CN105700389B - Intelligent home natural language control method - Google Patents
Intelligent home natural language control method Download PDFInfo
- Publication number
- CN105700389B CN105700389B CN201410695637.7A CN201410695637A CN105700389B CN 105700389 B CN105700389 B CN 105700389B CN 201410695637 A CN201410695637 A CN 201410695637A CN 105700389 B CN105700389 B CN 105700389B
- Authority
- CN
- China
- Prior art keywords
- user
- voice
- voice control
- command
- electric appliance
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 230000009471 action Effects 0.000 claims abstract description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000003111 delayed effect Effects 0.000 claims description 4
- 230000007704 transition Effects 0.000 claims description 3
- 238000004378 air conditioning Methods 0.000 description 20
- 238000010438 heat treatment Methods 0.000 description 9
- 238000005057 refrigeration Methods 0.000 description 8
- 238000012790 confirmation Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000009423 ventilation Methods 0.000 description 5
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000001816 cooling Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 241000238558 Eucarida Species 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000003287 bathing Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000013467 fragmentation Methods 0.000 description 1
- 238000006062 fragmentation reaction Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 208000020016 psychiatric disease Diseases 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Landscapes
- User Interface Of Digital Computer (AREA)
- Selective Calling Equipment (AREA)
Abstract
The invention discloses a natural language control method for an intelligent home, which comprises the following steps: (1) the voice receiving device receives a voice control command; (2) the control unit analyzes the command; (3) executing the command; in the step (2), the following sub-steps are further included: (21) analyzing the integrity of the voice control command, and directly entering the step (3) if the voice control command comprises the complete electric appliance type and the action command for controlling execution; otherwise, entering the step (22); (22) if the type of the electric appliance is not specified in the voice control command, the position of the user is located, the electric appliance which is closest to the user is found out according to the position of the user, the electric appliance is judged to be the specified electric appliance, and the step (3) is executed. The intelligent home natural language control method adopts a mode of indoor positioning for the user, and intelligently analyzes and judges the information implicitly contained in the incomplete voice control command of the user according to the position of the user, thereby improving the natural language recognition capability of the voice control system.
Description
Technical Field
The invention relates to the technical field of intelligent families, in particular to a natural language control method for an intelligent family.
Background
Smart homes are a product of the informatization and post-industrial era. In the post-industrial age, the industry and the informatization are closely combined, advanced computing methods such as computer vision, voice recognition and artificial intelligence are generally applied, household appliances generally have primary artificial intelligence, and on products such as televisions, air conditioners and the like, gesture control and voice recognition are gradually replacing remote controllers. Voice control is the most natural and convenient control method. At present, the voice recognition functions of the intelligent home are scattered and dispersed, for example, a user can only speak voice commands which are understood by a television and speak a television to a television, and speak voice commands which are understood by an air conditioner to the air conditioner, the voice control system which is separated from fragmentation enables the user to feel uncertainty, the user always uses the new functions with great care, the verbs or phrases which are very simple and solidified are used for operating the new functions, and the user can not visually see that target household appliances do not act according to own commands, so that the whole process is full of confusion and completely has no interest of natural language interaction.
Disclosure of Invention
The invention provides an intelligent household natural language control method, which aims to solve the problems that the existing intelligent household voice control system does not support natural language control, has poor natural voice recognition and judgment capability for a user, cannot recognize and execute the natural voice, or has execution errors caused by judgment errors, or has a plurality of confirmation prompts sent by the system, but brings inconvenience to the user.
In order to solve the technical problems, the invention adopts the following technical scheme:
a natural language control method for an intelligent home comprises the following steps: (1) the voice receiving device receives a voice control command; (2) the control unit analyzes the command; (3) executing the command; in the step (2), the following sub-steps are further included:
(21) analyzing the integrity of the voice control command, and directly entering the step (3) if the voice control command comprises the complete electric appliance type and the action command for controlling execution; otherwise, entering the step (22);
(22) if the type of the electric appliance is not specified in the voice control command, the position of the user is located, the electric appliance which is closest to the user is found out according to the position of the user, the electric appliance is judged to be the specified electric appliance, and the step (3) is executed.
Further, when the intelligent family natural language control method is initialized, the method also comprises the step of setting user permission, wherein the voice characteristics of different users of family members are collected, corresponding user permission levels are distributed to the users, and a user permission level table is established;
before step (3) is entered in step (21), a step of analyzing a command conflict is further included,
a. if the voice control commands of users with different authority levels are received at the same time or within a limited time, executing the voice control command with high authority level;
b. if the different voice control commands of the users at the same authority level conflict with each other, judging whether the conflicting voice control commands are from the same user, and if the conflicting voice control commands are from the same user, sending a voice prompt to confirm the user.
Still further, in the step b of analyzing command conflict, if the conflicting voice control commands are not from the same user, continuing to detect and receive the voice control commands, if the conflicting voice control commands continue to appear at high frequency, determining that the opinions of the two users are divergent, adopting a method of discounting an execution command, and executing a new voice control command in a delayed manner, wherein the time of delay is correspondingly increased every time of execution until the conflicting voice control commands do not appear any more.
Further, in the step b of analyzing the command conflict, if the voice control commands which conflict with each other are not from the same user and the repetition frequency of the voice control commands which conflict with each other is lower than the set limit value, it is determined that one of the users has prank control, the position of the user is located, the user which is closest to the controlled electrical appliance is found out according to the position of the user, and the voice control command of the user is executed.
Preferably, in the step (22), the method for locating the position of the user includes: the IPV6 address positioning is adopted, the IPV6 address of each electric appliance is bound with the actual space address where the electric appliance is located, the IPV6 address of each voice receiving device is bound with the actual space address where the electric appliance is located, the position where a user is located is judged according to the IPV6 address of the voice receiving device which receives voice control signals, and then the electric appliance which is closest to the position of the user is correspondingly controlled to execute a corresponding control command.
Further, in the step (22), if a plurality of voice receiving apparatuses simultaneously receive the voice control command, the voice receiving apparatus with the strongest received voice signal strength is compared according to the strength of the voice signal received by each voice receiving apparatus, and the position of the user is determined by the IPV6 address of the voice receiving apparatus.
Preferably, before the step (1), a step of presetting a trigger vocabulary for triggering a voice control operation is further included, and the step (1) or the subsequent steps are executed when a user utters a voice of the trigger vocabulary.
Preferably, in the step (3), if the voice command does not include specific parameter information, the user command is executed according to default parameters, and each electrical appliance is provided with default parameters.
Compared with the prior art, the invention has the advantages and positive effects that: the intelligent household natural language control method adopts a mode of indoor positioning for the user, and intelligently analyzes and judges the information implicitly contained in the incomplete voice control command of the user according to the position of the user, thereby improving the recognition capability of the voice control system for the natural language, avoiding the problem that the system does not execute actions because of being incapable of recognizing or provides more confirmation problems because of being incapable of accurately recognizing so as to ensure the confirmation of the user, bringing inconvenience to the user, and being beneficial to improving the pleasure and the feeling of the user for using the intelligent household system.
Other features and advantages of the present invention will become more apparent from the detailed description of the embodiments of the present invention when taken in conjunction with the accompanying drawings.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of an embodiment of a natural language control method for a smart home according to the present invention;
fig. 2 is a schematic diagram of discounting execution steps of the smart home natural language control method provided by the present invention.
Detailed Description
The voice control is the most natural and convenient control mode and is also the hotspot of the technical development in the years, and the Siri voice control function of the apple mobile phone is considered to start a new round of artificial intelligence scientific and technological revolution. Through the intelligent voice system, a user can read a short message, introduce a restaurant, inquire weather, set an alarm clock through voice and the like through a mobile phone, Siri can call applications of weather forecast, schedule arrangement, data searching and the like carried by the system, and can continuously learn new voice and tone to provide conversational response.
The domestic voice technology factory and business department provides a voice assistant 'smart', says 'one set in the center' for smart, and automatically switches a television channel to the one set in the center; for the inspiration saying 'help me boil cup coffee', the coffee machine starts working; to the inspiration saying "temperature turn down two degrees", the air conditioner just begins the cooperation of … … present many household electrical appliances manufacturers and internet hardware manufacturers of adjusting the temperature, fumble the application of speech technology in the intelligent house scene, some simple speech control discernments have been realized, but in the intelligent house trade, because the controlled household electrical appliances that involve are of a great variety, combine the current application environment of user control, can involve many scenes and many kinds of possibilities, therefore, brought very big difficulty and challenge for the speech recognition system, present speech recognition control needs to send out clear complete speech control command to specific controlled object, or can carry out fuzzy recognition to some incomplete commands, however, can't realize the discernment judgement to user's natural language completely yet. Based on the above, the invention provides the intelligent home natural language control method.
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment provides a natural language control method for an intelligent home, which includes the following steps:
s1, the voice receiving device receives the voice control command;
s2, analyzing the command by the control unit;
s3, executing the command;
in step S2, the method further includes the following substeps:
s21, analyzing the integrity of the voice control command, and if the voice control command contains the complete electric appliance type and the action command for controlling execution, directly entering the step S3; otherwise, go to step S22;
s22, if the electric appliance type is not designated in the voice control command, positioning the position of the user, finding out the electric appliance closest to the user according to the position of the user, judging the electric appliance to be the designated electric appliance, and executing the step S3.
One important challenge facing smart home speech recognition is language omission. A number of known preconditions are hidden in our natural language, such as "turn down a little bit", which means turn down a temperature, or turn down a curtain, or turn down a screen brightness? In daily life, people can know which equipment is turned down by a speaker through one eye, and intelligent household appliances are still incapable of sensing the expression mode of the transmission. The intelligent household natural language control method adopts a mode of indoor positioning for the user, and intelligently analyzes and judges the information hidden in the incomplete voice control command of the user according to the position of the user, thereby improving the recognition capability of the voice control system for the natural language, avoiding the problem that the system does not execute actions due to recognition or provides more confirmation problems due to inaccurate recognition so as to ensure the confirmation of the user, bringing inconvenience to the user, and reducing the fun and feeling of the user for the intelligent household system. The method comprises the steps that incomplete voice control commands are judged according to a user positioning mode, the problem of language simplification is actually solved by using a hidden Markov model, and the commands are considered to be sent to an air conditioner by means of indoor positioning information if a user is closer to the air conditioner; if the user is closer to the window, the command is deemed to be issued to the window. In fact, the method completely accords with the normal use habit of human beings, and is beneficial to improving the accuracy of voice judgment.
Then how does the air conditioner know that "the big spot" is the requirement "the cold spot"? Is "hot spot"? Or a little greater ventilation? The user's position information is not enough, and the judgment is needed by using the hidden Markov model algorithm.
According to the logical reasoning method of human, we can infer the true intention of the user to say "big" in this way:
1. if the window has just been opened, then "larger" shall mean that the window is larger again.
2. If the air conditioner is just turned on, the user also needs to see whether the air conditioner is used for cooling or heating, and the cooling refers to a little re-cooling; heating means "a little reheat". Generally, the possibility of adjusting the ventilation amount of the air conditioner is not high.
3. If the user has just adjusted the ventilation amount of the air conditioner, the possibility of requiring adjustment of the ventilation amount again becomes high. In this case, "a little larger" most likely means that the ventilation amount is a little larger.
Converting this process into an operation that a computer can perform requires the use of a hidden markov model. Hidden markov models are mathematical models, also known as "quintuple," of the following:
s: a set of hidden states;
n: observing a state set;
a: a transition probability matrix between hidden states;
b: output matrix (i.e., probability of hidden state to output state);
PI: initial probability distribution (initial probability distribution of hidden state);
taking the bedroom as an example, we can define a quintuple as follows:
s = { window opening, air conditioner cold, air conditioner hot, air conditioner air volume }
N = {
Opening degree of the window: { 0.0 spot cold, 0.0 spot hot, 0.5 spot hot and 0.5 spot small },
air-conditioning refrigeration: { 0.4. cold spot, 0.0. hot spot, 0.3. large spot, 0.3. small spot },
air conditioning and heating: { 0.0 spot cold, 0.4 spot hot, 0.3 spot large and 0.3 spot small },
air volume of the air conditioner: { 0.0 spot cold, 0.0 spot hot, 0.5 spot hot and 0.5 spot small },
}
A = {
opening degree of the window: { window opening: 0.7, air-conditioning refrigeration: 0.1, air-conditioning heating: 0.1, air-conditioning air volume: 0.1 },
air-conditioning refrigeration: { window opening: 0.1, air-conditioning refrigeration: 0.5, air-conditioning heating: 0.3, air-conditioning air volume: 0.1 },
air conditioning and heating: { window opening: 0.1, air-conditioning refrigeration: 0.3, air-conditioning heating: 0.5, air-conditioning air volume: 0.1 },
air volume of the air conditioner: { window opening: 0.1, air-conditioning refrigeration: 0.2, air-conditioning heating: 0.2, air-conditioning air volume: 0.5 },
}
PI = { window opening: 0.0, air conditioner cold: 0.0, air conditioner heat: 0.0, air conditioner air volume: 1.0}
In the quintuple N, the observation state set indicates the probability of each operation, and if the user wants to operate the opening of the window, he cannot say "cold spot" or "hot spot", so both probabilities are 0, and the user has half the possibility to say "big spot" or "small spot".
In the quintuple A, the transition probability matrix between the hidden states refers to the probability that the four states occur again after each state in the S set, and taking the window opening as an example, the last command of a user is known to adjust the window opening, so that the probability that the command adjusts the window opening is 70% now, and the probabilities that the command adjusts the air conditioning refrigeration, heating and air volume are all 10% very low.
The PI is initial probability distribution, namely the judgment result of the last time, and the calculation result of the last time is assumed to be the adjustment of the air volume of the air conditioner.
Having defined the above three arrays, the calculation result can then be obtained using the Viterbi algorithm. The viterbi algorithm is a commonly used algorithm in the hidden markov model, and details of the algorithm are not described in this embodiment.
For example, set the input sequence:
input = { major, minor, cold, major) }
After calculation by the Viterbi algorithm, the following output results can be obtained:
output = { air conditioning air volume, air conditioning refrigeration }
The calculation result is completely consistent with the previous logical reasoning result.
As a preferred embodiment, when the intelligent home natural language control method is initiated, the method further comprises the step of setting user permission, wherein the voice characteristics of different users of family members are collected, corresponding user permission levels are distributed to the voice characteristics, and a user permission level table is established;
before step (3) is entered in step (21), a step of analyzing a command conflict is further included,
a. if the voice control commands of users with different authority levels are received at the same time or within a limited time, executing the voice control command with high authority level;
b. if the different voice control commands of the users at the same authority level conflict with each other, judging whether the conflicting voice control commands are from the same user, and if the conflicting voice control commands are from the same user, sending a voice prompt to confirm the user. This step is to prevent users from having a tendency to play a 3,857 smart home control, and some users may use voice commands too strangely and arbitrarily, for example, the user just requests "temperature decrease 10 degrees" and then quickly sends "temperature increase 10 degrees" again. Air conditioning equipment may be damaged if the voice recognition system is operated strictly in accordance with user commands. Therefore, the system needs to send out a prompt for the user to confirm, which is beneficial to prompting the user to restore the rationality and improving the seriousness of the voice control.
In the step, different use authorities are given to different users, so that the intelligent degree is improved, for example, a system administrator has the highest authority of a complete control system, a parent user is set by the system administrator, meanwhile, the parent user can also designate a new parent user, the authority of the monitored user is lower than that of the parent user, when the monitored user conflicts with the command of the parent user, the system preferentially executes the command of the parent user, a visitor user mainly visits guests of a family for a short time or a home administration service person, and the intelligent home system provides the lowest convenient water and electricity and lighting service for the visitor. Certainly, the voice feature information of the visitor user may not be collected and stored in advance, and if the system cannot search for a user matched with the voice feature information in the stored data, the visitor user is uniformly classified. By limiting the authority level, for example, a person who is generally young, mentally incompetent, intoxicated, or ill-behaved, or has mental illness, can limit the control authority to 1, and cannot use a command violating a rule, such as a request for opening a television or opening a door to play during a writing operation. 2. Commands affecting neighbors, such as turning the room sound to maximum volume at night, cannot be used. For another example, the visitor is generally a guest, a housekeeping service person, and the like, and the control authority thereof may be limited to: 1. voice commands that are related to the privacy of the home, such as opening a home's mailbox, cannot be used. 2. System parameters cannot be set or modified. 3. Except for lights, air conditioners, water heaters, other household appliances are not allowed to be used. By adopting the limitation, the management and the control of the master user are facilitated, and meanwhile, corresponding services can be intelligently provided, so that great convenience is brought to the user.
In the step b of analyzing the command conflict, if the conflicting voice control commands are not from the same user, continuing to detect and receive the voice control commands, if the conflicting voice control commands continue to appear in high frequency, determining that the opinions of the two users are divergent, and executing the new voice control command in a delayed manner by adopting a method of discounting the execution command, wherein the delayed time is correspondingly increased every time of executing until the conflicting voice control commands do not appear any more. What this step can solve is the problem of parent-user conflicts, e.g., how do the male owner and the female owner are quarried? The male owner says 'turn on the air conditioner', and the female owner says 'turn off the air conditioner'. The best solution, discounting and executing the completely opposite commands, is adopted in the embodiment until one party gives up. The schematic diagram of "discounted execution" is shown in fig. 2, in short, the more a and B "discount" the smaller the slope of the line segment representing the command execution process, which means the system response is more and more dull and the parameter discount is more and more high. When a and B cease to quarrel, the system delays for 10 seconds to confirm that no objectionable commands are occurring, and returns to a normal state of rapid response and complete execution.
In addition, in the step b of analyzing the command conflict, if the conflicting voice control commands are not from the same user and the repetition frequency of the conflicting voice control commands is lower than the set limit, it is determined that there is a trick control for one of the users, the location of the user is located, the user closest to the controlled electrical appliance is found according to the location of the user, and the voice control command of the user is executed. For example, a female owner is bathing in a bathroom and a male owner shouts outside to "stop supplying hot water". Whether to execute the command can be judged according to the positions of the male owner and the female owner. Indoor positioning information is often the best decision support data to determine whether an activity is a prank activity. This embodiment proposes a simplest indoor location method, by binding the IPV6 address of an appliance and its spatial location into a table, as shown in table 1:
| ID | IPV6 address of household electrical appliance | Type of household appliance | Location information of home appliance |
| 1 | 2001:0DB8::1428:0950 | Television receiver | Master bedroom, east wall, center |
| 2 | 2001:0DB8::1428:0951 | Air conditioner | Master bedroom, east wall, south side |
| 3 | 2001:0DB8::1428:0952 | Electric control window | Master bedroom, south wall, center |
| …… | …… | …… | …… |
Table 1 IPV6 address and location comparison table for intelligent home appliances
Since the IPV6 addresses are sufficiently large, there is no concern about address exhaustion. Generally, the main home appliances are installed wall-wise, ceiling-wise or floor-wise, and thus it is not necessary to precisely describe their spatial positions using a cartesian coordinate system, which can greatly reduce the amount of data.
The present invention is not limited to this indoor positioning method. Other indoor positioning methods, such as intelligent floor, bluetooth beacon positioning, sound source positioning, wifi positioning, can be used to participate in the above operations based on location information.
Preferably, in this embodiment, in the step S22, the method for locating the position of the user includes: the IPV6 address positioning is adopted, the IPV6 address of each electric appliance is bound with the actual space address where the electric appliance is located, the IPV6 address of each voice receiving device is bound with the actual space address where the electric appliance is located, the position where a user is located is judged according to the IPV6 address of the voice receiving device which receives voice control signals, and then the electric appliance which is closest to the position of the user is correspondingly controlled to execute a corresponding control command. The binding method can be seen in table 1.
Furthermore, since a plurality of voice receivers may be installed indoors, in step S22, if a plurality of voice receivers simultaneously receive the voice control command, the voice receiver with the strongest received voice signal strength is compared according to the strength of the voice signal received by each voice receiver, and the IPV6 address of the voice receiver is used to determine the location of the user.
Preferably, before the step S1, a step of presetting a trigger vocabulary for triggering a voice control operation is further included, and the step S1 or the subsequent steps are executed when the user utters the voice of the trigger vocabulary. This is to prevent the user's daily conversations from being distinguished from the voice control commands sent to the smart home, and the system will only analyze and execute the voice if the user enables the voice control function.
In daily life, there is a possibility that the voice control command issued by the user does not include specific parameter information, for example, "the air conditioner temperature is turned up a little", the system only receives the command for turning up the air conditioner temperature, but does not know how much degree the user needs to turn up the air conditioner temperature, for example, "turn on the television", and the system does not know what station should be turned on, so in order to handle the above situation, in step S3, if the voice command does not include specific parameter information, the user command is executed according to the default parameters, and each electrical appliance is provided with the default parameters. Taking the television as an example, the default parameter for "watching television" is the station on which the television was last turned off. If that station has no signal, the station with the highest frequency of viewing is selected. Taking an air conditioner as an example, the default parameter is 1 degree plus or 1 degree minus, and other types of intelligent household appliances or intelligent devices should set appropriate default parameters.
To sum up, the intelligent home natural language control method of the embodiment combines the indoor positioning technology and the hidden markov principle, can judge the incomplete voice control command according to the normal habits and logical thinking of people, improves the accuracy of judgment, can judge various different application control environments, avoids the situation that the electric appliance is damaged due to mischief of a user, and simultaneously provides a solution when the user command conflicts, so that the intelligent home control is more intelligent, and better conforms to the logical thinking habits and living habits of people.
It is to be understood that the above description is not intended to limit the present invention, and the present invention is not limited to the above examples, and those skilled in the art may make modifications, alterations, additions or substitutions within the spirit and scope of the present invention.
Claims (8)
1. A natural language control method for an intelligent home comprises the following steps: (1) the voice receiving device receives a voice control command; (2) the control unit analyzes the command; (3) executing the command; characterized in that, in the step (2), the following substeps are also included:
(21) analyzing the integrity of the voice control command, and directly entering the step (3) if the voice control command comprises the complete electric appliance type and the action command for controlling execution; otherwise, entering the step (22); the method for analyzing the integrity of the voice control command comprises the following steps:
defining a quintuple comprising:
s: the hidden state set comprises a plurality of hidden states of the electric appliance to be adjusted;
n: observing a state set, wherein the observation state set represents the probability of each operation, and comprises the probability of each operation corresponding to each hidden state;
a: the transition probability matrix among the hidden states represents the probability that each state occurs again after the state, and comprises the probability that each hidden state in the hidden state set occurs again after any hidden state in the hidden state set occurs;
b: an output matrix which is the probability from a hidden state to an output state;
PI: an initial probability distribution which is an initial probability distribution of a hidden state;
the output matrix B is obtained by inputting the array S, N, A into a Viterbi algorithm for calculation;
(22) if the type of the electric appliance is not specified in the voice control command, the position of the user is located, the electric appliance which is closest to the user is found out according to the position of the user, the electric appliance is judged to be the specified electric appliance, and the step (3) is executed.
2. The intelligent home natural language control method according to claim 1, further comprising a step of setting user authority when the intelligent home natural language control method is initiated, collecting voice characteristics of different users of the family members, assigning corresponding user authority levels to the voice characteristics, and establishing a user authority level table;
before step (3) is entered in step (21), a step of analyzing a command conflict is further included,
a. if the voice control commands of users with different authority levels are received at the same time or within a limited time, executing the voice control command with high authority level;
b. if the different voice control commands of the users at the same authority level conflict with each other, judging whether the conflicting voice control commands are from the same user, and if the conflicting voice control commands are from the same user, sending a voice prompt to confirm the user.
3. The intelligent home natural language control method according to claim 2, wherein in the step b of analyzing the command conflict, if the conflicting voice control commands are not from the same user, the received voice control commands are continuously detected, if the conflicting voice control commands continue to appear, it is determined that there is a divergence between opinions of the two users, a method of performing the commands by discounting is employed, the new voice control commands are delayed, and the time of the delay is correspondingly increased every time the new voice control commands are performed until the conflicting voice control commands do not appear any more.
4. The method according to claim 3, wherein in the step b of analyzing the command conflict, if the conflicting voice control commands are not from the same user and the conflicting voice control command repetition frequency is lower than a set limit, it is determined that one of the users has prank control, the location of the user is located, the user closest to the controlled appliance is found according to the location of the user, and the voice control command of the user is executed.
5. The smart home natural language control method according to any one of claims 1 to 4, wherein in the step (22), the method for locating the position of the user comprises: the IPV6 address positioning is adopted, the IPV6 address of each electric appliance is bound with the actual space address where the electric appliance is located, the IPV6 address of each voice receiving device is bound with the actual space address where the electric appliance is located, the position where a user is located is judged according to the IPV6 address of the voice receiving device which receives voice control signals, and then the electric appliance which is closest to the position of the user is correspondingly controlled to execute a corresponding control command.
6. The intelligent home natural language control method according to claim 5, wherein in the step (22), if a plurality of voice receiving devices receive the voice control command at the same time, the voice receiving device with the strongest received voice signal strength is compared according to the strength of the voice signal received by each voice receiving device, and the position of the user is determined according to the IPV6 address of the voice receiving device.
7. The smart home natural language control method according to any one of claims 1 to 4, further comprising a step of presetting a trigger vocabulary for triggering a voice control operation before the step (1), and performing the step (1) or the subsequent steps when a user utters a voice of the trigger vocabulary.
8. The smart home natural language control method according to any one of claims 1 to 4, wherein in the step (3), if the voice command does not include specific parameter information, the user command is executed according to default parameters, and each appliance is provided with default parameters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410695637.7A CN105700389B (en) | 2014-11-27 | 2014-11-27 | Intelligent home natural language control method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410695637.7A CN105700389B (en) | 2014-11-27 | 2014-11-27 | Intelligent home natural language control method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105700389A CN105700389A (en) | 2016-06-22 |
| CN105700389B true CN105700389B (en) | 2020-08-11 |
Family
ID=56294893
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410695637.7A Active CN105700389B (en) | 2014-11-27 | 2014-11-27 | Intelligent home natural language control method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105700389B (en) |
Families Citing this family (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190258318A1 (en) * | 2016-06-28 | 2019-08-22 | Huawei Technologies Co., Ltd. | Terminal for controlling electronic device and processing method thereof |
| CN106452987B (en) * | 2016-07-01 | 2019-07-30 | 广东美的制冷设备有限公司 | A kind of sound control method and device, equipment |
| CN106325127B (en) * | 2016-08-30 | 2019-03-08 | 广东美的制冷设备有限公司 | It is a kind of to make the household electrical appliances expression method and device of mood, air-conditioning |
| CN106125567B (en) * | 2016-08-30 | 2019-11-08 | 广东美的制冷设备有限公司 | A kind of mthods, systems and devices based on user instruction identification household electrical appliances |
| KR102573383B1 (en) * | 2016-11-01 | 2023-09-01 | 삼성전자주식회사 | Electronic apparatus and controlling method thereof |
| CN106448658B (en) * | 2016-11-17 | 2019-09-20 | 海信集团有限公司 | The sound control method and intelligent domestic gateway of smart home device |
| CN106647821A (en) * | 2016-12-27 | 2017-05-10 | Tcl数码科技（深圳）有限责任公司 | Indoor projection following control method and system |
| CN108370492B (en) * | 2017-01-20 | 2021-08-20 | 华为技术有限公司 | Indoor positioning method and equipment |
| CN106647318A (en) * | 2017-02-27 | 2017-05-10 | 宁夏凯速德科技有限公司 | Method and system for user authority automatic adjusting based on environment state in smart home |
| CN107104942B (en) * | 2017-03-08 | 2019-12-20 | 芜湖美智空调设备有限公司 | Internet of things user management method and device |
| US10057715B1 (en) * | 2017-03-29 | 2018-08-21 | Honeywell International Inc. | Systems and methods for selecting an optimal device in a home security or automation system for presenting a notification or alert |
| CN108926198A (en) * | 2017-05-27 | 2018-12-04 | 芜湖美的厨房电器制造有限公司 | bathroom mirror and its control method |
| CN107255929A (en) * | 2017-07-07 | 2017-10-17 | 四川云图瑞科技有限公司 | Building based on virtual reality technology, household interactive system |
| CN107528753B (en) * | 2017-08-16 | 2021-02-26 | 捷开通讯(深圳)有限公司 | Intelligent household voice control method, intelligent equipment and device with storage function |
| CN107579883A (en) * | 2017-08-25 | 2018-01-12 | 上海肖克利信息科技股份有限公司 | Distributed pickup intelligent home furnishing control method |
| CN109493871A (en) * | 2017-09-11 | 2019-03-19 | 上海博泰悦臻网络技术服务有限公司 | The multi-screen voice interactive method and device of onboard system, storage medium and vehicle device |
| CN107544272B (en) * | 2017-09-18 | 2021-01-08 | 广东美的制冷设备有限公司 | Terminal control method, device and storage medium |
| CN107479397A (en) * | 2017-09-25 | 2017-12-15 | 千寻位置网络有限公司 | Intelligent household voice control system and method based on positional information |
| TWI656789B (en) * | 2017-12-29 | 2019-04-11 | 瑞軒科技股份有限公司 | Video control system |
| CN108470568B (en) * | 2018-01-22 | 2021-03-23 | 科大讯飞股份有限公司 | Intelligent device control method and device, storage medium and electronic device |
| CN108540357B (en) * | 2018-03-30 | 2020-10-09 | 深圳市沃特沃德股份有限公司 | Voice control method and device and sound equipment |
| EP3550939A1 (en) * | 2018-04-02 | 2019-10-09 | Signify Holding B.V. | System and methods for augmenting voice commands using connected lighting systems |
| CN109274562B (en) * | 2018-09-27 | 2020-08-04 | 珠海格力电器股份有限公司 | Voice instruction execution method and device, intelligent household appliance and medium |
| CN110648586B (en) | 2018-11-21 | 2022-04-01 | Oppo广东移动通信有限公司 | Electronic equipment |
| CN109981616B (en) * | 2019-03-12 | 2021-07-13 | 绿盟科技集团股份有限公司 | Voice attack detection method and device and network equipment |
| CN110189453A (en) * | 2019-06-15 | 2019-08-30 | 泉州昌荣贸易有限公司 | Smart home employs the control method of system |
| JP7392337B2 (en) * | 2019-09-10 | 2023-12-06 | 富士フイルムビジネスイノベーション株式会社 | Information processing equipment and programs |
| EP3836582B1 (en) * | 2019-12-09 | 2024-01-31 | Google LLC | Relay device for voice commands to be processed by a voice assistant, voice assistant and wireless network |
| CN111028839B (en) * | 2019-12-20 | 2022-09-23 | 思必驰科技股份有限公司 | Smart home control method and device and electronic equipment |
| CN112656309A (en) * | 2020-12-25 | 2021-04-16 | 北京小狗吸尘器集团股份有限公司 | Function execution method and device of sweeper, readable storage medium and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101794120A (en) * | 2010-02-09 | 2010-08-04 | 张文中 | Voice control system used for fuzzy control of household appliances |
| CN103916875A (en) * | 2014-04-24 | 2014-07-09 | 山东大学 | Management and planning system of multi-class control terminals based on WIFI wireless network |
| CN103914039A (en) * | 2013-12-31 | 2014-07-09 | 海尔集团公司 | Control method and system for household appliances |
| CN104093050A (en) * | 2014-06-12 | 2014-10-08 | 华南理工大学 | Controlled terminal controlled decision-making method and apparatus based on multiple intelligent remote controllers |
| CN104125262A (en) * | 2013-04-28 | 2014-10-29 | 海尔集团公司 | Household appliance control system and data analysis method thereof |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH10143190A (en) * | 1996-11-11 | 1998-05-29 | Matsushita Electric Ind Co Ltd | Speech recognition device |
| GB2409750B (en) * | 2004-01-05 | 2006-03-15 | Toshiba Res Europ Ltd | Speech recognition system and technique |
| CN101201818A (en) * | 2006-12-13 | 2008-06-18 | 李萍 | Method for calculating language structure, executing participle, machine translation and speech recognition using HMM |
| US20120084248A1 (en) * | 2010-09-30 | 2012-04-05 | Microsoft Corporation | Providing suggestions based on user intent |
| KR20140028174A (en) * | 2012-07-13 | 2014-03-10 | 삼성전자주식회사 | Method for recognizing speech and electronic device thereof |
-
2014
- 2014-11-27 CN CN201410695637.7A patent/CN105700389B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101794120A (en) * | 2010-02-09 | 2010-08-04 | 张文中 | Voice control system used for fuzzy control of household appliances |
| CN104125262A (en) * | 2013-04-28 | 2014-10-29 | 海尔集团公司 | Household appliance control system and data analysis method thereof |
| CN103914039A (en) * | 2013-12-31 | 2014-07-09 | 海尔集团公司 | Control method and system for household appliances |
| CN103916875A (en) * | 2014-04-24 | 2014-07-09 | 山东大学 | Management and planning system of multi-class control terminals based on WIFI wireless network |
| CN104093050A (en) * | 2014-06-12 | 2014-10-08 | 华南理工大学 | Controlled terminal controlled decision-making method and apparatus based on multiple intelligent remote controllers |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105700389A (en) | 2016-06-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105700389B (en) | Intelligent home natural language control method | |
| US11929844B2 (en) | Customized interface based on vocal input | |
| US10985936B2 (en) | Customized interface based on vocal input | |
| JP6823085B1 (en) | Position-based voice recognition system by voice command (A Location Based Voice Recognition System System Using A Voice Command) | |
| WO2019205134A1 (en) | Smart home voice control method, apparatus, device and system | |
| EP3599605A1 (en) | Home appliance and speech recognition server system using artificial intelligence and method for controlling thereof | |
| US20200232671A1 (en) | Device control system | |
| JP6140214B2 (en) | CONTROL DEVICE, CONTROL DEVICE CONTROL METHOD, CONTROL SYSTEM, ENVIRONMENT CONTROL DEVICE, AND CONTROL PROGRAM | |
| CN109347709B (en) | Intelligent equipment control method, device and system | |
| CN109547308A (en) | A kind of control method of smart home, device, storage medium and server | |
| CN106297781A (en) | Control method and controller | |
| CN111754997B (en) | Control device and operation method thereof, and voice interaction device and operation method thereof | |
| WO2019202666A1 (en) | Apparatus control system and apparatus control method | |
| CN110767225A (en) | Voice interaction method, device and system | |
| CN111477230A (en) | Intelligent sound box system, control method of intelligent sound box system and storage medium | |
| CN114120996A (en) | Voice interaction method and device | |
| CN111431776A (en) | Information configuration method, device and system | |
| CN112751734A (en) | Household appliance control method based on cleaning robot, cleaning robot and chip | |
| US20220270601A1 (en) | Multi-modal smart audio device system attentiveness expression | |
| EP3779618B1 (en) | Smart apparatus control method, apparatus, computer storage medium, and smart apparatus control apparatus | |
| EP3878243A1 (en) | Adapting a lighting control interface based on an analysis of conversational input | |
| CN113568320A (en) | Device control method and device, electronic device and computer-readable storage medium | |
| CN111256347B (en) | Recommendation terminal, receiving terminal, pushing method of comfortable temperature zone and storage medium | |
| CN117882130A (en) | Terminal equipment and server for voice control | |
| CN114815635A (en) | Computer readable storage medium, intelligent panel and voice interaction method thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20201106 Address after: 266101 No. 1 Haier Road, Laoshan District, Shandong, Qingdao Patentee after: QINGDAO HAIER SMART TECHNOLOGY R&D Co.,Ltd. Patentee after: Haier Smart Home Co., Ltd. Address before: 266101 No. 1 Haier Road, Laoshan District, Shandong, Qingdao Patentee before: QINGDAO HAIER SMART TECHNOLOGY R&D Co.,Ltd. |
|
| TR01 | Transfer of patent right |