Air conditioning control method, device and air conditioning
By extracting and analyzing the user's wake-up voiceprint information, automatically identifying the user's age and identity, the complex interaction of existing air conditioners is solved, and intelligent and humanized air conditioning control is realized, especially providing more suitable for special groups. experience of user.
Patent Information
- Application Number
- CN202210456438.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-04-27
- Publication Date
- 2024-12-24
- Estimated Expiration
- 2042-04-27
AI Technical Summary
The voice interaction methods of existing air conditioners are complex, especially for special groups such as the elderly and children, the registration system voiceprint recognition method is difficult to achieve accurate identity authentication, resulting in inconvenience in human-computer interaction.
By receiving the user's wake-up voice, extracting voiceprint information, and obtaining the user's age and identity confidence based on the voiceprint information, automatically switching the air conditioner operation mode, providing temperature and humidity control suitable for users, and supporting nickname recognition and home information database updates.
It improves the humanized and intelligent interaction of air conditioners, especially for special groups, and provides convenience, realizing automatic adjustment of temperature, wind direction and wind speed to meet the usage habits and environmental needs of different users.
Smart Images

Figure CN114999472B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent control technology, and in particular to an air conditioning control method and device and an air conditioner. Background Art
[0002] In the current air-conditioning market, the interactive process of voice air-conditioning is mostly mechanical question-and-answer. Although humanized answers that have gotten rid of mechanical answers have emerged, in the current period, the degree of intelligence is far from meeting the user's usage needs.
[0003] For example, the elderly have different needs for air conditioning usage habits, ambient temperature, humidity, etc. Based on this, it is urgent to be able to identify the user's age and usage habits when the user turns on the air conditioner, and then automatically adjust the air conditioner to the appropriate mode to improve the user's comfort.
[0004] The existing technology adopts a registered voiceprint recognition method, that is, the user on the app side allows the user to enter the corresponding voice into the system according to a text provided, and then bind or memorize it through the background. When the user performs identity authentication, the text must be accurately entered to achieve effective authentication. For some special groups, such as the elderly or children, it is very difficult to achieve. Summary of the invention
[0005] The present invention provides an air conditioning control method, device and an air conditioner, which are used to solve the defects of the registered voiceprint recognition method adopted in the prior art, which requires the user to accurately input pre-entered text, resulting in complex human-computer interaction and is not suitable for special groups of people.
[0006] In a first aspect, the present invention provides an air conditioning control method, comprising:
[0007] receiving a wake-up voice input by a user, and turning on the air conditioner in response to the wake-up voice;
[0008] Acquiring the voiceprint information of the user according to the wake-up voice;
[0009] Acquire, according to the voiceprint information, a first confidence level that the user belongs to a target population;
[0010] If it is determined that the first confidence level is greater than or equal to a first threshold, the air conditioner is controlled to switch to a first operating mode suitable for the target population.
[0011] According to an air conditioning control method provided by the present invention, after obtaining the first confidence level that the user belongs to the target population, the method further includes:
[0012] If it is determined that the first confidence level is less than a first threshold but greater than a second threshold, outputting a first prompt;
[0013] If a first response voice of the user to the first prompt is not received within a first preset time period, controlling the air conditioner to operate in an original operation mode;
[0014] The first prompt is used to inquire the user whether to turn on the first operating mode; the original operating mode is based on the operating mode of the air conditioner at the end of the previous operating cycle.
[0015] According to an air conditioning control method provided by the present invention, if a first response voice of the user to the first prompt is received within a first preset time period;
[0016] Acquire the first response semantics of the first response voice;
[0017] If it is determined according to the first response semantics that the user intends to turn on the first operating mode, controlling the air conditioner to switch to the first operating mode;
[0018] If it is determined according to the first response semantics that the user intends not to turn on the first operating mode, the air conditioner is controlled to operate in the original operating mode.
[0019] According to an air conditioning control method provided by the present invention, if it is determined that the first confidence level is less than or equal to the second threshold, the air conditioning is controlled to operate in the original operation mode.
[0020] According to an air conditioning control method provided by the present invention, obtaining the voiceprint information of the user according to the wake-up voice includes:
[0021] In the case of non-strong noise, extracting the Mel-frequency cepstral coefficient features of the wake-up speech in the short-time spectrum as the voiceprint information;
[0022] In the case of strong noise, at least one of the power normalized cepstral coefficient feature, the Gammatone frequency cepstral coefficient feature and the time-frequency Gabor filter feature of the wake-up speech is extracted as the voiceprint information.
[0023] According to an air conditioning control method provided by the present invention, obtaining a first confidence level that the user belongs to a target population according to the voiceprint information includes:
[0024] Comparing the voiceprint information with all voiceprint sample information in a voiceprint model library;
[0025] Filtering out target voiceprint sample information having the highest similarity to the voiceprint information in the voiceprint model library;
[0026] The population corresponding to the target voiceprint sample information is used as the target population to which the user is attributed, and the similarity is used as the first confidence level that the user belongs to the target population.
[0027] According to an air conditioning control method provided by the present invention, the method further includes: after acquiring the voiceprint information of the user, the method further includes:
[0028] According to the voiceprint information, obtaining the confidence level that the user is identified as any family member, and setting the highest confidence level as the second confidence level;
[0029] If it is determined that the second confidence level is greater than or equal to a third threshold, then obtaining identity information of the family member corresponding to the second confidence level, and starting a reply with nickname function; the identity information includes nickname information;
[0030] If it is determined that the second confidence level is less than a third threshold, a second prompt is output; the second prompt is used to prompt the user to enter a nickname;
[0031] If a second response voice of the user to the second prompt is received within a second preset time period;
[0032] Nickname information is extracted from the second response semantics corresponding to the second response voice, and the nickname information is stored in the cloud platform family information library.
[0033] According to an air conditioning control method provided by the present invention, obtaining the confidence level of the user being identified as any family member according to the voiceprint information includes:
[0034] Comparing the voiceprint information with the voiceprint sample information of each family member in the family information database of the cloud platform;
[0035] The comparison result is set as the confidence level that the user is identified as each family member.
[0036] According to an air conditioning control method provided by the present invention, after controlling the air conditioning to switch to a first operation mode suitable for the target population, the method further includes:
[0037] receiving a control instruction input by the user, and controlling the air conditioner to switch from the first operating mode to a second operating mode in response to the control instruction;
[0038] The second operating mode, the user's identity information, the ambient temperature and humidity information, and the current date information are uploaded together to the cloud platform family information library.
[0039] According to an air conditioning control method provided by the present invention, after receiving a wake-up voice input by a user, the method further includes:
[0040] Determining the position information of the user in front of the air conditioner according to the wake-up voice;
[0041] Based on the position information, the swing direction of the air conditioner is adjusted so that the wind direction of the circulating air blown out from the air outlet of the air conditioner deviates from the position where the user is located.
[0042] In a second aspect, the present invention further provides an air conditioning control device, comprising:
[0043] A voice collection unit receives a wake-up voice input by a user and turns on the air conditioner in response to the wake-up voice;
[0044] A voiceprint extraction unit, configured to obtain the voiceprint information of the user according to the wake-up voice;
[0045] A user identification unit, obtaining a first confidence level that the user belongs to a target population according to the voiceprint information;
[0046] An operation control unit is used to control the air conditioner to switch to a first operation mode suitable for the target population when it is determined that the first confidence level is greater than or equal to a first threshold.
[0047] In a third aspect, the present invention provides an air conditioner, comprising: an air conditioner body, wherein the air conditioner body is provided with a processor, a voice collection device and a wireless communication device, and the voice collection device and the wireless communication device are provided on the air conditioner body;
[0048] It also includes a memory and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, performs the air conditioning control method as described in any one of the first aspects.
[0049] In a fourth aspect, the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any of the above-mentioned air conditioning control methods are implemented.
[0050] In a fifth aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-described air conditioning control methods.
[0051] The air conditioning control method, device and air conditioner provided by the present invention can automatically perform air conditioning temperature and humidity control operations after performing voiceprint matching based on the user's wake-up voice to switch to an operating mode suitable for the age identity, effectively improving the humanization, intelligence and interactivity of the air conditioner, and can especially provide convenience for special groups of people and give them the most appropriate feeling and experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0052] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0053] Figure 1 It is one of the flow charts of the air conditioning control method provided by the present invention;
[0054] Figure 2 This is the second flow chart of the air conditioning control method provided by the present invention;
[0055] Figure 3 It is a schematic diagram of the process of obtaining voiceprint information provided by the present invention;
[0056] Figure 4 It is a flow chart of starting the reply with nickname function provided by the present invention;
[0057] Figure 5 is a structural schematic diagram of an air conditioning control device provided by the present invention;
[0058] Figure 6 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION
[0059] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0060] It should be noted that, in the description of the embodiments of the present invention, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "include one..." do not exclude the existence of other identical elements in the process, method, article or device including the elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances.
[0061] The terms "first", "second", etc. in this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more.
[0062] Combine the following Figure 1-Figure 6 The air conditioning control method and device provided by the embodiments of the present invention are described.
[0063] Figure 1 is a flow chart of the air conditioning control method provided by the present invention, such as Figure 1 As shown, including but not limited to the following steps:
[0064] Step 101: receiving a wake-up voice input by a user, and turning on an air conditioner in response to the wake-up voice.
[0065] Among them, the user can be any family member; the air conditioner can be one of a wall-mounted air conditioner, a cabinet air conditioner and a ceiling air conditioner, etc.; the wake-up voice can be a voice sent by the user to the air conditioner with the intention of turning on the air conditioner, for example: "Turn on the air conditioner", "Please turn on the air conditioner", etc., and the present invention does not make specific limitations on this.
[0066] Optionally, a voice collection device is provided on the air conditioner, including a microphone array, an analog-to-digital converter (ADC) chip, and a control chip (such as an XMOS chip). The microphone array includes a plurality of microphones, the ADC chip is connected to the microphones, and is used to convert the analog signal output by the microphone array into a digital signal for output; the XMOS chip is connected to the ADC chip, and is used to receive the digital signal output by the ADC chip.
[0067] After receiving the wake-up voice collected by the voice collection device, the internal processor of the air conditioner obtains the user's power-on intention based on the semantic judgment result converted from the wake-up voice, thereby controlling the air conditioner to turn on.
[0068] Step 102: Acquire the voiceprint information of the user according to the wake-up voice.
[0069] The so-called voiceprint information refers to a sound wave spectrum that can be displayed by electroacoustic instruments and carries speech information. The production of speech is a complex physiological and physical process between the human body's language center and the vocal organs. The vocal organs used by users when speaking, including the tongue, teeth, larynx, lungs, and nasal cavity, vary greatly in size and shape from person to person, so the sound wave spectra of any two users are different.
[0070] Although the acoustic characteristics of each user's voice are both relatively stable and variable, they are not absolute and unchanging. Such variation can come from physiology, pathology, psychology, simulation, disguise, and is also related to environmental interference. Nevertheless, since each user's pronunciation organs are different, in general, it is still possible to distinguish the voices of different users or determine whether they are the voice of the same person.
[0071] In view of this, as an optional embodiment, after acquiring the wake-up speech, the present invention converts the wake-up speech into a log domain spectrum; based on the log domain spectrum, a pre-trained voiceprint information extraction model is used to extract the voiceprint information of each frame of the wake-up speech.
[0072] It should be noted that the present invention implements voiceprint information extraction based on a text-independent recognition method and does not specify the user's voice content.
[0073] Step 103: Obtain a first confidence level that the user belongs to a target population based on the voiceprint information.
[0074] The target population may be different populations divided according to age groups, for example, children younger than a first preset age (such as 7 years old) may be divided into one population, and children older than a second preset age (such as 60 years old) may be divided into another population.
[0075] For ease of explanation, the target population is the elderly as an example in the subsequent embodiments, that is, the air conditioning control method provided by the present invention is an example of a control method serving the target population of the elderly, which is not regarded as a specific limitation on the protection scope of the present invention.
[0076] Optionally, after obtaining the voiceprint information corresponding to the user's wake-up voice, the voiceprint information is uploaded to the cloud server via a wireless network, and the voiceprint information is identified by age group in the cloud server to determine the confidence level (here referred to as the first confidence level, in percentage) that the user is a member of the target group of elderly people based on the voiceprint information, and the first confidence level is returned to the internal processor of the air conditioner.
[0077] Step 104: If it is determined that the first confidence level is greater than or equal to a first threshold, the air conditioner is controlled to switch to a first operating mode suitable for the target population.
[0078] When the target group is the elderly, the first operating mode refers to an operating mode suitable for the elderly. For example, the original temperature, wind direction, wind speed, etc. of the air conditioner are adjusted specifically for the elderly to achieve fully automatic indoor temperature, wind volume, and wind direction adjustment to meet the elderly's experience of using the air conditioner. For ease of description, the first operating mode suitable for the elderly may be referred to as the "elderly care mode" in subsequent embodiments.
[0079] The setting of the elder care mode can be pre-designed and stored in the storage unit of the internal processor of the air conditioner according to questionnaire surveys, user return visits, collection of user usage habits, etc. In this way, once the internal processor of the air conditioner determines that the first confidence level is greater than or equal to the first threshold, the elder care mode is automatically called and controlled to be executed.
[0080] Correspondingly, when the target population is children, the first operating mode refers to an operating mode suitable for children, which will not be described in detail here.
[0081] Assuming the first threshold is 80 (in percentage), the internal processor of the air conditioner can make a decision based on the comparison result between the first confidence level and the first threshold level. That is, when the first confidence level is greater than 80, it is determined that the user who inputs the wake-up voice is an elderly person. At this time, the air conditioner is controlled to switch to an operating mode suitable for the elderly.
[0082] An air conditioning control method provided by the present invention can automatically perform air conditioning temperature and humidity control operations after performing voiceprint matching based on the user's wake-up voice to switch to an operating mode suitable for the age identity, effectively improving the humanization, intelligence and interactivity of the air conditioning, and can especially provide convenience for special groups of people and give them the most appropriate feeling and experience.
[0083] Based on the content of the above embodiment, as an optional embodiment, after obtaining the first confidence that the user belongs to the target population, the method further includes:
[0084] If it is determined that the first confidence level is less than a first threshold but greater than a second threshold, outputting a first prompt;
[0085] If a first response voice of the user to the first prompt is not received within a first preset time period, controlling the air conditioner to operate in an original operation mode;
[0086] The first prompt is used to inquire the user whether to turn on the first operating mode; the original operating mode is based on the operating mode of the air conditioner at the end of the previous operating cycle.
[0087] Figure 2 This is a second flow chart of the air conditioning control method provided by the present invention. Figure 2As shown in the example, the first threshold is 80 and the second threshold is 70. After the user turns on the air conditioner by inputting the wake-up voice, when the internal processor of the air conditioner determines that the user has turned on the elderly voiceprint switch and started the elderly voiceprint detection function, the collected wake-up voice is converted into a corresponding digital signal and sent to the cloud server. The cloud server feeds back the first confidence level of identifying that the user is an elderly person to the internal processor of the air conditioner.
[0088] Among them, the user can turn on the elderly voiceprint switch by clicking the corresponding virtual button on the air-conditioning related APP, or set a corresponding virtual button on the air-conditioning panel for the user to trigger.
[0089] Optionally, after the elderly voiceprint switch is triggered, the internal processor of the air conditioner will memorize and store the user's choice, without the user having to trigger it every time the air conditioner is turned on, unless the user actively turns it off.
[0090] Furthermore, the internal processor of the air conditioner compares the first confidence level with the first threshold and the second threshold respectively. If the first confidence level is greater than or equal to the first threshold, it is determined that the user is an elderly person, and the air conditioner is directly controlled to switch to the elder care mode suitable for the elderly.
[0091] If the first confidence level is less than the first threshold but greater than the second threshold, that is, between 70-80, it cannot be determined that the user is an elderly person, but it cannot be confirmed that the user is not an elderly person. At this time, the first prompt is called by the internal processor of the air conditioner and played through the speaker pre-set on the air conditioner.
[0092] Optionally, the first prompt may be a voice prompt similar to “Do you need to turn on the elder care mode for you?” in which the user asks the user whether to turn on the elder care mode. The present invention does not make any specific limitation on this.
[0093] Furthermore, if no response voice from the user to the above-mentioned first prompt (referred to as the first response voice here) is received within a first preset time period (for example, 30 seconds), it is assumed that the user denies that he is an elderly person, that is, it is considered that the user does not need to turn on the elder care mode.
[0094] Or the user's first response voice is received within 30 seconds, but through semantic recognition of the first response voice, the recognized semantics is completely irrelevant to whether the elder care mode is turned on. For example, if the detected response voice is: "What time is it now?", it is also considered that the user does not need to turn on the elder care mode.
[0095] When it is determined that the user does not need to turn on the elder care mode, the air conditioner is controlled to execute the original operation mode, that is, to operate in a normal startup mode, that is, to operate based on the operation mode of the air conditioner at the end of the previous operation cycle.
[0096] The air conditioning control method provided by the present invention adopts voiceprint recognition technology, which can automatically obtain the confidence that the current user belongs to the target group, and then can adapt the corresponding operation mode for the user according to the confidence level, so as to achieve targeted adjustment and control of the original temperature, wind direction and wind speed of the air conditioner, and realize fully automatic indoor temperature and air volume adjustment, so as to achieve the effects of human identification, classification treatment, precise temperature adjustment and harmonious air supply. Most importantly, the method of re-inquiry in different confidence intervals can effectively avoid user misoperation.
[0097] Combination Figure 2 As shown, as an optional embodiment, if a first response voice of the user to the first prompt is received within a first preset time period;
[0098] Acquire the first response semantics of the first response voice;
[0099] If it is determined according to the first response semantics that the user intends to turn on the first operating mode, controlling the air conditioner to switch to the first operating mode;
[0100] If it is determined according to the first response semantics that the user intends not to turn on the first operating mode, the air conditioner is controlled to operate in the original operating mode.
[0101] Taking the target group as the elderly as an example, the first operating mode at this time is the elder care mode.
[0102] If the first response voice input by the user is received within a first preset time (such as 30 seconds), semantic recognition is performed on the first response voice to obtain the corresponding first response semantics.
[0103] Furthermore, the user intention is identified based on the first response semantics. If the first response semantics is used to turn on the elder care mode, for example, the converted first response semantics is an affirmative response such as: "Yes / Turn on / OK", then the air conditioner is controlled to switch to the elder care mode.
[0104] However, if the semantics of the converted first response is a negative reply such as "no / don't want / don't turn on", it is considered that the user's first response voice is not made in response to the first prompt, that is, it is judged that the user does not want to turn on the elder care mode. At this time, the internal processor of the air conditioner controls the air conditioner to continue to execute the original operating mode.
[0105] As another optional embodiment, Figure 2 As shown, if the internal processor of the air conditioner determines that the first confidence level is less than or equal to the second threshold, the air conditioner is controlled to run the original operation mode.
[0106] When the server calculates that the first confidence that the user belongs to the target group of elderly people based on the wake-up voice input by the user is less than or equal to the second threshold, it means that the wake-up voice cannot accurately determine that the user is elderly. At this time, the air conditioner can be controlled to run in the original operating mode.
[0107] Optionally, after determining that the first confidence level is less than or equal to the second threshold, the user may be reminded to re-enter any speech segment to re-extract the user's voiceprint information, and then re-identify the confidence level that the user belongs to the target population.
[0108] For example, the speaker plays: "I didn't hear your command clearly, please repeat it again." After receiving the user's re-entered voice, the corresponding voiceprint information is extracted and the confidence level is re-determined.
[0109] It should be noted that if the confidence level that the user belongs to the target group determined again based on the voice input by the user is still less than or equal to the second threshold, the air conditioner is directly controlled to run in the original operation mode.
[0110] The above embodiment describes the scenario where the air conditioner starts running when it is not turned on. As another optional embodiment, Figure 2 As shown, after determining that the air conditioner is already in the on state, if the user's wake-up voice is received, semantic recognition is performed on the wake-up voice to obtain the current user intention.
[0111] For example, if the semantics converted from the wake-up voice input by the user include semantics related to turning on the elder care mode, it is considered that the user intends to switch the current operation mode of the air conditioner to the elder care mode. If the semantics converted from the wake-up voice input by the user do not include semantics related to turning on the elder care mode, the current operation mode of the air conditioner remains unchanged.
[0112] The air conditioning control method provided by the present invention can switch to an operating mode suitable for the target group to which the user belongs according to the user's input voice not only during the air conditioning startup phase, but also during the air conditioning operation phase. The human-computer interaction process is simple and convenient for user control.
[0113] Based on the content of the above embodiment, as an optional embodiment, the above-mentioned obtaining the voiceprint information of the user according to the wake-up voice may include but is not limited to the following steps:
[0114] In the case of non-strong noise, extracting the Mel-frequency cepstral coefficient features of the wake-up speech in the short-time spectrum as the voiceprint information;
[0115] In the case of strong noise, at least one of the power normalized cepstral coefficient feature, the Gammatone frequency cepstral coefficient feature and the time-frequency Gabor filter feature of the wake-up speech is extracted as the voiceprint information.
[0116] From the perspective of features, in the case of non-strong noise, the Mel Frequency Cepstrum Coefficient (MFCC) feature based on the short-time spectrum can be used.
[0117] Mel frequency is based on the auditory characteristics of the human ear and has a nonlinear correspondence with the Hz frequency. MFCC uses this relationship to calculate the Hz spectrum features. MFCC extraction can generally be done in the following steps: pre-emphasis, framing, windowing, Fast Fourier Transform (FFT), Mel filter bank, and Discrete Cosine Transform (DCT). The specific implementation steps are not described here.
[0118] Furthermore, in the case of strong noise, some other features based on auditory perception can be used, such as power normalized cepstral coefficients (PNCC), gammatone frequency cepstral coefficients (GFCC), time-frequency Gabor filter features, etc.
[0119] Compared with MFCC, the main new features of PNCC processing include: using power-law nonlinearity instead of the traditional logarithmic nonlinearity used in MFCC coefficients, adding a noise suppression algorithm based on asymmetric filtering to suppress background excitations, and a module to implement temporal masking.
[0120] The Gammatone filter in GFCC can well simulate the frequency selection characteristics and spectrum analysis characteristics of the basilar membrane. The present invention can also propose an improved algorithm for the Gammatone filter cepstral coefficient extraction process based on the analysis of the original feature extraction algorithm, that is, using wavelet packet decomposition to replace Fourier transform, perform full-band multi-level frequency band division and fine orthogonal decomposition, and adjust the pre-emphasis coefficient at the same time to make the signal spectrum flatter.
[0121] The main idea of extracting time-frequency Gabor filter features is to first use Gabor wavelet transform to extract features from the analog signal corresponding to the wake-up speech, and use the calculated Gabor feature vector as the initial feature of the wake-up speech, thereby reducing the impact of other noises; then optimize the Gabor feature vector through sparse representation to form an enhanced Gabor filter feature, and use it as the voiceprint information corresponding to the wake-up speech.
[0122] The air conditioning control method provided by the present invention adopts different voiceprint information extraction methods for wake-up speech in different noise interference scenarios, which can effectively improve the extraction accuracy of voiceprint information.
[0123] Figure 3 is a schematic diagram of the process of obtaining voiceprint information provided by the present invention, as an optional embodiment, such as Figure 3 As shown, obtaining a first confidence level that the user belongs to a target population according to the voiceprint information includes:
[0124] Comparing the voiceprint information with all voiceprint sample information in a voiceprint model library;
[0125] Filtering out target voiceprint sample information having the highest similarity to the voiceprint information in the voiceprint model library;
[0126] The population corresponding to the target voiceprint sample information is used as the target population to which the user is attributed, and the similarity is used as the first confidence level that the user belongs to the target population.
[0127] Different users have different distributions of formant peaks in the speech spectrogram. Voiceprint information recognition determines whether they are the same person by comparing the voices of the users in two voice segments on the same phoneme, thereby realizing the function of recognizing people by hearing their voices. The main technical principles of voiceprint recognition are feature extraction and feature comparison.
[0128] The air conditioning control method provided by the present invention realizes the recognition of voiceprint information through a cloud server.
[0129] It should be noted that a voiceprint model library is pre-built on the cloud server side, which stores voiceprint sample information of many users with pre-collected identity information of different age groups, genders, occupations, etc. Each voiceprint sample information has a corresponding information tag for marking the identity information of the corresponding user.
[0130] After the air conditioner's internal processor collects the user's wake-up voice, it uploads it to the cloud server, which first extracts the voiceprint information corresponding to the wake-up voice.
[0131] Then, the voiceprint information of the user is matched in the voiceprint model library to determine a voiceprint sample information with the highest similarity to the voiceprint information as the target voiceprint sample information.
[0132] In this way, the target group to which the user belongs can be determined based on the information label corresponding to the target voiceprint sample information.
[0133] For example, after comparing the user's voiceprint information with the voiceprint sample information K in the voiceprint model library, the similarity is the highest, and the similarity between the two is 82 (in percentage), so the voiceprint sample information K is used as the target voiceprint sample information. Assuming that the user's age recorded in the information tag of the voiceprint sample information K is 70 years old, it can be determined that the target group to which the user belongs is the elderly. Accordingly, the first confidence that the user is classified as an elderly person is 82.
[0134] The present invention provides a method for realizing user classification and identification with the help of a cloud server, which can effectively improve the efficiency and accuracy of classification and identification.
[0135] Based on the content of the above embodiment, as an optional embodiment, the air conditioning control method provided by the present invention further includes: after obtaining the voiceprint information of the user, further including:
[0136] According to the voiceprint information, obtaining the confidence level that the user is identified as any family member, and setting the highest confidence level as the second confidence level;
[0137] If it is determined that the second confidence level is greater than or equal to a third threshold, then obtaining identity information of the family member corresponding to the second confidence level, and starting a reply with nickname function; the identity information includes nickname information;
[0138] If it is determined that the second confidence level is less than a third threshold, a second prompt is output; the second prompt is used to prompt the user to enter a nickname;
[0139] If a second response voice of the user to the second prompt is received within a second preset time period;
[0140] Nickname information is extracted from the second response semantics corresponding to the second response voice, and the nickname information is stored in the cloud platform family information library.
[0141] Figure 4 : is a flow chart of starting the reply with nickname function provided by the present invention, such as Figure 4 As shown, the present invention can utilize the family information database established on the cloud server to realize accurate identification of the user's identity.
[0142] Optionally, family members (ie, users) of the home where the air conditioner is installed can perform authentication registration in advance after the air conditioner is installed, so as to store personal identity information, including voiceprint information, age information, nickname, etc., in the home information database.
[0143] The registration method is that the user repeats the voice wake-up word to the air conditioner more than twice to complete the voiceprint collection. At the same time, the user can also upload his or her age, nickname, and preferences for the air conditioner's operating mode to the family information database by voice input. In this way, the family information database will store the identity information of each family member in units of each family (or each air conditioner).
[0144] As an optional embodiment, when a user uses the air conditioner, the air conditioner will collect data such as the age, air conditioner usage habits, ambient temperature, humidity, and season of different users based on the current user's identity, and upload and record them in the home information database respectively, and train the air conditioner operation mode decision model based on these data.
[0145] In this way, in the subsequent use process, once the current user is identified based on the voiceprint information input by the current user, the age and air-conditioning usage habits recorded in their identity information, combined with the current ambient temperature, humidity, month and season data, etc., can be used to use the trained air-conditioning operation mode decision model to directly switch the current user to an operation mode that meets his or her preferences, thereby giving users a smarter and more convenient experience.
[0146] At the same time, after the current user is identified based on the voiceprint information input by the current user, the reply with nickname function can be started during the human-computer interaction process, for example:
[0147] The nickname of family member A is "Lao Li". After starting the reply with nickname function, when asking family member A whether to start the elder care mode, you can output: "Lao Li, do you need to switch to the elder care mode?" This makes the human-computer dialogue more vivid and improves the user experience.
[0148] On the basis of the above, the air conditioning control method provided by the present invention can obtain the confidence level of the user being identified as any family member according to the voiceprint information, including:
[0149] The voiceprint information is compared with the voiceprint sample information of each family member in the family information database of the cloud platform; and the comparison result is set as the confidence level of the user being identified as each family member.
[0150] It should be noted that, taking the family as a unit, the voiceprint information corresponding to any voice of each family member can be extracted in advance and stored in the family information library of the cloud platform as the voiceprint sample information of each family member.
[0151] After collecting the wake-up voice input by any family member, it is uploaded to the cloud platform server. After the cloud platform server extracts the corresponding voiceprint information, it is input into the cloud platform family information library for voiceprint recognition.
[0152] As an optional method, each air conditioner has a device identification code. When the internal processor of the air conditioner uploads the wake-up voice, its device identification code is uploaded to the cloud platform server as a label. The cloud platform server can accurately compare the voiceprint information corresponding to the wake-up voice with all the voiceprint sample information of the family of the family member in the cloud platform family information database according to the device identification code, which can effectively reduce the scope of voiceprint comparison and improve the efficiency of voiceprint comparison.
[0153] Based on the content of the above embodiment, as an optional embodiment, after controlling the air conditioner to switch to the first operation mode applicable to the target population, it also includes:
[0154] receiving a control instruction input by the user, and controlling the air conditioner to switch from the first operating mode to a second operating mode in response to the control instruction;
[0155] The second operating mode, the user's identity information, the ambient temperature and humidity information, and the current date information are uploaded together to the cloud platform family information library.
[0156] Assume that the first operating mode is the elder care mode. When the air conditioner is operating in the elder care mode, if a user's control instruction is received, the control instruction instructs to make appropriate adjustments to the current elder care mode to achieve the second operating mode, and upload the adjusted second operating mode and the user's identity information, ambient temperature and humidity information, and current date information to the cloud platform family information library.
[0157] In this way, during the next operation, if the user's identity information is recognized, the operation mode of the air conditioner can be directly switched to the second operation mode without the user having to make adjustments.
[0158] Assume that the current date is June (consider it to be summer). At 8 o'clock in the evening, when the internal processor of the air conditioner receives the user's control command: "Increase the temperature", it controls the relevant components to increase the set temperature set in the original elder care mode (assuming 1°C is adjusted each time). The increased temperature is 26°C. The user's nickname is "Lao Li". The above information is used to update the relevant information of the user "Lao Li" pre-stored in the family information library of the cloud platform, and the updated operating mode is used as the second operating mode.
[0159] Then, when "Mr. Li" uses the method provided in the above embodiment to make the air conditioner enter the elder care mode in summer, it will automatically switch to the second operating mode, and "Mr. Li" does not need to control the temperature to 26°C by himself.
[0160] The air conditioning control method provided by the present invention can meet the usage habits of different users, and automatically record and store the usage habits of users. In the next same scenario, the operating mode is automatically switched for them, which is more intelligent and humane.
[0161] Based on the content of the above embodiment, as an optional embodiment, after receiving the wake-up voice input by the user, the method further includes:
[0162] Determining the position information of the user in front of the air conditioner according to the wake-up voice;
[0163] Based on the position information, the swing direction of the air conditioner is adjusted so that the wind direction of the circulating air blown out from the air outlet of the air conditioner deviates from the position where the user is located.
[0164] As an optional embodiment, it is assumed that the air conditioner provided by the present invention is used to realize the wake-up voice collection with a microphone array, which can automatically recognize the position information of the user in front of the air conditioner according to the wake-up voice input by the user. This invention will not be elaborated in detail.
[0165] It should be noted that after obtaining the user's location information, especially in the elder care mode, the direction of the air conditioner's swing blades can be adjusted automatically so that the direction of the circulating air blown out from the air outlet of the air conditioner deviates from the location of the elderly, so as to meet the elderly's general requirements for the air conditioning settings and further enhance the user's usage experience.
[0166] In summary, the air-conditioning control method provided by the present invention can automatically adjust the operating mode to suit a specific user. Through voiceprint recognition technology, it can automatically identify the identities of different air-conditioning users, and dynamically learn the user's preferences for temperature, wind speed, etc. in different time periods. After different users use voice to turn on the air-conditioner, the air-conditioner is automatically adjusted to a state suitable for the corresponding user; before learning the user's preferences, the age group is judged according to the voice, and the elderly care mode is automatically matched, which greatly improves the humanization, intelligence and interactivity of the air-conditioning.
[0167] Figure 5 is a schematic diagram of the structure of the air conditioning control device provided by the present invention, such as Figure 5 As shown, the present invention also provides an air conditioning control device, which mainly includes a voice collection unit 11, a voiceprint extraction unit 12, a user identification unit 13 and an operation control unit 14, wherein:
[0168] The voice collection unit 11 is mainly used to receive the wake-up voice input by the user, so as to turn on the air conditioner in response to the wake-up voice;
[0169] The voiceprint extraction unit 12 is mainly used to obtain the voiceprint information of the user according to the wake-up voice;
[0170] The user identification unit 13 is mainly used to obtain a first confidence level that the user belongs to the target population according to the voiceprint information;
[0171] The operation control unit 14 is mainly used to control the air conditioner to switch to a first operation mode suitable for the target population when it is determined that the first confidence level is greater than or equal to a first threshold.
[0172] It should be noted that the air conditioning control device provided in the embodiment of the present invention can execute the air conditioning control method described in any of the above embodiments during specific operation, which will not be elaborated in this embodiment.
[0173] Based on the contents of the above embodiments, as an optional embodiment, the present invention further provides an air conditioner, mainly comprising: an air conditioner body, wherein the air conditioner body is provided with a processor, a voice collection device and a wireless communication device, and the voice collection device and the wireless communication device are provided on the air conditioner body;
[0174] It also includes a memory and a program or instruction stored in the memory and executable on the processor, and when the program or instruction is executed by the processor, the air conditioning control method described in any one of the above embodiments is executed.
[0175] The air conditioning control device and air conditioner provided by the present invention can automatically perform air conditioning temperature and humidity control operations after performing voiceprint matching based on the user's wake-up voice to switch to an operating mode suitable for the age identity, effectively improving the humanization, intelligence and interactivity of the air conditioning, and can especially provide convenience for special groups of people and give them the most appropriate feeling and experience.
[0176] Figure 6 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 6As shown, the electronic device may include: a processor 610, a communication interface 620, a memory 630 and a communication bus 640, wherein the processor 610, the communication interface 620 and the memory 630 communicate with each other through the communication bus 640. The processor 610 may call the logic instructions in the memory 630 to execute the air conditioning control method, which includes: receiving a wake-up voice input by a user to turn on the air conditioning in response to the wake-up voice; obtaining the user's voiceprint information according to the wake-up voice; obtaining the first confidence that the user belongs to the target population according to the voiceprint information; if it is determined that the first confidence is greater than or equal to the first threshold, controlling the air conditioning to switch to the first operating mode applicable to the target population.
[0177] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.
[0178] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the air conditioning control method provided by the above methods, and the method includes: receiving a wake-up voice input by a user to turn on the air conditioner in response to the wake-up voice; obtaining the user's voiceprint information based on the wake-up voice; obtaining a first confidence level that the user belongs to a target population based on the voiceprint information; if it is determined that the first confidence level is greater than or equal to a first threshold, controlling the air conditioner to switch to a first operating mode applicable to the target population.
[0179] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is implemented to execute the air conditioning control method provided in the above-mentioned embodiments, the method comprising: receiving a wake-up voice input by a user to turn on the air conditioner in response to the wake-up voice; obtaining the user's voiceprint information based on the wake-up voice; obtaining a first confidence level that the user belongs to a target population based on the voiceprint information; if it is determined that the first confidence level is greater than or equal to a first threshold, controlling the air conditioner to switch to a first operating mode applicable to the target population.
[0180] The device embodiments described above are merely illustrative, wherein 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 they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.
[0181] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art 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, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0182] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. An air conditioning control method, characterized in that: include: receiving a wake-up voice input by a user, and turning on the air conditioner in response to the wake-up voice; Acquiring the voiceprint information of the user according to the wake-up voice; Acquire, according to the voiceprint information, a first confidence level that the user belongs to a target population; If it is determined that the first confidence level is greater than or equal to a first threshold, controlling the air conditioner to switch to a first operating mode suitable for the target population; If it is determined that the first confidence level is less than a first threshold but greater than a second threshold, outputting a first prompt; If a first response voice of the user to the first prompt is not received within a first preset time period, controlling the air conditioner to operate in an original operation mode; The first prompt is used to ask the user whether to turn on the first operating mode; the original operating mode is based on the operating mode of the air conditioner at the end of the previous operating cycle; If a first response voice of the user to the first prompt is received within a first preset time period; Acquire the first response semantics of the first response voice; If it is determined according to the first response semantics that the user intends to turn on the first operating mode, controlling the air conditioner to switch to the first operating mode; If it is determined according to the first response semantics that the user intends not to turn on the first operating mode, the air conditioner is controlled to operate in the original operating mode.
2. The air conditioning control method according to claim 1, characterized in that: If it is determined that the first confidence level is less than or equal to the second threshold, the air conditioner is controlled to operate in the original operation mode.
3. The air conditioning control method according to claim 1, characterized in that: The acquiring the voiceprint information of the user according to the wake-up voice includes: In the case of non-strong noise, extracting the Mel-frequency cepstral coefficient features of the wake-up speech in the short-time spectrum as the voiceprint information; In the case of strong noise, at least one of the power normalized cepstral coefficient feature, the Gammatone frequency cepstral coefficient feature and the time-frequency Gabor filter feature of the wake-up speech is extracted as the voiceprint information.
4. The air conditioning control method according to claim 1, characterized in that: Acquiring, according to the voiceprint information, a first confidence level that the user belongs to a target population, including: Comparing the voiceprint information with all voiceprint sample information in a voiceprint model library; Filtering out target voiceprint sample information having the highest similarity to the voiceprint information in the voiceprint model library; The population corresponding to the target voiceprint sample information is used as the target population to which the user is attributed, and the similarity is used as the first confidence level that the user belongs to the target population.
5. The air conditioning control method according to claim 1, characterized in that: Also includes: After obtaining the voiceprint information of the user, the method further includes: According to the voiceprint information, obtaining the confidence level that the user is identified as any family member, and setting the highest confidence level as the second confidence level; If it is determined that the second confidence level is greater than or equal to a third threshold, then obtaining identity information of the family member corresponding to the second confidence level, and starting a reply with nickname function; the identity information includes nickname information; If it is determined that the second confidence level is less than a third threshold, a second prompt is output; the second prompt is used to prompt the user to enter a nickname; If a second response voice of the user to the second prompt is received within a second preset time period; Nickname information is extracted from the second response semantics corresponding to the second response voice, and the nickname information is stored in the cloud platform family information library.
6. The air conditioning control method according to claim 5, characterized in that: The obtaining, based on the voiceprint information, a confidence level that the user is identified as any family member includes: Comparing the voiceprint information with the voiceprint sample information of each family member in the family information database of the cloud platform; The comparison result is set as the confidence level that the user is identified as each family member.
7. The air conditioning control method according to claim 6, characterized in that: After controlling the air conditioner to switch to the first operation mode suitable for the target population, the method further includes: receiving a control instruction input by the user, and controlling the air conditioner to switch from the first operating mode to a second operating mode in response to the control instruction; The second operating mode, the user's identity information, the ambient temperature and humidity information, and the current date information are uploaded together to the cloud platform family information library.
8. The air conditioning control method according to any one of claims 1 to 7, characterized in that: After receiving the wake-up voice input by the user, it also includes: Determining the position information of the user in front of the air conditioner according to the wake-up voice; Based on the position information, the swing direction of the air conditioner is adjusted so that the wind direction of the circulating air blown out from the air outlet of the air conditioner deviates from the position where the user is located.
9. An air conditioning control device, characterized in that: include: A voice collection unit receives a wake-up voice input by a user and turns on the air conditioner in response to the wake-up voice; A voiceprint extraction unit, configured to obtain the voiceprint information of the user according to the wake-up voice; A user identification unit, obtaining a first confidence level that the user belongs to a target population according to the voiceprint information; an operation control unit, for controlling the air conditioner to switch to a first operation mode suitable for the target population when determining that the first confidence level is greater than or equal to a first threshold; If it is determined that the first confidence level is less than a first threshold but greater than a second threshold, outputting a first prompt; If a first response voice of the user to the first prompt is not received within a first preset time period, controlling the air conditioner to operate in an original operation mode; The first prompt is used to ask the user whether to turn on the first operating mode; the original operating mode is based on the operating mode of the air conditioner at the end of the previous operating cycle; If a first response voice of the user to the first prompt is received within a first preset time period; Acquire the first response semantics of the first response voice; If it is determined according to the first response semantics that the user intends to turn on the first operating mode, controlling the air conditioner to switch to the first operating mode; If it is determined according to the first response semantics that the user intends not to turn on the first operating mode, the air conditioner is controlled to operate in the original operating mode.
10. An air conditioner, characterized in that: include: An air conditioner body, wherein the air conditioner body is provided with a processor, a voice collection device and a wireless communication device, and the voice collection device and the wireless communication device are arranged on the air conditioner body; It also includes a memory and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, performs the air conditioning control method as claimed in any one of claims 1 to 8.
Citation Information
Patent Citations
Voice processing method and device
CN110176229A
Startup mode determination method and device, storage medium and electronic device
CN113836508A
Terminal equipment control method and device, electronic equipment and storage medium
CN114842843A
Working mode setting method and device
CN114863932A
