WO2020000621A1 - 空调控制方法、空调控制装置、空调设备及存储介质 - Google Patents

空调控制方法、空调控制装置、空调设备及存储介质 Download PDF

Info

Publication number
WO2020000621A1
WO2020000621A1 PCT/CN2018/102059 CN2018102059W WO2020000621A1 WO 2020000621 A1 WO2020000621 A1 WO 2020000621A1 CN 2018102059 W CN2018102059 W CN 2018102059W WO 2020000621 A1 WO2020000621 A1 WO 2020000621A1
Authority
WO
WIPO (PCT)
Prior art keywords
voice
feature
information
historical
temperature adjustment
Prior art date
Application number
PCT/CN2018/102059
Other languages
English (en)
French (fr)
Inventor
潘燕飞
Original Assignee
平安科技（深圳）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 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2020000621A1 publication Critical patent/WO2020000621A1/zh

Links

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/50—Control or safety arrangements characterised by user interfaces or communication
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/50—Control or safety arrangements characterised by user interfaces or communication
    • F24F11/52—Indication arrangements, e.g. displays
    • F24F11/526—Indication arrangements, e.g. displays giving audible indications
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/50—Control or safety arrangements characterised by user interfaces or communication
    • F24F11/61—Control or safety arrangements characterised by user interfaces or communication using timers
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/26—Speech to text systems

Definitions

  • the present application relates to the technical field of air conditioning, and in particular, to an air conditioning control method, an air conditioning control device, an air conditioning device, and a storage medium.
  • the main purpose of this application is to provide an air-conditioning control method, an air-conditioning control device, an air-conditioning device, and a storage medium.
  • the purpose is to solve the problem that when a user uses an air-conditioning device to perform temperature adjustment in the prior art, the temperature needs to be adjusted manually or by voice input.
  • Technical issues with poor user experience are to provide an air-conditioning control method, an air-conditioning control device, an air-conditioning device, and a storage medium.
  • the present application provides a method for controlling an air conditioner, which includes the following steps:
  • Obtain a target historical speech feature sample that has been successfully matched find the temperature adjustment information associated with the target historical speech feature sample in the mapping relationship, and control the air conditioner to perform temperature adjustment according to the temperature adjustment information.
  • the present application also proposes an air conditioning control device, the device includes: a feature extraction module, a feature matching module, and a temperature adjustment module;
  • the feature extraction module is configured to obtain voice information in the current environment, and perform feature extraction on the voice information to obtain current voice feature data;
  • the feature matching module is configured to match the current voice feature data as a voice feature sample to be matched with a pre-stored historical voice feature sample;
  • the temperature adjustment module is configured to obtain a target historical speech feature sample that is successfully matched, find temperature adjustment information associated with the target historical speech feature sample in a mapping relationship, and control the air conditioner to perform temperature adjustment according to the temperature adjustment information .
  • the present application also proposes an air-conditioning apparatus, the air-conditioning apparatus includes: a memory, a processor, and an air-conditioning control program stored in the memory and operable on the processor.
  • the control program is configured to implement the steps of the air conditioning control method as described above.
  • the present application also proposes a storage medium, where the air-conditioning control program is stored on the storage medium, and when the air-conditioning control program is executed by the processor, the steps of the air-conditioning control method described above are implemented.
  • the air-conditioning control method, air-conditioning control device, air-conditioning equipment, and storage medium of this embodiment obtain current voice characteristic data by acquiring voice information in the current environment and feature extraction of the voice information; and use the current voice characteristic data as a sample of voice characteristics to be matched Match the pre-stored historical voice feature samples; obtain the successfully matched target historical voice feature samples, find the temperature adjustment information associated with the target historical voice feature samples in the mapping relationship, and control the air conditioner to perform temperature adjustment based on the temperature adjustment information. It obtains the current voice characteristic data based on the voice information sent by the user, and then finds the final temperature adjustment information based on the current voice characteristic data, and then controls the air conditioner to perform temperature adjustment according to the temperature adjustment information. Therefore, the user is not required to manually input the corresponding temperature Adjusting parameters improves the user experience.
  • FIG. 1 is a schematic structural diagram of an air conditioning device in a hardware operating environment according to a solution of an embodiment of the present application
  • FIG. 2 is a schematic flowchart of a first embodiment of an air conditioning control method of this application
  • FIG. 3 is a schematic flowchart of a second embodiment of an air conditioning control method of the present application.
  • FIG. 4 is a schematic flowchart of a third embodiment of an air conditioning control method of the present application.
  • FIG. 5 is a structural block diagram of a first embodiment of an air conditioning control device of the present application.
  • FIG. 1 is a schematic structural diagram of an air-conditioning apparatus in a hardware operating environment according to an embodiment of the present application.
  • the air conditioning device may include: a processor 1001, such as a central processing unit (Central Processing Unit). Unit (CPU), communication bus 1002, user interface 1003, network interface 1004, and memory 1005.
  • the communication bus 1002 is used to implement connection and communication between these components.
  • the user interface 1003 may include a display, an input unit such as a keyboard, and the optional user interface 1003 may further include a standard wired interface and a wireless interface.
  • the network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WIreless-FIdelity (WI-FI) interface).
  • WI-FI WIreless-FIdelity
  • the memory 1005 may be a high-speed random access memory (Random Access Memory (RAM) memory, or non-volatile memory (Non-Volatile) Memory (NVM), such as disk storage.
  • RAM Random Access Memory
  • NVM Non-Volatile Memory
  • the memory 1005 may optionally be a storage device independent of the foregoing processor 1001.
  • FIG. 1 does not constitute a limitation on the air-conditioning equipment, and may include more or fewer components than shown in the figure, or combine certain components, or arrange different components.
  • the memory 1005 as a storage medium may include an operating system, a data storage module, a network communication module, a user interface module, and an air conditioning control program.
  • the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the air-conditioning device of the present application may be set in In the air-conditioning apparatus, the air-conditioning apparatus calls the air-conditioning control program stored in the memory 1005 through the processor 1001 and executes the air-conditioning control method provided in the embodiment of the present application.
  • FIG. 2 is a schematic flowchart of a first embodiment of an air conditioning control method of the present application.
  • the air conditioning control method includes the following steps:
  • Step S10 acquiring voice information in the current environment, and performing feature extraction on the voice information to obtain current voice characteristic data
  • the execution subject of this method embodiment may be an air-conditioning main control board, and the air-conditioning main control board (hereinafter referred to as the main control board) may be a single central processing unit of an air conditioner or multiple air conditioners (such as different air conditioners installed in multiple rooms of a family).
  • the user can control the operation of multiple air conditioners at the same time through the central processor, and can also control the operation of a single air conditioner in a targeted manner.
  • the main control board may collect voice information in the current environment through a preset sound sensor, and then perform feature extraction on the collected voice information to obtain the current corresponding to the voice information.
  • Speech feature data The sound sensor may be an instrument with a sound wave collection function similar to a microphone or a microphone array, which may be built-in or external to an air-conditioning device, and the voice characteristic data to be extracted in this embodiment includes, but is not limited to, sound rays, Spectrum, cepstrum, formant, pitch, and reflection coefficient data.
  • the main control board in this embodiment may obtain the voice information in the current environment, perform analog-to-digital conversion on the voice information (analog signal) to obtain the voice information (digital signal) to be filtered; The information is filtered, and feature extraction is performed on the filtered voice information to obtain current voice feature data.
  • Step S20 Match the current voice feature data as a voice feature sample to be matched with a pre-stored historical voice feature sample
  • the voice feature data corresponding to a user (such as a family member) who has the right to use the air conditioner needs to be entered and saved as a sample of historical voice feature data for subsequent use.
  • the historical voice characteristic data sample corresponding to the father may be labeled as “father”, and the historical voice characteristic data sample corresponding to the mother may be labeled as “mother”, which is not limited in this embodiment.
  • the main control board may prompt the user to perform personalized settings for temperature adjustment through the human-machine interactive interface of the air conditioner.
  • the personalized settings include: setting a common name or logo of the air conditioner. (In the case of multiple air conditioners), target adjustment temperature, target temperature adjustment mode (such as cooling, heating, dehumidification) and other temperature adjustment information, and associate these temperature adjustment information with voice feature data samples (or their tags) To establish a mapping relationship.
  • the main control board may receive historical voice information and temperature adjustment information input by a user; perform feature extraction on the historical voice information, and use the extracted historical voice feature data as a historical voice feature sample corresponding to the user; Establishing a mapping relationship between the historical speech feature samples and the temperature adjustment information, and storing the mapping relationship.
  • the main control board can use the current voice feature data as the voice feature samples to be matched with the historical voice feature samples pre-stored locally in the air conditioner to find whether the voice feature data is the same. Or similar samples of historical speech features.
  • Step S30 Obtain a target historical voice feature sample that is successfully matched, find the temperature adjustment information associated with the target historical voice feature sample in the mapping relationship, and control the air conditioner to perform temperature adjustment according to the temperature adjustment information.
  • the main control board may find the temperature associated with the target historical voice feature sample according to a pre-established mapping relationship. Adjust the information, and then control the target air conditioner to perform temperature adjustment according to the information such as the name or logo of the target air conditioner, the target adjustment temperature, and the target temperature adjustment mode included in the temperature adjustment information.
  • the current voice feature data is obtained by acquiring voice information in the current environment and feature extraction of the voice information; the current voice feature data is used as a voice feature sample to be matched with a pre-stored historical voice feature sample; and a successful target is obtained.
  • Historical speech feature samples find the temperature adjustment information associated with the target historical speech feature samples in the mapping relationship, and control the air conditioner for temperature adjustment based on the temperature adjustment information. Because the current speech feature data is obtained based on the voice information sent by the user, then The final temperature adjustment information is found according to the current voice characteristic data, and then the air conditioner is controlled for temperature adjustment according to the temperature adjustment information, so that the user does not need to manually or soundly input the corresponding temperature adjustment parameters, which improves the user experience.
  • FIG. 3 is a schematic flowchart of a second embodiment of an air conditioning control method according to the present application.
  • the step S20 includes:
  • Step S201 Extract feature point data from the current voice feature data according to a preset dimension, and use the extracted feature point data as a feature sample of the voice to be matched;
  • the preset dimensions in this embodiment include but are not limited to: acoustic features (spectrum, cepstrum, formant, pitch, reflection coefficient), lexical features (speaker-related words n-gram, phoneme n -gram), prosodic features (basic and energy "gestures” described by n-grams), language, dialect and / or accent information, etc.
  • the main control board extracts the feature point data corresponding to the current speech recognition from the current voice feature data according to a preset dimension, and uses the extracted feature point data as a voice feature sample to be matched with a local pre-stored Match historical speech feature samples.
  • Step S202 Determine the matching degree between the speech feature samples to be matched and the historical speech feature samples pre-stored locally;
  • the main control board extracts pre-stored historical voice feature samples from the local database, and then matches the voice samples to be matched with the historical voice feature samples of different users one by one. To determine the final matching result.
  • the main control board may extract feature point data common to the voice feature samples to be matched and the historical voice feature samples; and determine that the common feature point data occupies the voice feature samples to be matched.
  • the feature point data contained in the speech samples to be matched is ⁇ A, B, C, D , H, J ⁇
  • the historical feature point data contained in the historical speech feature sample 1 is ⁇ A, B, D, E, J, I ⁇
  • the historical feature point data contained in the historical speech feature sample 2 is ⁇ B, C, D , E, F, I ⁇
  • the historical feature point data contained in historical speech feature sample 3 is ⁇ A, C, D, E, I, L ⁇
  • the main control board After the main control board determines the proportion of the feature point data shared by the voice feature samples to be matched and the historical voice feature samples to the voice feature samples to be matched, the main control board can determine the history of the voice feature samples to be matched and the locally stored history. The degree of matching between speech feature samples.
  • Step S203 It is detected whether there is a historical voice feature sample with a matching degree higher than a preset matching degree, if it exists, it determines that the matching is successful, and if it does not exist, it determines that the matching fails.
  • the preset matching degree may be a matching degree threshold value set according to empirical values, which is used to detect whether there is a historical voice feature sample matching the voice feature sample to be matched.
  • the specific value can be determined according to the actual situation, and there is no specific limitation on this.
  • the main control board determines that the matching is successful when it detects that there are historical voice feature samples with a matching degree higher than a preset matching degree, otherwise it determines that the matching fails.
  • the matching degree may be higher than the preset matching degree.
  • the corresponding matching degree of the historical speech feature samples is sorted in order from high to low, and then the historical speech feature samples corresponding to the first matching degree are used as target historical speech feature samples.
  • the main control board extracts feature point data from the current voice feature data according to a preset dimension, and uses the extracted feature point data as the voice feature samples to be matched; determines the voice feature samples to be matched and the historical voice feature samples pre-stored locally.
  • the degree of matching between them detecting whether there is a historical voice feature sample with a matching degree higher than a preset matching degree; if it exists, it determines that the matching is successful; if it does not exist, it determines that the matching fails, improving the accuracy of speech recognition.
  • FIG. 4 is a schematic flowchart of a third embodiment of an air conditioning control method according to the present application.
  • step S20 the method further includes:
  • Step S201 ' acquiring current time information when the matching fails, and determining a time period corresponding to the current time information
  • the voice samples to be matched fail to match.
  • the user's voice is very short, and the voice feature data that can be extracted from the voice information collected by the main control board is too small.
  • the matching voice feature samples are not enough to complete the matching; or the voice information sent by the user due to physical reasons is distorted, causing the matching to fail repeatedly; but in fact, each user's use of air conditioning has more or less certain rules, such as User A in a household is accustomed to use air conditioner 1 for ventilation during 10: 00-12: 00 in a day.
  • User B tends to use air conditioner 2 for cooling after returning home from work (such as 18:30).
  • User C likes to use air conditioner on weekends. 3Dehumidify.
  • the main control board can obtain the current time information when the matching fails, determine the time period corresponding to the current time information, and then Subsequent temperature adjustments are performed based on the time period.
  • the main control board can count the number of failed matching failures within a period of time (such as 1 minute, 2 minutes), and then compare the number of failures with a preset number of thresholds. When the number of times exceeds the number of times threshold, the step of obtaining current time information and determining a time period corresponding to the current time information is performed again, thereby effectively preventing accidental matching failures from causing the main control board to immediately execute the step S201 ′.
  • Step S202 ' Find a target operation log containing the time period in a pre-stored operation log according to the time period;
  • the air conditioning control method provided in this embodiment further includes the step of recording the adjustment time information of the air conditioner during temperature adjustment.
  • the adjustment time information includes an adjustment start time and an adjustment end time; determining an adjustment period to which the current temperature adjustment belongs according to the adjustment start time and the adjustment end time; and obtaining temperature adjustment information within the adjustment period, Generate an operation log of the air conditioner according to the temperature adjustment information, and save the operation log.
  • each time the main control board performs temperature adjustment it will record the adjustment information of the entire adjustment process (such as adjustment time information, adjustment information made by the user during the adjustment process, etc.), and then generate based on the recorded information During this period, the operation log of the air-conditioning system is stored in the operation log mark according to the adjustment time information.
  • the adjustment information of the entire adjustment process such as adjustment time information, adjustment information made by the user during the adjustment process, etc.
  • the main control board may convert the adjustment start time and the adjustment end time in the adjustment time information into a preset format (such as Unix format) timestamp, and then combine the timestamps to mark the operation log, that is, The combined timestamp is associated with the run log.
  • a preset format such as Unix format
  • the main control board may convert the determined time period into a time stamp of a preset format, and then combine the time stamps to obtain a combined time stamp, and then store the pre-stored data according to the association relationship between the combined time stamp and the running log. Find the target run log in the run log.
  • Step S203 ' extract corresponding target temperature adjustment information from the target operation log, and control the air conditioner to perform temperature adjustment according to the target temperature adjustment information.
  • the main control board may extract corresponding target temperature adjustment information from it and then control the air conditioner to perform temperature adjustment according to specific temperature adjustment parameters contained in the target temperature adjustment information.
  • the main control board obtains the current time information when the matching fails, and determines the time period corresponding to the current time information. According to the time period, the target operation log containing the time period is searched in the pre-stored operation log; and the corresponding operation log is extracted from the target operation log. Target temperature adjustment information, and control the air conditioner to perform temperature adjustment according to the target temperature adjustment information. When the matching fails, the air conditioner can still accurately control the temperature adjustment for the user.
  • the aforementioned storage medium may be a read-only memory, a magnetic disk, or an optical disk.
  • FIG. 5 is a structural block diagram of a first embodiment of an air conditioning control device of the present application.
  • the air conditioning control device includes: a feature extraction module 501, a feature matching module 502, and a temperature adjustment module 503;
  • the feature extraction module 501 is configured to obtain voice information in the current environment, and perform feature extraction on the voice information to obtain current voice feature data;
  • the air-conditioning control device proposed in this embodiment may be a processor or a controller for controlling the operation of the air-conditioning equipment.
  • the feature extraction module 501 may collect voice information in the current environment through a sound sensor preset by the air-conditioning device, and then perform feature extraction on the collected voice information to obtain the voice information.
  • the current voice feature data corresponding to the voice information.
  • the sound sensor may be an instrument with a sound wave collection function similar to a microphone or a microphone array, which may be built-in or external to an air-conditioning device, and the voice characteristic data to be extracted in this embodiment includes, but is not limited to, sound rays, Spectrum, cepstrum, formant, pitch, and reflection coefficient data.
  • the feature extraction module 501 in this embodiment is further configured to obtain voice information in the current environment, perform analog-to-digital conversion on the voice information to obtain the voice information to be filtered, perform filtering processing on the voice information to be filtered, and Feature extraction is performed on the filtered voice information to obtain the current voice feature data.
  • the feature matching module 502 is configured to match the current voice feature data as a voice feature sample to be matched with a pre-stored historical voice feature sample;
  • the feature matching module 502 described in this embodiment is further configured to record voice feature data corresponding to a user (such as a family member) who has the right to use the air conditioner and save it as a historical voice feature data sample tag, so as to facilitate For subsequent use.
  • a user such as a family member
  • the feature matching module 502 marks different historical speech feature data samples
  • specific marking rules can be customized by the user.
  • the historical voice characteristic data sample corresponding to the father may be labeled as “father”
  • the historical voice characteristic data sample corresponding to the mother may be labeled as “mother”, which is not limited in this embodiment.
  • the feature matching module 502 may prompt the user to perform personalized settings for temperature adjustment through the human-machine interaction interface of the air conditioner, and the personalized settings include: setting a common air conditioner name Or mark (in the case of multiple air conditioners), target adjustment temperature, target temperature adjustment mode (such as cooling, heating, dehumidification) and other temperature adjustment information, and use these temperature adjustment information and voice characteristic data samples (or their tags) Make associations and establish mapping relationships.
  • the personalized settings include: setting a common air conditioner name Or mark (in the case of multiple air conditioners), target adjustment temperature, target temperature adjustment mode (such as cooling, heating, dehumidification) and other temperature adjustment information, and use these temperature adjustment information and voice characteristic data samples (or their tags) Make associations and establish mapping relationships.
  • the feature matching module 502 may receive historical voice information and temperature adjustment information input by a user; perform feature extraction on the historical voice information, and use the extracted historical voice feature data as a historical voice feature sample corresponding to the user Establishing a mapping relationship between the historical speech feature samples and the temperature adjustment information, and storing the mapping relationship
  • the temperature adjustment module 503 is configured to obtain a target historical voice feature sample that is successfully matched, find temperature adjustment information associated with the target historical voice feature sample in a mapping relationship, and control the temperature of the air conditioner according to the temperature adjustment information. Adjustment.
  • the temperature adjustment module 503 may find the association with the target historical voice feature samples according to a pre-established mapping relationship. Temperature adjustment information, and then control the target air conditioner to perform temperature adjustment according to the target air conditioner's name or logo, target adjustment temperature, target temperature adjustment mode and other information contained in the temperature adjustment information.
  • the current voice feature data is obtained by acquiring voice information in the current environment and feature extraction of the voice information; the current voice feature data is used as a voice feature sample to be matched with a pre-stored historical voice feature sample; and a successful target is obtained.
  • Historical speech feature samples find the temperature adjustment information associated with the target historical speech feature samples in the mapping relationship, and control the air conditioner for temperature adjustment based on the temperature adjustment information. Because the current speech feature data is obtained based on the voice information sent by the user, then The final temperature adjustment information is found according to the current voice characteristic data, and then the air conditioner is controlled for temperature adjustment according to the temperature adjustment information, so that the user does not need to manually or soundly input the corresponding temperature adjustment parameters, which improves the user experience.
  • the feature matching module 502 is further configured to extract feature point data from the current voice feature data according to a preset dimension, and use the extracted feature point data as a voice feature sample to be matched; and determine the feature to be matched The degree of matching between the voice feature samples and the locally pre-stored historical voice feature samples; detecting whether there is a historical voice feature sample with a matching degree higher than the preset matching degree, and if it exists, it determines that the match is successful, and if it does not exist, it determines that the matching fails.
  • the feature matching module 502 is further configured to extract common feature point data in the feature samples to be matched and historical feature samples of the voice; determine the common feature point data in the features to be matched in the feature to be matched The proportion of the sample, and the proportion is taken as the degree of matching between the to-be-matched speech feature samples and the historical speech feature samples.
  • the air conditioning control device of the present application further includes a log recording module, which is used to record the adjustment time information of the air conditioner when the temperature is adjusted, and the adjustment time information includes the adjustment start time and the adjustment end time; The adjustment start time and the adjustment end time determine an adjustment period to which the current temperature adjustment belongs; obtain temperature adjustment information in the adjustment period, generate an operation log of the air conditioner according to the temperature adjustment information, and save the operation log .
  • a log recording module which is used to record the adjustment time information of the air conditioner when the temperature is adjusted, and the adjustment time information includes the adjustment start time and the adjustment end time; The adjustment start time and the adjustment end time determine an adjustment period to which the current temperature adjustment belongs; obtain temperature adjustment information in the adjustment period, generate an operation log of the air conditioner according to the temperature adjustment information, and save the operation log .
  • the temperature adjustment module 503 is further configured to obtain current time information when the matching fails, to determine a time period corresponding to the current time information; and to search the pre-stored operation log for the time period according to the time period.
  • a target operation log ; extracting corresponding target temperature adjustment information from the target operation log, and controlling the air conditioner to perform temperature adjustment according to the target temperature adjustment information.
  • the method of the embodiment can be implemented by means of software plus a necessary universal hardware platform, and of course, it can also be implemented by hardware, but in many cases the former is a better implementation.
  • the technical solution in essence or the part that contributes to the existing technology can be embodied in the form of a software product.
  • the computer software product is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, optical Disk) includes a number of instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in the embodiments of the present application.

Abstract

一种空调控制方法、空调控制装置、空调设备及存储介质，方法包括：获取当前环境中的语音信息，对语音信息进行特征提取获得当前语音特征数据；将当前语音特征数据作为待匹配语音特征样本与预存的历史语音特征样本进行匹配；获取匹配成功的目标历史语音特征样本，在映射关系中查找与目标历史语音特征样本关联的温度调节信息，并根据温度调节信息控制空调进行温度调节。

Description

空调控制方法、空调控制装置、空调设备及存储介质
本申请要求于2018年06月27日提交中国专利局、申请号为201810676088.7、发明名称为“空调控制方法、空调控制装置、空调设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在申请中。
技术领域
本申请涉及空调技术领域，尤其涉及一种空调控制方法、空调控制装置、空调设备及存储介质。
背景技术
随着物联网技术的快速发展，智能家居作为一个新兴产业，其相关的产品也越来越受到各类消费者的青睐。以空调行业为例，现有的智能空调虽然一定程度上实现了声控温度调节，但其精细化程度不高，用户在通过声音控制空调开启后，空调往往会根据上次关机时的温度/模式或默认的温度/模式来进行温度调节，此时用户仍然需要手动或声控输入相应的温度来使智能空调进行正确的温度调节，导致用户的使用体验不佳，不能为用户提供更人性化的服务。
发明内容
本申请的主要目的在于提供一种空调控制方法、空调控制装置、空调设备及存储介质，旨在解决现有技术中用户在使用空调设备进行温度调节时，需要手动或声控输入调节温度，导致用户使用体验不佳的技术问题。
为实现上述目的，本申请提供了一种空调控制方法，所述方法包括以下步骤:
获取当前环境中的语音信息，对所述语音信息进行特征提取获得当前语音特征数据；
将所述当前语音特征数据作为待匹配语音特征样本与预存的历史语音特征样本进行匹配；
获取匹配成功的目标历史语音特征样本，在映射关系中查找与所述目标历史语音特征样本相关联的温度调节信息，并根据所述温度调节信息控制空调进行温度调节。
此外，为实现上述目的，本申请还提出一种空调控制装置，所述装置包括：特征提取模块、特征匹配模块和温度调节模块；
其中，所述特征提取模块，用于获取当前环境中的语音信息，对所述语音信息进行特征提取获得当前语音特征数据；
所述特征匹配模块，用于将所述当前语音特征数据作为待匹配语音特征样本与预存的历史语音特征样本进行匹配；
所述温度调节模块，用于获取匹配成功的目标历史语音特征样本，在映射关系中查找与所述目标历史语音特征样本相关联的温度调节信息，并根据所述温度调节信息控制空调进行温度调节。
此外，为实现上述目的，本申请还提出一种空调设备，所述空调设备包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的空调控制程序，所述空调控制程序配置为实现如上文所述的空调控制方法的步骤。
此外，为实现上述目的，本申请还提出一种存储介质，所述存储介质上存储有空调控制程序，所述空调控制程序被处理器执行时实现如上文所述的空调控制方法的步骤。
本实施例的空调控制方法、空调控制装置、空调设备及存储介质，通过获取当前环境中的语音信息，对语音信息进行特征提取获得当前语音特征数据；将当前语音特征数据作为待匹配语音特征样本与预存的历史语音特征样本进行匹配；获取匹配成功的目标历史语音特征样本，在映射关系中查找与目标历史语音特征样本相关联的温度调节信息，并根据温度调节信息控制空调进行温度调节，由于是根据用户发出的语音信息来获取当前语音特征数据，再根据当前语音特征数据查找最终的温度调节信息，然后根据温度调节信息控制空调进行温度调节，因而并不需要用户手动或声控输入相应的温度调节参数，提高了用户的使用体验。
附图说明
图1是本申请实施例方案涉及的硬件运行环境的空调设备的结构示意图；
图2为本申请空调控制方法第一实施例的流程示意图；
图3为本申请空调控制方法第二实施例的流程示意图；
图4为本申请空调控制方法第三实施例的流程示意图；
图5为本申请空调控制装置第一实施例的结构框图。
本申请目的的实现、功能特点及优点将结合实施例，参照附图做进一步说明。
具体实施方式
应当理解，此处所描述的具体实施例仅用以解释本申请，并不用于限定本申请。
参照图1，图1为本申请实施例方案涉及的硬件运行环境的空调设备结构示意图。
如图1所示，该空调设备可以包括：处理器1001，例如中央处理器（Central Processing Unit，CPU），通信总线1002、用户接口1003，网络接口1004，存储器1005。其中，通信总线1002用于实现这些组件之间的连接通信。用户接口1003可以包括显示屏（Display）、输入单元比如键盘（Keyboard），可选用户接口1003还可以包括标准的有线接口、无线接口。网络接口1004可选的可以包括标准的有线接口、无线接口（如无线保真（WIreless-FIdelity，WI-FI）接口）。存储器1005可以是高速的随机存取存储器（Random Access Memory，RAM）存储器，也可以是稳定的非易失性存储器（Non-Volatile Memory，NVM），例如磁盘存储器。存储器1005可选的还可以是独立于前述处理器1001的存储装置。
本领域技术人员可以理解，图1中示出的结构并不构成对空调设备的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。
如图1所示，作为一种存储介质的存储器1005中可以包括操作系统、数据存储模块、网络通信模块、用户接口模块以及空调控制程序。
在图1所示的空调设备中，网络接口1004主要用于与网络服务器进行数据通信；用户接口1003主要用于与用户进行数据交互；本申请空调设备中的处理器1001、存储器1005可以设置在空调设备中，所述空调设备通过处理器1001调用存储器1005中存储的空调控制程序，并执行本申请实施例提供的空调控制方法。
本申请实施例提供了一种空调控制方法，参照图2，图2为本申请一种空调控制方法第一实施例的流程示意图。
本实施例中，所述空调控制方法包括以下步骤：
步骤S10：获取当前环境中的语音信息，对所述语音信息进行特征提取获得当前语音特征数据；
需要说明的是，本方法实施例的执行主体可以是空调主控板，所述空调主控板（以下简称主控板）可以是单独一台空调的中央处理器，也可以是多台空调（如家庭的多个房间中装设的不同空调）共用的中央处理器。在特定的场景中，用户可以通过该中央处理器同时控制多台空调的运行，也可以具有针对性的控制某一台空调运行。
在具体实现中，空调设备在启动时，主控板可通过预置的声音传感器来采集当前环境中的语音信息，然后对采集到的语音信息进行特征提取，以获取所述语音信息对应的当前语音特征数据。其中，所述声音传感器可以是类似于麦克风或麦克风阵列等具有声波采集功能的仪器，其可内置或外置于空调设备，且本实施例中需要提取的语音特征数据包括但不限于声线、频谱、倒频谱、共振峰、基音以及反射系数等数据。
进一步地，考虑到声音传感器采集到的语音信息中往往包含两类语音信息：一类是人类发出的，有效的语音信息；另一类是宠物、钟表、电视/电脑等事物发出的，对后续语音特征识别存在干扰的“噪声信息”。因此，为了保证语音识别的效果及准确性，需要将语音信息中的“噪声信息”进行剔除。具体的，本实施例中所述主控板可获取当前环境中的语音信息，对所述语音信息（模拟信号）进行模数转换获得待过滤语音信息（数字信号）；对所述待过滤语音信息进行滤波处理，并对滤波处理后的语音信息进行特征提取，获得当前语音特征数据。
步骤S20：将所述当前语音特征数据作为待匹配语音特征样本与预存的历史语音特征样本进行匹配；
可理解的是，在执行本步骤之前，需要将具有空调使用权限的用户（例如家庭成员）对应的语音特征数据进行录入并作为历史语音特征数据样本标记保存，以便于后续使用。
需要说明的是，对不同的历史语音特征数据样本进行标记时，具体的标记规则可以由用户自定义。以家用空调为例，父亲对应的历史语音特征数据样本可标记为“father”，母亲对应的历史语音特征数据样本可标记为“mother”，本实施例对此不作限制。
进一步地，主控板在用户录入各自对应的语音特征数据后，可通过空调的人机交互界面提示用户进行温度调节的个性化设定，该个性化设定包括：设定常用空调名称或标识（存在多台空调的情况时）、目标调节温度、目标温度调节模式（如制冷、制热、除湿）等温度调节信息，并将这些温度调节信息与语音特征数据样本（或其标记）进行关联，建立映射关系。具体的，所述主控板可接收用户输入的历史语音信息和温度调节信息；对所述历史语音信息进行特征提取，将提取出的历史语音特征数据作为所述用户对应的历史语音特征样本；建立所述历史语音特征样本与所述温度调节信息之间的映射关系，对所述映射关系进行保存。
在具体实现中，主控板在提取出当前语音特征数据后，可将当前语音特征数据作为待匹配语音特征样本与空调设备本地预存的历史语音特征样本进行匹配，以查找是否存在语音特征数据相同或相似的历史语音特征样本。
步骤S30：获取匹配成功的目标历史语音特征样本，在映射关系中查找与所述目标历史语音特征样本相关联的温度调节信息，并根据所述温度调节信息控制空调进行温度调节。
在具体实现中，主控板在获取到匹配成功的历史语音特征样本（即所述目标历史语音特征样本）后，可根据预先建立的映射关系查找与所述目标历史语音特征样本相关联的温度调节信息，然后根据温度调节信息中包含的目标空调的名称或标识、目标调节温度、目标温度调节模式等信息控制目标空调进行温度调节。
本实施例通过获取当前环境中的语音信息，对语音信息进行特征提取获得当前语音特征数据；将当前语音特征数据作为待匹配语音特征样本与预存的历史语音特征样本进行匹配；获取匹配成功的目标历史语音特征样本，在映射关系中查找与目标历史语音特征样本相关联的温度调节信息，并根据温度调节信息控制空调进行温度调节，由于是根据用户发出的语音信息来获取当前语音特征数据，再根据当前语音特征数据查找最终的温度调节信息，然后根据温度调节信息控制空调进行温度调节，从而使得用户并不需要手动或声控输入相应的温度调节参数，提高了用户的使用体验。
参考图3，图3为本申请一种空调控制方法第二实施例的流程示意图。
基于上述第一实施例，在本实施例中，所述步骤S20包括：
步骤S201：按预设维度从当前语音特征数据中提取特征点数据，将提取出的特征点数据作为待匹配语音特征样本；
需要说明的是，本实施例中所述预设维度包括但不限于：声学特征（频谱、倒频谱、共振峰、基音、反射系数）、词法特征（说话人相关的词n-gram，音素n-gram）、韵律特征（利用n-gram描述的基音和能量“姿势”）、语种、方言和/或口音信息等。
在具体实现中，主控板按照预先设定的维度从当前语音特征数据中提取出本次语音识别对应的特征点数据，并将提取出的特征点数据作为待匹配语音特征样本与本地预存的历史语音特征样本进行匹配。
步骤S202：确定所述待匹配语音特征样本与本地预存的历史语音特征样本之间的匹配度；
在具体实现中，主控板在获取到待匹配语音特征样本后，从本地数据库中提取预存的历史语音特征样本，然后将待匹配语音样本与不同用户的历史语音特征样本进行逐一匹配，根据两者之间的匹配度来判断最终的匹配结果。
进一步地，所述主控板可提取所述待匹配语音特征样本和所述历史语音特征样本中共有的特征点数据；确定所述共有的特征点数据在所述待匹配语音特征样本中所占的比重，并将所述比重作为所述待匹配语音特征样本和所述历史语音特征样本之间的匹配度，例如：待匹配语音样本中包含的特征点数据为{A,B,C,D,H,J}，历史语音特征样本1包含的历史特征点数据为{A,B,D,E,J,I}，历史语音特征样本2包含的历史特征点数据为{B,C,D,E,F,I}，历史语音特征样本3包含的历史特征点数据为{A,C,D,E,I,L}，则待匹配语音特征样本和历史语音特征样本1、2和3中共有的特征点数据分别为{A,B,D,J}、{B,C,D}和{A,C,D}，因此根据公式“比重=共有的特征点数据个数/待匹配语音样本中的特征点数据总数”可计算出上述共有的特征点数据在待匹配语音特征样本中所占的比重分别为66.7%、50%和50%。
主控板在确定出待匹配语音特征样本和历史语音特征样本中共有的特征点数据在待匹配语音特征样本中所占的比重后，即可确定所述待匹配语音特征样本与本地预存的历史语音特征样本之间的匹配度。
步骤S203：检测是否存在匹配度高于预设匹配度的历史语音特征样本，若存在则判定匹配成功，若不存在则判定匹配失败。
可理解的是，所述预设匹配度可以是根据经验值设定的匹配度阈值，其用于检测是否存在与待匹配语音特征样本相匹配的历史语音特征样本，所述预设匹配度的具体数值可根据实际情况确定，对此不作具体限制。
在具体实现中，主控板在检测到存在匹配度高于预设匹配度的历史语音特征样本时则判定匹配成功，反之则判定匹配失败。
当然，为了避免出现存在两个或两个以上的匹配度高于预设匹配度的历史语音特征样本，导致无法准确确定目标历史语音特征样本的情况，可将匹配度高于预设匹配度的历史语音特征样本各自对应的匹配度按从高到低的顺序进行排序，然后将排序第一的匹配度对应的历史语音特征样本作为目标历史语音特征样本。
本实施例主控板通过按预设维度从当前语音特征数据中提取特征点数据，将提取出的特征点数据作为待匹配语音特征样本；确定待匹配语音特征样本与本地预存的历史语音特征样本之间的匹配度；检测是否存在匹配度高于预设匹配度的历史语音特征样本，若存在则判定匹配成功，若不存在则判定匹配失败，提高了语音识别的准确度。
参考图4，图4为本申请一种空调控制方法第三实施例的流程示意图。
基于上述各实施例，在本实施例中，所述步骤S20之后，所述方法还包括：
步骤S201'：在匹配失败时获取当前时间信息，确定所述当前时间信息对应的时间段；
可理解的是，在实际生活中经常会存在待匹配语音样本匹配失败的情况，例如，用户发出的声音很短，主控板采集到的语音信息中能够提取的语音特征数据过少，导致待匹配语音特征样本不足以完成匹配；又或是用户由于身体原因发出的语音信息失真，导致匹配屡次失败；但实际上每个用户使用空调的方式或习惯或多或少都存在一定的规律，如同一家庭中用户A习惯在一天之中的10:00-12:00使用空调1换气，用户B往往在下班回家（如18:30）后使用空调2制冷，用户C喜欢在周末使用空调3除湿。因此为了使用户能够在匹配失败时，主控板仍能够精准地控制空调为用户进行温度调节，主控板可在匹配失败时获取当前时间信息，确定所述当前时间信息对应的时间段，然后根据时间段来进行后续的温度调节。
当然，为了保证较高的用户体验，主控板可统计一段时间（如1分钟、2分钟）内匹配失败的失败次数，然后将失败次数与预先设定的次数阈值进行比较，在所述失败次数超过所述次数阈值时，再执行获取当前时间信息，确定所述当前时间信息对应的时间段的步骤，从而有效的避免偶然的匹配失败导致主控板立即执行所述步骤S201'。
步骤S202'：根据所述时间段在预存的运行日志中查找包含所述时间段的目标运行日志；
需要说明的是，为了根据时间段获取到空调在同一历史时间段的温度调节信息，在执行本步骤之前，本实施例提供的空调控制方法还包括步骤：记录空调进行温度调节时的调节时间信息，所述调节时间信息包括调节起始时间和调节结束时间；根据所述调节起始时间和所述调节结束时间确定本次温度调节所属的调节时段；获取所述调节时段内的温度调节信息，根据所述温度调节信息生成空调的运行日志，并保存所述运行日志。也就是说本实施例中主控板在每次进行温度调节时，都会记录整个调节过程的调节信息（如调节时间信息、调节过程中的用户所作的调整信息等），然后根据记录的信息生成在这一时段内空调系统的运行日志，再根据调节时间信息对运行日志标记保存。
进一步地，主控板可将调节时间信息中的调节起始时间和调节结束时间分别转换为预设格式的（如Unix格式）时间戳，然后将时间戳进行组合后对运行日志进行标记，即将组合后的时间戳和运行日志进行关联。
在具体实现中，主控板可将确定出的时间段转换为预设格式的时间戳，然后将时间戳进行组合获得组合时间戳，再根据组合时间戳和运行日志之间的关联关系在预存的运行日志中查找目标运行日志。
步骤S203'：从所述目标运行日志中提取对应的目标温度调节信息，并根据所述目标温度调节信息控制所述空调进行温度调节。
在具体实现中，主控板在获取到目标运行日志后，可从中提取对应的目标温度调节信息然后根据所述目标温度调节信息中包含的具体温度调节参数控制空调进行温度调节。
本实施例主控板在匹配失败时获取当前时间信息，确定当前时间信息对应的时间段；根据时间段在预存的运行日志中查找包含时间段的目标运行日志；从目标运行日志中提取对应的目标温度调节信息，并根据目标温度调节信息控制空调进行温度调节，能够在匹配失败时，仍然准确地控制空调为用户进行温度调节。
需要说明的是，本领域普通技术人员可以理解实现上述实施例的全部或部分步骤可以通过硬件来完成，也可以通过程序来指令相关的硬件完成，所述的程序可以存储于一种计算机可读存储介质中，上述提到的存储介质可以是只读存储器，磁盘或光盘等。
参照图5，图5为本申请空调控制装置第一实施例的结构框图。
如图5所示，本申请实施例提出的空调控制装置包括：特征提取模块501、特征匹配模块502和温度调节模块503；
其中，所述特征提取模块501，用于获取当前环境中的语音信息，对所述语音信息进行特征提取获得当前语音特征数据；
需要说明的是，本实施例提出的空调控制装置可以是用于控制空调设备运行的处理器或控制器。
在具体实现中，空调设备在启动时，所述特征提取模块501可通过空调设备预置的声音传感器来采集当前环境中的语音信息，然后对采集到的语音信息进行特征提取，以获取所述语音信息对应的当前语音特征数据。其中，所述声音传感器可以是类似于麦克风或麦克风阵列等具有声波采集功能的仪器，其可内置或外置于空调设备，且本实施例中需要提取的语音特征数据包括但不限于声线、频谱、倒频谱、共振峰、基音以及反射系数等数据。
进一步地，为了保证语音识别的效果及准确性。本实施例中所述特征提取模块501，还用于获取当前环境中的语音信息，对所述语音信息进行模数转换获得待过滤语音信息；对所述待过滤语音信息进行滤波处理，并对滤波处理后的语音信息进行特征提取，获得当前语音特征数据。
所述特征匹配模块502，用于将所述当前语音特征数据作为待匹配语音特征样本与预存的历史语音特征样本进行匹配；
可理解的是，本实施例中所述特征匹配模块502，还用于将具有空调使用权限的用户（例如家庭成员）对应的语音特征数据进行录入并作为历史语音特征数据样本标记保存，以便于后续使用。
需要说明的是，特征匹配模块502对不同的历史语音特征数据样本进行标记时，具体的标记规则可以由用户自定义。以家用空调为例，父亲对应的历史语音特征数据样本可标记为“father”，母亲对应的历史语音特征数据样本可标记为“mother”，本实施例对此不作限制。
进一步地，在用户录入各自对应的语音特征数据后，特征匹配模块502可通过空调设备的人机交互界面提示用户进行温度调节的个性化设定，该个性化设定包括：设定常用空调名称或标识（存在多台空调的情况时）、目标调节温度、目标温度调节模式（如制冷、制热、除湿）等温度调节信息，并将这些温度调节信息与语音特征数据样本（或其标记）进行关联，建立映射关系。具体的，所述特征匹配模块502可接收用户输入的历史语音信息和温度调节信息；对所述历史语音信息进行特征提取，将提取出的历史语音特征数据作为所述用户对应的历史语音特征样本；建立所述历史语音特征样本与所述温度调节信息之间的映射关系，对所述映射关系进行保存
所述温度调节模块503，用于获取匹配成功的目标历史语音特征样本，在映射关系中查找与所述目标历史语音特征样本相关联的温度调节信息，并根据所述温度调节信息控制空调进行温度调节。
在具体实现中，温度调节模块503在获取到匹配成功的历史语音特征样本（即所述目标历史语音特征样本）后，可根据预先建立的映射关系查找与所述目标历史语音特征样本相关联的温度调节信息，然后根据温度调节信息中包含的目标空调的名称或标识、目标调节温度、目标温度调节模式等信息控制目标空调进行温度调节。
本实施例通过获取当前环境中的语音信息，对语音信息进行特征提取获得当前语音特征数据；将当前语音特征数据作为待匹配语音特征样本与预存的历史语音特征样本进行匹配；获取匹配成功的目标历史语音特征样本，在映射关系中查找与目标历史语音特征样本相关联的温度调节信息，并根据温度调节信息控制空调进行温度调节，由于是根据用户发出的语音信息来获取当前语音特征数据，再根据当前语音特征数据查找最终的温度调节信息，然后根据温度调节信息控制空调进行温度调节，从而使得用户并不需要手动或声控输入相应的温度调节参数，提高了用户的使用体验。
基于本申请上述空调控制装置第一实施例，提出本申请空调控制装置的第二实施例。
在本实施例中，所述特征匹配模块502，还用于按预设维度从当前语音特征数据中提取特征点数据，将提取出的特征点数据作为待匹配语音特征样本；确定所述待匹配语音特征样本与本地预存的历史语音特征样本之间的匹配度；检测是否存在匹配度高于预设匹配度的历史语音特征样本，若存在则判定匹配成功，若不存在则判定匹配失败。
进一步地，所述特征匹配模块502，还用于提取所述待匹配语音特征样本和所述历史语音特征样本中共有的特征点数据；确定所述共有的特征点数据在所述待匹配语音特征样本中所占的比重，并将所述比重作为所述待匹配语音特征样本和所述历史语音特征样本之间的匹配度。
进一步地，本申请空调控制装置还包括日志记录模块，所述日志记录模块，用于记录空调进行温度调节时的调节时间信息，所述调节时间信息包括调节起始时间和调节结束时间；根据所述调节起始时间和所述调节结束时间确定本次温度调节所属的调节时段；获取所述调节时段内的温度调节信息，根据所述温度调节信息生成空调的运行日志，并保存所述运行日志。
进一步地，所述温度调节模块503，还用于在匹配失败时获取当前时间信息，确定所述当前时间信息对应的时间段；根据所述时间段在预存的运行日志中查找包含所述时间段的目标运行日志；从所述目标运行日志中提取对应的目标温度调节信息，并根据所述目标温度调节信息控制所述空调进行温度调节。
本申请空调控制装置的其他实施例或具体实现方式可参照上述各方法实施例，此处不再赘述。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者系统不仅包括那些要素，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、物品或者系统所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者系统中还存在另外的相同要素。
上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
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上述 实施例方法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，但很多情况下前者是更佳的实施方式。基于这样的理解，本申请的 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，该计算机软件产品存储在一个存储介质（如只读存储器/随机存取存储器、磁碟、光 盘）中，包括若干指令用以使得一台终端设备(可以是手机，计算机，服务器，空调器，或者网络设备等)执行本申请各个实施例所述的方法。
以上仅为本申请的优选实施例，并非因此限制本申请的专利范围，凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本申请的专利保护范围内。

Claims (20)

  1. 一种空调控制方法，其特征在于，所述方法包括：
    获取当前环境中的语音信息，对所述语音信息进行特征提取获得当前语音特征数据；
    将所述当前语音特征数据作为待匹配语音特征样本与预存的历史语音特征样本进行匹配；
    获取匹配成功的目标历史语音特征样本，在映射关系中查找与所述目标历史语音特征样本相关联的温度调节信息，并根据所述温度调节信息控制空调进行温度调节。
  2. 如权利要求1所述的方法，其特征在于，所述获取当前环境中的语音信息，对所述语音信息进行特征提取获得当前语音特征数据的步骤，包括：
    获取当前环境中的语音信息，对所述语音信息进行模数转换获得待过滤语音信息；
    对所述待过滤语音信息进行滤波处理，并对滤波处理后的语音信息进行特征提取，获得当前语音特征数据。
  3. 如权利要求2所述的方法，其特征在于，所述将所述当前语音特征数据作为待匹配语音特征样本与预存的历史语音特征样本进行匹配的步骤之前，所述方法还包括：
    接收用户输入的历史语音信息和温度调节信息；
    对所述历史语音信息进行特征提取，将提取出的历史语音特征数据作为所述用户对应的历史语音特征样本；
    建立所述历史语音特征样本与所述温度调节信息之间的映射关系，对所述映射关系进行保存。
  4. 如权利要求3所述的方法，其特征在于，所述将所述当前语音特征数据作为待匹配语音特征样本与预存的历史语音特征样本进行匹配的步骤，包括：
    按预设维度从当前语音特征数据中提取特征点数据，将提取出的特征点数据作为待匹配语音特征样本；
    确定所述待匹配语音特征样本与本地预存的历史语音特征样本之间的匹配度；
    检测是否存在匹配度高于预设匹配度的历史语音特征样本，若存在则判定匹配成功，若不存在则判定匹配失败。
  5. 如权利要求4所述的方法，其特征在于，所述确定所述待匹配语音特征样本与本地预存的历史语音特征样本之间的匹配度的步骤，包括：
    提取所述待匹配语音特征样本和所述历史语音特征样本中共有的特征点数据；
    确定所述共有的特征点数据在所述待匹配语音特征样本中所占的比重，并将所述比重作为所述待匹配语音特征样本和所述历史语音特征样本之间的匹配度。
  6. 如权利要求5所述的方法，其特征在于，所述方法还包括：
    记录空调进行温度调节时的调节时间信息，所述调节时间信息包括调节起始时间和调节结束时间；
    根据所述调节起始时间和所述调节结束时间确定本次温度调节所属的调节时段；
    获取所述调节时段内的温度调节信息，根据所述温度调节信息生成空调的运行日志，并保存所述运行日志。
  7. 如权利要求6所述的方法，其特征在于，所述将所述当前语音特征数据作为待匹配语音特征样本与预存的历史语音特征样本进行匹配之后，所述方法还包括：
    在匹配失败时获取当前时间信息，确定所述当前时间信息对应的时间段；
    根据所述时间段在预存的运行日志中查找包含所述时间段的目标运行日志；
    从所述目标运行日志中提取对应的目标温度调节信息，并根据所述目标温度调节信息控制所述空调进行温度调节。
  8. 一种空调控制装置，其特征在于，所述装置包括：特征提取模块、特征匹配模块和温度调节模块；
    其中，所述特征提取模块，用于获取当前环境中的语音信息，对所述语音信息进行特征提取获得当前语音特征数据；
    所述特征匹配模块，用于将所述当前语音特征数据作为待匹配语音特征样本与预存的历史语音特征样本进行匹配；
    所述温度调节模块，用于获取匹配成功的目标历史语音特征样本，在映射关系中查找与所述目标历史语音特征样本相关联的温度调节信息，并根据所述温度调节信息控制空调进行温度调节。
  9. 一种空调设备，其特征在于，所述空调设备包括：存储器、处理器及存储在所述存储器上并可在所述处理器上运行的空调控制程序，所述空调控制程序配置为实现以下步骤：
    获取当前环境中的语音信息，对所述语音信息进行特征提取获得当前语音特征数据；
    将所述当前语音特征数据作为待匹配语音特征样本与预存的历史语音特征样本进行匹配；
    获取匹配成功的目标历史语音特征样本，在映射关系中查找与所述目标历史语音特征样本相关联的温度调节信息，并根据所述温度调节信息控制空调进行温度调节。
  10. 如权利要求9所述的空调设备，其特征在于，所述获取当前环境中的语音信息，对所述语音信息进行特征提取获得当前语音特征数据的步骤，包括：
    获取当前环境中的语音信息，对所述语音信息进行模数转换获得待过滤语音信息；
    对所述待过滤语音信息进行滤波处理，并对滤波处理后的语音信息进行特征提取，获得当前语音特征数据。
  11. 如权利要求10所述的空调设备，其特征在于，所述将所述当前语音特征数据作为待匹配语音特征样本与预存的历史语音特征样本进行匹配的步骤之前，所述方法还包括：
    接收用户输入的历史语音信息和温度调节信息；
    对所述历史语音信息进行特征提取，将提取出的历史语音特征数据作为所述用户对应的历史语音特征样本；
    建立所述历史语音特征样本与所述温度调节信息之间的映射关系，对所述映射关系进行保存。
  12. 如权利要求11所述的空调设备，其特征在于，所述将所述当前语音特征数据作为待匹配语音特征样本与预存的历史语音特征样本进行匹配的步骤，包括：
    按预设维度从当前语音特征数据中提取特征点数据，将提取出的特征点数据作为待匹配语音特征样本；
    确定所述待匹配语音特征样本与本地预存的历史语音特征样本之间的匹配度；
    检测是否存在匹配度高于预设匹配度的历史语音特征样本，若存在则判定匹配成功，若不存在则判定匹配失败。
  13. 如权利要求12所述的空调设备，其特征在于，所述确定所述待匹配语音特征样本与本地预存的历史语音特征样本之间的匹配度的步骤，包括：
    提取所述待匹配语音特征样本和所述历史语音特征样本中共有的特征点数据；
    确定所述共有的特征点数据在所述待匹配语音特征样本中所占的比重，并将所述比重作为所述待匹配语音特征样本和所述历史语音特征样本之间的匹配度。
  14. 如权利要求13所述的空调设备，其特征在于，所述方法还包括：
    记录空调进行温度调节时的调节时间信息，所述调节时间信息包括调节起始时间和调节结束时间；
    根据所述调节起始时间和所述调节结束时间确定本次温度调节所属的调节时段；
    获取所述调节时段内的温度调节信息，根据所述温度调节信息生成空调的运行日志，并保存所述运行日志。
  15. 如权利要求14所述的空调设备，其特征在于，所述将所述当前语音特征数据作为待匹配语音特征样本与预存的历史语音特征样本进行匹配之后，所述方法还包括：
    在匹配失败时获取当前时间信息，确定所述当前时间信息对应的时间段；
    根据所述时间段在预存的运行日志中查找包含所述时间段的目标运行日志；
    从所述目标运行日志中提取对应的目标温度调节信息，并根据所述目标温度调节信息控制所述空调进行温度调节。
  16. 一种存储介质，其特征在于，所述存储介质上存储有空调控制程序，所述空调控制程序被处理器执行时实现如以下步骤：
    获取当前环境中的语音信息，对所述语音信息进行特征提取获得当前语音特征数据；
    将所述当前语音特征数据作为待匹配语音特征样本与预存的历史语音特征样本进行匹配；
    获取匹配成功的目标历史语音特征样本，在映射关系中查找与所述目标历史语音特征样本相关联的温度调节信息，并根据所述温度调节信息控制空调进行温度调节。
  17. 如权利要求16所述的可读存储介质，其特征在于，所述获取当前环境中的语音信息，对所述语音信息进行特征提取获得当前语音特征数据的步骤，包括：
    获取当前环境中的语音信息，对所述语音信息进行模数转换获得待过滤语音信息；
    对所述待过滤语音信息进行滤波处理，并对滤波处理后的语音信息进行特征提取，获得当前语音特征数据。
  18. 如权利要求17所述的可读存储介质，其特征在于，所述将所述当前语音特征数据作为待匹配语音特征样本与预存的历史语音特征样本进行匹配的步骤之前，所述方法还包括：
    接收用户输入的历史语音信息和温度调节信息；
    对所述历史语音信息进行特征提取，将提取出的历史语音特征数据作为所述用户对应的历史语音特征样本；
    建立所述历史语音特征样本与所述温度调节信息之间的映射关系，对所述映射关系进行保存。
  19. 如权利要求18所述的可读存储介质，其特征在于，所述将所述当前语音特征数据作为待匹配语音特征样本与预存的历史语音特征样本进行匹配的步骤，包括：
    按预设维度从当前语音特征数据中提取特征点数据，将提取出的特征点数据作为待匹配语音特征样本；
    确定所述待匹配语音特征样本与本地预存的历史语音特征样本之间的匹配度；
    检测是否存在匹配度高于预设匹配度的历史语音特征样本，若存在则判定匹配成功，若不存在则判定匹配失败。
  20. 如权利要求19所述的可读存储介质，其特征在于，所述确定所述待匹配语音特征样本与本地预存的历史语音特征样本之间的匹配度的步骤，包括：
    提取所述待匹配语音特征样本和所述历史语音特征样本中共有的特征点数据；
    确定所述共有的特征点数据在所述待匹配语音特征样本中所占的比重，并将所述比重作为所述待匹配语音特征样本和所述历史语音特征样本之间的匹配度。
PCT/CN2018/102059 2018-06-27 2018-08-24 空调控制方法、空调控制装置、空调设备及存储介质 WO2020000621A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810676088.7 2018-06-27
CN201810676088.7A CN109724215A (zh) 2018-06-27 2018-06-27 空调控制方法、空调控制装置、空调设备及存储介质

Publications (1)

Publication Number Publication Date
WO2020000621A1 true WO2020000621A1 (zh) 2020-01-02

Family

ID=66294543

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/102059 WO2020000621A1 (zh) 2018-06-27 2018-08-24 空调控制方法、空调控制装置、空调设备及存储介质

Country Status (2)

Country Link
CN (1) CN109724215A (zh)
WO (1) WO2020000621A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114636231A (zh) * 2022-03-10 2022-06-17 北京小米移动软件有限公司 空调的控制方法、装置、终端及介质

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110619874B (zh) * 2019-08-30 2020-10-23 珠海格力电器股份有限公司 语音控制方法、装置、计算机设备和存储介质
CN111121218A (zh) * 2019-12-18 2020-05-08 珠海格力电器股份有限公司 一种基于声纹识别的空调控制方法、计算机可读存储介质及空调
CN113534671A (zh) * 2020-04-22 2021-10-22 阿里巴巴集团控股有限公司 设备控制方法、空间管理系统及物联网相关设备
CN111785293B (zh) * 2020-06-04 2023-04-25 杭州海康威视系统技术有限公司 语音传输方法、装置及设备、存储介质
CN111841007A (zh) * 2020-07-29 2020-10-30 网易（杭州）网络有限公司 游戏的控制方法、装置、设备和存储介质
CN113270096A (zh) * 2021-05-13 2021-08-17 前海七剑科技(深圳)有限公司 语音响应方法、装置、电子设备及计算机可读存储介质
CN113903337A (zh) * 2021-10-13 2022-01-07 海尔(深圳)研发有限责任公司 用于语音空调控制的方法、装置、云端服务器及存储介质
CN114719421B (zh) * 2022-05-18 2024-01-19 宁波奥克斯电气股份有限公司 一种空调智能控制方法、存储介质及空调器

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5010739A (en) * 1989-06-30 1991-04-30 Kabushiki Kaisha Toshiba Air conditioning apparatus having audible sound level control function
CN105091236A (zh) * 2015-08-18 2015-11-25 耿懿超 一种基于语音识别的空调器控制方法及其控制系统
CN105202706A (zh) * 2015-10-19 2015-12-30 广东美的制冷设备有限公司 空调器控制装置、控制系统及其控制方法
CN106448652A (zh) * 2016-09-12 2017-02-22 珠海格力电器股份有限公司 空调器的控制方法和装置
CN107742520A (zh) * 2017-11-23 2018-02-27 深圳市普瑞恩科技有限公司 语音控制方法、装置及系统

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101937676A (zh) * 2010-08-17 2011-01-05 深圳市同洲电子股份有限公司 通过音频识别实现远程控制设备的方法和移动终端
CN102780819A (zh) * 2012-07-27 2012-11-14 广东欧珀移动通信有限公司 一种移动终端的语音识别联系人的方法
EP2896901B1 (en) * 2012-09-06 2019-10-23 Mitsubishi Electric Corporation Device for increasing audio pleasantness of construction equipment sound
CN102927660B (zh) * 2012-11-30 2014-09-10 四川长虹电器股份有限公司 基于自适应温控技术的智能空调控制方法及系统
CN103743065B (zh) * 2014-01-20 2019-03-08 美的集团股份有限公司 空调器的控制方法、控制系统、空调器和终端
CN103982982B (zh) * 2014-05-05 2016-10-19 美的集团股份有限公司 空调器的控制方法和空调器
CN105202687B (zh) * 2014-06-11 2017-12-19 广东美的制冷设备有限公司 空调器的控制方法及控制系统、空调器和遥控器
KR200478906Y1 (ko) * 2015-07-02 2015-12-11 김병철 에어컨용 온도조절장치 및 시스템
CN107120791A (zh) * 2017-04-27 2017-09-01 珠海格力电器股份有限公司 一种空调控制方法、装置和空调器
CN107451242A (zh) * 2017-07-26 2017-12-08 广东美的制冷设备有限公司 数据播放控制方法、系统和计算机可读存储介质
CN108061358A (zh) * 2017-11-08 2018-05-22 珠海格力电器股份有限公司 控制方法及装置、空调

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5010739A (en) * 1989-06-30 1991-04-30 Kabushiki Kaisha Toshiba Air conditioning apparatus having audible sound level control function
CN105091236A (zh) * 2015-08-18 2015-11-25 耿懿超 一种基于语音识别的空调器控制方法及其控制系统
CN105202706A (zh) * 2015-10-19 2015-12-30 广东美的制冷设备有限公司 空调器控制装置、控制系统及其控制方法
CN106448652A (zh) * 2016-09-12 2017-02-22 珠海格力电器股份有限公司 空调器的控制方法和装置
CN107742520A (zh) * 2017-11-23 2018-02-27 深圳市普瑞恩科技有限公司 语音控制方法、装置及系统

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114636231A (zh) * 2022-03-10 2022-06-17 北京小米移动软件有限公司 空调的控制方法、装置、终端及介质

Also Published As

Publication number Publication date
CN109724215A (zh) 2019-05-07

Similar Documents

Publication Publication Date Title
WO2020000621A1 (zh) 空调控制方法、空调控制装置、空调设备及存储介质
WO2017201913A1 (zh) 一种精准语音控制方法及装置
WO2019041856A1 (zh) 家电控制方法、系统、控制终端、及存储介质
WO2019218444A1 (zh) 测试报告的生成方法、装置、设备及存储介质
WO2017101266A1 (zh) 语音控制方法及系统
WO2013143334A1 (zh) 一种更新移动终端nfc固件的方法及其移动终端
WO2017028601A1 (zh) 智能终端的语音控制方法、装置及电视机系统
WO2015178600A1 (en) Speech recognition method and apparatus using device information
WO2015085765A1 (zh) 推送资讯信息的方法和智能终端
WO2021040163A1 (en) Electronic device and method for providing conversational service
WO2019080406A1 (zh) 电视机语音交互方法、语音交互控制装置及存储介质
WO2019242090A1 (zh) 智能客服应答方法、设备、存储介质及装置
WO2015030474A1 (ko) 음성 인식을 위한 전자 장치 및 방법
WO2020096172A1 (en) Electronic device for processing user utterance and controlling method thereof
WO2015135443A1 (en) Method and apparatus for simulating sound in virtual scenario, and terminal
WO2018053964A1 (zh) 基于安卓系统的语音输入标点符号的方法及装置
WO2021020877A1 (en) System and method for registering device for voice assistant service
WO2019144585A1 (zh) 虚拟机器人的控制方法、装置、设备及可读存储介质
WO2020159288A1 (ko) 전자 장치 및 그 제어 방법
WO2020032563A1 (en) System for processing user voice utterance and method for operating same
EP3824462A1 (en) Electronic apparatus for processing user utterance and controlling method thereof
WO2019235793A1 (en) Electronic device and method for providing information related to image to application through input unit
WO2019075944A1 (zh) 基于用户行为的信息屏蔽方法、装置、终端和存储介质
WO2019051902A1 (zh) 终端控制方法、空调器及计算机可读存储介质
WO2014000627A1 (zh) 网络信息推送方法及其系统、计算机存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18924576

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18924576

Country of ref document: EP

Kind code of ref document: A1