A voice on-demand method, device and storage medium

Abstract

This application discloses a voice-activated playback method, device, and storage medium, relating to the field of voice interaction technology in smart cockpits. The method includes obtaining a playback command input by a user via voice, wherein the playback command includes a target entity name but does not include the media type corresponding to the target entity name; extracting the target entity name from the playback command; if the target entity name corresponds to multiple media types, determining a target media playback application based on a preset broadcast entity library, a preset mapping table, a historical behavior database, and the target entity name; wherein the broadcast entity library represents the correspondence between entity names and broadcast applications, the preset mapping table represents the correspondence between preset keywords in the entity name and media playback applications, and the media playback application is a preset playback application other than broadcast applications; and controlling the car cockpit system to execute a media resource playback operation corresponding to the target entity name based on the target media playback application.

Description

Technical Field

[0001] This application relates to the field of voice interaction technology in smart cockpits, and in particular to a voice-activated playback method, device, and storage medium. Background Technology

[0002] In smart cockpit voice interaction scenarios, users often use brief or vague commands to play media. The core problem with such commands lies in "entity type ambiguity," meaning that the target resource may exist simultaneously in multiple media domains such as music, video, audiobooks, and radio. Current related technical solutions have low domain accuracy, frequently resulting in playback results that do not meet user expectations. This not only affects the user experience but also forces the driver to make secondary manual corrections, increasing driving risks. Summary of the Invention

[0003] The embodiments of this application provide a voice-activated video-on-demand method, device, and storage medium, which can accurately identify which media playback application should execute the video-on-demand command when a user issues a vague video-on-demand command.

[0004] The summary section introduces a series of simplified concepts, which will be further explained in detail in the detailed description section. This summary section is not intended to limit the key and essential technical features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.

[0005] This application specifically includes the following aspects: Firstly, this application proposes a voice-on-demand method, including: Obtain the user's on-demand command input via voice, wherein the on-demand command contains the target entity name but does not contain the media type corresponding to the target entity name; The target entity name is extracted from the on-demand instruction. If the target entity name corresponds to multiple media types, the target media playback application is determined based on the preset broadcast entity library, the preset mapping table, the multiple types in the historical behavior database, and the target entity name. The broadcast entity library is used to represent the correspondence between entity names and broadcast applications, the preset mapping table is used to represent the correspondence between preset keywords in entity names and media playback applications, and the media playback application is a preset playback application other than broadcast applications. The vehicle cockpit system controls the media resource playback operation corresponding to the target entity name based on the target media playback application.

[0006] In one feasible implementation, determining the target media playback application based on a preset broadcast entity library, a preset mapping table, a historical behavior database, and the target entity name includes: The target entity name is matched with a preset broadcast entity library; if a match is found in the broadcast entity library, the broadcast application that matches the target entity name in the broadcast entity library is identified as the target media playback application. If the match with the broadcast entity library fails, the preset keywords in the target entity name are matched with the preset mapping table; if the match with the preset mapping table is successful, the media playback application that matches the preset keywords in the target entity name in the preset mapping table is identified as the target media playback application. If a match with the preset mapping table fails, the historical playback records associated with the target entity name are obtained based on the historical behavior database, and the target media playback application is determined based on the historical playback records.

[0007] In one feasible implementation, determining the target media playback application based on the historical playback records includes: If the target entity name in the historical playback record is associated with only one media playback application, then the associated media playback application is determined as the target media playback application; If the target entity name in the historical playback record is associated with multiple media playback applications, then one of the multiple media playback applications is selected as the target media playback application based on the most recent playback time or playback frequency.

[0008] In one feasible implementation, the method further includes: If no historical playback record associated with the target entity name is obtained based on the historical behavior database, then the media playback application corresponding to the target entity name is obtained based on the cloud media resource library; If there is only one type of media playback application corresponding to the target entity name, then the corresponding media playback application is determined as the target media playback application. If there is more than one media playback application corresponding to the target entity name, then based on the preset priority rules, the media playback application with the higher priority is determined as the target media playback application.

[0009] In one feasible implementation, the method further includes: If multiple target media playback applications are identified based on the priority rules, then query whether the name of the target entity is located in the preset popular resource list; If it is located in the popular resource list, then the media playback application corresponding to the popular resource list will be identified as the target media playback application; If it is not on the list of popular resources, the target media playback application is determined based on the real-time operating status of the car cockpit system.

[0010] In one feasible implementation, determining the target media playback application based on the real-time operating status of the vehicle cockpit system includes: Detect whether there is a running media playback application on the front end of the vehicle's infotainment system. If there is a running media playback application, then the running media playback application is identified as the target media playback application; If no media playback application is running, then check if there is a media playback application in the background of the vehicle's infotainment system that is playing audio. If a media playback application is in audio playback mode, then the media playback application in audio playback mode is identified as the target media playback application.

[0011] In one feasible implementation, the method further includes: If multiple target media playback applications are identified based on the real-time operating status of the vehicle cockpit system, the media playback application with the highest priority is selected as the target media playback application according to the preset system default priority; wherein, the system default priority is that the priority of music playback applications is higher than that of video playback applications, and the priority of video playback applications is higher than that of audiobook playback applications.

[0012] In one feasible implementation, after the vehicle cockpit control system executes a media resource playback operation corresponding to the target entity name based on the target media playback application, the system further includes: The system outputs a prompt message on the vehicle's infotainment interface, which indicates the media playback application to which the currently playing content belongs. If a media switching command is received from the user based on the prompt information, the system controls the car's cockpit system to switch to the media playback application specified by the user for replay, and saves this switching behavior to the user's historical behavior database.

[0013] Secondly, this application also proposes an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program stored in the memory to implement the steps of the voice-on-demand method as described in any of the first aspects above.

[0014] Thirdly, this application also proposes a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of any of the voice-on-demand methods of the first aspect.

[0015] This application proposes a voice-activated playback method that, upon receiving an ambiguous voice playback command, does not rely on a single data source or rule for arbitrary selection. Instead, it sequentially utilizes multiple layers of data, including a pre-set broadcast entity library, a pre-set mapping table, and a user historical behavior database, to collaboratively determine the target media playback application. This significantly increases the probability of the initial playback matching the user's true intent while maintaining decision-making efficiency. This not only significantly enhances the accuracy and user satisfaction of voice interaction but also greatly reduces the manual operations required to correct playback errors while driving through a highly automated decision-making process, effectively reducing the risk of driver distraction and achieving a comprehensive improvement in the intelligence, safety, and user experience of in-vehicle voice interaction.

[0016] This application discloses a voice-on-demand method, device, and storage medium. Other advantages, objectives, and features of this application will be partly apparent from the following description and partly understood by those skilled in the art through study and practice of this application. Attached Figure Description

[0017] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit this specification. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 A flowchart illustrating a voice-on-demand method provided in an embodiment of this application; Figure 2 A schematic diagram of the functional modules of a voice-on-demand system provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a voice-on-demand device provided in an embodiment of this application. Detailed Implementation

[0018] To better understand the technical solutions provided in the embodiments of this specification, the technical solutions of the embodiments of this specification will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of this specification and the specific features in the embodiments are detailed descriptions of the technical solutions of the embodiments of this specification, rather than limitations on the technical solutions of this specification. In the absence of conflict, the embodiments of this specification and the technical features in the embodiments can be combined with each other.

[0019] In this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, without necessarily requiring or implying any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. The term "two or more" includes two or more cases.

[0020] Please see Figure 1 This is a flowchart illustrating a voice-on-demand method provided in an embodiment of this application, which may specifically include: S110. Obtain the on-demand command input by the user via voice, wherein the on-demand command contains the target entity name but does not contain the media type corresponding to the target entity name.

[0021] Specifically, inside the smart cockpit, the user issues a vague request via voice. The car's cockpit system receives the request through the in-vehicle microphone, converts it into text using the automatic speech recognition module, and then uses a natural language understanding module to parse out the core action and target of the request. At this stage, the car's cockpit system makes a crucial judgment: whether the request is "vague".

[0022] It's important to clarify that "ambiguity" doesn't refer to unclear speech, but rather that the "operation object" (i.e., the target entity name) of the playback command itself doesn't contain a qualifier that directly and accurately identifies its corresponding media type. For example, "Play Z TV series" is relatively clear because "TV series" is a media type qualifier. However, "Play Z" is ambiguous because the name "Z" can refer to works of various media types, such as novels, TV series, movies, radio dramas, and audiobooks. The car's cockpit system only triggers the subsequent decision-making process after recognizing this "ambiguity."

[0023] S120. Extract the target entity name from the on-demand instruction. If the target entity name corresponds to multiple media types, determine the target media playback application based on the preset broadcast entity library, preset mapping table, multiple types in the historical behavior database, and the target entity name. The broadcast entity library is used to represent the correspondence between entity names and broadcast applications. The preset mapping table is used to represent the correspondence between preset keywords in entity names and media playback applications. The media playback application is a preset playback application other than the broadcast application.

[0024] Understandably, since the on-demand instruction does not include the media type corresponding to the target entity name, the target entity name may correspond to one media type or multiple media types. Different media types correspond to different media playback applications. Therefore, for the case where the target entity name corresponds to multiple media types, it is necessary to determine the most suitable target media playback application.

[0025] Specifically, once the user's input request is determined to be ambiguous, the vehicle's cockpit system employs a multi-level, progressive decision-making process based on a pre-defined broadcast entity library, a pre-defined mapping table, and a historical behavior database. It prioritizes the fastest and most deterministic local rules (i.e., the pre-defined broadcast entity library), then utilizes general rules (i.e., the pre-defined mapping table), and finally uses the personalized user data that needs to be queried (i.e., the historical behavior database). This decision-making process ensures that, in most cases, the vehicle's cockpit system can make the most likely correct choice with maximum efficiency.

[0026] S130, Control the vehicle cockpit system to execute media resource playback operations corresponding to the target entity name based on the target media playback application.

[0027] Specifically, once a unique "target media playback application" is identified, the vehicle's cockpit system sends a command to its media control module. This command contains two parts: "which application to play in" (i.e., the target media playback application) and "what to play" (i.e., the target entity name). Subsequently, the vehicle's cockpit system automatically launches the application and invokes its search and playback functions, achieving fully automated operation.

[0028] For example, user A says "Play Y" in the car. The car's cockpit system recognizes the action "play" and the entity name "Y". It finds that the request doesn't specify whether it's a movie or a song, classifying it as a vague instruction. It initiates a multi-level decision-making process: Checking the preset broadcast entity library: No match (this is not a radio program). Checking the preset mapping table: The entity name does not contain preset keywords such as "MV" or "concert", so no match. Checking user A's historical behavior database: It finds that A played song Y on an audio application last week. Based on this history, the car's cockpit system determines the target media playback application is an audio application and automatically launches the audio application to play song Y.

[0029] In some examples, the target media playback application is determined based on a pre-defined broadcast entity library, a pre-defined mapping table, multiple entities in a historical behavior database, and the target entity name, including: Match the target entity name with the preset broadcast entity library; if a match is found in the broadcast entity library, the broadcast application that matches the target entity name in the broadcast entity library is identified as the target media playback application. If a match with the broadcast entity library fails, the preset keywords in the target entity name are matched with the preset mapping table; if a match with the preset mapping table is successful, the media playback application that matches the preset keywords in the target entity name in the preset mapping table is identified as the target media playback application. If a match with the preset mapping table fails, the historical playback records associated with the target entity name are retrieved from the historical behavior database, and the target media playback application is determined based on the historical playback records.

[0030] Specifically, the number of broadcasts from common in-vehicle broadcast applications is not large. Given that the in-vehicle broadcast entity library is relatively fixed and limited in size, matching the target entity name with the preset broadcast entity library is used as the initial decision. This can resolve a portion of the requests with minimal computational overhead, thereby achieving efficient traffic distribution. If a match is found, the request is directly routed to the broadcast application and playback is executed; otherwise, a decision based on a preset mapping table is initiated.

[0031] Matching target entity names with a pre-defined mapping table is a quick judgment based on common keywords and experience. The automotive cockpit system maintains a pre-defined mapping table of "pre-defined keywords - media playback applications." For example, detecting "Season X / Part X" in an entity name maps it to a video app, and "DJ version / chorus version" maps it to a music app. This level of decision-making utilizes the "clues" that may be inherent in the entity name; it's a heuristic search, fast but may fail due to name ambiguity. For example, although the entity name "Music XX" contains the keyword "music", it could be a classic music film (video), a song album from a film (music), or a documentary about the behind-the-scenes production of a film (video) or an audio interpretation (audio); although the entity name "Song XX" contains the keyword "song", it could be a film (video), or the soundtrack or theme song of that film (music); although the entity name "Play XX Radio" contains the keyword "radio", it could be an internet radio station (broadcast), or the name of a film (video); although the entity name "Play XX Story" contains the keyword "story", it could be a children's bedtime story (audio), or a symphony or light music album of the same name (music), or an animated film or film (video).

[0032] If neither of the above two quick paths can determine a solution, the user's historical behavior database is immediately queried. This database records the user's media collection list, historical playback records (including playback count and most recent playback time), etc. By examining the user's historical playback records, it can be determined which applications the user has previously played the same entity in, thereby matching a playback scheme that matches the user's personality.

[0033] In some examples, the target media playback application is determined based on historical playback records, including: If the target entity name in the historical playback record is associated with only one media playback application, then the associated media playback application will be identified as the target media playback application. If the target entity name is associated with multiple media playback applications in the historical playback records, then one of the multiple media playback applications will be selected as the target media playback application based on the most recent playback time or playback frequency.

[0034] Specifically, if the history shows that a user has only played the target entity name in one media player application, then the user's preference is clear and unambiguous, and should be directly followed, which is the ideal situation.

[0035] However, when a user has played content from multiple media playback applications with the same target entity name in their playback history (e.g., having listened to a radio drama X in an audio application and watched a TV series X in a video application), the historical record is insufficient to make a single selection. In this case, the system selects one of the multiple media playback applications as the target media playback application based on the most recent playback time or playback frequency.

[0036] It's important to note that prioritizing recent playback time is based on the assumption of "continuity of recent user interests." If a user watched TV series X on a video app yesterday, but last listened to its audio drama version a month ago, the user is far more likely to want to watch the TV series now than listen to the audio drama version. Prioritizing playback frequency, on the other hand, is based on the assumption of "stability of long-term user habits." If a user plays "X" a total of 100 times, 95 times on an audiobook app and 5 times on a video app, then even if the user most recently watched a video, their long-established strong habit still indicates that an audiobook is the more likely choice. The car's cockpit system can be configured to prioritize either rule or to evaluate both comprehensively.

[0037] For example, in user B's history, the entries for "X" are: (Audiobook playback application, audiobook) Play count: 50 times, Last played: 3 days ago. (Video application, TV series) Play count: 10 times, Last played: 1 hour ago. If the most recent playback time priority rule is used: the car cockpit system will select the "Video application" (video) that was played 1 hour ago. If the playback frequency priority rule is used: the car cockpit system will select the "Audiobook playback application" (audiobook) that has been played 50 times.

[0038] By analyzing users' historical behavior (i.e., the time and frequency of media playback app usage), the vague "what users might like" is transformed into precise, calculable decision-making criteria. Simultaneously, it adapts to different user behavior patterns, accommodating different user types. For users with fluctuating interests, the "recently played" rule is better able to capture their current intent; for users with stable habits, the "playback frequency" rule better reflects their long-term preferences. Decisions based on explicit rules are easier for users to understand and accept; even if occasional errors occur, users understand the reasons.

[0039] In some examples, if no historical playback records associated with the target entity name are obtained based on the historical behavior database, the media playback application corresponding to the target entity name is obtained based on the cloud media resource library; If there is only one type of media playback application corresponding to the target entity name, then the corresponding media playback application is identified as the target media playback application. If there is more than one media playback application corresponding to the target entity name, the media playback application with the higher priority will be identified as the target media playback application based on the preset priority rules.

[0040] Specifically, when a user lacks relevant historical behavior data (new user, or access to entirely new content), the system queries the cloud-based media resource library. This cloud-based media resource library is a comprehensive media database maintained in the cloud. It contains data from various sources, including company data procurement, web scraping, and online user entity data. It maintains a unified database containing all entity types, entity resource names, and corresponding parameters. This unified database aggregates media resource metadata (resource name, type, popularity, etc.) from various channels.

[0041] If the "target entity name" is searched in the cloud media resource library and found to correspond to only one media type across the entire network, then the media playback application of that type is directly used. This leverages the global uniqueness of information.

[0042] If the query finds that the name corresponds to multiple media types (e.g., "X" can be used for multiple types of conflict such as video, audiobook, and music), then the preset priority rule is activated. This priority rule is predefined and may be based on the mainstream perception of the target entity name across the entire network (for example, for "X", the influence of its film and television works is much greater than that of its fan music, so the priority order is video > audiobook > music).

[0043] For example, a new user, C, uses the car's infotainment system for the first time and says, "Play X." A query of the historical behavior database shows no record. A query of the cloud-based media resource library shows that X primarily exists as a "movie" (video), but also as a "movie soundtrack" (music) and a "sci-fi interpretation podcast" (audio). In the preset priority rules, X is set as a currently popular sci-fi movie, therefore its "video (movie)" priority is marked as the highest. At this point, the car's cockpit system determines the target media playback application as a video application and plays movie X.

[0044] In some examples, if multiple target media playback applications are identified based on priority rules, the query will check whether the target entity name is in the preset popular resource list; If it is on the list of popular resources, then the media playback application corresponding to the list of popular resources will be identified as the target media playback application; If it is not on the list of popular resources, the target media playback application will be determined based on the real-time operating status of the car's cockpit system.

[0045] Specifically, if uncertainty persists after all the above steps (uncertainty refers to the inability to pinpoint the unique media playback application type corresponding to the target entity name through all the above decision-making processes; for example, in the results, video and music have equal priority: video = music; or: video = music > audio; or video = audio);), then the car cockpit system accesses real-time popular resource lists for various media playback applications, such as "Hot Drama Chart," "Rising Chart," and "New Song Chart." If the target entity name appears on a chart, it indicates that the target entity name is currently receiving widespread attention in that media format. For example, "X" may have both music and game videos, but if it suddenly surges to the "Hot Music Chart," it strongly suggests that the user currently wants to listen to a song.

[0046] If the popular resource list cannot provide a unique answer (or the target entity name is not on the popular resource list), then the real-time runtime status of the car cockpit system is detected.

[0047] For example, if the target entity name "W Concert" has the same priority for video and music types in the cloud media resource library, then the popular resource list is checked. It is found that the target entity name is in the TOP 10 of the "Popular Live Music List". The car cockpit system determines that since this content is becoming popular as a "live music video", users are more likely to want to watch the video; therefore, the target media playback application is set to a video application.

[0048] In some examples, the target media playback application is determined based on the real-time operating status of the vehicle's cockpit system, including: Check if there are any running media playback applications on the vehicle's infotainment system's front-end. If a media playback application is currently running, then the running media playback application will be identified as the target media playback application. If no media playback application is running, check if there is a media playback application playing audio in the background of the vehicle's infotainment system. If a media playback application is in audio playback mode, then the media playback application in audio playback mode will be identified as the target media playback application.

[0049] Specifically, if a user is using a media playback application on the in-vehicle infotainment system (e.g., browsing the menu page of a video application) and issues a vague play request, the car's cockpit system tends to interpret this as the user wanting to continue operating within the current application. Searching and playing directly within the current application aligns with the continuity of the workflow, eliminates the need to switch application interfaces, and provides the smoothest interaction.

[0050] If there's no media player app in the foreground, but one is playing audio in the background (e.g., an audio app playing a song in the background), and the user issues a vague request, the car's cockpit system tends to interpret it as the user wanting to interact with the currently playing media app or search for related content. Continuing the current audio playback provides the most natural user experience.

[0051] For example, user D is listening to an audiobook using an audiobook player on the car's infotainment system. He says, "Play X." The car's cockpit system detects that the audiobook player is currently running in the foreground. It then determines that the target media player is the currently foreground audiobook player, searches for and plays audiobook X within that app, and the user interface seamlessly transitions to that mode.

[0052] In some examples, if multiple target media playback applications are identified based on the real-time operating status of the vehicle's cockpit system, the media playback application with the highest priority is selected as the target media playback application according to the preset system default priority. The system default priority is that music playback applications have a higher priority than video playback applications, and video playback applications have a higher priority than audiobook playback applications.

[0053] Specifically, if, after all the aforementioned refined decision-making processes, the vehicle's cockpit system still cannot make a single choice (for example, there is a music application in the front-end of the infotainment system and a video application playing audio in the background, and the target entity exists in both), in order to prevent the process from "freezing" or making a random selection, the media playback application with the highest priority is selected as the target media playback application based on the preset system default priority.

[0054] It should be noted that the "music > video > audio" priority set in this embodiment is based on in-depth consideration of typical in-vehicle usage scenarios. Music has the highest priority: listening to music is the most frequent and mainstream need in driving scenarios. Music is usually used as background noise while driving, requiring no visual input, and thus has the highest safety. Video is the next highest priority: video consumption usually occurs when the vehicle is stationary (such as charging or waiting for someone), and playing videos while driving poses safety risks, but audio components (such as movie soundtracks and documentary narrations) can still be listened to. Audiobooks are the next lowest priority: although they are also in audio format, their consumption requires a higher level of cognitive focus, may not be suitable for complex road conditions, and the user base is relatively smaller than the first two.

[0055] Example (this is an extreme case): User E says, "Play 'Classic Masterpieces'." This title has a large number of entries in both the music app (music) and video app (video). Current vehicle system status: The foreground is the navigation map, and the background has the music app (paused) and the video app (last played music / video). There are no historical records, the media playback app types in the cloud media resource library conflict, it's not on the popular resource list, there's no media playback app in the foreground, but multiple media playback apps in the background. Therefore, based on the preset system default priority in the car's cockpit system: music > video, the higher-priority "music app" will be selected as the target media playback app for playback.

[0056] In some examples, after controlling the vehicle's cockpit system to perform a media resource playback operation corresponding to the target entity name based on the target media playback application, it also includes: The system displays a prompt message on the vehicle's infotainment interface, indicating the media playback application to which the currently playing content belongs. If a media switching command is received from the user based on the prompt information, the system controls the car's cockpit system to switch to the media playback application specified by the user for replay, and saves this switching behavior to the user's historical behavior database.

[0057] Specifically, when media playback begins, a small text message or icon on the vehicle's infotainment screen (e.g., "Playing through music app A") informs the user of the current decision. If the playback does not meet the user's expectations, the user can immediately switch to the correct media playback app with a very simple voice command (e.g., "Switch to video version") or a single click. This switching cost is far lower than the entire process of manually exiting, searching for, opening another media playback app, and then searching again.

[0058] Simultaneously, the car's cockpit system records the user's historical behavior database the action of "the user actively switched to media playback application B after the decision was made to use media playback application A for the target entity name XXX." This means that the car's cockpit system can learn from its own mistakes, thereby providing more accurate results for subsequent operations.

[0059] For example, user F says, "Play XX music." The car's cockpit system, based on some rules (such as a preset mapping table), selects "Music App A" to play its soundtrack. The infotainment screen displays "Playing XX music through Music App A." However, user F actually wants to watch a music movie, so they say, "Switch to Video App A." The car's cockpit system immediately switches to Video App A to play the music movie video, and simultaneously generates a record in the background: "User F, for the entity name 'XX music,' after recommending 'Music App A,' ultimately confirmed the selection of 'Video App A.'"

[0060] Through the aforementioned error correction mechanism, even if a decision is flawed, it can be quickly corrected through a minimalist interaction, ensuring a minimum level of user experience for each instance and minimizing potential negative experiences. Simultaneously, each error correction allows the car's cockpit system to better understand the user, enabling decision accuracy to continuously improve over time, achieving true intelligence.

[0061] Furthermore, this application also proposes a voice-on-demand system for implementing any of the above-described voice-on-demand methods, specifically as follows: Figure 2 The diagram shown is a functional module schematic of a voice-on-demand system proposed in this application. The system includes: The voice processing module 21 is used to obtain the on-demand command input by the user via voice, wherein the on-demand command contains the name of the target entity but does not contain the media playback application type of the target entity. The decision arbitration module 22 is used to extract the target entity name from the on-demand instruction. If the target entity name corresponds to multiple media playback applications, the target media playback application is determined based on the preset broadcast entity library, the preset mapping table, the multiple options in the historical behavior database, and the target entity name. The broadcast entity library is used to represent the correspondence between entity names and broadcast applications, the preset mapping table is used to represent the correspondence between entity names and media playback applications, and the media playback application is a preset playback application other than the broadcast application. The media control module 23 is used to control the vehicle cockpit system to perform media resource playback operations corresponding to the target entity name based on the target media playback application.

[0062] It should be noted that the above embodiments are merely best examples and are not intended to limit the implementation of this application.

[0063] Furthermore, such as Figure 3 As shown, this application embodiment also provides an electronic device 300, including a processor 310, a memory 320, and a computer program 321 stored in the memory 320 and executable on the processor. When the processor 310 executes the computer program 321, it implements the steps of any of the above-described voice-on-demand methods.

[0064] Since the electronic device described in this embodiment is a device used to implement a voice-on-demand method in the embodiments of this application, those skilled in the art can understand the specific implementation method and various variations of the electronic device in this embodiment based on the method described in the embodiments of this application. Therefore, how the electronic device implements the method in the embodiments of this application will not be described in detail here. Any device used by those skilled in the art to implement the method in the embodiments of this application falls within the scope of protection of this application.

[0065] In practical implementation, when the computer program 321 is executed by the processor, it can achieve the following: Figure 1 Any of the corresponding implementation methods in the embodiments.

[0066] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0067] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-readable program code.

[0068] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0069] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0070] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0071] This application also provides a computer program product, which includes computer software instructions that, when executed on a processing device, cause the processing device to perform the voice-on-demand method.

[0072] A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0073] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0074] In the several embodiments provided in this application, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0075] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0076] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0077] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0078] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

[0079] Although preferred embodiments have been described in this specification, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this specification.

[0080] Obviously, those skilled in the art can make various modifications and variations to this specification without departing from its spirit and scope. Therefore, if such modifications and variations fall within the scope of the claims and their equivalents, this specification is also intended to include such modifications and variations.

Claims

1. A voice-activated playback method, characterized in that, include: Obtain the user's on-demand command input via voice, wherein the on-demand command contains the target entity name but does not contain the media type corresponding to the target entity name; The target entity name is extracted from the on-demand instruction. If the target entity name corresponds to multiple media types, the target media playback application is determined based on the preset broadcast entity library, the preset mapping table, the multiple types in the historical behavior database, and the target entity name. The broadcast entity library is used to represent the correspondence between entity names and broadcast applications, the preset mapping table is used to represent the correspondence between preset keywords in entity names and media playback applications, and the media playback application is a preset playback application other than broadcast applications. The vehicle cockpit system controls the media resource playback operation corresponding to the target entity name based on the target media playback application.

2. The method according to claim 1, characterized in that, The process of determining the target media playback application based on a preset broadcast entity library, a preset mapping table, a historical behavior database, and the target entity name includes: The target entity name is matched with a preset broadcast entity library; if a match is found in the broadcast entity library, the broadcast application that matches the target entity name in the broadcast entity library is identified as the target media playback application. If the match with the broadcast entity library fails, the preset keywords in the target entity name are matched with the preset mapping table; if the match with the preset mapping table is successful, the media playback application that matches the preset keywords in the target entity name in the preset mapping table is identified as the target media playback application. If a match with the preset mapping table fails, the historical playback records associated with the target entity name are obtained based on the historical behavior database, and the target media playback application is determined based on the historical playback records.

3. The method according to claim 2, characterized in that, The step of determining the target media playback application based on the historical playback records includes: If the target entity name in the historical playback record is associated with only one media playback application, then the associated media playback application is determined as the target media playback application; If the target entity name in the historical playback record is associated with multiple media playback applications, then one of the multiple media playback applications is selected as the target media playback application based on the most recent playback time or playback frequency.

4. The method according to claim 2, characterized in that, Also includes: If no historical playback record associated with the target entity name is obtained based on the historical behavior database, then the media playback application corresponding to the target entity name is obtained based on the cloud media resource library; If there is only one type of media playback application corresponding to the target entity name, then the corresponding media playback application is determined as the target media playback application. If there is more than one media playback application corresponding to the target entity name, then based on the preset priority rules, the media playback application with the higher priority is determined as the target media playback application.

5. The method according to claim 4, characterized in that, Also includes: If multiple target media playback applications are identified based on the priority rules, then query whether the name of the target entity is located in the preset popular resource list; If it is located in the popular resource list, then the media playback application corresponding to the popular resource list will be identified as the target media playback application; If it is not on the list of popular resources, the target media playback application is determined based on the real-time operating status of the car cockpit system.

6. The method according to claim 5, characterized in that, The determination of the target media playback application based on the real-time operating status of the vehicle cockpit system includes: Detect whether there is a running media playback application on the front end of the vehicle's infotainment system. If there is a running media playback application, then the running media playback application is identified as the target media playback application; If no media playback application is running, then check if there is a media playback application in the background of the vehicle's infotainment system that is playing audio. If a media playback application is in audio playback mode, then the media playback application in audio playback mode is identified as the target media playback application.

7. The method according to claim 6, characterized in that, Also includes: If multiple target media playback applications are identified based on the real-time operating status of the vehicle cockpit system, the media playback application with the highest priority is selected as the target media playback application according to the preset system default priority; wherein, the system default priority is that the priority of music playback applications is higher than that of video playback applications, and the priority of video playback applications is higher than that of audiobook playback applications.

8. The method according to claim 1, characterized in that, After the vehicle cockpit control system executes a media resource playback operation corresponding to the target entity name based on the target media playback application, it further includes: The system outputs a prompt message on the vehicle's infotainment interface, which indicates the media playback application to which the currently playing content belongs. If a media switching command is received from the user based on the prompt information, the system controls the car's cockpit system to switch to the media playback application specified by the user for replay, and saves this switching behavior to the user's historical behavior database.

9. An electronic device, comprising: The memory and processor are characterized in that the processor, when executing a computer program stored in the memory, implements the steps of the voice-on-demand method as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the voice-on-demand method as described in any one of claims 1 to 8.

Images