WO2023019517A1 - 推荐指令的方法及其装置 - Google Patents

推荐指令的方法及其装置 Download PDF

Info

Publication number
WO2023019517A1
WO2023019517A1 PCT/CN2021/113575 CN2021113575W WO2023019517A1 WO 2023019517 A1 WO2023019517 A1 WO 2023019517A1 CN 2021113575 W CN2021113575 W CN 2021113575W WO 2023019517 A1 WO2023019517 A1 WO 2023019517A1
Authority
WO
WIPO (PCT)
Prior art keywords
instruction
application scenario
duration
user
recommended
Prior art date
Application number
PCT/CN2021/113575
Other languages
English (en)
French (fr)
Inventor
向伟
Original Assignee
阿波罗智联(北京)科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 阿波罗智联(北京)科技有限公司 filed Critical 阿波罗智联(北京)科技有限公司
Priority to PCT/CN2021/113575 priority Critical patent/WO2023019517A1/zh
Publication of WO2023019517A1 publication Critical patent/WO2023019517A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems

Definitions

  • the present disclosure relates to the technical field of artificial intelligence, in particular to the technical field of Internet of Vehicles and intelligent cockpit, and in particular to a method and device for recommending instructions, electronic equipment, computer storage media and computer program products.
  • Existing smart devices such as smart electronic products such as mobile phones, tablet computers, and vehicle-mounted voice interaction devices, usually have instruction recommendation devices.
  • instruction recommendation devices When the user issues a command, the corresponding command recommendation will be made according to the user's command.
  • the content of the instruction recommended each time by the existing instruction recommendation device is fixed.
  • the present disclosure provides a method for recommending instructions, including: acquiring a first instruction of a user; determining to enter a relevant first application scenario based on the first instruction; acquiring at least one first recommendation instruction matching the first application scenario, and displaying; in response to determining that at least one first recommended instruction has not been operated, selecting a second application scenario according to preset rules; and acquiring and displaying at least one second recommended instruction matching the second application scenario.
  • a device for recommending instructions including: an instruction acquiring unit configured to acquire a user's first instruction; a first determining unit configured to determine to enter a relevant first application based on the first instruction Scenario; a first acquisition unit configured to acquire and display at least one first recommendation instruction matching the first application scenario; a selection unit configured to select according to preset rules in response to determining that at least one first recommendation instruction has not been operated a second application scenario; and a second acquiring unit configured to acquire and display at least one second recommendation instruction matching the second application scenario.
  • a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the above method.
  • a computer program product including a computer program, wherein the computer program implements the above method when executed by a processor.
  • the instruction recommendation device after it is determined that the user has not selected the instruction recommended by the instruction recommendation device, it will actively switch from the current application scenario to another application scenario, and update the recommended instruction that matches the new application scenario , so as to realize more intelligent guidance to users.
  • the new application scenario switched to is determined according to preset rules rather than random or fixed, so that the recommended instructions are more targeted and the guidance recommendation is more intelligent.
  • FIG. 1 shows a flowchart of a method for recommending instructions according to an embodiment of the present disclosure
  • FIG. 2 shows a flow chart of a method for judging whether a first recommended instruction is operated according to an embodiment of the present disclosure
  • FIG. 3 shows a flowchart of a method for actively switching application scenarios according to an embodiment of the present disclosure
  • FIG. 4 shows a flowchart of a method for determining a first recommended instruction and a second recommended instruction according to an embodiment of the present disclosure
  • FIG. 5 shows a flowchart of a method for acquiring a first duration threshold according to an embodiment of the present disclosure
  • FIG. 6 shows a flowchart of a method for selecting a second application scenario according to a preset rule according to an embodiment of the present disclosure
  • FIG. 7 shows a flowchart of a method for determining a first application scenario according to a first voice instruction according to an embodiment of the present disclosure
  • Fig. 8 shows a schematic diagram of an apparatus for recommending instructions according to an embodiment of the present disclosure
  • Fig. 9 shows a schematic diagram of an apparatus for recommending instructions according to another embodiment of the present disclosure.
  • FIG. 10 shows a structural block diagram of an exemplary electronic device that can be used to implement the embodiments of the present disclosure.
  • first, second, etc. to describe various elements is not intended to limit the positional relationship, temporal relationship or importance relationship of these elements, and such terms are only used for Distinguishes one element from another.
  • first element and the second element may refer to the same instance of the element, and in some cases, they may also refer to different instances based on contextual description.
  • FIG. 1 shows a flowchart of a method 100 for recommending instructions according to an embodiment of the present disclosure.
  • the method 100 includes:
  • Step 101 obtaining the user's first instruction
  • Step 102 based on the first instruction, determine to enter a relevant first application scenario
  • Step 103 acquiring and displaying at least one first recommended instruction matching the first application scenario
  • Step 104 in response to determining that at least one first recommendation instruction has not been operated, select a second application scenario according to preset rules;
  • Step 105 acquiring and displaying at least one second recommended instruction matching the second application scenario.
  • the user after determining that the user has not selected the instruction recommended by the instruction recommending device, the user will actively switch from the current application scenario to another application scenario, and update the recommendation instructions that match the new application scenario, thereby Realize more intelligent guidance to users.
  • the new application scenario switched to is determined according to preset rules rather than random or fixed, so that the recommended instructions are more targeted and the guidance recommendation is more intelligent.
  • the instruction recommending apparatus acquires a user's first instruction.
  • the instruction recommendation device may be a vehicle-mounted voice interaction device, and in other embodiments, the instruction recommendation device may be other artificial intelligence devices or instruction recommendation devices for electronic equipment.
  • the above-mentioned first instruction may be a voice instruction, a text instruction or an instruction in other forms.
  • the instruction content of the first instruction may be analyzed, so as to obtain the user's intention. Enter the relevant first application scene according to the user's intention.
  • the above-mentioned first application scenario may be one of various application scenarios included in the instruction recommendation apparatus, and each application scenario includes functions and page display related to the scenario.
  • the vehicle-mounted voice interaction device can include multiple application scenarios such as navigation, music, and conversation.
  • the vehicle-mounted voice interaction device has map display and navigation functions, and displays nearby Map; in the music mode, the vehicle-mounted voice interaction device has a music playback function, and displays the songs that can be played on the relevant page, etc.
  • the vehicle-mounted voice interaction device After the user sends out the first instruction, for example: the user's voice indicates "play music", the vehicle-mounted voice interaction device will enter the music application scene according to the user's intention.
  • the instruction recommending apparatus has various application scenarios, and each application scenario has a matching recommended instruction.
  • the instruction recommending device can selectively display these recommended instructions for the user to select, and the user can select these instructions by operating the recommended instructions displayed on the touch screen of the instruction recommending device, or still Choose commands with voice control.
  • navigation application scenarios may include recommendation instructions such as: address query, nearby target location recommendation, intelligent voice navigation, etc.
  • Music application scenarios may include such as: playing music, selecting the next song, pausing music, etc. Recommended instructions.
  • the matching recommended instructions for each application scenario may be predetermined.
  • a matching recommended instruction set may be preset for each application scenario.
  • the instruction set may be obtained and displayed. some or all of .
  • step 104 if the user does not select at least one first recommended instruction recommended by the instruction recommending device, it means that the user is not interested in the instruction of the current application scenario, and then selects the second application scenario according to preset rules.
  • the preset rules can be selected according to the user's preferences, so that the recommended instructions are more targeted and the recommendation is more intelligent. For example, a historical log of the frequency of use of each application scenario by the user may be obtained, and an application scenario most frequently used by the user may be selected as the second application scenario based on the historical log.
  • At step 105 at least one second recommended instruction matching the second application scenario is acquired and displayed.
  • the second recommended instruction may be used instead of the first recommended instruction, so as to update the display of the recommended instruction.
  • the second recommendation instruction when the second recommendation instruction is displayed, it can automatically switch to the second application scene at the same time, so as to facilitate the user's operation.
  • the second recommendation instruction when the second recommendation instruction is displayed, it can still stay at the first An application scenario, and then switch to the second application scenario when the subsequent user selects the second recommendation instruction.
  • FIG. 2 shows a flow chart of a method 200 for judging whether a first recommended instruction is operated according to an embodiment of the present disclosure. As shown in FIG. 2 , the method 200 includes:
  • Step 201 recording the duration of at least one first recommended instruction not being operated in the first application scenario
  • Step 202 judging whether the duration exceeds a first duration threshold
  • Step 203 if the judgment result of step 202 is yes, it is determined that at least one first recommendation instruction has not been operated.
  • Step 204 if the judgment result of step 202 is no, start to re-record the duration when at least one first recommendation instruction is operated.
  • the method of this embodiment judges whether the first instruction is operated by recording the duration of the first recommended instruction not being operated.
  • step 201 after the instruction recommending device displays the first recommended instruction, it starts timing until the user selects the displayed first recommended instruction.
  • the instruction recommending device may display multiple first recommended instructions at the same time, and the timing ends after the user operates on one of the instructions.
  • the first duration threshold is predetermined and corresponds to the first application scenario.
  • each application scenario has a predetermined duration threshold corresponding to the application scenario, and each duration threshold is used as a duration standard indicating that no operation is performed on the recommended instruction of the current application scenario.
  • a first application scenario for example: navigation application scenario
  • a second application scenario for example: music application scenario
  • a second duration threshold for example: 80s.
  • step 203 if the user does not select the first recommended instruction within the first duration threshold, it is determined that at least one first recommended instruction has not been operated.
  • the above-mentioned first application scenario may be a navigation scenario, for example, and the first duration threshold corresponding to the navigation scenario is 100s, then within 100s after the first recommendation instruction is displayed, if the user has not selected the second any one of the recommended instructions, then it is determined that at least one first recommended instruction has not been operated.
  • step 204 if the user selects one or more of the first recommended instructions before the duration reaches the first duration threshold, it is determined that at least one of the first recommended instructions is operated, which means that the user is still using the first recommended instruction.
  • a function of the application scenario At this time, the recorded duration can be cleared, and the duration can be re-recorded at the point in time when the user selects the first recommended instruction.
  • FIG. 3 shows the flow of a method 300 for switching the application scene according to an embodiment of the present disclosure.
  • the method 300 includes:
  • Step 301 judging whether the user's second instruction is obtained within the duration of the first duration threshold
  • Step 302 in response to determining that the user's second instruction has been obtained, based on the second instruction, determine to enter a relevant third application scenario
  • Step 303 acquiring and displaying at least one third recommended instruction matching the third application scenario.
  • step 301 before the duration does not reach the first duration threshold, it is judged whether a second instruction from the user is obtained, wherein the second instruction may be a new instruction different from the first instruction;
  • step 302 based on the second instruction newly issued by the user, it is determined to enter a relevant third application scenario. If the user actively switches the application scene, then switch the application scene according to the user's new intention. For example, if the instruction recommending device is currently in a navigation application scene, and then the user issues a second instruction of "play music", then the instruction recommending device switches to a related music application scene (ie, the third application scene).
  • step 303 similar to step 103 in method 100, at least one third recommended instruction matching the third application scenario is obtained and displayed, and the third recommended instruction can be used to replace the first recommended instruction, thereby realizing the renew.
  • the method of this embodiment can switch the application scene according to the user's new instruction, and update the recommendation instruction accordingly, thus making the instruction recommendation process more intelligent.
  • FIG. 4 shows a flowchart of a method 400 for determining a first recommended instruction and a second recommended instruction according to an embodiment of the present disclosure. As shown in FIG. 4, the method 400 includes:
  • Step 401 separately acquire instruction parameters of multiple historical instructions issued by the user in multiple application scenarios, the application scenarios include a first application scenario and a second application scenario;
  • Step 402 Determine at least one first recommended instruction matching the first application scenario and at least one second recommended instruction matching the second application scenario based on the instruction parameters of the multiple historical instructions.
  • instruction parameters of historical instructions issued by users in multiple application scenarios may be acquired.
  • the multiple application scenarios include a first application scenario and a second application scenario
  • the historical instructions may include a first historical instruction issued by a user in the first application scenario, and a second historical instruction issued by a user in the second application scenario.
  • the above instruction parameters may be any parameters related to the historical instruction, for example, may be: instruction keywords, instruction usage frequency, instruction usage duration and so on.
  • the instruction parameters related to the instruction are obtained, such as: the keyword "XXX”, the use of the historical instruction Frequency 4 times/1 day and so on.
  • the instruction parameters listed above are only exemplary. In other disclosed embodiments, other related instruction parameters such as the total number of times of use may also be acquired, which will not be listed here.
  • the instruction parameters of historical instructions in each application scenario obtained in step 401 are used to determine a recommended instruction set matching each application scenario according to relevant rules, and each recommended instruction set includes at least one recommended instruction.
  • the first recommended instruction set including at least one first recommended instruction may be determined according to the instruction parameters of the first historical instructions in the first application scenario
  • the first recommended instruction set including at least one recommended instruction may be determined according to the instruction parameters of the second historical instructions in the second application scenario.
  • the above-mentioned related rules can be specific algorithms, such as artificial intelligence algorithms.
  • multiple samples of instruction parameters including the above-mentioned historical instructions can be input into the training model for training to obtain a trained model, and then step 401 can be followed.
  • the instruction parameters of the historical instructions obtained in are input into the trained model to obtain the corresponding recommended instruction set.
  • the method of this embodiment uses the instruction parameters of the user's historical instructions to determine the recommended instruction, so that the obtained recommended instruction is more biased towards the user's preference, which can arouse the user's interest, thereby improving the user's experience.
  • Fig. 5 shows a flowchart of a method 500 for acquiring a first duration threshold according to an embodiment of the present disclosure. As shown in FIG. 5, the method 500 includes:
  • Step 501 acquiring the duration information of each use of the first application scene by the user.
  • Step 502 Determine the first duration threshold based on the duration information.
  • the above-mentioned first duration threshold may also be obtained by analyzing relevant user historical usage data.
  • step 501 before implementing the method 100 shown in FIG. 1 , the duration information of each use of the first application scenario can be obtained.
  • a first duration threshold is determined based on the one or more pieces of duration information.
  • the average duration of each use of the first application scenario may be calculated by using the pieces of duration information obtained in step 501, and the average duration may be used as the first duration threshold.
  • FIG. 6 shows a flowchart 600 of a method for selecting a second application scenario according to preset rules according to an embodiment of the present disclosure. As shown in FIG. 6 , the method 600 includes:
  • Step 601 respectively acquiring user interaction information related to multiple application scenarios.
  • Step 602 Select a second application scenario from multiple application scenarios based on user interaction information.
  • the user interaction information may include historical usage information related to each application scenario, for example: usage frequency, total usage duration, etc. of each application scenario.
  • the user interaction information may be the usage frequency of each application scenario. If the instruction recommending device has 5 application scenarios in total, then the historical usage frequencies of the 5 application scenarios can be obtained respectively, that is, the first usage frequency to the fifth usage frequency usage frequency.
  • a second application scenario may be determined based on the first to fifth usage frequencies acquired in step 601. For example, the application scenario with the highest usage frequency among the five application scenarios may be selected as the second application scenario. It can be understood that the highest frequency of use means that the application scenario is the application scenario that the user prefers to use.
  • Using the application scenario preferred by the user as the basis for subsequent recommendation instructions can realize intelligent guidance to the user and give recommendation instructions that can arouse the user's interest. Improved user experience.
  • the first instruction may be a first voice instruction.
  • FIG. 7 shows a flowchart of a method 700 for determining a first application scenario according to a first voice instruction according to an embodiment of the present disclosure, as shown in FIG. 7 , the method 700 includes:
  • Step 701 performing voice recognition on the first voice command to obtain a voice recognition text
  • Step 702 performing semantic analysis on the speech recognition text to obtain a semantic analysis result
  • Step 703 according to the semantic analysis result, determine the first application scenario to be entered.
  • the received first voice instruction can be uploaded to the cloud server, and the cloud server can perform voice recognition on it to obtain the instruction text.
  • the cloud server may perform further semantic analysis on the instruction text, obtain the semantic analysis result, and send it back to the instruction recommendation device.
  • the above-mentioned semantic analysis method may, for example, use natural language processing (Natural Language Processing, NLP), and the above-mentioned analysis result may be, for example, keyword information in the instruction text.
  • NLP Natural Language Processing
  • the instruction text obtained in step 701 is "play music”
  • step 702 perform semantic analysis on it in step 702 to obtain the keyword "music”.
  • step 703 according to the keyword "music", it is determined that the related music application scene is the first application scene to be entered.
  • FIG. 8 shows a schematic diagram of an apparatus 800 for recommending instructions according to an embodiment of the present disclosure.
  • the apparatus 800 includes: an instruction acquiring unit 810 configured to acquire the user's first Instruction; the first determination unit 820 is configured to determine to enter a relevant first application scenario based on the first instruction; the first acquisition unit 830 is configured to acquire and display at least one first recommendation instruction matching the first application scenario; The selection unit 840 is configured to select a second application scenario according to preset rules in response to determining that at least one first recommendation instruction has not been operated; and the second acquisition unit 850 is configured to acquire at least one first recommendation instruction that matches the second application scenario. Two recommended commands are displayed.
  • Fig. 9 shows a schematic diagram of an apparatus 900 for recommending instructions according to an embodiment of the present disclosure.
  • the selection unit 940 includes: a timing module 941 configured to record the duration of at least one first recommendation instruction not being operated in the first application scenario; a first judging module 942 configured to judge whether the duration is Exceeding the first duration threshold, the first duration threshold corresponds to the first application scenario; and the first determination module 943 is configured to determine that at least one first recommendation instruction has not been operated in response to determining that the duration exceeds the first duration threshold.
  • the above-mentioned apparatus 900 further includes: an instruction parameter acquisition unit 961 configured to respectively acquire instruction parameters of historical instructions issued by the user in multiple application scenarios, where the application scenarios include a first application scenario and a second application scenario; And the second determining unit 962, based on the instruction parameter, determines at least one first recommended instruction matching the first application scenario and at least one second recommendation instruction matching the second application scenario.
  • the instruction parameters include one or more of the following parameters: instruction keywords, instruction usage frequency, and instruction usage duration.
  • the above-mentioned apparatus 900 further includes: a duration information acquiring unit 971 configured to acquire the duration information of each time the user uses the first application scene; and a third determining unit 972 configured to determine the first application scenario based on the duration information. duration threshold.
  • the selection unit 940 further includes: an interaction information obtaining module 944 configured to obtain user interaction information related to multiple application scenarios respectively; and a selection module 945 configured to obtain user interaction information from multiple application scenarios based on the user interaction information Select the second application scenario.
  • the first instruction includes a first voice instruction
  • the first determination unit 920 includes: a speech recognition module 921 configured to perform speech recognition on the first speech instruction to obtain a speech recognition text; and a semantic analysis module 922 configured to The paired speech recognition texts are semantically analyzed to obtain a semantic analysis result; wherein the first determination unit is further configured to determine the first application scenario to be entered according to the semantic analysis result.
  • the timing module 941 is further configured to: in response to determining that the duration does not exceed the first duration threshold, start to re-record the duration at the point in time when at least one first recommendation instruction is operated.
  • the above-mentioned device 900 further includes an update unit 980
  • the update unit 980 includes: a second judging module 981 configured to judge whether the user's second instruction is obtained within the duration of the first duration threshold;
  • the determination module 982 is configured to obtain the user's second instruction in response to the determination, and determine to enter a relevant third application scenario based on the second instruction; and
  • the recommended instruction acquisition module 983 is configured to obtain at least A third recommended instruction is displayed.
  • an electronic device a readable storage medium, and a computer program product are also provided.
  • Electronic device is intended to mean various forms of digital electronic computing equipment, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smart phones, wearable devices, and other similar computing devices.
  • the components shown herein, their connections and relationships, and their functions, are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.
  • the device 1000 includes a computing unit 1001 that can be executed according to a computer program stored in a read-only memory (ROM) 1002 or loaded from a storage unit 1008 into a random-access memory (RAM) 1003. Various appropriate actions and treatments. In the RAM 1003, various programs and data necessary for the operation of the device 1000 can also be stored.
  • the computing unit 1001, ROM 1002, and RAM 1003 are connected to each other through a bus 1004.
  • An input/output (I/O) interface 1005 is also connected to the bus 1004 .
  • the input unit 1006 can be any type of equipment capable of inputting information to the device 1000, the input unit 1006 can receive input digital or character information, and generate key signal input related to user settings and/or function control of the electronic device, and can Including but not limited to mouse, keyboard, touch screen, trackpad, trackball, joystick, microphone and/or remote control.
  • the output unit 1007 may be any type of device capable of presenting information, and may include, but is not limited to, a display, a speaker, a video/audio output terminal, a vibrator, and/or a printer.
  • the storage unit 1008 may include, but is not limited to, a magnetic disk and an optical disk.
  • the communication unit 1009 allows the device 1000 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks, and may include but not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver and/or a chipset , such as BluetoothTM devices, 802.11 devices, WiFi devices, WiMax devices, cellular communication devices, and/or the like.
  • the computing unit 1001 may be various general-purpose and/or special-purpose processing components having processing and computing capabilities. Some examples of computing units 1001 include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processing processor (DSP), and any suitable processor, controller, microcontroller, etc.
  • the calculation unit 1001 executes various methods and processes described above, such as the above-mentioned method of recommending instructions.
  • the method of recommending instructions may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 1008 .
  • part or all of the computer program may be loaded and/or installed on the device 1000 via the ROM 1002 and/or the communication unit 1009.
  • the computer program When the computer program is loaded into RAM 1003 and executed by computing unit 1001, one or more steps of the method for recommending instructions described above may be performed.
  • the computing unit 1001 may be configured in any other appropriate way (for example, by means of firmware) to execute the method of recommending instructions.
  • Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips Implemented in a system of systems (SOC), load programmable logic device (CPLD), computer hardware, firmware, software, and/or combinations thereof.
  • FPGAs field programmable gate arrays
  • ASICs application specific integrated circuits
  • ASSPs application specific standard products
  • SOC system of systems
  • CPLD load programmable logic device
  • computer hardware firmware, software, and/or combinations thereof.
  • programmable processor can be special-purpose or general-purpose programmable processor, can receive data and instruction from storage system, at least one input device, and at least one output device, and transmit data and instruction to this storage system, this at least one input device, and this at least one output device an output device.
  • Program codes for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special purpose computer, or other programmable data processing devices, so that the program codes, when executed by the processor or controller, make the functions/functions specified in the flow diagrams and/or block diagrams Action is implemented.
  • the program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device.
  • a machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • a machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing.
  • machine-readable storage media would include one or more wire-based electrical connections, portable computer discs, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash memory erasable programmable read only memory
  • CD-ROM compact disk read only memory
  • magnetic storage or any suitable combination of the foregoing.
  • the systems and techniques described herein can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user. ); and a keyboard and pointing device (eg, a mouse or a trackball) through which a user can provide input to the computer.
  • a display device e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor
  • a keyboard and pointing device eg, a mouse or a trackball
  • Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and can be in any form (including Acoustic input, speech input or, tactile input) to receive input from the user.
  • the systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., as a a user computer having a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system.
  • the components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include: Local Area Network (LAN), Wide Area Network (WAN) and the Internet.
  • a computer system may include clients and servers.
  • Clients and servers are generally remote from each other and typically interact through a communication network.
  • the relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other.
  • steps may be reordered, added or deleted using the various forms of flow shown above.
  • each step described in the present disclosure may be executed in parallel, sequentially or in a different order, as long as the desired result of the technical solution disclosed in the present disclosure can be achieved, no limitation is imposed herein.

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Acoustics & Sound (AREA)
  • Human Computer Interaction (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

一种推荐指令的方法及其装置，涉及人工智能技术领域，尤其涉及车联网和智能驾舱技术领域。方案包括：获取用户的第一指令（S101）；基于第一指令，确定进入相关的第一应用场景（S102）；获取与第一应用场景相匹配的至少一个第一推荐指令并显示（S103）；响应于确定至少一个第一推荐指令未被操作，根据预设规则选择第二应用场景（S104）；以及获取与第二应用场景相匹配的至少一个第二推荐指令并显示（S105）。本方法在用户未选用指令推荐装置推荐的指令之后(例如，用户在较长的一段时间内未选用推荐的指令)，将自动从当前的应用场景切换到另一应用场景，并更新与新的应用场景相匹配的操作指令，从而实现对用户的更加智能的引导。

Description

推荐指令的方法及其装置 技术领域
本公开涉及人工智能技术领域，尤其涉及车联网和智能驾舱技术领域，具体涉及一种推荐指令的方法及其装置、电子设备、计算机存储介质和计算机程序产品。
背景技术
现有的智能设备，诸如手机、平板电脑、车载语音交互设备等的智能电子产品通常具有指令推荐装置，现有的这些指令推荐装置的指令推荐完全依赖于用户自身发出的指令，也就是只有当用户发出命令的时候，才会根据用户的命令进行相应的指令推荐。而且，现有的指令推荐装置每次推荐的指令内容是固定的。
在此部分中描述的方法不一定是之前已经设想到或采用的方法。除非另有指明，否则不应假定此部分中描述的任何方法仅因其包括在此部分中就被认为是现有技术。类似地，除非另有指明，否则此部分中提及的问题不应认为在任何现有技术中已被公认。
发明内容
本公开提供了一种推荐指令的方法，包括：获取用户的第一指令；基于第一指令，确定进入相关的第一应用场景；获取与第一应用场景相匹配的至少一个第一推荐指令并显示；响应于确定至少一个第一推荐指令未被操作，根据预设规则选择第二应用场景；以及获取与第二应用场景相匹配的至少一个第二推荐指令并显示。
根据本公开的一方面，提供了一种推荐指令的装置，包括：指令获取单元，配置成获取用户的第一指令；第一确定单元，配置成基于第一指令，确定进入相关的第一应用场景；第一获取单元，配置成获取与第一应用场景相匹配的至少一个第一推荐指令并显示；选择单元，配置成响应于确定至少一 个第一推荐指令未被操作，根据预设规则选择第二应用场景；和第二获取单元，配置成获取与第二应用场景相匹配的至少一个第二推荐指令并显示。
根据本公开的另一方面，还提供了一种存储有计算机指令的非瞬时计算机可读存储介质，其中，计算机指令用于使计算机执行上述方法。
根据本公开的另一方面，还提供了一种计算机程序产品，包括计算机程序，其中，计算机程序在被处理器执行时实现上述方法。
根据本公开的一个或多个实施例，在确定用户未选用指令推荐装置推荐的指令之后，将主动从当前的应用场景切换到另一应用场景，并更新与新的应用场景相匹配的推荐指令，从而实现对用户的更加智能的引导。另外，切换到的新的应用场景根据预设规则确定而不是随机或固定的，从而使得推荐的指令更具有目标性，使得引导推荐更加智能。
应当理解，本部分所描述的内容并非旨在标识本公开的实施例的关键或重要特征，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说明书而变得容易理解。
附图说明
附图示例性地示出了实施例并且构成说明书的一部分，与说明书的文字描述一起用于讲解实施例的示例性实施方式。所示出的实施例仅出于例示的目的，并不限制权利要求的范围。在所有附图中，相同的附图标记指代类似但不一定相同的要素。
图1示出了根据本公开的一个实施例的推荐指令的方法的流程图；
图2示出了根据本公开的一个实施例的判断第一推荐指令是否被操作的方法的流程图；
图3示出了根据本公开的一个实施例的主动切换应用场景的方法的流程图；
图4示出了根据本公开的一个实施例的确定第一推荐指令和第二推荐指令的方法的流程图；
图5示出了根据本公开的一个实施例的获取第一时长阈值的方法的流程图；
图6示出了根据本公开的一个实施例的根据预设规则选择第二应用场景的方法的流程图；
图7示出了根据本公开一个实施例的根据第一语音指令确定第一应用场景的方法的流程图；
图8示出了根据本公开一个实施例的推荐指令的装置的示意图；
图9示出了根据本公开另一个实施例的推荐指令的装置的示意图；
图10示出了能够用于实现本公开的实施例的示例性电子设备的结构框图。
具体实施方式
以下结合附图对本公开的示范性实施例做出说明，其中包括本公开实施例的各种细节以助于理解，应当将它们认为仅仅是示范性的。因此，本领域普通技术人员应当认识到，可以对这里描述的实施例做出各种改变和修改，而不会背离本公开的范围。同样，为了清楚和简明，以下的描述中省略了对公知功能和结构的描述。
在本公开中，除非另有说明，否则使用术语“第一”、“第二”等来描述各种要素不意图限定这些要素的位置关系、时序关系或重要性关系，这种术语只是用于将一个元件与另一元件区分开。在一些示例中，第一要素和第二要素可以指向该要素的同一实例，而在某些情况下，基于上下文的描述，它们也可以指代不同实例。
在本公开中对各种示例的描述中所使用的术语只是为了描述特定示例的目的，而并非旨在进行限制。除非上下文另外明确地表明，如果不特意限定要素的数量，则该要素可以是一个也可以是多个。此外，本公开中所使用的术语“和/或”涵盖所列出的项目中的任何一个以及全部可能的组合方式。
下面将结合附图详细描述本公开的实施例。
本公开首先提供了一种推荐指令的方法，图1示出了根据本公开的一个实施例的推荐指令的方法100的流程图，该方法100包括：
步骤101，获取用户的第一指令；
步骤102，基于第一指令，确定进入相关的第一应用场景；
步骤103，获取与第一应用场景相匹配的至少一个第一推荐指令并显示；
步骤104，响应于确定至少一个第一推荐指令未被操作，根据预设规则选择第二应用场景；以及
步骤105，获取与第二应用场景相匹配的至少一个第二推荐指令并显示。
本公开实施例的推荐指令的方法在确定用户未选择指令推荐装置推荐的指令之后，将主动从当前的应用场景切换到另一应用场景，并更新与新的应用场景相匹配的推荐指令，从而实现对用户的更加智能的引导。另外，切换到的新的应用场景根据预设规则确定而不是随机或固定的，从而使得推荐的指令更具有目标性，使得引导推荐更加智能。
在步骤101中，指令推荐装置获取用户的第一指令。在一些实施例中，指令推荐装置可以是车载语音交互装置，在另外一些实施例中，指令推荐装置可以是其他人工智能装置或用于电子设备的指令推荐装置。上述第一指令可以是语音指令、文字指令或其他形式的指令。
在步骤102中，可以对第一指令的指令内容进行分析，从而得到用户的意图。根据用户的意图进入相关的第一应用场景。上述第一应用场景可以是指令推荐装置包含的多种应用场景中的一种，每种应用场景包括与该场景相关的功能以及页面显示。以车载语音交互装置为例，其可以包括诸如：导航、音乐、会话等多个应用场景，例如：在导航应用场景下，车载语音交互装置具有地图显示和导航功能，并在相关页面显示附近的地图；在音乐模式下，车载语音交互装置具有音乐播放功能，并在相关页面显示可以播放的歌曲等等。当用户发出第一指令后，例如：用户语音指示“播放音乐”，则车载语音交互装置将根据用户意图进入音乐应用场景。
在步骤103中，获取并显示与第一应用场景相匹配的第一推荐指令。如上所述，指令推荐装置具有多种应用场景，每一种应用场景均具有与之相匹配的推荐指令。在每一种应用场景下，指令推荐装置均能够选择性地显示这些推荐指令以供用户选用，用户可以通过操作指令推荐装置的触控显示屏上显示的这些推荐指令来选用这些指令，或者仍然通过语音控制来选用指令。还以车载语音交互装置为例，导航应用场景可以包括诸如：地址查询、附近的目标地点推荐、智能语音导航等推荐指令，音乐应用场景可以包括诸如：播放音乐、选择下一曲、暂停音乐等推荐指令。可以理解，每一种应用场景的匹配的推荐指令可以是预先确定好的，例如可以为每一个应用场景预先设 定好一个匹配的推荐指令集，在步骤103中，可以获取并显示该指令集中的一些或全部。
在步骤104中，若用户没有选用指令推荐装置所推荐的至少一个第一推荐指令，则说明用户对于当前应用场景的指令不感兴趣，那么则根据预设规则选择第二应用场景。该预设规则可以根据用户的喜好进行选择，从而使得推荐的指令更具有目标性，使得引推荐更加智能。例如，可以获取用户使用每一个应用场景的频率的历史日志，并基于该历史日志选择用户使用最频繁的应用场景作为第二应用场景。
在步骤105，获取与第二应用场景相匹配的至少一个第二推荐指令并显示。在显示第二推荐指令时，可以使用第二推荐指令代替第一推荐指令，以对推荐指令的显示进行更新。在一些实施例中，在显示第二推荐指令时，可以同时自动切换至第二应用场景，以便于用户进行操作，在另外一些实施例中，在显示第二推荐指令时，可以仍然停留在第一应用场景，在后续用户选用第二推荐指令时再切换到第二应用场景。
图2示出了根据本公开一个实施例的判断第一推荐指令是否被操作的方法200的流程图，如图2所示，该方法200包括：
步骤201，记录在第一应用场景下，至少一个第一推荐指令未被操作的持续时长；
步骤202，判断持续时长是否超过第一时长阈值；
步骤203，若步骤202的判断结果为是，确定至少一个第一推荐指令未被操作。
步骤204，若步骤202的判断结果为否，在至少一个第一推荐指令被操作的时间点开始重新记录持续时长。
本实施例的方法通过记录第一推荐指令未被操作的持续时长来判断第一指令是否被操作。在步骤201中，在指令推荐装置显示第一推荐指令之后，开始计时，直到用户选用了显示的第一推荐指令为止。在一些实施例中，指令推荐装置可以同时显示多个第一推荐指令，在用户对其中一个指令进行操作之后，则计时结束。
在步骤202中，第一时长阈值是预先确定好的并且和第一应用场景相对应。具体地，每个应用场景均具有预先确定好的与该应用场景对应的时长阈 值，每个时长阈值被用作表示未对当前应用场景的推荐指令进行操作的时长标准。例如：第一应用场景(例如：导航应用场景)对应于第一时长阈值(例如：100s)，第二应用场景(例如：音乐应用场景)对应于第二时长阈值(例如：80s)。
在步骤203中，若在第一时长阈值内，用户未选用第一推荐指令，那么确定至少一个第一推荐指令未被操作。还以车载语音交互装置为例，上述第一应用场景例如可以是导航场景，与导航场景对应的第一时长阈值为100s，那么在显示第一推荐指令之后的100s内，若用户始终未选用第一推荐指令中的任何一个，那么确定至少一个第一推荐指令未被操作。
在步骤204中，若在持续时长还未达到第一时长阈值之前，用户选用了第一推荐指令中的一个或多个，那么确定至少一个第一推荐指令被操作，这表示用户仍然在使用第一应用场景的功能。此时可以将记录的持续时长清零，并在用户选用第一推荐指令的时间点重新记录持续时长。
在本发明另外一些实施例中，在对上述持续时长进行计时期间，还可以根据用户新的指令切换应用场景，图3示出了根据本公开的一个实施例的切换应用场景的方法300的流程图，该方法300包括：
步骤301，判断在第一时长阈值的持续时长内，是否获取到用户的第二指令；
步骤302，响应于判定获取到用户的第二指令，基于第二指令，确定进入相关的第三应用场景；
步骤303，获取与第三应用场景相匹配的至少一个第三推荐指令并显示。
在步骤301中，在持续时长未达到第一时长阈值之前，判断是否获取到用户的第二指令，其中，第二指令可以是不同于第一指令的新的指令；
在步骤302中，基于用户新发出的第二指令，确定进入相关的第三应用场景。若用户主动进行应用场景的切换，那么根据用户的新的意图切换应用场景。例如，当前指令推荐装置处于导航应用场景，随后用户发出了“播放音乐”的第二指令，那么指令推荐装置切换到相关的音乐应用场景(即第三应用场景)。
在步骤303中，与方法100中的步骤103类似地，获取与第三应用场景相匹配的至少一个第三推荐指令并显示，可以使用第三推荐指令替换第一推 荐指令，从而实现推荐指令的更新。本实施例的方法能够根据用户新的指令切换应用场景，并相应地更新推荐指令，因此使得推荐指令过程更加智能。
图4示出了根据本公开一个实施例的确定第一推荐指令和第二推荐指令的方法400的流程图。如图4所示，该方法400包括：
步骤401，分别获取用户在多个应用场景下发出的多个历史指令的指令参数，应用场景包括第一应用场景和第二应用场景；以及
步骤402，基于多个历史指令的指令参数，确定与第一应用场景相匹配的至少一个第一推荐指令以及与第二应用场景相匹配的至少一个第二推荐指令。
在步骤401中，在实施图1所示的推荐指令的方法之前，可以获取用户在多个应用场景下发出的历史指令的指令参数。上述多个应用场景包括第一应用场景和第二应用场景，上述历史指令可以包括在第一应用场景下用户发出的第一历史指令，以及在第二应用场景下用户发出的第二历史指令。上述指令参数可以是任何与该历史指令相关的参数，例如可以是：指令关键词、指令使用频率和指令使用时长等等。示例性的，在音乐应用场景下，用户曾经发出过“播放XXX歌曲”的历史指令，则获取与该指令相关的指令参数，该指令参数例如是：关键词“XXX”、该历史指令的使用频率4次/1天等等。上述所列举的指令参数仅仅是示例性的，在公开另外一些实施例中，还可以获取例如使用总次数等其他相关的指令参数，这里不再一一列举。
在步骤402中，利用步骤401中获得的各个应用场景中的历史指令的指令参数按照相关的规则分别确定与每个应用场景相匹配的推荐指令集，每个推荐指令集包含至少一个推荐指令。具体地，可以根据第一应用场景中的第一历史指令的指令参数确定包含至少一个第一推荐指令的第一推荐指令集，根据第二应用场景中的第二历史指令的指令参数确定包含至少一个第二推荐指令的第二推荐指令集。上述相关的规则可以是特定的算法，例如人工智能算法，具体地，可以将包含上述历史指令的指令参数的多个样本输入到训练模型中进行训练，得到训练好的模型，后续可以将步骤401中得到的历史指令的指令参数输入到训练好的模型中，得到相应的推荐指令集。
本实施例的方法使用用户历史指令的指令参数确定推荐指令，使得得到的推荐指令更加偏向于用户的喜好，能够引起用户的兴趣，从而提高了用户的使用体验。
图5示出了根据本公开一个实施例的获取第一时长阈值的方法500的流程图。如图5所示，该方法500包括：
步骤501，获取用户每次使用第一应用场景的时长信息；以及
步骤502，基于时长信息，确定上述第一时长阈值。
在本实施例中，还可以通过分析相关的用户历史使用数据得到上述第一时长阈值。在步骤501中，可以在实施图1所示的方法100之前，获取每一次使用第一应用场景的时长信息。
在步骤502中，基于上述一个或多个时长信息，确定第一时长阈值。示例性地，可以使用步骤501中得到的多个时长信息计算得到每次使用第一应用场景的平均时长，并将该平均时长作为第一时长阈值。
图6示出了根据本公开一个实施例的根据预设规则选择第二应用场景的方法的流程图600，如图6所示，该方法600包括：
步骤601，分别获取与多个应用场景相关的用户交互信息；以及
步骤602，基于用户交互信息，从多个应用场景中选择第二应用场景。
在本实施例中，还可以通过分析相关的用户历史使用数据从多个应用场景中选择第二应用场景。在步骤601中，用户交互信息可以包括与每个应用场景相关的历史使用信息，例如：每个应用场景的使用频率、使用总时长等等。示例性地，用户交互信息可以是每个应用场景的使用频率，若指令推荐装置共具有5个应用场景，那么可以分别获取这5个应用场景的历史使用频率，即第一使用频率至第五使用频率。
在步骤602中，可以基于步骤601中获取的第一使用频率至第五使用频率确定第二应用场景。例如可以选择5个应用场景中使用频率最高的应用场景作为上述第二应用场景。可以理解，使用频率最高意味着该应用场景是用户偏好使用的应用场景，将用户偏好的应用场景作为后续推荐指令的依据能够实现对用户的智能引导，给出能够引起用户兴趣的推荐指令，从而提高了用户的使用体验。
在一些实施例中，第一指令可以是第一语音指令，图7示出了根据本公开一个实施例的根据第一语音指令确定第一应用场景的方法700的流程图，如图7所示，该方法700包括：
步骤701，对第一语音指令进行语音识别，得到语音识别文本；
步骤702，对语音识别文本进行语义解析，得到语义解析结果；以及
步骤703，根据语义解析结果，确定将要进入的第一应用场景。
在步骤701中，可以将接收到的第一语音指令上传至云服务器，云服务器可以对其进行语音识别得到指令文本。
在步骤702中，云服务器可以对指令文本进行进一步的语义解析，得到语义解析结果，并发送返回至指令推荐装置。上述语义解析方法例如可以使用自然语言处理(Natural Language Processing,NLP)，上述解析结果例如可以是指令文本中的关键词信息。示例性地，若步骤701中得到指令文本是“播放音乐”，在步骤702中对其进行语义解析得到关键词“音乐”。在步骤703中则根据关键词“音乐”，确定相关的音乐应用场景为将要进入的第一应用场景。
本公开还提供了一种推荐指令的装置800，图8示出了根据本公开一个实施例的推荐指令的装置800的示意图，该装置800包括：指令获取单元810，配置成获取用户的第一指令；第一确定单元820，配置成基于第一指令，确定进入相关的第一应用场景；第一获取单元830，配置成获取与第一应用场景相匹配的至少一个第一推荐指令并显示；选择单元840，配置成响应于确定至少一个第一推荐指令未被操作，根据预设规则选择第二应用场景；和第二获取单元850，配置成获取与第二应用场景相匹配的至少一个第二推荐指令并显示。
图9示出了根据本公开一个实施例的推荐指令的装置900的示意图。在一些实施例中，选择单元940包括：计时模块941，配置成记录在第一应用场景下，至少一个第一推荐指令未被操作的持续时长；第一判断模块942，配置成判断持续时长是否超过第一时长阈值，第一时长阈值与第一应用场景相对应；和第一确定模块943，配置成响应于判定持续时长超过第一时长阈值，确定至少一个第一推荐指令未被操作。
在一些实施例中，上述装置900还包括：指令参数获取单元961，配置成分别获取用户在多个应用场景下发出的历史指令的指令参数，应用场景包括第一应用场景和第二应用场景；和第二确定单元962，基于指令参数，确定与第一应用场景相匹配的至少一个第一推荐指令以及与第二应用场景相匹配的至少一个第二推荐指令。
在一些实施例中，指令参数包括以下参数中的一种或多种：指令关键词、指令使用频率和指令使用时长。
在一些实施例中，上述装置900还包括：时长信息获取单元971，配置成获取用户每次使用第一应用场景的时长信息；和第三确定单元972，配置成基于在时长信息，确定第一时长阈值。
在一些实施例中，选择单元940还包括：交互信息获取模块944，配置成分别获取与多个应用场景相关的用户交互信息；和选择模块945，配置成基于用户交互信息，从多个应用场景中选择第二应用场景。
在一些实施例中，第一指令包括第一语音指令，第一确定单元920包括：语音识别模块921，配置成对第一语音指令进行语音识别，得到语音识别文本；和语义解析模块922，配置成对语音识别文本进行语义解析，得到语义解析结果；其中第一确定单元，还配置成根据语义解析结果，确定将要进入的第一应用场景。
在一些实施例中，计时模块941还配置成：响应于判定持续时长未超过第一时长阈值，在至少一个第一推荐指令被操作的时间点开始重新记录持续时长。
在一些实施例中，上述装置900还包括更新单元980，更新单元980包括：第二判断模块981，配置成判断在第一时长阈值的持续时长内，是否获取到用户的第二指令；第二确定模块982，配置成响应于判定获取到用户的第二指令，基于第二指令，确定进入相关的第三应用场景；和推荐指令获取模块983，配置成获取与第三应用场景相匹配的至少一个第三推荐指令并显示。
上述单元910至单元980及其各个模块的操作方法与上述方法100至方法700中各步骤的操作方法类似，这里不再赘述。
根据本公开的实施例，还提供了一种电子设备、一种可读存储介质和一种计算机程序产品。
参考图10，现将描述可以作为本公开的服务器或客户端的电子设备1000的结构框图，其是可以应用于本公开的各方面的硬件设备的示例。电子设备旨在表示各种形式的数字电子的计算机设备，诸如，膝上型计算机、台式计算机、工作台、个人数字助理、服务器、刀片式服务器、大型计算机、和其它适合的计算机。电子设备还可以表示各种形式的移动装置，诸如，个人数字处理、蜂窝电话、智能电话、可穿戴设备和其它类似的计算装置。本文所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例，并且不意在限制本文中描述的和/或者要求的本公开的实现。
如图10所示，设备1000包括计算单元1001，其可以根据存储在只读存储器(ROM)1002中的计算机程序或者从存储单元1008加载到随机访问存储器(RAM)1003中的计算机程序，来执行各种适当的动作和处理。在RAM 1003中，还可存储设备1000操作所需的各种程序和数据。计算单元1001、ROM 1002以及RAM 1003通过总线1004彼此相连。输入/输出(I/O)接口1005也连接至总线1004。
设备1000中的多个部件连接至I/O接口1005，包括：输入单元1006、输出单元1007、存储单元1008以及通信单元1009。输入单元1006可以是能向设备1000输入信息的任何类型的设备，输入单元1006可以接收输入的数字或字符信息，以及产生与电子设备的用户设置和/或功能控制有关的键信号输入，并且可以包括但不限于鼠标、键盘、触摸屏、轨迹板、轨迹球、操作杆、麦克风和/或遥控器。输出单元1007可以是能呈现信息的任何类型的设备，并且可以包括但不限于显示器、扬声器、视频/音频输出终端、振动器和/或打印机。存储单元1008可以包括但不限于磁盘、光盘。通信单元1009允许设备1000通过诸如因特网的计算机网络和/或各种电信网络与其他设备交换信息/数据，并且可以包括但不限于调制解调器、网卡、红外通信设备、无线通信收发机和/或芯片组，例如蓝牙TM设备、802.11设备、WiFi设备、WiMax设备、蜂窝通信设备和/或类似物。
计算单元1001可以是各种具有处理和计算能力的通用和/或专用处理组件。计算单元1001的一些示例包括但不限于中央处理单元(CPU)、图形处 理单元(GPU)、各种专用的人工智能(AI)计算芯片、各种运行机器学习模型算法的计算单元、数字信号处理器(DSP)、以及任何适当的处理器、控制器、微控制器等。计算单元1001执行上文所描述的各个方法和处理，例如上述推荐指令的方法。例如，在一些实施例中，推荐指令的方法可被实现为计算机软件程序，其被有形地包含于机器可读介质，例如存储单元1008。在一些实施例中，计算机程序的部分或者全部可以经由ROM 1002和/或通信单元1009而被载入和/或安装到设备1000上。当计算机程序加载到RAM 1003并由计算单元1001执行时，可以执行上文描述的推荐指令的方法的一个或多个步骤。备选地，在其他实施例中，计算单元1001可以通过其他任何适当的方式(例如，借助于固件)而被配置为执行推荐指令的方法。
本文中以上描述的系统和技术的各种实施方式可以在数字电子电路系统、集成电路系统、场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、芯片上系统的系统(SOC)、负载可编程逻辑设备(CPLD)、计算机硬件、固件、软件、和/或它们的组合中实现。这些各种实施方式可以包括：实施在一个或者多个计算机程序中，该一个或者多个计算机程序可在包括至少一个可编程处理器的可编程系统上执行和/或解释，该可编程处理器可以是专用或者通用可编程处理器，可以从存储系统、至少一个输入装置、和至少一个输出装置接收数据和指令，并且将数据和指令传输至该存储系统、该至少一个输入装置、和该至少一个输出装置。
用于实施本公开的方法的程序代码可以采用一个或多个编程语言的任何组合来编写。这些程序代码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器或控制器，使得程序代码当由处理器或控制器执行时使流程图和/或框图中所规定的功能/操作被实施。程序代码可以完全在机器上执行、部分地在机器上执行，作为独立软件包部分地在机器上执行且部分地在远程机器上执行或完全在远程机器或服务器上执行。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可 读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
为了提供与用户的交互，可以在计算机上实施此处描述的系统和技术，该计算机具有：用于向用户显示信息的显示装置(例如，CRT(阴极射线管)或者LCD(液晶显示器)监视器)；以及键盘和指向装置(例如，鼠标或者轨迹球)，用户可以通过该键盘和该指向装置来将输入提供给计算机。其它种类的装置还可以用于提供与用户的交互；例如，提供给用户的反馈可以是任何形式的传感反馈(例如，视觉反馈、听觉反馈、或者触觉反馈)；并且可以用任何形式(包括声输入、语音输入或者、触觉输入)来接收来自用户的输入。
可以将此处描述的系统和技术实施在包括后台部件的计算系统(例如，作为数据服务器)、或者包括中间件部件的计算系统(例如，应用服务器)、或者包括前端部件的计算系统(例如，具有图形用户界面或者网络浏览器的用户计算机，用户可以通过该图形用户界面或者该网络浏览器来与此处描述的系统和技术的实施方式交互)、或者包括这种后台部件、中间件部件、或者前端部件的任何组合的计算系统中。可以通过任何形式或者介质的数字数据通信(例如，通信网络)来将系统的部件相互连接。通信网络的示例包括：局域网(LAN)、广域网(WAN)和互联网。
计算机系统可以包括客户端和服务器。客户端和服务器一般远离彼此并且通常通过通信网络进行交互。通过在相应的计算机上运行并且彼此具有客户端-服务器关系的计算机程序来产生客户端和服务器的关系。
应该理解，可以使用上面所示的各种形式的流程，重新排序、增加或删除步骤。例如，本公开中记载的各步骤可以并行地执行、也可以顺序地或以不同的次序执行，只要能够实现本公开公开的技术方案所期望的结果，本文在此不进行限制。
虽然已经参照附图描述了本公开的实施例或示例，但应理解，上述的方法、系统和设备仅仅是示例性的实施例或示例，本公开的范围并不由这些实施例或示例限制，而是仅由授权后的权利要求书及其等同范围来限定。实施 例或示例中的各种要素可以被省略或者可由其等同要素替代。此外，可以通过不同于本公开中描述的次序来执行各步骤。进一步地，可以以各种方式组合实施例或示例中的各种要素。重要的是随着技术的演进，在此描述的很多要素可以由本公开之后出现的等同要素进行替换。

Claims (22)

  1. 一种推荐指令的方法，包括：
    获取用户的第一指令；
    基于所述第一指令，确定进入相关的第一应用场景；
    获取与所述第一应用场景相匹配的至少一个第一推荐指令并显示；
    响应于确定所述至少一个第一推荐指令未被操作，根据预设规则选择第二应用场景；以及
    获取与所述第二应用场景相匹配的至少一个第二推荐指令并显示。
  2. 根据权利要求1所述的方法，其中，确定所述至少一个第一推荐指令是否被操作包括：
    记录在所述第一应用场景下，所述至少一个第一推荐指令未被操作的持续时长；
    判断所述持续时长是否超过第一时长阈值；
    响应于判定所述持续时长超过所述第一时长阈值，确定所述至少一个第一推荐指令未被操作。
  3. 根据权利要求1所述的方法，其中，在获取用户的第一指令之前还包括：
    分别获取用户在多个应用场景下发出的多个历史指令的指令参数，所述多个应用场景包括所述第一应用场景和所述第二应用场景；以及
    基于所述多个历史指令的指令参数，确定与所述第一应用场景相匹配的所述至少一个第一推荐指令以及与所述第二应用场景相匹配的所述至少一个第二推荐指令。
  4. 根据权利要求3所述的方法，其中，所述指令参数包括以下参数中的一种或多种：指令关键词、指令使用频率和指令使用时长。
  5. 根据权利要求2所述的方法，其中，在获取用户的第一指令之前还包括：
    获取用户每次使用所述第一应用场景的时长信息；以及
    基于所述时长信息，确定所述第一时长阈值。
  6. 根据权利要求1所述的方法，其中，响应于确定所述至少一个第一推荐指令未被操作，根据预设规则选择第二应用场景包括：
    分别获取与多个应用场景相关的用户交互信息；并且
    基于所述用户交互信息，从所述多个应用场景中选择所述第二应用场景。
  7. 根据权利要求1所述的方法，其中，所述第一指令包括第一语音指令，并且，基于所述第一指令，确定进入第一应用场景包括：
    对所述第一语音指令进行语音识别，得到语音识别文本；
    对所述语音识别文本进行语义解析，得到语义解析结果；以及
    根据所述语义解析结果，确定将要进入的所述第一应用场景。
  8. 根据权利要求2所述的方法，其中，在判断所述持续时长是否超过第一时长阈值之后还包括：
    响应于判定所述持续时长未超过所述第一时长阈值，在所述至少一个第一推荐指令被操作的时间点开始重新记录所述持续时长。
  9. 根据权利要求8所述的方法，还包括：
    判断在所述第一时长阈值的持续时长内，是否获取到用户的第二指令；
    响应于判定获取到用户的第二指令，基于所述第二指令，确定进入相关的第三应用场景；
    获取与所述第三应用场景相匹配的至少一个第三推荐指令并显示。
  10. 根据权利要求1至9中任一项所述的方法，其中，所述方法应用于车载语音交互。
  11. 一种推荐指令的装置，包括：
    指令获取单元，配置成获取用户的第一指令；
    第一确定单元，配置成基于所述第一指令，确定进入相关的第一应用场景；
    第一获取单元，配置成获取与所述第一应用场景相匹配的至少一个第一推荐指令并显示；
    选择单元，配置成响应于确定所述至少一个第一推荐指令未被操作，根据预设规则选择第二应用场景；和
    第二获取单元，配置成获取与所述第二应用场景相匹配的至少一个第二推荐指令并显示。
  12. 根据权利要求11所述的装置，其中，所述选择单元包括：
    计时模块，配置成记录在所述第一应用场景下，所述至少一个第一推荐指令未被操作的持续时长；
    第一判断模块，配置成判断所述持续时长是否超过第一时长阈值；和
    第一确定模块，配置成响应于判定所述持续时长超过第一时长阈值，确定所述至少一个第一推荐指令未被操作。
  13. 根据权利要求11所述的装置，还包括：
    指令参数获取单元，配置成分别获取用户在多个应用场景下发出的多个历史指令的指令参数，所述多个应用场景包括所述第一应用场景和所述第二应用场景；和
    第二确定单元，基于所述多个历史指令的指令参数，确定与所述第一应用场景相匹配的所述至少一个第一推荐指令以及与所述第二应用场景相匹配的所述至少一个第二推荐指令。
  14. 根据权利要求13所述的装置，其中，所述指令参数包括以下参数中的一种或多种：指令关键词、指令使用频率和指令使用时长。
  15. 根据权利要求12所述的装置，还包括：
    时长信息获取单元，配置成获取用户每次使用所述第一应用场景的时长信息；和
    第三确定单元，配置成基于所述时长信息，确定所述第一时长阈值。
  16. 根据权利要求11所述的装置，其中，所述选择单元还包括：
    交互信息获取模块，配置成分别获取与多个应用场景相关的用户交互信息；和
    选择模块，配置成基于所述用户交互信息，从所述多个应用场景中选择所述第二应用场景。
  17. 根据权利要求11所述的装置，其中，所述第一指令包括第一语音指令，所述第一确定单元包括：
    语音识别模块，配置成对所述第一语音指令进行语音识别，得到语音识别文本；和
    语义解析模块，配置成对所述语音识别文本进行语义解析，得到语义解析结果；其中
    所述第一确定单元，还配置成根据所述语义解析结果，确定将要进入的所述第一应用场景。
  18. 根据权利要求12所述的装置，其中，所述计时模块还配置成：
    响应于判定所述持续时长未超过所述第一时长阈值，在所述至少一个第一推荐指令被操作的时间点开始重新记录所述持续时长。
  19. 根据权利要求18所述的装置，还包括更新单元，所述更新单元包括：
    第二判断模块，配置成判断在所述第一时长阈值的持续时长内，是否获取到用户的第二指令；
    第二确定模块，配置成响应于判定获取到用户的第二指令，基于所述第二指令，确定进入相关的第三应用场景；和
    推荐指令获取模块，配置成获取与所述第三应用场景相匹配的至少一个第三推荐指令并显示。
  20. 一种电子设备，包括：
    至少一个处理器；以及
    与所述至少一个处理器通信连接的存储器；其中
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行权利要求1-10中任一项所述的方法。
  21. 一种存储有计算机指令的非瞬时计算机可读存储介质，其中，所述计算机指令用于使所述计算机执行根据权利要求1-10中任一项所述的方法。
  22. 一种计算机程序产品，包括计算机程序，其中，所述计算机程序在被处理器执行时实现权利要求1-10中任一项所述的方法。
PCT/CN2021/113575 2021-08-19 2021-08-19 推荐指令的方法及其装置 WO2023019517A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/113575 WO2023019517A1 (zh) 2021-08-19 2021-08-19 推荐指令的方法及其装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/113575 WO2023019517A1 (zh) 2021-08-19 2021-08-19 推荐指令的方法及其装置

Publications (1)

Publication Number Publication Date
WO2023019517A1 true WO2023019517A1 (zh) 2023-02-23

Family

ID=85239339

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/113575 WO2023019517A1 (zh) 2021-08-19 2021-08-19 推荐指令的方法及其装置

Country Status (1)

Country Link
WO (1) WO2023019517A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103187058A (zh) * 2011-12-28 2013-07-03 上海博泰悦臻电子设备制造有限公司 车内语音对话系统
CN109299994A (zh) * 2018-07-27 2019-02-01 北京三快在线科技有限公司 推荐方法、装置、设备及可读存储介质
CN110065455A (zh) * 2019-04-24 2019-07-30 深圳市麦谷科技有限公司 车载功能智能启动方法、装置、计算机设备及存储介质
CN111026932A (zh) * 2019-12-20 2020-04-17 北京百度网讯科技有限公司 人机对话交互方法、装置、电子设备和存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103187058A (zh) * 2011-12-28 2013-07-03 上海博泰悦臻电子设备制造有限公司 车内语音对话系统
CN109299994A (zh) * 2018-07-27 2019-02-01 北京三快在线科技有限公司 推荐方法、装置、设备及可读存储介质
CN110065455A (zh) * 2019-04-24 2019-07-30 深圳市麦谷科技有限公司 车载功能智能启动方法、装置、计算机设备及存储介质
CN111026932A (zh) * 2019-12-20 2020-04-17 北京百度网讯科技有限公司 人机对话交互方法、装置、电子设备和存储介质

Similar Documents

Publication Publication Date Title
US10831345B2 (en) Establishing user specified interaction modes in a question answering dialogue
CN106658129B (zh) 基于情绪的终端控制方法、装置及终端
JP6718828B2 (ja) 情報入力方法および装置
WO2017186050A1 (zh) 人机智能问答系统的断句识别方法和装置
EP3593346B1 (en) Graphical data selection and presentation of digital content
KR101072176B1 (ko) 음성 대화 의미처리를 통한 사용자 프로파일 자동 구성 장치, 및 그에 따른 콘텐츠 추천 장치
RU2685392C1 (ru) Обеспечение автономной семантической обработки в устройстве с ограниченными ресурсами
US20220148576A1 (en) Electronic device and control method
JP6728319B2 (ja) 人工知能機器で複数のウェイクワードを利用したサービス提供方法およびそのシステム
US20180046470A1 (en) Methods, systems, and media for presenting a user interface customized for a predicted user activity
CN110503954B (zh) 语音技能启动方法、装置、设备及存储介质
US9870772B2 (en) Guiding device, guiding method, program, and information storage medium
CN116501960B (zh) 内容检索方法、装置、设备及介质
CN116521841B (zh) 用于生成回复信息的方法、装置、设备及介质
KR102218640B1 (ko) 디스플레이 장치 및 디스플레이 장치의 제어 방법
CN111414512A (zh) 一种基于语音搜索的资源推荐方法、装置及电子设备
WO2023019517A1 (zh) 推荐指令的方法及其装置
KR102226427B1 (ko) 호칭 결정 장치, 이를 포함하는 대화 서비스 제공 시스템, 호칭 결정을 위한 단말 장치 및 호칭 결정 방법
KR102222637B1 (ko) 감성 분석 장치, 이를 포함하는 대화형 에이전트 시스템, 감성 분석을 수행하기 위한 단말 장치 및 감성 분석 방법
CN114760274B (zh) 在线课堂的语音交互方法、装置、设备及存储介质
JP2022547418A (ja) 全二重による音声対話の方法
CN113360590B (zh) 兴趣点信息的更新方法、装置、电子设备及存储介质
CN113395537B (zh) 用于推荐直播间的方法和装置
CN114424148B (zh) 电子设备及其用于提供手册的方法
US20210104240A1 (en) Description support device and description support method

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: 21953761

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE