Voice wake-up threshold adjustment method of household appliance, control device and server

Abstract

The invention discloses a voice wake-up threshold adjustment method of a household appliance, an operation control device, a server and a computer readable storage medium, and the method comprises the steps: obtaining wake-up audio data of all household appliances in a preset geographic area, the wake-up audio data comprising an original audio and a wake-up score; dividing the wake-up audio data into normal wake-up data and false wake-up data according to the original audio; calculating an average value of the wake-up scores of the normal wake-up data and recording the average value as a first average value, and calculating an average value of the wake-up scores of the error wake-up data and recording the average value as a second average value; and determining a wake-up threshold adjustment value according to the first average score and the second average score, and sending the wake-up threshold adjustment value to the household appliances in the preset geographic area. The method can improve the awakening accuracy of the household appliance, is high in adjustment timeliness, is short in response time, and effectively improves the user experience of the household appliance.

Description

Technical Field

[0001] The present invention relates to the field of household appliance control technology, and in particular to a method for adjusting a voice wake-up threshold of a household appliance, an operation control device, a server, and a computer-readable storage medium. Background Art

[0002] With the development of voice recognition technology, voice appliances have gradually entered people's lives. Voice appliances can obtain users' voice information, identify control instructions from the voice information, and perform corresponding operations according to the control instructions, greatly improving the convenience of use. Before voice control of voice appliances, the voice appliances need to be woken up first. Existing technical solutions gradually support the adjustable wake-up threshold function of voice appliances. However, the current adjustment method usually manually sets the wake-up threshold based on user feedback, which has disadvantages such as slow response time and poor accuracy. Summary of the invention

[0003] The purpose of the present invention is to solve at least one of the technical problems existing in the prior art, and to provide a method for adjusting the voice wake-up threshold of household appliances, an operation control device, a server and a computer-readable storage medium, which can improve the wake-up accuracy of household appliances, have high adjustment timeliness and short response time, and effectively improve the user experience of household appliances.

[0004] In a first aspect, an embodiment of the present invention provides a method for adjusting a voice wake-up threshold of a home appliance, comprising:

[0005] Acquire wake-up audio data of all household appliances in a preset geographical area, wherein the wake-up audio data includes original audio and a wake-up score;

[0006] dividing the wake-up audio data into normal wake-up data and false wake-up data according to the original audio;

[0007] Calculating an average of the awakening scores of all the normal awakening data, recorded as a first average score, and calculating an average of the awakening scores of all the false awakening data, recorded as a second average score;

[0008] A wake-up threshold adjustment value is determined according to the first average score and the second average score, and the wake-up threshold adjustment value is sent to household appliances in the preset geographical area.

[0009] The method for adjusting the voice wake-up threshold of a household appliance provided by an embodiment of the present invention has at least the following beneficial effects: by dividing geographical areas according to preset rules, the wake-up audio data of the household appliances in the preset geographical areas are obtained as reference data for adjusting the wake-up threshold, so that different geographical areas have different wake-up threshold adjustment values, that is, the influence of geographical area differences is considered when adjusting the wake-up threshold; further judgment is made through the original audio in the obtained wake-up audio data, so that normal wake-up data and false wake-up data are divided, and the average wake-up scores of the normal wake-up data and the false wake-up data are respectively counted, and then the wake-up threshold adjustment value is determined based on the average wake-up scores of the two data, and sent to the household appliances in the preset geographical area, so that the household appliances in the preset geographical area can adjust their own wake-up thresholds according to the wake-up threshold adjustment value, and the adjusted wake-up threshold can more accurately distinguish between normal wake-up and false wake-up, which is conducive to improving the wake-up accuracy of the household appliances, and there is no need for users to manually adjust the wake-up threshold, the adjustment timeliness is high, the response time is short, and the user's use experience of the household appliances can be effectively improved.

[0010] According to the voice wake-up threshold adjustment method provided by some embodiments of the present invention, determining the wake-up threshold adjustment value according to the first average score and the second average score includes:

[0011] When the difference between the first average score and the second average score is greater than a first preset value, an average of the first average score and the second average score is used as the wake-up threshold adjustment value.

[0012] According to the voice wake-up threshold adjustment method provided by some embodiments of the present invention, the determining the wake-up threshold adjustment value according to the first average score and the second average score further includes:

[0013] When the difference between the first average score and the second average score is less than the first preset value, the second average score is used as the wake-up threshold adjustment value.

[0014] According to the voice wake-up threshold adjustment method provided by some embodiments of the present invention, the dividing the wake-up audio data into normal wake-up data and false wake-up data according to the original audio includes:

[0015] Decomposing the original audio to obtain frequency features, duration features and intensity features;

[0016] The frequency feature, the duration feature, and the mandatory feature are matched with the standard wake-up audio, and the wake-up audio data is determined as normal wake-up data or false wake-up data according to the matching result.

[0017] According to the voice wake-up threshold adjustment method provided by some embodiments of the present invention, sending the wake-up threshold adjustment value to the home appliances in the preset geographical area includes:

[0018] Obtaining a threshold adjustment flag parameter of the household appliance;

[0019] When the threshold adjustment flag parameter indicates that the voice wake-up threshold of the home appliance can be adjusted, the wake-up threshold adjustment value is sent to the home appliance.

[0020] According to the voice wake-up threshold adjustment method provided by some embodiments of the present invention, when the threshold adjustment flag parameter indicates that the voice wake-up threshold of the home appliance is not adjustable, the wake-up threshold adjustment value is not sent to the home appliance.

[0021] According to the voice wake-up threshold adjustment method provided in some embodiments of the present invention, the wake-up audio data is the wake-up audio data of the home appliance during the night time period; the wake-up threshold adjustment value is the wake-up threshold adjustment value of the home appliance during the night time period.

[0022] According to the voice wake-up threshold adjustment method provided by some embodiments of the present invention, the night time period is from 23:00 in the evening of the same day to 07:00 in the morning of the next day.

[0023] According to the voice wake-up threshold adjustment method provided by some embodiments of the present invention, the preset geographical area includes seven administrative geographical divisions: North China region, Northeast region, East China region, Central China region, South China region, Southwest region, and Northwest region.

[0024] In a second aspect, an embodiment of the present invention provides an operation control device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the voice wake-up threshold adjustment method as described in the embodiment of the first aspect above.

[0025] The operation control device provided by the embodiment of the present invention has at least the following beneficial effects: by dividing the geographical areas according to the preset rules, the wake-up audio data of the household appliances in the preset geographical areas are obtained as the reference data for adjusting the wake-up threshold, so that different geographical areas have different wake-up threshold adjustment values, that is, the influence of the geographical area differences is considered when adjusting the wake-up threshold; further judgment is made through the original audio in the obtained wake-up audio data, so as to divide the normal wake-up data and the false wake-up data, and the average wake-up scores of the normal wake-up data and the false wake-up data are respectively counted, and then the wake-up threshold adjustment value is determined based on the average wake-up scores of the two data, and sent to the household appliances in the preset geographical area, so that the household appliances in the preset geographical area can adjust their own wake-up thresholds according to the wake-up threshold adjustment value, and the adjusted wake-up threshold can more accurately distinguish between normal wake-up and false wake-up, which is conducive to improving the wake-up accuracy of the household appliances, and there is no need for the user to manually adjust the wake-up threshold, the adjustment timeliness is high, the response time is short, and the user's use experience of the household appliances can be effectively improved.

[0026] In a third aspect, an embodiment of the present invention provides a server, comprising the operation control device as described in the embodiment of the second aspect above.

[0027] The server provided by the embodiment of the present invention has at least the following beneficial effects: by dividing the geographical areas according to the preset rules, the wake-up audio data of the household appliances in the preset geographical areas are obtained as the reference data for adjusting the wake-up threshold, so that different geographical areas have different wake-up threshold adjustment values, that is, the influence of the geographical area differences is considered when adjusting the wake-up threshold; further judgment is made through the original audio in the obtained wake-up audio data, so as to divide the normal wake-up data and the false wake-up data, and the average wake-up scores of the normal wake-up data and the false wake-up data are respectively counted, and then the wake-up threshold adjustment value is determined based on the average wake-up scores of the two data, and sent to the household appliances in the preset geographical area, so that the household appliances in the preset geographical area can adjust their own wake-up thresholds according to the wake-up threshold adjustment value, and the adjusted wake-up threshold can more accurately distinguish between normal wake-up and false wake-up, which is conducive to improving the wake-up accuracy of the household appliances, and there is no need for the user to manually adjust the wake-up threshold, the adjustment timeliness is high, the response time is short, and the user's use experience of the household appliances can be effectively improved.

[0028] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the voice wake-up threshold adjustment method as described in the embodiment of the first aspect above.

[0029] The computer-readable storage medium provided by the embodiment of the present invention has at least the following beneficial effects: by dividing the geographical areas according to the preset rules, the wake-up audio data of the household appliances in the preset geographical areas are obtained as the reference data for adjusting the wake-up threshold, so that different geographical areas have different wake-up threshold adjustment values, that is, the influence of the geographical area differences is considered when adjusting the wake-up threshold; further judgment is made through the original audio in the obtained wake-up audio data, so as to divide the normal wake-up data and the false wake-up data, and the average wake-up scores of the normal wake-up data and the false wake-up data are respectively counted, and then the wake-up threshold adjustment value is determined based on the average wake-up scores of the two data, and sent to the household appliances in the preset geographical area, so that the household appliances in the preset geographical area can adjust their own wake-up thresholds according to the wake-up threshold adjustment value, and the adjusted wake-up threshold can more accurately distinguish between normal wake-up and false wake-up, which is conducive to improving the wake-up accuracy of the household appliances, and there is no need for the user to manually adjust the wake-up threshold, the adjustment timeliness is high, the response time is short, and the user's use experience of the household appliances can be effectively improved.

[0030] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the technical solution of the present invention and do not constitute a limitation on the technical solution of the present invention.

[0032] The present invention is further described below in conjunction with the accompanying drawings and embodiments;

[0033] Figure 1 is a flow chart of a method for adjusting a voice wake-up threshold of a household appliance provided by an embodiment of the present invention;

[0034] Figure 2 yes Figure 1 A flowchart of the detailed method steps of step S120 in FIG.

[0035] Figure 3 yes Figure 1 A flowchart of the detailed method steps of step S140 in FIG.

[0036] Figure 4 is a flow chart of a method for adjusting a voice wake-up threshold of a household appliance provided by a specific embodiment of the present invention;

[0037] Figure 5It is a structural schematic diagram of the operation control device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0038] This section will describe in detail the specific embodiments of the present invention. The preferred embodiments of the present invention are shown in the accompanying drawings. The purpose of the accompanying drawings is to supplement the description of the text part of the specification with graphics, so that people can intuitively and vividly understand each technical feature and the overall technical solution of the present invention, but it cannot be understood as a limitation on the scope of protection of the present invention.

[0039] In the description of the present invention, "several" means one or more, "more" means more than two, "greater than", "less than", "exceed", etc. are understood to exclude the number itself, "above", "below", "within", etc. are understood to include the number itself, "at least one" means one or more, "at least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. If there is a description of the first and the second, it is only used for the purpose of distinguishing the technical features, and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0040] It should be noted that the terms such as setting, installing, and connecting in the embodiments of the present invention should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above terms in the embodiments of the present invention in combination with the specific content of the technical solution. For example, the term "connection" can be a mechanical connection, an electrical connection, or mutual communication; it can be directly connected or indirectly connected through an intermediate medium.

[0041] It should be noted that the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0042] The embodiments of the present invention provide a method for adjusting the voice wake-up threshold of a household appliance, an operation control device, a server, and a computer-readable storage medium, which can enable the adjusted wake-up threshold to more accurately distinguish between normal wake-up and false wake-up, which is beneficial to improving the wake-up accuracy of the household appliance. In addition, there is no need for the user to manually adjust the wake-up threshold, the adjustment timeliness is high, the response time is short, and the user's experience of using the household appliance can be effectively improved.

[0043] The embodiments of the present invention are further described below in conjunction with the accompanying drawings.

[0044] Reference Figure 1 The first aspect of the present invention provides a method for adjusting a voice wake-up threshold of a household appliance, including but not limited to steps S110 to S140:

[0045] Step S110: Obtain the wake-up audio data of all household appliances in a preset geographical area, the wake-up audio data including the original audio and the wake-up score. The original audio in the wake-up audio data refers to the audio data collected by the household appliance that successfully wakes up the household appliance, and the wake-up score in the wake-up audio data refers to the score corresponding to the original audio, which is obtained by the household appliance recognizing the original audio; in addition, in general, an initial wake-up threshold is set in the household appliance, and only audio data with a wake-up score higher than the initial wake-up threshold can successfully wake up the household appliance. It can be understood that after the household appliance collects a piece of original audio and the household appliance is successfully awakened, the original audio and the corresponding wake-up score will be stored in the household appliance as the wake-up audio data of the household appliance, so as to be adopted by the voice wake-up threshold adjustment method of this scheme.

[0046] It should be noted that there may be multiple rules for the division of preset geographical areas. For example, regional division may be performed according to accent differences. This is because accent differences may lead to large differences in the wake-up scores corresponding to the original audio. Therefore, regional division according to accent differences may improve the effectiveness of adjusting the wake-up threshold. Exemplarily, in some embodiments of the present invention, geographical division may be performed according to the areas where the classification of Chinese is popular. For example, Chinese is divided into standard Chinese and Chinese dialects, where standard Chinese is Mandarin, and Chinese dialects are generally divided into ten major dialects: Mandarin dialect, Jin dialect, Wu dialect, Min dialect, Hakka dialect, Cantonese dialect, Hunan dialect, Gan dialect, Hui dialect, and Pinghua dialect. Therefore, the areas where the above-mentioned Chinese classification is popular may be divided into a separate preset geographical area. It is understandable that geographical division may also be performed according to the classification of other languages, not just limited to the Chinese classification. In addition, division may also be performed according to the existing administrative geographical areas in my country. For example, in some embodiments of the present invention, the preset geographical areas include seven administrative geographical divisions: North China, Northeast China, East China, Central China, South China, Southwest China, and Northwest China. Among them: the North China region includes Beijing, Tianjin, Shanxi, Hebei, and Inner Mongolia Autonomous Region; the Northeast region includes Heilongjiang, Jilin, and Liaoning; the East China region includes Shanghai, Jiangsu, Zhejiang, Anhui, Fujian, Jiangxi, Shandong, and Taiwan; the Central China region includes Henan, Hubei, and Hunan; the South China region includes Guangdong, Guangxi, Hainan, the Hong Kong Special Administrative Region, and the Macao Special Administrative Region; the Southwest region includes Sichuan, Guizhou, Yunnan, Chongqing, and the Tibet Autonomous Region; the Northwest region includes Shaanxi, Gansu, Qinghai, Ningxia Hui Autonomous Region, and Xinjiang Uygur Autonomous Region. It is understandable that in order to further improve the accuracy, the preset geographical regions can be divided according to the administrative division principles of provinces, autonomous regions, and municipalities directly under the Central Government. By dividing the geographical regions according to the preset rules, the wake-up audio data of the home appliances in the preset geographical regions is obtained as reference data for adjusting the wake-up threshold, so that different geographical regions have different wake-up threshold adjustment values, that is, the impact of geographical differences is considered when adjusting the wake-up threshold.

[0047] Step S120: dividing the wake-up audio data into normal wake-up data and false wake-up data according to the original audio.

[0048] Since there are some false wake-up data in the wake-up audio data collected by the home appliance, and these false wake-up data cannot be accurately distinguished according to the wake-up scores in the wake-up audio data, it is necessary to re-identify according to the original audio in the wake-up audio data to divide the normal wake-up data and the false wake-up data. It can be understood that the recognition method of the original audio used in this step should be more accurate than the recognition method used by the home appliance for the original audio, such as using more dimensional features for recognition.

[0049] Step S130: calculating the average of the awakening scores of all normal awakening data, recorded as a first average score, and calculating the average of the awakening scores of all false awakening data, recorded as a second average score.

[0050] It can be understood that after dividing the wake-up audio data into normal wake-up data and false wake-up data, the average wake-up scores of the two types of data are respectively counted, so as to compare whether there is a significant difference in the scores of the two types of data on the home appliance device side, which can be used as a basis for adjustment.

[0051] Step S140: determining a wake-up threshold adjustment value according to the first average score and the second average score, and sending the wake-up threshold adjustment value to household appliances in a preset geographical area.

[0052] According to the voice wake-up threshold adjustment method for household appliances provided by an embodiment of the present invention, further judgment is made through the original audio in the acquired wake-up audio data, so as to divide normal wake-up data and false wake-up data, and the average values ​​of the wake-up scores of the normal wake-up data and the false wake-up data are respectively counted, and then the wake-up threshold adjustment value is determined based on the average value of the wake-up scores of the two data, and sent to the household appliances in a preset geographical area, so that the household appliances in the preset geographical area can adjust their own initial wake-up threshold according to the wake-up threshold adjustment value, and the adjusted wake-up threshold can more accurately distinguish between normal wake-up and false wake-up, which is beneficial to improving the wake-up accuracy of the household appliances, and there is no need for the user to manually adjust the wake-up threshold, the adjustment timeliness is high, the response time is short, and the user's experience of using the household appliances can be effectively improved.

[0053] In the voice wake-up threshold adjustment method provided in some embodiments of the present invention, determining the wake-up threshold adjustment value according to the first average score and the second average score in step S140 includes:

[0054] When the difference between the first average score and the second average score is greater than a first preset value, an average of the first average score and the second average score is used as the wake-up threshold adjustment value.

[0055] In this embodiment, when the difference between the first average score and the second average score is greater than the first preset value, that is, the average value of the wake-up scores of the normal wake-up data is significantly greater than the average value of the wake-up scores of the false wake-up data, the wake-up threshold adjustment value is increased to the middle value between the first average score and the second average score. This can effectively intercept false wake-ups without affecting the normal wake-up of the user, which is beneficial to improving the wake-up accuracy of home appliances.

[0056] In the voice wake-up threshold adjustment method provided in some embodiments of the present invention, determining the wake-up threshold adjustment value according to the first average score and the second average score in step S140 further includes:

[0057] When the difference between the first average score and the second average score is less than a first preset value, the second average score is used as the wake-up threshold adjustment value.

[0058] In this embodiment, when the difference between the first average score and the second average score is less than the first preset value, that is, the average value of the wake-up scores of the normal wake-up data is only slightly larger than the average value of the wake-up scores of the false wake-up data, the wake-up threshold adjustment value is increased to the second average score, that is, the threshold adjustment strategy is relatively mild, so as to avoid affecting normal wake-up while suppressing false wake-up.

[0059] Reference Figure 2 In the voice wake-up threshold adjustment method provided in some embodiments of the present invention, the step S120 of dividing the wake-up audio data into normal wake-up data and false wake-up data according to the original audio includes but is not limited to steps S210 to S220:

[0060] Step S210: Decomposing the original audio to obtain frequency features, duration features and intensity features;

[0061] Step S220: Match the frequency feature, duration feature and force feature with the standard wake-up audio, and determine the wake-up audio data as normal wake-up data or false wake-up data according to the matching result.

[0062] It is understandable that by first using feature decomposition to obtain the original audio frequency features, duration features, and intensity features, and then matching these features with the standard wake-up audio, that is, comparing the original audio with the standard wake-up audio from multiple dimensions, it is possible to effectively identify whether the wake-up audio data is normal wake-up data or false wake-up data. Furthermore, if the matching rate between the wake-up audio data and the standard wake-up audio is low, a false wake-up audio library can also be established, and the wake-up audio data can be feature matched with the false wake-up audio in the false wake-up audio library, thereby reducing the proportion of false wake-up data.

[0063] Reference Figure 3In the voice wake-up threshold adjustment method provided in some embodiments of the present invention, sending the wake-up threshold adjustment value to the home appliances in the preset geographical area in step S140 includes but is not limited to steps S310 to S320:

[0064] Step S310: obtaining a threshold adjustment flag parameter of a household appliance;

[0065] Step S320: When the threshold adjustment flag parameter indicates that the voice wake-up threshold of the home appliance can be adjusted, the wake-up threshold adjustment value is sent to the home appliance.

[0066] In the voice wake-up threshold adjustment method provided by some embodiments of the present invention, when the threshold adjustment flag parameter indicates that the voice wake-up threshold of the home appliance is not adjustable, the wake-up threshold adjustment value is not sent to the home appliance.

[0067] It can be understood that in this embodiment, before sending the wake-up threshold adjustment value, it interacts with the home appliance first to obtain the threshold adjustment flag parameters of the home appliance, know the user's settings for the home appliance, and avoid sending the wake-up threshold adjustment value to the home appliance that does not need to adjust the voice wake-up threshold.

[0068] In the voice wake-up threshold adjustment method provided in some embodiments of the present invention, the wake-up audio data is the wake-up audio data of the home appliance during the night time period; the wake-up threshold adjustment value is the wake-up threshold adjustment value of the home appliance during the night time period.

[0069] It is understandable that the nighttime period is the user's sleeping time. If the home appliance is mistakenly awakened during sleep, it will have an adverse effect on the user's normal rest. Therefore, the voice wake-up threshold adjustment method of this scheme is effective during the nighttime period and can effectively avoid this situation. Accordingly, the wake-up audio data collected by the home appliance should also be the wake-up audio data of the nighttime period, and the wake-up threshold adjustment value is only valid for the home appliance during the nighttime period.

[0070] In the voice wake-up threshold adjustment method provided in some embodiments of the present invention, the night time period is from 23:00 pm to 07:00 am the next day. It is understandable that the night time period can be adjusted by the user according to his or her own living habits.

[0071] In order to more clearly explain the operation control method of the air conditioner of the present invention, Figure 4 A comprehensive and detailed introduction to the voice wake-up threshold adjustment method provided in the embodiment of the present application is given.

[0072] Reference Figure 4 , the voice wake-up threshold adjustment method is applied to the server, comprising the following steps:

[0073] Step S1: Divide the geographical areas according to preset rules, for example, according to accent differences, to obtain multiple preset geographical areas; then jump to step S2;

[0074] Step S2: Acquire the wake-up audio data of all household appliances in a preset geographical area, for example, acquire the wake-up audio data of all household appliances in a preset night time period; then jump to step S3;

[0075] Step S3: judging the wake-up type according to the wake-up audio data one by one, so as to distinguish normal wake-up from false wake-up; if it is judged to be normal wake-up, jumping to step S41; if it is judged to be false wake-up, jumping to step S51;

[0076] Step S41: determine that the wake-up is normal; then jump to step S42;

[0077] Step S42: Calculate the average of the wake-up scores of all the wake-up audio data for normal wake-up, and record it as the first average score S1; then jump to step S6;

[0078] Step S51: determine that it is a false awakening; then jump to step S52;

[0079] Step S52: Calculate the average of the wake-up scores of all the wake-up audio data of false awakening, and record it as the second average score S2; then jump to step S6;

[0080] Step S6: Determine the wake-up threshold adjustment value according to the first average score S1 and the second average score S2. For example, when the first average score S1 is significantly greater than the second average score S2, the wake-up threshold adjustment value is increased to the average of the first average score S1 and the second average score S2, thereby effectively intercepting false wake-ups without affecting the normal wake-up of the user; when the first average score S1 is only slightly greater than the second average score S2, the wake-up threshold adjustment value is increased to the second average score S2, that is, the threshold adjustment strategy is relatively mild, thereby avoiding affecting the normal wake-up while suppressing the false wake-up.

[0081] The voice wake-up threshold adjustment method provided in the embodiment of the present invention uses cloud big data to accurately analyze the normal wake-up and false wake-up situations of users at night, divides regions according to accents, and accurately pushes them to users in each geographical area, thereby reducing the probability of false voice wake-up at night and the negative impact of false wake-up on users at night, while ensuring the effect of normal wake-up.

[0082] In addition, refer to Figure 5The second aspect of the present invention provides an operation control device 500, including a memory 510, a processor 520, and a computer program stored in the memory 510 and executable on the processor 520. The processor 520 executes the program to implement the voice wake-up threshold adjustment method of the first aspect of the present invention, for example, to execute Figure 1 Steps S110 to S140 of the method, Figure 2 Steps S210 to S220 of the method, Figure 3 Steps S310 to S320 in or Figure 4 The method flow in .

[0083] According to the operation control device 500 provided by the embodiment of the present invention, by dividing the geographical areas according to preset rules, the wake-up audio data of the household appliances in the preset geographical areas are obtained as reference data for adjusting the wake-up threshold, so that different geographical areas have different wake-up threshold adjustment values, that is, the influence of the geographical area differences is considered when adjusting the wake-up threshold; further judgment is made through the original audio in the obtained wake-up audio data, so as to divide the normal wake-up data and the false wake-up data, and the average wake-up scores of the normal wake-up data and the false wake-up data are respectively counted, and then the wake-up threshold adjustment value is determined based on the average wake-up scores of the two data, and sent to the household appliances in the preset geographical area, so that the household appliances in the preset geographical area can adjust their own wake-up thresholds according to the wake-up threshold adjustment value, and the adjusted wake-up threshold can more accurately distinguish between normal wake-up and false wake-up, which is conducive to improving the wake-up accuracy of the household appliances, and there is no need for the user to manually adjust the wake-up threshold, the adjustment timeliness is high, the response time is short, and the user's experience of using the household appliances can be effectively improved.

[0084] In addition, a third aspect of the present invention provides a server, including the operation control device 500 of the second aspect of the present invention.

[0085] According to the server provided by the embodiment of the present invention, by dividing the geographical areas according to preset rules, the wake-up audio data of the household appliances in the preset geographical areas are obtained as reference data for adjusting the wake-up threshold, so that different geographical areas have different wake-up threshold adjustment values, that is, the influence of the geographical area differences is considered when adjusting the wake-up threshold; further judgment is made through the original audio in the obtained wake-up audio data, so as to divide the normal wake-up data and the false wake-up data, and the average wake-up scores of the normal wake-up data and the false wake-up data are respectively counted, and then the wake-up threshold adjustment value is determined based on the average wake-up scores of the two data, and sent to the household appliances in the preset geographical area, so that the household appliances in the preset geographical area can adjust their own wake-up thresholds according to the wake-up threshold adjustment value, and the adjusted wake-up threshold can more accurately distinguish between normal wake-up and false wake-up, which is conducive to improving the wake-up accuracy of the household appliances, and there is no need for the user to manually adjust the wake-up threshold, the adjustment timeliness is high, the response time is short, and the user's use experience of the household appliances can be effectively improved.

[0086] In addition, a fourth aspect embodiment of the present invention provides a computer-readable storage medium, which stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the voice wake-up threshold adjustment method of the first aspect embodiment as above.

[0087] According to the computer-readable storage medium provided by the embodiment of the present invention, by dividing the geographical areas according to the preset rules, the wake-up audio data of the household appliances in the preset geographical areas are obtained as the reference data for adjusting the wake-up threshold, so that different geographical areas have different wake-up threshold adjustment values, that is, the influence of the geographical area differences is considered when adjusting the wake-up threshold; further judgment is made through the original audio in the obtained wake-up audio data, so as to divide the normal wake-up data and the false wake-up data, and the average wake-up scores of the normal wake-up data and the false wake-up data are respectively counted, and then the wake-up threshold adjustment value is determined based on the average wake-up scores of the two data, and sent to the household appliances in the preset geographical area, so that the household appliances in the preset geographical area can adjust their own wake-up thresholds according to the wake-up threshold adjustment value, and the adjusted wake-up threshold can more accurately distinguish between normal wake-up and false wake-up, which is conducive to improving the wake-up accuracy of the household appliances, and there is no need for the user to manually adjust the wake-up threshold, the adjustment timeliness is high, the response time is short, and the user's use experience of the household appliances can be effectively improved.

[0088] It will be appreciated by those skilled in the art that all or some of the steps and systems in the disclosed methods above may be implemented as software, firmware, hardware and appropriate combinations thereof. Some physical components or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium or a non-transitory medium and a communication medium or a temporary medium. As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information such as computer-readable instructions, data structures, program modules or other data. Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disk DVD or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that may be used to store desired information and may be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0089] The embodiments of the present invention are described in detail above with reference to the accompanying drawings. However, the present invention is not limited to the above embodiments. Various changes can be made within the knowledge scope of ordinary technicians in the technical field without departing from the purpose of the present invention.

Claims

1. A method for adjusting a voice wake-up threshold of a household appliance, characterized in that: include: Acquire wake-up audio data of all household appliances in a preset geographical area, wherein the wake-up audio data includes original audio and a wake-up score; dividing the wake-up audio data into normal wake-up data and false wake-up data according to the original audio; Calculating an average of the awakening scores of all the normal awakening data, recorded as a first average score, and calculating an average of the awakening scores of all the false awakening data, recorded as a second average score; A wake-up threshold adjustment value is determined according to the first average score and the second average score, and the wake-up threshold adjustment value is sent to household appliances in the preset geographical area.

2. The method for adjusting the voice wake-up threshold according to claim 1, characterized in that: The step of determining the wake-up threshold adjustment value according to the first average score and the second average score includes: When the difference between the first average score and the second average score is greater than a first preset value, an average of the first average score and the second average score is used as the wake-up threshold adjustment value.

3. The method for adjusting the voice wake-up threshold according to claim 2, characterized in that: The step of determining the wake-up threshold adjustment value according to the first average score and the second average score further includes: When the difference between the first average score and the second average score is less than the first preset value, the second average score is used as the wake-up threshold adjustment value.

4. The method for adjusting the voice wake-up threshold according to claim 1, characterized in that: The dividing the wake-up audio data into normal wake-up data and false wake-up data according to the original audio includes: Decomposing the original audio to obtain frequency features, duration features and intensity features; The frequency feature, the duration feature, and the mandatory feature are matched with the standard wake-up audio, and the wake-up audio data is determined as normal wake-up data or false wake-up data according to the matching result.

5. The method for adjusting the voice wake-up threshold according to claim 1, characterized in that: The step of sending the wake-up threshold adjustment value to household appliances within the preset geographical area includes: Obtaining a threshold adjustment flag parameter of the household appliance; When the threshold adjustment flag parameter indicates that the voice wake-up threshold of the home appliance can be adjusted, the wake-up threshold adjustment value is sent to the home appliance.

6. The method for adjusting the voice wake-up threshold according to claim 5, characterized in that: When the threshold adjustment flag parameter indicates that the voice wake-up threshold of the home appliance is not adjustable, the wake-up threshold adjustment value is not sent to the home appliance.

7. The method for adjusting the voice wake-up threshold according to claim 1, characterized in that: The wake-up audio data is the wake-up audio data of the household appliance during the night time period; and the wake-up threshold adjustment value is the wake-up threshold adjustment value of the household appliance during the night time period.

8. An operation control device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the voice wake-up threshold adjustment method according to any one of claims 1 to 7.

9. A server, characterized in that: Includes the operation control device as described in claim 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the voice wake-up threshold adjustment method according to any one of claims 1 to 7.

Images