In response to the interaction requirements corresponding to vehicle component abnormalities, the corresponding traffic information obtained can be nearby parking spots, or nearby maintenance points, etc.

Filtering of traffic information can include the following situations. For example, in the case where the traffic information is multiple navigation paths including traffic condition information, the navigation path with relatively simple traffic conditions can be used as the filtering result. When the traffic information includes multiple candidate interest points, the target interest point can be selected as the filtering result based on the driver's preferences or the evaluation of each interest point. The interactive content may be content formed by nesting the filtered results of traffic information using predetermined utterances that match the interaction requirements. In addition, it can also be summary information generated based on the filtering results, etc.

Based on the interaction content, driving parameters can be generated. This drives the digital humans in the interactive interface to broadcast interactive content. The so-called digital human can be the crystallization of digital character technology and artificial intelligence technology. A digital person can be a virtual character with a digital appearance that relies on a display device to exist. Digital people can have the appearance of humans (including cartoon images) and have specific characteristics such as appearance, gender, and personality. According to the control instructions, the digital human can output voice and movements, etc. Among them, the interactive interface including the digital human can be covered with the original picture of the car screen in the form of a translucent floating layer. The interactive interface may include multiple display areas. For example, as shown in FIG. 2 , the interactive interface may include a digital human area, an interactive content display area, and an additional content display area. Among them, the digital human area includes at least one digital human, and the digital human can perform expressions and different mouth shapes through driving parameters to correspondingly broadcast interactive content. The additional content display area can be used to display additional content such as candidate roads and candidate interest point introductions, and the interactive content display area can be used to display the interaction history within a certain period of time in the past.

Through the above process, terminals with intelligent interaction functions, such as cars and machines, can actively detect interaction needs. This allows terminals with intelligent interaction functions to determine traffic information based on interaction needs and provide assistance to drivers from different dimensions.

As shown in Figure 3, in one implementation, the acquisition method of interaction requirements involved in step S101 may include the following process:

S301: Analyze the obtained reference information to obtain an analysis result; the reference information includes at least one of user information and current vehicle driving information, and the driving information includes vehicle parameters detected by the vehicle sensor; user information includes the user's voice information and At least one type of action information;

S302: When the parsing result satisfies the predetermined conditions, it is determined that an interaction requirement is detected; the interaction requirement includes at least one of a navigation requirement, a companionship requirement, or a point of interest recommendation requirement.

Taking the user as a driver as an example, the reference information may be information collected with the driver's authorization. For example, the reference information may be driver information. Specifically, it may be video information, image information, etc. including the driver collected by an image collection device. Thus, the driver's action information can be determined based on the video information and/or image information. In addition, it can also be the driver's voice information collected through the radio equipment. For another example, the reference information may be the driving information of the current vehicle. For example, the driving information may include vehicle parameters detected by vehicle sensors, such as vehicle speed, remaining fuel level, tire pressure, engine parameters, gearbox parameters, motor parameters, battery parameters, etc.

By analyzing the obtained reference information and judging whether it meets the predetermined conditions, automatic detection of interaction requirements can be achieved. For example, the voice message contains content with clear instructions such as "turn on interactive mode", "chat with me", etc., indicating that the driver has interaction needs. Alternatively, detecting that the driver makes a specific action through video information and/or image information can also indicate that predetermined conditions are met, that is, the driver has interaction needs. It is easy to understand that the above instructions and specific actions are determined in advance. For this, interaction needs can be determined as companionship needs.

For another example, if the driver's anxiety, fatigue, or hunger is detected through pictures, videos, or audio, it can also be determined that the predetermined conditions are met. For this, the interaction requirement can be determined as a companionship requirement or a point-of-interest recommendation requirement. When there is a demand for point of interest recommendation, the corresponding point of interest can be selected according to the driver's specific situation. For example, a movie theater, a restaurant, or going home.

For another example, when the vehicle speed is determined to be 0 through vehicle parameters, or the vehicle speed is lower than the corresponding threshold for a long period of time, it can indicate the existence of traffic congestion. From this, it can be determined that the predetermined condition is satisfied. For this, the interaction requirement can be determined as a navigation requirement, that is, navigating other paths to avoid congestion.

For another example, when it is determined that there is a fault in the vehicle through vehicle parameters, it can also be determined that the predetermined condition is met. For this, the interaction requirement can be determined as the point of interest recommendation requirement. Points of interest can be automobile sales service 4S (Automobile Sales Servicshop 4S) stores, service areas or vehicle repair points, etc.

Through the above process, the interactive demand for drinks can be determined based on driver information, vehicle information, etc. This can provide drivers with more diversified services.

As shown in Figure 4, in one implementation, when the interaction requirements include navigation requirements, step S102 may include the following process:

S401: Based on the navigation requirements, select the target navigation path that meets the specified conditions from the traffic information. The specified conditions are determined based on at least one of the driving mileage of the navigation path and the driving time of the navigation path;

S402: Generate interactive content according to the target navigation path.

In the case where the interaction requirements include navigation requirements, the traffic information may be based on multiple navigation paths to the destination. The result of filtering traffic information may be to select a target navigation path from multiple navigation paths.

The filtering method may be based on at least one of the driving mileage of the navigation path, the driving time of the navigation path, and the travel cost of the navigation path. Travel costs can include fuel, electricity, tolls, etc. For example, you can weight different filter factors. For example, the weight of driving time is greater than the weight of driving mileage, and the weight of driving mileage is greater than the weight of travel cost. For the determined target route, only the travel time and mileage of the target route can be retained.

As shown in Figure 5, for the target path, the corresponding interactive content can be "According to the current traffic status, it is expected that more and more vehicles will converge on the congested road section ahead. I helped you find a new road. Route XXX, the time can be 2 minutes faster and the distance is about the same. Do you want to change it?" When the traditional navigation interface recommends routes to users, it usually also displays navigation guidance information, toll station information, remaining mileage, remaining time, and recommended congestion avoidance routes. As well as route time, tolls, traffic lights and mileage comparison, etc. For drivers who want to know if congestion ahead is increasing and they need to change routes, such information is too scattered to assist in quick decision-making.

In the current implementation, relatively concise information can be used to help the driver make quick decisions.

As shown in Figure 6, in one implementation, the confirmation method of navigation requirements may include the following process:

S601: Determine the speed of the current vehicle within a predetermined time period based on vehicle parameters;

S602: Determine the congestion level based on vehicle speed;

S603: When the congestion level meets the preset congestion standard, determine the interaction requirement as a navigation requirement.

The confirmation method of navigation requirements can be determined based on the vehicle speed in the vehicle parameters. For example, during driving, if the vehicle speed is 0 for more than a predetermined time (for example, 10 seconds) due to non-traffic lights, or if the vehicle speed is lower than the corresponding first speed threshold (for example, 5km/h) for more than a predetermined time, congestion can be determined. The level is "critical". For another example, if the vehicle speed is between the first vehicle speed threshold and the second vehicle speed threshold (for example, 15 km/h) for more than a predetermined time, the congestion level may be determined to be "normal".

Based on the congestion level, navigation needs can be determined. For example, when the congestion level is higher than "average", the interaction requirement can be determined to be a navigation requirement.

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

As shown in Figure 7, in one implementation, when the interaction requirement includes a companionship requirement, step S102 may include the following process:

S701: Determine a safe driving section based on the target navigation path in the traffic information and the corresponding road conditions. The safe driving section is a road section where the complexity of the road conditions is lower than the corresponding complexity threshold;

S702: Determine the driving time of the current vehicle on the safe driving section;

S703: Use artificial intelligence-based content production technology AIGC to generate interactive content that matches the driving time.

When the interaction requirements include companionship requirements, the target navigation path and the traffic conditions corresponding to the target navigation path can be obtained from the traffic information. For example, in scenarios such as highway driving or expressway driving, the exit can be determined in the remaining road segments. When the distance to the exit exceeds the corresponding distance threshold, it can mean that the driver does not need to perform complex operations, that is, it can correspond to a safe driving section where the road condition complexity is lower than the corresponding complexity threshold. That is, when the distance to the exit exceeds the corresponding distance threshold, it can mean that the driver only needs to drive on the main road (highway or expressway), so it can be considered that the road condition is less complex. The driving time for safe driving sections can be estimated based on distance and road conditions.

For another example, when waiting for a red light, the remaining duration of the red light can be obtained from the traffic conditions. If the remaining duration of the red light is greater than the corresponding duration threshold, it can be corresponding to driving in a road where the complexity of the traffic condition is lower than the corresponding complexity. Threshold safe driving section. That is, when the red light time is long, the driver is not required to perform driving operations, so it can be considered that the road condition is less complex. Thus, the road section corresponding to the current stopping position can be determined as a safe driving section. Correspondingly, the end time of the red light can be corresponding to the driving time of the safe driving section.

For another example, when the traffic jam is severe and there are no candidate routes, the traffic jam section can also be determined as a safe driving section where the road condition complexity is lower than the corresponding complexity threshold. Correspondingly, the time from driving to the end point of the traffic jam can be determined as the driving time of the safe driving section.

Based on the driving time of safe driving sections, artificial intelligence content production technology AIGC can be used to generate topics to achieve interaction with drivers. Correspondingly, the topic of the topic can be a current hot search topic, a topic determined based on the driver's user portrait, etc. Alternatively, as shown in FIG. 8 , the corresponding topic can also be determined based on the questions raised by the driver. For example, ask whether sports events were won or lost, ask about celebrity anecdotes, etc. The so-called AIGC means that artificial intelligence technology can be used to automatically generate multimedia content. For example, you can write poetry, compose music, generate news, etc. AIGC can generate multimedia content based on hot events on the Internet, and can also generate multimedia content based on received user inquiries.

During multiple rounds of interaction with users, interaction strategies can also be determined based on user portraits. Among them, user portraits can include the user's long-term preferences, medium-term preferences, and short-term preferences. For example, long-term preferences may include the user's interests and occupation, etc. The mid-term preference can be the current purpose of travel, such as traveling, attending a conference, etc. Short-term preferences can be the user's current emotional needs, such as current mood and tolerance to interruptions. When generating content, priorities can be determined in order of short-term, medium-term, and long-term, so as to better improve the user experience.

Through the above process, when the driver needs companionship, topics of interest to the driver can be generated to help the user get through the relatively monotonous driving process. Moreover, the driver's companionship can be based on road conditions, thereby ensuring the driver's safe driving to the greatest extent.

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

S901: Determine the POI type corresponding to the POI recommendation requirement;

S902: According to the type of interest point, select the target interest point from the candidate interest points included in the traffic information;

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

Points of interest recommendation requirements may include multiple categories. For example, if a driver is detected to yawn or blink frequently, it may indicate that the driver is tired. Based on this, it can be determined that the point of interest recommendation requirement is the need for rest. As shown in FIG. 10 , the point of interest type may be a leisure type, such as a service area, etc. Correspondingly, the store information contained in the service area obtained from the network can also be displayed based on the point of interest retrieval function. In the example shown in Figure 10, service area information can be introduced to the user based on the brands of gas stations that the user often goes to. In addition, the user can also be introduced based on the user's preferences, such as the type of food the user likes, preferred restaurants and shops, etc.

For another example, when an abnormality in a vehicle is detected, the type of interest point recommendation requirement can be determined based on the abnormal situation. For example, when a fuel vehicle is low on fuel, a gas station can be used as a point of interest type. When the power of new energy vehicles is insufficient, charging piles (stations) can be used as point-of-interest types. In the event that some parts of the vehicle fail, a 4S shop or repair point can be used as a point of interest type.

According to the type of interest points, the corresponding target interest points are screened out from the candidate interest points included in the traffic information. For example, when the point of interest type is a gas station, the target gas station can be selected as the target point of interest based on the gas station brand preferred by the driver. Similarly, when the type of point of interest is a hotel, the target hotel can be selected as the target point of interest based on the hotel's reputation, reviews, the driver's preferred hotel brand, etc. The selection methods for other target points of interest are similar and will not be described again.

Through the above process, the most suitable points of interest can be automatically selected as interaction results based on the detected interaction requirements.

As shown in Figure 11, in one implementation, the method for determining the recommendation requirements for points of interest may include the following process:

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

S1102: When the type of physiological state is a predetermined type, determine the interaction requirement as a point of interest recommendation requirement, and the predetermined type includes at least one of fatigue, hunger, internal urgency, and illness.

In one implementation, the determination of the interest point recommendation requirements may be based on the driver's information. For example, different physiological states of the driver can be determined based on the detection results of images, videos, voices, etc. of the driver (corresponding to the user).

For example, in the case where the driver frequently blinks or yawns, the type of the driver's physiological state may be determined to be fatigue. In this regard, it can be determined that the interaction requirements include the recommendation requirements for points of interest, and hotels, service areas, etc. are used as points of interest to be recommended.

When the driver expresses information such as hunger, it can be determined that the type of the driver's physiological state is hunger. In this regard, it can be determined that the interaction requirements include the recommendation requirements for points of interest, and restaurants, etc. are used as points of interest to be recommended.

When the driver expresses that he wants to go to the bathroom, it can be determined that the type of the driver's physiological state is internal urgency. In this regard, it can be determined that the interaction requirements include the recommendation requirements for points of interest, and service areas, shopping malls, etc. are used as points of interest to be recommended.

When it is detected that the driver frequently frowns, inhales, and repeatedly touches the same part with his hand, it can be determined that the driver's physiological state is sick. In this regard, it can be determined that the interaction requirements include the recommendation requirements for points of interest, and service areas, hospitals, etc. are used as points of interest to be recommended.

Through the above process, the driver's status can be determined based on the detection of the driver. Then the requirements for recommendation of points of interest are confirmed.

As shown in Figure 12, in one implementation, the method for determining the recommendation requirements for points of interest may include the following process:

S1201: Determine the current vehicle condition based on vehicle parameters;

S1202: When the vehicle condition reaches the fault standard, determine the interaction requirement as the point of interest recommendation requirement.

Based on the vehicle parameters, it can be determined whether the current vehicle condition is normal. When the vehicle parameters are not within the predetermined normal operating parameter range, it can be determined that the vehicle condition reaches the failure standard. Based on this, the interaction requirement can be determined as the POI recommendation requirement.

Furthermore, you can also select the corresponding points of interest based on the fault type. For example, if the fuel level is too low as mentioned above, the gas station will be used as a point of interest. If the battery is too low, use the charging pile (station) as a point of interest.

Through the above process, possible vehicle failures can be predicted to ensure the normal driving of the vehicle.

As shown in Figure 13, the present disclosure relates to a method of intelligent interaction, which is executed by an input layer, a calculation layer, and an output layer.

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

The speech recognition module is based on automatic speech recognition technology (Automatic Speech Recognition, ASR). It recognizes the user's voice in the scenario where the user actively wakes up and converts the voice into text. The speech recognition module has full-duplex multi-round communication capabilities.

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

The scene discrimination module makes active trigger judgments based on preset rules, such as whether the user is in congestion, whether the congestion is serious, whether the user passes through scenic spots or rest areas, and whether the user needs to rest after driving for a long time, etc.

Between the input layer and the calculation layer, demand analysis processing is also included. Demand analysis processing requires the construction of user portrait capabilities, and understanding the user's long-term (interests, occupations, etc.), mid-term (travel purpose, etc.) and short-term (current mood and tolerance to interruption) needs and preferences. Complete the understanding of requirements based on user input or triggering of preset rules.

The main function of the computing layer is to serve the needs of users and complete background calculations. The computing layer can include a traffic brain module, a knowledge graph module, a map point of interest module, a retrieval module, etc.

The traffic brain module can be used for traffic prediction, dynamic event perception, etc., providing users with rich route traffic information. Dynamic event awareness can include road construction, road control, road accidents, etc.

The knowledge graph module is used to provide chat information. For example, when users want to know about certain news, gossip, entertainment, and sports information, the knowledge graph module will integrate, calculate, and output the content based on this information.

The map point of interest module is used to provide information related to points of interest. When the user's needs are related to geographical location, for example, the user wants to know destination information, etc., the map point of interest module will provide the user with relevant content, such as business hours, consumption status, comments, etc.

The retrieval module can be used to search for points of interest. When the user's needs are related to searching for a geographical location, such as if the user wants to refuel nearby, rest nearby, etc., the retrieval module will provide services for the user.

The main function of the output layer is to provide users with a content presentation method based on the results of analytical processing and the results output by the calculation layer. Including navigation product service module, automatic content generation module, voice broadcast module and 3D virtual human synthesis module, etc.

The navigation product service module is used to directly adjust and change product services for users when the user's needs are related to the operation of the navigation product page, such as enlarging the base map, adjusting to the front mode, etc.

The automatic content generation module combines the user's preference settings to automatically produce content when it is necessary to provide users with oral content.

The broadcast module is used to convert the text generated by the automatic content generation module into speech. In order to make the spoken content closer to personification and endow it with emotional and personalized characteristics, the broadcasting module can use real-life vocal samples for model training, thereby converting the text generated by the automatic content generation module into speech.

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

As shown in Figure 14, the present disclosure relates to an intelligent interactive device, which may include:

The traffic information acquisition module 1401 is used to obtain corresponding traffic information according to the detected interaction requirements;

The interactive content generation module 1402 is used to generate interactive content based on the interaction requirements and the screening results of traffic information;

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.

In one implementation, the traffic information acquisition module 1401 may include:

The parsing sub-module is used to parse the obtained reference information to obtain parsing results; the reference information includes at least one of user information and current vehicle driving information, and the driving information includes vehicle parameters detected by vehicle sensors; user information includes user information At least one of voice information and action information;

The interaction requirement determination execution sub-module is used to determine that an interaction requirement is detected when the parsing result satisfies a predetermined condition, and the interaction requirement includes at least one of a navigation requirement, a companionship requirement, or a point of interest recommendation requirement.

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

The target navigation path determination submodule is used to filter out the target navigation path that meets the specified conditions from the traffic information according to the navigation requirements. The specified conditions are determined based on at least one of the driving mileage of the navigation path and the driving time of the navigation path;

The interactive content generation execution sub-module is used to generate the interactive content according to the target navigation path.

In one implementation, the interaction requirement determination execution submodule may include:

A vehicle speed condition determination unit is used to determine the vehicle speed condition of the current vehicle within a predetermined time period based on 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.

In one implementation, when the interaction requirements include companionship requirements, the interactive content generation module 1402 may include:

The safe driving section determination submodule is used to determine a safe driving section based on the target navigation path and corresponding road conditions in the traffic information. A safe driving section is a road section where the complexity of the road conditions is lower than the corresponding complexity threshold;

The driving time determination submodule is used to determine the driving time of the current vehicle on the safe driving section;

The interactive content generation execution sub-module is used to generate interactive content that matches the driving time using AIGC, a content production technology based on artificial intelligence.

In one implementation, when the interaction requirements include interest point recommendation requirements, the interactive content generation module 1402 may include:

The interest point type determination sub-module is used to determine the interest point type corresponding to the interest point recommendation requirements;

The target point of interest screening submodule is used to filter out target points of interest from the candidate interest points included in the traffic information according to the type of interest point;

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

A type determination unit, used to determine the type of the user's physiological state based on the user information;

The interaction demand determination unit is configured to determine the interaction demand as the interest point recommendation demand when the type of physiological state is a predetermined type, and the predetermined type includes at least one of fatigue, hunger, internal urgency, and illness.

The vehicle condition determination unit is used to determine the current vehicle condition based on vehicle parameters;

The interaction demand determination unit is used to determine the interaction demand as the recommendation demand for points of interest when the vehicle condition reaches the fault standard.

In the technical solution of this disclosure, the acquisition, storage and application of user personal information involved are in compliance with relevant laws and regulations and do not violate public order and good customs.

According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

15 illustrates a schematic block diagram of an example electronic device 1500 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to refer to various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are examples only and are not intended to limit implementations of the disclosure described and/or claimed herein.

As shown in FIG. 15 , the device 1500 includes a computing unit 1510 that can execute according to a computer program stored in a read-only memory (ROM) 1520 or loaded from a storage unit 1580 into a random access memory (RAM) 1530 Various appropriate actions and treatments. In the RAM 1530, various programs and data required for the operation of the device 1500 can also be stored. Computing unit 1510, ROM 1520 and RAM 1530 are connected to each other via bus 1540. An input/output (I/O) interface 1550 is also connected to bus 1540.

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 displays, speakers, etc.; storage unit 1580, such as magnetic disk, optical disk, etc. ; and communication unit 1590, such as a network card, modem, wireless communication transceiver, etc. The communication unit 1590 allows the device 1500 to exchange information/data with other devices through computer networks such as the Internet and/or various telecommunications networks.

Computing unit 1510 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing units 1510 include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processing processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 1510 performs various methods and processes described above, such as intelligent interaction methods. For example, in some embodiments, the method of intelligent interaction may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as the storage unit 1580. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 1500 via ROM 1520 and/or communication unit 1590. When the computer program is loaded into the 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 in any other suitable manner (eg, by means of firmware).

Various implementations of the systems and techniques described above may 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 implemented in a system (SOC), load programmable logic device (CPLD), computer hardware, firmware, software, and/or a combination thereof. These various embodiments may include implementation in one or more computer programs executable and/or interpreted on a programmable system including at least one programmable processor, the programmable processor The processor, which may be a special purpose or general purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device. An output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that the program codes, when executed by the processor or controller, cause the functions specified in the flowcharts and/or block diagrams/ The operation is implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include one or more wire-based electrical connections, laptop disks, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.

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

The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., A user's computer having a graphical user interface or web browser through which the user can interact with implementations of the systems and technologies described herein), or including such backend components, middleware components, or any combination of front-end components in a computing system. The components of the system may be interconnected by any form or medium of digital data communication (eg, a communications network). Examples of communication networks include: local area network (LAN), wide area network (WAN), and the Internet.

Computer systems may include clients and servers. Clients and servers are generally remote from each other and typically interact over a communications network. The relationship of client and server is created by computer programs running on corresponding computers and having a client-server relationship with each other. The server can be a cloud server, a distributed system server, or a server combined with a blockchain.

It should be understood that various forms of the process shown above may be used, with steps reordered, added or deleted. For example, each step described in the present disclosure can be executed in parallel, sequentially, or in a different order. As long as the desired results of the technical solution disclosed in the present disclosure can be achieved, there is no limitation here.

The above-mentioned specific embodiments do not constitute a limitation on the scope of the present disclosure. It will be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions are possible depending on design requirements and other factors. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this disclosure shall be included in the protection scope of this disclosure.

Claims

A method of intelligent interaction including:

Obtain corresponding traffic information based on the detected interaction requirements;

Generate interactive content based on the interaction requirements and the screening results of the traffic information;

Based on the interactive content, driving parameters are generated, where the driving parameters include parameters used to drive the digital human in the interactive interface to broadcast the interactive content.
The method according to claim 1, wherein the confirmation method of the interaction requirement includes:

The obtained reference information is analyzed to obtain an analysis 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 user At least one of voice information and action information;

When the parsing result satisfies the predetermined condition, it is determined that an interaction requirement is detected; the interaction requirement includes at least one of a navigation requirement, a companionship requirement, or a point of interest recommendation requirement.
The method according to claim 2, wherein, when the interaction requirements include navigation requirements, generating interactive content based on the interaction requirements and the screening results of the traffic information includes:

According to the navigation requirement, select a target navigation path that satisfies specified conditions from the traffic information, and the specified conditions are determined based on at least one of the driving mileage of the navigation path and the driving time of the navigation path;

The interactive content is generated according to the target navigation path.
The method according to claim 2 or 3, wherein the confirmation method of the navigation requirement includes:

Determine the vehicle speed of the current vehicle within a predetermined time period based on the vehicle parameters;

Determine the congestion level based on the vehicle speed;

When the congestion level meets the preset congestion standard, the interaction requirement is determined to be a navigation requirement.
The method according to claim 2, wherein, when the interaction requirement includes a companionship requirement, generating interactive content based on the interaction requirement and the screening results of the traffic information includes:

Determine a safe driving section based on the target navigation path and corresponding road conditions in the traffic information, where the safe driving section is a road section with a road condition complexity lower than the corresponding complexity threshold;

Determine the driving time of the current vehicle on the safe driving section;

Using artificial intelligence-based content production technology AIGC, interactive content matching the driving time is generated.
The method according to claim 2, wherein, when the interaction requirement includes a point of interest recommendation requirement, generating interactive content based on the interaction requirement and the screening results of the traffic information includes:

Determine the point of interest type corresponding to the point of interest recommendation requirement;

According to the type of interest point, target interest points are selected from the candidate interest points included in the traffic information;

The interactive content is generated according to the target point of interest.
The method according to claim 2 or 6, wherein the method for determining the interest point recommendation requirements includes:

Determine the type of physiological state of the user according to the user information;

When the type of the physiological state is a predetermined type, the interaction requirement is determined to be an interest point recommendation requirement, and the predetermined type includes at least one of fatigue, hunger, internal urgency, and illness.
The method according to claim 2 or 6, wherein the method for determining the interest point recommendation requirements includes:

Determine the vehicle condition of the current vehicle according to the vehicle parameters;

When the vehicle condition reaches the fault standard, the interaction requirement is determined to be a point of interest recommendation requirement.
An intelligent interactive device, including:

The traffic information acquisition module is used to obtain corresponding traffic information based on the detected interaction requirements;

An interactive content generation module, configured to generate interactive content based on the interaction requirements and the screening results of the traffic information;

A digital human driving module is configured to generate driving parameters based on the interactive content, where the driving parameters include parameters used to drive the digital human in the interactive interface to broadcast interactive content.
The device according to claim 9, wherein the traffic information acquisition module includes:

An analysis submodule, used to analyze the obtained reference information to obtain an analysis result; the reference information includes at least one of user information and current vehicle driving information, and the 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;

The interaction requirement determination execution submodule is configured to determine that an interaction requirement is detected when the parsing result satisfies a predetermined condition; the interaction requirement includes at least one of a navigation requirement, a companionship requirement, or a point of interest recommendation requirement.
The device according to claim 10, wherein when the interaction requirements include navigation requirements, the interactive content generation module includes:

The target navigation path determination submodule is used to filter out the target navigation path that meets specified conditions from the traffic information according to the navigation requirements. The specified conditions are based on the driving mileage of the navigation path and the driving time of the navigation path. At least one thing is certain;

An interactive content generation execution submodule is used to generate the interactive content according to the target navigation path.
The device according to claim 10 or 11, wherein the interaction requirement determination execution submodule includes:

A vehicle speed condition determination unit, configured to determine the vehicle speed condition of the current vehicle within a predetermined time period based on the vehicle parameters;

A congestion level determination unit determines the congestion level based on the vehicle speed;

An interaction demand determination unit is configured to determine the interaction demand as a navigation demand when the congestion level meets a preset congestion standard.
The device according to claim 10, wherein when the interaction requirement includes a companionship requirement, the interactive content generation module includes:

A safe driving section determination submodule is used to determine a safe driving section based on the target navigation path and corresponding road conditions in the traffic information. The safe driving section is a road section where the complexity of the road conditions is lower than the corresponding complexity threshold;

A driving time determination submodule, used to determine the driving time of the current vehicle on the safe driving section;

The interactive content generation execution sub-module is used to generate interactive content that matches the driving time using AIGC, a content production technology based on artificial intelligence.
The device according to claim 10, wherein when the interaction requirement includes a point of interest recommendation requirement, the interactive content generation module includes:

Point of interest type determination sub-module, used to determine the type of interest point corresponding to the interest point recommendation requirement;

A target point of interest screening sub-module is used to screen out target points of interest from candidate interest points included in the traffic information according to the type of interest point;

An interactive content generation execution submodule is used to generate the interactive content according to the target point of interest.
The device according to claim 10 or 14, wherein the interaction requirement determination execution sub-module includes:

A type determination unit, configured to determine the type of the user's physiological state according to the user information;

An interaction demand determination unit, configured to determine that the interaction demand is a point of interest recommendation demand when the type of the physiological state is a predetermined type, and the predetermined type includes: at least one of fatigue, hunger, internal urgency, and illness. kind.
The device according to claim 10 or 14, wherein the interaction requirement determination execution sub-module includes:

A vehicle condition determination unit, configured to determine the vehicle condition of the current vehicle according to the vehicle parameters;

An interaction demand determination unit is configured to determine the interaction demand as a point of interest recommendation demand when the vehicle condition reaches a fault standard.
An electronic device including:

at least one processor; and

a memory communicatively connected to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can perform any one of claims 1 to 8 Methods.
A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 8.
A computer program product comprising a computer program/instructions, wherein the computer program/instructions, when executed by a processor, implement the steps of the method according to any one of claims 1 to 8.