WO2025035983A1 - 处理请求的方法、装置、设备和存储介质 - Google Patents
处理请求的方法、装置、设备和存储介质 Download PDFInfo
- Publication number
- WO2025035983A1 WO2025035983A1 PCT/CN2024/102716 CN2024102716W WO2025035983A1 WO 2025035983 A1 WO2025035983 A1 WO 2025035983A1 CN 2024102716 W CN2024102716 W CN 2024102716W WO 2025035983 A1 WO2025035983 A1 WO 2025035983A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- user request
- model
- music
- response
- intent
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/16—Sound input; Sound output
Definitions
- Exemplary implementations of the present disclosure generally relate to the field of computers, and in particular, to methods, devices, apparatuses, and computer-readable storage media for processing requests.
- conversational applications as a highly interactive application, have gradually gained popularity among users. Users can interact with virtual objects through conversational applications to obtain various services, such as music-related services.
- a method for processing a request includes: obtaining a user request received in a conversation between a user and a virtual object, the virtual object being associated with a music service; processing the user request using a first model to determine whether a target intent corresponding to the user request matches a set of preset intents, the set of preset intents including a music playback intent or a playback control intent; and in response to the target intent not matching the set of preset intents, providing the user request to a second model to generate a first response to the user request, the second model being larger in size than the first model.
- the speed of processing music-related requests can be increased so that the request can be executed more efficiently.
- a device for processing a request comprises: a request acquisition module configured to acquire a user request received in a session between a user and a virtual object, the virtual object being associated with a music service; a first processing module configured to process the user request using a first model to determine whether a target intent corresponding to the user request matches a set of preset intents, the set of preset intents including a music playback intent; Figure or playback control intent; and a providing module, configured to provide the user request to a second model in response to the target intent not matching the set of preset intents to generate a first response to the user request, the second model being larger in size than the first model.
- an electronic device in a third aspect of the present disclosure, includes: at least one processing unit; and at least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit, and when the instructions are executed by the at least one processing unit, the electronic device executes the method according to the first aspect of the present disclosure.
- a computer-readable storage medium on which a computer program is stored.
- the processor implements the method according to the first aspect of the present disclosure.
- a computer program product comprising a computer program, wherein when the computer program is executed by a processor, the method according to the first aspect of the present disclosure is implemented.
- FIG1 is a schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented.
- FIG2 is a schematic diagram showing a process of processing a request according to some embodiments of the present disclosure
- 3A and 3B illustrate example interaction interfaces according to some embodiments of the present disclosure
- FIG4 is a schematic diagram showing a process of processing a request according to some embodiments of the present disclosure.
- FIG5 shows a schematic structural block diagram of an apparatus for processing a request according to some embodiments of the present disclosure.
- FIG6 illustrates a block diagram of an electronic device in which one or more embodiments of the present disclosure may be implemented.
- executing a step “in response to A” does not mean executing the step immediately after “A” but may include one or more intermediate steps.
- a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information, so that the user can independently choose whether to provide personal information to software or hardware such as electronic devices, applications, servers or storage media that execute the operations of the technical solution of the present disclosure based on the prompt message.
- the method of sending prompt information to the user through an automatic request may be, for example, a pop-up window, in which the prompt information may be presented in text form.
- the pop-up window may also carry a selection control for the user to choose "agree” or "disagree” to provide personal information to the electronic device.
- model can learn the association between the corresponding input and output from the training data, so that after the training is completed, the corresponding output can be generated for a given input.
- the generation of the model can be based on machine learning technology.
- Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs by using multi-layer processing units.
- a neural network model is an example of a model based on deep learning.
- model may also be referred to as “machine learning model”, “learning model”, “machine learning network” or “learning network”, and these terms are used interchangeably in this article.
- a virtual object can be a virtual processing entity created based on configuration information, which can be implemented based on a machine learning model, for example.
- a virtual object can also be referred to as a virtual entity, examples of which can include a robot program (bot), an agent (agent), etc.
- conversational applications have gradually gained popularity among users. Users can interact with virtual objects through conversational applications to obtain various services, such as music-related services.
- services such as music-related services.
- the response time for processing user requests often exceeds the user's expected time, which seriously affects the user's satisfaction with music services.
- a method, apparatus, device and storage medium for request processing includes: obtaining a user request received in a conversation between a user and a virtual object, the virtual object being associated with a music service; processing the user request using a first model to determine whether a target intent corresponding to the user request matches a set of preset intents, the set of preset intents including a music playback intent or a playback control intent; and in response to the target intent not matching the set of preset intents, providing the user request to a second model to generate a first response to the user request, the second model being larger in scale than the first model.
- the embodiments of the present disclosure may consider determining the processing for the user request based on the target intent corresponding to the user request, thereby being able to significantly improve the response speed for the user request.
- FIG. 1 shows a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented.
- an application 120 is installed in a terminal device 110.
- a user 140 can interact with the application 120 via the terminal device 110 and/or its attached devices.
- the application 120 can be any suitable application that supports interaction with a virtual object.
- the terminal device 110 may present an interface 150 of the application 120.
- the interface 150 may include various interfaces that the application 120 may provide, such as a conversation interface with a virtual object.
- the terminal device 110 communicates with the electronic device 130 to provide services (e.g., music services) for the application 120.
- the terminal device 110 may be any type of mobile terminal, fixed terminal, or portable terminal, including a mobile phone, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a personal communication system (PCS) device, a personal navigation device, a personal digital assistant (PDA), an audio/video player, a digital camera/camcorder, a positioning device, a television receiver, a radio receiver, an e-book device, a gaming device, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof.
- PCS personal communication system
- PDA personal digital assistant
- the terminal device 110 may also support any type of interface for the user (such as a "wearable" circuit, etc.).
- the electronic device 130 may be a computing system/server of various types that can provide computing power, including but not limited to a mainframe, an edge computing node, a computing device in a cloud environment, and the like.
- the terminal device 110 can cooperate with the electronic device 130 to provide a specific service for the user 140.
- the example process is described with the electronic device 130 as the execution subject. It should be understood that in other embodiments, the described example process can be implemented by the terminal device 110 and the electronic device 130 in cooperation. For the purpose of brevity only, the same or similar content will not be repeated.
- FIG2 shows an example process 200 for processing a request according to some embodiments of the present disclosure.
- the process 200 is described below with reference to FIG1 .
- the process may be implemented at least in part at the terminal device 110 shown in FIG1 .
- the process will be described with reference to the environment 100 of FIG1 .
- the terminal device 110 may obtain a user request 201 from a conversation between the user 140 and the virtual object.
- the terminal device 110 is installed with an application 120 that may support interaction with the virtual object.
- the interface 150 of the terminal device 110 may, for example, present a conversation interface with the virtual object.
- the virtual object is associated with a music service.
- the terminal device 110 can process the user request 201 using the first model 210 to determine whether the target intent corresponding to the user request 201 matches a set of preset intents.
- the preset intent may include, for example, a music playback intent or a playback control intent.
- the terminal device 110 determines that the target intent corresponding to the user request 201 matches the music playback intent or the playback control intent, an operation matching the target intent may be performed.
- the terminal device 110 may utilize the first model 210 to extract and classify ( 211 ) a set of parameter values for a set of preset query parameters involved in the user request 201 to determine the target intent corresponding to the user request 201 .
- the preset query parameters 202 may include song parameters, performer parameters, album parameters, scene parameters and/or additional description information, etc.
- the terminal device 110 determines that the user request 201 involves song parameters, performer parameters, and album parameters using the first model 210, the terminal device 110 can determine that the user request 201 corresponds to a music playback intention.
- the terminal device 110 determines that the user request 201 is "play songs sung by XXX" or "play XX songs" using the first model 210, the terminal device 110 can determine that the user request 201 corresponds to the explicit music playback intention 203. Next, the terminal device 110 can use the music service module 230 to implement the corresponding music search operation (231).
- the terminal device 110 can determine that the user request 201 corresponds to the explicit and ambiguous music playback intention 204. Next, the terminal device 110 can use the music service module 230 to implement the corresponding music recommendation operation (232).
- the terminal device 110 may also identify the playback control intention 205 from the user request 201. For example, if the terminal device 110 determines using the first model 210 that the user request 201 involves playback control intentions such as "pause playback”, “stop playback”, “play next song”, “play previous song”, etc., then it can be determined that the user request 201 corresponds to the playback control intention 205. Next, the terminal device 110 can perform the corresponding playback control operation (220).
- the terminal device 110 determines using the first model 210 that the target intent corresponding to the user request 201 does not match a set of preset intents, that is, the target intent satisfies neither the music playback intent nor the playback control intent, then as shown in FIG2 , the terminal device 110 provides the user request 201 to the second model 240.
- the second model 240 then processes (241) the user request 201 to output a user response 206.
- the second model 240 has a larger scale than the first model 210. This can be understood as, compared to the first model 210, the second model 240 involves a more complex algorithm and may take longer to generate a user response.
- the user request involving music playback intention or playback control intention determined by the first model 210 can be exempted from processing by the second model 240, thereby significantly speeding up the speed and efficiency of processing user requests.
- the terminal device 110 can use the first model 210 to extract and classify (211) a set of parameter values for a set of preset query parameters involved in the user request 201 to determine the target intent corresponding to the user request 201.
- the preset query parameter 202 may include additional description information.
- the terminal device 110 determines that the user request 201 involves additional descriptive information using the first model 210
- the user request is provided to the second model 240. For example, if the terminal device 110 determines that the user request 201 includes "play XX TV" using the first model 210, If the user request 201 is selected as the original soundtrack in the movie, it can be determined that "XX movie" corresponds to the additional description information because it does not involve any of the song parameters, performer parameters, album parameters, and scene parameters. In this case, the terminal device 110 provides the user request 201 to the second model 240. The second model 240 then processes (241) the user request 201 (e.g., the additional description information involved therein) to output a user response 206.
- the second model 240 may include a language model.
- the conversation window of the conversation between the user 140 and the virtual object may display a music playing component.
- the user response 206 output by the second model 240 is used to control the music playing component to execute the corresponding instruction.
- Figures 3A and 3B show example interactive interfaces according to some embodiments of the present disclosure.
- the interfaces 300A and 300B shown in Figures 3A and 3B may be presented by the terminal device 110.
- the interfaces 300A and 300B shown in Figures 3A and 3B are described below in conjunction with Figures 1 and 2.
- the interactive interfaces shown in Figures 3A to 3B are only examples, and various designs may actually exist.
- the various graphical elements and/or controls in the interactive interface may have different arrangements and different visual representations, one or more elements and/or controls therein may be omitted or replaced, and one or more other elements and/or controls may also exist.
- any appropriate content may be included in the user interface. The scope of the present disclosure is not limited in this respect.
- the user can switch and jump the interactive interface by activating the control/entry in each interactive interface or performing a predetermined operation in the interactive interface.
- the logic of switching and jumping the interactive interface can be set arbitrarily. For example, in an example embodiment, the user jumps from the first interactive interface to the second interactive interface by activating a control. In other embodiments, the user can jump from the first interactive interface to the third interactive interface by activating another control.
- the present disclosure is not limited in this respect. It should also be understood that although multiple interactive interfaces can be switched, the switching and jumping logic can be set arbitrarily. Although described in a specific embodiment, any interactive interface described in the present disclosure may be independently implemented as a separate implementation.
- the example interaction interfaces 300A to 500B may be implemented at the terminal device 110 , which may be any page of the application 120 .
- application 120 may be a conversational application. Specifically, for consumer users, consumer users may interact with virtual objects in the form of conversations.
- virtual objects may also be referred to as digital assistants, virtual avatars, etc.
- a music assistant will be used as an example of a virtual object.
- the virtual object is a music assistant.
- the user 140 inputs a message 310 (e.g., a user request 201) in a conversation with the music assistant.
- the music assistant returns a response 320.
- the response may relate to the responses output by the music search 231 and the music recommendation 232 provided by the music service module 230 shown in Figure 2 or the user response 206 output by the second model 240 for the user request processing 241.
- the response to the input message includes a reply message provided in a conversation window of the conversation, and the reply message includes text content and at least one music recommendation content.
- a response 320 is presented in a conversation for interacting with the music assistant, and further, the response 320 includes text content 330 and at least one music recommendation content 340.
- a music playback component provided in the session may be used to provide a playback service for at least one music recommendation content.
- the terminal device 110 may present an example interaction interface 300B shown in FIG3B .
- at least one music recommendation content may be played by the music playback component provided in the session.
- FIG. 4 shows a flow chart of a method 400 for processing a request according to some embodiments of the present disclosure.
- the method 400 may be at least partially implemented at the terminal device 110.
- the process 400 is described below with reference to FIG. 1 .
- the terminal device 110 obtains a user request received in a session between the user and a virtual object, the virtual object being associated with a music service.
- the terminal device 110 uses the first model to process the user request to determine whether the target intent corresponding to the user request matches a set of preset intents, and the set of preset intents includes music playback intent or playback control intent.
- the terminal device 110 in response to the target intent not matching the set of preset intents, the terminal device 110 provides the user request to a second model in box 440 to generate a first response to the user request, and the scale of the second model is larger than that of the first model.
- the terminal device 110 in response to the target intent matching the playback control intent, performs a playback control operation matching the target intent.
- the terminal device 110 determines a set of parameter values for a set of preset query parameters based on the user request; and in response to the parameter value of a target parameter in the set of preset query parameters being not empty, provides the user request to the second model to generate a second response to the user request, wherein the target parameter value indicates additional descriptive information about at least one other preset query parameter.
- the set of preset query parameters also includes at least one of the following: song parameters, performer parameters, album parameters, and scene parameters.
- the terminal device 110 in response to the target intent matching the music playback intent, the terminal device 110 generates a third response to the user request based on the set of parameter values of the set of preset query parameters.
- the terminal device 110 provides the set of parameter values to the music service module corresponding to the music playback intention to generate the third response to the user request.
- the music service module includes: a music search module corresponding to the first music playback intention; and/or a music recommendation module corresponding to the second music playback intention.
- the session window of the session displays a music playing component
- the first response is used to control the music playing component to execute a corresponding instruction.
- the second model comprises a language model.
- Fig. 5 shows a schematic structural block diagram of an apparatus 500 for processing a request according to some embodiments of the present disclosure.
- the apparatus 500 may be implemented as or included in the terminal device 110.
- Each module/component in the apparatus 500 may be implemented by hardware, software, firmware or any combination thereof.
- the device 500 includes: a request acquisition module 510, configured to acquire a user request received in a conversation between a user and a virtual object, wherein the virtual object is associated with a music service; a first processing module 520, configured to process the user request using a first model to determine whether a target intent corresponding to the user request matches a set of preset intents, wherein the set of preset intents includes a music playback intent or a playback control intent; and a providing module 530, configured to provide the user request to a second model in response to the target intent not matching the set of preset intents to generate a first response to the user request, wherein the scale of the second model is larger than that of the first model.
- a request acquisition module 510 configured to acquire a user request received in a conversation between a user and a virtual object, wherein the virtual object is associated with a music service
- a first processing module 520 configured to process the user request using a first model to determine whether a target intent corresponding to the user request matches
- the apparatus 500 may also be configured to, in response to the target intent matching the playback control intent, execute a playback control operation matching the target intent.
- the device 500 can also be configured to determine a set of parameter values for a set of preset query parameters based on the user request; and in response to the parameter value of a target parameter in the set of preset query parameters being not empty, provide the user request to the second model to generate a second response to the user request, wherein the target parameter value indicates additional descriptive information about at least one other preset query parameter.
- the set of preset query parameters also includes at least one of the following: song parameters, performer parameters, album parameters, and scene parameters.
- the device 500 may also be configured to, in response to the target intent matching the music playing intent, select a set of parameters based on the set of preset query parameters. A value is used to generate a third response to the user request.
- the apparatus 500 may also be configured to provide the set of parameter values to a music service module corresponding to the music playback intention to generate the third response to the user request.
- the music service module includes: a music search module corresponding to the first music playback intention; and/or a music recommendation module corresponding to the second music playback intention.
- the session window of the session displays a music playing component
- the first response is used to control the music playing component to execute a corresponding instruction.
- the second model comprises a language model.
- FIG6 shows a block diagram of an electronic device 600 in which one or more embodiments of the present disclosure may be implemented. It should be understood that the electronic device 600 shown in FIG6 is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. The electronic device 600 shown in FIG6 may be used to implement the terminal device 110 of FIG1 .
- the electronic device 600 is in the form of a general electronic device.
- the components of the electronic device 600 may include, but are not limited to, one or more processors or processing units 610, a memory 620, a storage device 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660.
- the processing unit 610 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 620. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 600.
- the electronic device 600 typically includes a plurality of computer storage media. Such media may be any retrievable media accessible to the electronic device 600, including but not limited to volatile and nonvolatile media, removable and non-removable media.
- the memory 620 may be a volatile memory (e.g., registers, cache, random access memory (RAM)), a nonvolatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof.
- the storage device 630 may be a removable or non-removable medium and may include a machine-readable medium such as a flash drive, a disk, or any other medium that may be capable of being used to store information and/or data (e.g., using a computer programmable memory device). training data for training) and can be accessed within the electronic device 600.
- a machine-readable medium such as a flash drive, a disk, or any other medium that may be capable of being used to store information and/or data (e.g., using a computer programmable memory device). training data for training) and can be accessed within the electronic device 600.
- the electronic device 600 may further include additional removable/non-removable, volatile/non-volatile storage media.
- a disk drive for reading or writing from a removable, non-volatile disk e.g., a “floppy disk”
- an optical drive for reading or writing from a removable, non-volatile optical disk may be provided.
- each drive may be connected to a bus (not shown) by one or more data media interfaces.
- the memory 620 may include a computer program product 625 having one or more program modules configured to perform various methods or actions of various embodiments of the present disclosure.
- the communication unit 640 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 600 can be implemented with a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 600 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.
- PC network personal computer
- the input device 650 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc.
- the output device 660 may be one or more output devices, such as a display, a speaker, a printer, etc.
- the electronic device 600 may also communicate with one or more external devices (not shown) through the communication unit 640 as needed, such as a storage device, a display device, etc., communicate with one or more devices that allow a user to interact with the electronic device 600, or communicate with any device that allows the electronic device 600 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input/output (I/O) interface (not shown).
- I/O input/output
- a computer-readable storage medium on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above.
- a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.
- These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions/actions specified in one or more boxes in the flowchart and/or block diagram is generated.
- These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and/or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions/actions specified in one or more boxes in the flowchart and/or block diagram.
- Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions/actions specified in one or more boxes in the flowchart and/or block diagram.
- each box in the flowchart or block diagram may represent a module, a program segment or a portion of an instruction, and a module, a program segment or a portion of an instruction contains one or more executable instructions for implementing the specified logical functions.
- the functions marked in the boxes may also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they may sometimes be executed in the opposite order, depending on the functions involved.
- each box in the block diagram and/or flowchart, and the combination of boxes in the block diagram and/or flowchart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with dedicated hardware and computer instructions. combination to achieve this.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
根据本公开的实施例,提供了用于请求处理的方法、装置、设备和存储介质。该方法包括:获取在用户与虚拟对象的会话中所接收到的用户请求,所述虚拟对象与音乐服务相关联;利用第一模型处理所述用户请求,以确定与所述用户请求对应的目标意图是否与一组预设意图匹配,所述一组预设意图包括音乐播放意图或播放控制意图;以及响应于所述目标意图与所述一组预设意图不匹配,向第二模型提供所述用户请求,以生成针对所述用户请求的第一响应,所述第二模型的规模大于所述第一模型。以此方式,可以提高处理音乐相关请求的速度,使得该请求能够被更加高效地执行。
Description
本公开的示例性实现方式总体涉及计算机领域,特别地涉及处理请求的方法、装置、设备和计算机可读存储介质。
随着互联网技术的飞速发展,对话式应用作为一种具有较强互动性的应用逐渐得到了用户的喜爱。用户可以通过对话式应用,与虚拟对象进行交互以获得各种服务,例如,获得音乐相关的服务。
发明内容
在本公开的第一方面,提供了一种处理请求的方法。该方法包括:获取在用户与虚拟对象的会话中所接收到的用户请求,所述虚拟对象与音乐服务相关联;利用第一模型处理所述用户请求,以确定与所述用户请求对应的目标意图是否与一组预设意图匹配,所述一组预设意图包括音乐播放意图或播放控制意图;以及响应于所述目标意图与所述一组预设意图不匹配,向第二模型提供所述用户请求,以生成针对所述用户请求的第一响应,所述第二模型的规模大于所述第一模型。以此方式,可以提高处理音乐相关请求的速度,使得该请求能够被更加高效地执行。
在本公开的第二方面,提供了一种处理请求的装置。该装置包括:请求获取模块,被配置为获取在用户与虚拟对象的会话中所接收到的用户请求,所述虚拟对象与音乐服务相关联;第一处理模块,被配置为利用第一模型处理所述用户请求,以确定与所述用户请求对应的目标意图是否与一组预设意图匹配,所述一组预设意图包括音乐播放意
图或播放控制意图;以及提供模块,被配置为响应于所述目标意图与所述一组预设意图不匹配,向第二模型提供所述用户请求,以生成针对所述用户请求的第一响应,所述第二模型的规模大于所述第一模型。
在本公开的第三方面,提供了一种电子设备。该电子设备包括:至少一个处理单元;以及至少一个存储器,至少一个存储器被耦合到至少一个处理单元并且存储用于由至少一个处理单元执行的指令,指令在由至少一个处理单元执行时使电子设备执行根据本公开第一方面的方法。
在本公开的第四方面,提供了一种计算机可读存储介质,其上存储有计算机程序,计算机程序在被处理器执行时使处理器实现根据本公开第一方面的方法。
根据本公开的第五方面,提供了一种计算机程序产品,包括计算机程序,其中计算机程序被处理器执行时实现根据本公开的第一方面的方法。
应当理解,本内容部分中所描述的内容并非旨在限定本公开的实现方式的关键特征或重要特征,也不用于限制本公开的范围。本公开的其它特征将通过以下的描述而变得容易理解。
在下文中,结合附图并参考以下详细说明,本公开各实现方式的上述和其他特征、优点及方面将变得更加明显。在附图中,相同或相似的附图标注表示相同或相似的元素,其中:
图1示出了本公开的实施例能够在其中实现的示例环境的示意图;
图2示出了根据本公开的一些实施例的处理请求的过程的示意图;
图3A和图3B示出了根据本公开的一些实施例的示例交互界面;
图4示出了根据本公开的一些实施例的处理请求的过程的示意图;
图5示出了根据本公开的一些实施例的处理请求的装置的示意性结构框图;以及
图6示出了其中可以实现本公开的一个或多个实施例的电子设备的框图。
下面将参照附图更详细地描述本公开的实施例。虽然附图中示出了本公开的某些实施例,然而应当理解的是,本公开可以通过各种形式来实现,而且不应该被解释为限于这里阐述的实施例,相反,提供这些实施例是为了更加透彻和完整地理解本公开。应当理解的是,本公开的附图及实施例仅用于示例性作用,并非用于限制本公开的保护范围。
在本公开的实施例的描述中,术语“包括”及其类似用语应当理解为开放性包含,即“包括但不限于”。术语“基于”应当理解为“至少部分地基于”。术语“一个实施例”或“该实施例”应当理解为“至少一个实施例”。术语“一些实施例”应当理解为“至少一些实施例”。下文还可能包括其他明确的和隐含的定义。
在本文中,除非明确说明,“响应于A”执行一个步骤并不意味着在“A”之后立即执行该步骤,而是可以包括一个或多个中间步骤。
可以理解的是,本技术方案所涉及的数据(包括但不限于数据本身、数据的获得或使用)应当遵循相应法律法规及相关规定的要求。
可以理解的是,在使用本公开各实施例公开的技术方案之前,均应当根据相关法律法规通过适当的方式对本公开所涉及个人信息的类型、使用范围、使用场景等告知用户并获得用户的授权。
例如,在响应于接收到用户的主动请求时,向用户发送提示信息,以明确地提示用户,其请求执行的操作将需要获得和使用到用户的个人信息,从而使得用户可以根据提示信息来自主地选择是否向执行本公开技术方案的操作的电子设备、应用、服务器或存储介质等软件或硬件提供个人信息。
作为一种可选的但非限制性的实现方式,响应于接收到用户的主
动请求,向用户发送提示信息的方式,例如可以是弹窗的方式,弹窗中可以以文字的方式呈现提示信息。此外,弹窗中还可以承载供用户选择“同意”或“不同意”向电子设备提供个人信息的选择控件。
可以理解的是,上述通知和获得用户授权过程仅是示意性的,不对本公开的实现方式构成限定,其他满足相关法律法规的方式也可应用于本公开的实现方式中。
如本文中所使用的,术语“模型”可以从训练数据中学习到相应的输入与输出之间的关联关系,从而在训练完成后可以针对给定的输入,生成对应的输出。模型的生成可以基于机器学习技术。深度学习是一种机器学习算法,通过使用多层处理单元来处理输入和提供相应输出。神经网络模型是基于深度学习的模型的一个示例。在本文中,“模型”也可以被称为“机器学习模型”、“学习模型”、“机器学习网络”或“学习网络”,这些术语在本文中可互换地使用。
“神经网络”是一种基于深度学习的机器学习网络。神经网络能够处理输入并且提供相应输出,其通常包括输入层和输出层以及在输入层与输出层之间的一个或多个隐藏层。在深度学习应用中使用的神经网络通常包括许多隐藏层,从而增加网络的深度。神经网络的各个层按顺序相连,从而前一层的输出被提供作为后一层的输入,其中输入层接收神经网络的输入,而输出层的输出作为神经网络的最终输出。神经网络的每个层包括一个或多个节点(也称为处理节点或神经元),每个节点处理来自上一层的输入。
通常,机器学习大致可以包括三个阶段,即训练阶段、测试阶段和应用阶段(也称为推理阶段)。在训练阶段,给定的模型可以使用大量的训练数据进行训练,不断迭代更新参数值,直到模型能够从训练数据中获得一致的满足预期目标的推理。通过训练,模型可以被认为能够从训练数据中学习从输入到输出之间的关联(也称为输入到输出的映射)。训练后的模型的参数值被确定。在测试阶段,将测试输入应用到训练后的模型,以测试模型是否能够提供正确的输出,从而
确定模型的性能。测试阶段有时候可以被融合在训练阶段。在应用或推理阶段,已训练的模型可以被用于基于训练得到的参数值,对实际的模型输入进行处理,确定对应的模型输出。
在本文的上下文中,虚拟对象可以是基于配置信息所创建的虚拟处理实体,其例如可以基于机器学习模型所实现。在一些场景中,虚拟对象也可以称为虚拟实体,其示例可以包括机器人程序(bot)、智能体(agent)等。
如上所简要讨论的,随着互联网技术的飞速发展,各式各样的应用已经成为人们日常生活中的重要工具。不同的应用往往具有不同的功能,用户可以通过具有特定功能的特定应用实现特定服务。
对话式应用作为一种具有较强互动性的应用逐渐得到了用户的喜爱。用户可以通过对话式应用,与虚拟对象进行交互以获得各种服务,例如,获得音乐相关的服务。现在,处理用户请求的响应时间往往超出用户的预期时间,严重影响了用户对于音乐服务的满意度。
根据本公开的实施例,提供了用于请求处理的方法、装置、设备和存储介质。该方法包括:获取在用户与虚拟对象的会话中所接收到的用户请求,所述虚拟对象与音乐服务相关联;利用第一模型处理所述用户请求,以确定与所述用户请求对应的目标意图是否与一组预设意图匹配,所述一组预设意图包括音乐播放意图或播放控制意图;以及响应于所述目标意图与所述一组预设意图不匹配,向第二模型提供所述用户请求,以生成针对所述用户请求的第一响应,所述第二模型的规模大于所述第一模型。
以此方式,本公开的实施例可以考虑基于用户请求对应的目标意图来确定针对用户请求的处理,从而能够显著提高针对用户请求的响应速度。
以下将继续参考附图描述本公开的一些示例实施例。
示例环境
图1示出了本公开的实施例能够在其中实现的示例环境100的示意图。在该示例环境100中,终端设备110中安装有应用120。用户140可以经由终端设备110和/或其附接设备来与应用120进行交互。应用120可以是支持与虚拟对象进行交互的任何适当应用。
在图1的环境100中,如果应用120处于活动状态,终端设备110可以呈现应用120的界面150。界面150可以包括应用120所能提供的各类界面,诸如与虚拟对象的会话界面。
在一些实施例中,终端设备110与电子设备130通信,以实现对应用120的服务(例如,音乐服务)的供应。终端设备110可以是任意类型的移动终端、固定终端或便携式终端,包括移动手机、台式计算机、膝上型计算机、笔记本计算机、上网本计算机、平板计算机、媒体计算机、多媒体平板、个人通信系统(PCS)设备、个人导航设备、个人数字助理(PDA)、音频/视频播放器、数码相机/摄像机、定位设备、电视接收器、无线电广播接收器、电子书设备、游戏设备或者前述各项的任意组合,包括这些设备的配件和外设或者其任意组合。在一些实施例中,终端设备110也能够支持任意类型的针对用户的接口(诸如“可佩戴”电路等)。电子设备130可以是能够提供计算能力的各种类型的计算系统/服务器,包括但不限于大型机、边缘计算节点、云环境中的计算设备,等等。
在一些实施例中,终端设备110可以和电子设备130共同协作以为用户140提供特定的服务。在本公开的一些示例实施例中,以电子设备130作为执行主体来描述示例过程。应当理解,在其他实施例中,所描述的示例过程可以由终端设备110和电子设备130协作实现。仅出于简要的目的,相同或类似的内容将不再重复。
应当理解,仅出于示例性的目的描述环境100中各个元素的结构和功能,而不暗示对于本公开的范围的任何限制。
以下将继续参考附图描述本公开的一些示例实施例。
示例过程
图2示出了根据本公开的一些实施例的用于处理请求示例过程200。下面参考图1来描述过程200。该过程可以至少部分地在图1所示终端设备110处被实施。为便于讨论,将参考图1的环境100来描述该过程。
如图2所示,终端设备110可以从用户140与虚拟对象的会话中获取用户请求201。如上文已经描述的,终端设备110中安装有应用120,其可以支持与虚拟对象进行交互。终端设备110的界面150例如可以呈现与虚拟对象的会话界面。该虚拟对象与音乐服务相关联。
在获取到用户请求后,终端设备110可以利用第一模型210处理该用户请求201,以确定与用户请求201对应的目标意图是否与一组预设意图匹配。该预设意图例如可以包括音乐播放意图或播放控制意图。
如果终端设备110确定用户请求201对应的目标意图与音乐播放意图或播放控制意图匹配,则可以执行与目标意图匹配的操作。
举例而言,终端设备110可以利用第一模型210对用户请求201所涉及的针对一组预设查询参数的一组参数值进行提取和分类(211),以确定用户请求201所对应的目标意图。
在一些实施例中,预设查询参数202可以包括歌曲参数、表演者参数、专辑参数、场景参数和/或附加描述信息等。
如果终端设备110利用第一模型210确定用户请求201涉及歌曲参数、表演者参数、专辑参数,则终端设备110可以确定用户请求201对应音乐播放意图。
例如,在一些实施例中,如果终端设备110利用第一模型210确定用户请求201为“播放XXX演唱的歌曲”或“播放XX歌曲”,则终端设备110可以确定用户请求201对应明确音乐播放意图203。接下来,终端设备110可以利用音乐服务模块230实现相应的音乐搜索操作(231)。
在一些其他实施例中,如果终端设备110利用第一模型210确定用户请求201涉及“推荐适合XX场景的音乐”,则终端设备110可以确定用户请求201对应明模糊音乐播放意图204。接下来,终端设备110可以利用音乐服务模块230实现相应的音乐推荐操作(232)。
终端设备110也可能从用户请求201中识别出播放控制意图205。例如,如果终端设备110利用第一模型210确定用户请求201涉及“暂停播放”、“停止播放”、“播放下一首”、“播放上一首”等播放控制意图,则可以确定用户请求201对应播放控制意图205。接下来,终端设备110可以执行相应的播放控制操作(220)。
在一些实施例中,终端设备110利用第一模型210确定用户请求201对应的目标意图与一组预设意图不匹配,也就是说,目标意图既不满足音乐播放意图,也不满足播放控制意图,则如图2所示,终端设备110向第二模型240提供用户请求201。第二模型240进而对用户请求201进行处理(241),以输出用户响应206。该第二模型240具有比第一模型210更大的规模。这可以理解为,相较于第一模型210而言,第二模型240涉及更复杂的算法,并且可能需要更长的时间生成用户响应。
由此可见,通过首先对用户请求201进行参数提取和分类,使得能够利用第一模型210确定的、涉及音乐播放意图或播放控制意图的用户请求可以免于通过第二模型240进行处理,由此显著加快了对用户请求的处理的速度和效率。
在上文已经提到,终端设备110可以利用第一模型210对用户请求201所涉及的针对一组预设查询参数的一组参数值进行提取和分类(211),以确定用户请求201所对应的目标意图。预设查询参数202可以包括附加描述信息。
一旦终端设备110利用第一模型210确定用户请求201中涉及附加描述信息,则将该用户请求提供到第二模型240。举例而言,如果终端设备110利用第一模型210确定用户请求201包括“播放XX电
影中的原声音乐”,则可以确定“XX电影”对应于附加描述信息,因为其不涉及歌曲参数、表演者参数、专辑参数、场景参数中的任一项。在这种情况下,终端设备110向第二模型240提供该用户请求201。第二模型240进而对用户请求201(例如其涉及的附加描述信息)进行处理(241),以输出用户响应206。
在一些实施例中,该第二模型240可以包括语言模型。用户140与虚拟对象的会话的会话窗口可以显示音乐播放组件。由第二模型240输出的用户响应206用于控制所述音乐播放组件执行对应的指令。
以此方式,可以提高处理音乐相关请求的速度,使得该请求能够被更加高效地执行。
示例界面
图3A和图3B示出了根据本公开的一些实施例的示例交互界面。图3A和图3B示出的界面300A和界面300B可以由终端设备110呈现。以下结合图1和图2来描述图3A和图3B示出的界面300A和界面300B。
应当理解,图3A至3B所示出的交互界面仅仅是示例,实际可以存在各种设计。例如,交互界面中的各个图形元素和/或控件可以具有不同的布置和不同的视觉表示,其中的一个或多个元素和/或控件可以省略或被替换,并且还可以存在一个或多个其它元素和/或控件。此外,用户界面中可以包含任意适当的内容。本公开的范围在此方面不受限制。
进一步地,用户可以通过激活各个交互界面中的控件/入口或者在交互界面中执行预定操作来实现交互界面的切换和跳转。应当理解,交互界面的切换和跳转的逻辑可以被任意设置。例如,在示例实施例中,用户通过激活控件由第一交互界面跳转至第二交互界面。在其它实施例中,用户可以通过激活另一控件由第一交互界面跳转至第三交互界面。本公开在此方面不受限制。还应当理解,尽管多个交互界面
被描述在一个特定实施例中,但是本公开所描述的任一交互界面,均可以作为单独的实施方式被独立地实现。
在本公开的各个示例实施例中,示例交互界面300A至500B可以在终端设备110处实现,其可以是应用120的任意页面。
在本公开的实施例中,应用120可以为对话式应用。具体而言,对于消费用户,消费用户可以和虚拟对象以对话的形式进行交互。在一些场景中,虚拟对象也可以被称为数字助手、虚拟分身等。在下本的实施例中,音乐助手将被作为虚拟对象的示例。
参见图3A和3B所示出的示例交互界面300A和300B。在图3A和3B的特定实施例中,虚拟对象为音乐助手。用户140在与音乐助手的会话中,输入消息310(例如用户请求201)。响应于该输入消息310,音乐助手返回响应320。该响应例如可以涉及在图2中示出的由音乐服务模块230提供的音乐搜索231和音乐推荐232输出的响应或由第二模型240输出的针对用户请求处理241的用户响应206。
在一些实施例中,针对输入消息的响应包括在会话的会话窗口中提供的回复消息,并且回复消息包括文本内容和与至少一项音乐推荐内容。参见图3A所示出的示例交互界面300A,响应320被呈现在与音乐助手进行交互的会话中,进一步地,响应320包括文本内容330和与至少一项音乐推荐内容340。
在一些实施例中,响应于对至少一项音乐推荐内容340的触发操作,可以利用会话中所提供的音乐播放组件,提供至少一项音乐推荐内容的播放服务。参见图3A所示出的示例交互界面300A,如果用户140触发至少一项音乐推荐内容340,终端设备110可以呈现图3B所示出的示例交互界面300B。在示例交互界面300B中,至少一项音乐推荐内容可以由会话中所提供的音乐播放组件来进行播放。
示例过程
图4示出了根据本公开的一些实施例的处理请求的方法400的流
程图。方法400可以至少部分地被实现在终端设备110处。下面参考图1描述过程400。
在框410,终端设备110获取在用户与虚拟对象的会话中所接收到的用户请求,所述虚拟对象与音乐服务相关联。
在框420,终端设备110利用第一模型处理所述用户请求,以确定与所述用户请求对应的目标意图是否与一组预设意图匹配,所述一组预设意图包括音乐播放意图或播放控制意图。
在框430,响应于所述目标意图与所述一组预设意图不匹配目标意图与所述一组预设意图不匹配,则在框440,终端设备110向第二模型提供所述用户请求,以生成针对所述用户请求的第一响应,所述第二模型的规模大于所述第一模型。
在一些实施例中,终端设备110响应于所述目标意图与所述播放控制意图匹配,执行与所述目标意图匹配的播放控制操作。
在一些实施例中,终端设备110基于所述用户请求,确定一组预设查询参数的一组参数值;以及响应于所述一组预设查询参数中的目标参数的参数值不为空,向所述第二模型提供所述用户请求,以生成针对所述用户请求的第二响应,所述目标参数值指示关于至少一项其他预设查询参数的附加描述信息。
在一些实施例中,所述一组预设查询参数还包括以下中的至少一项:歌曲参数、表演者参数、专辑参数、场景参数。
在一些实施例中,终端设备110响应于所述目标意图与所述音乐播放意图匹配,基于所述一组预设查询参数的所述一组参数值,生成针对所述用户请求的第三响应。
在一些实施例中,终端设备110向与所述音乐播放意图对应的音乐服务模块提供所述一组参数值,以生成针对所述用户请求的所述第三响应。
在一些实施例中,所述音乐服务模块包括:与第一音乐播放意图对应的音乐搜索模块;和/或与第二音乐播放意图对应的音乐推荐模块。
在一些实施例中,所述会话的会话窗口显示音乐播放组件,并且所述第一响应用于控制所述音乐播放组件执行对应的指令。
在一些实施例中,所述第二模型包括语言模型。
示例装置和设备
图5示出了根据本公开的某些实施例的处理请求的装置500的示意性结构框图。装置500可以被实现为或者被包括在终端设备110中。装置500中的各个模块/组件可以由硬件、软件、固件或者它们的任意组合来实现。
根据本公开的各个实施例,装置500包括:请求获取模块510,被配置为获取在用户与虚拟对象的会话中所接收到的用户请求,所述虚拟对象与音乐服务相关联;第一处理模块520,被配置为利用第一模型处理所述用户请求,以确定与所述用户请求对应的目标意图是否与一组预设意图匹配,所述一组预设意图包括音乐播放意图或播放控制意图;以及提供模块530,被配置为响应于所述目标意图与所述一组预设意图不匹配,向第二模型提供所述用户请求,以生成针对所述用户请求的第一响应,所述第二模型的规模大于所述第一模型。
在一些实施例中,装置500还可以被配置为响应于所述目标意图与所述播放控制意图匹配,执行与所述目标意图匹配的播放控制操作。
在一些实施例中,装置500还可以被配置为基于所述用户请求,确定一组预设查询参数的一组参数值;以及响应于所述一组预设查询参数中的目标参数的参数值不为空,向所述第二模型提供所述用户请求,以生成针对所述用户请求的第二响应,所述目标参数值指示关于至少一项其他预设查询参数的附加描述信息。
在一些实施例中,所述一组预设查询参数还包括以下中的至少一项:歌曲参数、表演者参数、专辑参数、场景参数。
在一些实施例中,装置500还可以被配置为响应于所述目标意图与所述音乐播放意图匹配,基于所述一组预设查询参数的所述一组参
数值,生成针对所述用户请求的第三响应。
在一些实施例中,装置500还可以被配置为向与所述音乐播放意图对应的音乐服务模块提供所述一组参数值,以生成针对所述用户请求的所述第三响应。
在一些实施例中,所述音乐服务模块包括:与第一音乐播放意图对应的音乐搜索模块;和/或与第二音乐播放意图对应的音乐推荐模块。
在一些实施例中,所述会话的会话窗口显示音乐播放组件,并且所述第一响应用于控制所述音乐播放组件执行对应的指令。
在一些实施例中,所述第二模型包括语言模型。
图6示出了其中可以实施本公开的一个或多个实施例的电子设备600的框图。应当理解,图6所示出的电子设备600仅仅是示例性的,而不应当构成对本文所描述的实施例的功能和范围的任何限制。图6所示出的电子设备600可以用于实现图1的终端设备110。
如图6所示,电子设备600是通用电子设备的形式。电子设备600的组件可以包括但不限于一个或多个处理器或处理单元610、存储器620、存储设备630、一个或多个通信单元640、一个或多个输入设备650以及一个或多个输出设备660。处理单元610可以是实际或虚拟处理器并且能够根据存储器620中存储的程序来执行各种处理。在多处理器系统中,多个处理单元并行执行计算机可执行指令,以提高电子设备600的并行处理能力。
电子设备600通常包括多个计算机存储介质。这样的介质可以是电子设备600可访问的任何可以获取的介质,包括但不限于易失性和非易失性介质、可拆卸和不可拆卸介质。存储器620可以是易失性存储器(例如寄存器、高速缓存、随机访问存储器(RAM))、非易失性存储器(例如,只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、闪存)或它们的某种组合。存储设备630可以是可拆卸或不可拆卸的介质,并且可以包括机器可读介质,诸如闪存驱动、磁盘或者任何其他介质,其可以能够用于存储信息和/或数据(例如用
于训练的训练数据)并且可以在电子设备600内被访问。
电子设备600可以进一步包括另外的可拆卸/不可拆卸、易失性/非易失性存储介质。尽管未在图6中示出,可以提供用于从可拆卸、非易失性磁盘(例如“软盘”)进行读取或写入的磁盘驱动和用于从可拆卸、非易失性光盘进行读取或写入的光盘驱动。在这些情况中,每个驱动可以由一个或多个数据介质接口被连接至总线(未示出)。存储器620可以包括计算机程序产品625,其具有一个或多个程序模块,这些程序模块被配置为执行本公开的各种实施例的各种方法或动作。
通信单元640实现通过通信介质与其他电子设备进行通信。附加地,电子设备600的组件的功能可以以单个计算集群或多个计算机器来实现,这些计算机器能够通过通信连接进行通信。因此,电子设备600可以使用与一个或多个其他服务器、网络个人计算机(PC)或者另一个网络节点的逻辑连接来在联网环境中进行操作。
输入设备650可以是一个或多个输入设备,例如鼠标、键盘、追踪球等。输出设备660可以是一个或多个输出设备,例如显示器、扬声器、打印机等。电子设备600还可以根据需要通过通信单元640与一个或多个外部设备(未示出)进行通信,外部设备诸如存储设备、显示设备等,与一个或多个使得用户与电子设备600交互的设备进行通信,或者与使得电子设备600与一个或多个其他电子设备通信的任何设备(例如,网卡、调制解调器等)进行通信。这样的通信可以经由输入/输出(I/O)接口(未示出)来执行。
根据本公开的示例性实现方式,提供了一种计算机可读存储介质,其上存储有计算机可执行指令,其中计算机可执行指令被处理器执行以实现上文描述的方法。根据本公开的示例性实现方式,还提供了一种计算机程序产品,计算机程序产品被有形地存储在非瞬态计算机可读介质上并且包括计算机可执行指令,而计算机可执行指令被处理器执行以实现上文描述的方法。
这里参照根据本公开实现的方法、装置、设备和计算机程序产品的流程图和/或框图描述了本公开的各个方面。应当理解,流程图和/或框图的每个方框以及流程图和/或框图中各方框的组合,都可以由计算机可读程序指令实现。
这些计算机可读程序指令可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理单元,从而生产出一种机器,使得这些指令在通过计算机或其他可编程数据处理装置的处理单元执行时,产生了实现流程图和/或框图中的一个或多个方框中规定的功能/动作的装置。也可以把这些计算机可读程序指令存储在计算机可读存储介质中,这些指令使得计算机、可编程数据处理装置和/或其他设备以特定方式工作,从而,存储有指令的计算机可读介质则包括一个制造品,其包括实现流程图和/或框图中的一个或多个方框中规定的功能/动作的各个方面的指令。
可以把计算机可读程序指令加载到计算机、其他可编程数据处理装置、或其他设备上,使得在计算机、其他可编程数据处理装置或其他设备上执行一系列操作步骤,以产生计算机实现的过程,从而使得在计算机、其他可编程数据处理装置、或其他设备上执行的指令实现流程图和/或框图中的一个或多个方框中规定的功能/动作。
附图中的流程图和框图显示了根据本公开的多个实现的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上,流程图或框图中的每个方框可以代表一个模块、程序段或指令的一部分,模块、程序段或指令的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。在有些作为替换的实现中,方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如,两个连续的方框实际上可以基本并行地执行,它们有时也可以按相反的顺序执行,这依所涉及的功能而定。也要注意的是,框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合,可以用执行规定的功能或动作的专用的基于硬件的系统来实现,或者可以用专用硬件与计算机指令
的组合来实现。
以上已经描述了本公开的各实现,上述说明是示例性的,并非穷尽性的,并且也不限于所公开的各实现。在不偏离所说明的各实现的范围和精神的情况下,对于本技术领域的普通技术人员来说许多修改和变更都是显而易见的。本文中所用术语的选择,旨在最好地解释各实现的原理、实际应用或对市场中的技术的改进,或者使本技术领域的其他普通技术人员能理解本文公开的各个实现方式。
Claims (13)
- 一种处理请求的方法,包括:获取在用户与虚拟对象的会话中所接收到的用户请求,所述虚拟对象与音乐服务相关联;利用第一模型处理所述用户请求,以确定与所述用户请求对应的目标意图是否与一组预设意图匹配,所述一组预设意图包括音乐播放意图或播放控制意图;以及响应于所述目标意图与所述一组预设意图不匹配,向第二模型提供所述用户请求,以生成针对所述用户请求的第一响应,所述第二模型的规模大于所述第一模型。
- 根据权利要求1所述的方法,还包括:响应于所述目标意图与所述播放控制意图匹配,执行与所述目标意图匹配的播放控制操作。
- 根据权利要求1所述的方法,还包括:基于所述用户请求,确定一组预设查询参数的一组参数值;以及响应于所述一组预设查询参数中的目标参数的参数值不为空,向所述第二模型提供所述用户请求,以生成针对所述用户请求的第二响应,所述目标参数值指示关于至少一项其他预设查询参数的附加描述信息。
- 根据权利要求3所述的方法,其中所述一组预设查询参数还包括以下中的至少一项:歌曲参数、表演者参数、专辑参数、场景参数。
- 根据权利要求3所述的方法,还包括:响应于所述目标意图与所述音乐播放意图匹配,基于所述一组预设查询参数的所述一组参数值,生成针对所述用户请求的第三响应。
- 根据权利要求5所述的方法,其中基于所述一组预设查询参数的所述一组参数值生成针对所述用户请求的第三响应包括:向与所述音乐播放意图对应的音乐服务模块提供所述一组参数值,以生成针对所述用户请求的所述第三响应。
- 根据权利要求6所述的方法,其中所述音乐服务模块包括:与第一音乐播放意图对应的音乐搜索模块;和/或与第二音乐播放意图对应的音乐推荐模块。
- 根据权利要求1所述的方法,其中所述会话的会话窗口显示音乐播放组件,并且所述第一响应用于控制所述音乐播放组件执行对应的指令。
- 根据权利要求1所述的方法,其中所述第二模型包括语言模型。
- 一种用于处理请求的装置,包括:请求获取模块,被配置为获取在用户与虚拟对象的会话中所接收到的用户请求,所述虚拟对象与音乐服务相关联;第一处理模块,被配置为利用第一模型处理所述用户请求,以确定与所述用户请求对应的目标意图是否与一组预设意图匹配,所述一组预设意图包括音乐播放意图或播放控制意图;以及提供模块,被配置为响应于所述目标意图与所述一组预设意图不匹配,向第二模型提供所述用户请求,以生成针对所述用户请求的第一响应,所述第二模型的规模大于所述第一模型。
- 一种电子设备,包括:至少一个处理单元;以及至少一个存储器,所述至少一个存储器被耦合到所述至少一个处理单元并且存储用于由所述至少一个处理单元执行的指令,所述指令在由所述至少一个处理单元执行时使所述电子设备执行根据权利要求1至9中任一项所述的方法。
- 一种计算机可读存储介质,其上存储有计算机程序,所述计算机程序可由处理器执行以实现根据权利要求1至9中任一项所述的方法。
- 一种计算机程序产品,包括计算机可执行指令,其中所述计算机可执行指令在被处理器执行时实现根据权利要求1至9中任一项所述的方法。
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202480004212.9A CN121646755A (zh) | 2024-06-28 | 2024-06-28 | 处理请求的方法、装置、设备和存储介质 |
| PCT/CN2024/102716 WO2025035983A1 (zh) | 2024-06-28 | 2024-06-28 | 处理请求的方法、装置、设备和存储介质 |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2024/102716 WO2025035983A1 (zh) | 2024-06-28 | 2024-06-28 | 处理请求的方法、装置、设备和存储介质 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2025035983A1 true WO2025035983A1 (zh) | 2025-02-20 |
Family
ID=94632145
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2024/102716 Pending WO2025035983A1 (zh) | 2024-06-28 | 2024-06-28 | 处理请求的方法、装置、设备和存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN121646755A (zh) |
| WO (1) | WO2025035983A1 (zh) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107480161A (zh) * | 2016-06-08 | 2017-12-15 | 苹果公司 | 用于媒体探究的智能自动化助理 |
| CN107833574A (zh) * | 2017-11-16 | 2018-03-23 | 百度在线网络技术(北京)有限公司 | 用于提供语音服务的方法和装置 |
| CN110795528A (zh) * | 2019-09-05 | 2020-02-14 | 腾讯科技(深圳)有限公司 | 一种数据查询方法、装置、电子设备及存储介质 |
| US20200151212A1 (en) * | 2018-11-13 | 2020-05-14 | Baidu Online Network Technology (Beijing) Co., Ltd. | Music recommending method, device, terminal, and storage medium |
| CN111274819A (zh) * | 2020-02-13 | 2020-06-12 | 北京声智科技有限公司 | 资源获取方法及装置 |
| CN114255745A (zh) * | 2020-09-10 | 2022-03-29 | 华为技术有限公司 | 一种人机交互的方法、电子设备及系统 |
| CN114627864A (zh) * | 2020-12-10 | 2022-06-14 | 海信视像科技股份有限公司 | 显示设备与语音交互方法 |
| CN115130478A (zh) * | 2021-03-25 | 2022-09-30 | 华为技术有限公司 | 意图决策方法及设备、计算机可读存储介质 |
| CN115776600A (zh) * | 2021-09-06 | 2023-03-10 | 聚好看科技股份有限公司 | 显示设备及音乐播放界面展示的方法 |
| CN117351952A (zh) * | 2023-09-19 | 2024-01-05 | 重庆长安汽车股份有限公司 | 语音指令交互方法、装置、电子设备及存储介质 |
| CN118013025A (zh) * | 2024-03-25 | 2024-05-10 | 北京字跳网络技术有限公司 | 用于书籍搜索的方法、装置、设备和介质 |
-
2024
- 2024-06-28 WO PCT/CN2024/102716 patent/WO2025035983A1/zh active Pending
- 2024-06-28 CN CN202480004212.9A patent/CN121646755A/zh active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107480161A (zh) * | 2016-06-08 | 2017-12-15 | 苹果公司 | 用于媒体探究的智能自动化助理 |
| CN107833574A (zh) * | 2017-11-16 | 2018-03-23 | 百度在线网络技术(北京)有限公司 | 用于提供语音服务的方法和装置 |
| US20200151212A1 (en) * | 2018-11-13 | 2020-05-14 | Baidu Online Network Technology (Beijing) Co., Ltd. | Music recommending method, device, terminal, and storage medium |
| CN110795528A (zh) * | 2019-09-05 | 2020-02-14 | 腾讯科技(深圳)有限公司 | 一种数据查询方法、装置、电子设备及存储介质 |
| CN111274819A (zh) * | 2020-02-13 | 2020-06-12 | 北京声智科技有限公司 | 资源获取方法及装置 |
| CN114255745A (zh) * | 2020-09-10 | 2022-03-29 | 华为技术有限公司 | 一种人机交互的方法、电子设备及系统 |
| CN114627864A (zh) * | 2020-12-10 | 2022-06-14 | 海信视像科技股份有限公司 | 显示设备与语音交互方法 |
| CN115130478A (zh) * | 2021-03-25 | 2022-09-30 | 华为技术有限公司 | 意图决策方法及设备、计算机可读存储介质 |
| CN115776600A (zh) * | 2021-09-06 | 2023-03-10 | 聚好看科技股份有限公司 | 显示设备及音乐播放界面展示的方法 |
| CN117351952A (zh) * | 2023-09-19 | 2024-01-05 | 重庆长安汽车股份有限公司 | 语音指令交互方法、装置、电子设备及存储介质 |
| CN118013025A (zh) * | 2024-03-25 | 2024-05-10 | 北京字跳网络技术有限公司 | 用于书籍搜索的方法、装置、设备和介质 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN121646755A (zh) | 2026-03-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109192212B (zh) | 语音控制方法及装置 | |
| WO2024240105A1 (zh) | 用于信息处理的方法、装置、设备和存储介质 | |
| CN118296228A (zh) | 搜索方法、装置、设备和存储介质 | |
| WO2025112605A1 (zh) | 用于会话交互的方法、装置、设备和存储介质 | |
| WO2025067533A1 (zh) | 一种文字处理方法、装置、计算机设备、存储介质及计算机程序产品 | |
| WO2025209146A1 (zh) | 用于图像编辑的方法、装置、设备、介质和程序产品 | |
| CN111339349A (zh) | 歌单推荐方法 | |
| WO2026001095A1 (zh) | 故事创作方法、装置、设备和存储介质 | |
| WO2025223031A1 (zh) | 信息处理方法、装置、设备和存储介质 | |
| WO2025241638A1 (zh) | 多媒体内容推荐的方法、装置、设备和存储介质 | |
| WO2025081899A1 (zh) | 一种交互方法、装置、设备和存储介质 | |
| WO2025035983A1 (zh) | 处理请求的方法、装置、设备和存储介质 | |
| CN119106216A (zh) | 信息交互方法、装置、电子设备和存储介质 | |
| WO2025081901A1 (zh) | 处理请求的方法、装置、设备和存储介质 | |
| WO2025077302A1 (zh) | 处理请求的方法、装置、设备和存储介质 | |
| WO2026055939A1 (zh) | 视频处理的方法、装置、设备、存储介质和程序产品 | |
| WO2025108115A1 (zh) | 数据处理的方法、装置、设备和存储介质 | |
| WO2026055943A1 (zh) | 任务处理的方法、装置、设备、存储介质和程序产品 | |
| WO2025097798A1 (zh) | 内容交互的方法、装置、设备和存储介质 | |
| CN119173867A (zh) | 用于查询的方法、装置、设备和存储介质 | |
| WO2025162201A1 (zh) | 用于信息播放的方法、装置、设备和存储介质 | |
| CN119631091A (zh) | 用于对话交互的方法、装置、设备和存储介质 | |
| CN115472162A (zh) | 通信终端的控制方法、装置、介质及设备 | |
| CN121838711A (zh) | 用于语音处理的方法、装置、设备、存储介质和程序产品 | |
| CN120872562A (zh) | 任务处理方法、装置、设备和存储介质 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 24853398 Country of ref document: EP Kind code of ref document: A1 |