CN113223525A - Voice control method and system for intelligent water dispenser under multiple instructions - Google Patents
Voice control method and system for intelligent water dispenser under multiple instructions Download PDFInfo
- Publication number
- CN113223525A CN113223525A CN202110491729.3A CN202110491729A CN113223525A CN 113223525 A CN113223525 A CN 113223525A CN 202110491729 A CN202110491729 A CN 202110491729A CN 113223525 A CN113223525 A CN 113223525A
- Authority
- CN
- China
- Prior art keywords
- preset
- target
- beverage
- evaluation
- brewing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 114
- 238000000034 method Methods 0.000 title claims abstract description 25
- 235000013361 beverage Nutrition 0.000 claims abstract description 148
- 238000012163 sequencing technique Methods 0.000 claims abstract description 20
- 238000010438 heat treatment Methods 0.000 claims abstract description 10
- 238000011156 evaluation Methods 0.000 claims description 196
- 238000005516 engineering process Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000002474 experimental method Methods 0.000 claims description 10
- 238000012217 deletion Methods 0.000 claims description 7
- 230000037430 deletion Effects 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 3
- 244000269722 Thea sinensis Species 0.000 description 73
- 235000013616 tea Nutrition 0.000 description 42
- 235000007516 Chrysanthemum Nutrition 0.000 description 22
- 244000189548 Chrysanthemum x morifolium Species 0.000 description 22
- 235000009569 green tea Nutrition 0.000 description 21
- 235000006468 Thea sinensis Nutrition 0.000 description 14
- 235000016213 coffee Nutrition 0.000 description 14
- 235000013353 coffee beverage Nutrition 0.000 description 14
- 230000009286 beneficial effect Effects 0.000 description 10
- 235000020279 black tea Nutrition 0.000 description 10
- 239000000843 powder Substances 0.000 description 10
- 235000017784 Mespilus germanica Nutrition 0.000 description 8
- 244000182216 Mimusops elengi Species 0.000 description 8
- 235000000560 Mimusops elengi Nutrition 0.000 description 8
- 235000007837 Vangueria infausta Nutrition 0.000 description 8
- 238000011835 investigation Methods 0.000 description 8
- 235000013336 milk Nutrition 0.000 description 6
- 239000008267 milk Substances 0.000 description 6
- 210000004080 milk Anatomy 0.000 description 6
- 240000006914 Aspalathus linearis Species 0.000 description 4
- 235000012984 Aspalathus linearis Nutrition 0.000 description 4
- 244000241838 Lycium barbarum Species 0.000 description 4
- 235000015459 Lycium barbarum Nutrition 0.000 description 4
- 235000015468 Lycium chinense Nutrition 0.000 description 4
- 230000035622 drinking Effects 0.000 description 4
- 235000020333 oolong tea Nutrition 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 235000019224 Camellia sinensis var Qingmao Nutrition 0.000 description 2
- 244000060011 Cocos nucifera Species 0.000 description 2
- 235000013162 Cocos nucifera Nutrition 0.000 description 2
- 241001284615 Frangula californica Species 0.000 description 2
- 235000010254 Jasminum officinale Nutrition 0.000 description 2
- 240000005385 Jasminum sambac Species 0.000 description 2
- 235000004433 Simmondsia californica Nutrition 0.000 description 2
- 235000009470 Theobroma cacao Nutrition 0.000 description 2
- 244000299461 Theobroma cacao Species 0.000 description 2
- 244000273928 Zingiber officinale Species 0.000 description 2
- 235000006886 Zingiber officinale Nutrition 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 235000015203 fruit juice Nutrition 0.000 description 2
- 235000008397 ginger Nutrition 0.000 description 2
- 235000008216 herbs Nutrition 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 235000020339 pu-erh tea Nutrition 0.000 description 2
- 235000020334 white tea Nutrition 0.000 description 2
- 235000020338 yellow tea Nutrition 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47J—KITCHEN EQUIPMENT; COFFEE MILLS; SPICE MILLS; APPARATUS FOR MAKING BEVERAGES
- A47J31/00—Apparatus for making beverages
- A47J31/44—Parts or details or accessories of beverage-making apparatus
- A47J31/52—Alarm-clock-controlled mechanisms for coffee- or tea-making apparatus ; Timers for coffee- or tea-making apparatus; Electronic control devices for coffee- or tea-making apparatus
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Food Science & Technology (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Apparatus For Making Beverages (AREA)
Abstract
The invention provides a voice control method and a voice control system for an intelligent water dispenser under multiple instructions, wherein the method comprises the following steps: acquiring a plurality of voice instructions input by a user, analyzing the voice instructions, and determining a plurality of beverage types which the user wants to brew; determining the brewing temperature corresponding to each beverage type from a preset brewing temperature database, and sequencing the brewing temperatures from low to high; and controlling the water dispenser to sequentially heat the water temperature to each brewing temperature after sequencing according to a preset sequence, reminding a user of brewing the corresponding beverage class by voice when each water temperature is heated to one brewing temperature, identifying whether the user finishes brewing, and if so, controlling the water dispenser to continue heating to the next brewing temperature. The voice control method and the voice control system for the intelligent water dispenser under the multi-command condition greatly improve the user experience and expand the application range.
Description
Technical Field
The invention relates to the technical field of voice control, in particular to a voice control method and system of an intelligent water dispenser under multiple instructions.
Background
At present, when a user uses a voice-controlled water dispenser, only one instruction (for example, please prepare for making coffee) can be sent to the water dispenser at a time, and when the user sends a plurality of instructions at one time (for example, i want to drink coffee) and then prepare for making green tea for my father, the system can automatically report an error, the user experience is poor, and meanwhile, the application range of the voice-controlled water dispenser is small.
Disclosure of Invention
One of the purposes of the invention is to provide a voice control method and system for an intelligent water dispenser under multiple instructions, which can receive multiple voice instructions sent by a user at the same time, determine multiple beverage types which the user wants to brew according to the voice instructions, and control the water dispenser to be sequentially heated to the brewing water temperature corresponding to each beverage type so as to prepare water with proper temperature for the user.
The embodiment of the invention provides a voice control method of an intelligent water dispenser under multiple instructions, which comprises the following steps:
acquiring a plurality of voice instructions input by a user, analyzing the voice instructions, and determining a plurality of beverage types which the user wants to brew;
determining the brewing temperature corresponding to each beverage type from a preset brewing temperature database, and sequencing the brewing temperatures from low to high;
and controlling the water dispenser to sequentially heat the water temperature to each brewing temperature after sequencing according to a preset sequence, reminding a user of brewing the corresponding beverage class by voice when each water temperature is heated to one brewing temperature, identifying whether the user finishes brewing, and if so, controlling the water dispenser to continue heating to the next brewing temperature.
Preferably, parsing each voice command to determine a plurality of beverage types that the user wants to brew includes:
recognizing each voice command based on a voice recognition technology to obtain a plurality of voice recognition texts;
integrating the voice recognition texts to obtain a target text;
determining a plurality of beverage keywords contained in the target text based on a preset beverage keyword database;
when at least two identical beverage keywords appear in the target text, selecting the beverage keyword appearing at last in the identical beverage keywords as a target keyword;
extracting a first text between the target keyword and the last beverage keyword and/or a second text between the target keyword and the next beverage keyword from the target text;
identifying the first text based on a semantic identification technology to obtain a first semantic feature;
recognizing the second text based on a semantic recognition technology to obtain a second semantic feature;
acquiring a preset negative feature database, matching the first semantic features and the second semantic features with negative features in the negative feature database, and if the first semantic features and/or the second semantic features match with the negative features in the negative feature database, removing target keywords and beverage keywords same as the target keywords;
after the beverage is removed, a preset beverage type comparison table is inquired, the beverage types corresponding to the rest beverage keywords are determined, and a plurality of beverage types which are brewed by the user are obtained.
Preferably, the voice control method of the intelligent water dispenser under the multi-command further comprises the following steps:
updating the brewing temperature database at preset time intervals;
wherein, update bubble temperature database, include:
acquiring first big data through a preset first acquisition path, wherein the first big data comprises: the missing items are beverage types of which the brewing temperature cannot be determined from the corresponding brewing temperature database when different users input voice instructions within a preset time period;
determining the occurrence frequency of each missing item in the first big data, and sequencing the missing items from big to small based on the corresponding frequency;
sequentially selecting one sequenced missing item as a target missing item according to a preset sequence;
acquiring second big data associated with the target missing item through a preset second acquisition path, wherein the second big data comprises: different suitable temperatures corresponding to the target missing item, wherein each suitable temperature corresponds to first evaluation data given by a large number of experiments by background experimenters;
acquiring third big data associated with the target missing item through a preset third acquisition path, wherein the third big data comprises: each suitable temperature corresponds to second evaluation data given by a large number of users from internet survey data;
analyzing the first evaluation data to obtain a plurality of first evaluation values and first credible values corresponding to the first evaluation values one by one;
analyzing the second evaluation data to obtain a plurality of second evaluation values and second credible values corresponding to the second evaluation values one by one; (ii) a
Calculating an evaluation index of each suitable temperature based on the first evaluation value, the second evaluation value, the first confidence value and the second confidence value, wherein the calculation formula is as follows:
wherein σtEvaluation index of the t-th optimum temperature corresponding to the target deletion term, αt,iAn ith first evaluation value mu obtained by analyzing the first evaluation data of the tth proper temperature corresponding to the target missing itemt,iA first credibility value m corresponding to the ith first evaluation value obtained by analyzing the first evaluation data of the tth proper temperature corresponding to the target missing itemt,1The total number of first evaluation values, beta, obtained by analyzing the first evaluation data of the tth suitable temperature corresponding to the target missing itemt,iAn ith second evaluation value gamma obtained by analyzing the second evaluation data of the tth proper temperature corresponding to the target missing itemt,iA second credible value, m, corresponding to the ith second evaluation value obtained by analyzing second evaluation data of the tth proper temperature corresponding to the target missing itemt,2The total number of second evaluation values, alpha, obtained by analyzing the second evaluation data of the tth suitable temperature corresponding to the target missing item0Is a preset first evaluation value threshold value, beta0Is a preset second evaluation value threshold, mu0Is a preset first confidence threshold value, gamma0Is a preset second confidence value threshold value, e is a natural constant, Z1And Z2Is a preset weight value, Z1>Z2;
And selecting the appropriate temperature corresponding to the maximum evaluation index value to combine with the target missing item, filling the combination into a brewing temperature database, and completing updating after all the target missing items are completed.
Preferably, the voice control method of the intelligent water dispenser under the multi-command further comprises the following steps:
acquiring a preset local use record, and adjusting the time interval based on the local use record;
wherein adjusting the time interval based on the local usage record comprises:
acquiring a preset identification model, inputting a local use record into the identification model, and acquiring a plurality of first use time intervals;
acquiring a plurality of preset second use time intervals;
determining the current time, and determining a target time which is a preset time after the current time;
adjusting the time interval based on the first using time interval, the second using time interval and the target time, wherein the adjusting formula is as follows:
t′=t+t0(ε1ρ1+ε2ρ2)
wherein t' is the time interval after adjustment, t is the time interval before adjustment, t0Adjusting amplitude values for preset times1And ε2Is a preset weight value, epsilon1>ε2,ρ1For a preset first adjusting coefficient, when the target time is within any first using time interval, rho1< 0, otherwise, ρ1>0,ρ2For a preset second adjusting coefficient, when the target time is within any second use time interval, rho2< 0, otherwise, ρ2>0。
Preferably, the step of identifying whether the user has finished brewing comprises:
and if a brewing completion instruction input by the user is received, determining that the brewing of the user is completed.
The embodiment of the invention provides a voice control system of an intelligent water dispenser under multiple instructions, which comprises:
the acquisition and analysis module is used for acquiring a plurality of voice instructions input by a user, analyzing each voice instruction and determining a plurality of beverage types which the user wants to brew;
the determining and sequencing module is used for determining the brewing temperature corresponding to each beverage type from a preset brewing temperature database and sequencing the brewing temperatures from low to high;
the control module is used for controlling the water dispenser to sequentially heat the water temperature to each brewing temperature after sequencing according to a preset sequence, when the water temperature is heated to one brewing temperature, the user is reminded of brewing the corresponding beverage type through voice, whether the user finishes brewing is identified, and if yes, the water dispenser is controlled to continue heating to the next brewing temperature.
Preferably, the determining and parsing module performs the following operations:
recognizing each voice command based on a voice recognition technology to obtain a plurality of voice recognition texts;
integrating the voice recognition texts to obtain a target text;
determining a plurality of beverage keywords contained in the target text based on a preset beverage keyword database;
when at least two identical beverage keywords appear in the target text, selecting the beverage keyword appearing at last in the identical beverage keywords as a target keyword;
extracting a first text between the target keyword and the last beverage keyword and/or a second text between the target keyword and the next beverage keyword from the target text;
identifying the first text based on a semantic identification technology to obtain a first semantic feature;
recognizing the second text based on a semantic recognition technology to obtain a second semantic feature;
acquiring a preset negative feature database, matching the first semantic features and the second semantic features with negative features in the negative feature database, and if the first semantic features and/or the second semantic features match with the negative features in the negative feature database, removing target keywords and beverage keywords same as the target keywords;
after the beverage is removed, a preset beverage type comparison table is inquired, the beverage types corresponding to the rest beverage keywords are determined, and a plurality of beverage types which are brewed by the user are obtained.
Preferably, the voice control system of the intelligent water dispenser under the multi-command further comprises:
the updating module is used for updating the brewing temperature database at preset time intervals;
the update module performs the following operations:
acquiring first big data through a preset first acquisition path, wherein the first big data comprises: the missing items are beverage types of which the brewing temperature cannot be determined from the corresponding brewing temperature database when different users input voice instructions within a preset time period;
determining the occurrence frequency of each missing item in the first big data, and sequencing the missing items from big to small based on the corresponding frequency;
sequentially selecting one sequenced missing item as a target missing item according to a preset sequence;
acquiring second big data associated with the target missing item through a preset second acquisition path, wherein the second big data comprises: different suitable temperatures corresponding to the target missing item, wherein each suitable temperature corresponds to first evaluation data given by a large number of experiments by background experimenters;
acquiring third big data associated with the target missing item through a preset third acquisition path, wherein the third big data comprises: each suitable temperature corresponds to second evaluation data given by a large number of users from internet survey data;
analyzing the first evaluation data to obtain a plurality of first evaluation values and first credible values corresponding to the first evaluation values one by one;
analyzing the second evaluation data to obtain a plurality of second evaluation values and second credible values corresponding to the second evaluation values one by one; (ii) a
Calculating an evaluation index of each suitable temperature based on the first evaluation value, the second evaluation value, the first confidence value and the second confidence value, wherein the calculation formula is as follows:
wherein σtEvaluation index of the t-th optimum temperature corresponding to the target deletion term, αt,iAn ith first evaluation value mu obtained by analyzing the first evaluation data of the tth proper temperature corresponding to the target missing itemt,iA first credibility value m corresponding to the ith first evaluation value obtained by analyzing the first evaluation data of the tth proper temperature corresponding to the target missing itemt,1The total number of first evaluation values, beta, obtained by analyzing the first evaluation data of the tth suitable temperature corresponding to the target missing itemt,iAn ith second evaluation value gamma obtained by analyzing the second evaluation data of the tth proper temperature corresponding to the target missing itemt,iA second credible value, m, corresponding to the ith second evaluation value obtained by analyzing second evaluation data of the tth proper temperature corresponding to the target missing itemt,2The total number of second evaluation values, alpha, obtained by analyzing the second evaluation data of the tth suitable temperature corresponding to the target missing item0Is a preset first evaluation value threshold value, beta0Is a preset second evaluation value threshold, mu0Is a preset first confidence threshold value, gamma0Is a preset second confidence value threshold value, e is a natural constant, Z1And Z2Is a preset weight value, Z1>Z2;
And selecting the appropriate temperature corresponding to the maximum evaluation index value to combine with the target missing item, filling the combination into a brewing temperature database, and completing updating after all the target missing items are completed.
Preferably, the voice control system of the intelligent water dispenser under the multi-command further comprises:
the adjusting module is used for acquiring a preset local use record and adjusting the time interval based on the local use record;
the adjustment module performs the following operations:
acquiring a preset identification model, inputting a local use record into the identification model, and acquiring a plurality of first use time intervals;
acquiring a plurality of preset second use time intervals;
determining the current time, and determining a target time which is a preset time after the current time;
adjusting the time interval based on the first using time interval, the second using time interval and the target time, wherein the adjusting formula is as follows:
t′=t+t0(ε1ρ1+ε2ρ2)
wherein t' is the time interval after adjustment, t is the time interval before adjustment, t0Adjusting amplitude values for preset times1And ε2Is a preset weight value, epsilon1>ε2,ρ1For a preset first adjusting coefficient, when the target time is within any first using time interval, rho1< 0, otherwise, ρ1>0,ρ2For a preset second adjusting coefficient, when the target time is within any second use time interval, rho2< 0, otherwise, ρ2>0。
Preferably, the control module performs the following operations:
and if a brewing completion instruction input by the user is received, determining that the brewing of the user is completed.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart of a voice control method of an intelligent water dispenser under multiple instructions in an embodiment of the invention;
fig. 2 is a schematic diagram of a voice control system of an intelligent water dispenser under multiple instructions in an embodiment of the invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
The embodiment of the invention provides a voice control method of an intelligent water dispenser under multiple instructions, as shown in figure 1, comprising the following steps:
s1, acquiring a plurality of voice instructions input by a user, analyzing the voice instructions, and determining a plurality of beverage types which the user wants to brew;
s2, determining the brewing temperature corresponding to each beverage type from a preset brewing temperature database, and sequencing the brewing temperatures from low to high;
s3, controlling the water dispenser to heat the water temperature to each brewing temperature after sequencing in sequence according to a preset sequence, reminding a user of brewing the corresponding beverage by voice when each water temperature is heated to one brewing temperature, identifying whether the user finishes brewing, and if so, controlling the water dispenser to continue heating to the next brewing temperature.
The working principle and the beneficial effects of the technical scheme are as follows:
the preset brewing temperature database specifically comprises: the database stores the appropriate brewing temperature corresponding to a large number of beverage types; the preset sequence specifically comprises: preferentially selecting items ranked in the front; acquiring a plurality of voice instructions input by a user (for example, "I wait for making coffee" and "I mom wait for making wolfberry tea", and the like), analyzing the voice instructions, and determining a plurality of beverage types (for example: coffee and wolfberry tea) which the user wants to make; determining the brewing temperature corresponding to each beverage type from a brewing temperature database (for example: the brewing temperature of coffee is 92 ℃, the brewing temperature of medlar tea is 60 ℃), and sequencing the brewing temperatures from low to high (for example: 60 ℃, 92 ℃); the water dispenser is controlled to correspondingly heat and a user is correspondingly controlled (for example, the water temperature is firstly heated to 60 ℃, the voice prompt is 'little main | the water for making coffee is ready to be cheer.', after the user finishes making coffee, the water temperature is heated to 92 ℃, and the voice prompt is 'the water for making medlar is ready to be cheer.').
The embodiment of the invention can receive a plurality of voice instructions sent by a user at the same time, determine a plurality of beverage types which the user wants to brew according to the voice instructions, and control the water dispenser to be sequentially heated to the brewing water temperature corresponding to each beverage type, so that water with proper temperature is prepared for the user, the user experience is greatly improved, and the application range is expanded.
The embodiment of the invention provides a voice control method of an intelligent water dispenser under multiple instructions, which is used for analyzing each voice instruction and determining a plurality of beverage types which a user wants to brew, and comprises the following steps:
recognizing each voice command based on a voice recognition technology to obtain a plurality of voice recognition texts;
integrating the voice recognition texts to obtain a target text;
determining a plurality of beverage keywords contained in the target text based on a preset beverage keyword database;
when at least two identical beverage keywords appear in the target text, selecting the beverage keyword appearing at last in the identical beverage keywords as a target keyword;
extracting a first text between the target keyword and the last beverage keyword and/or a second text between the target keyword and the next beverage keyword from the target text;
identifying the first text based on a semantic identification technology to obtain a first semantic feature;
recognizing the second text based on a semantic recognition technology to obtain a second semantic feature;
acquiring a preset negative feature database, matching the first semantic features and the second semantic features with negative features in the negative feature database, and if the first semantic features and/or the second semantic features match with the negative features in the negative feature database, removing target keywords and beverage keywords same as the target keywords;
after the beverage is removed, a preset beverage type comparison table is inquired, the beverage types corresponding to the rest beverage keywords are determined, and a plurality of beverage types which are brewed by the user are obtained.
The working principle and the beneficial effects of the technical scheme are as follows:
the preset beverage keyword database specifically comprises the following steps: a plurality of beverage keywords are stored in the database, for example: black tea, green tea, chrysanthemum tea, coffee, milk powder, and the like; the preset negative characteristic database specifically comprises: the database stores a plurality of negative semantic features, such as: not, calculated, replaced, etc.; the preset beverage type comparison table specifically comprises: a plurality of beverage keywords and a beverage type corresponding one-to-one to each beverage keyword, for example: the keyword 'black tea' corresponds to black tea; recognizing each voice command to obtain a plurality of voice texts (for example, the Chinese characters show that the Chinese character ' you are about to make green tea in five minutes, do not need green tea, and still drink a red tea bar '. and the Chinese character ' mu says that chrysanthemum tea is needed to make chrysanthemum tea and then changes the chrysanthemum tea bar into a Chinese character ' mu ' tea bar ', and the chrysanthemum tea is not needed '); integrating the voice recognition texts to obtain a target text (for example, the Chinese character ' you will be green tea after five minutes, you do not need green tea, I still drink a red tea bar '; I mom says to make chrysanthemum tea, and changes her into a medlar tea bar, and chrysanthemum tea does not need) '); determining a plurality of beverage keywords (such as 'green tea', 'black tea', 'chrysanthemum tea', 'medlar tea' and 'chrysanthemum tea') contained in the target text based on a beverage keyword database; the method comprises the steps of (1) extracting a first text (', no calculation and no requirement) and a second text (', i are still drinking) from the appearance of green tea and chrysanthemum tea twice, and obtaining a first semantic feature (no calculation and no requirement) and a second semantic feature (i are still drinking) based on a semantic recognition technology; the first semantic features and the second semantic features are matched with negative features in the negative feature database, and the user needs to replace green tea and remove the green tea; the principle of removing the chrysanthemum tea is the same as the principle.
According to the embodiment of the invention, the beverage types which are not needed in the voice command of the user are intelligently identified and eliminated, the user does not need to reorganize the voice to send the command again, the convenience is improved, and meanwhile, the user experience is also improved.
The embodiment of the invention provides a voice control method of an intelligent water dispenser under multiple instructions, which further comprises the following steps:
updating the brewing temperature database at preset time intervals;
wherein, update bubble temperature database, include:
acquiring first big data through a preset first acquisition path, wherein the first big data comprises: the missing items are beverage types of which the brewing temperature cannot be determined from the corresponding brewing temperature database when different users input voice instructions within a preset time period;
determining the occurrence frequency of each missing item in the first big data, and sequencing the missing items from big to small based on the corresponding frequency;
sequentially selecting one sequenced missing item as a target missing item according to a preset sequence;
acquiring second big data associated with the target missing item through a preset second acquisition path, wherein the second big data comprises: different suitable temperatures corresponding to the target missing item, wherein each suitable temperature corresponds to first evaluation data given by a large number of experiments by background experimenters;
acquiring third big data associated with the target missing item through a preset third acquisition path, wherein the third big data comprises: each suitable temperature corresponds to second evaluation data given by a large number of users from internet survey data;
analyzing the first evaluation data to obtain a plurality of first evaluation values and first credible values corresponding to the first evaluation values one by one;
analyzing the second evaluation data to obtain a plurality of second evaluation values and second credible values corresponding to the second evaluation values one by one; (ii) a
Calculating an evaluation index of each suitable temperature based on the first evaluation value, the second evaluation value, the first confidence value and the second confidence value, wherein the calculation formula is as follows:
wherein σtEvaluation index of the t-th optimum temperature corresponding to the target deletion term, αt,iAn ith first evaluation value mu obtained by analyzing the first evaluation data of the tth proper temperature corresponding to the target missing itemt,iA first credibility value m corresponding to the ith first evaluation value obtained by analyzing the first evaluation data of the tth proper temperature corresponding to the target missing itemt,1The total number of first evaluation values, beta, obtained by analyzing the first evaluation data of the tth suitable temperature corresponding to the target missing itemt,iAn ith second evaluation value gamma obtained by analyzing the second evaluation data of the tth proper temperature corresponding to the target missing itemt,iA second credible value, m, corresponding to the ith second evaluation value obtained by analyzing second evaluation data of the tth proper temperature corresponding to the target missing itemt,2The total number of second evaluation values, alpha, obtained by analyzing the second evaluation data of the tth suitable temperature corresponding to the target missing item0Is a preset first evaluation value threshold value, beta0Is a preset second evaluation value threshold, mu0Is a preset first confidence threshold value, gamma0Is a preset second confidence value threshold value, e is a natural constant, Z1And Z2Is a preset weight value, Z1>Z2;
And selecting the appropriate temperature corresponding to the maximum evaluation index value to combine with the target missing item, filling the combination into a brewing temperature database, and completing updating after all the target missing items are completed.
The working principle and the beneficial effects of the technical scheme are as follows:
the preset time period specifically comprises the following steps: the time from each update to the next update; the preset first obtaining path specifically includes: the device is connected with a database which stores records that the corresponding brewing water temperature cannot be determined from the brewing water temperature database after the beverage type is determined when a large number of users use the water dispenser; the preset second obtaining path specifically includes: the system is connected with a database for storing experimental data obtained by experiment carried out by laboratory staff (different beverage types are brewed at different temperatures to give corresponding evaluation); the preset third obtaining path specifically includes: the system is connected with a database which stores the data of the evaluation results directly given by users (such as tea experts or amateurs) participating in the investigation in the Internet investigation data or the experimental data obtained by performing experiments (different beverage types are brewed at different temperatures to give corresponding evaluations); when an experimenter and a user participating in investigation give evaluation data, the experimenter can give an evaluation value, the evaluation value is larger, the evaluation on the temperature is higher, meanwhile, the system can give a credible value according to data such as authenticity (whether real-name authentication is carried out or not, whether personal data is finished or not and the like) of the experimenter and the user participating in investigation, and the credible value is larger, and the corresponding evaluation data is more credible; calculating an evaluation index of each suitable temperature based on the first evaluation value, the second evaluation value, the first credible value and the second credible value, wherein the larger the evaluation index is, the more suitable the corresponding suitable temperature is for the target missing item; the preset first evaluation value threshold is specifically: for example, 50; the preset second evaluation value threshold is specifically: for example, 51; the preset first trust value threshold specifically includes: for example, 60; the preset second trust value threshold specifically includes: such as 63.
Because the beverage types (such as green tea, jasmine tea, white tea, oolong tea, black tea, Pu' er tea, yellow tea, oolong tea, milk powder, coffee, milk tea, cocoa powder, fruit juice, coconut powder, matcha powder, ginger tea, medicinal herbs capable of being brewed respectively and the like) are rich and diverse, and the brewing water temperature database needs updating at variable time, the embodiment of the invention can update the brewing water temperature database in time, determine missing items based on first big data, update the beverage types of which the brewing temperature cannot be determined by speaking instructions of other users to the local, greatly avoid the situation that the brewing temperature cannot be determined again, improve the user experience, simultaneously, calculate the evaluation index of each suitable temperature based on the first evaluation value, the second evaluation value, the first credible value and the second credible value through the formula, quickly and comprehensively judge the optimum temperature corresponding to each missing item, the working efficiency of the system is improved.
The embodiment of the invention provides a voice control method of an intelligent water dispenser under multiple instructions, which further comprises the following steps:
acquiring a preset local use record, and adjusting the time interval based on the local use record;
wherein adjusting the time interval based on the local usage record comprises:
acquiring a preset identification model, inputting a local use record into the identification model, and acquiring a plurality of first use time intervals;
acquiring a plurality of preset second use time intervals;
determining the current time, and determining a target time which is a preset time after the current time;
adjusting the time interval based on the first using time interval, the second using time interval and the target time, wherein the adjusting formula is as follows:
t′=t+t0(ε1ρ1+ε2ρ2)
wherein t' is the time interval after adjustment, t is the time interval before adjustment, t0Adjusting amplitude values for preset times1And ε2Is a preset weight value, epsilon1>ε2,ρ1For a preset first adjusting coefficient, when the target time is within any first using time interval, rho1< 0, otherwise, ρ1>0,ρ2For a preset second adjusting coefficient, when the target time is within any second use time interval, rho2< 0, otherwise, ρ2>0。
The working principle and the beneficial effects of the technical scheme are as follows:
the preset time is specifically as follows: for example, 10 minutes; the preset local use record is specifically as follows: time records of the user using the water dispenser historically; the preset identification model specifically comprises the following steps: the model is generated by learning based on a large number of historical usage records and corresponding manual extraction time interval records by using a machine learning algorithm, and can identify a plurality of time periods (namely a plurality of first usage time intervals) for regularly using the water dispenser by a user in the local usage records (for example, if the water dispensers are used by the user at about 7:00 am, the first usage time intervals are [ 6: 45,7:15 ]); the preset second use time intervals are specifically as follows: the plurality of time intervals set by the background staff are time intervals in which normal users can use the water dispenser (for example, most users can use the water dispenser about 7:00 in the morning, and the second use time interval is [ 6: 30,7:30 ]); if the current time is 7:00, the probability that the user uses the water dispenser is high, the time interval for updating the database is greatly reduced, and the database is fully updated, so that the situation that the brewing temperature cannot be determined when the user uses the water dispenser is avoided; if the current time is 1:00 in the morning, the current time is not in any first use time interval or any second use time interval, the updating time interval is greatly increased, and the power consumption is reduced; the preset time adjustment amplitude value is specifically as follows: for example 100 seconds.
The embodiment of the invention can intelligently adjust the updating time interval of the brewing water temperature database, the updating time interval can be increased when the possibility of non-use of a user is higher so as to save power consumption, the updating time interval can be reduced when the possibility of non-use of the user is lower so as to avoid the situation that the brewing temperature cannot be determined.
The embodiment of the invention provides a voice control method of an intelligent water dispenser under multiple instructions, which is used for identifying whether a user finishes brewing and comprises the following steps:
and if a brewing completion instruction input by the user is received, determining that the brewing of the user is completed.
The working principle and the beneficial effects of the technical scheme are as follows:
when the user receives the prompt and controls the water dispenser to discharge water for brewing, the user can press the 'continue heating' button to input a brewing completion instruction and can orally speak the 'continue heating' instruction.
The embodiment of the invention provides a voice control system of an intelligent water dispenser under multiple instructions, as shown in figure 2, comprising:
the acquisition and analysis module 1 is used for acquiring a plurality of voice instructions input by a user, analyzing each voice instruction and determining a plurality of beverage types which the user wants to brew;
the determining and sequencing module 2 is used for determining the brewing temperature corresponding to each beverage type from a preset brewing temperature database and sequencing the brewing temperatures from low to high;
and the control module 3 is used for controlling the water dispenser to sequentially heat the water temperature to each sequenced brewing temperature according to a preset sequence, reminding a user of brewing the corresponding beverage class by voice when the water temperature is heated to one brewing temperature, identifying whether the user finishes brewing or not, and if so, controlling the water dispenser to continue heating to the next brewing temperature.
The working principle and the beneficial effects of the technical scheme are as follows:
the preset brewing temperature database specifically comprises: the database stores the appropriate brewing temperature corresponding to a large number of beverage types; the preset sequence specifically comprises: preferentially selecting items ranked in the front; acquiring a plurality of voice instructions input by a user (for example, "I wait for making coffee" and "I mom wait for making wolfberry tea", and the like), analyzing the voice instructions, and determining a plurality of beverage types (for example: coffee and wolfberry tea) which the user wants to make; determining the brewing temperature corresponding to each beverage type from a brewing temperature database (for example: the brewing temperature of coffee is 92 ℃, the brewing temperature of medlar tea is 60 ℃), and sequencing the brewing temperatures from low to high (for example: 60 ℃, 92 ℃); the water dispenser is controlled to correspondingly heat and a user is correspondingly controlled (for example, the water temperature is firstly heated to 60 ℃, the voice prompt is 'little main | the water for making coffee is ready to be cheer.', after the user finishes making coffee, the water temperature is heated to 92 ℃, and the voice prompt is 'the water for making medlar is ready to be cheer.').
The embodiment of the invention can receive a plurality of voice instructions sent by a user at the same time, determine a plurality of beverage types which the user wants to brew according to the voice instructions, and control the water dispenser to be sequentially heated to the brewing water temperature corresponding to each beverage type, so that water with proper temperature is prepared for the user, the user experience is greatly improved, and the application range is expanded.
The embodiment of the invention provides a voice control system of an intelligent water dispenser under multiple instructions, wherein a determining and analyzing module executes the following operations:
recognizing each voice command based on a voice recognition technology to obtain a plurality of voice recognition texts;
integrating the voice recognition texts to obtain a target text;
determining a plurality of beverage keywords contained in the target text based on a preset beverage keyword database;
when at least two identical beverage keywords appear in the target text, selecting the beverage keyword appearing at last in the identical beverage keywords as a target keyword;
extracting a first text between the target keyword and the last beverage keyword and/or a second text between the target keyword and the next beverage keyword from the target text;
identifying the first text based on a semantic identification technology to obtain a first semantic feature;
recognizing the second text based on a semantic recognition technology to obtain a second semantic feature;
acquiring a preset negative feature database, matching the first semantic features and the second semantic features with negative features in the negative feature database, and if the first semantic features and/or the second semantic features match with the negative features in the negative feature database, removing target keywords and beverage keywords same as the target keywords;
after the beverage is removed, a preset beverage type comparison table is inquired, the beverage types corresponding to the rest beverage keywords are determined, and a plurality of beverage types which are brewed by the user are obtained.
The working principle and the beneficial effects of the technical scheme are as follows:
the preset beverage keyword database specifically comprises the following steps: a plurality of beverage keywords are stored in the database, for example: black tea, green tea, chrysanthemum tea, coffee, milk powder, and the like; the preset negative characteristic database specifically comprises: the database stores a plurality of negative semantic features, such as: not, calculated, replaced, etc.; the preset beverage type comparison table specifically comprises: a plurality of beverage keywords and a beverage type corresponding one-to-one to each beverage keyword, for example: the keyword 'black tea' corresponds to black tea; recognizing each voice command to obtain a plurality of voice texts (for example, the Chinese characters show that the Chinese character ' you are about to make green tea in five minutes, do not need green tea, and still drink a red tea bar '. and the Chinese character ' mu says that chrysanthemum tea is needed to make chrysanthemum tea and then changes the chrysanthemum tea bar into a Chinese character ' mu ' tea bar ', and the chrysanthemum tea is not needed '); integrating the voice recognition texts to obtain a target text (for example, the Chinese character ' you will be green tea after five minutes, you do not need green tea, I still drink a red tea bar '; I mom says to make chrysanthemum tea, and changes her into a medlar tea bar, and chrysanthemum tea does not need) '); determining a plurality of beverage keywords (such as 'green tea', 'black tea', 'chrysanthemum tea', 'medlar tea' and 'chrysanthemum tea') contained in the target text based on a beverage keyword database; the method comprises the steps of (1) extracting a first text (', no calculation and no requirement) and a second text (', i are still drinking) from the appearance of green tea and chrysanthemum tea twice, and obtaining a first semantic feature (no calculation and no requirement) and a second semantic feature (i are still drinking) based on a semantic recognition technology; the first semantic features and the second semantic features are matched with negative features in the negative feature database, and the user needs to replace green tea and remove the green tea; the principle of removing the chrysanthemum tea is the same as the principle.
According to the embodiment of the invention, the beverage types which are not needed in the voice command of the user are intelligently identified and eliminated, the user does not need to reorganize the voice to send the command again, the convenience is improved, and meanwhile, the user experience is also improved.
The embodiment of the invention provides a voice control system of an intelligent water dispenser under multiple instructions, which further comprises:
the updating module is used for updating the brewing temperature database at preset time intervals;
the update module performs the following operations:
acquiring first big data through a preset first acquisition path, wherein the first big data comprises: the missing items are beverage types of which the brewing temperature cannot be determined from the corresponding brewing temperature database when different users input voice instructions within a preset time period;
determining the occurrence frequency of each missing item in the first big data, and sequencing the missing items from big to small based on the corresponding frequency;
sequentially selecting one sequenced missing item as a target missing item according to a preset sequence;
acquiring second big data associated with the target missing item through a preset second acquisition path, wherein the second big data comprises: different suitable temperatures corresponding to the target missing item, wherein each suitable temperature corresponds to first evaluation data given by a large number of experiments by background experimenters;
acquiring third big data associated with the target missing item through a preset third acquisition path, wherein the third big data comprises: each suitable temperature corresponds to second evaluation data given by a large number of users from internet survey data;
analyzing the first evaluation data to obtain a plurality of first evaluation values and first credible values corresponding to the first evaluation values one by one;
analyzing the second evaluation data to obtain a plurality of second evaluation values and second credible values corresponding to the second evaluation values one by one; (ii) a
Calculating an evaluation index of each suitable temperature based on the first evaluation value, the second evaluation value, the first confidence value and the second confidence value, wherein the calculation formula is as follows:
wherein σtEvaluation index of the t-th optimum temperature corresponding to the target deletion term, αt,iAn ith first evaluation value mu obtained by analyzing the first evaluation data of the tth proper temperature corresponding to the target missing itemt,iA first credibility value m corresponding to the ith first evaluation value obtained by analyzing the first evaluation data of the tth proper temperature corresponding to the target missing itemt,1The total number of first evaluation values, beta, obtained by analyzing the first evaluation data of the tth suitable temperature corresponding to the target missing itemt,iSecond optimum temperature for t-th optimum temperature corresponding to target deletion termAn i-th second evaluation value, γ, obtained by analyzing the evaluation datat,iA second credible value, m, corresponding to the ith second evaluation value obtained by analyzing second evaluation data of the tth proper temperature corresponding to the target missing itemt,2The total number of second evaluation values, alpha, obtained by analyzing the second evaluation data of the tth suitable temperature corresponding to the target missing item0Is a preset first evaluation value threshold value, beta0Is a preset second evaluation value threshold, mu0Is a preset first confidence threshold value, gamma0Is a preset second confidence value threshold value, e is a natural constant, Z1And Z2Is a preset weight value, Z1>Z2;
And selecting the appropriate temperature corresponding to the maximum evaluation index value to combine with the target missing item, filling the combination into a brewing temperature database, and completing updating after all the target missing items are completed.
The working principle and the beneficial effects of the technical scheme are as follows:
the preset time period specifically comprises the following steps: the time from each update to the next update; the preset first obtaining path specifically includes: the device is connected with a database which stores records that the corresponding brewing water temperature cannot be determined from the brewing water temperature database after the beverage type is determined when a large number of users use the water dispenser; the preset second obtaining path specifically includes: the system is connected with a database for storing experimental data obtained by experiment carried out by laboratory staff (different beverage types are brewed at different temperatures to give corresponding evaluation); the preset third obtaining path specifically includes: the system is connected with a database which stores the data of the evaluation results directly given by users (such as tea experts or amateurs) participating in the investigation in the Internet investigation data or the experimental data obtained by performing experiments (different beverage types are brewed at different temperatures to give corresponding evaluations); when an experimenter and a user participating in investigation give evaluation data, the experimenter can give an evaluation value, the evaluation value is larger, the evaluation on the temperature is higher, meanwhile, the system can give a credible value according to data such as authenticity (whether real-name authentication is carried out or not, whether personal data is finished or not and the like) of the experimenter and the user participating in investigation, and the credible value is larger, and the corresponding evaluation data is more credible; calculating an evaluation index of each suitable temperature based on the first evaluation value, the second evaluation value, the first credible value and the second credible value, wherein the larger the evaluation index is, the more suitable the corresponding suitable temperature is for the target missing item; the preset first evaluation value threshold is specifically: for example, 50; the preset second evaluation value threshold is specifically: for example, 51; the preset first trust value threshold specifically includes: for example, 60; the preset second trust value threshold specifically includes: such as 63.
Because the beverage types (such as green tea, jasmine tea, white tea, oolong tea, black tea, Pu' er tea, yellow tea, oolong tea, milk powder, coffee, milk tea, cocoa powder, fruit juice, coconut powder, matcha powder, ginger tea, medicinal herbs capable of being brewed respectively and the like) are rich and diverse, and the brewing water temperature database needs updating at variable time, the embodiment of the invention can update the brewing water temperature database in time, determine missing items based on first big data, update the beverage types of which the brewing temperature cannot be determined by speaking instructions of other users to the local, greatly avoid the situation that the brewing temperature cannot be determined again, improve the user experience, simultaneously, calculate the evaluation index of each suitable temperature based on the first evaluation value, the second evaluation value, the first credible value and the second credible value through the formula, quickly and comprehensively judge the optimum temperature corresponding to each missing item, the working efficiency of the system is improved.
The embodiment of the invention provides a voice control system of an intelligent water dispenser under multiple instructions, which further comprises:
the adjusting module is used for acquiring a preset local use record and adjusting the time interval based on the local use record;
the adjustment module performs the following operations:
acquiring a preset identification model, inputting a local use record into the identification model, and acquiring a plurality of first use time intervals;
acquiring a plurality of preset second use time intervals;
determining the current time, and determining a target time which is a preset time after the current time;
adjusting the time interval based on the first using time interval, the second using time interval and the target time, wherein the adjusting formula is as follows:
t′=t+t0(ε1ρ1+ε2ρ2)
wherein t' is the time interval after adjustment, t is the time interval before adjustment, t0Adjusting amplitude values for preset times1And ε2Is a preset weight value, epsilon1>ε2,ρ1For a preset first adjusting coefficient, when the target time is within any first using time interval, rho1< 0, otherwise, ρ1>0,ρ2For a preset second adjusting coefficient, when the target time is within any second use time interval, rho2< 0, otherwise, ρ2>0。
The working principle and the beneficial effects of the technical scheme are as follows:
the preset time is specifically as follows: for example, 10 minutes; the preset local use record is specifically as follows: time records of the user using the water dispenser historically; the preset identification model specifically comprises the following steps: the model is generated by learning based on a large number of historical usage records and corresponding manual extraction time interval records by using a machine learning algorithm, and can identify a plurality of time periods (namely a plurality of first usage time intervals) for regularly using the water dispenser by a user in the local usage records (for example, if the water dispensers are used by the user at about 7:00 am, the first usage time intervals are [ 6: 45,7:15 ]); the preset second use time intervals are specifically as follows: the plurality of time intervals set by the background staff are time intervals in which normal users can use the water dispenser (for example, most users can use the water dispenser about 7:00 in the morning, and the second use time interval is [ 6: 30,7:30 ]); if the current time is 7:00, the probability that the user uses the water dispenser is high, the time interval for updating the database is greatly reduced, and the database is fully updated, so that the situation that the brewing temperature cannot be determined when the user uses the water dispenser is avoided; if the current time is 1:00 in the morning, the current time is not in any first use time interval or any second use time interval, the updating time interval is greatly increased, and the power consumption is reduced; the preset time adjustment amplitude value is specifically as follows: for example 100 seconds.
The embodiment of the invention can intelligently adjust the updating time interval of the brewing water temperature database, the updating time interval can be increased when the possibility of non-use of a user is higher so as to save power consumption, the updating time interval can be reduced when the possibility of non-use of the user is lower so as to avoid the situation that the brewing temperature cannot be determined.
The embodiment of the invention provides a voice control system of an intelligent water dispenser under multiple instructions, wherein a control module 3 executes the following operations:
and if a brewing completion instruction input by the user is received, determining that the brewing of the user is completed.
The working principle and the beneficial effects of the technical scheme are as follows:
when the user receives the prompt and controls the water dispenser to discharge water for brewing, the user can press the 'continue heating' button to input a brewing completion instruction and can orally speak the 'continue heating' instruction.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A voice control method of an intelligent water dispenser under multiple instructions is characterized by comprising the following steps:
acquiring a plurality of voice instructions input by a user, analyzing each voice instruction, and determining a plurality of beverage types which the user wants to brew;
determining the brewing temperature corresponding to each beverage type from a preset brewing temperature database, and sequencing the brewing temperatures from low to high;
and controlling the water dispenser to sequentially heat the water temperature to each of the ordered brewing temperatures according to a preset sequence, reminding the user of brewing the corresponding beverage class by voice when each water temperature is heated to one brewing temperature, identifying whether the user finishes brewing, and if so, controlling the water dispenser to continue heating to the next brewing temperature.
2. The voice control method of the intelligent water dispenser under the multiple instructions according to claim 1, wherein the analyzing of each voice instruction to determine the multiple beverage types that the user wants to brew comprises:
recognizing each voice instruction based on a voice recognition technology to obtain a plurality of voice recognition texts;
integrating the voice recognition texts to obtain a target text;
determining a plurality of beverage keywords contained in the target text based on a preset beverage keyword database;
when at least two identical beverage keywords appear in the target text, selecting the beverage keyword appearing last in the identical beverage keywords as a target keyword;
extracting a first text between the target keyword and the last beverage keyword and/or a second text between the target keyword and the next beverage keyword from the target text;
identifying the first text based on a semantic identification technology to obtain a first semantic feature;
recognizing the second text based on a semantic recognition technology to obtain a second semantic feature;
acquiring a preset negative feature database, matching the first semantic feature and the second semantic feature with negative features in the negative feature database, and if the first semantic feature and/or the second semantic feature match and meet the matching requirement, rejecting the target keyword and the beverage keyword which is the same as the target keyword;
after the beverage is removed, a preset beverage type comparison table is inquired, the beverage types corresponding to the residual beverage keywords are determined, and a plurality of beverage types which the user wants to brew are obtained.
3. The voice control method of the intelligent water dispenser under the multiple instructions as claimed in claim 1, further comprising:
updating the brewing temperature database at preset time intervals;
wherein updating the brewing temperature database comprises:
acquiring first big data through a preset first acquisition path, wherein the first big data comprises: the method comprises the following steps that a plurality of missing items are obtained, wherein the missing items are beverage types of which the brewing temperature cannot be determined from a corresponding brewing temperature database when different users input voice instructions within a preset time period;
determining the occurrence frequency of each missing item in the first big data, and sorting the missing items from big to small based on the corresponding frequency;
sequentially selecting one ordered missing item as a target missing item according to a preset sequence;
acquiring second big data associated with the target missing item through a preset second acquisition path, wherein the second big data comprises: different suitable temperatures corresponding to the target missing item, wherein each suitable temperature corresponds to first evaluation data given by a large number of experiments by background experimenters;
acquiring third big data associated with the target missing item through a preset third acquisition path, wherein the third big data comprises: each suitable temperature corresponds to second evaluation data given by a large number of users in internet survey data;
analyzing the first evaluation data to obtain a plurality of first evaluation values and first credible values in one-to-one correspondence with the first evaluation values;
analyzing the second evaluation data to obtain a plurality of second evaluation values and second credible values corresponding to the second evaluation values one by one; (ii) a
Calculating an evaluation index of each of the suitable temperatures based on the first evaluation value, the second evaluation value, the first confidence value, and the second confidence value, the calculation formula being as follows:
wherein σtThe evaluation index, a, of the suitable temperature at the tth corresponding to the target deletion termt,iThe ith first evaluation value mu obtained by analyzing the first evaluation data of the tth suitable temperature corresponding to the target missing itemt,iThe first credible value, m, corresponding to the ith first evaluation value obtained by analyzing the first evaluation data of the tth suitable temperature corresponding to the target missing itemt,1A total number β of the first evaluation values obtained by analyzing the first evaluation data of the tth suitable temperature corresponding to the target missing itemt,iThe ith second evaluation value γ obtained by analyzing the second evaluation data of the tth suitable temperature corresponding to the target missing itemt,iThe second credible value m corresponding to the ith second evaluation value obtained by analyzing the second evaluation data of the tth suitable temperature corresponding to the target missing itemt,2A total number, α, of the second evaluation values obtained by analyzing the second evaluation data of the tth suitable temperature corresponding to the target missing item0Is a preset first evaluation value threshold value, beta0Is a preset second evaluation value threshold, mu0Is a preset first confidence threshold value, gamma0Is a preset second confidence value threshold value, e is a natural constant, Z1And Z2Is a preset weight value, Z1>Z2;
And selecting the appropriate temperature corresponding to the maximum evaluation index value and the target missing item to be combined and then filling the combined combination into the brewing temperature database, and completing updating after all the target missing items are completed.
4. The voice control method of the intelligent water dispenser under the multiple instructions as claimed in claim 3, further comprising:
acquiring a preset local use record, and adjusting the time interval based on the local use record;
wherein adjusting the time interval based on the local usage record comprises:
acquiring a preset identification model, inputting the local use record into the identification model, and acquiring a plurality of first use time intervals;
acquiring a plurality of preset second use time intervals;
determining the current time, and determining a target time which is a preset time after the current time;
adjusting the time interval based on the first usage time interval, the second usage time interval and the target time, wherein an adjustment formula is as follows:
t′=t+t0(ε1ρ1+ε2ρ2)
wherein t' is the time interval after adjustment, t is the time interval before adjustment, t0Adjusting amplitude values for preset times1And ε2Is a preset weight value, epsilon1>ε2,ρ1Is a preset first adjusting coefficient, and when the target time is within any one first use time interval, the rho1< 0, otherwise, ρ1>0,ρ2Is a preset second adjusting coefficient, and when the target time is within any second use time interval, the rho2< 0, otherwise, ρ2>0。
5. The voice control method of the intelligent water dispenser under the multiple instructions of claim 1, wherein recognizing whether the user has finished brewing comprises:
and if the brewing completion instruction input by the user is received, determining that the brewing of the user is completed.
6. The utility model provides an intelligent water dispenser voice control system under many instructions which characterized in that includes:
the acquisition and analysis module is used for acquiring a plurality of voice instructions input by a user, analyzing each voice instruction and determining a plurality of beverage types which the user wants to brew;
the determining and sequencing module is used for determining the brewing temperature corresponding to each beverage type from a preset brewing temperature database and sequencing the brewing temperatures from low to high;
the control module is used for controlling the water dispenser to sequentially heat the water temperature to each of the ordered brewing temperatures according to a preset sequence, when the water temperature is heated to one brewing temperature, the user is reminded of brewing the corresponding beverage class through voice, whether the brewing of the user is finished is identified, and if yes, the water dispenser is controlled to continue to heat to the next brewing temperature.
7. The voice control system of an intelligent water dispenser under multiple instructions of claim 6, wherein the determining and parsing module performs the following operations:
recognizing each voice instruction based on a voice recognition technology to obtain a plurality of voice recognition texts;
integrating the voice recognition texts to obtain a target text;
determining a plurality of beverage keywords contained in the target text based on a preset beverage keyword database;
when at least two identical beverage keywords appear in the target text, selecting the beverage keyword appearing last in the identical beverage keywords as a target keyword;
extracting a first text between the target keyword and the last beverage keyword and/or a second text between the target keyword and the next beverage keyword from the target text;
identifying the first text based on a semantic identification technology to obtain a first semantic feature;
recognizing the second text based on a semantic recognition technology to obtain a second semantic feature;
acquiring a preset negative feature database, matching the first semantic feature and the second semantic feature with negative features in the negative feature database, and if the first semantic feature and/or the second semantic feature match and meet the matching requirement, rejecting the target keyword and the beverage keyword which is the same as the target keyword;
after the beverage is removed, a preset beverage type comparison table is inquired, the beverage types corresponding to the residual beverage keywords are determined, and a plurality of beverage types which the user wants to brew are obtained.
8. The voice control system of the intelligent water dispenser under the multiple instructions of claim 6, further comprising:
the updating module is used for updating the brewing temperature database at preset time intervals;
the update module performs the following operations:
acquiring first big data through a preset first acquisition path, wherein the first big data comprises: the method comprises the following steps that a plurality of missing items are obtained, wherein the missing items are beverage types of which the brewing temperature cannot be determined from a corresponding brewing temperature database when different users input voice instructions within a preset time period;
determining the occurrence frequency of each missing item in the first big data, and sorting the missing items from big to small based on the corresponding frequency;
sequentially selecting one ordered missing item as a target missing item according to a preset sequence;
acquiring second big data associated with the target missing item through a preset second acquisition path, wherein the second big data comprises: different suitable temperatures corresponding to the target missing item, wherein each suitable temperature corresponds to first evaluation data given by a large number of experiments by background experimenters;
acquiring third big data associated with the target missing item through a preset third acquisition path, wherein the third big data comprises: each suitable temperature corresponds to second evaluation data given by a large number of users in internet survey data;
analyzing the first evaluation data to obtain a plurality of first evaluation values and first credible values in one-to-one correspondence with the first evaluation values;
analyzing the second evaluation data to obtain a plurality of second evaluation values and second credible values corresponding to the second evaluation values one by one; (ii) a
Calculating an evaluation index of each of the suitable temperatures based on the first evaluation value, the second evaluation value, the first confidence value, and the second confidence value, the calculation formula being as follows:
wherein σtThe evaluation index, a, of the suitable temperature at the tth corresponding to the target deletion termt,iThe ith first evaluation value mu obtained by analyzing the first evaluation data of the tth suitable temperature corresponding to the target missing itemt,iThe first credible value, m, corresponding to the ith first evaluation value obtained by analyzing the first evaluation data of the tth suitable temperature corresponding to the target missing itemt,1A total number β of the first evaluation values obtained by analyzing the first evaluation data of the tth suitable temperature corresponding to the target missing itemt,iThe ith second evaluation value γ obtained by analyzing the second evaluation data of the tth suitable temperature corresponding to the target missing itemt,iThe second credible value m corresponding to the ith second evaluation value obtained by analyzing the second evaluation data of the tth suitable temperature corresponding to the target missing itemt,2A total number, α, of the second evaluation values obtained by analyzing the second evaluation data of the tth suitable temperature corresponding to the target missing item0Is a preset first evaluation value threshold value, beta0Is a preset second evaluation value threshold, mu0Is a preset first confidence threshold value, gamma0Is a preset second confidence value threshold value, e is a natural constant, Z1And Z2Is a preset weight value, Z1>Z2;
And selecting the appropriate temperature corresponding to the maximum evaluation index value and the target missing item to be combined and then filling the combined combination into the brewing temperature database, and completing updating after all the target missing items are completed.
9. The voice control system of the intelligent water dispenser under the multiple instructions of claim 8, further comprising:
the adjusting module is used for acquiring a preset local use record and adjusting the time interval based on the local use record;
the adjustment module performs the following operations:
acquiring a preset identification model, inputting the local use record into the identification model, and acquiring a plurality of first use time intervals;
acquiring a plurality of preset second use time intervals;
determining the current time, and determining a target time which is a preset time after the current time;
adjusting the time interval based on the first usage time interval, the second usage time interval and the target time, wherein an adjustment formula is as follows:
t′=t+t0(ε1ρ1+ε2ρ2)
wherein t' is the time interval after adjustment, t is the time interval before adjustment, t0Adjusting amplitude values for preset times1And ε2Is a preset weight value, epsilon1>ε2,ρ1Is a preset first adjusting coefficient, and when the target time is within any one first use time interval, the rho1< 0, otherwise, ρ1>0,ρ2Is a preset second adjusting coefficient, and when the target time is within any second use time interval, the rho2< 0, otherwise, ρ2>0。
10. The voice control system of the intelligent water dispenser under the multiple instructions of claim 6 is characterized in that the control module executes the following operations:
and if the brewing completion instruction input by the user is received, determining that the brewing of the user is completed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110491729.3A CN113223525A (en) | 2021-05-06 | 2021-05-06 | Voice control method and system for intelligent water dispenser under multiple instructions |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110491729.3A CN113223525A (en) | 2021-05-06 | 2021-05-06 | Voice control method and system for intelligent water dispenser under multiple instructions |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113223525A true CN113223525A (en) | 2021-08-06 |
Family
ID=77091048
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110491729.3A Withdrawn CN113223525A (en) | 2021-05-06 | 2021-05-06 | Voice control method and system for intelligent water dispenser under multiple instructions |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113223525A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114532851A (en) * | 2022-03-17 | 2022-05-27 | 佛山市顺德区美的饮水机制造有限公司 | Control method and device of drinking equipment, readable storage medium and drinking equipment |
-
2021
- 2021-05-06 CN CN202110491729.3A patent/CN113223525A/en not_active Withdrawn
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114532851A (en) * | 2022-03-17 | 2022-05-27 | 佛山市顺德区美的饮水机制造有限公司 | Control method and device of drinking equipment, readable storage medium and drinking equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108852023B (en) | Can realize interconnected steaming and baking equipment of intelligence | |
US20240070755A1 (en) | Systems and methods for tracking consumer tasting preferences | |
CN108826824B (en) | Refrigerator control method and device, storage medium and refrigerator | |
CN104799696B (en) | A kind of capsule drink brewing machine, reconstitute system and reconstitute method | |
CN107886348A (en) | A kind of artificial intelligence method of ordering and system | |
CN107644487A (en) | Intelligent beverage vending machine and pushing method | |
US9784722B2 (en) | Systems and methods for evaluation of wine characteristics | |
CN106339576A (en) | Health management method and system | |
CN113223525A (en) | Voice control method and system for intelligent water dispenser under multiple instructions | |
WO2011044497A3 (en) | Automatic method to generate product attributes based solely on product images | |
CN110148405A (en) | Phonetic order processing method and processing device, electronic equipment and storage medium | |
CN111667261B (en) | Intelligent voice dialogue household wine cabinet | |
CN107515900A (en) | Intelligent robot and its event memorandum system and method | |
CN109448817A (en) | A kind of recipe recommendation method and apparatus based on deep neural network | |
CN107729527A (en) | Annual age based on program cloud intelligently matches somebody with somebody the control method and system of milk machine | |
CN111666893A (en) | Ordering processing method and device | |
WO2021236884A1 (en) | Food-recognition systems and methods | |
CN109671485A (en) | A kind of raising pets system based on big data | |
CN109561824A (en) | Diagnostic system | |
CN109284415A (en) | The automatic method, apparatus for recommending food | |
CN113223523A (en) | Voice recognition method and system for intelligent water dispenser | |
CN106251255A (en) | Customized formula intelligence food and beverage sevice system and method | |
CN108523682A (en) | The device and method of brewing tea | |
CN112463782B (en) | Data cleaning method and system based on optimized edit distance | |
CN109541986A (en) | Cooking appliance control method and cooking appliance |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210806 |