TWI675305B - Intelligent voice control management system and method thereof - Google Patents

Abstract

An intelligent voice control management method includes the steps of: obtaining voice control text recognition and semantic analysis to obtain control instructions after receiving a voice signal through voiceprint verification; obtaining a source position and a source direction of a voice signal according to a plurality of microphone units; Relative distance and relative position between a controlled device and the intelligent voice control management system; according to the relative distance and relative position between each controlled device and the intelligent voice control management system, the source location and direction of the voice signal, The control database and the control instructions screen out the controlled devices corresponding to the control instructions; and transmit the control instructions to the corresponding controlled devices to perform the corresponding operations. Therefore, the technical effect of performing voice control on the controlled devices in the area safely through voiceprint recognition can be achieved.

Description

Intelligent voice control management system and method

The invention relates to a management system and a method thereof, in particular to an intelligent voice control management system and a method thereof.

With the development of communication technology, many application technologies related to speech recognition have gradually become one of the indispensable items. Users can directly use language to communicate with electronic products, making the control interface of electronic devices easier to be accepted by users. .

However, currently some electronic devices on the market do not have a voice recognition function, which prevents users from having a good control experience. In addition, the conventional voice control technology only recognizes the speaker's voice content, so that anyone can use the voice to operate the corresponding electronic device. Therefore, it may cause young children to misuse high-risk electronic devices, and even strangers can use the electronic devices at will, which seriously affects the use safety of electronic devices or violates the rights of legal users of electronic devices.

The invention discloses an intelligent voice control management system and method.

First, the present invention discloses an intelligent voice control management system. The system includes a receiving module, a voiceprint recognition module, a semantic analysis module, a positioning module, and a processing module. Among them, the receiving module includes multiple microphone units for receiving voice signals; the voiceprint recognition module is used to obtain the voice characteristics from the voice signals, and the voice characteristics are verified according to the voiceprint database; the semantic analysis module is used for The control instruction is obtained by performing speech-to-text recognition and semantic analysis on the voice signal after the voice feature is verified by the voiceprint; the positioning module is used to determine the time difference between the voice signals received by the multiple microphone units and the relative positions of the microphone units. Obtaining the source position and direction of the voice signal, and obtaining the relative distance and relative position between each controlled device and the intelligent voice control management system according to the positioning signal and the position signal transmitted by each controlled device; and a processing module It is used to filter out the controlled devices corresponding to the control instruction according to the relative distance and relative position between each controlled device and the intelligent voice control management system, the source location and direction of the voice signal, the control database and the control instruction, and transmit The control instruction is given to the corresponding controlled device so that it performs the corresponding operation.

In addition, the present invention discloses an intelligent voice control management method, whose steps include: multiple microphone units receive voice signals; obtaining voice characteristics from the voice signals, and performing voiceprint verification on the voice characteristics according to the voiceprint database; when the voice characteristics pass the voice After voice verification, the speech signal is subjected to speech-to-text recognition and semantic analysis to obtain control instructions; the source position and direction of the speech signal are obtained based on the time difference between the speech signals received by multiple microphone units and the relative positions of the microphone units; The positioning signal and the position signal transmitted by each controlled device obtain the relative distance and relative position between each controlled device and the intelligent voice control management system; according to the relative distance between each controlled device and the intelligent voice control management system The distance and relative position, the source position and direction of the voice signal, the control database and the control instruction screen out the controlled device corresponding to the control instruction; and transmit the control instruction to the corresponding controlled device to perform the corresponding operation.

The system and method disclosed in the present invention are as described above. The difference from the prior art is that the present invention obtains control instructions through voice-to-text recognition and semantic analysis after the received voice signal is verified by voiceprint verification; the voice signals are obtained according to multiple microphone units. Source location and source direction; obtain the relative distance and relative position between each controlled device and the intelligent voice control management system; based on the relative distance and relative position between each controlled device and the intelligent voice control management system, The source location and direction of the voice signal, the control database and the control instruction screen out the controlled devices corresponding to the control instruction; and transmit the control instructions to the corresponding controlled device to perform the corresponding operation.

Through the above-mentioned technical means, the present invention can achieve the technical effect of safely controlling the voice of controlled devices in the area through voiceprint recognition.

Before describing the intelligent voice control management system and method disclosed in the present invention, the terms defined by the present invention are explained first. The voiceprint recognition module and semantic analysis module included in the intelligent voice control management system according to the present invention. Groups, positioning modules, processing modules, statistics modules, and learning modules can be implemented in various ways, including software, hardware, firmware, or any combination thereof. The software or firmware used in the proposed technology can be stored on machine-readable storage media, such as: read-only memory (ROM), random access memory (RAM), disk storage media, optical storage media, flash memory Flash memory devices, etc., and can be executed by one or more general-purpose or special-purpose programmable microprocessors. The intelligent voice control management system and the controlled device according to the present invention can communicate with each other through a network, such as: a mobile communication network, the Internet, a local area network, a wide area network, and / or a wireless network.

In the following, the embodiments of the present invention will be described in detail with reference to the drawings and examples, so as to fully understand and implement the implementation process of how the present invention applies technical means to solve technical problems and achieve technical effects.

Please refer to "Figure 1" first. "Figure 1" is a system block diagram of an embodiment of the intelligent voice control management system of the present invention. The intelligent voice control management system 100 includes a receiving module 101, a voiceprint recognition module 102, The semantic analysis module 103, the positioning module 104, and the processing module 105. The receiving module 101 is connected to the voiceprint identification module 102 and the semantic analysis module 103, the voiceprint identification module 102 is connected to the semantic analysis module 103, the semantic analysis module 103 is connected to the positioning module 104, and the positioning module 104 is connected to process Module 105.

In this embodiment, the receiving module 101 may include a plurality of microphone units 50 for receiving voice signals. The number of the microphone units 50 may be, but is not limited to, five, and the configuration positions of the microphone units 50 may be, but are not limited to, arranged on the casing of the management device to which the intelligent voice control management system 100 is applied. The embodiment is not intended to limit the present invention, and the number of microphone units 50 and their configuration positions can be adjusted according to actual needs. In addition, the distance between two adjacent microphone units 50 may be equal to improve the accuracy of the source location and source direction of subsequent voice signals, but this embodiment is not intended to limit the present invention. Furthermore, the radius of the circumference of the microphone units 50 arranged in a circle may be greater than eighty millimeters, so as to obtain the voice signal for identification of the source direction, but this embodiment is not intended to limit the present invention.

In this embodiment, the voiceprint recognition module 102 is configured to obtain voice characteristics from a voice signal, and perform voiceprint verification on the voice characteristics according to the voiceprint database 60. The voiceprint database 60 stores a plurality of preset voiceprint data, and each preset voiceprint data represents voiceprint data (ie, voice characteristics) of a user who can legally use the intelligent voice control management system 100. Because the vocal organs used by people are different, any two people have different voiceprint patterns. You can observe the voice characteristics of the speaker's pronunciation from the voiceprint pattern and use these voice characteristics to identify the speaker. , So in general, the sound of different people can be distinguished through sound characteristics. In this embodiment, the voiceprint recognition module 102 converts the voice signal into a voiceprint map after receiving the voice signal, and then obtains the voice characteristics from the voiceprint map, and then compares the acquired voice characteristics one by one to the voiceprint database 60. For each preset voiceprint data (that is, to perform voiceprint verification), when it is determined that the acquired voice characteristics match one of the preset voiceprint data, it means that the acquired voice characteristics pass voiceprint verification; When the sound feature does not match one of the preset voiceprint data, the obtained voice feature cannot be verified by the voiceprint.

In addition, the voiceprint database 60 can also store multiple identity data, which correspond to the preset voiceprint data in a one-to-one manner. Wherein, each identity data represents identification data of a user who can legally use the intelligent voice control management system 100, and may be, but not limited to, an identity card number, and may be adjusted according to actual needs. When the voiceprint recognition module 102 determines that the acquired voice characteristics match one of the preset voiceprint data, the identity of the speaker can be known.

In this embodiment, the semantic analysis module 103 is configured to obtain a control instruction by performing speech-to-text recognition and semantic analysis on a speech signal after a voice feature is verified by a voiceprint. In more detail, the semantic analysis module 103 may include an acoustic model unit (not drawn) and a semantic analysis unit (not drawn). After the sound features are verified by the voiceprint, the acoustic model unit may be passed through a hidden Markov model (Hidden Markov Model). , HMM), Neural Networks, Dynamic Time Warping (DTW), or Template Matching to perform speech recognition. When the acoustic model unit uses the acoustic model comparison method for speech recognition, multiple acoustic features can be extracted from the speech signal (that is, the Linear Predictive Cepstral Coefficient (LPCC) corresponding to the speech signal, Parameters such as Mel Frequency Cepstral Coefficient (MFCC), MPEG7, and Log Energy, and then compare these acoustic characteristics with one of the above acoustic models to find the most acoustic characteristics Matching corresponding vocabulary. For example, when the voice signal is "turn on the TV", the corresponding vocabulary obtained through the analysis of the acoustic model unit can be "" on "," television ".

Then, the semantic analysis unit may query the category corresponding to the vocabulary in the semantic database 70 to obtain a control instruction. The control instruction may include an operation command and an object name. Specifically, the category can be a behavior (corresponding to an operation command) or an object (corresponding to an object name). More specifically, the semantic database 70 may record the relationship between the vocabulary and the corresponding category (as shown in "Figure 2", "Figure 2" is the semantic database of the intelligent voice control management system of "Figure 1" An example comparison table of the recorded vocabulary and category), each vocabulary corresponds to a category. Since a complete control instruction can include a behavior category (that is, the operation that the speaker wants to perform) and an object category (that is, the target that the speaker wants to operate), the semantic analysis unit needs to query the acoustic model unit analysis from the semantic database 70 Whether the vocabulary obtained by the voice signal corresponds to at least a behavior category and an object category, and then confirm whether a complete control instruction has been collected. The control instruction may have a specific format, which may include an object name and an operation command ( As shown in "Figure 3A", "Figure 3A" is an example format of control instructions in the intelligent voice control management system of "Figure 1." In practice, the ordering of object names and operation commands can be based on The actual needs are adjusted. The object name is used to indicate the object to be operated, and the operation command is used to indicate the operation that the speaker wants to perform on the object. For example, when the corresponding vocabulary obtained by the acoustic model unit analyzing the speech signal is "" on "," television "", the semantic analysis unit can obtain the query "on" and the corresponding category is "behavior" according to the semantic database 70 The category corresponding to "TV" is "Object", so the content of the control instruction may be as shown in "Figure 3B", and "Figure 3B" is one of the control instructions in the intelligent voice control management system of "Figure 1." In the content of the embodiment, "Figure 3B" indicates that the speaker wants to "open" the object, and the name of the object is "television".

It should be noted that the vocabulary obtained from the analysis of the acoustic model unit may not be able to query the corresponding category from the semantic database 70 (that is, it indicates that the vocabulary cannot identify its category), but the correspondence table between the vocabulary and category recorded in the semantic database 70 It can be updated at any time according to requirements. The vocabulary in the comparison table needs to include the name of each controlled device that can be controlled by voice through the intelligent voice control management system 100 and the category corresponding to the names of the controlled devices is "object ", Operation commands can be deleted according to user needs and the category corresponding to these operation commands is" behavior ". In addition, when the semantic analysis module 102 confirms that the categories corresponding to the vocabularies lack behavior categories or object categories, or confirms that the vocabularies correspond to multiple behavior categories or multiple object categories, it is judged that a complete control instruction cannot be collected, and cannot Get control instructions.

In this embodiment, the positioning module 104 may be configured to obtain a source position and a source direction of a voice signal according to a time difference between the microphone units receiving the voice signals and a relative configuration position of the microphone units. It should be noted that the accuracy of the location and direction of the voice signal obtained by the positioning module 104 has a positive correlation with the arrangement density and quantity of the microphone units 50. In other words, when the arrangement density and quantity of the microphone units 50 are more dense The more the positioning module 104 obtains the accuracy of the source position and source direction of the voice signal, the higher the accuracy.

In addition, the positioning module 104 can obtain the relative distance and relative position between each controlled device and the intelligent voice control management system according to the positioning signal and the position signal transmitted by each controlled device. The positioning signal may be, but is not limited to, a positioning signal provided by the Global Positioning System (GPS) positioning intelligent voice control management system 100, and the positioning signal may include an identification code of the intelligent voice control management system 100 or the Internet. Internet Protocol Address; the position signal transmitted by each controlled device can be, but is not limited to, the position signal provided by each controlled device through GPS positioning, and the position signal can include the identification code of the controlled device or IP address. Therefore, the positioning module 104 can obtain each target based on the location of the intelligent voice control management system 100 (that is, the corresponding positioning signal) and the location of each controlled device (that is, the corresponding position signal transmitted by each controlled device). The relative distance and relative position between the control device and the intelligent voice control management system.

In this embodiment, the processing module 105 can be used to determine the relative distance and relative position between each controlled device and the intelligent voice control management system 100, the source position and direction of the voice signal, the control database 90 and the control instruction. The controlled devices corresponding to the control instructions are screened out, and the control instructions are transmitted to the corresponding controlled devices to perform the corresponding operations. Among them, the control database 90 may include the name and address of each controlled device and its corresponding operation (as shown in "Figure 4", "Figure 4" is the intelligent voice control management system of "Figure 1" A schematic diagram of an embodiment of the content recorded in the control database), the name of each controlled device (ie, the object name) can correspond to multiple operations (that is, corresponding to multiple operation commands), and the address of each controlled device can be But it is not limited to the IP address. Although the names of the controlled devices may be the same, different controlled devices can be distinguished by the IP address.

In more detail, the processing module 105 can find the controlled device corresponding to the control instruction from the control database 90 according to the control instruction (which includes the operation command and the object name). When the number of control devices is one, the processing module 105 transmits the control instruction to the controlled device through the address of the controlled device in the control database 90, so that it performs corresponding operations; when the processing module 105 screens out the corresponding control When the number of instructed controlled devices is multiple, the processing module 105 can further judge the user based on the relative distance and relative position between each controlled device and the intelligent voice control management system 100, and the source position and direction of the voice signal. The controlled device most likely to be controlled. Since the affected range of the corresponding operation performed by the controlled device should be related to the location of the user (that is, the source location and direction of the voice signal), the processing module 105 can further control each of the controlled devices and the intelligent voice control management system 100 The relative distance and relative position and the source position and direction of the voice signal (ie, the relative distance and relative orientation between the speaker and the intelligent voice control management system 100) screen out the best controlled device corresponding to the control instruction, The basis for screening may be, but is not limited to, the relative distance and / or the relative orientation between the speaker and the controlled device is the smallest or the closest (can be determined by the relative distance between the controlled device and the intelligent voice control management system 100 and The relative position and the source position and direction of the voice signal are calculated). The actual screening mechanism can be adjusted according to actual needs. Therefore, the present invention can achieve the technical effect of safely controlling the voice of controlled devices in the area through voiceprint recognition.

Because the controlled device selected by the processing module 105 according to the above method (using the minimum or closest relative distance and / or relative orientation between the speaker and the controlled device) may not be the subject of the speaker's real item for voice control Therefore, the user can cause the intelligent voice control management system 100 to make corrections and adjustments by re-entering the same voice signal. In more detail, when a controlled device performs a corresponding operation according to a control instruction transmitted by the processing module 105 for a predetermined time (that is, after a wrong controlled device executes a control command for a predetermined time), the processing module 105 receives again To the same control instruction (that is, the user can input the same voice signal again) and judge the relative distance and relative position between each controlled device and the intelligent voice control management system 100, and the source position and direction of the voice signal. Time-varying (that is, the relative distance and / or relative orientation between the speaker and the controlled device remains the same), the processing module 105 can select another controlled device according to the control database 90, and transmit a control instruction to the other controlled device The controlled device causes it to perform the corresponding operation and transmits a stop instruction to the controlled device that originally executed the control instruction (ie, the wrong controlled device) to stop the corresponding operation. The processing module 105 may select another controlled device according to the control database 90. The method may be, but is not limited to, the relative distance and / or the relative orientation between the speaker and the controlled device is the second smallest or the second. Approach, the actual screening mechanism can be adjusted according to actual needs.

In addition, in order to allow the processing module 105 to more accurately screen out the controlled devices that the speaker wants to perform voice control, the intelligent voice control management system 100 may further include a statistics module 106 for counting the control of each controlled device. The number of times the instruction performs the corresponding operation provides a further basis for the processing module 105 to screen out the controlled device corresponding to the control instruction. In other words, the speaker's habits of voice control can be understood through the statistics module 106, so that the processing module 105 performs screening of controlled devices in addition to the relative distance and / or relative position between the speaker and the controlled device. , You can also refer to the speaker's habits of voice control. Among them, the statistics module 106 needs to perform statistics on the voice control habits of different speakers (the identity of different speakers can be obtained by means of voiceprint recognition for subsequent voice control statistics), and the processing module 105 can refer to two references Based on (the relative distance and / or relative position between the speaker and the controlled device, the speaker's voice control habits), a weighted calculation method is used to evaluate the screening of the controlled device, and then the most appropriate control instruction is selected. Best controlled device. For example, the relative distance and / or relative position between the speaker and the controlled device, the speaker's voice control habits, and the corresponding controlled device may be ranked separately. The calculation is performed in a weighted manner to screen out the best controlled device corresponding to the control instruction.

Furthermore, the intelligent voice control management system 100 of this embodiment may further include a learning module 107 for counting the time when each controlled device performs a corresponding operation according to its corresponding control instruction, and in the same control instruction in the same When the time point or time period repeatedly occurs over a preset number of times, the corresponding controlled device is automatically caused to repeatedly execute the control instruction at the time point or time period. Therefore, the learning module 107 can be used to understand the speaker's habits of voice control (the same control instruction repeatedly occurs at the same time point or time period over a preset number of times), and automatically generates and transmits the same at that time point or time period. The control instruction is given to the corresponding controlled device, so that the corresponding controlled device repeatedly executes the control instruction. For example, when a speaker often controls a TV to be turned on at 5 pm through the intelligent voice control management system 100 and the number of times exceeds five times (that is, more than a preset number of times), the intelligent voice control management system 100 can use a learning module 107 automatically generates and transmits the control instruction to the TV at 5 pm to turn it on.

Next, please refer to "Figure 5". "Figure 5" is a method flowchart of one embodiment of the intelligent voice control management method performed by the intelligent voice control management system of "Figure 1." The steps include: multiple microphone units receive A voice signal (step 210); obtaining a voice feature from the voice signal, and performing voiceprint verification on the voice feature according to the voiceprint database (step 220); performing voice-to-text recognition on the voice signal after the voice feature passes the voiceprint verification and Obtain a control instruction by semantic analysis (step 230); obtain the source position and direction of the voice signal according to the time difference between the time when the microphone units receive the voice signal and the relative position of the microphone units (step 240); according to the positioning signal and each The position signal transmitted by a controlled device obtains the relative distance and relative position between each controlled device and the intelligent voice control management system (step 250); according to the relative distance between each controlled device and the intelligent voice control management system Distance and relative position, source position and direction of voice signal, control database and control finger Selected controlled device (step 260) corresponding to a control command; transmission control instruction corresponding to the controlled device to execute a corresponding operation (step 270). The control database may include the name and address of each controlled device and the corresponding operations.

Through the above steps, voice control can be used to safely control the controlled devices within the area (selection of controlled devices based on the relative distance and / or relative orientation between the speaker and the controlled device) through voice recognition. The detailed description has been described in the above paragraphs, and will not be repeated here.

In this embodiment, the intelligent voice control management method may further include: counting the number of times each controlled device performs a corresponding operation according to the control instruction, and providing a further basis for the processing module to screen out the controlled device corresponding to the control instruction (not draw). The detailed description has been described in the above paragraphs, and will not be repeated here.

In addition, in this embodiment, the intelligent voice control management method may further include: when a controlled device performs a corresponding operation according to a control instruction transmitted by the processing module for a predetermined time, the processing module receives the same control instruction again When determining the relative distance and relative position between each controlled device and the intelligent voice control management system and the source location and direction of the voice signal, the processing module selects another controlled device based on the control database ( (Not drawn); transmitting the control instruction to the other controlled device to perform the corresponding operation (not drawn); and transmitting a stop instruction to the controlled device that originally executed the control instruction to stop the corresponding operation (not drawn) . The detailed description has been described in the above paragraphs, and will not be repeated here.

Furthermore, in this embodiment, the intelligent voice control management method may also include: counting the time when each controlled device performs a corresponding operation according to its corresponding control instruction (not drawn); and the same control instruction at the same time When the point or time period repeatedly occurs more than a preset number of times, the control instruction is automatically generated and transmitted to the corresponding controlled device at the time point or time period, so that the corresponding controlled device repeatedly executes the control instruction (not draw). The detailed description has been described in the above paragraphs, and will not be repeated here.

It should be particularly noted that, in addition to explaining the causal relationship in the above intelligent voice control management method, the above steps may be performed in any order.

In summary, it can be seen that the difference between the present invention and the prior art is that the control instruction is obtained through speech-to-text recognition and semantic analysis after the received voice signal is verified by voiceprint verification; the source position of the voice signal is obtained according to multiple microphone units And source direction; obtain the relative distance and relative position between each controlled device and the intelligent voice control management system; according to the relative distance and relative position between each controlled device and the intelligent voice control management system, the The source location and source direction, the control database and the control instruction screen out the controlled devices corresponding to the control instruction; and transmit the control instruction to the corresponding controlled device to perform the corresponding operation, by which a technical means can solve the problem of the previous technology The existing problems further achieve the technical effect of voice control of controlled devices in the area safely through voiceprint recognition.

Although the present invention is disclosed in the foregoing embodiments as above, it is not intended to limit the present invention. Any person skilled in similar arts can make some modifications and retouches without departing from the spirit and scope of the present invention. The scope of patent protection shall be determined by the scope of the patent application attached to this specification.

50‧‧‧ microphone unit

60‧‧‧ Voiceprint Database

70‧‧‧ Semantic Database

90‧‧‧Control database

100‧‧‧ Intelligent Voice Control Management System

101‧‧‧Receiving module

102‧‧‧Voiceprint recognition module

103‧‧‧Semantic parsing module

104‧‧‧Positioning module

105‧‧‧Processing Module

106‧‧‧ Statistics Module

107‧‧‧Learning Module

Step 210‧‧‧ multiple microphone units receive a voice signal

Step 220‧‧‧ Obtain a voice feature from the voice signal, and perform voiceprint verification on the voice feature according to the voiceprint database

Step 230‧‧‧ After voice features are verified by voiceprint, voice-to-text recognition and semantic analysis are performed on the voice signal to obtain control instructions

Step 240‧‧‧ Obtain the source position and source direction of the voice signal according to the time difference between the microphone units receiving the voice signals and the relative position of the microphone units

Step 250‧‧‧ Obtain the relative distance and relative position between each controlled device and the intelligent voice control management system according to the positioning signal and the position signal transmitted by each controlled device

Step 260‧‧‧ Screen out the controlled device corresponding to the control instruction according to the relative distance and relative position between each controlled device and the intelligent voice control management system, the source position and direction of the voice signal, the control database and the control instruction

Step 270‧‧‧ transmits a control instruction to the corresponding controlled device, so that it performs the corresponding operation

FIG. 1 is a system block diagram of an embodiment of an intelligent voice control management system according to the present invention. FIG. 2 is a comparison table of the embodiment of the vocabulary and category recorded in the semantic database of the intelligent voice control management system of FIG. 1. FIG. 3A is a format of an embodiment of a control instruction in the intelligent voice control management system of FIG. 1. FIG. 3B is an embodiment of the control instructions in the intelligent voice control management system of FIG. 1. FIG. 4 is a schematic diagram of an embodiment of the content recorded in the control database of the intelligent voice control management system of FIG. 1. FIG. 5 is a method flowchart of an embodiment of the intelligent voice control management system performed by the intelligent voice control management system of FIG. 1.

Claims (8)

An intelligent voice control management system includes: a receiving module including a plurality of microphone units for receiving a voice signal; a voiceprint recognition module for obtaining a voice feature from the voice signal, and based on a voice The texture database performs voiceprint verification on the sound feature; a semantic analysis module is used to obtain a control instruction for speech-to-text recognition and semantic analysis of the voice signal after the voice feature is verified by the voiceprint verification; a positioning mode A group for obtaining the source position and source direction of the voice signal according to the time difference between the time when the microphone units received the voice signal and the relative position of the microphone units, and according to a positioning signal and each of the controlled devices. A position signal obtains a relative distance and a relative position between each of the controlled devices and the intelligent voice control management system; and a processing module, which is based on each of the controlled devices and the intelligent voice control management system The relative distance and the relative position, the source position of the voice signal and the source direction, a control database and The control instruction screens out the controlled device corresponding to the control instruction, and transmits the control instruction to the corresponding controlled device to cause the corresponding operation to be performed; wherein, when a certain controlled device according to the transmission of the processing module After the control instruction performs the corresponding operation for a predetermined time, the processing module receives the same control instruction again and judges the relative distance and relative position between each controlled device and the intelligent voice control management system and the voice When the source position and direction of the signal are not changed, the processing module selects another controlled device according to the control database, and transmits the control instruction to the other controlled device, so that it performs corresponding operations and transfers. A stop instruction is input to the controlled device that originally executed the control instruction to stop the corresponding operation. The intelligent voice control management system according to item 1 of the scope of patent application, wherein the intelligent voice control management system further includes a statistical module for counting the number of times each controlled device performs a corresponding operation according to the control instruction, which is the The processing module screens out the controlled device corresponding to the control instruction to provide further basis. According to the intelligent voice control management system of the first patent application scope, wherein the control database includes the name, address and corresponding operations of each controlled device. The intelligent voice control management system according to item 1 of the scope of patent application, wherein the intelligent voice control management system further includes a learning module for counting the occurrence of a corresponding operation performed by each controlled device according to its corresponding control instruction Time, and when the same control instruction repeatedly occurs at the same time point or time period for more than a preset number of times, the control instruction is automatically generated and transmitted to the corresponding controlled device at the time point or time period, so that the corresponding The controlled device repeatedly executes the control instruction. A method for intelligent voice control management includes the steps of: receiving a voice signal by a plurality of microphone units; obtaining a voice feature from the voice signal, and performing voiceprint verification on the voice feature according to a voiceprint database; when the voice feature passes After voiceprint verification, the voice signal is subjected to speech-to-text recognition and semantic analysis to obtain a control instruction; the source position of the voice signal is obtained according to the time difference between the time when the microphone units receive the voice signal and the relative position of the microphone units. And source direction Obtain the relative distance and relative position between each controlled device and the intelligent voice control management system according to a positioning signal and a position signal transmitted by each controlled device; according to each controlled device and the intelligent voice The relative distance and the relative position between the control management system, the source position and the source direction of the voice signal, a control database and the control instruction screen out the controlled device corresponding to the control instruction; transmit the control instruction The corresponding controlled device to perform the corresponding operation; when a certain controlled device performs the corresponding operation according to the control instruction transmitted by the processing module for a predetermined time, the processing module receives the same When controlling the command and determining that the relative distance and relative position between each controlled device and the intelligent voice control management system and the source position and source direction of the voice signal are unchanged, the processing module is based on the control database Screening out another controlled device; transmitting the control instruction to the other controlled device to perform a corresponding operation; and transmitting a stop The controlled device so that I originally executing the control instruction corresponding to the operation to stop. The intelligent voice control management method according to item 5 of the scope of patent application, wherein the intelligent voice control management method further comprises: counting the number of times each controlled device performs a corresponding operation according to the control instruction, and screening out pairs for the processing module. The controlled device that should control the instructions provides further evidence. The method for intelligent voice control management according to item 5 of the scope of patent application, wherein the control database includes the name, address and corresponding operations of each controlled device. The intelligent voice control management method according to item 5 of the scope of patent application, wherein the intelligent voice control management method further includes: counting the time when each controlled device performs a corresponding operation according to its corresponding control instruction; and in the same control When the instruction repeatedly occurs at the same time point or time period for more than a preset number of times, the control instruction is automatically generated and transmitted to the corresponding controlled device at the time point or time period, so that the corresponding controlled device is repeatedly executed. The control instruction.