CN115240668B - Voice interaction home control method and robot - Google Patents
Voice interaction home control method and robot Download PDFInfo
- Publication number
- CN115240668B CN115240668B CN202210785096.1A CN202210785096A CN115240668B CN 115240668 B CN115240668 B CN 115240668B CN 202210785096 A CN202210785096 A CN 202210785096A CN 115240668 B CN115240668 B CN 115240668B
- Authority
- CN
- China
- Prior art keywords
- control instructions
- instruction
- control
- instruction set
- instructions
- 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
- 230000003993 interaction Effects 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000007717 exclusion Effects 0.000 claims abstract description 42
- 238000012423 maintenance Methods 0.000 claims description 9
- 230000002452 interceptive effect Effects 0.000 claims 6
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000009423 ventilation 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
-
- 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
- G10L15/26—Speech to text systems
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/2803—Home automation networks
- H04L12/2816—Controlling appliance services of a home automation network by calling their functionalities
- H04L12/282—Controlling appliance services of a home automation network by calling their functionalities based on user interaction within the home
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Automation & Control Theory (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Manipulator (AREA)
Abstract
The disclosure relates to the technical field of application services of the internet of things, in particular to a voice interaction home control method and a robot. The voice interaction home control method comprises the following steps: obtaining a rule base, wherein the rule base comprises a mutually exclusive rule base; acquiring legal control instructions through voice interaction with a user; acquiring a constant hold instruction from the plurality of control instructions; dividing the plurality of control instructions to obtain a first instruction set and a second instruction set; dividing the first instruction set into one or more execution combinations according to the mutual exclusion rule base, wherein control instructions in the execution combinations are mutually exclusive; executing the execution combination of the first instruction set one by one; all control instructions in the second instruction set are executed after the first instruction set is completed. The method and the device can give the execution sequence of a plurality of control instructions obtained by single-round voice interaction, do not need a user to provide the execution sequence of the control instructions at the same time, and can control household equipment more conveniently.
Description
Technical Field
The disclosure relates to the technical field of application services of the internet of things, in particular to a voice interaction home control method and a robot.
Background
The household control robot is used in an intelligent household environment, a user sends a control instruction to the household control robot through voice interaction, and the household control robot respectively controls all household devices in the intelligent household environment according to the control instruction.
In the prior art, if a user needs to execute a plurality of control instructions by the home control robot, a plurality of rounds of dialogue are required to be repeatedly started, and the user is required to wake up the home control robot repeatedly, so that inconvenience is brought to control of home equipment.
Disclosure of Invention
In order to solve the technical problems or at least partially solve the technical problems, the present disclosure provides a voice interaction home control method, which can control home equipment more conveniently.
In a first aspect, the present disclosure provides a method for controlling a voice interaction home, including:
obtaining a rule base, wherein the rule base comprises a mutual exclusion rule base which comprises a combination of control instructions which cannot be executed simultaneously;
acquiring legal control instructions through voice interaction with a user;
obtaining a constant hold instruction from the plurality of control instructions, wherein the constant hold instruction is a control instruction with unlimited execution time;
dividing the plurality of control instructions according to a mutual exclusion rule base and a constant holding instruction to obtain a first instruction set and a second instruction set, wherein the first instruction set comprises all control instructions which are repelled by the constant holding instruction in the plurality of control instructions, and the second instruction set comprises all control instructions which are not mutually exclusive with the constant holding instruction in the plurality of control instructions;
dividing the first instruction set into one or more execution combinations according to the mutual exclusion rule base, wherein control instructions in the execution combinations are mutually exclusive;
executing the execution combination of the first instruction set one by one;
all control instructions in the second instruction set are executed after the first instruction set is completed.
Optionally, acquiring a single hold command from the plurality of control commands;
the voice interaction home control method further comprises the following steps:
dividing the second instruction set into execution combinations within two according to the mutual exclusion rule base;
executing all control instructions in the second instruction set after completing the first instruction set, including:
after the first instruction set is completed, the execution combination of the single constant maintenance instruction included in the second instruction set is executed first, and then the rest execution combination is executed.
Optionally, acquiring a single hold command from the plurality of control commands includes:
and consulting the mutual exclusion rule base, and selecting a constant hold instruction with the least mutual exclusion number with other control instructions.
Optionally, obtaining legal multiple control instructions through voice interaction includes:
acquiring a plurality of control instructions through voice interaction;
and checking whether the constant holding instructions in the plurality of control instructions are mutually exclusive according to a mutual exclusion rule base, and if not, determining that the constant holding instructions are legal.
Optionally, the rule base further includes a parallel rule base, where the parallel rule base includes a combination of control instructions that can be executed simultaneously and a combination weight table of corresponding weights;
executing the execution combination of the first instruction set in an execution combination unit, comprising:
and after the combination weight table is consulted and the execution sequence of the execution combination of the first instruction set is ordered according to the size of the weight, the execution combination is used as a unit to execute the execution combination of the first instruction set one by one according to the execution sequence.
Optionally, the weights of the combinations including the control instructions in the combination weight table are updated according to a preset function according to the number of times that the user has once said control instructions.
Optionally, the user includes a plurality of user roles, the parallel rule base includes a combination weight table of different user roles, and the voice interaction home control method further includes:
acquiring a user role sending out a control instruction;
looking up a combined weight table corresponding to the user role according to the obtained user role,
and ordering the execution sequence of the execution combination of the first instruction set according to the combination weight table of the corresponding user role.
Optionally, according to the number of times that the different user roles have once spoken the control instruction, the weights of the combinations including the control instruction in the combination weight table of the different user roles are updated according to a preset function.
Optionally, the preset function includes:
W x =W 1 +ln（x+1）
the W is x Weights representing combinations of control instructions having x times over which said control instructions occur, W 1 Representing the initial weights of the combinations with the control instructions.
In a second aspect, the present disclosure provides a home control robot, comprising:
the voice interaction module is used for carrying out voice interaction with a user to obtain legal control instructions;
the rule base comprises a mutually exclusive rule base, wherein the mutually exclusive rule base comprises a combination of control instructions which cannot be executed simultaneously;
the constant holding instruction acquisition module is used for acquiring a constant holding instruction from the plurality of control instructions, wherein the constant holding instruction is a control instruction with unlimited execution time;
the instruction set dividing module is used for dividing the plurality of control instructions according to the mutual exclusion rule base and the normal holding instructions to obtain a first instruction set and a second instruction set, wherein the first instruction set comprises all control instructions which are mutually exclusive with the normal holding instructions in the plurality of control instructions, and the second instruction set comprises all control instructions which are not mutually exclusive with the normal holding instructions in the plurality of control instructions;
the execution combination dividing module is used for dividing the first instruction set into one or more execution combinations according to the mutual exclusion rule base, and control instructions in the execution combinations are mutually exclusive;
the execution module is used for executing the execution combination of the first instruction set one by one and executing all control instructions in the second instruction set after the first instruction set is completed;
and the control module is used for controlling the corresponding household equipment according to the content of the control instruction when the control instruction is executed.
Compared with the prior art, the technical scheme provided by the embodiment of the disclosure has the following advantages:
compared with the prior art, the voice interaction home control method has the advantages that the execution sequence of a plurality of control instructions obtained by single-round dialogue can be given, the user is not required to give the execution sequence of the control instructions while giving the plurality of control instructions, the user can more smoothly say all the control instructions, and the user can more conveniently control home equipment.
Drawings
Fig. 1 is an application scenario diagram provided in an embodiment of the present disclosure;
fig. 2 is a schematic flow chart of a voice interaction home control method according to an embodiment of the disclosure;
fig. 3 is a second flowchart of a voice interaction home control method according to an embodiment of the disclosure;
fig. 4 is a schematic structural diagram of a home control robot according to an embodiment of the present disclosure.
Detailed Description
In order that the above objects, features and advantages of the present disclosure may be more clearly understood, a further description of aspects of the present disclosure will be provided below. It should be noted that, without conflict, the embodiments of the present disclosure and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure, but the present disclosure may be practiced otherwise than as described herein; it will be apparent that the embodiments in the specification are only some, but not all, embodiments of the disclosure.
Fig. 1 is an application scenario diagram provided by an embodiment of the present disclosure, and a voice interaction home control method may be applied to the smart home scenario described in fig. 1. As shown in fig. 1, a user 11 completes single-round voice interaction with a home control robot 12 to issue a plurality of control instructions to the home control robot 12, and after the home control robot 12 obtains the plurality of control instructions issued by the user 11, the plurality of control instructions are grouped and sequenced according to a preset voice interaction home control method to give a feasible execution sequence of the control instructions. The home control robot 12 executes the control instructions in the execution order, and controls the corresponding home devices 13 in accordance with the content of the executed control instructions.
Embodiment one:
fig. 2 is a schematic flow chart of a voice interaction home control method according to an embodiment of the disclosure. As shown in fig. 2, the flow of the voice interaction home control method provided by the embodiment of the disclosure includes:
s101: and obtaining a rule base, wherein the rule base comprises a mutually exclusive rule base which comprises a combination of control instructions which cannot be executed simultaneously.
Specifically, the mutually exclusive rule base is a data table recording a combination of all control instructions that cannot be executed simultaneously. For example:
the control instruction can only select { A, b, c, d, E } from the event set;
that is, the control instruction has only 5 possible values A, b, c, d and E, and the mutually exclusive rule base is:
it should be appreciated that the present embodiment presents the mutually exclusive rule base in tabular form for ease of understanding. However, in an actual data storage structure, mutually exclusive control instructions are stored in combination in the data table of a particular database.
The control instruction a and the control instruction E are normal hold instructions, and the normal hold instructions refer to control instructions whose execution time is not limited. For example, the control instruction a is to turn on the air conditioner.
Wherein, the control instructions b, c and d are control instructions for limiting the execution time. For example, the control command b is to turn on the fresh air system for x minutes.
S102: and acquiring legal control instructions through voice interaction.
Specifically, the home control robot completes voice interaction with a user through voice playing and receiving equipment by utilizing a voice recognition technology, and obtains a plurality of control instructions issued by the user.
And then the home control robot checks whether the constant hold instructions in the plurality of control instructions are mutually exclusive according to the mutually exclusive rule base, and if not, the constant hold instructions are legal.
If the mutual exclusion is determined to be illegal, discarding the obtained control instructions.
For example, the home control robot obtains the control instruction A, b, c, d, E issued by the user, obtains the constant hold instructions a and E in the control instruction, refers to the mutual exclusion rule base, does not have the record of mutual exclusion of the constant hold instructions a and E, and determines that a plurality of control instructions issued by the user are legal. In contrast, the judgment is illegal.
The home control robot is provided with a processor, and the voice playing and receiving equipment comprises a microphone and a loudspeaker. The microphone is used for collecting sound waves of a user, converting the sound waves into electric signals and inputting the electric signals to the processor of the home control robot for processing. For the purpose of stereo acquisition or noise reduction, a plurality of microphones can be arranged at different positions of the home control robot respectively. The speaker is then used to convert the electrical signals from the processor into sound waves. In other embodiments, the microphone may also be an array microphone or an omni-directional pickup microphone.
The processor of the home control robot analyzes the user voice information received by the microphone to obtain a plurality of control instructions by utilizing the voice analysis technology of the existing mass-information flying stock limited company.
S103: and acquiring a constant hold instruction from the plurality of control instructions, wherein the constant hold instruction is a control instruction with unlimited execution time.
Specifically, all the hold instructions are selected from a plurality of control instructions. For example, the control instruction A, b, c, d, E acquires the hold instructions a and E in the control instruction.
S104: dividing the plurality of control instructions according to the mutual exclusion rule base and the normal holding instructions to obtain a first instruction set and a second instruction set, wherein the first instruction set comprises all control instructions which are repelled by the normal holding instructions in the plurality of control instructions, and the second instruction set comprises all control instructions which are not mutually exclusive with the normal holding instructions in the plurality of control instructions.
Specifically, the mutual exclusion relation between a plurality of constant holding instructions and the rest of the plurality of control instructions is respectively consulted, and the control instructions mutually exclusive with the constant holding instructions and not mutually exclusive are divided into two instruction sets.
For example: often keeping instruction a mutually exclusive to control instructions b and d. Often keeping instruction E mutually exclusive to control instruction c. The first instruction set is { control instruction b, control instruction c, control instruction d }, and the second instruction set is { control instruction a, control instruction E }.
S105: and dividing the first instruction set into one or more execution combinations according to the mutual exclusion rule base, wherein control instructions in the execution combinations are mutually exclusive.
Specifically, it is referred whether the control instructions in the first instruction set are mutually exclusive, and if so, the control instructions are divided into different execution combinations.
For example: the first instruction set is { control instruction b, control instruction c and control instruction d }, the mutual exclusion rule base is consulted to find that the control instruction b and the control instruction d are mutually exclusive, and the control instruction b and the control instruction c are mutually exclusive, so that the first instruction set is divided into two execution combinations { control instruction b }, { control instruction c and control instruction d }.
S106: the execution combination of the first instruction set is executed one by one.
Specifically, the execution combination in the first instruction set is executed one by one in the execution combination unit. That is, only if all control instructions in a certain execution combination are executed, all control instructions of the next execution combination can be executed.
For example, the execution combination { control instruction b } is completed first, and only the control instruction b in the execution completed execution combination can execute the next execution combination { control instruction c, control instruction d }. If the execution combination has a plurality of control instructions, for example { control instruction c, control instruction d }, the control instructions c, d may be executed in parallel, and the execution time of the execution combination is the longest execution time of the two control instructions.
In a preferred embodiment, the rule base further comprises a parallel rule base comprising a combination of control instructions and a combination weight table of corresponding weights that are simultaneously executable.
For example:
the combining weight table provided in the embodiments of the present disclosure shows only a part of them for ease of understanding.
And after the combination weight table is consulted and the execution sequence of the execution combination of the first instruction set is ordered according to the size of the weight, the execution combination of the first instruction set is executed according to the execution sequence by taking the execution combination as a unit.
For example: after the execution combinations in the first order combination are ordered according to the rule that the weight is big-small, the execution sequence of the first instruction set is that the execution combination { control instruction c and control instruction d } is completed first, and then the execution combination { control instruction b } is completed.
In the preferred embodiment, the execution sequence of the execution combinations in the first execution set may be ordered by presetting the combination weight table, so that the execution sequence of the execution combinations in the first execution set may better meet the requirements of the user.
In the preferred embodiment, the parallel rule base can also be updated according to a preset function according to the number of times the user has once spoken the control instructions, including the weights of the combinations of control instructions.
The preset function includes:
W x =W 1 +ln（x+1）
the Wx represents the weight of the combination of control instructions when the control instructions occur x times, and W1 represents the initial weight of the combination of control instructions.
For example, in the past use, the user has once said control command c a total of 5 times, and the combination { control command c, control command d } including control command c has an initial weight of 5, and when control command c appears 5 times, the combination has a weight of 5+ln (6), that is, a weight of about 6.79.
In the preferred embodiment, the weights of the combination weight table may be updated according to the number of times used by the user, so that the execution sequence of the execution combination in the first execution set may better conform to the requirement of the user.
Also in the preferred embodiment, a logarithmic function with a base greater than 1 is selected as the weighted variation. The preferred embodiment utilizes the characteristic that the logarithmic function grows obviously at the beginning and slowly at the subsequent dependent variable, can quickly learn the weight which is more satisfactory to the user at the beginning and can maintain the weight of the combined weight table to be stable at the subsequent, avoids the excessive variance of the combined weight comprising the common control instruction and the combined weight not comprising the common control instruction, and is beneficial to the subsequent developer to redesign the initial weight in the combined weight table and is convenient to maintain.
In another preferred embodiment, the user comprises a plurality of user roles. For example: father, mother and child.
And the parallel rule base is respectively provided with a combination weight table of different user roles according to the different user roles.
Specifically, the home control robot also obtains a user role sending a control instruction according to the voiceprint. The acquisition of different user roles according to voiceprint recognition is a prior art in the art, and is not described in detail herein, and in the preferred embodiment, the voiceprint recognition technology of the cosigneous femto is used.
And then, referring to a combination weight table corresponding to the user role according to the obtained user role, sequencing the execution sequence of the execution combination of the first instruction set according to the combination weight table corresponding to the user role, and executing the execution combination in the first instruction set one by one according to the execution sequence.
Further, in the preferred embodiment, the weights in the combination weight table of different user roles can be updated according to the times that the different user roles speak the control instructions.
The implementation process and principle are the same as those of the above preferred embodiment, and will not be described herein.
S107: all control instructions in the second instruction set are executed after the first instruction set is completed.
For example, after all control instructions in the first instruction set { control instruction b, control instruction c, control instruction d } are completed, control instruction a and control instruction E in the second instruction set are executed in parallel.
In the intelligent home scene, the distribution positions of the home devices are wide and the number of the home devices is numerous, so that a home control robot is required to provide a unified interaction interface, and interaction between each home device and a user is facilitated. The home control robot generally establishes communication with each home device through a wired or wireless connection mode, and sends a control signal to control each home device.
The voice recognition technology in the prior art is already perfect, and all control instructions uttered by a user in a sentence can be recognized and obtained in a single dialogue. However, even if the home control robot can recognize a plurality of control instructions in a single-round dialogue, the home control robot does not know the execution sequence of the plurality of control instructions, and the plurality of control instructions are usually executed directly, and there is a conflict between the plurality of control instructions.
Or the home control robot directly executes the control instructions one by one according to the sequence of the control instructions which are spoken by the user, but for the user, in a single dialogue, the user needs to memorize and provide the control instructions and speak the control instructions in sequence, so that the user is very easy to speak the control instructions wrongly or can not speak all the instructions smoothly.
Therefore, the prior art is difficult to realize that the home control robot executes a plurality of control instructions after a single-round dialogue.
The present disclosure provides a voice interaction home control method, and the inventor notes that a plurality of control instructions issued by a user generally include a constant hold instruction, where the constant hold instruction is generally a core instruction of the plurality of control instructions.
That is, among the plurality of control commands normally spoken by the user, the control command which cannot be executed simultaneously with the normal maintenance command is generally a pre-operation for the normal maintenance command, for example, the fresh air system is turned on for ventilation before the air conditioner is turned on, and the lamp is turned off before the projector is turned on.
Even if the plurality of control instructions issued by the user do not include the constant hold instruction, the method of dividing the plurality of control instructions into a plurality of execution combinations directly according to the first execution instruction set may divide the plurality of control instructions and execute the plurality of control instructions in the execution combination unit to obtain an execution order of the plurality of control instructions without collision.
The present disclosure utilizes a constant hold instruction and a mutually exclusive rule base to divide a plurality of execution instructions into a plurality of execution combinations, and the execution combinations are executed as units, so that the execution instructions do not conflict with each other. And the control instructions in the same execution combination can be executed in parallel, so that a plurality of control instructions do not need to be executed one by one, and the time is saved. Therefore, the voice interaction home control method can give out the execution sequence of a plurality of control instructions obtained by single-round dialogue, and the user does not need to give out the execution sequence of the control instructions while giving out the plurality of control instructions, so that the user can more smoothly say all the control instructions, and the user can more conveniently control home equipment.
Embodiment two:
fig. 3 is a second flowchart of a voice interaction home control method according to an embodiment of the disclosure. The embodiment of the present disclosure is illustrated by way of example of embodiment one, as shown in fig. 3, and includes the following steps:
s201: and obtaining a rule base, wherein the rule base comprises a mutually exclusive rule base which comprises a combination of control instructions which cannot be executed simultaneously.
S202: and acquiring legal control instructions through voice interaction with the user.
The steps and illustrations that differ from embodiment one include:
s203: and acquiring a single constant-hold instruction from the plurality of control instructions, wherein the constant-hold instruction is a control instruction with unlimited execution time.
Specifically, from among the plurality of control instructions, only one constant hold instruction needs to be selected. For example, the control instruction A, b, c, d, E acquires the hold instruction a or E among the control instructions.
In a preferred embodiment, selecting a single hold command further has the steps of:
and consulting the mutual exclusion rule base to obtain the constant maintenance instruction with the minimum mutual exclusion quantity with other control instructions in the constant maintenance instructions.
For example: often keeping instruction a mutually exclusive to control instructions b and d. Often keeping instruction E mutually exclusive to control instruction c. And if the number of mutual exclusion of the normal holding instruction E and other control instructions is smaller than that of the normal holding instruction A, acquiring the normal holding instruction E from a plurality of control instructions.
In a preferred embodiment, the present disclosure selects the constant hold instruction with the least mutual exclusion with other control instructions for the basis of the subsequent divided instruction set, so that the number of control instructions in the first instruction set of the subsequent division is smaller. The fewer the number of control instructions present in the first instruction set, the lower the probability that a control instruction may be present in the first instruction set that takes a longer time to complete. Thus, in a preferred embodiment, instructions in the first instruction set may be more easily completed in a short time to quickly execute the hold instructions in the second instruction set. The hold instructions are generally used as core instructions specified by the user, and in a preferred embodiment, the hold instructions can be executed faster, thereby providing a better use experience for the user.
S204: dividing the plurality of control instructions according to the mutual exclusion rule base and the normal holding instructions to obtain a first instruction set and a second instruction set, wherein the first instruction set comprises all control instructions which are repelled by the normal holding instructions in the plurality of control instructions, and the second instruction set comprises all control instructions which are not mutually exclusive with the normal holding instructions in the plurality of control instructions.
For example: in step S203, a normal hold command E is selected, and a plurality of control commands are divided according to the normal hold command and the mutual exclusion rule base, wherein the normal hold command E is mutually exclusive to the control command c. The first instruction set is control instruction c and the second instruction set is control instruction a, control instruction b, control instruction d, control instruction E.
S205: and dividing the first instruction set into one or more execution combinations according to the mutual exclusion rule base, wherein control instructions in the execution combinations are mutually exclusive.
For example: the first instruction set { control instruction c } is divided into a single execution combination { control instruction c }.
S206: the second instruction set is divided into two execution combinations according to the mutual exclusion rule base.
For example: the second instruction set is { control instruction A, control instruction b, control instruction d, control instruction E }, wherein the constant keeping instruction A mutually exclusive with the control instructions b and d, the second instruction set is divided into two execution combinations { control instruction b, control instruction d, control instruction E } and { control instruction A }.
S207: the execution combination of the first set of instructions is executed in an execution combination unit.
S208: all control instructions in the second instruction set are executed after the first instruction set is completed.
Specifically, the second instruction set is executed first, including the execution combination of the single constant-hold instruction, and then the remaining execution combination is executed.
For example: the execution combination { control instruction b, control instruction d, control instruction E } including the constant hold instruction E for dividing the first instruction set and the second instruction set is completed first, and then the execution combination { control instruction a } is completed. After the normal hold instruction starts to execute, the execution of the control instruction is regarded as complete.
The embodiments of the present disclosure may execute to hold instructions faster than the embodiments. Since the first execution instruction set and the second execution instruction set need to be divided according to all of the hold instructions in the first embodiment. For one embodiment, when the number of hold instructions is greater, the number of conflicting control instructions is greater, resulting in substantially all hold instructions being in the second instruction set and the remaining control instructions being in the first instruction set. Thus, for one embodiment, most of the control instructions need to be completed to execute the hold instruction, which is typically the core instruction specified by the user. Therefore, in the first embodiment, the core instruction desired by the user cannot be executed in time, and the user has poor experience.
According to the embodiment of the disclosure, the plurality of control instructions are divided by selecting one constant hold instruction, so that the number of the control instructions in the first instruction set is reduced, and the instructions in the first instruction set can be finished more easily in a short time, so that the constant hold instructions in the second instruction set can be executed rapidly. The normal hold instruction is generally used as a core instruction appointed by a user, can be executed faster, and can bring better use experience to the user.
Fig. 4 is a schematic structural diagram of a home control robot according to an embodiment of the present disclosure. As shown in fig. four, the embodiment of the present disclosure provides a home control robot including:
a voice interaction module 41, configured to obtain legal multiple control instructions through voice interaction with a user;
a rule base 42 comprising a mutually exclusive rule base comprising a combination of control instructions that are not executable simultaneously;
a constant hold instruction obtaining module 43, configured to obtain a constant hold instruction from the plurality of control instructions, where the constant hold instruction is a control instruction whose execution time is not limited;
the instruction set dividing module 44 is configured to divide the plurality of control instructions according to a mutual exclusion rule base and a normal holding instruction, so as to obtain a first instruction set and a second instruction set, where the first instruction set includes all control instructions that are mutually exclusive to the normal holding instruction in the plurality of control instructions, and the second instruction set includes all control instructions that are not mutually exclusive to the normal holding instruction in the plurality of control instructions;
an execution combination dividing module 45, configured to divide the first instruction set into one or more execution combinations according to the mutual exclusion rule base, where control instructions in the execution combinations are mutually exclusive;
the execution module 46 is configured to execute the execution combination of the first instruction set one by one, and execute all control instructions in the second instruction set after completing the first instruction set;
the control module 47 is configured to control the corresponding home device according to the content of the control instruction when the control instruction is executed.
It should be noted that in this document, relational terms such as "first" and "second" and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The foregoing is merely a specific embodiment of the disclosure to enable one skilled in the art to understand or practice the disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown and described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (9)
1. The voice interaction home control method is characterized by comprising the following steps:
obtaining a rule base, wherein the rule base comprises a mutual exclusion rule base which comprises a combination of control instructions which cannot be executed simultaneously;
acquiring legal control instructions through voice interaction with a user;
obtaining a constant hold instruction from the plurality of control instructions, wherein the constant hold instruction is a control instruction with unlimited execution time;
dividing the plurality of control instructions according to a mutual exclusion rule base and a normal holding instruction to obtain a first instruction set and a second instruction set, wherein the first instruction set comprises all control instructions which are repelled by the normal holding instruction in the plurality of control instructions, and the second instruction set comprises all control instructions and normal holding instructions which are not mutually exclusive with the normal holding instruction in the plurality of control instructions;
dividing the first instruction set into one or more execution combinations according to the mutual exclusion rule base, wherein control instructions in the execution combinations are mutually exclusive;
executing the execution combination of the first instruction set one by one;
executing all control instructions in the second instruction set after the first instruction set is completed;
obtaining legal control instructions through voice interaction, wherein the legal control instructions comprise:
acquiring a plurality of control instructions through voice interaction;
and checking whether the constant holding instructions in the plurality of control instructions are mutually exclusive according to a mutual exclusion rule base, and if not, determining that the constant holding instructions are legal.
2. The voice interaction home control method is characterized by comprising the following steps:
obtaining a rule base, wherein the rule base comprises a mutual exclusion rule base which comprises a combination of control instructions which cannot be executed simultaneously;
acquiring legal control instructions through voice interaction with a user;
acquiring a single constant-hold instruction from the plurality of control instructions, wherein the constant-hold instruction is a control instruction with unlimited execution time;
dividing the plurality of control instructions according to a mutual exclusion rule base and the single normal holding instruction to obtain a first instruction set and a second instruction set, wherein the first instruction set comprises all control instructions which are repelled from the single normal holding instruction in the plurality of control instructions, and the second instruction set comprises all control instructions which are not mutually exclusive from the single normal holding instruction in the plurality of control instructions and the single normal holding instruction;
dividing the first instruction set into one or more execution combinations according to the mutual exclusion rule base, wherein control instructions in the execution combinations are mutually exclusive;
executing the execution combination of the first instruction set one by one;
executing all control instructions in the second instruction set after the first instruction set is completed;
obtaining legal control instructions through voice interaction, wherein the legal control instructions comprise:
acquiring a plurality of control instructions through voice interaction;
checking whether the constant hold instructions in the plurality of control instructions are mutually exclusive according to a mutual exclusion rule base, and if not, determining that the constant hold instructions are legal;
the voice interaction home control method further comprises the following steps:
dividing the second instruction set into execution combinations within two according to the mutual exclusion rule base, wherein the dividing the second instruction set into execution combinations within two according to the mutual exclusion rule base comprises:
acquiring other constant maintenance instructions except the single constant maintenance instruction from a second instruction set, dividing the other constant maintenance instructions mutually exclusive with the control instruction with limited execution time into one execution combination, and dividing the rest control instructions of the second instruction set into another execution combination;
executing all control instructions in the second instruction set after completing the first instruction set, including:
after the first instruction set is completed, the execution combination of the single constant maintenance instruction included in the second instruction set is executed first, and then the rest execution combination is executed.
3. The voice interactive home control method according to claim 2, wherein obtaining a single constant hold instruction from the plurality of control instructions comprises:
and consulting the mutual exclusion rule base, and selecting a constant hold instruction with the least mutual exclusion number with other control instructions.
4. The voice interactive home control method according to claim 1 or 2, wherein the rule base further comprises a parallel rule base including a combination of control instructions and a combination weight table of corresponding weights that can be executed simultaneously;
executing the execution combination of the first instruction set in an execution combination unit, comprising:
and after the combination weight table is consulted and the execution sequence of the execution combination of the first instruction set is ordered according to the size of the weight, the execution combination is used as a unit to execute the execution combination of the first instruction set one by one according to the execution sequence.
5. The voice interactive home control method according to claim 4, wherein the weights of the combinations including the control instructions in the combination weight table are updated according to a preset function according to the number of times the user has once spoken the control instructions.
6. The voice interactive home control method of claim 4, wherein the user comprises a plurality of user roles, the parallel rule base comprises a combination weight table of different user roles, the voice interactive home control method further comprising:
acquiring a user role sending out a control instruction;
looking up a combined weight table corresponding to the user role according to the obtained user role,
and ordering the execution sequence of the execution combination of the first instruction set according to the combination weight table of the corresponding user role.
7. The voice interaction home control method according to claim 6, wherein weights of combinations including the control instructions in the combination weight table of different user roles are updated according to a preset function according to the number of times the different user roles have spoken the control instructions.
8. The voice interactive home control method according to claim 5 or 7, wherein the preset function comprises:
W x =W 1 +ln（x+1）
the W is x Weights representing combinations of control instructions having x times over which said control instructions occur, W 1 Representing the initial weights of the combinations with the control instructions.
9. Household control robot, its characterized in that includes:
the voice interaction module is used for obtaining legal multiple control instructions through voice interaction with a user, and comprises the following steps:
acquiring a plurality of control instructions through voice interaction;
checking whether the constant hold instructions in the plurality of control instructions are mutually exclusive according to a mutual exclusion rule base, and if not, determining that the constant hold instructions are legal;
the rule base comprises a mutually exclusive rule base, wherein the mutually exclusive rule base comprises a combination of control instructions which cannot be executed simultaneously;
the constant holding instruction acquisition module is used for acquiring a constant holding instruction from the plurality of control instructions, wherein the constant holding instruction is a control instruction with unlimited execution time;
the instruction set dividing module is used for dividing the plurality of control instructions according to the mutual exclusion rule base and the normal holding instructions to obtain a first instruction set and a second instruction set, wherein the first instruction set comprises all control instructions which are mutually exclusive with the normal holding instructions in the plurality of control instructions, and the second instruction set comprises all control instructions and normal holding instructions which are not mutually exclusive with the normal holding instructions in the plurality of control instructions;
the execution combination dividing module is used for dividing the first instruction set into one or more execution combinations according to the mutual exclusion rule base, and control instructions in the execution combinations are mutually exclusive;
the execution module is used for executing the execution combination of the first instruction set one by one and executing all control instructions in the second instruction set after the first instruction set is completed;
and the control module is used for controlling the corresponding household equipment according to the content of the control instruction when the control instruction is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210785096.1A CN115240668B (en) | 2022-07-06 | 2022-07-06 | Voice interaction home control method and robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210785096.1A CN115240668B (en) | 2022-07-06 | 2022-07-06 | Voice interaction home control method and robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115240668A CN115240668A (en) | 2022-10-25 |
| CN115240668B true CN115240668B (en) | 2023-06-02 |
Family
ID=83672462
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210785096.1A Active CN115240668B (en) | 2022-07-06 | 2022-07-06 | Voice interaction home control method and robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115240668B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110570855A (en) * | 2019-08-28 | 2019-12-13 | 珠海格力电器股份有限公司 | system, method and device for controlling intelligent household equipment through conversation mechanism |
| CN113076201A (en) * | 2020-01-03 | 2021-07-06 | 中国移动通信集团广东有限公司 | Mutual exclusion checking method for task instruction and electronic equipment |
| CN113990324A (en) * | 2021-11-24 | 2022-01-28 | 深圳市品索科技有限公司 | Voice intelligent home control system |
| CN114283799A (en) * | 2021-11-23 | 2022-04-05 | 阿里巴巴达摩院(杭州)科技有限公司 | Voice interaction method, device, equipment and storage medium |
Family Cites Families (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202363104U (en) * | 2011-11-29 | 2012-08-01 | 俞峰 | Voice control system for fuzzy control |
| KR102429260B1 (en) * | 2015-10-12 | 2022-08-05 | 삼성전자주식회사 | Apparatus and method for processing control command based on voice agent, agent apparatus |
| JP2018120203A (en) * | 2016-11-02 | 2018-08-02 | パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカＰａｎａｓｏｎｉｃ Ｉｎｔｅｌｌｅｃｔｕａｌ Ｐｒｏｐｅｒｔｙ Ｃｏｒｐｏｒａｔｉｏｎ ｏｆ Ａｍｅｒｉｃａ | Information processing method and program |
| CN107146616B (en) * | 2017-06-13 | 2020-05-08 | Oppo广东移动通信有限公司 | Equipment control method and related product |
| CN108711428B (en) * | 2018-05-30 | 2021-05-25 | Oppo广东移动通信有限公司 | Instruction execution method and device, storage medium and electronic equipment |
| CN109493865A (en) * | 2018-10-17 | 2019-03-19 | 北京车和家信息技术有限公司 | Signal processing method, terminal and vehicle |
| US10944588B2 (en) * | 2018-11-29 | 2021-03-09 | International Business Machines Corporation | Resolving conflicting commands received by an electronic device |
| CN110047486A (en) * | 2019-05-20 | 2019-07-23 | 合肥美的电冰箱有限公司 | Sound control method, device, server, system and storage medium |
| CN111128148B (en) * | 2019-11-18 | 2022-08-12 | 北京小米移动软件有限公司 | Voice ordering method, device, system and computer readable storage medium |
| CN111009245B (en) * | 2019-12-18 | 2021-09-14 | 腾讯科技（深圳）有限公司 | Instruction execution method, system and storage medium |
| CN113129878A (en) * | 2019-12-30 | 2021-07-16 | 富泰华工业（深圳）有限公司 | Voice control method and terminal device |
| CN111294258A (en) * | 2020-02-10 | 2020-06-16 | 成都捷顺宝信息科技有限公司 | Voice interaction system and method for controlling intelligent household equipment |
| CN114333812A (en) * | 2020-09-30 | 2022-04-12 | 青岛海尔洗衣机有限公司 | Voice interaction method and device, intelligent sound box and storage medium |
| CN113436631B (en) * | 2021-05-20 | 2023-01-13 | 青岛海尔空调器有限总公司 | Voice information processing method and system and device for voice information processing |
| CN114019817A (en) * | 2021-11-16 | 2022-02-08 | 青岛海尔科技有限公司 | Control method and control device of intelligent household equipment and Internet of things system |
-
2022
- 2022-07-06 CN CN202210785096.1A patent/CN115240668B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110570855A (en) * | 2019-08-28 | 2019-12-13 | 珠海格力电器股份有限公司 | system, method and device for controlling intelligent household equipment through conversation mechanism |
| CN113076201A (en) * | 2020-01-03 | 2021-07-06 | 中国移动通信集团广东有限公司 | Mutual exclusion checking method for task instruction and electronic equipment |
| CN114283799A (en) * | 2021-11-23 | 2022-04-05 | 阿里巴巴达摩院(杭州)科技有限公司 | Voice interaction method, device, equipment and storage medium |
| CN113990324A (en) * | 2021-11-24 | 2022-01-28 | 深圳市品索科技有限公司 | Voice intelligent home control system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115240668A (en) | 2022-10-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9472193B2 (en) | Speech dialogue control method | |
| US10950230B2 (en) | Information processing device and information processing method | |
| EP3343559B1 (en) | De-reverberation control method and device thereof | |
| US9396727B2 (en) | Systems and methods for spoken dialog service arbitration | |
| CN110347367B (en) | Volume adjusting method, terminal device, storage medium and electronic device | |
| JP2021516790A (en) | System and method of selective wake word detection using neural network model | |
| JP2019057273A (en) | Method and apparatus for pushing information | |
| EP3833036A1 (en) | Display apparatus, electronic device, interactive system, and controlling methods thereof | |
| US20180090152A1 (en) | Parameter prediction device and parameter prediction method for acoustic signal processing | |
| CN108536418A (en) | A kind of method, apparatus and wireless sound box of the switching of wireless sound box play mode | |
| CN109360558B (en) | Voice response method and device | |
| US20200265843A1 (en) | Speech broadcast method, device and terminal | |
| CN110347366B (en) | Volume adjusting method, terminal device, storage medium and electronic device | |
| CN110989968A (en) | Intelligent sound effect processing method, electronic equipment, storage medium and multi-sound effect sound box | |
| CN110738992B (en) | Voice information processing method and device, storage medium and electronic device | |
| CN110164425A (en) | A kind of noise-reduction method, device and the equipment that can realize noise reduction | |
| US11233490B2 (en) | Context based volume adaptation by voice assistant devices | |
| JP7117972B2 (en) | Speech recognition device, speech recognition method and speech recognition program | |
| CN115240668B (en) | Voice interaction home control method and robot | |
| CN114402383A (en) | Electronic device and method for controlling voice recognition thereof | |
| CN113793623B (en) | Sound effect setting method, device, equipment and computer readable storage medium | |
| CN112002340A (en) | Voice acquisition method and device based on multiple users | |
| JP7009092B2 (en) | Information processing equipment and information processing method | |
| CN110635976B (en) | Accompanying equipment control method, accompanying equipment control system and storage medium | |
| CN105282658A (en) | Control method, system and device for audio playing equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |