WO2021184794A1 - 对话文本的技能领域确定方法及装置 - Google Patents

对话文本的技能领域确定方法及装置 Download PDF

Info

Publication number
WO2021184794A1
WO2021184794A1 PCT/CN2020/129342 CN2020129342W WO2021184794A1 WO 2021184794 A1 WO2021184794 A1 WO 2021184794A1 CN 2020129342 W CN2020129342 W CN 2020129342W WO 2021184794 A1 WO2021184794 A1 WO 2021184794A1
Authority
WO
WIPO (PCT)
Prior art keywords
skill
field
semantic slot
domain
knowledge base
Prior art date
Application number
PCT/CN2020/129342
Other languages
English (en)
French (fr)
Inventor
朱成亚
樊帅
李春
石韡斯
Original Assignee
思必驰科技股份有限公司
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 思必驰科技股份有限公司 filed Critical 思必驰科技股份有限公司
Priority to US17/912,112 priority Critical patent/US20230133146A1/en
Priority to JP2022555166A priority patent/JP7481475B2/ja
Priority to EP20925821.9A priority patent/EP4123497A4/en
Publication of WO2021184794A1 publication Critical patent/WO2021184794A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/22Procedures used during a speech recognition process, e.g. man-machine dialogue
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/20Natural language analysis
    • G06F40/279Recognition of textual entities
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/30Semantic analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/30Semantic analysis
    • G06F40/35Discourse or dialogue representation
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/08Speech classification or search
    • G10L15/18Speech classification or search using natural language modelling
    • G10L15/1815Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/22Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223Execution procedure of a spoken command
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00Speech recognition
    • G10L15/22Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/226Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics
    • G10L2015/228Procedures used during a speech recognition process, e.g. man-machine dialogue using non-speech characteristics of application context

Definitions

  • the present invention relates to the field of intelligent speech, in particular to a method and device for determining the field of skills of dialogue text.
  • the corresponding skills hit by the user's dialogue will be determined, so as to enter the corresponding skill field to answer the user.
  • skill areas regular-based matching methods are usually used.
  • TV voice products contain movie skills, and the rules used are usually "playing ******", for example, "playing Andy Lau's love for ten thousand years", task-based skills analysis
  • the task-based skills of film and television analysis are as follows, the filmmaker: Maria Teng, the title: the sweetness.
  • the default priority skill will be used to reply to the user. For example, in TV voice products, film and television skills will have a higher priority than music skills. For the "Play Maria Teng's Sweet Honey” dialogue, TV voice products will give priority to film skills. If there is no Teresa in the "Filmmaker” dictionary or the “Title” dictionary does not have sweetness, then the music will be re-selected Skills, but the content of the parsed semantic slots “Teng Lijun” and "Sweet Honey” exist in the "filmmaker” and “title” lexicons respectively, but the corresponding semantic slots are not connected, resulting in an error in the skill domain. The dialogue that should have fallen into music skills falls into film and television skills, and it is impossible to find a sweet movie starring Maria Teng, and the user experience is poor.
  • an embodiment of the present invention provides a method for determining a skill domain of a dialog text, including:
  • the second skill field is determined as the skill field of the dialogue text.
  • an embodiment of the present invention provides an apparatus for determining a field of skill in a dialog text, including:
  • the information determination program module determines the skill field hit by the dialog text input by the user, and the name semantic slot and the character semantic slot under the skill field;
  • the first matching program module is configured to determine whether the name semantic slot and the character semantic slot match according to the knowledge base of the first skill field when the skill field hit by the dialogue text is the first skill field;
  • the second matching program module is configured to, if the name semantic slot and the character semantic slot do not match under the knowledge base of the first skill domain, further judge the name semantic slot and the character semantic slot according to the knowledge base of the second skill domain. Whether the character semantic slot matches;
  • the skill domain determination program module is configured to determine the second skill domain as the skill domain of the dialog text if the name semantic slot matches the character semantic slot in the knowledge base of the second skill domain.
  • an electronic device which includes: at least one processor, and a memory communicatively connected with the at least one processor, wherein the memory stores instructions that can be executed by the at least one processor, The instructions are executed by the at least one processor, so that the at least one processor can execute the steps of the method for determining the field of skill of the dialog text of any embodiment of the present invention.
  • an embodiment of the present invention provides a storage medium on which a computer program is stored, characterized in that, when the program is executed by a processor, it implements the steps of the method for determining the field of skill of the dialog text of any embodiment of the present invention.
  • the beneficial effects of the embodiments of the present invention are that the association between semantic slots is established, the error rate of field classification is reduced, the skill field hit by the user's voice dialogue is more accurate, and the user's use effect is improved.
  • FIG. 1 is a flowchart of a method for determining a skill domain of a dialog text according to an embodiment of the present invention
  • FIG. 2 is a schematic structural diagram of an apparatus for determining a field of skill in a dialog text according to an embodiment of the present invention
  • FIG. 3 is a schematic structural diagram of an embodiment of the electronic device of the present invention.
  • the embodiment of the present invention provides a method for determining the skill domain of a dialog text, which is applied to an electronic device.
  • the electronic device may be a smart TV, a smart phone, a smart speaker, a smart car device, a smart screen, etc., which is not limited in the present invention.
  • Fig. 1 is a flowchart of a method for determining a skill domain of a dialog text according to an embodiment of the present invention, which includes the following steps:
  • S11 The electronic device determines the skill domain hit by the dialogue text input by the user, and the name semantic slot and the character semantic slot under the skill domain;
  • a knowledge base in the field of film and television and a knowledge base in the field of music are established in advance.
  • the knowledge base in the field of film and television can search for all corresponding "filmmakers" by "title", for example, the film title "Sweet Honey” corresponds to Filmmakers include: Chen Kexin, Maggie Cheung, Liming, and Zeng Zhiwei.
  • the filmmaker not only can include information about actors, but also information about directors.
  • step S11 electronic devices (for example, smart TVs) are usually equipped with TV voice products.
  • TV voice products include film skills and music skills, but the priority of film and television skills is higher than that of music skills.
  • the two skills have the same analytical confidence Next, prioritize film and television skills.
  • the intelligent dialogue voice products also include movie skills and music skills, but the priority of music skills is higher than that of film and television skills. In the case of the same analytical confidence of the two skills, priority is given to music Skill.
  • step S12 since it is a smart TV, the film and television skill is the first skill, and the music skill is the second skill.
  • the "Play Maria Teng's Sweet Honey” priority hits the film and television skill field, it will judge whether “Sweet Honey” and "Teng Lijun” match according to the film and television domain knowledge base.
  • the film title "Sweet Honey” in the knowledge base in the field of film and television, the corresponding filmmakers are: Chen Kexin, Zhang Manyu, Liming, and Zeng Zhiwei. Therefore, the name semantic slot in the film and television field does not match the character semantic slot.
  • step S13 the name semantic slot under the film and television domain determined in step S12 does not match the character semantic slot, and the movie title "Sweet Honey” in the film and television domain knowledge base does not have "Teng Lijun” in the corresponding filmmaker. .
  • the knowledge base in the field of "music skills” is further used to determine whether “Teng Lijun” and "Sweet Honey” match.
  • step S14 in the music skill field, "Teng Lijun” and “Sweet Honey” are matched, and the music skill field is determined as the skill field of "Playing Maria Teng's Sweet Honey”. Then call the music skills to play the sweetness of Maria Teng to the user.
  • the second skill field is the music field; when the first skill field is the music field, the second skill The field is the film and television field.
  • the music skill has a higher priority than the film and television skill, and when the analytical confidence of the two skills is the same, the music skill is given priority.
  • the first skill field is the music field
  • the second skill field is the film and television field.
  • the priorities of different skills are pre-configured according to different voice products and can be adjusted freely. For smart phones, it can be avoided that conversations that should have fallen into film and television skills fall into voice skills. Further improve the accuracy rate of the voice dialogue hitting the skill field.
  • the first skill field is determined as the dialogue text Areas of skill.
  • the second skill field is the music field; "playing the Ye Wen of Donnie Yen”. If the name semantic slot matches the character semantic slot under the knowledge base in the field of film and television. Then directly determine the field of film and television as the skill field of "Playing Yen Zidan's Ye Wen".
  • the method further includes:
  • the second skill field is preferentially determined as the skill field of the dialogue text.
  • FIG. 2 is a schematic structural diagram of a device for determining a field of skill in a dialog text provided by an embodiment of the present invention.
  • the device can execute the method for determining a field of skill in a dialog text according to any of the foregoing embodiments, and is configured in a terminal .
  • the apparatus for determining the skill domain of dialog text includes: an information determining program module 11, a first matching program module 12, a second matching program module 13, and a skill domain determining program module 14.
  • the information determining program module 11 determines the skill field that the dialogue text entered by the user hits, as well as the name semantic slot and the character semantic slot under the skill field; the first matching program module 12 is used for when the dialogue text hits the skill field When it is the first skill field, judge whether the name semantic slot matches the character semantic slot according to the knowledge base of the first skill field; the second matching program module 13 is used to determine whether the knowledge in the first skill field The name semantic slot under the library does not match the character semantic slot, and it is further judged according to the knowledge base of the second skill domain whether the name semantic slot matches the character semantic slot; the skill domain determination program module 14 is used for The name semantic slot under the knowledge base of the second skill domain matches the character semantic slot, and the second skill domain is determined as the skill domain of the dialogue text.
  • the device is also used for:
  • a knowledge base in the field of film and television and a knowledge base in the field of music are established in advance.
  • the knowledge base in the field of film and television stores the association information between the name of the film and the filmmaker, and the knowledge base in the field of music stores the relationship between the name of the music and the name of the singer. ’S associated information.
  • the second skill field is a music field; when the first skill field is a music field, the second skill field is a film and television field.
  • the first skill field is determined as the skill field of the dialogue text.
  • the device is also used for:
  • the second skill field is preferentially determined as the skill field of the dialogue text.
  • the embodiment of the present invention also provides a non-volatile computer storage medium, the computer storage medium stores computer-executable instructions, and the computer-executable instructions can execute the method for determining the field of skill of the dialog text in any of the foregoing method embodiments;
  • the non-volatile computer storage medium of the present invention stores computer executable instructions, and the computer executable instructions are set as:
  • the second skill field is determined as the skill field of the dialogue text.
  • non-volatile computer-readable storage medium it can be used to store non-volatile software programs, non-volatile computer-executable programs and modules, such as program instructions/modules corresponding to the methods in the embodiments of the present invention.
  • One or more program instructions are stored in a non-volatile computer-readable storage medium, and when executed by a processor, execute the method for determining the skill domain of the dialog text in any of the foregoing method embodiments.
  • the non-volatile computer-readable storage medium may include a storage program area and a storage data area.
  • the storage program area may store an operating system and an application program required by at least one function; Data etc.
  • the non-volatile computer-readable storage medium may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices.
  • the non-volatile computer-readable storage medium may optionally include memories remotely provided with respect to the processor, and these remote memories may be connected to the device through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
  • An embodiment of the present invention further provides an electronic device, which includes: at least one processor, and a memory communicatively connected with the at least one processor, wherein the memory stores instructions that can be executed by the at least one processor , The instruction is executed by the at least one processor, so that the at least one processor can execute:
  • the second skill domain is determined as the skill domain of the dialogue text.
  • the processor is further configured to: establish a knowledge base in the field of film and television and a knowledge base in the field of music in advance.
  • the association information between music names and singer names is stored in the knowledge base.
  • the second skill field when the first skill field is a film and television field, the second skill field is a music field; when the first skill field is a music field, the second skill field is a film and television field.
  • the processor is further configured to: if the name semantic slot matches the character semantic slot in the knowledge base of the first skill field, determine the first skill field as the dialogue text Areas of skill.
  • the processor is further configured to: after determining the second skill domain as the skill domain of the dialog text, when the user re-enters the dialog text, prioritize the second skill The domain is determined as the skill domain of the dialogue text.
  • FIG. 3 is a schematic diagram of the hardware structure of an electronic device that executes a method for determining a skill domain of a dialog text according to another embodiment of the present invention. As shown in FIG. 3, the device includes:
  • One or more processors 310 and a memory 320 are taken as an example in FIG. 3.
  • the device for performing the method for determining the skill domain of the dialog text may further include: an input device 330 and an output device 340.
  • the processor 310, the memory 320, the input device 330, and the output device 340 may be connected by a bus or in other ways. In FIG. 3, the connection by a bus is taken as an example.
  • the memory 320 can be used to store non-volatile software programs, non-volatile computer-executable programs and modules, such as the method for determining the field of skill of the dialog text in the embodiment of the present invention Corresponding program instructions/modules.
  • the processor 310 executes various functional applications and data processing of the server by running non-volatile software programs, instructions, and modules stored in the memory 320, that is, realizing the method for determining the field of skill of the dialog text of the foregoing method embodiment.
  • the memory 320 may include a storage program area and a storage data area.
  • the storage program area may store an operating system and an application program required by at least one function; the storage data area may store data created by determining the use of the device according to the skill domain of the dialog text. Wait.
  • the memory 320 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices.
  • the memory 320 may optionally include a memory remotely provided with respect to the processor 310, and these remote memories may be connected to a device for determining the skill domain of the dialog text via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
  • the input device 330 may receive inputted numeric or character information, and generate signals related to the user setting and function control of the device for determining the skill domain of the dialog text.
  • the output device 340 may include a display device such as a display screen.
  • the one or more modules are stored in the memory 320, and when executed by the one or more processors 310, the skill domain of the dialog text in any of the foregoing method embodiments is determined.
  • the electronic devices in the embodiments of the present invention exist in various forms, including but not limited to:
  • Mobile communication equipment This type of equipment is characterized by mobile communication functions, and its main goal is to provide voice and data communications.
  • Such terminals include: smart phones, multimedia phones, functional phones, and low-end phones.
  • Ultra-mobile personal computer equipment This type of equipment belongs to the category of personal computers, has calculation and processing functions, and generally also has mobile Internet features.
  • Such terminals include: PDA, MID and UMPC devices, such as tablet computers.
  • Portable entertainment equipment This type of equipment can display and play multimedia content. Such devices include: audio, video players, handheld game consoles, e-books, as well as smart toys and portable car navigation devices.
  • the device embodiments described above are merely illustrative.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in One place, or it can be distributed to multiple network units.
  • Some or all of the modules can be selected according to actual needs to achieve the objectives of the solutions of the embodiments. Those of ordinary skill in the art can understand and implement it without creative work.
  • each implementation manner can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware.
  • the above technical solution essentially or the part that contributes to the existing technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic A disc, an optical disc, etc., include a number of instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiment.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • Acoustics & Sound (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Machine Translation (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

一种对话文本的技能领域确定方法和系统。所述方法包括:确定用户输入的对话文本命中的技能领域,以及技能领域下的名称语义槽和人物语义槽(S11);当对话文本命中的技能领域为第一技能领域时,根据第一技能领域的知识库判断名称语义槽和人物语义槽是否匹配(S12);若在第一技能领域的知识库下名称语义槽和人物语义槽不匹配,进一步根据第二技能领域的知识库判断名称语义槽和人物语义槽是否匹配(S13);若在第二技能领域的知识库下名称语义槽和人物语义槽匹配,将第二技能领域确定为对话文本的技能领域(S14)。该方法降低了领域分类的错误率,让用户的语音对话命中的技能领域更加准确。

Description

对话文本的技能领域确定方法及装置 技术领域
本发明涉及智能语音领域,尤其涉及一种对话文本的技能领域确定方法及装置。
背景技术
在智能语音交互时,为了确保准确答复用户的对话,会确定用户对话命中的相应技能,从而进入相应的技能领域来向用户答复。在确定技能领域时,通常会使用基于正则的匹配方法。在做技能领域分类时,例如,电视语音产品中包含电影技能,使用的规则通常为“播放***的***”,例如,“播放刘德华的爱你一万年”,任务型技能解析如下,电影人:刘德华,片名:爱你一万年;“播放邓丽君的甜蜜蜜”,任务型技能影视解析如下,电影人:邓丽君,片名:甜蜜蜜。
然而“播放***的***”的这种规则同样适用于音乐技能,“播放刘德华的爱你一万年”,任务型技能音乐解析如下,歌曲名:爱你一万年,歌手名:刘德华;“播放邓丽君的甜蜜蜜”,任务型技能音乐解析如下,歌曲名:甜蜜蜜,歌手名:邓丽君。
在实现本发明过程中,发明人发现相关技术中至少存在如下问题:
如果对于同一句话,两个技能解析置信度相同的情况下,会使用默认优先的技能向用户答复。例如,电视语音产品中,影视技能的优先级会高于音乐技能。对于“播放邓丽君的甜蜜蜜”这种对话时,电视语音产品会优先选择电影技能,如果在“电影人”词库中没有邓丽君或者“片名”词库中没有甜蜜蜜的话,会重新选择音乐技能,然而解析出的语义槽的内容“邓丽君”、“甜蜜蜜”分别在“电影人”,“片名”词库中都存在,但是对应的语义槽却没有联系,导致技能领域命中错误,将本应落入音乐技能的对话落入到影视技能中,无法找到邓丽君出演的甜蜜蜜的电影,用户体验较差。
发明内容
为了至少解决现有技术中语义槽之间没有联系,使得技能领域命中错误的问题。
第一方面,本发明实施例提供一种对话文本的技能领域确定方法,包括:
确定用户输入的对话文本命中的技能领域,以及所述技能领域下的名称语义槽和人物语义槽;
当所述对话文本命中的技能领域为第一技能领域时,根据所述第一技能领域的知识库判断所述名称语义槽和所述人物语义槽是否匹配;
若在所述第一技能领域的知识库下所述名称语义槽和所述人物语义槽不匹配,进一步根据第二技能领域的知识库判断所述名称语义槽和所述人物语义槽是否匹配;
若在所述第二技能领域的知识库下所述名称语义槽和所述人物语义槽匹配,将所述第二技能领域确定为所述对话文本的技能领域。
第二方面,本发明实施例提供一种对话文本的技能领域确定装置,包括:
信息确定程序模块,确定用户输入的对话文本命中的技能领域,以及所述技能领域下的名称语义槽和人物语义槽;
第一匹配程序模块,用于当所述对话文本命中的技能领域为第一技能领域时,根据所述第一技能领域的知识库判断所述名称语义槽和所述人物语义槽是否匹配;
第二匹配程序模块,用于若在所述第一技能领域的知识库下所述名称语义槽和所述人物语义槽不匹配,进一步根据第二技能领域的知识库判断所述名称语义槽和所述人物语义槽是否匹配;
技能领域确定程序模块,用于若在所述第二技能领域的知识库下所述名称语义槽和所述人物语义槽匹配,将所述第二技能领域确定为所述对话文本的技能领域。
第三方面,提供一种电子设备,其包括: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本发明任一实施例的对话文本的技能领域确定方法的步骤。
第四方面,本发明实施例提供一种存储介质,其上存储有计算机程序,其特征在于,该程序被处理器执行时实现本发明任一实施例的对话文本的技能领域确定方法的步骤。
本发明实施例的有益效果在于:建立语义槽之间的关联,降低了领域分类的错误率,让用户的语音对话命中的技能领域更加准确,提高用户的使用效果。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍,显而易见地,下面描述中的附图是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。
图1是本发明一实施例提供的一种对话文本的技能领域确定方法的流程图;
图2是本发明一实施例提供的一种对话文本的技能领域确定装置的结构示意图;
图3为本发明的电子设备的一实施例的结构示意图。
具体实施方式
为使本发明实施例的目的、技术方案和优点更加清楚,下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。
本发明实施例提供一种对话文本的技能领域确定方法,应用于电子设备。该电子设备可以为智能电视、智能手机、智能音箱、智能车机装置、智慧屏等,本发明对此不作限定。
如图1所示为本发明一实施例提供的一种对话文本的技能领域确定方法 的流程图,包括如下步骤:
S11:电子设备确定用户输入的对话文本命中的技能领域,以及所述技能领域下的名称语义槽和人物语义槽;
S12:当所述对话文本命中的技能领域为第一技能领域时,电子设备根据所述第一技能领域的知识库判断所述名称语义槽和所述人物语义槽是否匹配;
S13:若在所述第一技能领域的知识库下所述名称语义槽和所述人物语义槽不匹配,电子设备进一步根据第二技能领域的知识库判断所述名称语义槽和所述人物语义槽是否匹配;
S14:若在所述第二技能领域的知识库下所述名称语义槽和所述人物语义槽匹配,电子设备将所述第二技能领域确定为所述对话文本的技能领域。
在本实施方式中,虽然直接删除影视技能中“片名”或“电影人”词库中对应的说法,但这样会导致在真正说指定“片名”或“电影人”时,语义解析失败。
为了解决这些缺陷,预先建立影视领域知识库以及音乐领域知识库,例如,影视领域知识库可以通过“片名”查找所有对应的“电影人”,例如,电影片名《甜蜜蜜》,对应的电影人有:陈可辛、张曼玉、黎明、曾志伟。在电影人中,不但可以包含演员的信息,还可以包含导演的信息。
同样的,音乐领域知识库,可以通过“歌曲名”查找所有对应的“歌手名”列表,例如,歌曲名《甜蜜蜜》,对应的歌手名有邓丽君、麻吉弟弟、薛凯琪。
对于步骤S11,电子设备(例如,智能电视)通常会搭载电视语音产品,电视语音产品中包含电影技能和音乐技能,但影视技能优先级高于音乐技能,在两个技能解析置信度相同的情况下,优先影视技能。
如果是智能手机通常会搭载智能对话语音产品,智能对话语音产品中也包含了电影技能和音乐技能,但音乐技能优先级高于影视技能,在两个技能解析置信度相同的情况下,优先音乐技能。
下面以智能电视为例,用户对智能电视说“播放邓丽君的甜蜜蜜”,平行调度任务型技能语义服务和知识型技能服务。通过任务型技能语义服 务确定用户这句话会命中哪些技能领域,例如,可以命中“影视领域”和“音乐领域”。确定出“影视领域”下影视名称语义槽“甜蜜蜜”和电影人语义槽“邓丽君”;“音乐领域”下音乐名称语义槽“甜蜜蜜”和歌手名语义槽“邓丽君”。知识型技能服务包括影视领域知识库以及音乐领域知识库。
对于步骤S12,由于是智能电视,影视技能为第一技能,音乐技能为第二技能。当“播放邓丽君的甜蜜蜜”优先命中的技能为影视技能领域,会根据影视领域知识库来判断“甜蜜蜜”和“邓丽君”是否匹配。在上文中,影视领域知识库中电影片名《甜蜜蜜》,对应的电影人有:陈可辛、张曼玉、黎明、曾志伟。因此,在影视领域下的名称语义槽和所述人物语义槽不匹配。
对于步骤S13,在步骤S12中确定的影视领域下的名称语义槽和所述人物语义槽不匹配,在影视领域知识库中电影片名《甜蜜蜜》,对应的电影人中并没有“邓丽君”。进一步地根据“音乐技能”领域的知识库来判断“邓丽君”和“甜蜜蜜”是否匹配。
对于步骤S14,在音乐技能领域中,“邓丽君”和“甜蜜蜜”匹配,进而将音乐技能领域确定为“播放邓丽君的甜蜜蜜”的技能领域。进而调用音乐技能向用户播放邓丽君的甜蜜蜜。
为了进行校验,随机获取影视数据共计2001条,原badcase 69条,错误率3.4%,引入上面策略后,可以有效解决36条case,错误率降低到1.64%,错误率降低52.17%。
通过该实施方式可以看出,降低了领域分类的错误率,让用户的语音对话命中的技能领域更加准确,提高用户的使用效果。
作为一种实施方式,在本实施例中,当所述第一技能领域为影视领域时,所述第二技能领域为音乐领域;当所述第一技能领域为音乐领域,所述第二技能领域为影视领域。
在本实施方式中,如果是智能手机为例,音乐技能优先级高于影视技能,在两个技能解析置信度相同的情况下,优先音乐技能。当第一技能领域为音乐领域,第二技能领域为影视领域。
通过该实施方式可以看出,根据不同的语音产品预先配置不同技能的优先级,可以自由调整,对于智能手机,可以避免本应落入影视技能的对话落入到语音技能中。进一步提高语音对话命中技能领域的准确率。
作为一种实施方式,在本实施例中,若在所述第一技能领域的知识库下所述名称语义槽和所述人物语义槽匹配,将所述第一技能领域确定为所述对话文本的技能领域。
在本实施方式中,智能电视为例,第一技能领域为影视领域时,第二技能领域为音乐领域;“播放甄子丹的叶问”。如果影视领域的知识库下所述名称语义槽和所述人物语义槽匹配。那么直接将影视领域确定为“播放甄子丹的叶问”的技能领域。
作为一种实施方式,在所述将所述第二技能领域确定为所述对话文本的技能领域之后,所述方法还包括:
当用户再次输入所述对话文本时,优先将所述第二技能领域确定为所述对话文本的技能领域。
在本实施方式中,智能电视为例,如果用户首次输入“播放邓丽君的甜蜜蜜”,会进行上述方法的判断,确定音乐技能。当用户第二次再次输入“播放邓丽君的甜蜜蜜”时,此时无需判断,直接将音乐技能领域确定为“播放邓丽君的甜蜜蜜”的技能领域。进而调用音乐技能向用户播放邓丽君的甜蜜蜜。
通过该实施方式可以看出,对重复输入的对话,直接使用历史确定的技能领域对用户进行答复,提高交互效率。
如图2所示为本发明一实施例提供的一种对话文本的技能领域确定装置的结构示意图,该装置可执行上述任意实施例所述的对话文本的技能领域确定方法,并配置在终端中。
本实施例提供的一种对话文本的技能领域确定装置包括:信息确定程序模块11,第一匹配程序模块12,第二匹配程序模块13和技能领域确定程序模块14。
其中,信息确定程序模块11确定用户输入的对话文本命中的技能领 域,以及所述技能领域下的名称语义槽和人物语义槽;第一匹配程序模块12用于当所述对话文本命中的技能领域为第一技能领域时,根据所述第一技能领域的知识库判断所述名称语义槽和所述人物语义槽是否匹配;第二匹配程序模块13用于若在所述第一技能领域的知识库下所述名称语义槽和所述人物语义槽不匹配,进一步根据第二技能领域的知识库判断所述名称语义槽和所述人物语义槽是否匹配;技能领域确定程序模块14用于若在所述第二技能领域的知识库下所述名称语义槽和所述人物语义槽匹配,将所述第二技能领域确定为所述对话文本的技能领域。
进一步地,所述装置还用于:
预先建立影视领域知识库以及音乐领域知识库,其中,所述影视领域知识库中存储有影视名称与电影人之间的关联信息,所述音乐领域知识库中存储有音乐名称与歌手名之间的关联信息。
进一步地,当所述第一技能领域为影视领域时,所述第二技能领域为音乐领域;当所述第一技能领域为音乐领域,所述第二技能领域为影视领域。
进一步地,若在所述第一技能领域的知识库下所述名称语义槽和所述人物语义槽匹配,将所述第一技能领域确定为所述对话文本的技能领域。
进一步地,所述装置还用于:
当用户再次输入所述对话文本时,优先将所述第二技能领域确定为所述对话文本的技能领域。
本发明实施例还提供了一种非易失性计算机存储介质,计算机存储介质存储有计算机可执行指令,该计算机可执行指令可执行上述任意方法实施例中的对话文本的技能领域确定方法;
作为一种实施方式,本发明的非易失性计算机存储介质存储有计算机可执行指令,计算机可执行指令设置为:
确定用户输入的对话文本命中的技能领域,以及所述技能领域下的名称语义槽和人物语义槽;
当所述对话文本命中的技能领域为第一技能领域时,根据所述第一技能领域的知识库判断所述名称语义槽和所述人物语义槽是否匹配;
若在所述第一技能领域的知识库下所述名称语义槽和所述人物语义槽不匹配,进一步根据第二技能领域的知识库判断所述名称语义槽和所述人物语义槽是否匹配;
若在所述第二技能领域的知识库下所述名称语义槽和所述人物语义槽匹配,将所述第二技能领域确定为所述对话文本的技能领域。
作为一种非易失性计算机可读存储介质,可用于存储非易失性软件程序、非易失性计算机可执行程序以及模块,如本发明实施例中的方法对应的程序指令/模块。一个或者多个程序指令存储在非易失性计算机可读存储介质中,当被处理器执行时,执行上述任意方法实施例中的对话文本的技能领域确定方法。
非易失性计算机可读存储介质可以包括存储程序区和存储数据区,其中,存储程序区可存储操作系统、至少一个功能所需要的应用程序;存储数据区可存储根据装置的使用所创建的数据等。此外,非易失性计算机可读存储介质可以包括高速随机存取存储器,还可以包括非易失性存储器,例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实施例中,非易失性计算机可读存储介质可选包括相对于处理器远程设置的存储器,这些远程存储器可以通过网络连接至装置。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
本发明实施例还提供一种电子设备,其包括: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:
确定用户输入的对话文本命中的技能领域,以及所述技能领域下的名称语义槽和人物语义槽;
当所述对话文本命中的技能领域为第一技能领域时,根据所述第一技能领域的知识库判断所述名称语义槽和所述人物语义槽是否匹配;
若在所述第一技能领域的知识库下所述名称语义槽和所述人物语义槽不匹配,进一步根据第二技能领域的知识库判断所述名称语义槽和所述人物语义槽是否匹配;
若在所述第二技能领域的知识库下所述名称语义槽和所述人物语义 槽匹配,将所述第二技能领域确定为所述对话文本的技能领域。
在一些实施例中,处理器还用于:预先建立影视领域知识库以及音乐领域知识库,其中,所述影视领域知识库中存储有影视名称与电影人之间的关联信息,所述音乐领域知识库中存储有音乐名称与歌手名之间的关联信息。
在一些实施例中,当所述第一技能领域为影视领域时,所述第二技能领域为音乐领域;当所述第一技能领域为音乐领域,所述第二技能领域为影视领域。
在一些实施例中,处理器还用于:若在所述第一技能领域的知识库下所述名称语义槽和所述人物语义槽匹配,将所述第一技能领域确定为所述对话文本的技能领域。
在一些实施例中,处理器还用于:在所述将所述第二技能领域确定为所述对话文本的技能领域之后,当用户再次输入所述对话文本时,优先将所述第二技能领域确定为所述对话文本的技能领域。
图3是本发明另一实施例提供的执行对话文本的技能领域确定方法的电子设备的硬件结构示意图,如图3所示,该设备包括:
一个或多个处理器310以及存储器320,图3中以一个处理器310为例。
执行对话文本的技能领域确定方法的设备还可以包括:输入装置330和输出装置340。
处理器310、存储器320、输入装置330和输出装置340可以通过总线或者其他方式连接,图3中以通过总线连接为例。
存储器320作为一种非易失性计算机可读存储介质,可用于存储非易失性软件程序、非易失性计算机可执行程序以及模块,如本发明实施例中的对话文本的技能领域确定方法对应的程序指令/模块。处理器310通过运行存储在存储器320中的非易失性软件程序、指令以及模块,从而执行服务器的各种功能应用以及数据处理,即实现上述方法实施例对话文本的技能领域确定方法。
存储器320可以包括存储程序区和存储数据区,其中,存储程序区可 存储操作系统、至少一个功能所需要的应用程序;存储数据区可存储根据对话文本的技能领域确定装置的使用所创建的数据等。此外,存储器320可以包括高速随机存取存储器,还可以包括非易失性存储器,例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实施例中,存储器320可选包括相对于处理器310远程设置的存储器,这些远程存储器可以通过网络连接至对话文本的技能领域确定装置。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
输入装置330可接收输入的数字或字符信息,以及产生与对话文本的技能领域确定装置的用户设置以及功能控制有关的信号。输出装置340可包括显示屏等显示设备。
所述一个或者多个模块存储在所述存储器320中,当被所述一个或者多个处理器310执行时,执行上述任意方法实施例中的对话文本的技能领域确定。
本发明实施例的电子设备以多种形式存在,包括但不限于:
(1)移动通信设备:这类设备的特点是具备移动通信功能,并且以提供话音、数据通信为主要目标。这类终端包括:智能手机、多媒体手机、功能性手机,以及低端手机等。
(2)超移动个人计算机设备:这类设备属于个人计算机的范畴,有计算和处理功能,一般也具备移动上网特性。这类终端包括:PDA、MID和UMPC设备等,例如平板电脑。
(3)便携式娱乐设备:这类设备可以显示和播放多媒体内容。该类设备包括:音频、视频播放器,掌上游戏机,电子书,以及智能玩具和便携式车载导航设备。
(4)其他具有语音交互的电子装置。
在本文中,诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来,而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且,术语“包括”、“包含”,不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况 下,由语句“包括……”限定的要素,并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。
以上所描述的装置实施例仅仅是示意性的,其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性的劳动的情况下,即可以理解并实施。
通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到各实施方式可借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件。基于这样的理解,上述技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来,该计算机软件产品可以存储在计算机可读存储介质中,如ROM/RAM、磁碟、光盘等,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行各个实施例或者实施例的某些部分所述的方法。
最后应说明的是:以上实施例仅用以说明本发明的技术方案,而非对其限制;尽管参照前述实施例对本发明进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本发明各实施例技术方案的精神和范围。

Claims (10)

  1. 一种对话文本的技能领域确定方法,用于电子设备,该方法包括:
    所述电子设备确定用户输入的对话文本命中的技能领域,以及所述技能领域下的名称语义槽和人物语义槽;
    当所述对话文本命中的技能领域为第一技能领域时,所述电子设备根据所述第一技能领域的知识库判断所述名称语义槽和所述人物语义槽是否匹配;
    若在所述第一技能领域的知识库下所述名称语义槽和所述人物语义槽不匹配,所述电子设备进一步根据第二技能领域的知识库判断所述名称语义槽和所述人物语义槽是否匹配;
    若在所述第二技能领域的知识库下所述名称语义槽和所述人物语义槽匹配,所述电子设备将所述第二技能领域确定为所述对话文本的技能领域。
  2. 根据权利要求1所述的方法,其中,所述方法还包括:
    预先建立影视领域知识库以及音乐领域知识库,其中,所述影视领域知识库中存储有影视名称与电影人之间的关联信息,所述音乐领域知识库中存储有音乐名称与歌手名之间的关联信息。
  3. 根据权利要求1所述的方法,其中,当所述第一技能领域为影视领域时,所述第二技能领域为音乐领域;当所述第一技能领域为音乐领域,所述第二技能领域为影视领域。
  4. 根据权利要求1所述的方法,其中,若在所述第一技能领域的知识库下所述名称语义槽和所述人物语义槽匹配,将所述第一技能领域确定为所述对话文本的技能领域。
  5. 根据权利要求1所述的方法,其中,在所述将所述第二技能领域确定为所述对话文本的技能领域之后,所述方法还包括:
    当用户再次输入所述对话文本时,优先将所述第二技能领域确定为所 述对话文本的技能领域。
  6. 一种对话文本的技能领域确定装置,包括:
    信息确定程序模块,确定用户输入的对话文本命中的技能领域,以及所述技能领域下的名称语义槽和人物语义槽;
    第一匹配程序模块,用于当所述对话文本命中的技能领域为第一技能领域时,根据所述第一技能领域的知识库判断所述名称语义槽和所述人物语义槽是否匹配;
    第二匹配程序模块,用于若在所述第一技能领域的知识库下所述名称语义槽和所述人物语义槽不匹配,进一步根据第二技能领域的知识库判断所述名称语义槽和所述人物语义槽是否匹配;
    技能领域确定程序模块,用于若在所述第二技能领域的知识库下所述名称语义槽和所述人物语义槽匹配,将所述第二技能领域确定为所述对话文本的技能领域。
  7. 根据权利要求6所述的装置,其中,所述装置还用于:
    预先建立影视领域知识库以及音乐领域知识库,其中,所述影视领域知识库中存储有影视名称与电影人之间的关联信息,所述音乐领域知识库中存储有音乐名称与歌手名之间的关联信息。
  8. 根据权利要求6所述的装置,其中,当所述第一技能领域为影视领域时,所述第二技能领域为音乐领域;当所述第一技能领域为音乐领域,所述第二技能领域为影视领域。
  9. 一种电子设备,其包括: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1-5中任一项所述方法的步骤。
  10. 一种存储介质,其上存储有计算机程序,其中,该程序被处理器 执行时实现权利要求1-5中任一项所述方法的步骤。
PCT/CN2020/129342 2020-03-18 2020-11-17 对话文本的技能领域确定方法及装置 WO2021184794A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
US17/912,112 US20230133146A1 (en) 2020-03-18 2020-11-17 Method and apparatus for determining skill field of dialogue text
JP2022555166A JP7481475B2 (ja) 2020-03-18 2020-11-17 対話テキストの機能領域確定方法及び装置
EP20925821.9A EP4123497A4 (en) 2020-03-18 2020-11-17 METHOD AND APPARATUS FOR DETERMINING DIALOGUE TEXT SKILLS

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010193878.7A CN111414764A (zh) 2020-03-18 2020-03-18 对话文本的技能领域确定方法及系统
CN202010193878.7 2020-03-18

Publications (1)

Publication Number Publication Date
WO2021184794A1 true WO2021184794A1 (zh) 2021-09-23

Family

ID=71493106

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/129342 WO2021184794A1 (zh) 2020-03-18 2020-11-17 对话文本的技能领域确定方法及装置

Country Status (5)

Country Link
US (1) US20230133146A1 (zh)
EP (1) EP4123497A4 (zh)
JP (1) JP7481475B2 (zh)
CN (1) CN111414764A (zh)
WO (1) WO2021184794A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114547283A (zh) * 2022-02-25 2022-05-27 广域铭岛数字科技有限公司 基于语义理解的对话质量分析方法、装置、设备和介质

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111414764A (zh) * 2020-03-18 2020-07-14 苏州思必驰信息科技有限公司 对话文本的技能领域确定方法及系统
CN112581954B (zh) * 2020-12-01 2023-08-04 杭州九阳小家电有限公司 一种高匹配性语音交互方法和智能设备

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108920497A (zh) * 2018-05-23 2018-11-30 北京奇艺世纪科技有限公司 一种人机交互方法及装置
US20190147052A1 (en) * 2017-11-16 2019-05-16 Baidu Online Network Technology (Beijing) Co., Ltd. Method and apparatus for playing multimedia
CN109783735A (zh) * 2019-01-18 2019-05-21 广东小天才科技有限公司 一种基于用户语料获取内容的方法和装置
CN110008314A (zh) * 2019-04-12 2019-07-12 广东小天才科技有限公司 一种意图解析方法及装置
CN110543633A (zh) * 2019-08-29 2019-12-06 腾讯科技(深圳)有限公司 语句意图识别方法、装置
CN110808051A (zh) * 2019-10-30 2020-02-18 腾讯科技(深圳)有限公司 一种技能选取的方法以及相关装置
CN111414764A (zh) * 2020-03-18 2020-07-14 苏州思必驰信息科技有限公司 对话文本的技能领域确定方法及系统

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103020047A (zh) * 2012-12-31 2013-04-03 威盛电子股份有限公司 修正语音应答的方法及自然语言对话系统
CN103177079B (zh) * 2013-02-06 2016-07-13 小米科技有限责任公司 一种主题更新的检测方法、终端和服务器
JP2017224155A (ja) * 2016-06-15 2017-12-21 パナソニックIpマネジメント株式会社 対話処理方法、対話処理システム、及びプログラム
US10453117B1 (en) * 2016-06-29 2019-10-22 Amazon Technologies, Inc. Determining domains for natural language understanding
CN106126503B (zh) * 2016-07-12 2020-02-11 海信集团有限公司 业务领域定位方法及终端
CN107943793A (zh) * 2018-01-10 2018-04-20 威盛电子股份有限公司 自然语言的语义解析方法
CN108932278B (zh) * 2018-04-28 2021-05-18 厦门快商通信息技术有限公司 基于语义框架的人机对话方法及系统
CN109063152A (zh) * 2018-08-08 2018-12-21 鲸数科技(北京)有限公司 智能问答方法、装置及智能终端
CN109190116B (zh) * 2018-08-15 2023-10-24 思必驰科技股份有限公司 语义解析方法、系统、电子设备及存储介质
CN109918673B (zh) * 2019-03-14 2021-08-03 湖北亿咖通科技有限公司 语义仲裁方法、装置、电子设备和计算机可读存储介质

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190147052A1 (en) * 2017-11-16 2019-05-16 Baidu Online Network Technology (Beijing) Co., Ltd. Method and apparatus for playing multimedia
CN108920497A (zh) * 2018-05-23 2018-11-30 北京奇艺世纪科技有限公司 一种人机交互方法及装置
CN109783735A (zh) * 2019-01-18 2019-05-21 广东小天才科技有限公司 一种基于用户语料获取内容的方法和装置
CN110008314A (zh) * 2019-04-12 2019-07-12 广东小天才科技有限公司 一种意图解析方法及装置
CN110543633A (zh) * 2019-08-29 2019-12-06 腾讯科技(深圳)有限公司 语句意图识别方法、装置
CN110808051A (zh) * 2019-10-30 2020-02-18 腾讯科技(深圳)有限公司 一种技能选取的方法以及相关装置
CN111414764A (zh) * 2020-03-18 2020-07-14 苏州思必驰信息科技有限公司 对话文本的技能领域确定方法及系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4123497A4 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114547283A (zh) * 2022-02-25 2022-05-27 广域铭岛数字科技有限公司 基于语义理解的对话质量分析方法、装置、设备和介质

Also Published As

Publication number Publication date
EP4123497A4 (en) 2023-08-09
JP2023517363A (ja) 2023-04-25
US20230133146A1 (en) 2023-05-04
EP4123497A1 (en) 2023-01-25
JP7481475B2 (ja) 2024-05-10
CN111414764A (zh) 2020-07-14

Similar Documents

Publication Publication Date Title
WO2021184794A1 (zh) 对话文本的技能领域确定方法及装置
CN110446115B (zh) 直播互动方法、装置、电子设备及存储介质
RU2690199C1 (ru) Управление поставщиками данных для диалога
US11368754B2 (en) Video playing method, apparatus, electronic device and storage medium
WO2017166650A1 (zh) 语音识别方法及装置
CN108962233B (zh) 用于语音对话平台的语音对话处理方法及系统
US20120108221A1 (en) Augmenting communication sessions with applications
CN110223692B (zh) 用于语音对话平台跨技能的多轮对话方法及系统
WO2017181598A1 (zh) 视频播放方法及装置
WO2021208392A1 (zh) 用于人机对话的语音技能跳转方法、电子设备及存储介质
CN107613400A (zh) 一种语音弹幕的实现方法和装置
WO2017166651A1 (zh) 语音识别模型训练方法、说话人类型识别方法及装置
CN109979450B (zh) 信息处理方法、装置及电子设备
CN109460503B (zh) 答案输入方法、装置、存储介质及电子设备
US20190197263A1 (en) Method, device and electronic apparatus for testing capability of analyzing a two-dimensional code
JP2023515897A (ja) 音声対話の訂正方法及び装置
US20180033450A1 (en) Method and computer system for performing audio search on a social networking platform
WO2021135561A1 (zh) 技能语音唤醒方法及装置
US20170195710A1 (en) Method and electronic device for preview play
WO2020135773A1 (zh) 数据处理方法、装置及计算机可读存储介质
WO2020215089A1 (en) Voice control for virtual reality platform background
WO2021169092A1 (zh) 信息显示控制方法及装置、电子设备、存储介质
WO2021042584A1 (zh) 全双工语音对话方法
WO2021077528A1 (zh) 人机对话打断方法
WO2022089546A1 (zh) 标签生成方法、装置及相关设备

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: 20925821

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022555166

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2020925821

Country of ref document: EP

Effective date: 20221018